lnp_ml/models/pretrain/mpnn/pretrain.log

58 lines
486 KiB
Plaintext
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

nohup: ignoring input
2026-08-07 06:43:53.431 | INFO | lnp_ml.config:<module>:11 - PROJ_ROOT path is: /home/gongruyi/lnp_ml
2026-08-07 06:43:53.749 | INFO  | __main__:main:273 - Using device: cuda | seed: 42
2026-08-07 06:43:53.749 | INFO  | __main__:main:277 - Loading train data from /home/gongruyi/lnp_ml/data/processed/train_pretrain.parquet
2026-08-07 06:43:54.598 | INFO  | __main__:main:281 - Loading val data from /home/gongruyi/lnp_ml/data/processed/val_pretrain.parquet
2026-08-07 06:43:54.622 | INFO  | __main__:main:285 - Train samples: 8236, Val samples: 1454
2026-08-07 06:43:54.623 | INFO  | __main__:main:301 - Auto-detecting MPNN ensemble from /home/gongruyi/lnp_ml/models/mpnn/all_amine_split_for_LiON
2026-08-07 06:43:54.624 | INFO  | __main__:main:303 - Found 5 MPNN models
2026-08-07 06:43:54.624 | INFO  | __main__:main:308 - Creating model (use_mpnn=True, use_moe=False, use_llm=False)...
2026-08-07 06:43:54.661 | INFO  | __main__:main:346 - Model parameters: 3,961,386 total, 3,961,386 trainable
2026-08-07 06:43:54.663 | INFO  | __main__:warmup_cache:64 - Warming up RDKit cache for 7493 unique SMILES...
Cache warmup: 0%| | 0/30 [00:00<?, ?it/s]
Cache warmup: 3%|▎ | 1/30 [00:11<05:42, 11.82s/it]
Cache warmup: 7%|▋ | 2/30 [00:21<04:56, 10.58s/it]
Cache warmup: 10%|█ | 3/30 [00:32<04:54, 10.90s/it]
Cache warmup: 13%|█▎ | 4/30 [00:43<04:43, 10.90s/it]
Cache warmup: 17%|█▋ | 5/30 [00:54<04:28, 10.73s/it]
Cache warmup: 20%|██ | 6/30 [01:05<04:21, 10.88s/it]
Cache warmup: 23%|██▎ | 7/30 [01:15<04:03, 10.57s/it]
Cache warmup: 27%|██▋ | 8/30 [01:27<04:01, 10.98s/it]
Cache warmup: 30%|███ | 9/30 [01:36<03:43, 10.63s/it]
Cache warmup: 33%|███▎ | 10/30 [01:47<03:32, 10.64s/it]
Cache warmup: 37%|███▋ | 11/30 [01:58<03:20, 10.57s/it]
Cache warmup: 40%|████ | 12/30 [02:08<03:09, 10.55s/it]
Cache warmup: 43%|████▎ | 13/30 [02:19<03:01, 10.70s/it]
Cache warmup: 47%|████▋ | 14/30 [02:30<02:49, 10.62s/it]
Cache warmup: 50%|█████ | 15/30 [02:40<02:39, 10.64s/it]
Cache warmup: 53%|█████▎ | 16/30 [02:52<02:33, 10.99s/it]
Cache warmup: 57%|█████▋ | 17/30 [03:03<02:21, 10.86s/it]
Cache warmup: 60%|██████ | 18/30 [03:14<02:13, 11.11s/it]
Cache warmup: 63%|██████▎ | 19/30 [03:25<02:00, 10.92s/it]
Cache warmup: 67%|██████▋ | 20/30 [03:35<01:48, 10.80s/it]
Cache warmup: 70%|███████ | 21/30 [03:46<01:37, 10.88s/it]
Cache warmup: 73%|███████▎ | 22/30 [03:57<01:26, 10.82s/it]
Cache warmup: 77%|███████▋ | 23/30 [04:07<01:14, 10.62s/it]
Cache warmup: 80%|████████ | 24/30 [04:17<01:02, 10.37s/it]
Cache warmup: 83%|████████▎ | 25/30 [04:28<00:52, 10.43s/it]
Cache warmup: 87%|████████▋ | 26/30 [04:39<00:42, 10.63s/it]
Cache warmup: 90%|█████████ | 27/30 [04:48<00:30, 10.33s/it]
Cache warmup: 93%|█████████▎| 28/30 [04:59<00:21, 10.56s/it]
Cache warmup: 97%|█████████▋| 29/30 [05:10<00:10, 10.54s/it]
Cache warmup: 100%|██████████| 30/30 [05:13<00:00, 8.19s/it]
Cache warmup: 100%|██████████| 30/30 [05:13<00:00, 10.44s/it]
2026-08-07 06:49:07.718 | SUCCESS  | __main__:warmup_cache:70 - Cache warmup complete. Cached 7493 SMILES.
2026-08-07 06:49:07.718 | INFO  | __main__:main:353 - Starting pretraining on external data (delivery only)...
Epoch 1 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 1 [Train]: 0%| | 0/129 [00:01<?, ?it/s, loss=0.993]
Epoch 1 [Train]: 1%| | 1/129 [00:01<03:07, 1.47s/it, loss=0.993]
Epoch 1 [Train]: 1%| | 1/129 [00:02<03:07, 1.47s/it, loss=0.963]
Epoch 1 [Train]: 2%|▏ | 2/129 [00:02<02:01, 1.05it/s, loss=0.963]
Epoch 1 [Train]: 2%|▏ | 2/129 [00:02<02:01, 1.05it/s, loss=1.04]
Epoch 1 [Train]: 2%|▏ | 3/129 [00:02<01:30, 1.40it/s, loss=1.04]
Epoch 1 [Train]: 2%|▏ | 3/129 [00:02<01:30, 1.40it/s, loss=1.03]
Epoch 1 [Train]: 3%|▎ | 4/129 [00:02<01:15, 1.66it/s, loss=1.03]
Epoch 1 [Train]: 3%|▎ | 4/129 [00:03<01:15, 1.66it/s, loss=1.03]
Epoch 1 [Train]: 4%|▍ | 5/129 [00:03<01:06, 1.85it/s, loss=1.03]
Epoch 1 [Train]: 4%|▍ | 5/129 [00:03<01:06, 1.85it/s, loss=1.06]
Epoch 1 [Train]: 5%|▍ | 6/129 [00:03<01:08, 1.80it/s, loss=1.06]
Epoch 1 [Train]: 5%|▍ | 6/129 [00:04<01:08, 1.80it/s, loss=1.02]
Epoch 1 [Train]: 5%|▌ | 7/129 [00:04<01:01, 1.97it/s, loss=1.02]
Epoch 1 [Train]: 5%|▌ | 7/129 [00:04<01:01, 1.97it/s, loss=0.964]
Epoch 1 [Train]: 6%|▌ | 8/129 [00:04<00:56, 2.12it/s, loss=0.964]
Epoch 1 [Train]: 6%|▌ | 8/129 [00:05<00:56, 2.12it/s, loss=0.953]
Epoch 1 [Train]: 7%|▋ | 9/129 [00:05<00:54, 2.20it/s, loss=0.953]
Epoch 1 [Train]: 7%|▋ | 9/129 [00:05<00:54, 2.20it/s, loss=0.99]
Epoch 1 [Train]: 8%|▊ | 10/129 [00:05<00:53, 2.23it/s, loss=0.99]
Epoch 1 [Train]: 8%|▊ | 10/129 [00:06<00:53, 2.23it/s, loss=0.961]
Epoch 1 [Train]: 9%|▊ | 11/129 [00:06<00:53, 2.20it/s, loss=0.961]
Epoch 1 [Train]: 9%|▊ | 11/129 [00:06<00:53, 2.20it/s, loss=0.963]
Epoch 1 [Train]: 9%|▉ | 12/129 [00:06<00:50, 2.33it/s, loss=0.963]
Epoch 1 [Train]: 9%|▉ | 12/129 [00:06<00:50, 2.33it/s, loss=0.947]
Epoch 1 [Train]: 10%|█ | 13/129 [00:06<00:45, 2.54it/s, loss=0.947]
Epoch 1 [Train]: 10%|█ | 13/129 [00:07<00:45, 2.54it/s, loss=0.956]
Epoch 1 [Train]: 11%|█ | 14/129 [00:07<00:43, 2.62it/s, loss=0.956]
Epoch 1 [Train]: 11%|█ | 14/129 [00:07<00:43, 2.62it/s, loss=0.973]
Epoch 1 [Train]: 12%|█▏ | 15/129 [00:07<00:42, 2.69it/s, loss=0.973]
Epoch 1 [Train]: 12%|█▏ | 15/129 [00:07<00:42, 2.69it/s, loss=0.973]
Epoch 1 [Train]: 12%|█▏ | 16/129 [00:07<00:41, 2.70it/s, loss=0.973]
Epoch 1 [Train]: 12%|█▏ | 16/129 [00:08<00:41, 2.70it/s, loss=0.984]
Epoch 1 [Train]: 13%|█▎ | 17/129 [00:08<00:47, 2.35it/s, loss=0.984]
Epoch 1 [Train]: 13%|█▎ | 17/129 [00:08<00:47, 2.35it/s, loss=0.981]
Epoch 1 [Train]: 14%|█▍ | 18/129 [00:08<00:44, 2.47it/s, loss=0.981]
Epoch 1 [Train]: 14%|█▍ | 18/129 [00:09<00:44, 2.47it/s, loss=0.996]
Epoch 1 [Train]: 15%|█▍ | 19/129 [00:09<00:43, 2.56it/s, loss=0.996]
Epoch 1 [Train]: 15%|█▍ | 19/129 [00:09<00:43, 2.56it/s, loss=0.976]
Epoch 1 [Train]: 16%|█▌ | 20/129 [00:09<00:41, 2.61it/s, loss=0.976]
Epoch 1 [Train]: 16%|█▌ | 20/129 [00:09<00:41, 2.61it/s, loss=0.997]
Epoch 1 [Train]: 16%|█▋ | 21/129 [00:09<00:40, 2.65it/s, loss=0.997]
Epoch 1 [Train]: 16%|█▋ | 21/129 [00:10<00:40, 2.65it/s, loss=0.982]
Epoch 1 [Train]: 17%|█▋ | 22/129 [00:10<00:37, 2.83it/s, loss=0.982]
Epoch 1 [Train]: 17%|█▋ | 22/129 [00:10<00:37, 2.83it/s, loss=0.99]
Epoch 1 [Train]: 18%|█▊ | 23/129 [00:10<00:41, 2.55it/s, loss=0.99]
Epoch 1 [Train]: 18%|█▊ | 23/129 [00:10<00:41, 2.55it/s, loss=1.01]
Epoch 1 [Train]: 19%|█▊ | 24/129 [00:10<00:39, 2.68it/s, loss=1.01]
Epoch 1 [Train]: 19%|█▊ | 24/129 [00:11<00:39, 2.68it/s, loss=0.989]
Epoch 1 [Train]: 19%|█▉ | 25/129 [00:11<00:37, 2.79it/s, loss=0.989]
Epoch 1 [Train]: 19%|█▉ | 25/129 [00:11<00:37, 2.79it/s, loss=0.987]
Epoch 1 [Train]: 20%|██ | 26/129 [00:11<00:36, 2.85it/s, loss=0.987]
Epoch 1 [Train]: 20%|██ | 26/129 [00:11<00:36, 2.85it/s, loss=0.981]
Epoch 1 [Train]: 21%|██ | 27/129 [00:11<00:35, 2.90it/s, loss=0.981]
Epoch 1 [Train]: 21%|██ | 27/129 [00:12<00:35, 2.90it/s, loss=0.981]
Epoch 1 [Train]: 22%|██▏ | 28/129 [00:12<00:34, 2.91it/s, loss=0.981]
Epoch 1 [Train]: 22%|██▏ | 28/129 [00:12<00:34, 2.91it/s, loss=0.978]
Epoch 1 [Train]: 22%|██▏ | 29/129 [00:12<00:35, 2.80it/s, loss=0.978]
Epoch 1 [Train]: 22%|██▏ | 29/129 [00:13<00:35, 2.80it/s, loss=0.979]
Epoch 1 [Train]: 23%|██▎ | 30/129 [00:13<00:39, 2.51it/s, loss=0.979]
Epoch 1 [Train]: 23%|██▎ | 30/129 [00:13<00:39, 2.51it/s, loss=0.975]
Epoch 1 [Train]: 24%|██▍ | 31/129 [00:13<00:37, 2.59it/s, loss=0.975]
Epoch 1 [Train]: 24%|██▍ | 31/129 [00:13<00:37, 2.59it/s, loss=0.967]
Epoch 1 [Train]: 25%|██▍ | 32/129 [00:13<00:35, 2.71it/s, loss=0.967]
Epoch 1 [Train]: 25%|██▍ | 32/129 [00:14<00:35, 2.71it/s, loss=0.959]
Epoch 1 [Train]: 26%|██▌ | 33/129 [00:14<00:33, 2.84it/s, loss=0.959]
Epoch 1 [Train]: 26%|██▌ | 33/129 [00:14<00:33, 2.84it/s, loss=0.954]
Epoch 1 [Train]: 26%|██▋ | 34/129 [00:14<00:33, 2.82it/s, loss=0.954]
Epoch 1 [Train]: 26%|██▋ | 34/129 [00:14<00:33, 2.82it/s, loss=0.956]
Epoch 1 [Train]: 27%|██▋ | 35/129 [00:14<00:32, 2.88it/s, loss=0.956]
Epoch 1 [Train]: 27%|██▋ | 35/129 [00:15<00:32, 2.88it/s, loss=0.948]
Epoch 1 [Train]: 28%|██▊ | 36/129 [00:15<00:35, 2.59it/s, loss=0.948]
Epoch 1 [Train]: 28%|██▊ | 36/129 [00:15<00:35, 2.59it/s, loss=0.936]
Epoch 1 [Train]: 29%|██▊ | 37/129 [00:15<00:34, 2.64it/s, loss=0.936]
Epoch 1 [Train]: 29%|██▊ | 37/129 [00:15<00:34, 2.64it/s, loss=0.934]
Epoch 1 [Train]: 29%|██▉ | 38/129 [00:15<00:32, 2.84it/s, loss=0.934]
Epoch 1 [Train]: 29%|██▉ | 38/129 [00:16<00:32, 2.84it/s, loss=0.93]
Epoch 1 [Train]: 30%|███ | 39/129 [00:16<00:31, 2.89it/s, loss=0.93]
Epoch 1 [Train]: 30%|███ | 39/129 [00:16<00:31, 2.89it/s, loss=0.936]
Epoch 1 [Train]: 31%|███ | 40/129 [00:16<00:30, 2.87it/s, loss=0.936]
Epoch 1 [Train]: 31%|███ | 40/129 [00:16<00:30, 2.87it/s, loss=0.927]
Epoch 1 [Train]: 32%|███▏ | 41/129 [00:16<00:29, 2.98it/s, loss=0.927]
Epoch 1 [Train]: 32%|███▏ | 41/129 [00:17<00:29, 2.98it/s, loss=0.928]
Epoch 1 [Train]: 33%|███▎ | 42/129 [00:17<00:32, 2.68it/s, loss=0.928]
Epoch 1 [Train]: 33%|███▎ | 42/129 [00:17<00:32, 2.68it/s, loss=0.927]
Epoch 1 [Train]: 33%|███▎ | 43/129 [00:17<00:30, 2.80it/s, loss=0.927]
Epoch 1 [Train]: 33%|███▎ | 43/129 [00:18<00:30, 2.80it/s, loss=0.928]
Epoch 1 [Train]: 34%|███▍ | 44/129 [00:18<00:29, 2.93it/s, loss=0.928]
Epoch 1 [Train]: 34%|███▍ | 44/129 [00:18<00:29, 2.93it/s, loss=0.922]
Epoch 1 [Train]: 35%|███▍ | 45/129 [00:18<00:27, 3.04it/s, loss=0.922]
Epoch 1 [Train]: 35%|███▍ | 45/129 [00:18<00:27, 3.04it/s, loss=0.92]
Epoch 1 [Train]: 36%|███▌ | 46/129 [00:18<00:27, 3.07it/s, loss=0.92]
Epoch 1 [Train]: 36%|███▌ | 46/129 [00:18<00:27, 3.07it/s, loss=0.921]
Epoch 1 [Train]: 36%|███▋ | 47/129 [00:18<00:26, 3.05it/s, loss=0.921]
Epoch 1 [Train]: 36%|███▋ | 47/129 [00:19<00:26, 3.05it/s, loss=0.92]
Epoch 1 [Train]: 37%|███▋ | 48/129 [00:19<00:26, 3.06it/s, loss=0.92]
Epoch 1 [Train]: 37%|███▋ | 48/129 [00:19<00:26, 3.06it/s, loss=0.917]
Epoch 1 [Train]: 38%|███▊ | 49/129 [00:19<00:29, 2.71it/s, loss=0.917]
Epoch 1 [Train]: 38%|███▊ | 49/129 [00:20<00:29, 2.71it/s, loss=0.913]
Epoch 1 [Train]: 39%|███▉ | 50/129 [00:20<00:27, 2.86it/s, loss=0.913]
Epoch 1 [Train]: 39%|███▉ | 50/129 [00:20<00:27, 2.86it/s, loss=0.906]
Epoch 1 [Train]: 40%|███▉ | 51/129 [00:20<00:26, 2.94it/s, loss=0.906]
Epoch 1 [Train]: 40%|███▉ | 51/129 [00:20<00:26, 2.94it/s, loss=0.901]
Epoch 1 [Train]: 40%|████ | 52/129 [00:20<00:25, 3.02it/s, loss=0.901]
Epoch 1 [Train]: 40%|████ | 52/129 [00:21<00:25, 3.02it/s, loss=0.895]
Epoch 1 [Train]: 41%|████ | 53/129 [00:21<00:27, 2.73it/s, loss=0.895]
Epoch 1 [Train]: 41%|████ | 53/129 [00:21<00:27, 2.73it/s, loss=0.89]
Epoch 1 [Train]: 42%|████▏ | 54/129 [00:21<00:27, 2.75it/s, loss=0.89]
Epoch 1 [Train]: 42%|████▏ | 54/129 [00:21<00:27, 2.75it/s, loss=0.89]
Epoch 1 [Train]: 43%|████▎ | 55/129 [00:21<00:28, 2.58it/s, loss=0.89]
Epoch 1 [Train]: 43%|████▎ | 55/129 [00:22<00:28, 2.58it/s, loss=0.883]
Epoch 1 [Train]: 43%|████▎ | 56/129 [00:22<00:25, 2.81it/s, loss=0.883]
Epoch 1 [Train]: 43%|████▎ | 56/129 [00:22<00:25, 2.81it/s, loss=0.878]
Epoch 1 [Train]: 44%|████▍ | 57/129 [00:22<00:26, 2.71it/s, loss=0.878]
Epoch 1 [Train]: 44%|████▍ | 57/129 [00:22<00:26, 2.71it/s, loss=0.88]
Epoch 1 [Train]: 45%|████▍ | 58/129 [00:22<00:24, 2.88it/s, loss=0.88]
Epoch 1 [Train]: 45%|████▍ | 58/129 [00:23<00:24, 2.88it/s, loss=0.881]
Epoch 1 [Train]: 46%|████▌ | 59/129 [00:23<00:23, 2.92it/s, loss=0.881]
Epoch 1 [Train]: 46%|████▌ | 59/129 [00:23<00:23, 2.92it/s, loss=0.877]
Epoch 1 [Train]: 47%|████▋ | 60/129 [00:23<00:22, 3.11it/s, loss=0.877]
Epoch 1 [Train]: 47%|████▋ | 60/129 [00:23<00:22, 3.11it/s, loss=0.88]
Epoch 1 [Train]: 47%|████▋ | 61/129 [00:23<00:21, 3.18it/s, loss=0.88]
Epoch 1 [Train]: 47%|████▋ | 61/129 [00:24<00:21, 3.18it/s, loss=0.882]
Epoch 1 [Train]: 48%|████▊ | 62/129 [00:24<00:20, 3.27it/s, loss=0.882]
Epoch 1 [Train]: 48%|████▊ | 62/129 [00:24<00:20, 3.27it/s, loss=0.883]
Epoch 1 [Train]: 49%|████▉ | 63/129 [00:24<00:23, 2.77it/s, loss=0.883]
Epoch 1 [Train]: 49%|████▉ | 63/129 [00:24<00:23, 2.77it/s, loss=0.889]
Epoch 1 [Train]: 50%|████▉ | 64/129 [00:24<00:22, 2.90it/s, loss=0.889]
Epoch 1 [Train]: 50%|████▉ | 64/129 [00:25<00:22, 2.90it/s, loss=0.885]
Epoch 1 [Train]: 50%|█████ | 65/129 [00:25<00:21, 3.02it/s, loss=0.885]
Epoch 1 [Train]: 50%|█████ | 65/129 [00:25<00:21, 3.02it/s, loss=0.882]
Epoch 1 [Train]: 51%|█████ | 66/129 [00:25<00:20, 3.05it/s, loss=0.882]
Epoch 1 [Train]: 51%|█████ | 66/129 [00:25<00:20, 3.05it/s, loss=0.881]
Epoch 1 [Train]: 52%|█████▏ | 67/129 [00:25<00:19, 3.12it/s, loss=0.881]
Epoch 1 [Train]: 52%|█████▏ | 67/129 [00:26<00:19, 3.12it/s, loss=0.877]
Epoch 1 [Train]: 53%|█████▎ | 68/129 [00:26<00:19, 3.17it/s, loss=0.877]
Epoch 1 [Train]: 53%|█████▎ | 68/129 [00:26<00:19, 3.17it/s, loss=0.875]
Epoch 1 [Train]: 53%|█████▎ | 69/129 [00:26<00:18, 3.28it/s, loss=0.875]
Epoch 1 [Train]: 53%|█████▎ | 69/129 [00:26<00:18, 3.28it/s, loss=0.874]
Epoch 1 [Train]: 54%|█████▍ | 70/129 [00:26<00:21, 2.77it/s, loss=0.874]
Epoch 1 [Train]: 54%|█████▍ | 70/129 [00:27<00:21, 2.77it/s, loss=0.875]
Epoch 1 [Train]: 55%|█████▌ | 71/129 [00:27<00:20, 2.81it/s, loss=0.875]
Epoch 1 [Train]: 55%|█████▌ | 71/129 [00:27<00:20, 2.81it/s, loss=0.869]
Epoch 1 [Train]: 56%|█████▌ | 72/129 [00:27<00:19, 2.90it/s, loss=0.869]
Epoch 1 [Train]: 56%|█████▌ | 72/129 [00:27<00:19, 2.90it/s, loss=0.867]
Epoch 1 [Train]: 57%|█████▋ | 73/129 [00:27<00:18, 3.09it/s, loss=0.867]
Epoch 1 [Train]: 57%|█████▋ | 73/129 [00:28<00:18, 3.09it/s, loss=0.863]
Epoch 1 [Train]: 57%|█████▋ | 74/129 [00:28<00:18, 3.02it/s, loss=0.863]
Epoch 1 [Train]: 57%|█████▋ | 74/129 [00:28<00:18, 3.02it/s, loss=0.86]
Epoch 1 [Train]: 58%|█████▊ | 75/129 [00:28<00:16, 3.25it/s, loss=0.86]
Epoch 1 [Train]: 58%|█████▊ | 75/129 [00:28<00:16, 3.25it/s, loss=0.857]
Epoch 1 [Train]: 59%|█████▉ | 76/129 [00:28<00:17, 3.06it/s, loss=0.857]
Epoch 1 [Train]: 59%|█████▉ | 76/129 [00:29<00:17, 3.06it/s, loss=0.857]
Epoch 1 [Train]: 60%|█████▉ | 77/129 [00:29<00:19, 2.65it/s, loss=0.857]
Epoch 1 [Train]: 60%|█████▉ | 77/129 [00:29<00:19, 2.65it/s, loss=0.856]
Epoch 1 [Train]: 60%|██████ | 78/129 [00:29<00:18, 2.79it/s, loss=0.856]
Epoch 1 [Train]: 60%|██████ | 78/129 [00:30<00:18, 2.79it/s, loss=0.854]
Epoch 1 [Train]: 61%|██████ | 79/129 [00:30<00:18, 2.68it/s, loss=0.854]
Epoch 1 [Train]: 61%|██████ | 79/129 [00:30<00:18, 2.68it/s, loss=0.849]
Epoch 1 [Train]: 62%|██████▏ | 80/129 [00:30<00:17, 2.85it/s, loss=0.849]
Epoch 1 [Train]: 62%|██████▏ | 80/129 [00:30<00:17, 2.85it/s, loss=0.848]
Epoch 1 [Train]: 63%|██████▎ | 81/129 [00:30<00:16, 2.94it/s, loss=0.848]
Epoch 1 [Train]: 63%|██████▎ | 81/129 [00:30<00:16, 2.94it/s, loss=0.85]
Epoch 1 [Train]: 64%|██████▎ | 82/129 [00:30<00:15, 3.03it/s, loss=0.85]
Epoch 1 [Train]: 64%|██████▎ | 82/129 [00:31<00:15, 3.03it/s, loss=0.855]
Epoch 1 [Train]: 64%|██████▍ | 83/129 [00:31<00:17, 2.68it/s, loss=0.855]
Epoch 1 [Train]: 64%|██████▍ | 83/129 [00:31<00:17, 2.68it/s, loss=0.851]
Epoch 1 [Train]: 65%|██████▌ | 84/129 [00:31<00:16, 2.72it/s, loss=0.851]
Epoch 1 [Train]: 65%|██████▌ | 84/129 [00:32<00:16, 2.72it/s, loss=0.847]
Epoch 1 [Train]: 66%|██████▌ | 85/129 [00:32<00:15, 2.91it/s, loss=0.847]
Epoch 1 [Train]: 66%|██████▌ | 85/129 [00:32<00:15, 2.91it/s, loss=0.849]
Epoch 1 [Train]: 67%|██████▋ | 86/129 [00:32<00:14, 2.98it/s, loss=0.849]
Epoch 1 [Train]: 67%|██████▋ | 86/129 [00:32<00:14, 2.98it/s, loss=0.847]
Epoch 1 [Train]: 67%|██████▋ | 87/129 [00:32<00:13, 3.09it/s, loss=0.847]
Epoch 1 [Train]: 67%|██████▋ | 87/129 [00:33<00:13, 3.09it/s, loss=0.847]
Epoch 1 [Train]: 68%|██████▊ | 88/129 [00:33<00:13, 3.12it/s, loss=0.847]
Epoch 1 [Train]: 68%|██████▊ | 88/129 [00:33<00:13, 3.12it/s, loss=0.847]
Epoch 1 [Train]: 69%|██████▉ | 89/129 [00:33<00:12, 3.16it/s, loss=0.847]
Epoch 1 [Train]: 69%|██████▉ | 89/129 [00:33<00:12, 3.16it/s, loss=0.845]
Epoch 1 [Train]: 70%|██████▉ | 90/129 [00:33<00:14, 2.73it/s, loss=0.845]
Epoch 1 [Train]: 70%|██████▉ | 90/129 [00:34<00:14, 2.73it/s, loss=0.843]
Epoch 1 [Train]: 71%|███████ | 91/129 [00:34<00:13, 2.86it/s, loss=0.843]
Epoch 1 [Train]: 71%|███████ | 91/129 [00:34<00:13, 2.86it/s, loss=0.842]
Epoch 1 [Train]: 71%|███████▏ | 92/129 [00:34<00:12, 2.97it/s, loss=0.842]
Epoch 1 [Train]: 71%|███████▏ | 92/129 [00:34<00:12, 2.97it/s, loss=0.841]
Epoch 1 [Train]: 72%|███████▏ | 93/129 [00:34<00:11, 3.10it/s, loss=0.841]
Epoch 1 [Train]: 72%|███████▏ | 93/129 [00:35<00:11, 3.10it/s, loss=0.839]
Epoch 1 [Train]: 73%|███████▎ | 94/129 [00:35<00:11, 3.18it/s, loss=0.839]
Epoch 1 [Train]: 73%|███████▎ | 94/129 [00:35<00:11, 3.18it/s, loss=0.836]
Epoch 1 [Train]: 74%|███████▎ | 95/129 [00:35<00:11, 2.94it/s, loss=0.836]
Epoch 1 [Train]: 74%|███████▎ | 95/129 [00:35<00:11, 2.94it/s, loss=0.834]
Epoch 1 [Train]: 74%|███████▍ | 96/129 [00:35<00:11, 2.93it/s, loss=0.834]
Epoch 1 [Train]: 74%|███████▍ | 96/129 [00:36<00:11, 2.93it/s, loss=0.832]
Epoch 1 [Train]: 75%|███████▌ | 97/129 [00:36<00:11, 2.71it/s, loss=0.832]
Epoch 1 [Train]: 75%|███████▌ | 97/129 [00:36<00:11, 2.71it/s, loss=0.832]
Epoch 1 [Train]: 76%|███████▌ | 98/129 [00:36<00:11, 2.71it/s, loss=0.832]
Epoch 1 [Train]: 76%|███████▌ | 98/129 [00:36<00:11, 2.71it/s, loss=0.834]
Epoch 1 [Train]: 77%|███████▋ | 99/129 [00:36<00:10, 2.79it/s, loss=0.834]
Epoch 1 [Train]: 77%|███████▋ | 99/129 [00:37<00:10, 2.79it/s, loss=0.835]
Epoch 1 [Train]: 78%|███████▊ | 100/129 [00:37<00:09, 2.92it/s, loss=0.835]
Epoch 1 [Train]: 78%|███████▊ | 100/129 [00:37<00:09, 2.92it/s, loss=0.834]
Epoch 1 [Train]: 78%|███████▊ | 101/129 [00:37<00:09, 3.05it/s, loss=0.834]
Epoch 1 [Train]: 78%|███████▊ | 101/129 [00:37<00:09, 3.05it/s, loss=0.837]
Epoch 1 [Train]: 79%|███████▉ | 102/129 [00:37<00:08, 3.03it/s, loss=0.837]
Epoch 1 [Train]: 79%|███████▉ | 102/129 [00:38<00:08, 3.03it/s, loss=0.837]
Epoch 1 [Train]: 80%|███████▉ | 103/129 [00:38<00:09, 2.87it/s, loss=0.837]
Epoch 1 [Train]: 80%|███████▉ | 103/129 [00:38<00:09, 2.87it/s, loss=0.834]
Epoch 1 [Train]: 81%|████████ | 104/129 [00:38<00:08, 3.01it/s, loss=0.834]
Epoch 1 [Train]: 81%|████████ | 104/129 [00:38<00:08, 3.01it/s, loss=0.836]
Epoch 1 [Train]: 81%|████████▏ | 105/129 [00:38<00:08, 2.93it/s, loss=0.836]
Epoch 1 [Train]: 81%|████████▏ | 105/129 [00:39<00:08, 2.93it/s, loss=0.832]
Epoch 1 [Train]: 82%|████████▏ | 106/129 [00:39<00:07, 2.93it/s, loss=0.832]
Epoch 1 [Train]: 82%|████████▏ | 106/129 [00:39<00:07, 2.93it/s, loss=0.829]
Epoch 1 [Train]: 83%|████████▎ | 107/129 [00:39<00:07, 3.06it/s, loss=0.829]
Epoch 1 [Train]: 83%|████████▎ | 107/129 [00:39<00:07, 3.06it/s, loss=0.828]
Epoch 1 [Train]: 84%|████████▎ | 108/129 [00:39<00:06, 3.07it/s, loss=0.828]
Epoch 1 [Train]: 84%|████████▎ | 108/129 [00:40<00:06, 3.07it/s, loss=0.831]
Epoch 1 [Train]: 84%|████████▍ | 109/129 [00:40<00:06, 2.88it/s, loss=0.831]
Epoch 1 [Train]: 84%|████████▍ | 109/129 [00:40<00:06, 2.88it/s, loss=0.829]
Epoch 1 [Train]: 85%|████████▌ | 110/129 [00:40<00:06, 2.72it/s, loss=0.829]
Epoch 1 [Train]: 85%|████████▌ | 110/129 [00:40<00:06, 2.72it/s, loss=0.828]
Epoch 1 [Train]: 86%|████████▌ | 111/129 [00:40<00:06, 2.97it/s, loss=0.828]
Epoch 1 [Train]: 86%|████████▌ | 111/129 [00:41<00:06, 2.97it/s, loss=0.828]
Epoch 1 [Train]: 87%|████████▋ | 112/129 [00:41<00:05, 3.01it/s, loss=0.828]
Epoch 1 [Train]: 87%|████████▋ | 112/129 [00:41<00:05, 3.01it/s, loss=0.826]
Epoch 1 [Train]: 88%|████████▊ | 113/129 [00:41<00:04, 3.25it/s, loss=0.826]
Epoch 1 [Train]: 88%|████████▊ | 113/129 [00:41<00:04, 3.25it/s, loss=0.826]
Epoch 1 [Train]: 88%|████████▊ | 114/129 [00:41<00:04, 3.09it/s, loss=0.826]
Epoch 1 [Train]: 88%|████████▊ | 114/129 [00:42<00:04, 3.09it/s, loss=0.823]
Epoch 1 [Train]: 89%|████████▉ | 115/129 [00:42<00:04, 3.26it/s, loss=0.823]
Epoch 1 [Train]: 89%|████████▉ | 115/129 [00:42<00:04, 3.26it/s, loss=0.826]
Epoch 1 [Train]: 90%|████████▉ | 116/129 [00:42<00:04, 2.89it/s, loss=0.826]
Epoch 1 [Train]: 90%|████████▉ | 116/129 [00:42<00:04, 2.89it/s, loss=0.824]
Epoch 1 [Train]: 91%|█████████ | 117/129 [00:42<00:04, 2.94it/s, loss=0.824]
Epoch 1 [Train]: 91%|█████████ | 117/129 [00:43<00:04, 2.94it/s, loss=0.822]
Epoch 1 [Train]: 91%|█████████▏| 118/129 [00:43<00:03, 3.13it/s, loss=0.822]
Epoch 1 [Train]: 91%|█████████▏| 118/129 [00:43<00:03, 3.13it/s, loss=0.823]
Epoch 1 [Train]: 92%|█████████▏| 119/129 [00:43<00:03, 3.25it/s, loss=0.823]
Epoch 1 [Train]: 92%|█████████▏| 119/129 [00:43<00:03, 3.25it/s, loss=0.823]
Epoch 1 [Train]: 93%|█████████▎| 120/129 [00:43<00:02, 3.04it/s, loss=0.823]
Epoch 1 [Train]: 93%|█████████▎| 120/129 [00:44<00:02, 3.04it/s, loss=0.824]
Epoch 1 [Train]: 94%|█████████▍| 121/129 [00:44<00:02, 3.16it/s, loss=0.824]
Epoch 1 [Train]: 94%|█████████▍| 121/129 [00:44<00:02, 3.16it/s, loss=0.826]
Epoch 1 [Train]: 95%|█████████▍| 122/129 [00:44<00:02, 3.33it/s, loss=0.826]
Epoch 1 [Train]: 95%|█████████▍| 122/129 [00:44<00:02, 3.33it/s, loss=0.825]
Epoch 1 [Train]: 95%|█████████▌| 123/129 [00:44<00:02, 2.77it/s, loss=0.825]
Epoch 1 [Train]: 95%|█████████▌| 123/129 [00:45<00:02, 2.77it/s, loss=0.822]
Epoch 1 [Train]: 96%|█████████▌| 124/129 [00:45<00:01, 2.89it/s, loss=0.822]
Epoch 1 [Train]: 96%|█████████▌| 124/129 [00:45<00:01, 2.89it/s, loss=0.823]
Epoch 1 [Train]: 97%|█████████▋| 125/129 [00:45<00:01, 3.06it/s, loss=0.823]
Epoch 1 [Train]: 97%|█████████▋| 125/129 [00:45<00:01, 3.06it/s, loss=0.823]
Epoch 1 [Train]: 98%|█████████▊| 126/129 [00:45<00:00, 3.10it/s, loss=0.823]
Epoch 1 [Train]: 98%|█████████▊| 126/129 [00:46<00:00, 3.10it/s, loss=0.824]
Epoch 1 [Train]: 98%|█████████▊| 127/129 [00:46<00:00, 3.25it/s, loss=0.824]
Epoch 1 [Train]: 98%|█████████▊| 127/129 [00:46<00:00, 3.25it/s, loss=0.821]
Epoch 1 [Train]: 99%|█████████▉| 128/129 [00:46<00:00, 3.37it/s, loss=0.821]
Epoch 1 [Train]: 99%|█████████▉| 128/129 [00:46<00:00, 3.37it/s, loss=0.821]
Epoch 1 [Train]: 100%|██████████| 129/129 [00:46<00:00, 3.68it/s, loss=0.821]
2026-08-07 06:50:01.521 | INFO  | __main__:pretrain:180 - Epoch 1/50 | Train Loss: 0.8207 | Val Loss: 0.7837
2026-08-07 06:50:01.535 | INFO  | __main__:pretrain:196 -  -> New best model (val_loss=0.7837)
Epoch 2 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 2 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.67]
Epoch 2 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.701]
Epoch 2 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.662]
Epoch 2 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.667]
Epoch 2 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.37it/s, loss=0.667]
Epoch 2 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.37it/s, loss=0.655]
Epoch 2 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.37it/s, loss=0.692]
Epoch 2 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.37it/s, loss=0.688]
Epoch 2 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.37it/s, loss=0.69]
Epoch 2 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.24it/s, loss=0.69]
Epoch 2 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.24it/s, loss=0.679]
Epoch 2 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.24it/s, loss=0.646]
Epoch 2 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.24it/s, loss=0.669]
Epoch 2 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.24it/s, loss=0.657]
Epoch 2 [Train]: 9%|▉ | 12/129 [00:00<00:04, 29.21it/s, loss=0.657]
Epoch 2 [Train]: 9%|▉ | 12/129 [00:00<00:04, 29.21it/s, loss=0.654]
Epoch 2 [Train]: 9%|▉ | 12/129 [00:00<00:04, 29.21it/s, loss=0.688]
Epoch 2 [Train]: 9%|▉ | 12/129 [00:00<00:04, 29.21it/s, loss=0.69]
Epoch 2 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 28.44it/s, loss=0.69]
Epoch 2 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 28.44it/s, loss=0.722]
Epoch 2 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 28.44it/s, loss=0.713]
Epoch 2 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 28.44it/s, loss=0.725]
Epoch 2 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.14it/s, loss=0.725]
Epoch 2 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.14it/s, loss=0.724]
Epoch 2 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.14it/s, loss=0.724]
Epoch 2 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.14it/s, loss=0.717]
Epoch 2 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.49it/s, loss=0.717]
Epoch 2 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.49it/s, loss=0.719]
Epoch 2 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.49it/s, loss=0.714]
Epoch 2 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.49it/s, loss=0.714]
Epoch 2 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.78it/s, loss=0.714]
Epoch 2 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.78it/s, loss=0.714]
Epoch 2 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.78it/s, loss=0.717]
Epoch 2 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.78it/s, loss=0.712]
Epoch 2 [Train]: 21%|██ | 27/129 [00:00<00:03, 26.93it/s, loss=0.712]
Epoch 2 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.93it/s, loss=0.704]
Epoch 2 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.93it/s, loss=0.701]
Epoch 2 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.93it/s, loss=0.7]
Epoch 2 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.56it/s, loss=0.7]
Epoch 2 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.56it/s, loss=0.702]
Epoch 2 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.56it/s, loss=0.7]
Epoch 2 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.56it/s, loss=0.695]
Epoch 2 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.24it/s, loss=0.695]
Epoch 2 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.24it/s, loss=0.691]
Epoch 2 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.24it/s, loss=0.685]
Epoch 2 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.24it/s, loss=0.68]
Epoch 2 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.42it/s, loss=0.68]
Epoch 2 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.42it/s, loss=0.681]
Epoch 2 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.42it/s, loss=0.679]
Epoch 2 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.42it/s, loss=0.693]
Epoch 2 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.85it/s, loss=0.693]
Epoch 2 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.85it/s, loss=0.692]
Epoch 2 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.85it/s, loss=0.691]
Epoch 2 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.85it/s, loss=0.69]
Epoch 2 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.99it/s, loss=0.69]
Epoch 2 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.99it/s, loss=0.692]
Epoch 2 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.99it/s, loss=0.698]
Epoch 2 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.99it/s, loss=0.704]
Epoch 2 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.93it/s, loss=0.704]
Epoch 2 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.93it/s, loss=0.703]
Epoch 2 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.93it/s, loss=0.705]
Epoch 2 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.93it/s, loss=0.704]
Epoch 2 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.01it/s, loss=0.704]
Epoch 2 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.01it/s, loss=0.706]
Epoch 2 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.01it/s, loss=0.705]
Epoch 2 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.01it/s, loss=0.706]
Epoch 2 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.24it/s, loss=0.706]
Epoch 2 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.24it/s, loss=0.705]
Epoch 2 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.24it/s, loss=0.711]
Epoch 2 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.24it/s, loss=0.713]
Epoch 2 [Train]: 42%|████▏ | 54/129 [00:01<00:02, 27.53it/s, loss=0.713]
Epoch 2 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.53it/s, loss=0.714]
Epoch 2 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.53it/s, loss=0.711]
Epoch 2 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.53it/s, loss=0.712]
Epoch 2 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.61it/s, loss=0.712]
Epoch 2 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.61it/s, loss=0.709]
Epoch 2 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.61it/s, loss=0.711]
Epoch 2 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.61it/s, loss=0.707]
Epoch 2 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.81it/s, loss=0.707]
Epoch 2 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.81it/s, loss=0.713]
Epoch 2 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.81it/s, loss=0.712]
Epoch 2 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.81it/s, loss=0.716]
Epoch 2 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.56it/s, loss=0.716]
Epoch 2 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.56it/s, loss=0.718]
Epoch 2 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.56it/s, loss=0.718]
Epoch 2 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.56it/s, loss=0.717]
Epoch 2 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.26it/s, loss=0.717]
Epoch 2 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.26it/s, loss=0.717]
Epoch 2 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.26it/s, loss=0.713]
Epoch 2 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.26it/s, loss=0.714]
Epoch 2 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.00it/s, loss=0.714]
Epoch 2 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.00it/s, loss=0.717]
Epoch 2 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.00it/s, loss=0.715]
Epoch 2 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.00it/s, loss=0.716]
Epoch 2 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.13it/s, loss=0.716]
Epoch 2 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.13it/s, loss=0.715]
Epoch 2 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.13it/s, loss=0.717]
Epoch 2 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.13it/s, loss=0.714]
Epoch 2 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 25.79it/s, loss=0.714]
Epoch 2 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 25.79it/s, loss=0.711]
Epoch 2 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 25.79it/s, loss=0.71]
Epoch 2 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 25.79it/s, loss=0.708]
Epoch 2 [Train]: 60%|██████ | 78/129 [00:02<00:01, 25.65it/s, loss=0.708]
Epoch 2 [Train]: 60%|██████ | 78/129 [00:02<00:01, 25.65it/s, loss=0.706]
Epoch 2 [Train]: 60%|██████ | 78/129 [00:02<00:01, 25.65it/s, loss=0.702]
Epoch 2 [Train]: 60%|██████ | 78/129 [00:03<00:01, 25.65it/s, loss=0.7]
Epoch 2 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.86it/s, loss=0.7]
Epoch 2 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.86it/s, loss=0.698]
Epoch 2 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.86it/s, loss=0.704]
Epoch 2 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.86it/s, loss=0.704]
Epoch 2 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.62it/s, loss=0.704]
Epoch 2 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.62it/s, loss=0.704]
Epoch 2 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.62it/s, loss=0.704]
Epoch 2 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.62it/s, loss=0.705]
Epoch 2 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.03it/s, loss=0.705]
Epoch 2 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.03it/s, loss=0.701]
Epoch 2 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.03it/s, loss=0.701]
Epoch 2 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.03it/s, loss=0.701]
Epoch 2 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.85it/s, loss=0.701]
Epoch 2 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.85it/s, loss=0.699]
Epoch 2 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.85it/s, loss=0.699]
Epoch 2 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.85it/s, loss=0.698]
Epoch 2 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 26.73it/s, loss=0.698]
Epoch 2 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 26.73it/s, loss=0.696]
Epoch 2 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 26.73it/s, loss=0.703]
Epoch 2 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 26.73it/s, loss=0.706]
Epoch 2 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.03it/s, loss=0.706]
Epoch 2 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.03it/s, loss=0.71]
Epoch 2 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.03it/s, loss=0.707]
Epoch 2 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.03it/s, loss=0.706]
Epoch 2 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.92it/s, loss=0.706]
Epoch 2 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.92it/s, loss=0.708]
Epoch 2 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.92it/s, loss=0.71]
Epoch 2 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.92it/s, loss=0.708]
Epoch 2 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.81it/s, loss=0.708]
Epoch 2 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.81it/s, loss=0.709]
Epoch 2 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.81it/s, loss=0.708]
Epoch 2 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.81it/s, loss=0.706]
Epoch 2 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.64it/s, loss=0.706]
Epoch 2 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.64it/s, loss=0.705]
Epoch 2 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.64it/s, loss=0.706]
Epoch 2 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 27.64it/s, loss=0.707]
Epoch 2 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.70it/s, loss=0.707]
Epoch 2 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.70it/s, loss=0.705]
Epoch 2 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.70it/s, loss=0.704]
Epoch 2 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.70it/s, loss=0.702]
Epoch 2 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.73it/s, loss=0.702]
Epoch 2 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.73it/s, loss=0.705]
Epoch 2 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.73it/s, loss=0.705]
Epoch 2 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.73it/s, loss=0.706]
Epoch 2 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.15it/s, loss=0.706]
Epoch 2 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.15it/s, loss=0.706]
Epoch 2 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.15it/s, loss=0.703]
Epoch 2 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.15it/s, loss=0.703]
Epoch 2 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 28.17it/s, loss=0.703]
Epoch 2 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 28.17it/s, loss=0.704]
Epoch 2 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 28.17it/s, loss=0.706]
Epoch 2 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 28.17it/s, loss=0.705]
Epoch 2 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.99it/s, loss=0.705]
Epoch 2 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.99it/s, loss=0.707]
Epoch 2 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.99it/s, loss=0.706]
Epoch 2 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.99it/s, loss=0.709]
Epoch 2 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.96it/s, loss=0.709]
Epoch 2 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.96it/s, loss=0.708]
Epoch 2 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.96it/s, loss=0.707]
Epoch 2 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.96it/s, loss=0.706]
Epoch 2 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.74it/s, loss=0.706]
Epoch 2 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.74it/s, loss=0.706]
Epoch 2 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.74it/s, loss=0.705]
Epoch 2 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.74it/s, loss=0.704]
Epoch 2 [Train]: 100%|██████████| 129/129 [00:04<00:00, 27.00it/s, loss=0.704]
2026-08-07 06:50:06.487 | INFO  | __main__:pretrain:180 - Epoch 2/50 | Train Loss: 0.7038 | Val Loss: 0.7153
2026-08-07 06:50:06.504 | INFO  | __main__:pretrain:196 -  -> New best model (val_loss=0.7153)
Epoch 3 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 3 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.808]
Epoch 3 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.657]
Epoch 3 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.669]
Epoch 3 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.601]
Epoch 3 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.05it/s, loss=0.601]
Epoch 3 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.05it/s, loss=0.575]
Epoch 3 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.05it/s, loss=0.587]
Epoch 3 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.05it/s, loss=0.588]
Epoch 3 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.05it/s, loss=0.592]
Epoch 3 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.52it/s, loss=0.592]
Epoch 3 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.52it/s, loss=0.605]
Epoch 3 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.52it/s, loss=0.652]
Epoch 3 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.52it/s, loss=0.634]
Epoch 3 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.52it/s, loss=0.65]
Epoch 3 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.35it/s, loss=0.65]
Epoch 3 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.35it/s, loss=0.634]
Epoch 3 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.35it/s, loss=0.638]
Epoch 3 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.35it/s, loss=0.641]
Epoch 3 [Train]: 12%|█▏ | 15/129 [00:00<00:03, 28.62it/s, loss=0.641]
Epoch 3 [Train]: 12%|█▏ | 15/129 [00:00<00:03, 28.62it/s, loss=0.641]
Epoch 3 [Train]: 12%|█▏ | 15/129 [00:00<00:03, 28.62it/s, loss=0.636]
Epoch 3 [Train]: 12%|█▏ | 15/129 [00:00<00:03, 28.62it/s, loss=0.632]
Epoch 3 [Train]: 14%|█▍ | 18/129 [00:00<00:03, 28.51it/s, loss=0.632]
Epoch 3 [Train]: 14%|█▍ | 18/129 [00:00<00:03, 28.51it/s, loss=0.63]
Epoch 3 [Train]: 14%|█▍ | 18/129 [00:00<00:03, 28.51it/s, loss=0.636]
Epoch 3 [Train]: 14%|█▍ | 18/129 [00:00<00:03, 28.51it/s, loss=0.635]
Epoch 3 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 28.70it/s, loss=0.635]
Epoch 3 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 28.70it/s, loss=0.63]
Epoch 3 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 28.70it/s, loss=0.624]
Epoch 3 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 28.70it/s, loss=0.623]
Epoch 3 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 28.02it/s, loss=0.623]
Epoch 3 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 28.02it/s, loss=0.627]
Epoch 3 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 28.02it/s, loss=0.629]
Epoch 3 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 28.02it/s, loss=0.636]
Epoch 3 [Train]: 21%|██ | 27/129 [00:00<00:03, 27.33it/s, loss=0.636]
Epoch 3 [Train]: 21%|██ | 27/129 [00:00<00:03, 27.33it/s, loss=0.632]
Epoch 3 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.33it/s, loss=0.631]
Epoch 3 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.33it/s, loss=0.629]
Epoch 3 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.71it/s, loss=0.629]
Epoch 3 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.71it/s, loss=0.622]
Epoch 3 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.71it/s, loss=0.621]
Epoch 3 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.71it/s, loss=0.618]
Epoch 3 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.36it/s, loss=0.618]
Epoch 3 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.36it/s, loss=0.619]
Epoch 3 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.36it/s, loss=0.62]
Epoch 3 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.36it/s, loss=0.626]
Epoch 3 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.57it/s, loss=0.626]
Epoch 3 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.57it/s, loss=0.627]
Epoch 3 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.57it/s, loss=0.628]
Epoch 3 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.57it/s, loss=0.629]
Epoch 3 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.77it/s, loss=0.629]
Epoch 3 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.77it/s, loss=0.634]
Epoch 3 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.77it/s, loss=0.637]
Epoch 3 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.77it/s, loss=0.635]
Epoch 3 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.96it/s, loss=0.635]
Epoch 3 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.96it/s, loss=0.647]
Epoch 3 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.96it/s, loss=0.645]
Epoch 3 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.96it/s, loss=0.639]
Epoch 3 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.67it/s, loss=0.639]
Epoch 3 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.67it/s, loss=0.635]
Epoch 3 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.67it/s, loss=0.631]
Epoch 3 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.67it/s, loss=0.632]
Epoch 3 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.23it/s, loss=0.632]
Epoch 3 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.23it/s, loss=0.64]
Epoch 3 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.23it/s, loss=0.642]
Epoch 3 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.23it/s, loss=0.638]
Epoch 3 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.32it/s, loss=0.638]
Epoch 3 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.32it/s, loss=0.637]
Epoch 3 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.32it/s, loss=0.646]
Epoch 3 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.32it/s, loss=0.644]
Epoch 3 [Train]: 42%|████▏ | 54/129 [00:01<00:02, 25.86it/s, loss=0.644]
Epoch 3 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 25.86it/s, loss=0.641]
Epoch 3 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 25.86it/s, loss=0.637]
Epoch 3 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 25.86it/s, loss=0.638]
Epoch 3 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.14it/s, loss=0.638]
Epoch 3 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.14it/s, loss=0.636]
Epoch 3 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.14it/s, loss=0.634]
Epoch 3 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.14it/s, loss=0.632]
Epoch 3 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.74it/s, loss=0.632]
Epoch 3 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.74it/s, loss=0.635]
Epoch 3 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.74it/s, loss=0.634]
Epoch 3 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.74it/s, loss=0.635]
Epoch 3 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.29it/s, loss=0.635]
Epoch 3 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.29it/s, loss=0.639]
Epoch 3 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.29it/s, loss=0.64]
Epoch 3 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.29it/s, loss=0.639]
Epoch 3 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.72it/s, loss=0.639]
Epoch 3 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.72it/s, loss=0.639]
Epoch 3 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.72it/s, loss=0.641]
Epoch 3 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.72it/s, loss=0.642]
Epoch 3 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.16it/s, loss=0.642]
Epoch 3 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.16it/s, loss=0.643]
Epoch 3 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.16it/s, loss=0.643]
Epoch 3 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.16it/s, loss=0.64]
Epoch 3 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.18it/s, loss=0.64]
Epoch 3 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.18it/s, loss=0.639]
Epoch 3 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.18it/s, loss=0.64]
Epoch 3 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.18it/s, loss=0.643]
Epoch 3 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.28it/s, loss=0.643]
Epoch 3 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.28it/s, loss=0.642]
Epoch 3 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.28it/s, loss=0.641]
Epoch 3 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.28it/s, loss=0.639]
Epoch 3 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.17it/s, loss=0.639]
Epoch 3 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.17it/s, loss=0.639]
Epoch 3 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.17it/s, loss=0.64]
Epoch 3 [Train]: 60%|██████ | 78/129 [00:03<00:01, 26.17it/s, loss=0.642]
Epoch 3 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.01it/s, loss=0.642]
Epoch 3 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.01it/s, loss=0.64]
Epoch 3 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.01it/s, loss=0.638]
Epoch 3 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.01it/s, loss=0.636]
Epoch 3 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.84it/s, loss=0.636]
Epoch 3 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.84it/s, loss=0.636]
Epoch 3 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.84it/s, loss=0.635]
Epoch 3 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.84it/s, loss=0.635]
Epoch 3 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.14it/s, loss=0.635]
Epoch 3 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.14it/s, loss=0.637]
Epoch 3 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.14it/s, loss=0.634]
Epoch 3 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.14it/s, loss=0.634]
Epoch 3 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.70it/s, loss=0.634]
Epoch 3 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.70it/s, loss=0.633]
Epoch 3 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.70it/s, loss=0.637]
Epoch 3 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.70it/s, loss=0.638]
Epoch 3 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.52it/s, loss=0.638]
Epoch 3 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.52it/s, loss=0.637]
Epoch 3 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.52it/s, loss=0.637]
Epoch 3 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.52it/s, loss=0.636]
Epoch 3 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.90it/s, loss=0.636]
Epoch 3 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.90it/s, loss=0.637]
Epoch 3 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.90it/s, loss=0.636]
Epoch 3 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.90it/s, loss=0.638]
Epoch 3 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.85it/s, loss=0.638]
Epoch 3 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.85it/s, loss=0.638]
Epoch 3 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.85it/s, loss=0.639]
Epoch 3 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.85it/s, loss=0.64]
Epoch 3 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.67it/s, loss=0.64]
Epoch 3 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.67it/s, loss=0.638]
Epoch 3 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.67it/s, loss=0.64]
Epoch 3 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.67it/s, loss=0.64]
Epoch 3 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.07it/s, loss=0.64]
Epoch 3 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.07it/s, loss=0.638]
Epoch 3 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.07it/s, loss=0.638]
Epoch 3 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.07it/s, loss=0.642]
Epoch 3 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 26.82it/s, loss=0.642]
Epoch 3 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.82it/s, loss=0.641]
Epoch 3 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.82it/s, loss=0.64]
Epoch 3 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.82it/s, loss=0.641]
Epoch 3 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.85it/s, loss=0.641]
Epoch 3 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.85it/s, loss=0.642]
Epoch 3 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.85it/s, loss=0.646]
Epoch 3 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.85it/s, loss=0.645]
Epoch 3 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.42it/s, loss=0.645]
Epoch 3 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.42it/s, loss=0.646]
Epoch 3 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.42it/s, loss=0.646]
Epoch 3 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.42it/s, loss=0.645]
Epoch 3 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.35it/s, loss=0.645]
Epoch 3 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.35it/s, loss=0.644]
Epoch 3 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.35it/s, loss=0.644]
Epoch 3 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.35it/s, loss=0.644]
Epoch 3 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.60it/s, loss=0.644]
Epoch 3 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.60it/s, loss=0.644]
Epoch 3 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.60it/s, loss=0.642]
Epoch 3 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.60it/s, loss=0.641]
Epoch 3 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.23it/s, loss=0.641]
Epoch 3 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.23it/s, loss=0.642]
Epoch 3 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.23it/s, loss=0.643]
Epoch 3 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.23it/s, loss=0.643]
Epoch 3 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.38it/s, loss=0.643]
Epoch 3 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.38it/s, loss=0.642]
Epoch 3 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.38it/s, loss=0.643]
Epoch 3 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.38it/s, loss=0.642]
Epoch 3 [Train]: 100%|██████████| 129/129 [00:04<00:00, 26.38it/s, loss=0.642]
2026-08-07 06:50:11.434 | INFO  | __main__:pretrain:180 - Epoch 3/50 | Train Loss: 0.6420 | Val Loss: 0.7234
Epoch 4 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 4 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.684]
Epoch 4 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.677]
Epoch 4 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.668]
Epoch 4 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.607]
Epoch 4 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.16it/s, loss=0.607]
Epoch 4 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.16it/s, loss=0.621]
Epoch 4 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.16it/s, loss=0.578]
Epoch 4 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.16it/s, loss=0.586]
Epoch 4 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.16it/s, loss=0.57]
Epoch 4 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.87it/s, loss=0.57]
Epoch 4 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.87it/s, loss=0.574]
Epoch 4 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.87it/s, loss=0.591]
Epoch 4 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.87it/s, loss=0.573]
Epoch 4 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.06it/s, loss=0.573]
Epoch 4 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.06it/s, loss=0.575]
Epoch 4 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.06it/s, loss=0.568]
Epoch 4 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.06it/s, loss=0.559]
Epoch 4 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.57it/s, loss=0.559]
Epoch 4 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.57it/s, loss=0.55]
Epoch 4 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.57it/s, loss=0.567]
Epoch 4 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.57it/s, loss=0.561]
Epoch 4 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 26.49it/s, loss=0.561]
Epoch 4 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 26.49it/s, loss=0.561]
Epoch 4 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 26.49it/s, loss=0.555]
Epoch 4 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 26.49it/s, loss=0.553]
Epoch 4 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.10it/s, loss=0.553]
Epoch 4 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.10it/s, loss=0.546]
Epoch 4 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.10it/s, loss=0.557]
Epoch 4 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.10it/s, loss=0.567]
Epoch 4 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 25.43it/s, loss=0.567]
Epoch 4 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 25.43it/s, loss=0.565]
Epoch 4 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 25.43it/s, loss=0.568]
Epoch 4 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 25.43it/s, loss=0.585]
Epoch 4 [Train]: 20%|██ | 26/129 [00:00<00:03, 26.00it/s, loss=0.585]
Epoch 4 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.00it/s, loss=0.592]
Epoch 4 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.00it/s, loss=0.587]
Epoch 4 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.00it/s, loss=0.581]
Epoch 4 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.60it/s, loss=0.581]
Epoch 4 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.60it/s, loss=0.577]
Epoch 4 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.60it/s, loss=0.583]
Epoch 4 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.60it/s, loss=0.581]
Epoch 4 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 27.21it/s, loss=0.581]
Epoch 4 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 27.21it/s, loss=0.581]
Epoch 4 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 27.21it/s, loss=0.585]
Epoch 4 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 27.21it/s, loss=0.587]
Epoch 4 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 27.44it/s, loss=0.587]
Epoch 4 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 27.44it/s, loss=0.589]
Epoch 4 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 27.44it/s, loss=0.585]
Epoch 4 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 27.44it/s, loss=0.588]
Epoch 4 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 27.38it/s, loss=0.588]
Epoch 4 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 27.38it/s, loss=0.585]
Epoch 4 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 27.38it/s, loss=0.581]
Epoch 4 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 27.38it/s, loss=0.578]
Epoch 4 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 27.34it/s, loss=0.578]
Epoch 4 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 27.34it/s, loss=0.579]
Epoch 4 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 27.34it/s, loss=0.577]
Epoch 4 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 27.34it/s, loss=0.57]
Epoch 4 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 27.39it/s, loss=0.57]
Epoch 4 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 27.39it/s, loss=0.572]
Epoch 4 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 27.39it/s, loss=0.578]
Epoch 4 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 27.39it/s, loss=0.591]
Epoch 4 [Train]: 36%|███▋ | 47/129 [00:01<00:02, 27.63it/s, loss=0.591]
Epoch 4 [Train]: 36%|███▋ | 47/129 [00:01<00:02, 27.63it/s, loss=0.596]
Epoch 4 [Train]: 36%|███▋ | 47/129 [00:01<00:02, 27.63it/s, loss=0.6]
Epoch 4 [Train]: 36%|███▋ | 47/129 [00:01<00:02, 27.63it/s, loss=0.6]
Epoch 4 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.60it/s, loss=0.6]
Epoch 4 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.60it/s, loss=0.601]
Epoch 4 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.60it/s, loss=0.601]
Epoch 4 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.60it/s, loss=0.603]
Epoch 4 [Train]: 41%|████ | 53/129 [00:01<00:02, 27.18it/s, loss=0.603]
Epoch 4 [Train]: 41%|████ | 53/129 [00:01<00:02, 27.18it/s, loss=0.601]
Epoch 4 [Train]: 41%|████ | 53/129 [00:02<00:02, 27.18it/s, loss=0.601]
Epoch 4 [Train]: 41%|████ | 53/129 [00:02<00:02, 27.18it/s, loss=0.598]
Epoch 4 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.44it/s, loss=0.598]
Epoch 4 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.44it/s, loss=0.604]
Epoch 4 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.44it/s, loss=0.602]
Epoch 4 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.44it/s, loss=0.6]
Epoch 4 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.90it/s, loss=0.6]
Epoch 4 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.90it/s, loss=0.598]
Epoch 4 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.90it/s, loss=0.597]
Epoch 4 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.90it/s, loss=0.596]
Epoch 4 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.99it/s, loss=0.596]
Epoch 4 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.99it/s, loss=0.594]
Epoch 4 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.99it/s, loss=0.594]
Epoch 4 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.99it/s, loss=0.596]
Epoch 4 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.31it/s, loss=0.596]
Epoch 4 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.31it/s, loss=0.593]
Epoch 4 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.31it/s, loss=0.591]
Epoch 4 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.31it/s, loss=0.589]
Epoch 4 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.05it/s, loss=0.589]
Epoch 4 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.05it/s, loss=0.592]
Epoch 4 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.05it/s, loss=0.592]
Epoch 4 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.05it/s, loss=0.59]
Epoch 4 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.51it/s, loss=0.59]
Epoch 4 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.51it/s, loss=0.59]
Epoch 4 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.51it/s, loss=0.588]
Epoch 4 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.51it/s, loss=0.591]
Epoch 4 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.38it/s, loss=0.591]
Epoch 4 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.38it/s, loss=0.591]
Epoch 4 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.38it/s, loss=0.592]
Epoch 4 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.38it/s, loss=0.592]
Epoch 4 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.24it/s, loss=0.592]
Epoch 4 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.24it/s, loss=0.592]
Epoch 4 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.24it/s, loss=0.593]
Epoch 4 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.24it/s, loss=0.591]
Epoch 4 [Train]: 62%|██████▏ | 80/129 [00:02<00:01, 26.03it/s, loss=0.591]
Epoch 4 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.03it/s, loss=0.59]
Epoch 4 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.03it/s, loss=0.59]
Epoch 4 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.03it/s, loss=0.588]
Epoch 4 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.22it/s, loss=0.588]
Epoch 4 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.22it/s, loss=0.586]
Epoch 4 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.22it/s, loss=0.584]
Epoch 4 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.22it/s, loss=0.59]
Epoch 4 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.47it/s, loss=0.59]
Epoch 4 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.47it/s, loss=0.588]
Epoch 4 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.47it/s, loss=0.588]
Epoch 4 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.47it/s, loss=0.586]
Epoch 4 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.62it/s, loss=0.586]
Epoch 4 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.62it/s, loss=0.588]
Epoch 4 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.62it/s, loss=0.585]
Epoch 4 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.62it/s, loss=0.587]
Epoch 4 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 26.12it/s, loss=0.587]
Epoch 4 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 26.12it/s, loss=0.586]
Epoch 4 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 26.12it/s, loss=0.586]
Epoch 4 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 26.12it/s, loss=0.588]
Epoch 4 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.54it/s, loss=0.588]
Epoch 4 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.54it/s, loss=0.587]
Epoch 4 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.54it/s, loss=0.589]
Epoch 4 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.54it/s, loss=0.589]
Epoch 4 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.36it/s, loss=0.589]
Epoch 4 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.36it/s, loss=0.591]
Epoch 4 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.36it/s, loss=0.591]
Epoch 4 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.36it/s, loss=0.592]
Epoch 4 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.41it/s, loss=0.592]
Epoch 4 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.41it/s, loss=0.596]
Epoch 4 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.41it/s, loss=0.599]
Epoch 4 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.41it/s, loss=0.6]
Epoch 4 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.10it/s, loss=0.6]
Epoch 4 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.10it/s, loss=0.599]
Epoch 4 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.10it/s, loss=0.598]
Epoch 4 [Train]: 81%|████████ | 104/129 [00:04<00:00, 26.10it/s, loss=0.598]
Epoch 4 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 25.68it/s, loss=0.598]
Epoch 4 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 25.68it/s, loss=0.599]
Epoch 4 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 25.68it/s, loss=0.599]
Epoch 4 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 25.68it/s, loss=0.6]
Epoch 4 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.73it/s, loss=0.6]
Epoch 4 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.73it/s, loss=0.602]
Epoch 4 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.73it/s, loss=0.603]
Epoch 4 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.73it/s, loss=0.601]
Epoch 4 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.24it/s, loss=0.601]
Epoch 4 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.24it/s, loss=0.602]
Epoch 4 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.24it/s, loss=0.602]
Epoch 4 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.24it/s, loss=0.605]
Epoch 4 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.62it/s, loss=0.605]
Epoch 4 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.62it/s, loss=0.604]
Epoch 4 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.62it/s, loss=0.603]
Epoch 4 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.62it/s, loss=0.603]
Epoch 4 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.91it/s, loss=0.603]
Epoch 4 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.91it/s, loss=0.603]
Epoch 4 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.91it/s, loss=0.603]
Epoch 4 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.91it/s, loss=0.603]
Epoch 4 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.09it/s, loss=0.603]
Epoch 4 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.09it/s, loss=0.605]
Epoch 4 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.09it/s, loss=0.607]
Epoch 4 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.09it/s, loss=0.605]
Epoch 4 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.46it/s, loss=0.605]
Epoch 4 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.46it/s, loss=0.605]
Epoch 4 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.46it/s, loss=0.606]
Epoch 4 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.46it/s, loss=0.608]
Epoch 4 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 26.92it/s, loss=0.608]
Epoch 4 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 26.92it/s, loss=0.607]
2026-08-07 06:50:16.402 | INFO  | __main__:pretrain:180 - Epoch 4/50 | Train Loss: 0.6071 | Val Loss: 0.6935
2026-08-07 06:50:16.412 | INFO  | __main__:pretrain:196 -  -> New best model (val_loss=0.6935)
Epoch 5 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 5 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.709]
Epoch 5 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.604]
Epoch 5 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.569]
Epoch 5 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.585]
Epoch 5 [Train]: 3%|▎ | 4/129 [00:00<00:03, 34.05it/s, loss=0.585]
Epoch 5 [Train]: 3%|▎ | 4/129 [00:00<00:03, 34.05it/s, loss=0.598]
Epoch 5 [Train]: 3%|▎ | 4/129 [00:00<00:03, 34.05it/s, loss=0.61]
Epoch 5 [Train]: 3%|▎ | 4/129 [00:00<00:03, 34.05it/s, loss=0.593]
Epoch 5 [Train]: 3%|▎ | 4/129 [00:00<00:03, 34.05it/s, loss=0.579]
Epoch 5 [Train]: 6%|▌ | 8/129 [00:00<00:04, 27.85it/s, loss=0.579]
Epoch 5 [Train]: 6%|▌ | 8/129 [00:00<00:04, 27.85it/s, loss=0.604]
Epoch 5 [Train]: 6%|▌ | 8/129 [00:00<00:04, 27.85it/s, loss=0.604]
Epoch 5 [Train]: 6%|▌ | 8/129 [00:00<00:04, 27.85it/s, loss=0.603]
Epoch 5 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.66it/s, loss=0.603]
Epoch 5 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.66it/s, loss=0.609]
Epoch 5 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.66it/s, loss=0.606]
Epoch 5 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.66it/s, loss=0.599]
Epoch 5 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.77it/s, loss=0.599]
Epoch 5 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.77it/s, loss=0.596]
Epoch 5 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.77it/s, loss=0.606]
Epoch 5 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.77it/s, loss=0.606]
Epoch 5 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 26.38it/s, loss=0.606]
Epoch 5 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 26.38it/s, loss=0.602]
Epoch 5 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 26.38it/s, loss=0.598]
Epoch 5 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 26.38it/s, loss=0.602]
Epoch 5 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.24it/s, loss=0.602]
Epoch 5 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.24it/s, loss=0.595]
Epoch 5 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.24it/s, loss=0.592]
Epoch 5 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.24it/s, loss=0.588]
Epoch 5 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 25.75it/s, loss=0.588]
Epoch 5 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 25.75it/s, loss=0.584]
Epoch 5 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 25.75it/s, loss=0.578]
Epoch 5 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 25.75it/s, loss=0.572]
Epoch 5 [Train]: 20%|██ | 26/129 [00:00<00:04, 25.43it/s, loss=0.572]
Epoch 5 [Train]: 20%|██ | 26/129 [00:01<00:04, 25.43it/s, loss=0.573]
Epoch 5 [Train]: 20%|██ | 26/129 [00:01<00:04, 25.43it/s, loss=0.586]
Epoch 5 [Train]: 20%|██ | 26/129 [00:01<00:04, 25.43it/s, loss=0.587]
Epoch 5 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 25.52it/s, loss=0.587]
Epoch 5 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 25.52it/s, loss=0.587]
Epoch 5 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 25.52it/s, loss=0.582]
Epoch 5 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 25.52it/s, loss=0.578]
Epoch 5 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.42it/s, loss=0.578]
Epoch 5 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.42it/s, loss=0.574]
Epoch 5 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.42it/s, loss=0.58]
Epoch 5 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.42it/s, loss=0.576]
Epoch 5 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.18it/s, loss=0.576]
Epoch 5 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.18it/s, loss=0.579]
Epoch 5 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.18it/s, loss=0.58]
Epoch 5 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.18it/s, loss=0.576]
Epoch 5 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.59it/s, loss=0.576]
Epoch 5 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.59it/s, loss=0.577]
Epoch 5 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.59it/s, loss=0.583]
Epoch 5 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.59it/s, loss=0.579]
Epoch 5 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 27.14it/s, loss=0.579]
Epoch 5 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 27.14it/s, loss=0.584]
Epoch 5 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 27.14it/s, loss=0.585]
Epoch 5 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 27.14it/s, loss=0.588]
Epoch 5 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.49it/s, loss=0.588]
Epoch 5 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.49it/s, loss=0.586]
Epoch 5 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.49it/s, loss=0.583]
Epoch 5 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.49it/s, loss=0.581]
Epoch 5 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.76it/s, loss=0.581]
Epoch 5 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.76it/s, loss=0.581]
Epoch 5 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.76it/s, loss=0.582]
Epoch 5 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.76it/s, loss=0.579]
Epoch 5 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 26.63it/s, loss=0.579]
Epoch 5 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 26.63it/s, loss=0.576]
Epoch 5 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 26.63it/s, loss=0.576]
Epoch 5 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 26.63it/s, loss=0.577]
Epoch 5 [Train]: 41%|████ | 53/129 [00:01<00:02, 26.30it/s, loss=0.577]
Epoch 5 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.30it/s, loss=0.575]
Epoch 5 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.30it/s, loss=0.575]
Epoch 5 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.30it/s, loss=0.575]
Epoch 5 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.04it/s, loss=0.575]
Epoch 5 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.04it/s, loss=0.574]
Epoch 5 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.04it/s, loss=0.579]
Epoch 5 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.04it/s, loss=0.583]
Epoch 5 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.15it/s, loss=0.583]
Epoch 5 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.15it/s, loss=0.582]
Epoch 5 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.15it/s, loss=0.58]
Epoch 5 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.15it/s, loss=0.577]
Epoch 5 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.30it/s, loss=0.577]
Epoch 5 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.30it/s, loss=0.573]
Epoch 5 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.30it/s, loss=0.573]
Epoch 5 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.30it/s, loss=0.575]
Epoch 5 [Train]: 50%|█████ | 65/129 [00:02<00:02, 25.82it/s, loss=0.575]
Epoch 5 [Train]: 50%|█████ | 65/129 [00:02<00:02, 25.82it/s, loss=0.574]
Epoch 5 [Train]: 50%|█████ | 65/129 [00:02<00:02, 25.82it/s, loss=0.573]
Epoch 5 [Train]: 50%|█████ | 65/129 [00:02<00:02, 25.82it/s, loss=0.572]
Epoch 5 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.29it/s, loss=0.572]
Epoch 5 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.29it/s, loss=0.571]
Epoch 5 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.29it/s, loss=0.572]
Epoch 5 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.29it/s, loss=0.573]
Epoch 5 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.48it/s, loss=0.573]
Epoch 5 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.48it/s, loss=0.573]
Epoch 5 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.48it/s, loss=0.578]
Epoch 5 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.48it/s, loss=0.576]
Epoch 5 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.52it/s, loss=0.576]
Epoch 5 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.52it/s, loss=0.579]
Epoch 5 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.52it/s, loss=0.575]
Epoch 5 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.52it/s, loss=0.572]
Epoch 5 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.45it/s, loss=0.572]
Epoch 5 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.45it/s, loss=0.571]
Epoch 5 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.45it/s, loss=0.569]
Epoch 5 [Train]: 60%|█████▉ | 77/129 [00:03<00:01, 26.45it/s, loss=0.566]
Epoch 5 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.90it/s, loss=0.566]
Epoch 5 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.90it/s, loss=0.564]
Epoch 5 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.90it/s, loss=0.562]
Epoch 5 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.90it/s, loss=0.564]
Epoch 5 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.31it/s, loss=0.564]
Epoch 5 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.31it/s, loss=0.564]
Epoch 5 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.31it/s, loss=0.561]
Epoch 5 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.31it/s, loss=0.564]
Epoch 5 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.09it/s, loss=0.564]
Epoch 5 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.09it/s, loss=0.565]
Epoch 5 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.09it/s, loss=0.563]
Epoch 5 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.09it/s, loss=0.566]
Epoch 5 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.08it/s, loss=0.566]
Epoch 5 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.08it/s, loss=0.565]
Epoch 5 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.08it/s, loss=0.567]
Epoch 5 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.08it/s, loss=0.569]
Epoch 5 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 25.57it/s, loss=0.569]
Epoch 5 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 25.57it/s, loss=0.573]
Epoch 5 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 25.57it/s, loss=0.571]
Epoch 5 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 25.57it/s, loss=0.572]
Epoch 5 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 25.80it/s, loss=0.572]
Epoch 5 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 25.80it/s, loss=0.574]
Epoch 5 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 25.80it/s, loss=0.576]
Epoch 5 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 25.80it/s, loss=0.575]
Epoch 5 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.19it/s, loss=0.575]
Epoch 5 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.19it/s, loss=0.575]
Epoch 5 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.19it/s, loss=0.574]
Epoch 5 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.19it/s, loss=0.573]
Epoch 5 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.46it/s, loss=0.573]
Epoch 5 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.46it/s, loss=0.572]
Epoch 5 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.46it/s, loss=0.575]
Epoch 5 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.46it/s, loss=0.572]
Epoch 5 [Train]: 81%|████████ | 104/129 [00:03<00:00, 27.16it/s, loss=0.572]
Epoch 5 [Train]: 81%|████████ | 104/129 [00:03<00:00, 27.16it/s, loss=0.572]
Epoch 5 [Train]: 81%|████████ | 104/129 [00:03<00:00, 27.16it/s, loss=0.572]
Epoch 5 [Train]: 81%|████████ | 104/129 [00:04<00:00, 27.16it/s, loss=0.575]
Epoch 5 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.44it/s, loss=0.575]
Epoch 5 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.44it/s, loss=0.573]
Epoch 5 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.44it/s, loss=0.572]
Epoch 5 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.44it/s, loss=0.572]
Epoch 5 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.77it/s, loss=0.572]
Epoch 5 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.77it/s, loss=0.572]
Epoch 5 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.77it/s, loss=0.573]
Epoch 5 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.77it/s, loss=0.572]
Epoch 5 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.76it/s, loss=0.572]
Epoch 5 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.76it/s, loss=0.57]
Epoch 5 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.76it/s, loss=0.569]
Epoch 5 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.76it/s, loss=0.57]
Epoch 5 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.52it/s, loss=0.57]
Epoch 5 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.52it/s, loss=0.57]
Epoch 5 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.52it/s, loss=0.57]
Epoch 5 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.52it/s, loss=0.569]
Epoch 5 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.75it/s, loss=0.569]
Epoch 5 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.75it/s, loss=0.569]
Epoch 5 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.75it/s, loss=0.571]
Epoch 5 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.75it/s, loss=0.571]
Epoch 5 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.33it/s, loss=0.571]
Epoch 5 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.33it/s, loss=0.57]
Epoch 5 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.33it/s, loss=0.57]
Epoch 5 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.33it/s, loss=0.569]
Epoch 5 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.90it/s, loss=0.569]
Epoch 5 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.90it/s, loss=0.568]
Epoch 5 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.90it/s, loss=0.567]
Epoch 5 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.90it/s, loss=0.567]
Epoch 5 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 26.81it/s, loss=0.567]
Epoch 5 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 26.81it/s, loss=0.566]
2026-08-07 06:50:21.421 | INFO  | __main__:pretrain:180 - Epoch 5/50 | Train Loss: 0.5664 | Val Loss: 0.6741
2026-08-07 06:50:21.430 | INFO  | __main__:pretrain:196 -  -> New best model (val_loss=0.6741)
Epoch 6 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 6 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.685]
Epoch 6 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.584]
Epoch 6 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.525]
Epoch 6 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.561]
Epoch 6 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.84it/s, loss=0.561]
Epoch 6 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.84it/s, loss=0.512]
Epoch 6 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.84it/s, loss=0.484]
Epoch 6 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.84it/s, loss=0.475]
Epoch 6 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.84it/s, loss=0.464]
Epoch 6 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.23it/s, loss=0.464]
Epoch 6 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.23it/s, loss=0.489]
Epoch 6 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.23it/s, loss=0.484]
Epoch 6 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.23it/s, loss=0.49]
Epoch 6 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.73it/s, loss=0.49]
Epoch 6 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.73it/s, loss=0.48]
Epoch 6 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.73it/s, loss=0.493]
Epoch 6 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.73it/s, loss=0.491]
Epoch 6 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.96it/s, loss=0.491]
Epoch 6 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.96it/s, loss=0.493]
Epoch 6 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.96it/s, loss=0.495]
Epoch 6 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.96it/s, loss=0.514]
Epoch 6 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.10it/s, loss=0.514]
Epoch 6 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.10it/s, loss=0.527]
Epoch 6 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.10it/s, loss=0.542]
Epoch 6 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.10it/s, loss=0.539]
Epoch 6 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 27.16it/s, loss=0.539]
Epoch 6 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 27.16it/s, loss=0.535]
Epoch 6 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 27.16it/s, loss=0.535]
Epoch 6 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 27.16it/s, loss=0.532]
Epoch 6 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.05it/s, loss=0.532]
Epoch 6 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.05it/s, loss=0.532]
Epoch 6 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.05it/s, loss=0.543]
Epoch 6 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.05it/s, loss=0.544]
Epoch 6 [Train]: 20%|██ | 26/129 [00:00<00:03, 27.13it/s, loss=0.544]
Epoch 6 [Train]: 20%|██ | 26/129 [00:00<00:03, 27.13it/s, loss=0.548]
Epoch 6 [Train]: 20%|██ | 26/129 [00:01<00:03, 27.13it/s, loss=0.546]
Epoch 6 [Train]: 20%|██ | 26/129 [00:01<00:03, 27.13it/s, loss=0.545]
Epoch 6 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 27.56it/s, loss=0.545]
Epoch 6 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 27.56it/s, loss=0.544]
Epoch 6 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 27.56it/s, loss=0.545]
Epoch 6 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 27.56it/s, loss=0.541]
Epoch 6 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 27.58it/s, loss=0.541]
Epoch 6 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 27.58it/s, loss=0.538]
Epoch 6 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 27.58it/s, loss=0.534]
Epoch 6 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 27.58it/s, loss=0.546]
Epoch 6 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.81it/s, loss=0.546]
Epoch 6 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.81it/s, loss=0.548]
Epoch 6 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.81it/s, loss=0.56]
Epoch 6 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.81it/s, loss=0.565]
Epoch 6 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.65it/s, loss=0.565]
Epoch 6 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.65it/s, loss=0.559]
Epoch 6 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.65it/s, loss=0.556]
Epoch 6 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.65it/s, loss=0.554]
Epoch 6 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.78it/s, loss=0.554]
Epoch 6 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.78it/s, loss=0.55]
Epoch 6 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.78it/s, loss=0.548]
Epoch 6 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.78it/s, loss=0.548]
Epoch 6 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.83it/s, loss=0.548]
Epoch 6 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.83it/s, loss=0.549]
Epoch 6 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.83it/s, loss=0.549]
Epoch 6 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.83it/s, loss=0.552]
Epoch 6 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 27.13it/s, loss=0.552]
Epoch 6 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 27.13it/s, loss=0.549]
Epoch 6 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 27.13it/s, loss=0.549]
Epoch 6 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 27.13it/s, loss=0.555]
Epoch 6 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.25it/s, loss=0.555]
Epoch 6 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.25it/s, loss=0.552]
Epoch 6 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.25it/s, loss=0.55]
Epoch 6 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.25it/s, loss=0.549]
Epoch 6 [Train]: 41%|████ | 53/129 [00:01<00:02, 27.08it/s, loss=0.549]
Epoch 6 [Train]: 41%|████ | 53/129 [00:01<00:02, 27.08it/s, loss=0.548]
Epoch 6 [Train]: 41%|████ | 53/129 [00:02<00:02, 27.08it/s, loss=0.55]
Epoch 6 [Train]: 41%|████ | 53/129 [00:02<00:02, 27.08it/s, loss=0.55]
Epoch 6 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.10it/s, loss=0.55]
Epoch 6 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.10it/s, loss=0.551]
Epoch 6 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.10it/s, loss=0.55]
Epoch 6 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 27.10it/s, loss=0.548]
Epoch 6 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.19it/s, loss=0.548]
Epoch 6 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.19it/s, loss=0.552]
Epoch 6 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.19it/s, loss=0.554]
Epoch 6 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 27.19it/s, loss=0.552]
Epoch 6 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.19it/s, loss=0.552]
Epoch 6 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.19it/s, loss=0.556]
Epoch 6 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.19it/s, loss=0.556]
Epoch 6 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.19it/s, loss=0.554]
Epoch 6 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.21it/s, loss=0.554]
Epoch 6 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.21it/s, loss=0.552]
Epoch 6 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.21it/s, loss=0.552]
Epoch 6 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.21it/s, loss=0.55]
Epoch 6 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.10it/s, loss=0.55]
Epoch 6 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.10it/s, loss=0.551]
Epoch 6 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.10it/s, loss=0.547]
Epoch 6 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.10it/s, loss=0.547]
Epoch 6 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 27.43it/s, loss=0.547]
Epoch 6 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 27.43it/s, loss=0.545]
Epoch 6 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 27.43it/s, loss=0.544]
Epoch 6 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 27.43it/s, loss=0.546]
Epoch 6 [Train]: 57%|█████▋ | 74/129 [00:02<00:01, 27.66it/s, loss=0.546]
Epoch 6 [Train]: 57%|█████▋ | 74/129 [00:02<00:01, 27.66it/s, loss=0.544]
Epoch 6 [Train]: 57%|█████▋ | 74/129 [00:02<00:01, 27.66it/s, loss=0.543]
Epoch 6 [Train]: 57%|█████▋ | 74/129 [00:02<00:01, 27.66it/s, loss=0.542]
Epoch 6 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 27.38it/s, loss=0.542]
Epoch 6 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 27.38it/s, loss=0.542]
Epoch 6 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 27.38it/s, loss=0.54]
Epoch 6 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 27.38it/s, loss=0.541]
Epoch 6 [Train]: 62%|██████▏ | 80/129 [00:02<00:01, 26.70it/s, loss=0.541]
Epoch 6 [Train]: 62%|██████▏ | 80/129 [00:02<00:01, 26.70it/s, loss=0.543]
Epoch 6 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.70it/s, loss=0.542]
Epoch 6 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.70it/s, loss=0.54]
Epoch 6 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.94it/s, loss=0.54]
Epoch 6 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.94it/s, loss=0.538]
Epoch 6 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.94it/s, loss=0.538]
Epoch 6 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.94it/s, loss=0.537]
Epoch 6 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.69it/s, loss=0.537]
Epoch 6 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.69it/s, loss=0.535]
Epoch 6 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.69it/s, loss=0.535]
Epoch 6 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.69it/s, loss=0.534]
Epoch 6 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.42it/s, loss=0.534]
Epoch 6 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.42it/s, loss=0.532]
Epoch 6 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.42it/s, loss=0.534]
Epoch 6 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 26.42it/s, loss=0.534]
Epoch 6 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 26.26it/s, loss=0.534]
Epoch 6 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 26.26it/s, loss=0.536]
Epoch 6 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 26.26it/s, loss=0.535]
Epoch 6 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 26.26it/s, loss=0.534]
Epoch 6 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.03it/s, loss=0.534]
Epoch 6 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.03it/s, loss=0.535]
Epoch 6 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.03it/s, loss=0.535]
Epoch 6 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.03it/s, loss=0.535]
Epoch 6 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.94it/s, loss=0.535]
Epoch 6 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.94it/s, loss=0.534]
Epoch 6 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.94it/s, loss=0.533]
Epoch 6 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.94it/s, loss=0.534]
Epoch 6 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.19it/s, loss=0.534]
Epoch 6 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.19it/s, loss=0.534]
Epoch 6 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.19it/s, loss=0.533]
Epoch 6 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.19it/s, loss=0.534]
Epoch 6 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.89it/s, loss=0.534]
Epoch 6 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.89it/s, loss=0.532]
Epoch 6 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.89it/s, loss=0.532]
Epoch 6 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.89it/s, loss=0.536]
Epoch 6 [Train]: 83%|████████▎ | 107/129 [00:03<00:00, 26.21it/s, loss=0.536]
Epoch 6 [Train]: 83%|████████▎ | 107/129 [00:03<00:00, 26.21it/s, loss=0.536]
Epoch 6 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.21it/s, loss=0.535]
Epoch 6 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.21it/s, loss=0.537]
Epoch 6 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.05it/s, loss=0.537]
Epoch 6 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.05it/s, loss=0.539]
Epoch 6 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.05it/s, loss=0.538]
Epoch 6 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.05it/s, loss=0.537]
Epoch 6 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.04it/s, loss=0.537]
Epoch 6 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.04it/s, loss=0.538]
Epoch 6 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.04it/s, loss=0.54]
Epoch 6 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.04it/s, loss=0.539]
Epoch 6 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.39it/s, loss=0.539]
Epoch 6 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.39it/s, loss=0.541]
Epoch 6 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.39it/s, loss=0.543]
Epoch 6 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.39it/s, loss=0.543]
Epoch 6 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.73it/s, loss=0.543]
Epoch 6 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.73it/s, loss=0.542]
Epoch 6 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.73it/s, loss=0.542]
Epoch 6 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.73it/s, loss=0.543]
Epoch 6 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 28.18it/s, loss=0.543]
Epoch 6 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 28.18it/s, loss=0.545]
Epoch 6 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 28.18it/s, loss=0.546]
Epoch 6 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 28.18it/s, loss=0.546]
Epoch 6 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 28.16it/s, loss=0.546]
Epoch 6 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 28.16it/s, loss=0.546]
Epoch 6 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 28.16it/s, loss=0.547]
Epoch 6 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 28.16it/s, loss=0.548]
Epoch 6 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 28.46it/s, loss=0.548]
Epoch 6 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 28.46it/s, loss=0.548]
2026-08-07 06:50:26.315 | INFO  | __main__:pretrain:180 - Epoch 6/50 | Train Loss: 0.5478 | Val Loss: 0.6921
Epoch 7 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 7 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.385]
Epoch 7 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.459]
Epoch 7 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.461]
Epoch 7 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.465]
Epoch 7 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.05it/s, loss=0.465]
Epoch 7 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.05it/s, loss=0.428]
Epoch 7 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.05it/s, loss=0.437]
Epoch 7 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.05it/s, loss=0.429]
Epoch 7 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.05it/s, loss=0.429]
Epoch 7 [Train]: 6%|▌ | 8/129 [00:00<00:04, 26.79it/s, loss=0.429]
Epoch 7 [Train]: 6%|▌ | 8/129 [00:00<00:04, 26.79it/s, loss=0.446]
Epoch 7 [Train]: 6%|▌ | 8/129 [00:00<00:04, 26.79it/s, loss=0.441]
Epoch 7 [Train]: 6%|▌ | 8/129 [00:00<00:04, 26.79it/s, loss=0.43]
Epoch 7 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.33it/s, loss=0.43]
Epoch 7 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.33it/s, loss=0.443]
Epoch 7 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.33it/s, loss=0.445]
Epoch 7 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.33it/s, loss=0.443]
Epoch 7 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.29it/s, loss=0.443]
Epoch 7 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.29it/s, loss=0.442]
Epoch 7 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.29it/s, loss=0.45]
Epoch 7 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.29it/s, loss=0.456]
Epoch 7 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.36it/s, loss=0.456]
Epoch 7 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.36it/s, loss=0.457]
Epoch 7 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.36it/s, loss=0.455]
Epoch 7 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.36it/s, loss=0.45]
Epoch 7 [Train]: 16%|█▌ | 20/129 [00:00<00:03, 27.77it/s, loss=0.45]
Epoch 7 [Train]: 16%|█▌ | 20/129 [00:00<00:03, 27.77it/s, loss=0.441]
Epoch 7 [Train]: 16%|█▌ | 20/129 [00:00<00:03, 27.77it/s, loss=0.437]
Epoch 7 [Train]: 16%|█▌ | 20/129 [00:00<00:03, 27.77it/s, loss=0.438]
Epoch 7 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 26.75it/s, loss=0.438]
Epoch 7 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 26.75it/s, loss=0.436]
Epoch 7 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 26.75it/s, loss=0.435]
Epoch 7 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 26.75it/s, loss=0.432]
Epoch 7 [Train]: 20%|██ | 26/129 [00:00<00:03, 26.20it/s, loss=0.432]
Epoch 7 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.20it/s, loss=0.441]
Epoch 7 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.20it/s, loss=0.452]
Epoch 7 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.20it/s, loss=0.456]
Epoch 7 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 25.75it/s, loss=0.456]
Epoch 7 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 25.75it/s, loss=0.461]
Epoch 7 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 25.75it/s, loss=0.461]
Epoch 7 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 25.75it/s, loss=0.464]
Epoch 7 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 25.51it/s, loss=0.464]
Epoch 7 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 25.51it/s, loss=0.463]
Epoch 7 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 25.51it/s, loss=0.465]
Epoch 7 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 25.51it/s, loss=0.465]
Epoch 7 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 25.89it/s, loss=0.465]
Epoch 7 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 25.89it/s, loss=0.463]
Epoch 7 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 25.89it/s, loss=0.462]
Epoch 7 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 25.89it/s, loss=0.483]
Epoch 7 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 25.73it/s, loss=0.483]
Epoch 7 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 25.73it/s, loss=0.483]
Epoch 7 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 25.73it/s, loss=0.485]
Epoch 7 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 25.73it/s, loss=0.482]
Epoch 7 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 25.93it/s, loss=0.482]
Epoch 7 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 25.93it/s, loss=0.489]
Epoch 7 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 25.93it/s, loss=0.486]
Epoch 7 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 25.93it/s, loss=0.485]
Epoch 7 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 25.46it/s, loss=0.485]
Epoch 7 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 25.46it/s, loss=0.485]
Epoch 7 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 25.46it/s, loss=0.485]
Epoch 7 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 25.46it/s, loss=0.486]
Epoch 7 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 25.50it/s, loss=0.486]
Epoch 7 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 25.50it/s, loss=0.486]
Epoch 7 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 25.50it/s, loss=0.487]
Epoch 7 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 25.50it/s, loss=0.491]
Epoch 7 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 26.00it/s, loss=0.491]
Epoch 7 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 26.00it/s, loss=0.489]
Epoch 7 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 26.00it/s, loss=0.494]
Epoch 7 [Train]: 39%|███▉ | 50/129 [00:02<00:03, 26.00it/s, loss=0.496]
Epoch 7 [Train]: 41%|████ | 53/129 [00:02<00:02, 25.69it/s, loss=0.496]
Epoch 7 [Train]: 41%|████ | 53/129 [00:02<00:02, 25.69it/s, loss=0.499]
Epoch 7 [Train]: 41%|████ | 53/129 [00:02<00:02, 25.69it/s, loss=0.499]
Epoch 7 [Train]: 41%|████ | 53/129 [00:02<00:02, 25.69it/s, loss=0.5]
Epoch 7 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.11it/s, loss=0.5]
Epoch 7 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.11it/s, loss=0.501]
Epoch 7 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.11it/s, loss=0.499]
Epoch 7 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.11it/s, loss=0.501]
Epoch 7 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.86it/s, loss=0.501]
Epoch 7 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.86it/s, loss=0.498]
Epoch 7 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.86it/s, loss=0.505]
Epoch 7 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.86it/s, loss=0.505]
Epoch 7 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.08it/s, loss=0.505]
Epoch 7 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.08it/s, loss=0.502]
Epoch 7 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.08it/s, loss=0.512]
Epoch 7 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 27.08it/s, loss=0.514]
Epoch 7 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.14it/s, loss=0.514]
Epoch 7 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.14it/s, loss=0.519]
Epoch 7 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.14it/s, loss=0.519]
Epoch 7 [Train]: 50%|█████ | 65/129 [00:02<00:02, 27.14it/s, loss=0.519]
Epoch 7 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.93it/s, loss=0.519]
Epoch 7 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.93it/s, loss=0.519]
Epoch 7 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.93it/s, loss=0.518]
Epoch 7 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.93it/s, loss=0.52]
Epoch 7 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.26it/s, loss=0.52]
Epoch 7 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.26it/s, loss=0.522]
Epoch 7 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.26it/s, loss=0.521]
Epoch 7 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.26it/s, loss=0.52]
Epoch 7 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.60it/s, loss=0.52]
Epoch 7 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.60it/s, loss=0.519]
Epoch 7 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.60it/s, loss=0.517]
Epoch 7 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.60it/s, loss=0.516]
Epoch 7 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.63it/s, loss=0.516]
Epoch 7 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.63it/s, loss=0.515]
Epoch 7 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.63it/s, loss=0.514]
Epoch 7 [Train]: 60%|█████▉ | 77/129 [00:03<00:01, 26.63it/s, loss=0.515]
Epoch 7 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.21it/s, loss=0.515]
Epoch 7 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.21it/s, loss=0.515]
Epoch 7 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.21it/s, loss=0.517]
Epoch 7 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.21it/s, loss=0.518]
Epoch 7 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.49it/s, loss=0.518]
Epoch 7 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.49it/s, loss=0.52]
Epoch 7 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.49it/s, loss=0.524]
Epoch 7 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.49it/s, loss=0.523]
Epoch 7 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 25.95it/s, loss=0.523]
Epoch 7 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 25.95it/s, loss=0.523]
Epoch 7 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 25.95it/s, loss=0.522]
Epoch 7 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 25.95it/s, loss=0.523]
Epoch 7 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 25.99it/s, loss=0.523]
Epoch 7 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 25.99it/s, loss=0.523]
Epoch 7 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 25.99it/s, loss=0.522]
Epoch 7 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 25.99it/s, loss=0.523]
Epoch 7 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 25.93it/s, loss=0.523]
Epoch 7 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 25.93it/s, loss=0.528]
Epoch 7 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 25.93it/s, loss=0.528]
Epoch 7 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 25.93it/s, loss=0.528]
Epoch 7 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.26it/s, loss=0.528]
Epoch 7 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.26it/s, loss=0.527]
Epoch 7 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.26it/s, loss=0.528]
Epoch 7 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.26it/s, loss=0.527]
Epoch 7 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.60it/s, loss=0.527]
Epoch 7 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.60it/s, loss=0.527]
Epoch 7 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.60it/s, loss=0.526]
Epoch 7 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.60it/s, loss=0.525]
Epoch 7 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.12it/s, loss=0.525]
Epoch 7 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.12it/s, loss=0.525]
Epoch 7 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.12it/s, loss=0.527]
Epoch 7 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.12it/s, loss=0.525]
Epoch 7 [Train]: 81%|████████ | 104/129 [00:03<00:00, 27.29it/s, loss=0.525]
Epoch 7 [Train]: 81%|████████ | 104/129 [00:03<00:00, 27.29it/s, loss=0.523]
Epoch 7 [Train]: 81%|████████ | 104/129 [00:04<00:00, 27.29it/s, loss=0.522]
Epoch 7 [Train]: 81%|████████ | 104/129 [00:04<00:00, 27.29it/s, loss=0.522]
Epoch 7 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.39it/s, loss=0.522]
Epoch 7 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.39it/s, loss=0.523]
Epoch 7 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.39it/s, loss=0.525]
Epoch 7 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.39it/s, loss=0.524]
Epoch 7 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.88it/s, loss=0.524]
Epoch 7 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.88it/s, loss=0.526]
Epoch 7 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.88it/s, loss=0.526]
Epoch 7 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.88it/s, loss=0.524]
Epoch 7 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 25.90it/s, loss=0.524]
Epoch 7 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 25.90it/s, loss=0.524]
Epoch 7 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 25.90it/s, loss=0.522]
Epoch 7 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 25.90it/s, loss=0.522]
Epoch 7 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.13it/s, loss=0.522]
Epoch 7 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.13it/s, loss=0.523]
Epoch 7 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.13it/s, loss=0.523]
Epoch 7 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.13it/s, loss=0.522]
Epoch 7 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 25.97it/s, loss=0.522]
Epoch 7 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 25.97it/s, loss=0.521]
Epoch 7 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 25.97it/s, loss=0.52]
Epoch 7 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 25.97it/s, loss=0.52]
Epoch 7 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 26.79it/s, loss=0.52]
Epoch 7 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 26.79it/s, loss=0.519]
Epoch 7 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 26.79it/s, loss=0.52]
Epoch 7 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 26.79it/s, loss=0.52]
Epoch 7 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.41it/s, loss=0.52]
Epoch 7 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.41it/s, loss=0.52]
Epoch 7 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.41it/s, loss=0.523]
Epoch 7 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.41it/s, loss=0.524]
Epoch 7 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 27.00it/s, loss=0.524]
Epoch 7 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 27.00it/s, loss=0.523]
2026-08-07 06:50:31.353 | INFO  | __main__:pretrain:180 - Epoch 7/50 | Train Loss: 0.5226 | Val Loss: 0.6984
Epoch 8 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 8 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.325]
Epoch 8 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.486]
Epoch 8 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.547]
Epoch 8 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.35it/s, loss=0.547]
Epoch 8 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.35it/s, loss=0.501]
Epoch 8 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.35it/s, loss=0.496]
Epoch 8 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.35it/s, loss=0.509]
Epoch 8 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.67it/s, loss=0.509]
Epoch 8 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.67it/s, loss=0.492]
Epoch 8 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.67it/s, loss=0.499]
Epoch 8 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.67it/s, loss=0.496]
Epoch 8 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.83it/s, loss=0.496]
Epoch 8 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.83it/s, loss=0.48]
Epoch 8 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.83it/s, loss=0.482]
Epoch 8 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.83it/s, loss=0.465]
Epoch 8 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.31it/s, loss=0.465]
Epoch 8 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.31it/s, loss=0.465]
Epoch 8 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.31it/s, loss=0.471]
Epoch 8 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.31it/s, loss=0.472]
Epoch 8 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.22it/s, loss=0.472]
Epoch 8 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.22it/s, loss=0.475]
Epoch 8 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.22it/s, loss=0.461]
Epoch 8 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.22it/s, loss=0.465]
Epoch 8 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.03it/s, loss=0.465]
Epoch 8 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.03it/s, loss=0.47]
Epoch 8 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.03it/s, loss=0.469]
Epoch 8 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.03it/s, loss=0.463]
Epoch 8 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.74it/s, loss=0.463]
Epoch 8 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.74it/s, loss=0.47]
Epoch 8 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.74it/s, loss=0.467]
Epoch 8 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.74it/s, loss=0.468]
Epoch 8 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.91it/s, loss=0.468]
Epoch 8 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.91it/s, loss=0.475]
Epoch 8 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.91it/s, loss=0.474]
Epoch 8 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.91it/s, loss=0.474]
Epoch 8 [Train]: 21%|██ | 27/129 [00:00<00:03, 27.10it/s, loss=0.474]
Epoch 8 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.10it/s, loss=0.473]
Epoch 8 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.10it/s, loss=0.468]
Epoch 8 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.10it/s, loss=0.47]
Epoch 8 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.33it/s, loss=0.47]
Epoch 8 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.33it/s, loss=0.477]
Epoch 8 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.33it/s, loss=0.476]
Epoch 8 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.33it/s, loss=0.484]
Epoch 8 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.49it/s, loss=0.484]
Epoch 8 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.49it/s, loss=0.486]
Epoch 8 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.49it/s, loss=0.485]
Epoch 8 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.49it/s, loss=0.491]
Epoch 8 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.01it/s, loss=0.491]
Epoch 8 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.01it/s, loss=0.496]
Epoch 8 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.01it/s, loss=0.502]
Epoch 8 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.01it/s, loss=0.502]
Epoch 8 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.53it/s, loss=0.502]
Epoch 8 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.53it/s, loss=0.499]
Epoch 8 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.53it/s, loss=0.502]
Epoch 8 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.53it/s, loss=0.498]
Epoch 8 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.74it/s, loss=0.498]
Epoch 8 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.74it/s, loss=0.501]
Epoch 8 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.74it/s, loss=0.497]
Epoch 8 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.74it/s, loss=0.495]
Epoch 8 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.78it/s, loss=0.495]
Epoch 8 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.78it/s, loss=0.493]
Epoch 8 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.78it/s, loss=0.492]
Epoch 8 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.78it/s, loss=0.496]
Epoch 8 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.84it/s, loss=0.496]
Epoch 8 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.84it/s, loss=0.496]
Epoch 8 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.84it/s, loss=0.494]
Epoch 8 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.84it/s, loss=0.491]
Epoch 8 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.43it/s, loss=0.491]
Epoch 8 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.43it/s, loss=0.494]
Epoch 8 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.43it/s, loss=0.494]
Epoch 8 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.43it/s, loss=0.494]
Epoch 8 [Train]: 42%|████▏ | 54/129 [00:01<00:02, 26.79it/s, loss=0.494]
Epoch 8 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.79it/s, loss=0.496]
Epoch 8 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.79it/s, loss=0.496]
Epoch 8 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.79it/s, loss=0.494]
Epoch 8 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.85it/s, loss=0.494]
Epoch 8 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.85it/s, loss=0.492]
Epoch 8 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.85it/s, loss=0.492]
Epoch 8 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.85it/s, loss=0.494]
Epoch 8 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.29it/s, loss=0.494]
Epoch 8 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.29it/s, loss=0.494]
Epoch 8 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.29it/s, loss=0.492]
Epoch 8 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.29it/s, loss=0.492]
Epoch 8 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.51it/s, loss=0.492]
Epoch 8 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.51it/s, loss=0.492]
Epoch 8 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.51it/s, loss=0.493]
Epoch 8 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.51it/s, loss=0.493]
Epoch 8 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.78it/s, loss=0.493]
Epoch 8 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.78it/s, loss=0.492]
Epoch 8 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.78it/s, loss=0.491]
Epoch 8 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.78it/s, loss=0.492]
Epoch 8 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.94it/s, loss=0.492]
Epoch 8 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.94it/s, loss=0.492]
Epoch 8 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.94it/s, loss=0.49]
Epoch 8 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.94it/s, loss=0.494]
Epoch 8 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.84it/s, loss=0.494]
Epoch 8 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.84it/s, loss=0.496]
Epoch 8 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.84it/s, loss=0.494]
Epoch 8 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.84it/s, loss=0.493]
Epoch 8 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.03it/s, loss=0.493]
Epoch 8 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.03it/s, loss=0.493]
Epoch 8 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.03it/s, loss=0.493]
Epoch 8 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.03it/s, loss=0.49]
Epoch 8 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.17it/s, loss=0.49]
Epoch 8 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.17it/s, loss=0.489]
Epoch 8 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.17it/s, loss=0.49]
Epoch 8 [Train]: 60%|██████ | 78/129 [00:03<00:01, 26.17it/s, loss=0.495]
Epoch 8 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.46it/s, loss=0.495]
Epoch 8 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.46it/s, loss=0.494]
Epoch 8 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.46it/s, loss=0.493]
Epoch 8 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.46it/s, loss=0.494]
Epoch 8 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.82it/s, loss=0.494]
Epoch 8 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.82it/s, loss=0.498]
Epoch 8 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.82it/s, loss=0.498]
Epoch 8 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.82it/s, loss=0.497]
Epoch 8 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.35it/s, loss=0.497]
Epoch 8 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.35it/s, loss=0.496]
Epoch 8 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.35it/s, loss=0.5]
Epoch 8 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.35it/s, loss=0.502]
Epoch 8 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.41it/s, loss=0.502]
Epoch 8 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.41it/s, loss=0.501]
Epoch 8 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.41it/s, loss=0.507]
Epoch 8 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.41it/s, loss=0.507]
Epoch 8 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.44it/s, loss=0.507]
Epoch 8 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.44it/s, loss=0.508]
Epoch 8 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.44it/s, loss=0.51]
Epoch 8 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.44it/s, loss=0.509]
Epoch 8 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.37it/s, loss=0.509]
Epoch 8 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.37it/s, loss=0.509]
Epoch 8 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.37it/s, loss=0.509]
Epoch 8 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.37it/s, loss=0.508]
Epoch 8 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.08it/s, loss=0.508]
Epoch 8 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.08it/s, loss=0.507]
Epoch 8 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.08it/s, loss=0.507]
Epoch 8 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.08it/s, loss=0.507]
Epoch 8 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.09it/s, loss=0.507]
Epoch 8 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.09it/s, loss=0.506]
Epoch 8 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.09it/s, loss=0.505]
Epoch 8 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.09it/s, loss=0.505]
Epoch 8 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 26.48it/s, loss=0.505]
Epoch 8 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 26.48it/s, loss=0.507]
Epoch 8 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 26.48it/s, loss=0.508]
Epoch 8 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 26.48it/s, loss=0.508]
Epoch 8 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.44it/s, loss=0.508]
Epoch 8 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.44it/s, loss=0.506]
Epoch 8 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.44it/s, loss=0.506]
Epoch 8 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.44it/s, loss=0.507]
Epoch 8 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.72it/s, loss=0.507]
Epoch 8 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.72it/s, loss=0.506]
Epoch 8 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.72it/s, loss=0.509]
Epoch 8 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.72it/s, loss=0.508]
Epoch 8 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.05it/s, loss=0.508]
Epoch 8 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.05it/s, loss=0.509]
Epoch 8 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.05it/s, loss=0.508]
Epoch 8 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.05it/s, loss=0.51]
Epoch 8 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.89it/s, loss=0.51]
Epoch 8 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.89it/s, loss=0.51]
Epoch 8 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.89it/s, loss=0.511]
Epoch 8 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.89it/s, loss=0.51]
Epoch 8 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.96it/s, loss=0.51]
Epoch 8 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.96it/s, loss=0.511]
Epoch 8 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.96it/s, loss=0.509]
Epoch 8 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.96it/s, loss=0.51]
Epoch 8 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.19it/s, loss=0.51]
Epoch 8 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.19it/s, loss=0.509]
Epoch 8 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.19it/s, loss=0.509]
Epoch 8 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.19it/s, loss=0.508]
Epoch 8 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.49it/s, loss=0.508]
Epoch 8 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.49it/s, loss=0.507]
Epoch 8 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.49it/s, loss=0.507]
Epoch 8 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.49it/s, loss=0.507]
Epoch 8 [Train]: 100%|██████████| 129/129 [00:04<00:00, 27.64it/s, loss=0.507]
2026-08-07 06:50:36.286 | INFO  | __main__:pretrain:180 - Epoch 8/50 | Train Loss: 0.5069 | Val Loss: 0.6875
Epoch 9 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 9 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.32]
Epoch 9 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.455]
Epoch 9 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.407]
Epoch 9 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.394]
Epoch 9 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.24it/s, loss=0.394]
Epoch 9 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.24it/s, loss=0.42]
Epoch 9 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.24it/s, loss=0.427]
Epoch 9 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.24it/s, loss=0.438]
Epoch 9 [Train]: 3%|▎ | 4/129 [00:00<00:04, 30.24it/s, loss=0.444]
Epoch 9 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.63it/s, loss=0.444]
Epoch 9 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.63it/s, loss=0.428]
Epoch 9 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.63it/s, loss=0.43]
Epoch 9 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.63it/s, loss=0.434]
Epoch 9 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.42it/s, loss=0.434]
Epoch 9 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.42it/s, loss=0.426]
Epoch 9 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.42it/s, loss=0.438]
Epoch 9 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.42it/s, loss=0.437]
Epoch 9 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.89it/s, loss=0.437]
Epoch 9 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.89it/s, loss=0.434]
Epoch 9 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.89it/s, loss=0.435]
Epoch 9 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.89it/s, loss=0.431]
Epoch 9 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.69it/s, loss=0.431]
Epoch 9 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.69it/s, loss=0.444]
Epoch 9 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.69it/s, loss=0.459]
Epoch 9 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.69it/s, loss=0.45]
Epoch 9 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 27.19it/s, loss=0.45]
Epoch 9 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 27.19it/s, loss=0.458]
Epoch 9 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 27.19it/s, loss=0.457]
Epoch 9 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 27.19it/s, loss=0.452]
Epoch 9 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.27it/s, loss=0.452]
Epoch 9 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.27it/s, loss=0.451]
Epoch 9 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.27it/s, loss=0.451]
Epoch 9 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.27it/s, loss=0.453]
Epoch 9 [Train]: 20%|██ | 26/129 [00:00<00:03, 26.50it/s, loss=0.453]
Epoch 9 [Train]: 20%|██ | 26/129 [00:00<00:03, 26.50it/s, loss=0.452]
Epoch 9 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.50it/s, loss=0.457]
Epoch 9 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.50it/s, loss=0.458]
Epoch 9 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.59it/s, loss=0.458]
Epoch 9 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.59it/s, loss=0.455]
Epoch 9 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.59it/s, loss=0.456]
Epoch 9 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.59it/s, loss=0.453]
Epoch 9 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.87it/s, loss=0.453]
Epoch 9 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.87it/s, loss=0.454]
Epoch 9 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.87it/s, loss=0.452]
Epoch 9 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.87it/s, loss=0.45]
Epoch 9 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.80it/s, loss=0.45]
Epoch 9 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.80it/s, loss=0.451]
Epoch 9 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.80it/s, loss=0.451]
Epoch 9 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.80it/s, loss=0.451]
Epoch 9 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.88it/s, loss=0.451]
Epoch 9 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.88it/s, loss=0.456]
Epoch 9 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.88it/s, loss=0.457]
Epoch 9 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.88it/s, loss=0.461]
Epoch 9 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.38it/s, loss=0.461]
Epoch 9 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.38it/s, loss=0.458]
Epoch 9 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.38it/s, loss=0.458]
Epoch 9 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.38it/s, loss=0.458]
Epoch 9 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 25.83it/s, loss=0.458]
Epoch 9 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 25.83it/s, loss=0.457]
Epoch 9 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 25.83it/s, loss=0.459]
Epoch 9 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 25.83it/s, loss=0.457]
Epoch 9 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.07it/s, loss=0.457]
Epoch 9 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.07it/s, loss=0.458]
Epoch 9 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.07it/s, loss=0.46]
Epoch 9 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.07it/s, loss=0.462]
Epoch 9 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 25.90it/s, loss=0.462]
Epoch 9 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 25.90it/s, loss=0.458]
Epoch 9 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 25.90it/s, loss=0.456]
Epoch 9 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 25.90it/s, loss=0.456]
Epoch 9 [Train]: 41%|████ | 53/129 [00:01<00:02, 26.18it/s, loss=0.456]
Epoch 9 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.18it/s, loss=0.454]
Epoch 9 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.18it/s, loss=0.452]
Epoch 9 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.18it/s, loss=0.452]
Epoch 9 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 25.95it/s, loss=0.452]
Epoch 9 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 25.95it/s, loss=0.451]
Epoch 9 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 25.95it/s, loss=0.455]
Epoch 9 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 25.95it/s, loss=0.455]
Epoch 9 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.62it/s, loss=0.455]
Epoch 9 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.62it/s, loss=0.456]
Epoch 9 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.62it/s, loss=0.454]
Epoch 9 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.62it/s, loss=0.454]
Epoch 9 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.22it/s, loss=0.454]
Epoch 9 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.22it/s, loss=0.453]
Epoch 9 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.22it/s, loss=0.452]
Epoch 9 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.22it/s, loss=0.453]
Epoch 9 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.44it/s, loss=0.453]
Epoch 9 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.44it/s, loss=0.456]
Epoch 9 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.44it/s, loss=0.458]
Epoch 9 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.44it/s, loss=0.459]
Epoch 9 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.76it/s, loss=0.459]
Epoch 9 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.76it/s, loss=0.458]
Epoch 9 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.76it/s, loss=0.457]
Epoch 9 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.76it/s, loss=0.457]
Epoch 9 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 27.24it/s, loss=0.457]
Epoch 9 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 27.24it/s, loss=0.46]
Epoch 9 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 27.24it/s, loss=0.459]
Epoch 9 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 27.24it/s, loss=0.457]
Epoch 9 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.83it/s, loss=0.457]
Epoch 9 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.83it/s, loss=0.459]
Epoch 9 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.83it/s, loss=0.46]
Epoch 9 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.83it/s, loss=0.462]
Epoch 9 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.85it/s, loss=0.462]
Epoch 9 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.85it/s, loss=0.46]
Epoch 9 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.85it/s, loss=0.467]
Epoch 9 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.85it/s, loss=0.471]
Epoch 9 [Train]: 62%|██████▏ | 80/129 [00:02<00:01, 26.24it/s, loss=0.471]
Epoch 9 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.24it/s, loss=0.474]
Epoch 9 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.24it/s, loss=0.476]
Epoch 9 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.24it/s, loss=0.476]
Epoch 9 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.87it/s, loss=0.476]
Epoch 9 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.87it/s, loss=0.475]
Epoch 9 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.87it/s, loss=0.476]
Epoch 9 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.87it/s, loss=0.475]
Epoch 9 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.20it/s, loss=0.475]
Epoch 9 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.20it/s, loss=0.473]
Epoch 9 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.20it/s, loss=0.473]
Epoch 9 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.20it/s, loss=0.473]
Epoch 9 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.12it/s, loss=0.473]
Epoch 9 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.12it/s, loss=0.471]
Epoch 9 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.12it/s, loss=0.471]
Epoch 9 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.12it/s, loss=0.471]
Epoch 9 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.03it/s, loss=0.471]
Epoch 9 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.03it/s, loss=0.471]
Epoch 9 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.03it/s, loss=0.47]
Epoch 9 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.03it/s, loss=0.472]
Epoch 9 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.27it/s, loss=0.472]
Epoch 9 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.27it/s, loss=0.472]
Epoch 9 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.27it/s, loss=0.472]
Epoch 9 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.27it/s, loss=0.477]
Epoch 9 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.33it/s, loss=0.477]
Epoch 9 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.33it/s, loss=0.477]
Epoch 9 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.33it/s, loss=0.476]
Epoch 9 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 26.33it/s, loss=0.484]
Epoch 9 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.11it/s, loss=0.484]
Epoch 9 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.11it/s, loss=0.484]
Epoch 9 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.11it/s, loss=0.484]
Epoch 9 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.11it/s, loss=0.483]
Epoch 9 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.45it/s, loss=0.483]
Epoch 9 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.45it/s, loss=0.483]
Epoch 9 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.45it/s, loss=0.485]
Epoch 9 [Train]: 81%|████████ | 104/129 [00:04<00:00, 26.45it/s, loss=0.485]
Epoch 9 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.61it/s, loss=0.485]
Epoch 9 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.61it/s, loss=0.483]
Epoch 9 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.61it/s, loss=0.483]
Epoch 9 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.61it/s, loss=0.483]
Epoch 9 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.26it/s, loss=0.483]
Epoch 9 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.26it/s, loss=0.484]
Epoch 9 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.26it/s, loss=0.484]
Epoch 9 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 26.26it/s, loss=0.486]
Epoch 9 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.31it/s, loss=0.486]
Epoch 9 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.31it/s, loss=0.487]
Epoch 9 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.31it/s, loss=0.488]
Epoch 9 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.31it/s, loss=0.487]
Epoch 9 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 25.98it/s, loss=0.487]
Epoch 9 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 25.98it/s, loss=0.487]
Epoch 9 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 25.98it/s, loss=0.484]
Epoch 9 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 25.98it/s, loss=0.484]
Epoch 9 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.21it/s, loss=0.484]
Epoch 9 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.21it/s, loss=0.483]
Epoch 9 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.21it/s, loss=0.482]
Epoch 9 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.21it/s, loss=0.481]
Epoch 9 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 25.79it/s, loss=0.481]
Epoch 9 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 25.79it/s, loss=0.481]
Epoch 9 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 25.79it/s, loss=0.486]
Epoch 9 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 25.79it/s, loss=0.486]
Epoch 9 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.14it/s, loss=0.486]
Epoch 9 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.14it/s, loss=0.486]
Epoch 9 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.14it/s, loss=0.487]
Epoch 9 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.14it/s, loss=0.489]
Epoch 9 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 26.58it/s, loss=0.489]
Epoch 9 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 26.58it/s, loss=0.488]
2026-08-07 06:50:41.297 | INFO  | __main__:pretrain:180 - Epoch 9/50 | Train Loss: 0.4883 | Val Loss: 0.6951
Epoch 10 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 10 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.328]
Epoch 10 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.439]
Epoch 10 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.468]
Epoch 10 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.15it/s, loss=0.468]
Epoch 10 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.15it/s, loss=0.463]
Epoch 10 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.15it/s, loss=0.48]
Epoch 10 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.15it/s, loss=0.502]
Epoch 10 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.64it/s, loss=0.502]
Epoch 10 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.64it/s, loss=0.507]
Epoch 10 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.64it/s, loss=0.494]
Epoch 10 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.64it/s, loss=0.478]
Epoch 10 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.92it/s, loss=0.478]
Epoch 10 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.92it/s, loss=0.492]
Epoch 10 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.92it/s, loss=0.49]
Epoch 10 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.92it/s, loss=0.488]
Epoch 10 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.76it/s, loss=0.488]
Epoch 10 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.76it/s, loss=0.487]
Epoch 10 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.76it/s, loss=0.478]
Epoch 10 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.76it/s, loss=0.511]
Epoch 10 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.73it/s, loss=0.511]
Epoch 10 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.73it/s, loss=0.503]
Epoch 10 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.73it/s, loss=0.497]
Epoch 10 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.73it/s, loss=0.489]
Epoch 10 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.17it/s, loss=0.489]
Epoch 10 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.17it/s, loss=0.486]
Epoch 10 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.17it/s, loss=0.484]
Epoch 10 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.17it/s, loss=0.486]
Epoch 10 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.56it/s, loss=0.486]
Epoch 10 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.56it/s, loss=0.492]
Epoch 10 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.56it/s, loss=0.498]
Epoch 10 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.56it/s, loss=0.496]
Epoch 10 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.34it/s, loss=0.496]
Epoch 10 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.34it/s, loss=0.495]
Epoch 10 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.34it/s, loss=0.491]
Epoch 10 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.34it/s, loss=0.499]
Epoch 10 [Train]: 21%|██ | 27/129 [00:00<00:03, 27.26it/s, loss=0.499]
Epoch 10 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.26it/s, loss=0.503]
Epoch 10 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.26it/s, loss=0.504]
Epoch 10 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.26it/s, loss=0.507]
Epoch 10 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.55it/s, loss=0.507]
Epoch 10 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.55it/s, loss=0.504]
Epoch 10 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.55it/s, loss=0.499]
Epoch 10 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.55it/s, loss=0.501]
Epoch 10 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.28it/s, loss=0.501]
Epoch 10 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.28it/s, loss=0.502]
Epoch 10 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.28it/s, loss=0.499]
Epoch 10 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.28it/s, loss=0.506]
Epoch 10 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.22it/s, loss=0.506]
Epoch 10 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.22it/s, loss=0.508]
Epoch 10 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.22it/s, loss=0.508]
Epoch 10 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.22it/s, loss=0.506]
Epoch 10 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.44it/s, loss=0.506]
Epoch 10 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.44it/s, loss=0.504]
Epoch 10 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.44it/s, loss=0.502]
Epoch 10 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.44it/s, loss=0.505]
Epoch 10 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.12it/s, loss=0.505]
Epoch 10 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.12it/s, loss=0.505]
Epoch 10 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.12it/s, loss=0.505]
Epoch 10 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.12it/s, loss=0.504]
Epoch 10 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.86it/s, loss=0.504]
Epoch 10 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.86it/s, loss=0.505]
Epoch 10 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.86it/s, loss=0.502]
Epoch 10 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.86it/s, loss=0.5]
Epoch 10 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.08it/s, loss=0.5]
Epoch 10 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.08it/s, loss=0.497]
Epoch 10 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.08it/s, loss=0.497]
Epoch 10 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.08it/s, loss=0.496]
Epoch 10 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.52it/s, loss=0.496]
Epoch 10 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.52it/s, loss=0.494]
Epoch 10 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.52it/s, loss=0.491]
Epoch 10 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.52it/s, loss=0.488]
Epoch 10 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.61it/s, loss=0.488]
Epoch 10 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.61it/s, loss=0.485]
Epoch 10 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.61it/s, loss=0.487]
Epoch 10 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.61it/s, loss=0.487]
Epoch 10 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.99it/s, loss=0.487]
Epoch 10 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.99it/s, loss=0.489]
Epoch 10 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.99it/s, loss=0.489]
Epoch 10 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.99it/s, loss=0.487]
Epoch 10 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.07it/s, loss=0.487]
Epoch 10 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.07it/s, loss=0.485]
Epoch 10 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.07it/s, loss=0.483]
Epoch 10 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.07it/s, loss=0.481]
Epoch 10 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.81it/s, loss=0.481]
Epoch 10 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.81it/s, loss=0.484]
Epoch 10 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.81it/s, loss=0.488]
Epoch 10 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.81it/s, loss=0.487]
Epoch 10 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.23it/s, loss=0.487]
Epoch 10 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.23it/s, loss=0.487]
Epoch 10 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.23it/s, loss=0.485]
Epoch 10 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.23it/s, loss=0.486]
Epoch 10 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.36it/s, loss=0.486]
Epoch 10 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.36it/s, loss=0.483]
Epoch 10 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.36it/s, loss=0.483]
Epoch 10 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.36it/s, loss=0.483]
Epoch 10 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.53it/s, loss=0.483]
Epoch 10 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.53it/s, loss=0.482]
Epoch 10 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.53it/s, loss=0.481]
Epoch 10 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.53it/s, loss=0.481]
Epoch 10 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.76it/s, loss=0.481]
Epoch 10 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.76it/s, loss=0.479]
Epoch 10 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.76it/s, loss=0.479]
Epoch 10 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.76it/s, loss=0.479]
Epoch 10 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.04it/s, loss=0.479]
Epoch 10 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.04it/s, loss=0.478]
Epoch 10 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.04it/s, loss=0.478]
Epoch 10 [Train]: 60%|██████ | 78/129 [00:03<00:01, 26.04it/s, loss=0.478]
Epoch 10 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.80it/s, loss=0.478]
Epoch 10 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.80it/s, loss=0.477]
Epoch 10 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.80it/s, loss=0.474]
Epoch 10 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.80it/s, loss=0.473]
Epoch 10 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.65it/s, loss=0.473]
Epoch 10 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.65it/s, loss=0.475]
Epoch 10 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.65it/s, loss=0.478]
Epoch 10 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.65it/s, loss=0.478]
Epoch 10 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 25.91it/s, loss=0.478]
Epoch 10 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 25.91it/s, loss=0.477]
Epoch 10 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 25.91it/s, loss=0.476]
Epoch 10 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 25.91it/s, loss=0.476]
Epoch 10 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 26.06it/s, loss=0.476]
Epoch 10 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 26.06it/s, loss=0.477]
Epoch 10 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 26.06it/s, loss=0.476]
Epoch 10 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 26.06it/s, loss=0.479]
Epoch 10 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 25.93it/s, loss=0.479]
Epoch 10 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 25.93it/s, loss=0.479]
Epoch 10 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 25.93it/s, loss=0.48]
Epoch 10 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 25.93it/s, loss=0.478]
Epoch 10 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.61it/s, loss=0.478]
Epoch 10 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.61it/s, loss=0.48]
Epoch 10 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.61it/s, loss=0.481]
Epoch 10 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.61it/s, loss=0.48]
Epoch 10 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.12it/s, loss=0.48]
Epoch 10 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.12it/s, loss=0.479]
Epoch 10 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.12it/s, loss=0.478]
Epoch 10 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.12it/s, loss=0.477]
Epoch 10 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.90it/s, loss=0.477]
Epoch 10 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.90it/s, loss=0.476]
Epoch 10 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.90it/s, loss=0.476]
Epoch 10 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.90it/s, loss=0.475]
Epoch 10 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.03it/s, loss=0.475]
Epoch 10 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.03it/s, loss=0.474]
Epoch 10 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 27.03it/s, loss=0.474]
Epoch 10 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 27.03it/s, loss=0.474]
Epoch 10 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.57it/s, loss=0.474]
Epoch 10 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.57it/s, loss=0.474]
Epoch 10 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.57it/s, loss=0.474]
Epoch 10 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.57it/s, loss=0.475]
Epoch 10 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.06it/s, loss=0.475]
Epoch 10 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.06it/s, loss=0.476]
Epoch 10 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.06it/s, loss=0.476]
Epoch 10 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.06it/s, loss=0.474]
Epoch 10 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.67it/s, loss=0.474]
Epoch 10 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.67it/s, loss=0.473]
Epoch 10 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.67it/s, loss=0.473]
Epoch 10 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.67it/s, loss=0.474]
Epoch 10 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.03it/s, loss=0.474]
Epoch 10 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.03it/s, loss=0.473]
Epoch 10 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.03it/s, loss=0.473]
Epoch 10 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.03it/s, loss=0.473]
Epoch 10 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.63it/s, loss=0.473]
Epoch 10 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.63it/s, loss=0.473]
Epoch 10 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.63it/s, loss=0.474]
Epoch 10 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.63it/s, loss=0.475]
Epoch 10 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.20it/s, loss=0.475]
Epoch 10 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.20it/s, loss=0.474]
Epoch 10 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.20it/s, loss=0.474]
Epoch 10 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.20it/s, loss=0.475]
Epoch 10 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.43it/s, loss=0.475]
Epoch 10 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.43it/s, loss=0.474]
Epoch 10 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.43it/s, loss=0.473]
Epoch 10 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.43it/s, loss=0.474]
Epoch 10 [Train]: 100%|██████████| 129/129 [00:04<00:00, 26.81it/s, loss=0.474]
2026-08-07 06:50:46.293 | INFO  | __main__:pretrain:180 - Epoch 10/50 | Train Loss: 0.4736 | Val Loss: 0.6682
2026-08-07 06:50:46.302 | INFO  | __main__:pretrain:196 -  -> New best model (val_loss=0.6682)
Epoch 11 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 11 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.319]
Epoch 11 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.342]
Epoch 11 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.359]
Epoch 11 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.362]
Epoch 11 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.89it/s, loss=0.362]
Epoch 11 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.89it/s, loss=0.383]
Epoch 11 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.89it/s, loss=0.424]
Epoch 11 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.89it/s, loss=0.424]
Epoch 11 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.89it/s, loss=0.427]
Epoch 11 [Train]: 6%|▌ | 8/129 [00:00<00:04, 27.14it/s, loss=0.427]
Epoch 11 [Train]: 6%|▌ | 8/129 [00:00<00:04, 27.14it/s, loss=0.435]
Epoch 11 [Train]: 6%|▌ | 8/129 [00:00<00:04, 27.14it/s, loss=0.419]
Epoch 11 [Train]: 6%|▌ | 8/129 [00:00<00:04, 27.14it/s, loss=0.407]
Epoch 11 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.67it/s, loss=0.407]
Epoch 11 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.67it/s, loss=0.416]
Epoch 11 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.67it/s, loss=0.418]
Epoch 11 [Train]: 9%|▊ | 11/129 [00:00<00:04, 26.67it/s, loss=0.429]
Epoch 11 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.43it/s, loss=0.429]
Epoch 11 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.43it/s, loss=0.441]
Epoch 11 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.43it/s, loss=0.441]
Epoch 11 [Train]: 11%|█ | 14/129 [00:00<00:04, 26.43it/s, loss=0.446]
Epoch 11 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 25.91it/s, loss=0.446]
Epoch 11 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 25.91it/s, loss=0.447]
Epoch 11 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 25.91it/s, loss=0.461]
Epoch 11 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 25.91it/s, loss=0.463]
Epoch 11 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.07it/s, loss=0.463]
Epoch 11 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.07it/s, loss=0.466]
Epoch 11 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.07it/s, loss=0.465]
Epoch 11 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.07it/s, loss=0.473]
Epoch 11 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 26.69it/s, loss=0.473]
Epoch 11 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 26.69it/s, loss=0.471]
Epoch 11 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 26.69it/s, loss=0.465]
Epoch 11 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 26.69it/s, loss=0.46]
Epoch 11 [Train]: 20%|██ | 26/129 [00:00<00:03, 27.02it/s, loss=0.46]
Epoch 11 [Train]: 20%|██ | 26/129 [00:01<00:03, 27.02it/s, loss=0.462]
Epoch 11 [Train]: 20%|██ | 26/129 [00:01<00:03, 27.02it/s, loss=0.463]
Epoch 11 [Train]: 20%|██ | 26/129 [00:01<00:03, 27.02it/s, loss=0.458]
Epoch 11 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.90it/s, loss=0.458]
Epoch 11 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.90it/s, loss=0.47]
Epoch 11 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.90it/s, loss=0.469]
Epoch 11 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.90it/s, loss=0.468]
Epoch 11 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.93it/s, loss=0.468]
Epoch 11 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.93it/s, loss=0.463]
Epoch 11 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.93it/s, loss=0.46]
Epoch 11 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.93it/s, loss=0.458]
Epoch 11 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.93it/s, loss=0.458]
Epoch 11 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.93it/s, loss=0.459]
Epoch 11 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.93it/s, loss=0.457]
Epoch 11 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.93it/s, loss=0.455]
Epoch 11 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.25it/s, loss=0.455]
Epoch 11 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.25it/s, loss=0.455]
Epoch 11 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.25it/s, loss=0.458]
Epoch 11 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.25it/s, loss=0.456]
Epoch 11 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.32it/s, loss=0.456]
Epoch 11 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.32it/s, loss=0.454]
Epoch 11 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.32it/s, loss=0.455]
Epoch 11 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.32it/s, loss=0.454]
Epoch 11 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.60it/s, loss=0.454]
Epoch 11 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.60it/s, loss=0.453]
Epoch 11 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.60it/s, loss=0.454]
Epoch 11 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.60it/s, loss=0.453]
Epoch 11 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 27.05it/s, loss=0.453]
Epoch 11 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 27.05it/s, loss=0.454]
Epoch 11 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 27.05it/s, loss=0.454]
Epoch 11 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 27.05it/s, loss=0.452]
Epoch 11 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.49it/s, loss=0.452]
Epoch 11 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.49it/s, loss=0.452]
Epoch 11 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.49it/s, loss=0.454]
Epoch 11 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.49it/s, loss=0.453]
Epoch 11 [Train]: 41%|████ | 53/129 [00:01<00:02, 26.73it/s, loss=0.453]
Epoch 11 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.73it/s, loss=0.452]
Epoch 11 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.73it/s, loss=0.45]
Epoch 11 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.73it/s, loss=0.455]
Epoch 11 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.20it/s, loss=0.455]
Epoch 11 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.20it/s, loss=0.459]
Epoch 11 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.20it/s, loss=0.46]
Epoch 11 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.20it/s, loss=0.462]
Epoch 11 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 25.92it/s, loss=0.462]
Epoch 11 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 25.92it/s, loss=0.463]
Epoch 11 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 25.92it/s, loss=0.465]
Epoch 11 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 25.92it/s, loss=0.464]
Epoch 11 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.02it/s, loss=0.464]
Epoch 11 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.02it/s, loss=0.465]
Epoch 11 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.02it/s, loss=0.466]
Epoch 11 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.02it/s, loss=0.465]
Epoch 11 [Train]: 50%|█████ | 65/129 [00:02<00:02, 25.79it/s, loss=0.465]
Epoch 11 [Train]: 50%|█████ | 65/129 [00:02<00:02, 25.79it/s, loss=0.464]
Epoch 11 [Train]: 50%|█████ | 65/129 [00:02<00:02, 25.79it/s, loss=0.47]
Epoch 11 [Train]: 50%|█████ | 65/129 [00:02<00:02, 25.79it/s, loss=0.468]
Epoch 11 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.13it/s, loss=0.468]
Epoch 11 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.13it/s, loss=0.471]
Epoch 11 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.13it/s, loss=0.469]
Epoch 11 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 26.13it/s, loss=0.468]
Epoch 11 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.05it/s, loss=0.468]
Epoch 11 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.05it/s, loss=0.468]
Epoch 11 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.05it/s, loss=0.469]
Epoch 11 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.05it/s, loss=0.468]
Epoch 11 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.76it/s, loss=0.468]
Epoch 11 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.76it/s, loss=0.469]
Epoch 11 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.76it/s, loss=0.471]
Epoch 11 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.76it/s, loss=0.47]
Epoch 11 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 27.00it/s, loss=0.47]
Epoch 11 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 27.00it/s, loss=0.471]
Epoch 11 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 27.00it/s, loss=0.469]
Epoch 11 [Train]: 60%|█████▉ | 77/129 [00:03<00:01, 27.00it/s, loss=0.468]
Epoch 11 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 27.03it/s, loss=0.468]
Epoch 11 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 27.03it/s, loss=0.469]
Epoch 11 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 27.03it/s, loss=0.467]
Epoch 11 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 27.03it/s, loss=0.47]
Epoch 11 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.01it/s, loss=0.47]
Epoch 11 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.01it/s, loss=0.468]
Epoch 11 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.01it/s, loss=0.469]
Epoch 11 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.01it/s, loss=0.469]
Epoch 11 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.25it/s, loss=0.469]
Epoch 11 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.25it/s, loss=0.47]
Epoch 11 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.25it/s, loss=0.471]
Epoch 11 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.25it/s, loss=0.47]
Epoch 11 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.68it/s, loss=0.47]
Epoch 11 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.68it/s, loss=0.474]
Epoch 11 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.68it/s, loss=0.474]
Epoch 11 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.68it/s, loss=0.472]
Epoch 11 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 28.15it/s, loss=0.472]
Epoch 11 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 28.15it/s, loss=0.472]
Epoch 11 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 28.15it/s, loss=0.473]
Epoch 11 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 28.15it/s, loss=0.472]
Epoch 11 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.96it/s, loss=0.472]
Epoch 11 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.96it/s, loss=0.47]
Epoch 11 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.96it/s, loss=0.47]
Epoch 11 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.96it/s, loss=0.469]
Epoch 11 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 28.03it/s, loss=0.469]
Epoch 11 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 28.03it/s, loss=0.469]
Epoch 11 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 28.03it/s, loss=0.469]
Epoch 11 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 28.03it/s, loss=0.468]
Epoch 11 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.85it/s, loss=0.468]
Epoch 11 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.85it/s, loss=0.468]
Epoch 11 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.85it/s, loss=0.469]
Epoch 11 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 27.85it/s, loss=0.468]
Epoch 11 [Train]: 81%|████████ | 104/129 [00:03<00:00, 27.96it/s, loss=0.468]
Epoch 11 [Train]: 81%|████████ | 104/129 [00:03<00:00, 27.96it/s, loss=0.467]
Epoch 11 [Train]: 81%|████████ | 104/129 [00:03<00:00, 27.96it/s, loss=0.467]
Epoch 11 [Train]: 81%|████████ | 104/129 [00:03<00:00, 27.96it/s, loss=0.465]
Epoch 11 [Train]: 83%|████████▎ | 107/129 [00:03<00:00, 28.34it/s, loss=0.465]
Epoch 11 [Train]: 83%|████████▎ | 107/129 [00:03<00:00, 28.34it/s, loss=0.464]
Epoch 11 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 28.34it/s, loss=0.465]
Epoch 11 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 28.34it/s, loss=0.466]
Epoch 11 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 28.10it/s, loss=0.466]
Epoch 11 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 28.10it/s, loss=0.465]
Epoch 11 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 28.10it/s, loss=0.464]
Epoch 11 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 28.10it/s, loss=0.465]
Epoch 11 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.82it/s, loss=0.465]
Epoch 11 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.82it/s, loss=0.468]
Epoch 11 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.82it/s, loss=0.469]
Epoch 11 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.82it/s, loss=0.469]
Epoch 11 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.66it/s, loss=0.469]
Epoch 11 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.66it/s, loss=0.472]
Epoch 11 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.66it/s, loss=0.471]
Epoch 11 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.66it/s, loss=0.47]
Epoch 11 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.15it/s, loss=0.47]
Epoch 11 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.15it/s, loss=0.469]
Epoch 11 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.15it/s, loss=0.47]
Epoch 11 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.15it/s, loss=0.469]
Epoch 11 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 26.39it/s, loss=0.469]
Epoch 11 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 26.39it/s, loss=0.471]
Epoch 11 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 26.39it/s, loss=0.47]
Epoch 11 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 26.39it/s, loss=0.469]
Epoch 11 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.60it/s, loss=0.469]
Epoch 11 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.60it/s, loss=0.47]
Epoch 11 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.60it/s, loss=0.472]
Epoch 11 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 26.60it/s, loss=0.471]
Epoch 11 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 26.29it/s, loss=0.471]
Epoch 11 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 26.29it/s, loss=0.471]
2026-08-07 06:50:51.252 | INFO  | __main__:pretrain:180 - Epoch 11/50 | Train Loss: 0.4711 | Val Loss: 0.7055
Epoch 12 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 12 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.337]
Epoch 12 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.409]
Epoch 12 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.407]
Epoch 12 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.528]
Epoch 12 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.41it/s, loss=0.528]
Epoch 12 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.41it/s, loss=0.558]
Epoch 12 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.41it/s, loss=0.553]
Epoch 12 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.41it/s, loss=0.581]
Epoch 12 [Train]: 5%|▌ | 7/129 [00:00<00:04, 26.86it/s, loss=0.581]
Epoch 12 [Train]: 5%|▌ | 7/129 [00:00<00:04, 26.86it/s, loss=0.58]
Epoch 12 [Train]: 5%|▌ | 7/129 [00:00<00:04, 26.86it/s, loss=0.558]
Epoch 12 [Train]: 5%|▌ | 7/129 [00:00<00:04, 26.86it/s, loss=0.582]
Epoch 12 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.95it/s, loss=0.582]
Epoch 12 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.95it/s, loss=0.561]
Epoch 12 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.95it/s, loss=0.555]
Epoch 12 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.95it/s, loss=0.54]
Epoch 12 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.74it/s, loss=0.54]
Epoch 12 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.74it/s, loss=0.543]
Epoch 12 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.74it/s, loss=0.527]
Epoch 12 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.74it/s, loss=0.528]
Epoch 12 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.22it/s, loss=0.528]
Epoch 12 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.22it/s, loss=0.523]
Epoch 12 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.22it/s, loss=0.53]
Epoch 12 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.22it/s, loss=0.524]
Epoch 12 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 25.75it/s, loss=0.524]
Epoch 12 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 25.75it/s, loss=0.518]
Epoch 12 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 25.75it/s, loss=0.508]
Epoch 12 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 25.75it/s, loss=0.501]
Epoch 12 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 25.73it/s, loss=0.501]
Epoch 12 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 25.73it/s, loss=0.492]
Epoch 12 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 25.73it/s, loss=0.488]
Epoch 12 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 25.73it/s, loss=0.487]
Epoch 12 [Train]: 19%|█▉ | 25/129 [00:00<00:04, 22.90it/s, loss=0.487]
Epoch 12 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 22.90it/s, loss=0.487]
Epoch 12 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 22.90it/s, loss=0.483]
Epoch 12 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 22.90it/s, loss=0.485]
Epoch 12 [Train]: 22%|██▏ | 28/129 [00:01<00:04, 23.24it/s, loss=0.485]
Epoch 12 [Train]: 22%|██▏ | 28/129 [00:01<00:04, 23.24it/s, loss=0.481]
Epoch 12 [Train]: 22%|██▏ | 28/129 [00:01<00:04, 23.24it/s, loss=0.481]
Epoch 12 [Train]: 22%|██▏ | 28/129 [00:01<00:04, 23.24it/s, loss=0.484]
Epoch 12 [Train]: 24%|██▍ | 31/129 [00:01<00:04, 23.64it/s, loss=0.484]
Epoch 12 [Train]: 24%|██▍ | 31/129 [00:01<00:04, 23.64it/s, loss=0.48]
Epoch 12 [Train]: 24%|██▍ | 31/129 [00:01<00:04, 23.64it/s, loss=0.48]
Epoch 12 [Train]: 24%|██▍ | 31/129 [00:01<00:04, 23.64it/s, loss=0.482]
Epoch 12 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 24.02it/s, loss=0.482]
Epoch 12 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 24.02it/s, loss=0.477]
Epoch 12 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 24.02it/s, loss=0.471]
Epoch 12 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 24.02it/s, loss=0.471]
Epoch 12 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 24.55it/s, loss=0.471]
Epoch 12 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 24.55it/s, loss=0.468]
Epoch 12 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 24.55it/s, loss=0.47]
Epoch 12 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 24.55it/s, loss=0.469]
Epoch 12 [Train]: 31%|███ | 40/129 [00:01<00:03, 25.25it/s, loss=0.469]
Epoch 12 [Train]: 31%|███ | 40/129 [00:01<00:03, 25.25it/s, loss=0.466]
Epoch 12 [Train]: 31%|███ | 40/129 [00:01<00:03, 25.25it/s, loss=0.465]
Epoch 12 [Train]: 31%|███ | 40/129 [00:01<00:03, 25.25it/s, loss=0.465]
Epoch 12 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.30it/s, loss=0.465]
Epoch 12 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.30it/s, loss=0.464]
Epoch 12 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.30it/s, loss=0.466]
Epoch 12 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.30it/s, loss=0.464]
Epoch 12 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.48it/s, loss=0.464]
Epoch 12 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.48it/s, loss=0.463]
Epoch 12 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.48it/s, loss=0.463]
Epoch 12 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.48it/s, loss=0.464]
Epoch 12 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 25.99it/s, loss=0.464]
Epoch 12 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 25.99it/s, loss=0.464]
Epoch 12 [Train]: 38%|███▊ | 49/129 [00:02<00:03, 25.99it/s, loss=0.464]
Epoch 12 [Train]: 38%|███▊ | 49/129 [00:02<00:03, 25.99it/s, loss=0.467]
Epoch 12 [Train]: 40%|████ | 52/129 [00:02<00:02, 25.94it/s, loss=0.467]
Epoch 12 [Train]: 40%|████ | 52/129 [00:02<00:02, 25.94it/s, loss=0.464]
Epoch 12 [Train]: 40%|████ | 52/129 [00:02<00:02, 25.94it/s, loss=0.463]
Epoch 12 [Train]: 40%|████ | 52/129 [00:02<00:02, 25.94it/s, loss=0.471]
Epoch 12 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.89it/s, loss=0.471]
Epoch 12 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.89it/s, loss=0.477]
Epoch 12 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.89it/s, loss=0.473]
Epoch 12 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.89it/s, loss=0.475]
Epoch 12 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.47it/s, loss=0.475]
Epoch 12 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.47it/s, loss=0.476]
Epoch 12 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.47it/s, loss=0.475]
Epoch 12 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.47it/s, loss=0.473]
Epoch 12 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.37it/s, loss=0.473]
Epoch 12 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.37it/s, loss=0.474]
Epoch 12 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.37it/s, loss=0.473]
Epoch 12 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.37it/s, loss=0.472]
Epoch 12 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.33it/s, loss=0.472]
Epoch 12 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.33it/s, loss=0.468]
Epoch 12 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.33it/s, loss=0.468]
Epoch 12 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.33it/s, loss=0.465]
Epoch 12 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.38it/s, loss=0.465]
Epoch 12 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.38it/s, loss=0.462]
Epoch 12 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.38it/s, loss=0.463]
Epoch 12 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.38it/s, loss=0.462]
Epoch 12 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.32it/s, loss=0.462]
Epoch 12 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.32it/s, loss=0.461]
Epoch 12 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.32it/s, loss=0.46]
Epoch 12 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.32it/s, loss=0.459]
Epoch 12 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.95it/s, loss=0.459]
Epoch 12 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.95it/s, loss=0.457]
Epoch 12 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.95it/s, loss=0.458]
Epoch 12 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.95it/s, loss=0.456]
Epoch 12 [Train]: 59%|█████▉ | 76/129 [00:02<00:02, 26.27it/s, loss=0.456]
Epoch 12 [Train]: 59%|█████▉ | 76/129 [00:02<00:02, 26.27it/s, loss=0.457]
Epoch 12 [Train]: 59%|█████▉ | 76/129 [00:03<00:02, 26.27it/s, loss=0.458]
Epoch 12 [Train]: 59%|█████▉ | 76/129 [00:03<00:02, 26.27it/s, loss=0.46]
Epoch 12 [Train]: 61%|██████ | 79/129 [00:03<00:01, 25.81it/s, loss=0.46]
Epoch 12 [Train]: 61%|██████ | 79/129 [00:03<00:01, 25.81it/s, loss=0.458]
Epoch 12 [Train]: 61%|██████ | 79/129 [00:03<00:01, 25.81it/s, loss=0.46]
Epoch 12 [Train]: 61%|██████ | 79/129 [00:03<00:01, 25.81it/s, loss=0.458]
Epoch 12 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 25.89it/s, loss=0.458]
Epoch 12 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 25.89it/s, loss=0.456]
Epoch 12 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 25.89it/s, loss=0.457]
Epoch 12 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 25.89it/s, loss=0.455]
Epoch 12 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.65it/s, loss=0.455]
Epoch 12 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.65it/s, loss=0.456]
Epoch 12 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.65it/s, loss=0.454]
Epoch 12 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.65it/s, loss=0.452]
Epoch 12 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 26.71it/s, loss=0.452]
Epoch 12 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 26.71it/s, loss=0.453]
Epoch 12 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 26.71it/s, loss=0.452]
Epoch 12 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 26.71it/s, loss=0.455]
Epoch 12 [Train]: 71%|███████ | 91/129 [00:03<00:01, 26.12it/s, loss=0.455]
Epoch 12 [Train]: 71%|███████ | 91/129 [00:03<00:01, 26.12it/s, loss=0.455]
Epoch 12 [Train]: 71%|███████ | 91/129 [00:03<00:01, 26.12it/s, loss=0.456]
Epoch 12 [Train]: 71%|███████ | 91/129 [00:03<00:01, 26.12it/s, loss=0.457]
Epoch 12 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.55it/s, loss=0.457]
Epoch 12 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.55it/s, loss=0.458]
Epoch 12 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.55it/s, loss=0.458]
Epoch 12 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.55it/s, loss=0.458]
Epoch 12 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.31it/s, loss=0.458]
Epoch 12 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.31it/s, loss=0.46]
Epoch 12 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.31it/s, loss=0.459]
Epoch 12 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.31it/s, loss=0.457]
Epoch 12 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.21it/s, loss=0.457]
Epoch 12 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.21it/s, loss=0.456]
Epoch 12 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.21it/s, loss=0.455]
Epoch 12 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.21it/s, loss=0.455]
Epoch 12 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 27.35it/s, loss=0.455]
Epoch 12 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 27.35it/s, loss=0.453]
Epoch 12 [Train]: 80%|███████▉ | 103/129 [00:04<00:00, 27.35it/s, loss=0.452]
Epoch 12 [Train]: 80%|███████▉ | 103/129 [00:04<00:00, 27.35it/s, loss=0.453]
Epoch 12 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.52it/s, loss=0.453]
Epoch 12 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.52it/s, loss=0.454]
Epoch 12 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.52it/s, loss=0.455]
Epoch 12 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.52it/s, loss=0.457]
Epoch 12 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 27.13it/s, loss=0.457]
Epoch 12 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 27.13it/s, loss=0.459]
Epoch 12 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 27.13it/s, loss=0.458]
Epoch 12 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 27.13it/s, loss=0.458]
Epoch 12 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.94it/s, loss=0.458]
Epoch 12 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.94it/s, loss=0.457]
Epoch 12 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.94it/s, loss=0.456]
Epoch 12 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.94it/s, loss=0.456]
Epoch 12 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.61it/s, loss=0.456]
Epoch 12 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.61it/s, loss=0.456]
Epoch 12 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.61it/s, loss=0.457]
Epoch 12 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.61it/s, loss=0.456]
Epoch 12 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 27.17it/s, loss=0.456]
Epoch 12 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 27.17it/s, loss=0.455]
Epoch 12 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 27.17it/s, loss=0.454]
Epoch 12 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 27.17it/s, loss=0.454]
Epoch 12 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.53it/s, loss=0.454]
Epoch 12 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.53it/s, loss=0.455]
Epoch 12 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.53it/s, loss=0.457]
Epoch 12 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.53it/s, loss=0.455]
Epoch 12 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.75it/s, loss=0.455]
Epoch 12 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.75it/s, loss=0.454]
Epoch 12 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.75it/s, loss=0.453]
Epoch 12 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.75it/s, loss=0.453]
Epoch 12 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.88it/s, loss=0.453]
Epoch 12 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.88it/s, loss=0.452]
Epoch 12 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.88it/s, loss=0.452]
2026-08-07 06:50:56.306 | INFO  | __main__:pretrain:180 - Epoch 12/50 | Train Loss: 0.4520 | Val Loss: 0.7177
Epoch 13 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 13 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.302]
Epoch 13 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.41]
Epoch 13 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.364]
Epoch 13 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.343]
Epoch 13 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.38it/s, loss=0.343]
Epoch 13 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.38it/s, loss=0.332]
Epoch 13 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.38it/s, loss=0.352]
Epoch 13 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.38it/s, loss=0.358]
Epoch 13 [Train]: 5%|▌ | 7/129 [00:00<00:04, 27.93it/s, loss=0.358]
Epoch 13 [Train]: 5%|▌ | 7/129 [00:00<00:04, 27.93it/s, loss=0.36]
Epoch 13 [Train]: 5%|▌ | 7/129 [00:00<00:04, 27.93it/s, loss=0.378]
Epoch 13 [Train]: 5%|▌ | 7/129 [00:00<00:04, 27.93it/s, loss=0.376]
Epoch 13 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.74it/s, loss=0.376]
Epoch 13 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.74it/s, loss=0.381]
Epoch 13 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.74it/s, loss=0.379]
Epoch 13 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.74it/s, loss=0.376]
Epoch 13 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.83it/s, loss=0.376]
Epoch 13 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.83it/s, loss=0.382]
Epoch 13 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.83it/s, loss=0.385]
Epoch 13 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.83it/s, loss=0.385]
Epoch 13 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.95it/s, loss=0.385]
Epoch 13 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.95it/s, loss=0.403]
Epoch 13 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.95it/s, loss=0.41]
Epoch 13 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.95it/s, loss=0.405]
Epoch 13 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.76it/s, loss=0.405]
Epoch 13 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.76it/s, loss=0.427]
Epoch 13 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.76it/s, loss=0.434]
Epoch 13 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.76it/s, loss=0.43]
Epoch 13 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.13it/s, loss=0.43]
Epoch 13 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.13it/s, loss=0.427]
Epoch 13 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.13it/s, loss=0.422]
Epoch 13 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.13it/s, loss=0.42]
Epoch 13 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 27.03it/s, loss=0.42]
Epoch 13 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 27.03it/s, loss=0.419]
Epoch 13 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 27.03it/s, loss=0.419]
Epoch 13 [Train]: 19%|█▉ | 25/129 [00:01<00:03, 27.03it/s, loss=0.422]
Epoch 13 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 26.97it/s, loss=0.422]
Epoch 13 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 26.97it/s, loss=0.424]
Epoch 13 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 26.97it/s, loss=0.423]
Epoch 13 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 26.97it/s, loss=0.426]
Epoch 13 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.14it/s, loss=0.426]
Epoch 13 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.14it/s, loss=0.43]
Epoch 13 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.14it/s, loss=0.429]
Epoch 13 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.14it/s, loss=0.431]
Epoch 13 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.94it/s, loss=0.431]
Epoch 13 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.94it/s, loss=0.432]
Epoch 13 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.94it/s, loss=0.436]
Epoch 13 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.94it/s, loss=0.439]
Epoch 13 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.04it/s, loss=0.439]
Epoch 13 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.04it/s, loss=0.435]
Epoch 13 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.04it/s, loss=0.436]
Epoch 13 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.04it/s, loss=0.44]
Epoch 13 [Train]: 31%|███ | 40/129 [00:01<00:03, 26.82it/s, loss=0.44]
Epoch 13 [Train]: 31%|███ | 40/129 [00:01<00:03, 26.82it/s, loss=0.439]
Epoch 13 [Train]: 31%|███ | 40/129 [00:01<00:03, 26.82it/s, loss=0.439]
Epoch 13 [Train]: 31%|███ | 40/129 [00:01<00:03, 26.82it/s, loss=0.438]
Epoch 13 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.50it/s, loss=0.438]
Epoch 13 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.50it/s, loss=0.441]
Epoch 13 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.50it/s, loss=0.44]
Epoch 13 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.50it/s, loss=0.438]
Epoch 13 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.66it/s, loss=0.438]
Epoch 13 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.66it/s, loss=0.435]
Epoch 13 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.66it/s, loss=0.435]
Epoch 13 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.66it/s, loss=0.433]
Epoch 13 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 26.03it/s, loss=0.433]
Epoch 13 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 26.03it/s, loss=0.435]
Epoch 13 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 26.03it/s, loss=0.435]
Epoch 13 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 26.03it/s, loss=0.435]
Epoch 13 [Train]: 40%|████ | 52/129 [00:01<00:02, 26.24it/s, loss=0.435]
Epoch 13 [Train]: 40%|████ | 52/129 [00:01<00:02, 26.24it/s, loss=0.435]
Epoch 13 [Train]: 40%|████ | 52/129 [00:02<00:02, 26.24it/s, loss=0.434]
Epoch 13 [Train]: 40%|████ | 52/129 [00:02<00:02, 26.24it/s, loss=0.432]
Epoch 13 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.70it/s, loss=0.432]
Epoch 13 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.70it/s, loss=0.434]
Epoch 13 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.70it/s, loss=0.435]
Epoch 13 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.70it/s, loss=0.435]
Epoch 13 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.15it/s, loss=0.435]
Epoch 13 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.15it/s, loss=0.435]
Epoch 13 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.15it/s, loss=0.437]
Epoch 13 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.15it/s, loss=0.438]
Epoch 13 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.10it/s, loss=0.438]
Epoch 13 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.10it/s, loss=0.439]
Epoch 13 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.10it/s, loss=0.44]
Epoch 13 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.10it/s, loss=0.441]
Epoch 13 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.46it/s, loss=0.441]
Epoch 13 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.46it/s, loss=0.44]
Epoch 13 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.46it/s, loss=0.44]
Epoch 13 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.46it/s, loss=0.438]
Epoch 13 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.66it/s, loss=0.438]
Epoch 13 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.66it/s, loss=0.439]
Epoch 13 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.66it/s, loss=0.446]
Epoch 13 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.66it/s, loss=0.444]
Epoch 13 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.71it/s, loss=0.444]
Epoch 13 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.71it/s, loss=0.443]
Epoch 13 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.71it/s, loss=0.441]
Epoch 13 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.71it/s, loss=0.445]
Epoch 13 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.26it/s, loss=0.445]
Epoch 13 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.26it/s, loss=0.446]
Epoch 13 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.26it/s, loss=0.446]
Epoch 13 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.26it/s, loss=0.446]
Epoch 13 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.39it/s, loss=0.446]
Epoch 13 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.39it/s, loss=0.444]
Epoch 13 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.39it/s, loss=0.442]
Epoch 13 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.39it/s, loss=0.446]
Epoch 13 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.39it/s, loss=0.447]
Epoch 13 [Train]: 62%|██████▏ | 80/129 [00:02<00:01, 28.03it/s, loss=0.447]
Epoch 13 [Train]: 62%|██████▏ | 80/129 [00:02<00:01, 28.03it/s, loss=0.447]
Epoch 13 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 28.03it/s, loss=0.448]
Epoch 13 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 28.03it/s, loss=0.449]
Epoch 13 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.01it/s, loss=0.449]
Epoch 13 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.01it/s, loss=0.451]
Epoch 13 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.01it/s, loss=0.449]
Epoch 13 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.01it/s, loss=0.45]
Epoch 13 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.42it/s, loss=0.45]
Epoch 13 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.42it/s, loss=0.449]
Epoch 13 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.42it/s, loss=0.448]
Epoch 13 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 26.42it/s, loss=0.446]
Epoch 13 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.09it/s, loss=0.446]
Epoch 13 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.09it/s, loss=0.445]
Epoch 13 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.09it/s, loss=0.443]
Epoch 13 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.09it/s, loss=0.444]
Epoch 13 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.27it/s, loss=0.444]
Epoch 13 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.27it/s, loss=0.446]
Epoch 13 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.27it/s, loss=0.443]
Epoch 13 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.27it/s, loss=0.443]
Epoch 13 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.71it/s, loss=0.443]
Epoch 13 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.71it/s, loss=0.441]
Epoch 13 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.71it/s, loss=0.442]
Epoch 13 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.71it/s, loss=0.441]
Epoch 13 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.53it/s, loss=0.441]
Epoch 13 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.53it/s, loss=0.443]
Epoch 13 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.53it/s, loss=0.442]
Epoch 13 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.53it/s, loss=0.443]
Epoch 13 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.95it/s, loss=0.443]
Epoch 13 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.95it/s, loss=0.444]
Epoch 13 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.95it/s, loss=0.444]
Epoch 13 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.95it/s, loss=0.447]
Epoch 13 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.83it/s, loss=0.447]
Epoch 13 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.83it/s, loss=0.446]
Epoch 13 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.83it/s, loss=0.446]
Epoch 13 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.83it/s, loss=0.447]
Epoch 13 [Train]: 83%|████████▎ | 107/129 [00:03<00:00, 26.13it/s, loss=0.447]
Epoch 13 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.13it/s, loss=0.447]
Epoch 13 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.13it/s, loss=0.447]
Epoch 13 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 26.13it/s, loss=0.446]
Epoch 13 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.96it/s, loss=0.446]
Epoch 13 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.96it/s, loss=0.446]
Epoch 13 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.96it/s, loss=0.447]
Epoch 13 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 25.96it/s, loss=0.447]
Epoch 13 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.24it/s, loss=0.447]
Epoch 13 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.24it/s, loss=0.447]
Epoch 13 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.24it/s, loss=0.447]
Epoch 13 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 26.24it/s, loss=0.45]
Epoch 13 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.61it/s, loss=0.45]
Epoch 13 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.61it/s, loss=0.448]
Epoch 13 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.61it/s, loss=0.447]
Epoch 13 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 26.61it/s, loss=0.448]
Epoch 13 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.71it/s, loss=0.448]
Epoch 13 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.71it/s, loss=0.449]
Epoch 13 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.71it/s, loss=0.448]
Epoch 13 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 26.71it/s, loss=0.449]
Epoch 13 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.13it/s, loss=0.449]
Epoch 13 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.13it/s, loss=0.452]
Epoch 13 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.13it/s, loss=0.453]
Epoch 13 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.13it/s, loss=0.454]
Epoch 13 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 27.48it/s, loss=0.454]
Epoch 13 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 27.48it/s, loss=0.454]
Epoch 13 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 27.48it/s, loss=0.453]
Epoch 13 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 27.48it/s, loss=0.453]
Epoch 13 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 27.47it/s, loss=0.453]
Epoch 13 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 27.47it/s, loss=0.452]
2026-08-07 06:51:01.242 | INFO  | __main__:pretrain:180 - Epoch 13/50 | Train Loss: 0.4523 | Val Loss: 0.6767
Epoch 14 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 14 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.313]
Epoch 14 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.388]
Epoch 14 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.396]
Epoch 14 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.03it/s, loss=0.396]
Epoch 14 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.03it/s, loss=0.364]
Epoch 14 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.03it/s, loss=0.379]
Epoch 14 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.03it/s, loss=0.393]
Epoch 14 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.54it/s, loss=0.393]
Epoch 14 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.54it/s, loss=0.404]
Epoch 14 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.54it/s, loss=0.402]
Epoch 14 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.54it/s, loss=0.388]
Epoch 14 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.77it/s, loss=0.388]
Epoch 14 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.77it/s, loss=0.386]
Epoch 14 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.77it/s, loss=0.392]
Epoch 14 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.77it/s, loss=0.398]
Epoch 14 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.94it/s, loss=0.398]
Epoch 14 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.94it/s, loss=0.389]
Epoch 14 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.94it/s, loss=0.378]
Epoch 14 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.94it/s, loss=0.434]
Epoch 14 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.10it/s, loss=0.434]
Epoch 14 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.10it/s, loss=0.439]
Epoch 14 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.10it/s, loss=0.44]
Epoch 14 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.10it/s, loss=0.435]
Epoch 14 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.12it/s, loss=0.435]
Epoch 14 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.12it/s, loss=0.439]
Epoch 14 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.12it/s, loss=0.437]
Epoch 14 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.12it/s, loss=0.431]
Epoch 14 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.81it/s, loss=0.431]
Epoch 14 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.81it/s, loss=0.438]
Epoch 14 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.81it/s, loss=0.431]
Epoch 14 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.81it/s, loss=0.43]
Epoch 14 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.89it/s, loss=0.43]
Epoch 14 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.89it/s, loss=0.429]
Epoch 14 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.89it/s, loss=0.431]
Epoch 14 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.89it/s, loss=0.428]
Epoch 14 [Train]: 21%|██ | 27/129 [00:00<00:03, 28.13it/s, loss=0.428]
Epoch 14 [Train]: 21%|██ | 27/129 [00:01<00:03, 28.13it/s, loss=0.438]
Epoch 14 [Train]: 21%|██ | 27/129 [00:01<00:03, 28.13it/s, loss=0.442]
Epoch 14 [Train]: 21%|██ | 27/129 [00:01<00:03, 28.13it/s, loss=0.444]
Epoch 14 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.76it/s, loss=0.444]
Epoch 14 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.76it/s, loss=0.451]
Epoch 14 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.76it/s, loss=0.45]
Epoch 14 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.76it/s, loss=0.453]
Epoch 14 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.25it/s, loss=0.453]
Epoch 14 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.25it/s, loss=0.451]
Epoch 14 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.25it/s, loss=0.446]
Epoch 14 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.25it/s, loss=0.444]
Epoch 14 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.33it/s, loss=0.444]
Epoch 14 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.33it/s, loss=0.446]
Epoch 14 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.33it/s, loss=0.446]
Epoch 14 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.33it/s, loss=0.446]
Epoch 14 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.44it/s, loss=0.446]
Epoch 14 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.44it/s, loss=0.444]
Epoch 14 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.44it/s, loss=0.445]
Epoch 14 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.44it/s, loss=0.443]
Epoch 14 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.49it/s, loss=0.443]
Epoch 14 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.49it/s, loss=0.44]
Epoch 14 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.49it/s, loss=0.439]
Epoch 14 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.49it/s, loss=0.439]
Epoch 14 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.55it/s, loss=0.439]
Epoch 14 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.55it/s, loss=0.437]
Epoch 14 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.55it/s, loss=0.439]
Epoch 14 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.55it/s, loss=0.44]
Epoch 14 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.79it/s, loss=0.44]
Epoch 14 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.79it/s, loss=0.439]
Epoch 14 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.79it/s, loss=0.438]
Epoch 14 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.79it/s, loss=0.434]
Epoch 14 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.40it/s, loss=0.434]
Epoch 14 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.40it/s, loss=0.438]
Epoch 14 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.40it/s, loss=0.438]
Epoch 14 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.40it/s, loss=0.438]
Epoch 14 [Train]: 42%|████▏ | 54/129 [00:01<00:02, 26.95it/s, loss=0.438]
Epoch 14 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.95it/s, loss=0.438]
Epoch 14 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.95it/s, loss=0.437]
Epoch 14 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.95it/s, loss=0.437]
Epoch 14 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.94it/s, loss=0.437]
Epoch 14 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.94it/s, loss=0.438]
Epoch 14 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.94it/s, loss=0.442]
Epoch 14 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.94it/s, loss=0.445]
Epoch 14 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.13it/s, loss=0.445]
Epoch 14 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.13it/s, loss=0.443]
Epoch 14 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.13it/s, loss=0.449]
Epoch 14 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.13it/s, loss=0.449]
Epoch 14 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.61it/s, loss=0.449]
Epoch 14 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.61it/s, loss=0.458]
Epoch 14 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.61it/s, loss=0.457]
Epoch 14 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.61it/s, loss=0.454]
Epoch 14 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.65it/s, loss=0.454]
Epoch 14 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.65it/s, loss=0.454]
Epoch 14 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.65it/s, loss=0.452]
Epoch 14 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.65it/s, loss=0.452]
Epoch 14 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 28.04it/s, loss=0.452]
Epoch 14 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 28.04it/s, loss=0.452]
Epoch 14 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 28.04it/s, loss=0.452]
Epoch 14 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 28.04it/s, loss=0.452]
Epoch 14 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 28.07it/s, loss=0.452]
Epoch 14 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 28.07it/s, loss=0.454]
Epoch 14 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 28.07it/s, loss=0.455]
Epoch 14 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 28.07it/s, loss=0.455]
Epoch 14 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.50it/s, loss=0.455]
Epoch 14 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.50it/s, loss=0.454]
Epoch 14 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.50it/s, loss=0.454]
Epoch 14 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.50it/s, loss=0.454]
Epoch 14 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.26it/s, loss=0.454]
Epoch 14 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.26it/s, loss=0.453]
Epoch 14 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.26it/s, loss=0.455]
Epoch 14 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.26it/s, loss=0.454]
Epoch 14 [Train]: 63%|██████▎ | 81/129 [00:02<00:01, 26.48it/s, loss=0.454]
Epoch 14 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.48it/s, loss=0.457]
Epoch 14 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.48it/s, loss=0.458]
Epoch 14 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.48it/s, loss=0.456]
Epoch 14 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.56it/s, loss=0.456]
Epoch 14 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.56it/s, loss=0.456]
Epoch 14 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.56it/s, loss=0.456]
Epoch 14 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.56it/s, loss=0.456]
Epoch 14 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.24it/s, loss=0.456]
Epoch 14 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.24it/s, loss=0.456]
Epoch 14 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.24it/s, loss=0.455]
Epoch 14 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.24it/s, loss=0.453]
Epoch 14 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 26.54it/s, loss=0.453]
Epoch 14 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 26.54it/s, loss=0.453]
Epoch 14 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 26.54it/s, loss=0.452]
Epoch 14 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 26.54it/s, loss=0.453]
Epoch 14 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.37it/s, loss=0.453]
Epoch 14 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.37it/s, loss=0.453]
Epoch 14 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.37it/s, loss=0.453]
Epoch 14 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.37it/s, loss=0.456]
Epoch 14 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.66it/s, loss=0.456]
Epoch 14 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.66it/s, loss=0.456]
Epoch 14 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.66it/s, loss=0.456]
Epoch 14 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.66it/s, loss=0.454]
Epoch 14 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.14it/s, loss=0.454]
Epoch 14 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.14it/s, loss=0.453]
Epoch 14 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.14it/s, loss=0.459]
Epoch 14 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.14it/s, loss=0.458]
Epoch 14 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.60it/s, loss=0.458]
Epoch 14 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.60it/s, loss=0.457]
Epoch 14 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.60it/s, loss=0.456]
Epoch 14 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.60it/s, loss=0.455]
Epoch 14 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.78it/s, loss=0.455]
Epoch 14 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.78it/s, loss=0.454]
Epoch 14 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.78it/s, loss=0.453]
Epoch 14 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.78it/s, loss=0.452]
Epoch 14 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 27.41it/s, loss=0.452]
Epoch 14 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 27.41it/s, loss=0.452]
Epoch 14 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.41it/s, loss=0.451]
Epoch 14 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.41it/s, loss=0.452]
Epoch 14 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.84it/s, loss=0.452]
Epoch 14 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.84it/s, loss=0.45]
Epoch 14 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.84it/s, loss=0.451]
Epoch 14 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.84it/s, loss=0.451]
Epoch 14 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.29it/s, loss=0.451]
Epoch 14 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.29it/s, loss=0.454]
Epoch 14 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.29it/s, loss=0.453]
Epoch 14 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.29it/s, loss=0.452]
Epoch 14 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.87it/s, loss=0.452]
Epoch 14 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.87it/s, loss=0.452]
Epoch 14 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.87it/s, loss=0.452]
Epoch 14 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.87it/s, loss=0.452]
Epoch 14 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.63it/s, loss=0.452]
Epoch 14 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.63it/s, loss=0.452]
Epoch 14 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.63it/s, loss=0.452]
Epoch 14 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.63it/s, loss=0.451]
Epoch 14 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.83it/s, loss=0.451]
Epoch 14 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.83it/s, loss=0.451]
Epoch 14 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.83it/s, loss=0.451]
Epoch 14 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.83it/s, loss=0.45]
Epoch 14 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.55it/s, loss=0.45]
Epoch 14 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.55it/s, loss=0.45]
Epoch 14 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.55it/s, loss=0.449]
Epoch 14 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.55it/s, loss=0.45]
Epoch 14 [Train]: 100%|██████████| 129/129 [00:04<00:00, 27.68it/s, loss=0.45]
2026-08-07 06:51:06.104 | INFO  | __main__:pretrain:180 - Epoch 14/50 | Train Loss: 0.4501 | Val Loss: 1.1059
Epoch 15 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 15 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.462]
Epoch 15 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.469]
Epoch 15 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.431]
Epoch 15 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.407]
Epoch 15 [Train]: 3%|▎ | 4/129 [00:00<00:04, 28.89it/s, loss=0.407]
Epoch 15 [Train]: 3%|▎ | 4/129 [00:00<00:04, 28.89it/s, loss=0.387]
Epoch 15 [Train]: 3%|▎ | 4/129 [00:00<00:04, 28.89it/s, loss=0.395]
Epoch 15 [Train]: 3%|▎ | 4/129 [00:00<00:04, 28.89it/s, loss=0.411]
Epoch 15 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.45it/s, loss=0.411]
Epoch 15 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.45it/s, loss=0.412]
Epoch 15 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.45it/s, loss=0.41]
Epoch 15 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.45it/s, loss=0.41]
Epoch 15 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.89it/s, loss=0.41]
Epoch 15 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.89it/s, loss=0.403]
Epoch 15 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.89it/s, loss=0.408]
Epoch 15 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.89it/s, loss=0.4]
Epoch 15 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.91it/s, loss=0.4]
Epoch 15 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.91it/s, loss=0.4]
Epoch 15 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.91it/s, loss=0.398]
Epoch 15 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.91it/s, loss=0.399]
Epoch 15 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.56it/s, loss=0.399]
Epoch 15 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.56it/s, loss=0.402]
Epoch 15 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.56it/s, loss=0.397]
Epoch 15 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.56it/s, loss=0.388]
Epoch 15 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.41it/s, loss=0.388]
Epoch 15 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.41it/s, loss=0.385]
Epoch 15 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.41it/s, loss=0.382]
Epoch 15 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.41it/s, loss=0.386]
Epoch 15 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 25.78it/s, loss=0.386]
Epoch 15 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 25.78it/s, loss=0.392]
Epoch 15 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 25.78it/s, loss=0.399]
Epoch 15 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 25.78it/s, loss=0.397]
Epoch 15 [Train]: 19%|█▉ | 25/129 [00:00<00:04, 25.63it/s, loss=0.397]
Epoch 15 [Train]: 19%|█▉ | 25/129 [00:00<00:04, 25.63it/s, loss=0.393]
Epoch 15 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 25.63it/s, loss=0.39]
Epoch 15 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 25.63it/s, loss=0.388]
Epoch 15 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 25.89it/s, loss=0.388]
Epoch 15 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 25.89it/s, loss=0.395]
Epoch 15 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 25.89it/s, loss=0.396]
Epoch 15 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 25.89it/s, loss=0.397]
Epoch 15 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 25.89it/s, loss=0.397]
Epoch 15 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 25.89it/s, loss=0.393]
Epoch 15 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 25.89it/s, loss=0.389]
Epoch 15 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 25.89it/s, loss=0.389]
Epoch 15 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.69it/s, loss=0.389]
Epoch 15 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.69it/s, loss=0.387]
Epoch 15 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.69it/s, loss=0.389]
Epoch 15 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.69it/s, loss=0.388]
Epoch 15 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.97it/s, loss=0.388]
Epoch 15 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.97it/s, loss=0.392]
Epoch 15 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.97it/s, loss=0.389]
Epoch 15 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.97it/s, loss=0.386]
Epoch 15 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.37it/s, loss=0.386]
Epoch 15 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.37it/s, loss=0.383]
Epoch 15 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.37it/s, loss=0.382]
Epoch 15 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.37it/s, loss=0.38]
Epoch 15 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.57it/s, loss=0.38]
Epoch 15 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.57it/s, loss=0.378]
Epoch 15 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.57it/s, loss=0.379]
Epoch 15 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.57it/s, loss=0.386]
Epoch 15 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.41it/s, loss=0.386]
Epoch 15 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.41it/s, loss=0.386]
Epoch 15 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.41it/s, loss=0.391]
Epoch 15 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.41it/s, loss=0.399]
Epoch 15 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 26.74it/s, loss=0.399]
Epoch 15 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 26.74it/s, loss=0.399]
Epoch 15 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 26.74it/s, loss=0.399]
Epoch 15 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 26.74it/s, loss=0.397]
Epoch 15 [Train]: 40%|████ | 52/129 [00:01<00:02, 26.96it/s, loss=0.397]
Epoch 15 [Train]: 40%|████ | 52/129 [00:01<00:02, 26.96it/s, loss=0.396]
Epoch 15 [Train]: 40%|████ | 52/129 [00:02<00:02, 26.96it/s, loss=0.396]
Epoch 15 [Train]: 40%|████ | 52/129 [00:02<00:02, 26.96it/s, loss=0.4]
Epoch 15 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.79it/s, loss=0.4]
Epoch 15 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.79it/s, loss=0.399]
Epoch 15 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.79it/s, loss=0.4]
Epoch 15 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.79it/s, loss=0.401]
Epoch 15 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.89it/s, loss=0.401]
Epoch 15 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.89it/s, loss=0.4]
Epoch 15 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.89it/s, loss=0.4]
Epoch 15 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.89it/s, loss=0.399]
Epoch 15 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.57it/s, loss=0.399]
Epoch 15 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.57it/s, loss=0.403]
Epoch 15 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.57it/s, loss=0.403]
Epoch 15 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.57it/s, loss=0.402]
Epoch 15 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.19it/s, loss=0.402]
Epoch 15 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.19it/s, loss=0.401]
Epoch 15 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.19it/s, loss=0.404]
Epoch 15 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.19it/s, loss=0.402]
Epoch 15 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.20it/s, loss=0.402]
Epoch 15 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.20it/s, loss=0.4]
Epoch 15 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.20it/s, loss=0.4]
Epoch 15 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.20it/s, loss=0.402]
Epoch 15 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.83it/s, loss=0.402]
Epoch 15 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.83it/s, loss=0.401]
Epoch 15 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.83it/s, loss=0.401]
Epoch 15 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.83it/s, loss=0.4]
Epoch 15 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.22it/s, loss=0.4]
Epoch 15 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.22it/s, loss=0.399]
Epoch 15 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.22it/s, loss=0.398]
Epoch 15 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.22it/s, loss=0.397]
Epoch 15 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 26.83it/s, loss=0.397]
Epoch 15 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 26.83it/s, loss=0.398]
Epoch 15 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 26.83it/s, loss=0.397]
Epoch 15 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 26.83it/s, loss=0.398]
Epoch 15 [Train]: 61%|██████ | 79/129 [00:02<00:01, 26.26it/s, loss=0.398]
Epoch 15 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.26it/s, loss=0.399]
Epoch 15 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.26it/s, loss=0.399]
Epoch 15 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.26it/s, loss=0.402]
Epoch 15 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.29it/s, loss=0.402]
Epoch 15 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.29it/s, loss=0.401]
Epoch 15 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.29it/s, loss=0.402]
Epoch 15 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.29it/s, loss=0.402]
Epoch 15 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.03it/s, loss=0.402]
Epoch 15 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.03it/s, loss=0.402]
Epoch 15 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.03it/s, loss=0.409]
Epoch 15 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.03it/s, loss=0.409]
Epoch 15 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 25.71it/s, loss=0.409]
Epoch 15 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 25.71it/s, loss=0.409]
Epoch 15 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 25.71it/s, loss=0.41]
Epoch 15 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 25.71it/s, loss=0.41]
Epoch 15 [Train]: 71%|███████ | 91/129 [00:03<00:01, 25.49it/s, loss=0.41]
Epoch 15 [Train]: 71%|███████ | 91/129 [00:03<00:01, 25.49it/s, loss=0.412]
Epoch 15 [Train]: 71%|███████ | 91/129 [00:03<00:01, 25.49it/s, loss=0.415]
Epoch 15 [Train]: 71%|███████ | 91/129 [00:03<00:01, 25.49it/s, loss=0.417]
Epoch 15 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.05it/s, loss=0.417]
Epoch 15 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.05it/s, loss=0.415]
Epoch 15 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.05it/s, loss=0.415]
Epoch 15 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.05it/s, loss=0.414]
Epoch 15 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.70it/s, loss=0.414]
Epoch 15 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.70it/s, loss=0.42]
Epoch 15 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.70it/s, loss=0.422]
Epoch 15 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.70it/s, loss=0.422]
Epoch 15 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.55it/s, loss=0.422]
Epoch 15 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.55it/s, loss=0.421]
Epoch 15 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.55it/s, loss=0.422]
Epoch 15 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.55it/s, loss=0.422]
Epoch 15 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.70it/s, loss=0.422]
Epoch 15 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.70it/s, loss=0.425]
Epoch 15 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.70it/s, loss=0.424]
Epoch 15 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.70it/s, loss=0.425]
Epoch 15 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 27.10it/s, loss=0.425]
Epoch 15 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.10it/s, loss=0.426]
Epoch 15 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.10it/s, loss=0.426]
Epoch 15 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.10it/s, loss=0.426]
Epoch 15 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.58it/s, loss=0.426]
Epoch 15 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.58it/s, loss=0.426]
Epoch 15 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.58it/s, loss=0.425]
Epoch 15 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.58it/s, loss=0.426]
Epoch 15 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.13it/s, loss=0.426]
Epoch 15 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.13it/s, loss=0.427]
Epoch 15 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.13it/s, loss=0.426]
Epoch 15 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.13it/s, loss=0.426]
Epoch 15 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.16it/s, loss=0.426]
Epoch 15 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.16it/s, loss=0.425]
Epoch 15 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.16it/s, loss=0.425]
Epoch 15 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.16it/s, loss=0.425]
Epoch 15 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.00it/s, loss=0.425]
Epoch 15 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.00it/s, loss=0.427]
Epoch 15 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.00it/s, loss=0.426]
Epoch 15 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.00it/s, loss=0.426]
Epoch 15 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 25.68it/s, loss=0.426]
Epoch 15 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 25.68it/s, loss=0.425]
Epoch 15 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 25.68it/s, loss=0.426]
Epoch 15 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 25.68it/s, loss=0.425]
Epoch 15 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 25.96it/s, loss=0.425]
Epoch 15 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 25.96it/s, loss=0.425]
Epoch 15 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 25.96it/s, loss=0.428]
Epoch 15 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 25.96it/s, loss=0.428]
Epoch 15 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.42it/s, loss=0.428]
Epoch 15 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.42it/s, loss=0.428]
Epoch 15 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.42it/s, loss=0.427]
2026-08-07 06:51:11.134 | INFO  | __main__:pretrain:180 - Epoch 15/50 | Train Loss: 0.4275 | Val Loss: 0.7007
Epoch 16 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 16 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.327]
Epoch 16 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.348]
Epoch 16 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.329]
Epoch 16 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.51it/s, loss=0.329]
Epoch 16 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.51it/s, loss=0.323]
Epoch 16 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.51it/s, loss=0.33]
Epoch 16 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.51it/s, loss=0.341]
Epoch 16 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.57it/s, loss=0.341]
Epoch 16 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.57it/s, loss=0.355]
Epoch 16 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.57it/s, loss=0.346]
Epoch 16 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.57it/s, loss=0.337]
Epoch 16 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.11it/s, loss=0.337]
Epoch 16 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.11it/s, loss=0.345]
Epoch 16 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.11it/s, loss=0.341]
Epoch 16 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.11it/s, loss=0.333]
Epoch 16 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.94it/s, loss=0.333]
Epoch 16 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.94it/s, loss=0.341]
Epoch 16 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.94it/s, loss=0.344]
Epoch 16 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.94it/s, loss=0.342]
Epoch 16 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.67it/s, loss=0.342]
Epoch 16 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.67it/s, loss=0.353]
Epoch 16 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.67it/s, loss=0.356]
Epoch 16 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.67it/s, loss=0.356]
Epoch 16 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.30it/s, loss=0.356]
Epoch 16 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.30it/s, loss=0.361]
Epoch 16 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.30it/s, loss=0.359]
Epoch 16 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.30it/s, loss=0.36]
Epoch 16 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 25.81it/s, loss=0.36]
Epoch 16 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 25.81it/s, loss=0.37]
Epoch 16 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 25.81it/s, loss=0.37]
Epoch 16 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 25.81it/s, loss=0.367]
Epoch 16 [Train]: 19%|█▊ | 24/129 [00:00<00:04, 25.79it/s, loss=0.367]
Epoch 16 [Train]: 19%|█▊ | 24/129 [00:00<00:04, 25.79it/s, loss=0.369]
Epoch 16 [Train]: 19%|█▊ | 24/129 [00:00<00:04, 25.79it/s, loss=0.367]
Epoch 16 [Train]: 19%|█▊ | 24/129 [00:01<00:04, 25.79it/s, loss=0.365]
Epoch 16 [Train]: 21%|██ | 27/129 [00:01<00:03, 25.69it/s, loss=0.365]
Epoch 16 [Train]: 21%|██ | 27/129 [00:01<00:03, 25.69it/s, loss=0.366]
Epoch 16 [Train]: 21%|██ | 27/129 [00:01<00:03, 25.69it/s, loss=0.37]
Epoch 16 [Train]: 21%|██ | 27/129 [00:01<00:03, 25.69it/s, loss=0.373]
Epoch 16 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 25.63it/s, loss=0.373]
Epoch 16 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 25.63it/s, loss=0.375]
Epoch 16 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 25.63it/s, loss=0.376]
Epoch 16 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 25.63it/s, loss=0.379]
Epoch 16 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 25.93it/s, loss=0.379]
Epoch 16 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 25.93it/s, loss=0.383]
Epoch 16 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 25.93it/s, loss=0.386]
Epoch 16 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 25.93it/s, loss=0.382]
Epoch 16 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 25.66it/s, loss=0.382]
Epoch 16 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 25.66it/s, loss=0.383]
Epoch 16 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 25.66it/s, loss=0.39]
Epoch 16 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 25.66it/s, loss=0.388]
Epoch 16 [Train]: 30%|███ | 39/129 [00:01<00:03, 25.57it/s, loss=0.388]
Epoch 16 [Train]: 30%|███ | 39/129 [00:01<00:03, 25.57it/s, loss=0.391]
Epoch 16 [Train]: 30%|███ | 39/129 [00:01<00:03, 25.57it/s, loss=0.391]
Epoch 16 [Train]: 30%|███ | 39/129 [00:01<00:03, 25.57it/s, loss=0.39]
Epoch 16 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 25.74it/s, loss=0.39]
Epoch 16 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 25.74it/s, loss=0.393]
Epoch 16 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 25.74it/s, loss=0.394]
Epoch 16 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 25.74it/s, loss=0.395]
Epoch 16 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 25.49it/s, loss=0.395]
Epoch 16 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 25.49it/s, loss=0.394]
Epoch 16 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 25.49it/s, loss=0.393]
Epoch 16 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 25.49it/s, loss=0.393]
Epoch 16 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.14it/s, loss=0.393]
Epoch 16 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.14it/s, loss=0.394]
Epoch 16 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.14it/s, loss=0.393]
Epoch 16 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.14it/s, loss=0.392]
Epoch 16 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.45it/s, loss=0.392]
Epoch 16 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.45it/s, loss=0.391]
Epoch 16 [Train]: 40%|███▉ | 51/129 [00:02<00:02, 26.45it/s, loss=0.399]
Epoch 16 [Train]: 40%|███▉ | 51/129 [00:02<00:02, 26.45it/s, loss=0.398]
Epoch 16 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.75it/s, loss=0.398]
Epoch 16 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.75it/s, loss=0.399]
Epoch 16 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.75it/s, loss=0.4]
Epoch 16 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.75it/s, loss=0.4]
Epoch 16 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.46it/s, loss=0.4]
Epoch 16 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.46it/s, loss=0.401]
Epoch 16 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.46it/s, loss=0.399]
Epoch 16 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.46it/s, loss=0.399]
Epoch 16 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.85it/s, loss=0.399]
Epoch 16 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.85it/s, loss=0.401]
Epoch 16 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.85it/s, loss=0.402]
Epoch 16 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.85it/s, loss=0.401]
Epoch 16 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.06it/s, loss=0.401]
Epoch 16 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.06it/s, loss=0.401]
Epoch 16 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.06it/s, loss=0.402]
Epoch 16 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.06it/s, loss=0.403]
Epoch 16 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.35it/s, loss=0.403]
Epoch 16 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.35it/s, loss=0.401]
Epoch 16 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.35it/s, loss=0.4]
Epoch 16 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.35it/s, loss=0.402]
Epoch 16 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.31it/s, loss=0.402]
Epoch 16 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.31it/s, loss=0.4]
Epoch 16 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.31it/s, loss=0.4]
Epoch 16 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.31it/s, loss=0.402]
Epoch 16 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.24it/s, loss=0.402]
Epoch 16 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.24it/s, loss=0.399]
Epoch 16 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.24it/s, loss=0.399]
Epoch 16 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.24it/s, loss=0.4]
Epoch 16 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.43it/s, loss=0.4]
Epoch 16 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.43it/s, loss=0.399]
Epoch 16 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.43it/s, loss=0.399]
Epoch 16 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.43it/s, loss=0.398]
Epoch 16 [Train]: 60%|██████ | 78/129 [00:02<00:01, 25.97it/s, loss=0.398]
Epoch 16 [Train]: 60%|██████ | 78/129 [00:02<00:01, 25.97it/s, loss=0.398]
Epoch 16 [Train]: 60%|██████ | 78/129 [00:03<00:01, 25.97it/s, loss=0.399]
Epoch 16 [Train]: 60%|██████ | 78/129 [00:03<00:01, 25.97it/s, loss=0.399]
Epoch 16 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.64it/s, loss=0.399]
Epoch 16 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.64it/s, loss=0.398]
Epoch 16 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.64it/s, loss=0.398]
Epoch 16 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.64it/s, loss=0.396]
Epoch 16 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.39it/s, loss=0.396]
Epoch 16 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.39it/s, loss=0.396]
Epoch 16 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.39it/s, loss=0.402]
Epoch 16 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 25.39it/s, loss=0.401]
Epoch 16 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 25.24it/s, loss=0.401]
Epoch 16 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 25.24it/s, loss=0.399]
Epoch 16 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 25.24it/s, loss=0.4]
Epoch 16 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 25.24it/s, loss=0.4]
Epoch 16 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.53it/s, loss=0.4]
Epoch 16 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.53it/s, loss=0.407]
Epoch 16 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.53it/s, loss=0.407]
Epoch 16 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.53it/s, loss=0.409]
Epoch 16 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 26.04it/s, loss=0.409]
Epoch 16 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 26.04it/s, loss=0.409]
Epoch 16 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 26.04it/s, loss=0.407]
Epoch 16 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 26.04it/s, loss=0.409]
Epoch 16 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.84it/s, loss=0.409]
Epoch 16 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.84it/s, loss=0.41]
Epoch 16 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.84it/s, loss=0.409]
Epoch 16 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.84it/s, loss=0.409]
Epoch 16 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.45it/s, loss=0.409]
Epoch 16 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.45it/s, loss=0.408]
Epoch 16 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.45it/s, loss=0.406]
Epoch 16 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.45it/s, loss=0.405]
Epoch 16 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 25.56it/s, loss=0.405]
Epoch 16 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 25.56it/s, loss=0.405]
Epoch 16 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 25.56it/s, loss=0.404]
Epoch 16 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 25.56it/s, loss=0.405]
Epoch 16 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 26.35it/s, loss=0.405]
Epoch 16 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 26.35it/s, loss=0.405]
Epoch 16 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 26.35it/s, loss=0.407]
Epoch 16 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 26.35it/s, loss=0.405]
Epoch 16 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.76it/s, loss=0.405]
Epoch 16 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.76it/s, loss=0.404]
Epoch 16 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.76it/s, loss=0.406]
Epoch 16 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.76it/s, loss=0.405]
Epoch 16 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.73it/s, loss=0.405]
Epoch 16 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.73it/s, loss=0.404]
Epoch 16 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.73it/s, loss=0.403]
Epoch 16 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.73it/s, loss=0.403]
Epoch 16 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.07it/s, loss=0.403]
Epoch 16 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.07it/s, loss=0.408]
Epoch 16 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.07it/s, loss=0.408]
Epoch 16 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.07it/s, loss=0.41]
Epoch 16 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 25.70it/s, loss=0.41]
Epoch 16 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 25.70it/s, loss=0.409]
Epoch 16 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 25.70it/s, loss=0.41]
Epoch 16 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 25.70it/s, loss=0.41]
Epoch 16 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 25.42it/s, loss=0.41]
Epoch 16 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 25.42it/s, loss=0.411]
Epoch 16 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 25.42it/s, loss=0.412]
Epoch 16 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 25.42it/s, loss=0.411]
Epoch 16 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 25.85it/s, loss=0.411]
Epoch 16 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 25.85it/s, loss=0.412]
Epoch 16 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 25.85it/s, loss=0.411]
Epoch 16 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 25.85it/s, loss=0.412]
Epoch 16 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.18it/s, loss=0.412]
Epoch 16 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.18it/s, loss=0.413]
Epoch 16 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.18it/s, loss=0.412]
Epoch 16 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.18it/s, loss=0.412]
Epoch 16 [Train]: 100%|██████████| 129/129 [00:04<00:00, 26.62it/s, loss=0.412]
2026-08-07 06:51:16.206 | INFO  | __main__:pretrain:180 - Epoch 16/50 | Train Loss: 0.4120 | Val Loss: 0.7132
Epoch 17 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 17 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.293]
Epoch 17 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.42]
Epoch 17 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.395]
Epoch 17 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.03it/s, loss=0.395]
Epoch 17 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.03it/s, loss=0.434]
Epoch 17 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.03it/s, loss=0.405]
Epoch 17 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.03it/s, loss=0.4]
Epoch 17 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.28it/s, loss=0.4]
Epoch 17 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.28it/s, loss=0.425]
Epoch 17 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.28it/s, loss=0.409]
Epoch 17 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.28it/s, loss=0.402]
Epoch 17 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.99it/s, loss=0.402]
Epoch 17 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.99it/s, loss=0.391]
Epoch 17 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.99it/s, loss=0.398]
Epoch 17 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.99it/s, loss=0.398]
Epoch 17 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.49it/s, loss=0.398]
Epoch 17 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.49it/s, loss=0.415]
Epoch 17 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.49it/s, loss=0.42]
Epoch 17 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.49it/s, loss=0.411]
Epoch 17 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.51it/s, loss=0.411]
Epoch 17 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.51it/s, loss=0.404]
Epoch 17 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.51it/s, loss=0.412]
Epoch 17 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 26.51it/s, loss=0.423]
Epoch 17 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 25.89it/s, loss=0.423]
Epoch 17 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 25.89it/s, loss=0.419]
Epoch 17 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 25.89it/s, loss=0.415]
Epoch 17 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 25.89it/s, loss=0.409]
Epoch 17 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 25.58it/s, loss=0.409]
Epoch 17 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 25.58it/s, loss=0.404]
Epoch 17 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 25.58it/s, loss=0.407]
Epoch 17 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 25.58it/s, loss=0.406]
Epoch 17 [Train]: 19%|█▊ | 24/129 [00:00<00:04, 25.32it/s, loss=0.406]
Epoch 17 [Train]: 19%|█▊ | 24/129 [00:00<00:04, 25.32it/s, loss=0.404]
Epoch 17 [Train]: 19%|█▊ | 24/129 [00:01<00:04, 25.32it/s, loss=0.404]
Epoch 17 [Train]: 19%|█▊ | 24/129 [00:01<00:04, 25.32it/s, loss=0.407]
Epoch 17 [Train]: 21%|██ | 27/129 [00:01<00:04, 25.15it/s, loss=0.407]
Epoch 17 [Train]: 21%|██ | 27/129 [00:01<00:04, 25.15it/s, loss=0.405]
Epoch 17 [Train]: 21%|██ | 27/129 [00:01<00:04, 25.15it/s, loss=0.408]
Epoch 17 [Train]: 21%|██ | 27/129 [00:01<00:04, 25.15it/s, loss=0.413]
Epoch 17 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 25.08it/s, loss=0.413]
Epoch 17 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 25.08it/s, loss=0.415]
Epoch 17 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 25.08it/s, loss=0.414]
Epoch 17 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 25.08it/s, loss=0.409]
Epoch 17 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 24.99it/s, loss=0.409]
Epoch 17 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 24.99it/s, loss=0.41]
Epoch 17 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 24.99it/s, loss=0.42]
Epoch 17 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 24.99it/s, loss=0.414]
Epoch 17 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 24.93it/s, loss=0.414]
Epoch 17 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 24.93it/s, loss=0.412]
Epoch 17 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 24.93it/s, loss=0.411]
Epoch 17 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 24.93it/s, loss=0.41]
Epoch 17 [Train]: 30%|███ | 39/129 [00:01<00:03, 24.90it/s, loss=0.41]
Epoch 17 [Train]: 30%|███ | 39/129 [00:01<00:03, 24.90it/s, loss=0.407]
Epoch 17 [Train]: 30%|███ | 39/129 [00:01<00:03, 24.90it/s, loss=0.406]
Epoch 17 [Train]: 30%|███ | 39/129 [00:01<00:03, 24.90it/s, loss=0.403]
Epoch 17 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 24.92it/s, loss=0.403]
Epoch 17 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 24.92it/s, loss=0.402]
Epoch 17 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 24.92it/s, loss=0.402]
Epoch 17 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 24.92it/s, loss=0.401]
Epoch 17 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 24.94it/s, loss=0.401]
Epoch 17 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 24.94it/s, loss=0.4]
Epoch 17 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 24.94it/s, loss=0.398]
Epoch 17 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 24.94it/s, loss=0.398]
Epoch 17 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 24.95it/s, loss=0.398]
Epoch 17 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 24.95it/s, loss=0.396]
Epoch 17 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 24.95it/s, loss=0.398]
Epoch 17 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 24.95it/s, loss=0.397]
Epoch 17 [Train]: 40%|███▉ | 51/129 [00:01<00:03, 25.35it/s, loss=0.397]
Epoch 17 [Train]: 40%|███▉ | 51/129 [00:02<00:03, 25.35it/s, loss=0.395]
Epoch 17 [Train]: 40%|███▉ | 51/129 [00:02<00:03, 25.35it/s, loss=0.395]
Epoch 17 [Train]: 40%|███▉ | 51/129 [00:02<00:03, 25.35it/s, loss=0.4]
Epoch 17 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 25.34it/s, loss=0.4]
Epoch 17 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 25.34it/s, loss=0.4]
Epoch 17 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 25.34it/s, loss=0.399]
Epoch 17 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 25.34it/s, loss=0.398]
Epoch 17 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 25.56it/s, loss=0.398]
Epoch 17 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 25.56it/s, loss=0.395]
Epoch 17 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 25.56it/s, loss=0.393]
Epoch 17 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 25.56it/s, loss=0.392]
Epoch 17 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 25.74it/s, loss=0.392]
Epoch 17 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 25.74it/s, loss=0.391]
Epoch 17 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 25.74it/s, loss=0.391]
Epoch 17 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 25.74it/s, loss=0.392]
Epoch 17 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.01it/s, loss=0.392]
Epoch 17 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.01it/s, loss=0.393]
Epoch 17 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.01it/s, loss=0.392]
Epoch 17 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.01it/s, loss=0.39]
Epoch 17 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.61it/s, loss=0.39]
Epoch 17 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.61it/s, loss=0.39]
Epoch 17 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.61it/s, loss=0.388]
Epoch 17 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.61it/s, loss=0.387]
Epoch 17 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.58it/s, loss=0.387]
Epoch 17 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.58it/s, loss=0.387]
Epoch 17 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.58it/s, loss=0.388]
Epoch 17 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.58it/s, loss=0.387]
Epoch 17 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.20it/s, loss=0.387]
Epoch 17 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.20it/s, loss=0.391]
Epoch 17 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.20it/s, loss=0.391]
Epoch 17 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.20it/s, loss=0.397]
Epoch 17 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.32it/s, loss=0.397]
Epoch 17 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.32it/s, loss=0.397]
Epoch 17 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.32it/s, loss=0.396]
Epoch 17 [Train]: 58%|█████▊ | 75/129 [00:03<00:01, 27.32it/s, loss=0.398]
Epoch 17 [Train]: 60%|██████ | 78/129 [00:03<00:01, 27.22it/s, loss=0.398]
Epoch 17 [Train]: 60%|██████ | 78/129 [00:03<00:01, 27.22it/s, loss=0.398]
Epoch 17 [Train]: 60%|██████ | 78/129 [00:03<00:01, 27.22it/s, loss=0.397]
Epoch 17 [Train]: 60%|██████ | 78/129 [00:03<00:01, 27.22it/s, loss=0.396]
Epoch 17 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.21it/s, loss=0.396]
Epoch 17 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.21it/s, loss=0.396]
Epoch 17 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.21it/s, loss=0.396]
Epoch 17 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.21it/s, loss=0.396]
Epoch 17 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.05it/s, loss=0.396]
Epoch 17 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.05it/s, loss=0.396]
Epoch 17 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.05it/s, loss=0.396]
Epoch 17 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.05it/s, loss=0.397]
Epoch 17 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.35it/s, loss=0.397]
Epoch 17 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.35it/s, loss=0.398]
Epoch 17 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.35it/s, loss=0.396]
Epoch 17 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 26.35it/s, loss=0.395]
Epoch 17 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.74it/s, loss=0.395]
Epoch 17 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.74it/s, loss=0.394]
Epoch 17 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.74it/s, loss=0.394]
Epoch 17 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 25.74it/s, loss=0.394]
Epoch 17 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 25.70it/s, loss=0.394]
Epoch 17 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 25.70it/s, loss=0.394]
Epoch 17 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 25.70it/s, loss=0.393]
Epoch 17 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 25.70it/s, loss=0.392]
Epoch 17 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.99it/s, loss=0.392]
Epoch 17 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.99it/s, loss=0.392]
Epoch 17 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.99it/s, loss=0.393]
Epoch 17 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 25.99it/s, loss=0.392]
Epoch 17 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.65it/s, loss=0.392]
Epoch 17 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.65it/s, loss=0.392]
Epoch 17 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.65it/s, loss=0.391]
Epoch 17 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 25.65it/s, loss=0.391]
Epoch 17 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 25.96it/s, loss=0.391]
Epoch 17 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 25.96it/s, loss=0.393]
Epoch 17 [Train]: 79%|███████▉ | 102/129 [00:04<00:01, 25.96it/s, loss=0.394]
Epoch 17 [Train]: 79%|███████▉ | 102/129 [00:04<00:01, 25.96it/s, loss=0.395]
Epoch 17 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 25.67it/s, loss=0.395]
Epoch 17 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 25.67it/s, loss=0.395]
Epoch 17 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 25.67it/s, loss=0.394]
Epoch 17 [Train]: 81%|████████▏ | 105/129 [00:04<00:00, 25.67it/s, loss=0.396]
Epoch 17 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 25.98it/s, loss=0.396]
Epoch 17 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 25.98it/s, loss=0.397]
Epoch 17 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 25.98it/s, loss=0.397]
Epoch 17 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 25.98it/s, loss=0.397]
Epoch 17 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.61it/s, loss=0.397]
Epoch 17 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.61it/s, loss=0.396]
Epoch 17 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.61it/s, loss=0.395]
Epoch 17 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 26.61it/s, loss=0.395]
Epoch 17 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.81it/s, loss=0.395]
Epoch 17 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.81it/s, loss=0.394]
Epoch 17 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.81it/s, loss=0.394]
Epoch 17 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.81it/s, loss=0.395]
Epoch 17 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.66it/s, loss=0.395]
Epoch 17 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.66it/s, loss=0.394]
Epoch 17 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.66it/s, loss=0.394]
Epoch 17 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.66it/s, loss=0.394]
Epoch 17 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.10it/s, loss=0.394]
Epoch 17 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.10it/s, loss=0.394]
Epoch 17 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.10it/s, loss=0.395]
Epoch 17 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.10it/s, loss=0.395]
Epoch 17 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 25.67it/s, loss=0.395]
Epoch 17 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 25.67it/s, loss=0.395]
Epoch 17 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 25.67it/s, loss=0.395]
Epoch 17 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 25.67it/s, loss=0.396]
Epoch 17 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 25.92it/s, loss=0.396]
Epoch 17 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 25.92it/s, loss=0.395]
Epoch 17 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 25.92it/s, loss=0.395]
Epoch 17 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 25.92it/s, loss=0.395]
Epoch 17 [Train]: 100%|██████████| 129/129 [00:04<00:00, 25.75it/s, loss=0.395]
2026-08-07 06:51:21.334 | INFO  | __main__:pretrain:180 - Epoch 17/50 | Train Loss: 0.3953 | Val Loss: 0.6577
2026-08-07 06:51:21.344 | INFO  | __main__:pretrain:196 -  -> New best model (val_loss=0.6577)
Epoch 18 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 18 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.302]
Epoch 18 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.243]
Epoch 18 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.251]
Epoch 18 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.252]
Epoch 18 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.63it/s, loss=0.252]
Epoch 18 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.63it/s, loss=0.316]
Epoch 18 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.63it/s, loss=0.334]
Epoch 18 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.63it/s, loss=0.344]
Epoch 18 [Train]: 3%|▎ | 4/129 [00:00<00:03, 36.63it/s, loss=0.362]
Epoch 18 [Train]: 6%|▌ | 8/129 [00:00<00:03, 30.67it/s, loss=0.362]
Epoch 18 [Train]: 6%|▌ | 8/129 [00:00<00:03, 30.67it/s, loss=0.365]
Epoch 18 [Train]: 6%|▌ | 8/129 [00:00<00:03, 30.67it/s, loss=0.37]
Epoch 18 [Train]: 6%|▌ | 8/129 [00:00<00:03, 30.67it/s, loss=0.364]
Epoch 18 [Train]: 6%|▌ | 8/129 [00:00<00:03, 30.67it/s, loss=0.367]
Epoch 18 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.94it/s, loss=0.367]
Epoch 18 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.94it/s, loss=0.359]
Epoch 18 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.94it/s, loss=0.36]
Epoch 18 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.94it/s, loss=0.355]
Epoch 18 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.47it/s, loss=0.355]
Epoch 18 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.47it/s, loss=0.359]
Epoch 18 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.47it/s, loss=0.36]
Epoch 18 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.47it/s, loss=0.362]
Epoch 18 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.72it/s, loss=0.362]
Epoch 18 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.72it/s, loss=0.366]
Epoch 18 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.72it/s, loss=0.366]
Epoch 18 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.72it/s, loss=0.361]
Epoch 18 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.87it/s, loss=0.361]
Epoch 18 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.87it/s, loss=0.373]
Epoch 18 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.87it/s, loss=0.376]
Epoch 18 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.87it/s, loss=0.375]
Epoch 18 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.02it/s, loss=0.375]
Epoch 18 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.02it/s, loss=0.374]
Epoch 18 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.02it/s, loss=0.376]
Epoch 18 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.02it/s, loss=0.382]
Epoch 18 [Train]: 21%|██ | 27/129 [00:00<00:03, 27.74it/s, loss=0.382]
Epoch 18 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.74it/s, loss=0.384]
Epoch 18 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.74it/s, loss=0.384]
Epoch 18 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.74it/s, loss=0.381]
Epoch 18 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.46it/s, loss=0.381]
Epoch 18 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.46it/s, loss=0.378]
Epoch 18 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.46it/s, loss=0.376]
Epoch 18 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.46it/s, loss=0.375]
Epoch 18 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.69it/s, loss=0.375]
Epoch 18 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.69it/s, loss=0.375]
Epoch 18 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.69it/s, loss=0.375]
Epoch 18 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.69it/s, loss=0.386]
Epoch 18 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.36it/s, loss=0.386]
Epoch 18 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.36it/s, loss=0.383]
Epoch 18 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.36it/s, loss=0.383]
Epoch 18 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.36it/s, loss=0.383]
Epoch 18 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.64it/s, loss=0.383]
Epoch 18 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.64it/s, loss=0.381]
Epoch 18 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.64it/s, loss=0.38]
Epoch 18 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.64it/s, loss=0.381]
Epoch 18 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 28.06it/s, loss=0.381]
Epoch 18 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 28.06it/s, loss=0.382]
Epoch 18 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 28.06it/s, loss=0.382]
Epoch 18 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 28.06it/s, loss=0.382]
Epoch 18 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.46it/s, loss=0.382]
Epoch 18 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.46it/s, loss=0.382]
Epoch 18 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.46it/s, loss=0.381]
Epoch 18 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.46it/s, loss=0.38]
Epoch 18 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.78it/s, loss=0.38]
Epoch 18 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.78it/s, loss=0.385]
Epoch 18 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.78it/s, loss=0.383]
Epoch 18 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.78it/s, loss=0.379]
Epoch 18 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.25it/s, loss=0.379]
Epoch 18 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.25it/s, loss=0.379]
Epoch 18 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.25it/s, loss=0.377]
Epoch 18 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.25it/s, loss=0.381]
Epoch 18 [Train]: 42%|████▏ | 54/129 [00:01<00:02, 26.35it/s, loss=0.381]
Epoch 18 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.35it/s, loss=0.381]
Epoch 18 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.35it/s, loss=0.38]
Epoch 18 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.35it/s, loss=0.379]
Epoch 18 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.58it/s, loss=0.379]
Epoch 18 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.58it/s, loss=0.376]
Epoch 18 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.58it/s, loss=0.374]
Epoch 18 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.58it/s, loss=0.373]
Epoch 18 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.87it/s, loss=0.373]
Epoch 18 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.87it/s, loss=0.381]
Epoch 18 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.87it/s, loss=0.38]
Epoch 18 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.87it/s, loss=0.38]
Epoch 18 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.67it/s, loss=0.38]
Epoch 18 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.67it/s, loss=0.38]
Epoch 18 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.67it/s, loss=0.382]
Epoch 18 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.67it/s, loss=0.38]
Epoch 18 [Train]: 51%|█████ | 66/129 [00:02<00:02, 28.15it/s, loss=0.38]
Epoch 18 [Train]: 51%|█████ | 66/129 [00:02<00:02, 28.15it/s, loss=0.385]
Epoch 18 [Train]: 51%|█████ | 66/129 [00:02<00:02, 28.15it/s, loss=0.386]
Epoch 18 [Train]: 51%|█████ | 66/129 [00:02<00:02, 28.15it/s, loss=0.384]
Epoch 18 [Train]: 51%|█████ | 66/129 [00:02<00:02, 28.15it/s, loss=0.382]
Epoch 18 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 28.66it/s, loss=0.382]
Epoch 18 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 28.66it/s, loss=0.382]
Epoch 18 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 28.66it/s, loss=0.383]
Epoch 18 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 28.66it/s, loss=0.384]
Epoch 18 [Train]: 57%|█████▋ | 73/129 [00:02<00:01, 28.52it/s, loss=0.384]
Epoch 18 [Train]: 57%|█████▋ | 73/129 [00:02<00:01, 28.52it/s, loss=0.383]
Epoch 18 [Train]: 57%|█████▋ | 73/129 [00:02<00:01, 28.52it/s, loss=0.381]
Epoch 18 [Train]: 57%|█████▋ | 73/129 [00:02<00:01, 28.52it/s, loss=0.381]
Epoch 18 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.77it/s, loss=0.381]
Epoch 18 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.77it/s, loss=0.38]
Epoch 18 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.77it/s, loss=0.379]
Epoch 18 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.77it/s, loss=0.377]
Epoch 18 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.17it/s, loss=0.377]
Epoch 18 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.17it/s, loss=0.377]
Epoch 18 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.17it/s, loss=0.38]
Epoch 18 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.17it/s, loss=0.382]
Epoch 18 [Train]: 64%|██████▎ | 82/129 [00:02<00:01, 26.65it/s, loss=0.382]
Epoch 18 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.65it/s, loss=0.382]
Epoch 18 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.65it/s, loss=0.382]
Epoch 18 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.65it/s, loss=0.381]
Epoch 18 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.70it/s, loss=0.381]
Epoch 18 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.70it/s, loss=0.379]
Epoch 18 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.70it/s, loss=0.378]
Epoch 18 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.70it/s, loss=0.377]
Epoch 18 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 26.33it/s, loss=0.377]
Epoch 18 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 26.33it/s, loss=0.375]
Epoch 18 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 26.33it/s, loss=0.375]
Epoch 18 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 26.33it/s, loss=0.375]
Epoch 18 [Train]: 71%|███████ | 91/129 [00:03<00:01, 26.42it/s, loss=0.375]
Epoch 18 [Train]: 71%|███████ | 91/129 [00:03<00:01, 26.42it/s, loss=0.375]
Epoch 18 [Train]: 71%|███████ | 91/129 [00:03<00:01, 26.42it/s, loss=0.375]
Epoch 18 [Train]: 71%|███████ | 91/129 [00:03<00:01, 26.42it/s, loss=0.375]
Epoch 18 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.63it/s, loss=0.375]
Epoch 18 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.63it/s, loss=0.374]
Epoch 18 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.63it/s, loss=0.374]
Epoch 18 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.63it/s, loss=0.375]
Epoch 18 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.23it/s, loss=0.375]
Epoch 18 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.23it/s, loss=0.374]
Epoch 18 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.23it/s, loss=0.374]
Epoch 18 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.23it/s, loss=0.375]
Epoch 18 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.56it/s, loss=0.375]
Epoch 18 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.56it/s, loss=0.375]
Epoch 18 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.56it/s, loss=0.374]
Epoch 18 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.56it/s, loss=0.373]
Epoch 18 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.69it/s, loss=0.373]
Epoch 18 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.69it/s, loss=0.373]
Epoch 18 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.69it/s, loss=0.374]
Epoch 18 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.69it/s, loss=0.374]
Epoch 18 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.86it/s, loss=0.374]
Epoch 18 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.86it/s, loss=0.375]
Epoch 18 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.86it/s, loss=0.375]
Epoch 18 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.86it/s, loss=0.374]
Epoch 18 [Train]: 84%|████████▍ | 109/129 [00:03<00:00, 26.96it/s, loss=0.374]
Epoch 18 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.96it/s, loss=0.374]
Epoch 18 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.96it/s, loss=0.374]
Epoch 18 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.96it/s, loss=0.374]
Epoch 18 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 27.31it/s, loss=0.374]
Epoch 18 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 27.31it/s, loss=0.375]
Epoch 18 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 27.31it/s, loss=0.374]
Epoch 18 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 27.31it/s, loss=0.375]
Epoch 18 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.89it/s, loss=0.375]
Epoch 18 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.89it/s, loss=0.376]
Epoch 18 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.89it/s, loss=0.376]
Epoch 18 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.89it/s, loss=0.375]
Epoch 18 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.88it/s, loss=0.375]
Epoch 18 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.88it/s, loss=0.376]
Epoch 18 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.88it/s, loss=0.376]
Epoch 18 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.88it/s, loss=0.375]
Epoch 18 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.87it/s, loss=0.375]
Epoch 18 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.87it/s, loss=0.375]
Epoch 18 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.87it/s, loss=0.376]
Epoch 18 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.87it/s, loss=0.376]
Epoch 18 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.47it/s, loss=0.376]
Epoch 18 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.47it/s, loss=0.376]
Epoch 18 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.47it/s, loss=0.376]
Epoch 18 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.47it/s, loss=0.375]
Epoch 18 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.50it/s, loss=0.375]
Epoch 18 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.50it/s, loss=0.375]
Epoch 18 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.50it/s, loss=0.374]
2026-08-07 06:51:26.251 | INFO  | __main__:pretrain:180 - Epoch 18/50 | Train Loss: 0.3738 | Val Loss: 0.6736
Epoch 19 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 19 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.418]
Epoch 19 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.446]
Epoch 19 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.416]
Epoch 19 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.419]
Epoch 19 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.25it/s, loss=0.419]
Epoch 19 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.25it/s, loss=0.388]
Epoch 19 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.25it/s, loss=0.464]
Epoch 19 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.25it/s, loss=0.436]
Epoch 19 [Train]: 5%|▌ | 7/129 [00:00<00:04, 26.78it/s, loss=0.436]
Epoch 19 [Train]: 5%|▌ | 7/129 [00:00<00:04, 26.78it/s, loss=0.424]
Epoch 19 [Train]: 5%|▌ | 7/129 [00:00<00:04, 26.78it/s, loss=0.412]
Epoch 19 [Train]: 5%|▌ | 7/129 [00:00<00:04, 26.78it/s, loss=0.4]
Epoch 19 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.04it/s, loss=0.4]
Epoch 19 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.04it/s, loss=0.392]
Epoch 19 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.04it/s, loss=0.39]
Epoch 19 [Train]: 8%|▊ | 10/129 [00:00<00:04, 26.04it/s, loss=0.386]
Epoch 19 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.31it/s, loss=0.386]
Epoch 19 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.31it/s, loss=0.381]
Epoch 19 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.31it/s, loss=0.372]
Epoch 19 [Train]: 10%|█ | 13/129 [00:00<00:04, 26.31it/s, loss=0.372]
Epoch 19 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.54it/s, loss=0.372]
Epoch 19 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.54it/s, loss=0.368]
Epoch 19 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.54it/s, loss=0.364]
Epoch 19 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 26.54it/s, loss=0.368]
Epoch 19 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.73it/s, loss=0.368]
Epoch 19 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.73it/s, loss=0.365]
Epoch 19 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.73it/s, loss=0.37]
Epoch 19 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 26.73it/s, loss=0.371]
Epoch 19 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 26.06it/s, loss=0.371]
Epoch 19 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 26.06it/s, loss=0.368]
Epoch 19 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 26.06it/s, loss=0.363]
Epoch 19 [Train]: 17%|█▋ | 22/129 [00:00<00:04, 26.06it/s, loss=0.371]
Epoch 19 [Train]: 19%|█▉ | 25/129 [00:00<00:04, 25.65it/s, loss=0.371]
Epoch 19 [Train]: 19%|█▉ | 25/129 [00:00<00:04, 25.65it/s, loss=0.371]
Epoch 19 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 25.65it/s, loss=0.369]
Epoch 19 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 25.65it/s, loss=0.366]
Epoch 19 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 25.59it/s, loss=0.366]
Epoch 19 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 25.59it/s, loss=0.369]
Epoch 19 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 25.59it/s, loss=0.365]
Epoch 19 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 25.59it/s, loss=0.365]
Epoch 19 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.43it/s, loss=0.365]
Epoch 19 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.43it/s, loss=0.364]
Epoch 19 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.43it/s, loss=0.361]
Epoch 19 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.43it/s, loss=0.362]
Epoch 19 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.75it/s, loss=0.362]
Epoch 19 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.75it/s, loss=0.36]
Epoch 19 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.75it/s, loss=0.357]
Epoch 19 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.75it/s, loss=0.357]
Epoch 19 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.04it/s, loss=0.357]
Epoch 19 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.04it/s, loss=0.361]
Epoch 19 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.04it/s, loss=0.36]
Epoch 19 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.04it/s, loss=0.365]
Epoch 19 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.17it/s, loss=0.365]
Epoch 19 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.17it/s, loss=0.363]
Epoch 19 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.17it/s, loss=0.362]
Epoch 19 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.17it/s, loss=0.361]
Epoch 19 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.52it/s, loss=0.361]
Epoch 19 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.52it/s, loss=0.36]
Epoch 19 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.52it/s, loss=0.358]
Epoch 19 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.52it/s, loss=0.361]
Epoch 19 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.57it/s, loss=0.361]
Epoch 19 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.57it/s, loss=0.36]
Epoch 19 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.57it/s, loss=0.359]
Epoch 19 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.57it/s, loss=0.36]
Epoch 19 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.22it/s, loss=0.36]
Epoch 19 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.22it/s, loss=0.361]
Epoch 19 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.22it/s, loss=0.361]
Epoch 19 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.22it/s, loss=0.361]
Epoch 19 [Train]: 40%|████ | 52/129 [00:01<00:02, 26.99it/s, loss=0.361]
Epoch 19 [Train]: 40%|████ | 52/129 [00:01<00:02, 26.99it/s, loss=0.364]
Epoch 19 [Train]: 40%|████ | 52/129 [00:02<00:02, 26.99it/s, loss=0.363]
Epoch 19 [Train]: 40%|████ | 52/129 [00:02<00:02, 26.99it/s, loss=0.361]
Epoch 19 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.26it/s, loss=0.361]
Epoch 19 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.26it/s, loss=0.361]
Epoch 19 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.26it/s, loss=0.361]
Epoch 19 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.26it/s, loss=0.361]
Epoch 19 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.80it/s, loss=0.361]
Epoch 19 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.80it/s, loss=0.362]
Epoch 19 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.80it/s, loss=0.361]
Epoch 19 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.80it/s, loss=0.361]
Epoch 19 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.33it/s, loss=0.361]
Epoch 19 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.33it/s, loss=0.359]
Epoch 19 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.33it/s, loss=0.356]
Epoch 19 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.33it/s, loss=0.357]
Epoch 19 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.82it/s, loss=0.357]
Epoch 19 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.82it/s, loss=0.358]
Epoch 19 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.82it/s, loss=0.359]
Epoch 19 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.82it/s, loss=0.36]
Epoch 19 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.56it/s, loss=0.36]
Epoch 19 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.56it/s, loss=0.359]
Epoch 19 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.56it/s, loss=0.358]
Epoch 19 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.56it/s, loss=0.358]
Epoch 19 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.56it/s, loss=0.358]
Epoch 19 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.56it/s, loss=0.358]
Epoch 19 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.56it/s, loss=0.358]
Epoch 19 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.56it/s, loss=0.357]
Epoch 19 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.67it/s, loss=0.357]
Epoch 19 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.67it/s, loss=0.359]
Epoch 19 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.67it/s, loss=0.359]
Epoch 19 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.67it/s, loss=0.36]
Epoch 19 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.65it/s, loss=0.36]
Epoch 19 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.65it/s, loss=0.361]
Epoch 19 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.65it/s, loss=0.362]
Epoch 19 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.65it/s, loss=0.361]
Epoch 19 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.50it/s, loss=0.361]
Epoch 19 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.50it/s, loss=0.361]
Epoch 19 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.50it/s, loss=0.362]
Epoch 19 [Train]: 61%|██████ | 79/129 [00:03<00:01, 27.50it/s, loss=0.361]
Epoch 19 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 27.69it/s, loss=0.361]
Epoch 19 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 27.69it/s, loss=0.359]
Epoch 19 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 27.69it/s, loss=0.361]
Epoch 19 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 27.69it/s, loss=0.36]
Epoch 19 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.46it/s, loss=0.36]
Epoch 19 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.46it/s, loss=0.36]
Epoch 19 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.46it/s, loss=0.362]
Epoch 19 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.46it/s, loss=0.362]
Epoch 19 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.51it/s, loss=0.362]
Epoch 19 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.51it/s, loss=0.362]
Epoch 19 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.51it/s, loss=0.362]
Epoch 19 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.51it/s, loss=0.362]
Epoch 19 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.43it/s, loss=0.362]
Epoch 19 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.43it/s, loss=0.362]
Epoch 19 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.43it/s, loss=0.362]
Epoch 19 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.43it/s, loss=0.364]
Epoch 19 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.35it/s, loss=0.364]
Epoch 19 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.35it/s, loss=0.363]
Epoch 19 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.35it/s, loss=0.362]
Epoch 19 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.35it/s, loss=0.362]
Epoch 19 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.53it/s, loss=0.362]
Epoch 19 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.53it/s, loss=0.362]
Epoch 19 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.53it/s, loss=0.362]
Epoch 19 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.53it/s, loss=0.361]
Epoch 19 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 25.96it/s, loss=0.361]
Epoch 19 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 25.96it/s, loss=0.362]
Epoch 19 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 25.96it/s, loss=0.361]
Epoch 19 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 25.96it/s, loss=0.362]
Epoch 19 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.43it/s, loss=0.362]
Epoch 19 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.43it/s, loss=0.362]
Epoch 19 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.43it/s, loss=0.362]
Epoch 19 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.43it/s, loss=0.361]
Epoch 19 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.98it/s, loss=0.361]
Epoch 19 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.98it/s, loss=0.362]
Epoch 19 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 26.98it/s, loss=0.365]
Epoch 19 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 26.98it/s, loss=0.367]
Epoch 19 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.73it/s, loss=0.367]
Epoch 19 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.73it/s, loss=0.367]
Epoch 19 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.73it/s, loss=0.369]
Epoch 19 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.73it/s, loss=0.368]
Epoch 19 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 27.25it/s, loss=0.368]
Epoch 19 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 27.25it/s, loss=0.368]
Epoch 19 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 27.25it/s, loss=0.368]
Epoch 19 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 27.25it/s, loss=0.368]
Epoch 19 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.47it/s, loss=0.368]
Epoch 19 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.47it/s, loss=0.367]
Epoch 19 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.47it/s, loss=0.367]
Epoch 19 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.47it/s, loss=0.366]
Epoch 19 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.64it/s, loss=0.366]
Epoch 19 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.64it/s, loss=0.366]
Epoch 19 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.64it/s, loss=0.365]
Epoch 19 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.64it/s, loss=0.367]
Epoch 19 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.86it/s, loss=0.367]
Epoch 19 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.86it/s, loss=0.366]
Epoch 19 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.86it/s, loss=0.37]
Epoch 19 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.86it/s, loss=0.37]
Epoch 19 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.74it/s, loss=0.37]
Epoch 19 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.74it/s, loss=0.37]
Epoch 19 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.74it/s, loss=0.37]
Epoch 19 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.74it/s, loss=0.371]
Epoch 19 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.30it/s, loss=0.371]
Epoch 19 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.30it/s, loss=0.371]
Epoch 19 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 26.30it/s, loss=0.371]
2026-08-07 06:51:31.209 | INFO  | __main__:pretrain:180 - Epoch 19/50 | Train Loss: 0.3710 | Val Loss: 0.7037
Epoch 20 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 20 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.344]
Epoch 20 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.354]
Epoch 20 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.345]
Epoch 20 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.61it/s, loss=0.345]
Epoch 20 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.61it/s, loss=0.313]
Epoch 20 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.61it/s, loss=0.342]
Epoch 20 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.61it/s, loss=0.346]
Epoch 20 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.86it/s, loss=0.346]
Epoch 20 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.86it/s, loss=0.358]
Epoch 20 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.86it/s, loss=0.372]
Epoch 20 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.86it/s, loss=0.36]
Epoch 20 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.24it/s, loss=0.36]
Epoch 20 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.24it/s, loss=0.369]
Epoch 20 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.24it/s, loss=0.362]
Epoch 20 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.24it/s, loss=0.358]
Epoch 20 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.10it/s, loss=0.358]
Epoch 20 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.10it/s, loss=0.367]
Epoch 20 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.10it/s, loss=0.358]
Epoch 20 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.10it/s, loss=0.349]
Epoch 20 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.82it/s, loss=0.349]
Epoch 20 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.82it/s, loss=0.343]
Epoch 20 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.82it/s, loss=0.337]
Epoch 20 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.82it/s, loss=0.335]
Epoch 20 [Train]: 14%|█▍ | 18/129 [00:00<00:03, 28.02it/s, loss=0.335]
Epoch 20 [Train]: 14%|█▍ | 18/129 [00:00<00:03, 28.02it/s, loss=0.343]
Epoch 20 [Train]: 14%|█▍ | 18/129 [00:00<00:03, 28.02it/s, loss=0.341]
Epoch 20 [Train]: 14%|█▍ | 18/129 [00:00<00:03, 28.02it/s, loss=0.344]
Epoch 20 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.90it/s, loss=0.344]
Epoch 20 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.90it/s, loss=0.349]
Epoch 20 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.90it/s, loss=0.344]
Epoch 20 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.90it/s, loss=0.346]
Epoch 20 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 28.17it/s, loss=0.346]
Epoch 20 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 28.17it/s, loss=0.343]
Epoch 20 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 28.17it/s, loss=0.346]
Epoch 20 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 28.17it/s, loss=0.344]
Epoch 20 [Train]: 21%|██ | 27/129 [00:00<00:03, 27.93it/s, loss=0.344]
Epoch 20 [Train]: 21%|██ | 27/129 [00:00<00:03, 27.93it/s, loss=0.341]
Epoch 20 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.93it/s, loss=0.343]
Epoch 20 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.93it/s, loss=0.345]
Epoch 20 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.88it/s, loss=0.345]
Epoch 20 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.88it/s, loss=0.347]
Epoch 20 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.88it/s, loss=0.344]
Epoch 20 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.88it/s, loss=0.348]
Epoch 20 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.72it/s, loss=0.348]
Epoch 20 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.72it/s, loss=0.35]
Epoch 20 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.72it/s, loss=0.35]
Epoch 20 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.72it/s, loss=0.352]
Epoch 20 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.97it/s, loss=0.352]
Epoch 20 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.97it/s, loss=0.355]
Epoch 20 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.97it/s, loss=0.352]
Epoch 20 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.97it/s, loss=0.351]
Epoch 20 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.15it/s, loss=0.351]
Epoch 20 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.15it/s, loss=0.353]
Epoch 20 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.15it/s, loss=0.357]
Epoch 20 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.15it/s, loss=0.355]
Epoch 20 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.54it/s, loss=0.355]
Epoch 20 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.54it/s, loss=0.355]
Epoch 20 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.54it/s, loss=0.351]
Epoch 20 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.54it/s, loss=0.351]
Epoch 20 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.32it/s, loss=0.351]
Epoch 20 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.32it/s, loss=0.353]
Epoch 20 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.32it/s, loss=0.353]
Epoch 20 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 27.32it/s, loss=0.355]
Epoch 20 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.98it/s, loss=0.355]
Epoch 20 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.98it/s, loss=0.356]
Epoch 20 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.98it/s, loss=0.358]
Epoch 20 [Train]: 37%|███▋ | 48/129 [00:01<00:02, 27.98it/s, loss=0.361]
Epoch 20 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 28.30it/s, loss=0.361]
Epoch 20 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 28.30it/s, loss=0.361]
Epoch 20 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 28.30it/s, loss=0.36]
Epoch 20 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 28.30it/s, loss=0.36]
Epoch 20 [Train]: 42%|████▏ | 54/129 [00:01<00:02, 28.08it/s, loss=0.36]
Epoch 20 [Train]: 42%|████▏ | 54/129 [00:01<00:02, 28.08it/s, loss=0.359]
Epoch 20 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 28.08it/s, loss=0.358]
Epoch 20 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 28.08it/s, loss=0.358]
Epoch 20 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.82it/s, loss=0.358]
Epoch 20 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.82it/s, loss=0.357]
Epoch 20 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.82it/s, loss=0.356]
Epoch 20 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.82it/s, loss=0.353]
Epoch 20 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.61it/s, loss=0.353]
Epoch 20 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.61it/s, loss=0.353]
Epoch 20 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.61it/s, loss=0.353]
Epoch 20 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.61it/s, loss=0.355]
Epoch 20 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.78it/s, loss=0.355]
Epoch 20 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.78it/s, loss=0.354]
Epoch 20 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.78it/s, loss=0.353]
Epoch 20 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.78it/s, loss=0.355]
Epoch 20 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.52it/s, loss=0.355]
Epoch 20 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.52it/s, loss=0.355]
Epoch 20 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.52it/s, loss=0.356]
Epoch 20 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.52it/s, loss=0.355]
Epoch 20 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.72it/s, loss=0.355]
Epoch 20 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.72it/s, loss=0.355]
Epoch 20 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.72it/s, loss=0.355]
Epoch 20 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.72it/s, loss=0.353]
Epoch 20 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.48it/s, loss=0.353]
Epoch 20 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.48it/s, loss=0.353]
Epoch 20 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.48it/s, loss=0.352]
Epoch 20 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.48it/s, loss=0.352]
Epoch 20 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.72it/s, loss=0.352]
Epoch 20 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.72it/s, loss=0.352]
Epoch 20 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.72it/s, loss=0.351]
Epoch 20 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.72it/s, loss=0.351]
Epoch 20 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.15it/s, loss=0.351]
Epoch 20 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.15it/s, loss=0.351]
Epoch 20 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.15it/s, loss=0.35]
Epoch 20 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.15it/s, loss=0.35]
Epoch 20 [Train]: 63%|██████▎ | 81/129 [00:02<00:01, 25.97it/s, loss=0.35]
Epoch 20 [Train]: 63%|██████▎ | 81/129 [00:02<00:01, 25.97it/s, loss=0.354]
Epoch 20 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.97it/s, loss=0.356]
Epoch 20 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 25.97it/s, loss=0.357]
Epoch 20 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.76it/s, loss=0.357]
Epoch 20 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.76it/s, loss=0.356]
Epoch 20 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.76it/s, loss=0.355]
Epoch 20 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 26.76it/s, loss=0.354]
Epoch 20 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.14it/s, loss=0.354]
Epoch 20 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.14it/s, loss=0.356]
Epoch 20 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.14it/s, loss=0.356]
Epoch 20 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.14it/s, loss=0.355]
Epoch 20 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.45it/s, loss=0.355]
Epoch 20 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.45it/s, loss=0.359]
Epoch 20 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.45it/s, loss=0.358]
Epoch 20 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.45it/s, loss=0.36]
Epoch 20 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.38it/s, loss=0.36]
Epoch 20 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.38it/s, loss=0.36]
Epoch 20 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.38it/s, loss=0.36]
Epoch 20 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.38it/s, loss=0.362]
Epoch 20 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.80it/s, loss=0.362]
Epoch 20 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.80it/s, loss=0.362]
Epoch 20 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.80it/s, loss=0.361]
Epoch 20 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.80it/s, loss=0.361]
Epoch 20 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.65it/s, loss=0.361]
Epoch 20 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.65it/s, loss=0.359]
Epoch 20 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.65it/s, loss=0.359]
Epoch 20 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.65it/s, loss=0.359]
Epoch 20 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.81it/s, loss=0.359]
Epoch 20 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.81it/s, loss=0.36]
Epoch 20 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.81it/s, loss=0.36]
Epoch 20 [Train]: 79%|███████▉ | 102/129 [00:03<00:01, 26.81it/s, loss=0.36]
Epoch 20 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 26.85it/s, loss=0.36]
Epoch 20 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 26.85it/s, loss=0.361]
Epoch 20 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 26.85it/s, loss=0.361]
Epoch 20 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 26.85it/s, loss=0.363]
Epoch 20 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 26.50it/s, loss=0.363]
Epoch 20 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 26.50it/s, loss=0.363]
Epoch 20 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.50it/s, loss=0.362]
Epoch 20 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 26.50it/s, loss=0.362]
Epoch 20 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.06it/s, loss=0.362]
Epoch 20 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.06it/s, loss=0.361]
Epoch 20 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.06it/s, loss=0.36]
Epoch 20 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.06it/s, loss=0.36]
Epoch 20 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.55it/s, loss=0.36]
Epoch 20 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.55it/s, loss=0.36]
Epoch 20 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.55it/s, loss=0.36]
Epoch 20 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.55it/s, loss=0.36]
Epoch 20 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.70it/s, loss=0.36]
Epoch 20 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.70it/s, loss=0.36]
Epoch 20 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.70it/s, loss=0.361]
Epoch 20 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 26.70it/s, loss=0.362]
Epoch 20 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.81it/s, loss=0.362]
Epoch 20 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.81it/s, loss=0.363]
Epoch 20 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.81it/s, loss=0.362]
Epoch 20 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.81it/s, loss=0.363]
Epoch 20 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.30it/s, loss=0.363]
Epoch 20 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.30it/s, loss=0.363]
Epoch 20 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.30it/s, loss=0.363]
Epoch 20 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 26.30it/s, loss=0.363]
Epoch 20 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.73it/s, loss=0.363]
Epoch 20 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.73it/s, loss=0.363]
Epoch 20 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.73it/s, loss=0.362]
Epoch 20 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 26.73it/s, loss=0.362]
Epoch 20 [Train]: 100%|██████████| 129/129 [00:04<00:00, 27.08it/s, loss=0.362]
2026-08-07 06:51:36.091 | INFO  | __main__:pretrain:180 - Epoch 20/50 | Train Loss: 0.3622 | Val Loss: 0.6836
Epoch 21 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 21 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.598]
Epoch 21 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.485]
Epoch 21 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.413]
Epoch 21 [Train]: 2%|▏ | 3/129 [00:00<00:04, 28.96it/s, loss=0.413]
Epoch 21 [Train]: 2%|▏ | 3/129 [00:00<00:04, 28.96it/s, loss=0.376]
Epoch 21 [Train]: 2%|▏ | 3/129 [00:00<00:04, 28.96it/s, loss=0.37]
Epoch 21 [Train]: 2%|▏ | 3/129 [00:00<00:04, 28.96it/s, loss=0.383]
Epoch 21 [Train]: 5%|▍ | 6/129 [00:00<00:04, 27.46it/s, loss=0.383]
Epoch 21 [Train]: 5%|▍ | 6/129 [00:00<00:04, 27.46it/s, loss=0.389]
Epoch 21 [Train]: 5%|▍ | 6/129 [00:00<00:04, 27.46it/s, loss=0.391]
Epoch 21 [Train]: 5%|▍ | 6/129 [00:00<00:04, 27.46it/s, loss=0.379]
Epoch 21 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.54it/s, loss=0.379]
Epoch 21 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.54it/s, loss=0.389]
Epoch 21 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.54it/s, loss=0.388]
Epoch 21 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.54it/s, loss=0.392]
Epoch 21 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.36it/s, loss=0.392]
Epoch 21 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.36it/s, loss=0.389]
Epoch 21 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.36it/s, loss=0.387]
Epoch 21 [Train]: 9%|▉ | 12/129 [00:00<00:04, 27.36it/s, loss=0.382]
Epoch 21 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.18it/s, loss=0.382]
Epoch 21 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.18it/s, loss=0.415]
Epoch 21 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.18it/s, loss=0.418]
Epoch 21 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.18it/s, loss=0.412]
Epoch 21 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.49it/s, loss=0.412]
Epoch 21 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.49it/s, loss=0.404]
Epoch 21 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.49it/s, loss=0.396]
Epoch 21 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.49it/s, loss=0.404]
Epoch 21 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.63it/s, loss=0.404]
Epoch 21 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.63it/s, loss=0.399]
Epoch 21 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.63it/s, loss=0.397]
Epoch 21 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.63it/s, loss=0.396]
Epoch 21 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.91it/s, loss=0.396]
Epoch 21 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.91it/s, loss=0.395]
Epoch 21 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.91it/s, loss=0.399]
Epoch 21 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.91it/s, loss=0.398]
Epoch 21 [Train]: 21%|██ | 27/129 [00:00<00:03, 27.45it/s, loss=0.398]
Epoch 21 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.45it/s, loss=0.4]
Epoch 21 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.45it/s, loss=0.397]
Epoch 21 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.45it/s, loss=0.393]
Epoch 21 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.59it/s, loss=0.393]
Epoch 21 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.59it/s, loss=0.389]
Epoch 21 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.59it/s, loss=0.39]
Epoch 21 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.59it/s, loss=0.384]
Epoch 21 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.18it/s, loss=0.384]
Epoch 21 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.18it/s, loss=0.385]
Epoch 21 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.18it/s, loss=0.386]
Epoch 21 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.18it/s, loss=0.383]
Epoch 21 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.49it/s, loss=0.383]
Epoch 21 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.49it/s, loss=0.384]
Epoch 21 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.49it/s, loss=0.382]
Epoch 21 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.49it/s, loss=0.379]
Epoch 21 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.51it/s, loss=0.379]
Epoch 21 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.51it/s, loss=0.377]
Epoch 21 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.51it/s, loss=0.378]
Epoch 21 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.51it/s, loss=0.378]
Epoch 21 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.10it/s, loss=0.378]
Epoch 21 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.10it/s, loss=0.38]
Epoch 21 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.10it/s, loss=0.378]
Epoch 21 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.10it/s, loss=0.379]
Epoch 21 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.64it/s, loss=0.379]
Epoch 21 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.64it/s, loss=0.376]
Epoch 21 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.64it/s, loss=0.376]
Epoch 21 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.64it/s, loss=0.374]
Epoch 21 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.51it/s, loss=0.374]
Epoch 21 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.51it/s, loss=0.376]
Epoch 21 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.51it/s, loss=0.375]
Epoch 21 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.51it/s, loss=0.373]
Epoch 21 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.62it/s, loss=0.373]
Epoch 21 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.62it/s, loss=0.372]
Epoch 21 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.62it/s, loss=0.372]
Epoch 21 [Train]: 40%|███▉ | 51/129 [00:02<00:02, 26.62it/s, loss=0.37]
Epoch 21 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.07it/s, loss=0.37]
Epoch 21 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.07it/s, loss=0.371]
Epoch 21 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.07it/s, loss=0.37]
Epoch 21 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.07it/s, loss=0.373]
Epoch 21 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.94it/s, loss=0.373]
Epoch 21 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.94it/s, loss=0.37]
Epoch 21 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.94it/s, loss=0.368]
Epoch 21 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 26.94it/s, loss=0.369]
Epoch 21 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.08it/s, loss=0.369]
Epoch 21 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.08it/s, loss=0.369]
Epoch 21 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.08it/s, loss=0.368]
Epoch 21 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.08it/s, loss=0.368]
Epoch 21 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.94it/s, loss=0.368]
Epoch 21 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.94it/s, loss=0.368]
Epoch 21 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.94it/s, loss=0.369]
Epoch 21 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.94it/s, loss=0.371]
Epoch 21 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.65it/s, loss=0.371]
Epoch 21 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.65it/s, loss=0.373]
Epoch 21 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.65it/s, loss=0.372]
Epoch 21 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.65it/s, loss=0.373]
Epoch 21 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.39it/s, loss=0.373]
Epoch 21 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.39it/s, loss=0.37]
Epoch 21 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.39it/s, loss=0.368]
Epoch 21 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.39it/s, loss=0.367]
Epoch 21 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.16it/s, loss=0.367]
Epoch 21 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.16it/s, loss=0.367]
Epoch 21 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.16it/s, loss=0.365]
Epoch 21 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.16it/s, loss=0.364]
Epoch 21 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.24it/s, loss=0.364]
Epoch 21 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.24it/s, loss=0.364]
Epoch 21 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.24it/s, loss=0.365]
Epoch 21 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.24it/s, loss=0.366]
Epoch 21 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.74it/s, loss=0.366]
Epoch 21 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.74it/s, loss=0.364]
Epoch 21 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.74it/s, loss=0.363]
Epoch 21 [Train]: 60%|██████ | 78/129 [00:03<00:01, 27.74it/s, loss=0.367]
Epoch 21 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.98it/s, loss=0.367]
Epoch 21 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.98it/s, loss=0.37]
Epoch 21 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.98it/s, loss=0.369]
Epoch 21 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.98it/s, loss=0.369]
Epoch 21 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.14it/s, loss=0.369]
Epoch 21 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.14it/s, loss=0.368]
Epoch 21 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.14it/s, loss=0.368]
Epoch 21 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.14it/s, loss=0.368]
Epoch 21 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.57it/s, loss=0.368]
Epoch 21 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.57it/s, loss=0.368]
Epoch 21 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.57it/s, loss=0.368]
Epoch 21 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.57it/s, loss=0.366]
Epoch 21 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.11it/s, loss=0.366]
Epoch 21 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.11it/s, loss=0.365]
Epoch 21 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.11it/s, loss=0.365]
Epoch 21 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.11it/s, loss=0.365]
Epoch 21 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.23it/s, loss=0.365]
Epoch 21 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.23it/s, loss=0.364]
Epoch 21 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.23it/s, loss=0.364]
Epoch 21 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.23it/s, loss=0.365]
Epoch 21 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.46it/s, loss=0.365]
Epoch 21 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.46it/s, loss=0.367]
Epoch 21 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.46it/s, loss=0.367]
Epoch 21 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.46it/s, loss=0.367]
Epoch 21 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.42it/s, loss=0.367]
Epoch 21 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.42it/s, loss=0.369]
Epoch 21 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.42it/s, loss=0.367]
Epoch 21 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.42it/s, loss=0.367]
Epoch 21 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.22it/s, loss=0.367]
Epoch 21 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.22it/s, loss=0.367]
Epoch 21 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.22it/s, loss=0.368]
Epoch 21 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.22it/s, loss=0.367]
Epoch 21 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.12it/s, loss=0.367]
Epoch 21 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.12it/s, loss=0.366]
Epoch 21 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.12it/s, loss=0.366]
Epoch 21 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.12it/s, loss=0.368]
Epoch 21 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 27.87it/s, loss=0.368]
Epoch 21 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.87it/s, loss=0.368]
Epoch 21 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.87it/s, loss=0.367]
Epoch 21 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.87it/s, loss=0.366]
Epoch 21 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.02it/s, loss=0.366]
Epoch 21 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.02it/s, loss=0.365]
Epoch 21 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.02it/s, loss=0.364]
Epoch 21 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.02it/s, loss=0.363]
Epoch 21 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.34it/s, loss=0.363]
Epoch 21 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.34it/s, loss=0.363]
Epoch 21 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.34it/s, loss=0.363]
Epoch 21 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 26.34it/s, loss=0.364]
Epoch 21 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 25.86it/s, loss=0.364]
Epoch 21 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 25.86it/s, loss=0.363]
Epoch 21 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 25.86it/s, loss=0.361]
Epoch 21 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 25.86it/s, loss=0.364]
Epoch 21 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.34it/s, loss=0.364]
Epoch 21 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.34it/s, loss=0.363]
Epoch 21 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.34it/s, loss=0.363]
Epoch 21 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.34it/s, loss=0.363]
Epoch 21 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.09it/s, loss=0.363]
Epoch 21 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.09it/s, loss=0.362]
Epoch 21 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.09it/s, loss=0.361]
Epoch 21 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.09it/s, loss=0.361]
Epoch 21 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.38it/s, loss=0.361]
Epoch 21 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.38it/s, loss=0.361]
Epoch 21 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.38it/s, loss=0.362]
Epoch 21 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.38it/s, loss=0.363]
Epoch 21 [Train]: 100%|██████████| 129/129 [00:04<00:00, 27.73it/s, loss=0.363]
2026-08-07 06:51:41.027 | INFO  | __main__:pretrain:180 - Epoch 21/50 | Train Loss: 0.3631 | Val Loss: 0.6451
2026-08-07 06:51:41.037 | INFO  | __main__:pretrain:196 -  -> New best model (val_loss=0.6451)
Epoch 22 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 22 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.257]
Epoch 22 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.289]
Epoch 22 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.298]
Epoch 22 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.278]
Epoch 22 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.41it/s, loss=0.278]
Epoch 22 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.41it/s, loss=0.29]
Epoch 22 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.41it/s, loss=0.289]
Epoch 22 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.41it/s, loss=0.286]
Epoch 22 [Train]: 3%|▎ | 4/129 [00:00<00:03, 35.41it/s, loss=0.296]
Epoch 22 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.18it/s, loss=0.296]
Epoch 22 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.18it/s, loss=0.297]
Epoch 22 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.18it/s, loss=0.289]
Epoch 22 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.18it/s, loss=0.293]
Epoch 22 [Train]: 6%|▌ | 8/129 [00:00<00:04, 30.18it/s, loss=0.294]
Epoch 22 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.23it/s, loss=0.294]
Epoch 22 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.23it/s, loss=0.297]
Epoch 22 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.23it/s, loss=0.303]
Epoch 22 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.23it/s, loss=0.309]
Epoch 22 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.75it/s, loss=0.309]
Epoch 22 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.75it/s, loss=0.311]
Epoch 22 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.75it/s, loss=0.308]
Epoch 22 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.75it/s, loss=0.309]
Epoch 22 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.45it/s, loss=0.309]
Epoch 22 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.45it/s, loss=0.323]
Epoch 22 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.45it/s, loss=0.336]
Epoch 22 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.45it/s, loss=0.342]
Epoch 22 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.54it/s, loss=0.342]
Epoch 22 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.54it/s, loss=0.342]
Epoch 22 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.54it/s, loss=0.34]
Epoch 22 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.54it/s, loss=0.337]
Epoch 22 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.71it/s, loss=0.337]
Epoch 22 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.71it/s, loss=0.332]
Epoch 22 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.71it/s, loss=0.338]
Epoch 22 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.71it/s, loss=0.337]
Epoch 22 [Train]: 21%|██ | 27/129 [00:00<00:03, 27.29it/s, loss=0.337]
Epoch 22 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.29it/s, loss=0.338]
Epoch 22 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.29it/s, loss=0.338]
Epoch 22 [Train]: 21%|██ | 27/129 [00:01<00:03, 27.29it/s, loss=0.339]
Epoch 22 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.76it/s, loss=0.339]
Epoch 22 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.76it/s, loss=0.34]
Epoch 22 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.76it/s, loss=0.341]
Epoch 22 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.76it/s, loss=0.339]
Epoch 22 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.15it/s, loss=0.339]
Epoch 22 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.15it/s, loss=0.343]
Epoch 22 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.15it/s, loss=0.34]
Epoch 22 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 26.15it/s, loss=0.34]
Epoch 22 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.69it/s, loss=0.34]
Epoch 22 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.69it/s, loss=0.343]
Epoch 22 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.69it/s, loss=0.344]
Epoch 22 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 26.69it/s, loss=0.343]
Epoch 22 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.48it/s, loss=0.343]
Epoch 22 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.48it/s, loss=0.343]
Epoch 22 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.48it/s, loss=0.35]
Epoch 22 [Train]: 30%|███ | 39/129 [00:01<00:03, 26.48it/s, loss=0.356]
Epoch 22 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.05it/s, loss=0.356]
Epoch 22 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.05it/s, loss=0.358]
Epoch 22 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.05it/s, loss=0.357]
Epoch 22 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 26.05it/s, loss=0.357]
Epoch 22 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.42it/s, loss=0.357]
Epoch 22 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.42it/s, loss=0.353]
Epoch 22 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.42it/s, loss=0.353]
Epoch 22 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.42it/s, loss=0.351]
Epoch 22 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.59it/s, loss=0.351]
Epoch 22 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.59it/s, loss=0.349]
Epoch 22 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.59it/s, loss=0.35]
Epoch 22 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.59it/s, loss=0.349]
Epoch 22 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.09it/s, loss=0.349]
Epoch 22 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.09it/s, loss=0.35]
Epoch 22 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.09it/s, loss=0.349]
Epoch 22 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 27.09it/s, loss=0.347]
Epoch 22 [Train]: 42%|████▏ | 54/129 [00:01<00:02, 27.24it/s, loss=0.347]
Epoch 22 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.24it/s, loss=0.357]
Epoch 22 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.24it/s, loss=0.355]
Epoch 22 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.24it/s, loss=0.353]
Epoch 22 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.39it/s, loss=0.353]
Epoch 22 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.39it/s, loss=0.355]
Epoch 22 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.39it/s, loss=0.355]
Epoch 22 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.39it/s, loss=0.356]
Epoch 22 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.36it/s, loss=0.356]
Epoch 22 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.36it/s, loss=0.356]
Epoch 22 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.36it/s, loss=0.357]
Epoch 22 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.36it/s, loss=0.356]
Epoch 22 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.20it/s, loss=0.356]
Epoch 22 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.20it/s, loss=0.358]
Epoch 22 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.20it/s, loss=0.357]
Epoch 22 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 27.20it/s, loss=0.357]
Epoch 22 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.44it/s, loss=0.357]
Epoch 22 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.44it/s, loss=0.356]
Epoch 22 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.44it/s, loss=0.354]
Epoch 22 [Train]: 51%|█████ | 66/129 [00:02<00:02, 27.44it/s, loss=0.356]
Epoch 22 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.64it/s, loss=0.356]
Epoch 22 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.64it/s, loss=0.357]
Epoch 22 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.64it/s, loss=0.357]
Epoch 22 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 27.64it/s, loss=0.355]
Epoch 22 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.68it/s, loss=0.355]
Epoch 22 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.68it/s, loss=0.357]
Epoch 22 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.68it/s, loss=0.357]
Epoch 22 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.68it/s, loss=0.357]
Epoch 22 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.44it/s, loss=0.357]
Epoch 22 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.44it/s, loss=0.358]
Epoch 22 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.44it/s, loss=0.357]
Epoch 22 [Train]: 58%|█████▊ | 75/129 [00:02<00:01, 27.44it/s, loss=0.355]
Epoch 22 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.19it/s, loss=0.355]
Epoch 22 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.19it/s, loss=0.355]
Epoch 22 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.19it/s, loss=0.355]
Epoch 22 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.19it/s, loss=0.354]
Epoch 22 [Train]: 63%|██████▎ | 81/129 [00:02<00:01, 27.29it/s, loss=0.354]
Epoch 22 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.29it/s, loss=0.353]
Epoch 22 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.29it/s, loss=0.352]
Epoch 22 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.29it/s, loss=0.354]
Epoch 22 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.32it/s, loss=0.354]
Epoch 22 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.32it/s, loss=0.355]
Epoch 22 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.32it/s, loss=0.355]
Epoch 22 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.32it/s, loss=0.356]
Epoch 22 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.24it/s, loss=0.356]
Epoch 22 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.24it/s, loss=0.357]
Epoch 22 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.24it/s, loss=0.355]
Epoch 22 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.24it/s, loss=0.356]
Epoch 22 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.57it/s, loss=0.356]
Epoch 22 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.57it/s, loss=0.355]
Epoch 22 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.57it/s, loss=0.359]
Epoch 22 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.57it/s, loss=0.359]
Epoch 22 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.41it/s, loss=0.359]
Epoch 22 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.41it/s, loss=0.361]
Epoch 22 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.41it/s, loss=0.361]
Epoch 22 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.41it/s, loss=0.36]
Epoch 22 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.85it/s, loss=0.36]
Epoch 22 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.85it/s, loss=0.363]
Epoch 22 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.85it/s, loss=0.367]
Epoch 22 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 26.85it/s, loss=0.367]
Epoch 22 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.85it/s, loss=0.367]
Epoch 22 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.85it/s, loss=0.366]
Epoch 22 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.85it/s, loss=0.366]
Epoch 22 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 26.85it/s, loss=0.365]
Epoch 22 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.21it/s, loss=0.365]
Epoch 22 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.21it/s, loss=0.365]
Epoch 22 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.21it/s, loss=0.364]
Epoch 22 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.21it/s, loss=0.364]
Epoch 22 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.71it/s, loss=0.364]
Epoch 22 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.71it/s, loss=0.363]
Epoch 22 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.71it/s, loss=0.363]
Epoch 22 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.71it/s, loss=0.364]
Epoch 22 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 27.72it/s, loss=0.364]
Epoch 22 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 27.72it/s, loss=0.363]
Epoch 22 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.72it/s, loss=0.362]
Epoch 22 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.72it/s, loss=0.362]
Epoch 22 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.99it/s, loss=0.362]
Epoch 22 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.99it/s, loss=0.361]
Epoch 22 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.99it/s, loss=0.361]
Epoch 22 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.99it/s, loss=0.363]
Epoch 22 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.12it/s, loss=0.363]
Epoch 22 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.12it/s, loss=0.363]
Epoch 22 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.12it/s, loss=0.363]
Epoch 22 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.12it/s, loss=0.363]
Epoch 22 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 28.45it/s, loss=0.363]
Epoch 22 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 28.45it/s, loss=0.363]
Epoch 22 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 28.45it/s, loss=0.362]
Epoch 22 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 28.45it/s, loss=0.361]
Epoch 22 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 28.60it/s, loss=0.361]
Epoch 22 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 28.60it/s, loss=0.361]
Epoch 22 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 28.60it/s, loss=0.36]
Epoch 22 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 28.60it/s, loss=0.36]
Epoch 22 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.27it/s, loss=0.36]
Epoch 22 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.27it/s, loss=0.36]
Epoch 22 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.27it/s, loss=0.361]
Epoch 22 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.27it/s, loss=0.361]
Epoch 22 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.21it/s, loss=0.361]
Epoch 22 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.21it/s, loss=0.361]
Epoch 22 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.21it/s, loss=0.36]
Epoch 22 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.21it/s, loss=0.361]
Epoch 22 [Train]: 100%|██████████| 129/129 [00:04<00:00, 26.93it/s, loss=0.361]
2026-08-07 06:51:45.910 | INFO  | __main__:pretrain:180 - Epoch 22/50 | Train Loss: 0.3614 | Val Loss: 0.6778
Epoch 23 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 23 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.207]
Epoch 23 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.205]
Epoch 23 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.229]
Epoch 23 [Train]: 2%|▏ | 3/129 [00:00<00:04, 28.97it/s, loss=0.229]
Epoch 23 [Train]: 2%|▏ | 3/129 [00:00<00:04, 28.97it/s, loss=0.224]
Epoch 23 [Train]: 2%|▏ | 3/129 [00:00<00:04, 28.97it/s, loss=0.218]
Epoch 23 [Train]: 2%|▏ | 3/129 [00:00<00:04, 28.97it/s, loss=0.223]
Epoch 23 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.74it/s, loss=0.223]
Epoch 23 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.74it/s, loss=0.23]
Epoch 23 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.74it/s, loss=0.251]
Epoch 23 [Train]: 5%|▍ | 6/129 [00:00<00:04, 26.74it/s, loss=0.26]
Epoch 23 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.72it/s, loss=0.26]
Epoch 23 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.72it/s, loss=0.259]
Epoch 23 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.72it/s, loss=0.266]
Epoch 23 [Train]: 7%|▋ | 9/129 [00:00<00:04, 26.72it/s, loss=0.271]
Epoch 23 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.07it/s, loss=0.271]
Epoch 23 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.07it/s, loss=0.272]
Epoch 23 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.07it/s, loss=0.276]
Epoch 23 [Train]: 9%|▉ | 12/129 [00:00<00:04, 26.07it/s, loss=0.283]
Epoch 23 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.02it/s, loss=0.283]
Epoch 23 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.02it/s, loss=0.288]
Epoch 23 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.02it/s, loss=0.285]
Epoch 23 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.02it/s, loss=0.286]
Epoch 23 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.69it/s, loss=0.286]
Epoch 23 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.69it/s, loss=0.285]
Epoch 23 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.69it/s, loss=0.287]
Epoch 23 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 26.69it/s, loss=0.288]
Epoch 23 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.65it/s, loss=0.288]
Epoch 23 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.65it/s, loss=0.288]
Epoch 23 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.65it/s, loss=0.291]
Epoch 23 [Train]: 16%|█▋ | 21/129 [00:00<00:04, 26.65it/s, loss=0.291]
Epoch 23 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.54it/s, loss=0.291]
Epoch 23 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.54it/s, loss=0.294]
Epoch 23 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 26.54it/s, loss=0.299]
Epoch 23 [Train]: 19%|█▊ | 24/129 [00:01<00:03, 26.54it/s, loss=0.296]
Epoch 23 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.30it/s, loss=0.296]
Epoch 23 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.30it/s, loss=0.292]
Epoch 23 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.30it/s, loss=0.291]
Epoch 23 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.30it/s, loss=0.293]
Epoch 23 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.02it/s, loss=0.293]
Epoch 23 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.02it/s, loss=0.293]
Epoch 23 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.02it/s, loss=0.295]
Epoch 23 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 27.02it/s, loss=0.296]
Epoch 23 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.36it/s, loss=0.296]
Epoch 23 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.36it/s, loss=0.294]
Epoch 23 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.36it/s, loss=0.303]
Epoch 23 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.36it/s, loss=0.3]
Epoch 23 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.81it/s, loss=0.3]
Epoch 23 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.81it/s, loss=0.303]
Epoch 23 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.81it/s, loss=0.304]
Epoch 23 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.81it/s, loss=0.304]
Epoch 23 [Train]: 30%|███ | 39/129 [00:01<00:03, 28.19it/s, loss=0.304]
Epoch 23 [Train]: 30%|███ | 39/129 [00:01<00:03, 28.19it/s, loss=0.319]
Epoch 23 [Train]: 30%|███ | 39/129 [00:01<00:03, 28.19it/s, loss=0.323]
Epoch 23 [Train]: 30%|███ | 39/129 [00:01<00:03, 28.19it/s, loss=0.323]
Epoch 23 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.82it/s, loss=0.323]
Epoch 23 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.82it/s, loss=0.325]
Epoch 23 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.82it/s, loss=0.324]
Epoch 23 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.82it/s, loss=0.327]
Epoch 23 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.95it/s, loss=0.327]
Epoch 23 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.95it/s, loss=0.325]
Epoch 23 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.95it/s, loss=0.325]
Epoch 23 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.95it/s, loss=0.323]
Epoch 23 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.41it/s, loss=0.323]
Epoch 23 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.41it/s, loss=0.328]
Epoch 23 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.41it/s, loss=0.328]
Epoch 23 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.41it/s, loss=0.33]
Epoch 23 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.82it/s, loss=0.33]
Epoch 23 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.82it/s, loss=0.329]
Epoch 23 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.82it/s, loss=0.33]
Epoch 23 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.82it/s, loss=0.334]
Epoch 23 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.99it/s, loss=0.334]
Epoch 23 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.99it/s, loss=0.335]
Epoch 23 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.99it/s, loss=0.334]
Epoch 23 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 26.99it/s, loss=0.333]
Epoch 23 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.27it/s, loss=0.333]
Epoch 23 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.27it/s, loss=0.331]
Epoch 23 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.27it/s, loss=0.331]
Epoch 23 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.27it/s, loss=0.33]
Epoch 23 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.14it/s, loss=0.33]
Epoch 23 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.14it/s, loss=0.333]
Epoch 23 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.14it/s, loss=0.333]
Epoch 23 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 27.14it/s, loss=0.332]
Epoch 23 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.57it/s, loss=0.332]
Epoch 23 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.57it/s, loss=0.332]
Epoch 23 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.57it/s, loss=0.332]
Epoch 23 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.57it/s, loss=0.334]
Epoch 23 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.72it/s, loss=0.334]
Epoch 23 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.72it/s, loss=0.335]
Epoch 23 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.72it/s, loss=0.336]
Epoch 23 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.72it/s, loss=0.335]
Epoch 23 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.30it/s, loss=0.335]
Epoch 23 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.30it/s, loss=0.336]
Epoch 23 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.30it/s, loss=0.337]
Epoch 23 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.30it/s, loss=0.338]
Epoch 23 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.31it/s, loss=0.338]
Epoch 23 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.31it/s, loss=0.341]
Epoch 23 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.31it/s, loss=0.342]
Epoch 23 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 26.31it/s, loss=0.343]
Epoch 23 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.01it/s, loss=0.343]
Epoch 23 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.01it/s, loss=0.344]
Epoch 23 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.01it/s, loss=0.343]
Epoch 23 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 26.01it/s, loss=0.345]
Epoch 23 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.34it/s, loss=0.345]
Epoch 23 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.34it/s, loss=0.346]
Epoch 23 [Train]: 60%|██████ | 78/129 [00:02<00:01, 26.34it/s, loss=0.346]
Epoch 23 [Train]: 60%|██████ | 78/129 [00:03<00:01, 26.34it/s, loss=0.345]
Epoch 23 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.98it/s, loss=0.345]
Epoch 23 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.98it/s, loss=0.344]
Epoch 23 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.98it/s, loss=0.344]
Epoch 23 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 26.98it/s, loss=0.345]
Epoch 23 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.50it/s, loss=0.345]
Epoch 23 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.50it/s, loss=0.346]
Epoch 23 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.50it/s, loss=0.348]
Epoch 23 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.50it/s, loss=0.348]
Epoch 23 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.60it/s, loss=0.348]
Epoch 23 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.60it/s, loss=0.347]
Epoch 23 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.60it/s, loss=0.347]
Epoch 23 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.60it/s, loss=0.345]
Epoch 23 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.57it/s, loss=0.345]
Epoch 23 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.57it/s, loss=0.345]
Epoch 23 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.57it/s, loss=0.345]
Epoch 23 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.57it/s, loss=0.346]
Epoch 23 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 28.18it/s, loss=0.346]
Epoch 23 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 28.18it/s, loss=0.345]
Epoch 23 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 28.18it/s, loss=0.345]
Epoch 23 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 28.18it/s, loss=0.344]
Epoch 23 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.84it/s, loss=0.344]
Epoch 23 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.84it/s, loss=0.343]
Epoch 23 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.84it/s, loss=0.343]
Epoch 23 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.84it/s, loss=0.344]
Epoch 23 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.72it/s, loss=0.344]
Epoch 23 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.72it/s, loss=0.345]
Epoch 23 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.72it/s, loss=0.345]
Epoch 23 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.72it/s, loss=0.344]
Epoch 23 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.60it/s, loss=0.344]
Epoch 23 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.60it/s, loss=0.344]
Epoch 23 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.60it/s, loss=0.344]
Epoch 23 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.60it/s, loss=0.343]
Epoch 23 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.63it/s, loss=0.343]
Epoch 23 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.63it/s, loss=0.344]
Epoch 23 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.63it/s, loss=0.344]
Epoch 23 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.63it/s, loss=0.344]
Epoch 23 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 27.93it/s, loss=0.344]
Epoch 23 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.93it/s, loss=0.345]
Epoch 23 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.93it/s, loss=0.345]
Epoch 23 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.93it/s, loss=0.347]
Epoch 23 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.83it/s, loss=0.347]
Epoch 23 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.83it/s, loss=0.348]
Epoch 23 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.83it/s, loss=0.348]
Epoch 23 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.83it/s, loss=0.348]
Epoch 23 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.17it/s, loss=0.348]
Epoch 23 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.17it/s, loss=0.348]
Epoch 23 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.17it/s, loss=0.347]
Epoch 23 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 28.17it/s, loss=0.349]
Epoch 23 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.81it/s, loss=0.349]
Epoch 23 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.81it/s, loss=0.348]
Epoch 23 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.81it/s, loss=0.347]
Epoch 23 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.81it/s, loss=0.346]
Epoch 23 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.93it/s, loss=0.346]
Epoch 23 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.93it/s, loss=0.346]
Epoch 23 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.93it/s, loss=0.349]
Epoch 23 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 26.93it/s, loss=0.349]
Epoch 23 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.06it/s, loss=0.349]
Epoch 23 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.06it/s, loss=0.349]
Epoch 23 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.06it/s, loss=0.349]
Epoch 23 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.06it/s, loss=0.349]
Epoch 23 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.06it/s, loss=0.349]
Epoch 23 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.06it/s, loss=0.349]
Epoch 23 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.06it/s, loss=0.349]
Epoch 23 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.06it/s, loss=0.349]
Epoch 23 [Train]: 100%|██████████| 129/129 [00:04<00:00, 27.32it/s, loss=0.349]
2026-08-07 06:51:50.816 | INFO  | __main__:pretrain:180 - Epoch 23/50 | Train Loss: 0.3487 | Val Loss: 0.7331
Epoch 24 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 24 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.237]
Epoch 24 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.271]
Epoch 24 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.242]
Epoch 24 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.251]
Epoch 24 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.41it/s, loss=0.251]
Epoch 24 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.41it/s, loss=0.252]
Epoch 24 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.41it/s, loss=0.296]
Epoch 24 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.41it/s, loss=0.297]
Epoch 24 [Train]: 3%|▎ | 4/129 [00:00<00:03, 31.41it/s, loss=0.296]
Epoch 24 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.85it/s, loss=0.296]
Epoch 24 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.85it/s, loss=0.306]
Epoch 24 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.85it/s, loss=0.308]
Epoch 24 [Train]: 6%|▌ | 8/129 [00:00<00:04, 28.85it/s, loss=0.304]
Epoch 24 [Train]: 9%|▊ | 11/129 [00:00<00:04, 28.18it/s, loss=0.304]
Epoch 24 [Train]: 9%|▊ | 11/129 [00:00<00:04, 28.18it/s, loss=0.302]
Epoch 24 [Train]: 9%|▊ | 11/129 [00:00<00:04, 28.18it/s, loss=0.303]
Epoch 24 [Train]: 9%|▊ | 11/129 [00:00<00:04, 28.18it/s, loss=0.304]
Epoch 24 [Train]: 11%|█ | 14/129 [00:00<00:04, 28.00it/s, loss=0.304]
Epoch 24 [Train]: 11%|█ | 14/129 [00:00<00:04, 28.00it/s, loss=0.298]
Epoch 24 [Train]: 11%|█ | 14/129 [00:00<00:04, 28.00it/s, loss=0.295]
Epoch 24 [Train]: 11%|█ | 14/129 [00:00<00:04, 28.00it/s, loss=0.303]
Epoch 24 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.82it/s, loss=0.303]
Epoch 24 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.82it/s, loss=0.299]
Epoch 24 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.82it/s, loss=0.295]
Epoch 24 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.82it/s, loss=0.292]
Epoch 24 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.79it/s, loss=0.292]
Epoch 24 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.79it/s, loss=0.292]
Epoch 24 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.79it/s, loss=0.297]
Epoch 24 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.79it/s, loss=0.3]
Epoch 24 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 26.28it/s, loss=0.3]
Epoch 24 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 26.28it/s, loss=0.302]
Epoch 24 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 26.28it/s, loss=0.301]
Epoch 24 [Train]: 18%|█▊ | 23/129 [00:00<00:04, 26.28it/s, loss=0.304]
Epoch 24 [Train]: 20%|██ | 26/129 [00:00<00:03, 26.62it/s, loss=0.304]
Epoch 24 [Train]: 20%|██ | 26/129 [00:00<00:03, 26.62it/s, loss=0.304]
Epoch 24 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.62it/s, loss=0.306]
Epoch 24 [Train]: 20%|██ | 26/129 [00:01<00:03, 26.62it/s, loss=0.303]
Epoch 24 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.94it/s, loss=0.303]
Epoch 24 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.94it/s, loss=0.303]
Epoch 24 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.94it/s, loss=0.307]
Epoch 24 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 26.94it/s, loss=0.31]
Epoch 24 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.56it/s, loss=0.31]
Epoch 24 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.56it/s, loss=0.313]
Epoch 24 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.56it/s, loss=0.309]
Epoch 24 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.56it/s, loss=0.31]
Epoch 24 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.07it/s, loss=0.31]
Epoch 24 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.07it/s, loss=0.31]
Epoch 24 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.07it/s, loss=0.31]
Epoch 24 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.07it/s, loss=0.312]
Epoch 24 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.33it/s, loss=0.312]
Epoch 24 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.33it/s, loss=0.316]
Epoch 24 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.33it/s, loss=0.318]
Epoch 24 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.33it/s, loss=0.316]
Epoch 24 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 25.94it/s, loss=0.316]
Epoch 24 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 25.94it/s, loss=0.314]
Epoch 24 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 25.94it/s, loss=0.315]
Epoch 24 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 25.94it/s, loss=0.316]
Epoch 24 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.43it/s, loss=0.316]
Epoch 24 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.43it/s, loss=0.317]
Epoch 24 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.43it/s, loss=0.319]
Epoch 24 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.43it/s, loss=0.318]
Epoch 24 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.98it/s, loss=0.318]
Epoch 24 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.98it/s, loss=0.317]
Epoch 24 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.98it/s, loss=0.316]
Epoch 24 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.98it/s, loss=0.315]
Epoch 24 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.07it/s, loss=0.315]
Epoch 24 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.07it/s, loss=0.316]
Epoch 24 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.07it/s, loss=0.313]
Epoch 24 [Train]: 39%|███▉ | 50/129 [00:01<00:02, 27.07it/s, loss=0.312]
Epoch 24 [Train]: 41%|████ | 53/129 [00:01<00:02, 26.95it/s, loss=0.312]
Epoch 24 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.95it/s, loss=0.311]
Epoch 24 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.95it/s, loss=0.321]
Epoch 24 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.95it/s, loss=0.32]
Epoch 24 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.43it/s, loss=0.32]
Epoch 24 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.43it/s, loss=0.318]
Epoch 24 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.43it/s, loss=0.319]
Epoch 24 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.43it/s, loss=0.321]
Epoch 24 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 25.93it/s, loss=0.321]
Epoch 24 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 25.93it/s, loss=0.322]
Epoch 24 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 25.93it/s, loss=0.322]
Epoch 24 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 25.93it/s, loss=0.32]
Epoch 24 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.22it/s, loss=0.32]
Epoch 24 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.22it/s, loss=0.322]
Epoch 24 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.22it/s, loss=0.322]
Epoch 24 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.22it/s, loss=0.322]
Epoch 24 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.56it/s, loss=0.322]
Epoch 24 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.56it/s, loss=0.321]
Epoch 24 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.56it/s, loss=0.32]
Epoch 24 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.56it/s, loss=0.322]
Epoch 24 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.03it/s, loss=0.322]
Epoch 24 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.03it/s, loss=0.324]
Epoch 24 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.03it/s, loss=0.323]
Epoch 24 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 27.03it/s, loss=0.323]
Epoch 24 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.59it/s, loss=0.323]
Epoch 24 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.59it/s, loss=0.323]
Epoch 24 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.59it/s, loss=0.325]
Epoch 24 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.59it/s, loss=0.328]
Epoch 24 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.13it/s, loss=0.328]
Epoch 24 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.13it/s, loss=0.331]
Epoch 24 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.13it/s, loss=0.332]
Epoch 24 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.13it/s, loss=0.332]
Epoch 24 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.18it/s, loss=0.332]
Epoch 24 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.18it/s, loss=0.334]
Epoch 24 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.18it/s, loss=0.333]
Epoch 24 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.18it/s, loss=0.334]
Epoch 24 [Train]: 62%|██████▏ | 80/129 [00:02<00:01, 26.66it/s, loss=0.334]
Epoch 24 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.66it/s, loss=0.333]
Epoch 24 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.66it/s, loss=0.334]
Epoch 24 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.66it/s, loss=0.334]
Epoch 24 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.76it/s, loss=0.334]
Epoch 24 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.76it/s, loss=0.333]
Epoch 24 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.76it/s, loss=0.336]
Epoch 24 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 26.76it/s, loss=0.337]
Epoch 24 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.01it/s, loss=0.337]
Epoch 24 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.01it/s, loss=0.336]
Epoch 24 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.01it/s, loss=0.336]
Epoch 24 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 27.01it/s, loss=0.335]
Epoch 24 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.02it/s, loss=0.335]
Epoch 24 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.02it/s, loss=0.335]
Epoch 24 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.02it/s, loss=0.335]
Epoch 24 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.02it/s, loss=0.335]
Epoch 24 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.11it/s, loss=0.335]
Epoch 24 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.11it/s, loss=0.336]
Epoch 24 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.11it/s, loss=0.336]
Epoch 24 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.11it/s, loss=0.338]
Epoch 24 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.26it/s, loss=0.338]
Epoch 24 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.26it/s, loss=0.338]
Epoch 24 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.26it/s, loss=0.337]
Epoch 24 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 27.26it/s, loss=0.338]
Epoch 24 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.53it/s, loss=0.338]
Epoch 24 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.53it/s, loss=0.339]
Epoch 24 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.53it/s, loss=0.339]
Epoch 24 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.53it/s, loss=0.34]
Epoch 24 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.68it/s, loss=0.34]
Epoch 24 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.68it/s, loss=0.339]
Epoch 24 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.68it/s, loss=0.338]
Epoch 24 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.68it/s, loss=0.338]
Epoch 24 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.89it/s, loss=0.338]
Epoch 24 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.89it/s, loss=0.338]
Epoch 24 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.89it/s, loss=0.339]
Epoch 24 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.89it/s, loss=0.339]
Epoch 24 [Train]: 83%|████████▎ | 107/129 [00:03<00:00, 27.25it/s, loss=0.339]
Epoch 24 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.25it/s, loss=0.34]
Epoch 24 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.25it/s, loss=0.342]
Epoch 24 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.25it/s, loss=0.342]
Epoch 24 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 27.69it/s, loss=0.342]
Epoch 24 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 27.69it/s, loss=0.341]
Epoch 24 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 27.69it/s, loss=0.34]
Epoch 24 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 27.69it/s, loss=0.34]
Epoch 24 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.73it/s, loss=0.34]
Epoch 24 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.73it/s, loss=0.34]
Epoch 24 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.73it/s, loss=0.339]
Epoch 24 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.73it/s, loss=0.338]
Epoch 24 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.39it/s, loss=0.338]
Epoch 24 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.39it/s, loss=0.339]
Epoch 24 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.39it/s, loss=0.338]
Epoch 24 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.39it/s, loss=0.339]
Epoch 24 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.06it/s, loss=0.339]
Epoch 24 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.06it/s, loss=0.338]
Epoch 24 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.06it/s, loss=0.34]
Epoch 24 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.06it/s, loss=0.34]
Epoch 24 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.40it/s, loss=0.34]
Epoch 24 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.40it/s, loss=0.343]
Epoch 24 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.40it/s, loss=0.345]
Epoch 24 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.40it/s, loss=0.345]
Epoch 24 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 28.04it/s, loss=0.345]
Epoch 24 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 28.04it/s, loss=0.344]
Epoch 24 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 28.04it/s, loss=0.344]
Epoch 24 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 28.04it/s, loss=0.345]
Epoch 24 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 28.28it/s, loss=0.345]
Epoch 24 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 28.28it/s, loss=0.347]
2026-08-07 06:51:55.740 | INFO  | __main__:pretrain:180 - Epoch 24/50 | Train Loss: 0.3468 | Val Loss: 0.6992
Epoch 25 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 25 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.384]
Epoch 25 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.308]
Epoch 25 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.376]
Epoch 25 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.70it/s, loss=0.376]
Epoch 25 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.70it/s, loss=0.36]
Epoch 25 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.70it/s, loss=0.34]
Epoch 25 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.70it/s, loss=0.338]
Epoch 25 [Train]: 5%|▍ | 6/129 [00:00<00:04, 27.57it/s, loss=0.338]
Epoch 25 [Train]: 5%|▍ | 6/129 [00:00<00:04, 27.57it/s, loss=0.349]
Epoch 25 [Train]: 5%|▍ | 6/129 [00:00<00:04, 27.57it/s, loss=0.338]
Epoch 25 [Train]: 5%|▍ | 6/129 [00:00<00:04, 27.57it/s, loss=0.342]
Epoch 25 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.19it/s, loss=0.342]
Epoch 25 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.19it/s, loss=0.328]
Epoch 25 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.19it/s, loss=0.323]
Epoch 25 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.19it/s, loss=0.324]
Epoch 25 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.19it/s, loss=0.321]
Epoch 25 [Train]: 10%|█ | 13/129 [00:00<00:03, 29.20it/s, loss=0.321]
Epoch 25 [Train]: 10%|█ | 13/129 [00:00<00:03, 29.20it/s, loss=0.323]
Epoch 25 [Train]: 10%|█ | 13/129 [00:00<00:03, 29.20it/s, loss=0.321]
Epoch 25 [Train]: 10%|█ | 13/129 [00:00<00:03, 29.20it/s, loss=0.317]
Epoch 25 [Train]: 12%|█▏ | 16/129 [00:00<00:03, 28.55it/s, loss=0.317]
Epoch 25 [Train]: 12%|█▏ | 16/129 [00:00<00:03, 28.55it/s, loss=0.322]
Epoch 25 [Train]: 12%|█▏ | 16/129 [00:00<00:03, 28.55it/s, loss=0.317]
Epoch 25 [Train]: 12%|█▏ | 16/129 [00:00<00:03, 28.55it/s, loss=0.313]
Epoch 25 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 27.89it/s, loss=0.313]
Epoch 25 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 27.89it/s, loss=0.341]
Epoch 25 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 27.89it/s, loss=0.345]
Epoch 25 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 27.89it/s, loss=0.345]
Epoch 25 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.73it/s, loss=0.345]
Epoch 25 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.73it/s, loss=0.36]
Epoch 25 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.73it/s, loss=0.357]
Epoch 25 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.73it/s, loss=0.355]
Epoch 25 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 26.90it/s, loss=0.355]
Epoch 25 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 26.90it/s, loss=0.357]
Epoch 25 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 26.90it/s, loss=0.353]
Epoch 25 [Train]: 19%|█▉ | 25/129 [00:01<00:03, 26.90it/s, loss=0.349]
Epoch 25 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 26.37it/s, loss=0.349]
Epoch 25 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 26.37it/s, loss=0.347]
Epoch 25 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 26.37it/s, loss=0.344]
Epoch 25 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 26.37it/s, loss=0.344]
Epoch 25 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.97it/s, loss=0.344]
Epoch 25 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.97it/s, loss=0.344]
Epoch 25 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.97it/s, loss=0.344]
Epoch 25 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.97it/s, loss=0.345]
Epoch 25 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.11it/s, loss=0.345]
Epoch 25 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.11it/s, loss=0.343]
Epoch 25 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.11it/s, loss=0.343]
Epoch 25 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.11it/s, loss=0.343]
Epoch 25 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.11it/s, loss=0.343]
Epoch 25 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.11it/s, loss=0.34]
Epoch 25 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.11it/s, loss=0.337]
Epoch 25 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.11it/s, loss=0.338]
Epoch 25 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.23it/s, loss=0.338]
Epoch 25 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.23it/s, loss=0.337]
Epoch 25 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.23it/s, loss=0.337]
Epoch 25 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.23it/s, loss=0.335]
Epoch 25 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.16it/s, loss=0.335]
Epoch 25 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.16it/s, loss=0.336]
Epoch 25 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.16it/s, loss=0.336]
Epoch 25 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.16it/s, loss=0.338]
Epoch 25 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.36it/s, loss=0.338]
Epoch 25 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.36it/s, loss=0.338]
Epoch 25 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.36it/s, loss=0.336]
Epoch 25 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.36it/s, loss=0.336]
Epoch 25 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 25.96it/s, loss=0.336]
Epoch 25 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 25.96it/s, loss=0.339]
Epoch 25 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 25.96it/s, loss=0.339]
Epoch 25 [Train]: 38%|███▊ | 49/129 [00:01<00:03, 25.96it/s, loss=0.344]
Epoch 25 [Train]: 40%|████ | 52/129 [00:01<00:03, 25.57it/s, loss=0.344]
Epoch 25 [Train]: 40%|████ | 52/129 [00:01<00:03, 25.57it/s, loss=0.344]
Epoch 25 [Train]: 40%|████ | 52/129 [00:02<00:03, 25.57it/s, loss=0.345]
Epoch 25 [Train]: 40%|████ | 52/129 [00:02<00:03, 25.57it/s, loss=0.345]
Epoch 25 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 25.92it/s, loss=0.345]
Epoch 25 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 25.92it/s, loss=0.345]
Epoch 25 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 25.92it/s, loss=0.346]
Epoch 25 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 25.92it/s, loss=0.346]
Epoch 25 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.30it/s, loss=0.346]
Epoch 25 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.30it/s, loss=0.346]
Epoch 25 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.30it/s, loss=0.344]
Epoch 25 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.30it/s, loss=0.345]
Epoch 25 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.04it/s, loss=0.345]
Epoch 25 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.04it/s, loss=0.348]
Epoch 25 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.04it/s, loss=0.349]
Epoch 25 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.04it/s, loss=0.347]
Epoch 25 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.79it/s, loss=0.347]
Epoch 25 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.79it/s, loss=0.346]
Epoch 25 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.79it/s, loss=0.344]
Epoch 25 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.79it/s, loss=0.345]
Epoch 25 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.00it/s, loss=0.345]
Epoch 25 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.00it/s, loss=0.344]
Epoch 25 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.00it/s, loss=0.346]
Epoch 25 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.00it/s, loss=0.349]
Epoch 25 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.02it/s, loss=0.349]
Epoch 25 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.02it/s, loss=0.35]
Epoch 25 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.02it/s, loss=0.348]
Epoch 25 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.02it/s, loss=0.347]
Epoch 25 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.46it/s, loss=0.347]
Epoch 25 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.46it/s, loss=0.346]
Epoch 25 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.46it/s, loss=0.348]
Epoch 25 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.46it/s, loss=0.349]
Epoch 25 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.15it/s, loss=0.349]
Epoch 25 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.15it/s, loss=0.349]
Epoch 25 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.15it/s, loss=0.352]
Epoch 25 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.15it/s, loss=0.352]
Epoch 25 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.33it/s, loss=0.352]
Epoch 25 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.33it/s, loss=0.351]
Epoch 25 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.33it/s, loss=0.35]
Epoch 25 [Train]: 61%|██████ | 79/129 [00:03<00:01, 27.33it/s, loss=0.349]
Epoch 25 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 27.13it/s, loss=0.349]
Epoch 25 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 27.13it/s, loss=0.348]
Epoch 25 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 27.13it/s, loss=0.348]
Epoch 25 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 27.13it/s, loss=0.347]
Epoch 25 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.07it/s, loss=0.347]
Epoch 25 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.07it/s, loss=0.347]
Epoch 25 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.07it/s, loss=0.346]
Epoch 25 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.07it/s, loss=0.345]
Epoch 25 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.56it/s, loss=0.345]
Epoch 25 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.56it/s, loss=0.344]
Epoch 25 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.56it/s, loss=0.344]
Epoch 25 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.56it/s, loss=0.344]
Epoch 25 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.59it/s, loss=0.344]
Epoch 25 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.59it/s, loss=0.343]
Epoch 25 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.59it/s, loss=0.343]
Epoch 25 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.59it/s, loss=0.343]
Epoch 25 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.95it/s, loss=0.343]
Epoch 25 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.95it/s, loss=0.345]
Epoch 25 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.95it/s, loss=0.344]
Epoch 25 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.95it/s, loss=0.343]
Epoch 25 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 28.13it/s, loss=0.343]
Epoch 25 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 28.13it/s, loss=0.344]
Epoch 25 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 28.13it/s, loss=0.343]
Epoch 25 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 28.13it/s, loss=0.343]
Epoch 25 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.41it/s, loss=0.343]
Epoch 25 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.41it/s, loss=0.342]
Epoch 25 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.41it/s, loss=0.341]
Epoch 25 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.41it/s, loss=0.341]
Epoch 25 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.55it/s, loss=0.341]
Epoch 25 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.55it/s, loss=0.34]
Epoch 25 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.55it/s, loss=0.339]
Epoch 25 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.55it/s, loss=0.339]
Epoch 25 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.17it/s, loss=0.339]
Epoch 25 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.17it/s, loss=0.34]
Epoch 25 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.17it/s, loss=0.34]
Epoch 25 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 26.17it/s, loss=0.34]
Epoch 25 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.43it/s, loss=0.34]
Epoch 25 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.43it/s, loss=0.341]
Epoch 25 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.43it/s, loss=0.342]
Epoch 25 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.43it/s, loss=0.342]
Epoch 25 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.69it/s, loss=0.342]
Epoch 25 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.69it/s, loss=0.342]
Epoch 25 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.69it/s, loss=0.341]
Epoch 25 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.69it/s, loss=0.341]
Epoch 25 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 27.53it/s, loss=0.341]
Epoch 25 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 27.53it/s, loss=0.341]
Epoch 25 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 27.53it/s, loss=0.34]
Epoch 25 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 27.53it/s, loss=0.34]
Epoch 25 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 28.10it/s, loss=0.34]
Epoch 25 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 28.10it/s, loss=0.341]
Epoch 25 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 28.10it/s, loss=0.341]
Epoch 25 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 28.10it/s, loss=0.34]
Epoch 25 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.95it/s, loss=0.34]
Epoch 25 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.95it/s, loss=0.34]
Epoch 25 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.95it/s, loss=0.34]
Epoch 25 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.95it/s, loss=0.34]
Epoch 25 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.58it/s, loss=0.34]
Epoch 25 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.58it/s, loss=0.342]
Epoch 25 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.58it/s, loss=0.34]
Epoch 25 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.58it/s, loss=0.341]
Epoch 25 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.45it/s, loss=0.341]
Epoch 25 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.45it/s, loss=0.341]
Epoch 25 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.45it/s, loss=0.34]
2026-08-07 06:52:00.645 | INFO  | __main__:pretrain:180 - Epoch 25/50 | Train Loss: 0.3405 | Val Loss: 0.6879
Epoch 26 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 26 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.239]
Epoch 26 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.247]
Epoch 26 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.251]
Epoch 26 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.257]
Epoch 26 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.68it/s, loss=0.257]
Epoch 26 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.68it/s, loss=0.267]
Epoch 26 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.68it/s, loss=0.298]
Epoch 26 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.68it/s, loss=0.289]
Epoch 26 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.53it/s, loss=0.289]
Epoch 26 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.53it/s, loss=0.332]
Epoch 26 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.53it/s, loss=0.316]
Epoch 26 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.53it/s, loss=0.328]
Epoch 26 [Train]: 8%|▊ | 10/129 [00:00<00:04, 27.95it/s, loss=0.328]
Epoch 26 [Train]: 8%|▊ | 10/129 [00:00<00:04, 27.95it/s, loss=0.326]
Epoch 26 [Train]: 8%|▊ | 10/129 [00:00<00:04, 27.95it/s, loss=0.321]
Epoch 26 [Train]: 8%|▊ | 10/129 [00:00<00:04, 27.95it/s, loss=0.323]
Epoch 26 [Train]: 10%|█ | 13/129 [00:00<00:04, 27.87it/s, loss=0.323]
Epoch 26 [Train]: 10%|█ | 13/129 [00:00<00:04, 27.87it/s, loss=0.337]
Epoch 26 [Train]: 10%|█ | 13/129 [00:00<00:04, 27.87it/s, loss=0.341]
Epoch 26 [Train]: 10%|█ | 13/129 [00:00<00:04, 27.87it/s, loss=0.342]
Epoch 26 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 28.12it/s, loss=0.342]
Epoch 26 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 28.12it/s, loss=0.343]
Epoch 26 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 28.12it/s, loss=0.341]
Epoch 26 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 28.12it/s, loss=0.339]
Epoch 26 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 28.14it/s, loss=0.339]
Epoch 26 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 28.14it/s, loss=0.335]
Epoch 26 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 28.14it/s, loss=0.331]
Epoch 26 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 28.14it/s, loss=0.334]
Epoch 26 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 28.39it/s, loss=0.334]
Epoch 26 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 28.39it/s, loss=0.334]
Epoch 26 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 28.39it/s, loss=0.334]
Epoch 26 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 28.39it/s, loss=0.33]
Epoch 26 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 28.54it/s, loss=0.33]
Epoch 26 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 28.54it/s, loss=0.326]
Epoch 26 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 28.54it/s, loss=0.323]
Epoch 26 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 28.54it/s, loss=0.322]
Epoch 26 [Train]: 22%|██▏ | 28/129 [00:00<00:03, 27.58it/s, loss=0.322]
Epoch 26 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.58it/s, loss=0.323]
Epoch 26 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.58it/s, loss=0.323]
Epoch 26 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.58it/s, loss=0.321]
Epoch 26 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.56it/s, loss=0.321]
Epoch 26 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.56it/s, loss=0.32]
Epoch 26 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.56it/s, loss=0.317]
Epoch 26 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.56it/s, loss=0.315]
Epoch 26 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.98it/s, loss=0.315]
Epoch 26 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.98it/s, loss=0.315]
Epoch 26 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.98it/s, loss=0.318]
Epoch 26 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.98it/s, loss=0.315]
Epoch 26 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.97it/s, loss=0.315]
Epoch 26 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.97it/s, loss=0.318]
Epoch 26 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.97it/s, loss=0.323]
Epoch 26 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.97it/s, loss=0.323]
Epoch 26 [Train]: 31%|███ | 40/129 [00:01<00:03, 28.11it/s, loss=0.323]
Epoch 26 [Train]: 31%|███ | 40/129 [00:01<00:03, 28.11it/s, loss=0.319]
Epoch 26 [Train]: 31%|███ | 40/129 [00:01<00:03, 28.11it/s, loss=0.332]
Epoch 26 [Train]: 31%|███ | 40/129 [00:01<00:03, 28.11it/s, loss=0.331]
Epoch 26 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.07it/s, loss=0.331]
Epoch 26 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.07it/s, loss=0.327]
Epoch 26 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.07it/s, loss=0.331]
Epoch 26 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.07it/s, loss=0.329]
Epoch 26 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.11it/s, loss=0.329]
Epoch 26 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.11it/s, loss=0.331]
Epoch 26 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.11it/s, loss=0.33]
Epoch 26 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.11it/s, loss=0.336]
Epoch 26 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.11it/s, loss=0.336]
Epoch 26 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.11it/s, loss=0.336]
Epoch 26 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.11it/s, loss=0.337]
Epoch 26 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.11it/s, loss=0.336]
Epoch 26 [Train]: 40%|████ | 52/129 [00:01<00:02, 27.66it/s, loss=0.336]
Epoch 26 [Train]: 40%|████ | 52/129 [00:01<00:02, 27.66it/s, loss=0.336]
Epoch 26 [Train]: 40%|████ | 52/129 [00:01<00:02, 27.66it/s, loss=0.336]
Epoch 26 [Train]: 40%|████ | 52/129 [00:01<00:02, 27.66it/s, loss=0.334]
Epoch 26 [Train]: 43%|████▎ | 55/129 [00:01<00:02, 27.52it/s, loss=0.334]
Epoch 26 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.52it/s, loss=0.333]
Epoch 26 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.52it/s, loss=0.333]
Epoch 26 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.52it/s, loss=0.332]
Epoch 26 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.69it/s, loss=0.332]
Epoch 26 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.69it/s, loss=0.332]
Epoch 26 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.69it/s, loss=0.332]
Epoch 26 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.69it/s, loss=0.343]
Epoch 26 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.83it/s, loss=0.343]
Epoch 26 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.83it/s, loss=0.344]
Epoch 26 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.83it/s, loss=0.344]
Epoch 26 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.83it/s, loss=0.343]
Epoch 26 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.44it/s, loss=0.343]
Epoch 26 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.44it/s, loss=0.342]
Epoch 26 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.44it/s, loss=0.346]
Epoch 26 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.44it/s, loss=0.346]
Epoch 26 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.70it/s, loss=0.346]
Epoch 26 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.70it/s, loss=0.345]
Epoch 26 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.70it/s, loss=0.345]
Epoch 26 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 27.70it/s, loss=0.347]
Epoch 26 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.77it/s, loss=0.347]
Epoch 26 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.77it/s, loss=0.347]
Epoch 26 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.77it/s, loss=0.349]
Epoch 26 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 27.77it/s, loss=0.349]
Epoch 26 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.79it/s, loss=0.349]
Epoch 26 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.79it/s, loss=0.351]
Epoch 26 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.79it/s, loss=0.351]
Epoch 26 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.79it/s, loss=0.351]
Epoch 26 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.92it/s, loss=0.351]
Epoch 26 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.92it/s, loss=0.354]
Epoch 26 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.92it/s, loss=0.354]
Epoch 26 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 27.92it/s, loss=0.353]
Epoch 26 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.91it/s, loss=0.353]
Epoch 26 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.91it/s, loss=0.352]
Epoch 26 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.91it/s, loss=0.352]
Epoch 26 [Train]: 61%|██████ | 79/129 [00:02<00:01, 27.91it/s, loss=0.352]
Epoch 26 [Train]: 64%|██████▎ | 82/129 [00:02<00:01, 28.09it/s, loss=0.352]
Epoch 26 [Train]: 64%|██████▎ | 82/129 [00:02<00:01, 28.09it/s, loss=0.352]
Epoch 26 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 28.09it/s, loss=0.351]
Epoch 26 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 28.09it/s, loss=0.35]
Epoch 26 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.76it/s, loss=0.35]
Epoch 26 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.76it/s, loss=0.35]
Epoch 26 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.76it/s, loss=0.351]
Epoch 26 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.76it/s, loss=0.351]
Epoch 26 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.80it/s, loss=0.351]
Epoch 26 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.80it/s, loss=0.354]
Epoch 26 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.80it/s, loss=0.356]
Epoch 26 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.80it/s, loss=0.356]
Epoch 26 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.71it/s, loss=0.356]
Epoch 26 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.71it/s, loss=0.354]
Epoch 26 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.71it/s, loss=0.352]
Epoch 26 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.71it/s, loss=0.353]
Epoch 26 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.92it/s, loss=0.353]
Epoch 26 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.92it/s, loss=0.353]
Epoch 26 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.92it/s, loss=0.353]
Epoch 26 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.92it/s, loss=0.353]
Epoch 26 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.74it/s, loss=0.353]
Epoch 26 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.74it/s, loss=0.353]
Epoch 26 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.74it/s, loss=0.353]
Epoch 26 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.74it/s, loss=0.353]
Epoch 26 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.39it/s, loss=0.353]
Epoch 26 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.39it/s, loss=0.353]
Epoch 26 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.39it/s, loss=0.352]
Epoch 26 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.39it/s, loss=0.352]
Epoch 26 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.81it/s, loss=0.352]
Epoch 26 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.81it/s, loss=0.352]
Epoch 26 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.81it/s, loss=0.352]
Epoch 26 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.81it/s, loss=0.35]
Epoch 26 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.92it/s, loss=0.35]
Epoch 26 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.92it/s, loss=0.35]
Epoch 26 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.92it/s, loss=0.35]
Epoch 26 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.92it/s, loss=0.349]
Epoch 26 [Train]: 84%|████████▍ | 109/129 [00:03<00:00, 27.19it/s, loss=0.349]
Epoch 26 [Train]: 84%|████████▍ | 109/129 [00:03<00:00, 27.19it/s, loss=0.349]
Epoch 26 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 27.19it/s, loss=0.353]
Epoch 26 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 27.19it/s, loss=0.353]
Epoch 26 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.92it/s, loss=0.353]
Epoch 26 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.92it/s, loss=0.354]
Epoch 26 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.92it/s, loss=0.354]
Epoch 26 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.92it/s, loss=0.353]
Epoch 26 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.29it/s, loss=0.353]
Epoch 26 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.29it/s, loss=0.354]
Epoch 26 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.29it/s, loss=0.354]
Epoch 26 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.29it/s, loss=0.354]
Epoch 26 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.05it/s, loss=0.354]
Epoch 26 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.05it/s, loss=0.354]
Epoch 26 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.05it/s, loss=0.352]
Epoch 26 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.05it/s, loss=0.353]
Epoch 26 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.54it/s, loss=0.353]
Epoch 26 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.54it/s, loss=0.352]
Epoch 26 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.54it/s, loss=0.352]
Epoch 26 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.54it/s, loss=0.352]
Epoch 26 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.94it/s, loss=0.352]
Epoch 26 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.94it/s, loss=0.356]
Epoch 26 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.94it/s, loss=0.356]
Epoch 26 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.94it/s, loss=0.355]
Epoch 26 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.12it/s, loss=0.355]
Epoch 26 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.12it/s, loss=0.355]
Epoch 26 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.12it/s, loss=0.354]
2026-08-07 06:52:05.487 | INFO  | __main__:pretrain:180 - Epoch 26/50 | Train Loss: 0.3542 | Val Loss: 0.6829
Epoch 27 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 27 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.321]
Epoch 27 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.28]
Epoch 27 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.291]
Epoch 27 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.3]
Epoch 27 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.43it/s, loss=0.3]
Epoch 27 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.43it/s, loss=0.315]
Epoch 27 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.43it/s, loss=0.301]
Epoch 27 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.43it/s, loss=0.296]
Epoch 27 [Train]: 5%|▌ | 7/129 [00:00<00:04, 27.13it/s, loss=0.296]
Epoch 27 [Train]: 5%|▌ | 7/129 [00:00<00:04, 27.13it/s, loss=0.303]
Epoch 27 [Train]: 5%|▌ | 7/129 [00:00<00:04, 27.13it/s, loss=0.379]
Epoch 27 [Train]: 5%|▌ | 7/129 [00:00<00:04, 27.13it/s, loss=0.366]
Epoch 27 [Train]: 8%|▊ | 10/129 [00:00<00:07, 14.89it/s, loss=0.366]
Epoch 27 [Train]: 8%|▊ | 10/129 [00:00<00:07, 14.89it/s, loss=0.356]
Epoch 27 [Train]: 8%|▊ | 10/129 [00:00<00:07, 14.89it/s, loss=0.358]
Epoch 27 [Train]: 8%|▊ | 10/129 [00:00<00:07, 14.89it/s, loss=0.36]
Epoch 27 [Train]: 10%|█ | 13/129 [00:00<00:06, 17.62it/s, loss=0.36]
Epoch 27 [Train]: 10%|█ | 13/129 [00:00<00:06, 17.62it/s, loss=0.363]
Epoch 27 [Train]: 10%|█ | 13/129 [00:00<00:06, 17.62it/s, loss=0.358]
Epoch 27 [Train]: 10%|█ | 13/129 [00:00<00:06, 17.62it/s, loss=0.357]
Epoch 27 [Train]: 12%|█▏ | 16/129 [00:00<00:05, 20.35it/s, loss=0.357]
Epoch 27 [Train]: 12%|█▏ | 16/129 [00:00<00:05, 20.35it/s, loss=0.35]
Epoch 27 [Train]: 12%|█▏ | 16/129 [00:00<00:05, 20.35it/s, loss=0.354]
Epoch 27 [Train]: 12%|█▏ | 16/129 [00:00<00:05, 20.35it/s, loss=0.349]
Epoch 27 [Train]: 15%|█▍ | 19/129 [00:00<00:05, 21.90it/s, loss=0.349]
Epoch 27 [Train]: 15%|█▍ | 19/129 [00:00<00:05, 21.90it/s, loss=0.349]
Epoch 27 [Train]: 15%|█▍ | 19/129 [00:00<00:05, 21.90it/s, loss=0.35]
Epoch 27 [Train]: 15%|█▍ | 19/129 [00:01<00:05, 21.90it/s, loss=0.346]
Epoch 27 [Train]: 17%|█▋ | 22/129 [00:01<00:04, 23.43it/s, loss=0.346]
Epoch 27 [Train]: 17%|█▋ | 22/129 [00:01<00:04, 23.43it/s, loss=0.347]
Epoch 27 [Train]: 17%|█▋ | 22/129 [00:01<00:04, 23.43it/s, loss=0.343]
Epoch 27 [Train]: 17%|█▋ | 22/129 [00:01<00:04, 23.43it/s, loss=0.337]
Epoch 27 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 24.32it/s, loss=0.337]
Epoch 27 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 24.32it/s, loss=0.338]
Epoch 27 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 24.32it/s, loss=0.341]
Epoch 27 [Train]: 19%|█▉ | 25/129 [00:01<00:04, 24.32it/s, loss=0.339]
Epoch 27 [Train]: 22%|██▏ | 28/129 [00:01<00:04, 24.69it/s, loss=0.339]
Epoch 27 [Train]: 22%|██▏ | 28/129 [00:01<00:04, 24.69it/s, loss=0.339]
Epoch 27 [Train]: 22%|██▏ | 28/129 [00:01<00:04, 24.69it/s, loss=0.336]
Epoch 27 [Train]: 22%|██▏ | 28/129 [00:01<00:04, 24.69it/s, loss=0.333]
Epoch 27 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 25.75it/s, loss=0.333]
Epoch 27 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 25.75it/s, loss=0.338]
Epoch 27 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 25.75it/s, loss=0.344]
Epoch 27 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 25.75it/s, loss=0.343]
Epoch 27 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.31it/s, loss=0.343]
Epoch 27 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.31it/s, loss=0.341]
Epoch 27 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.31it/s, loss=0.34]
Epoch 27 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 26.31it/s, loss=0.343]
Epoch 27 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.48it/s, loss=0.343]
Epoch 27 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.48it/s, loss=0.339]
Epoch 27 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.48it/s, loss=0.339]
Epoch 27 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.48it/s, loss=0.336]
Epoch 27 [Train]: 31%|███ | 40/129 [00:01<00:03, 25.95it/s, loss=0.336]
Epoch 27 [Train]: 31%|███ | 40/129 [00:01<00:03, 25.95it/s, loss=0.338]
Epoch 27 [Train]: 31%|███ | 40/129 [00:01<00:03, 25.95it/s, loss=0.335]
Epoch 27 [Train]: 31%|███ | 40/129 [00:01<00:03, 25.95it/s, loss=0.336]
Epoch 27 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.33it/s, loss=0.336]
Epoch 27 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.33it/s, loss=0.334]
Epoch 27 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.33it/s, loss=0.333]
Epoch 27 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.33it/s, loss=0.332]
Epoch 27 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 25.88it/s, loss=0.332]
Epoch 27 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 25.88it/s, loss=0.33]
Epoch 27 [Train]: 36%|███▌ | 46/129 [00:02<00:03, 25.88it/s, loss=0.331]
Epoch 27 [Train]: 36%|███▌ | 46/129 [00:02<00:03, 25.88it/s, loss=0.331]
Epoch 27 [Train]: 38%|███▊ | 49/129 [00:02<00:03, 26.43it/s, loss=0.331]
Epoch 27 [Train]: 38%|███▊ | 49/129 [00:02<00:03, 26.43it/s, loss=0.33]
Epoch 27 [Train]: 38%|███▊ | 49/129 [00:02<00:03, 26.43it/s, loss=0.328]
Epoch 27 [Train]: 38%|███▊ | 49/129 [00:02<00:03, 26.43it/s, loss=0.331]
Epoch 27 [Train]: 40%|████ | 52/129 [00:02<00:02, 27.04it/s, loss=0.331]
Epoch 27 [Train]: 40%|████ | 52/129 [00:02<00:02, 27.04it/s, loss=0.331]
Epoch 27 [Train]: 40%|████ | 52/129 [00:02<00:02, 27.04it/s, loss=0.332]
Epoch 27 [Train]: 40%|████ | 52/129 [00:02<00:02, 27.04it/s, loss=0.333]
Epoch 27 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.06it/s, loss=0.333]
Epoch 27 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.06it/s, loss=0.331]
Epoch 27 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.06it/s, loss=0.33]
Epoch 27 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.06it/s, loss=0.33]
Epoch 27 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.22it/s, loss=0.33]
Epoch 27 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.22it/s, loss=0.33]
Epoch 27 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.22it/s, loss=0.332]
Epoch 27 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.22it/s, loss=0.332]
Epoch 27 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.78it/s, loss=0.332]
Epoch 27 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.78it/s, loss=0.333]
Epoch 27 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.78it/s, loss=0.331]
Epoch 27 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 26.78it/s, loss=0.33]
Epoch 27 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.63it/s, loss=0.33]
Epoch 27 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.63it/s, loss=0.328]
Epoch 27 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.63it/s, loss=0.328]
Epoch 27 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.63it/s, loss=0.328]
Epoch 27 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.69it/s, loss=0.328]
Epoch 27 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.69it/s, loss=0.329]
Epoch 27 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.69it/s, loss=0.327]
Epoch 27 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.69it/s, loss=0.326]
Epoch 27 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.97it/s, loss=0.326]
Epoch 27 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.97it/s, loss=0.327]
Epoch 27 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.97it/s, loss=0.325]
Epoch 27 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.97it/s, loss=0.324]
Epoch 27 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.42it/s, loss=0.324]
Epoch 27 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 27.42it/s, loss=0.328]
Epoch 27 [Train]: 57%|█████▋ | 73/129 [00:03<00:02, 27.42it/s, loss=0.327]
Epoch 27 [Train]: 57%|█████▋ | 73/129 [00:03<00:02, 27.42it/s, loss=0.329]
Epoch 27 [Train]: 59%|█████▉ | 76/129 [00:03<00:01, 26.81it/s, loss=0.329]
Epoch 27 [Train]: 59%|█████▉ | 76/129 [00:03<00:01, 26.81it/s, loss=0.328]
Epoch 27 [Train]: 59%|█████▉ | 76/129 [00:03<00:01, 26.81it/s, loss=0.328]
Epoch 27 [Train]: 59%|█████▉ | 76/129 [00:03<00:01, 26.81it/s, loss=0.329]
Epoch 27 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.63it/s, loss=0.329]
Epoch 27 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.63it/s, loss=0.331]
Epoch 27 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.63it/s, loss=0.33]
Epoch 27 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.63it/s, loss=0.329]
Epoch 27 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.43it/s, loss=0.329]
Epoch 27 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.43it/s, loss=0.33]
Epoch 27 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.43it/s, loss=0.329]
Epoch 27 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.43it/s, loss=0.329]
Epoch 27 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.03it/s, loss=0.329]
Epoch 27 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.03it/s, loss=0.331]
Epoch 27 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.03it/s, loss=0.331]
Epoch 27 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 27.03it/s, loss=0.329]
Epoch 27 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.22it/s, loss=0.329]
Epoch 27 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.22it/s, loss=0.331]
Epoch 27 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.22it/s, loss=0.33]
Epoch 27 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.22it/s, loss=0.329]
Epoch 27 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.04it/s, loss=0.329]
Epoch 27 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.04it/s, loss=0.328]
Epoch 27 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.04it/s, loss=0.328]
Epoch 27 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.04it/s, loss=0.328]
Epoch 27 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.16it/s, loss=0.328]
Epoch 27 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.16it/s, loss=0.326]
Epoch 27 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.16it/s, loss=0.327]
Epoch 27 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.16it/s, loss=0.327]
Epoch 27 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.19it/s, loss=0.327]
Epoch 27 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.19it/s, loss=0.328]
Epoch 27 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.19it/s, loss=0.329]
Epoch 27 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 27.19it/s, loss=0.33]
Epoch 27 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.92it/s, loss=0.33]
Epoch 27 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.92it/s, loss=0.33]
Epoch 27 [Train]: 78%|███████▊ | 100/129 [00:04<00:01, 26.92it/s, loss=0.329]
Epoch 27 [Train]: 78%|███████▊ | 100/129 [00:04<00:01, 26.92it/s, loss=0.335]
Epoch 27 [Train]: 80%|███████▉ | 103/129 [00:04<00:00, 27.04it/s, loss=0.335]
Epoch 27 [Train]: 80%|███████▉ | 103/129 [00:04<00:00, 27.04it/s, loss=0.334]
Epoch 27 [Train]: 80%|███████▉ | 103/129 [00:04<00:00, 27.04it/s, loss=0.335]
Epoch 27 [Train]: 80%|███████▉ | 103/129 [00:04<00:00, 27.04it/s, loss=0.336]
Epoch 27 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.06it/s, loss=0.336]
Epoch 27 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.06it/s, loss=0.337]
Epoch 27 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.06it/s, loss=0.337]
Epoch 27 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 27.06it/s, loss=0.337]
Epoch 27 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.53it/s, loss=0.337]
Epoch 27 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.53it/s, loss=0.337]
Epoch 27 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.53it/s, loss=0.336]
Epoch 27 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.53it/s, loss=0.336]
Epoch 27 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.90it/s, loss=0.336]
Epoch 27 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.90it/s, loss=0.335]
Epoch 27 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.90it/s, loss=0.334]
Epoch 27 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.90it/s, loss=0.334]
Epoch 27 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 27.22it/s, loss=0.334]
Epoch 27 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 27.22it/s, loss=0.334]
Epoch 27 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 27.22it/s, loss=0.334]
Epoch 27 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 27.22it/s, loss=0.335]
Epoch 27 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 27.37it/s, loss=0.335]
Epoch 27 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 27.37it/s, loss=0.335]
Epoch 27 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 27.37it/s, loss=0.336]
Epoch 27 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 27.37it/s, loss=0.336]
Epoch 27 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.42it/s, loss=0.336]
Epoch 27 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.42it/s, loss=0.335]
Epoch 27 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.42it/s, loss=0.336]
Epoch 27 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.42it/s, loss=0.336]
Epoch 27 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.31it/s, loss=0.336]
Epoch 27 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.31it/s, loss=0.336]
Epoch 27 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.31it/s, loss=0.336]
Epoch 27 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.31it/s, loss=0.336]
Epoch 27 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.80it/s, loss=0.336]
Epoch 27 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.80it/s, loss=0.337]
Epoch 27 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.80it/s, loss=0.336]
2026-08-07 06:52:10.628 | INFO  | __main__:pretrain:180 - Epoch 27/50 | Train Loss: 0.3358 | Val Loss: 0.6680
Epoch 28 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 28 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.26]
Epoch 28 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.229]
Epoch 28 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.198]
Epoch 28 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.227]
Epoch 28 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.74it/s, loss=0.227]
Epoch 28 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.74it/s, loss=0.227]
Epoch 28 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.74it/s, loss=0.238]
Epoch 28 [Train]: 3%|▎ | 4/129 [00:00<00:04, 29.74it/s, loss=0.227]
Epoch 28 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.81it/s, loss=0.227]
Epoch 28 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.81it/s, loss=0.25]
Epoch 28 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.81it/s, loss=0.277]
Epoch 28 [Train]: 5%|▌ | 7/129 [00:00<00:04, 28.81it/s, loss=0.279]
Epoch 28 [Train]: 8%|▊ | 10/129 [00:00<00:04, 27.37it/s, loss=0.279]
Epoch 28 [Train]: 8%|▊ | 10/129 [00:00<00:04, 27.37it/s, loss=0.282]
Epoch 28 [Train]: 8%|▊ | 10/129 [00:00<00:04, 27.37it/s, loss=0.277]
Epoch 28 [Train]: 8%|▊ | 10/129 [00:00<00:04, 27.37it/s, loss=0.282]
Epoch 28 [Train]: 10%|█ | 13/129 [00:00<00:04, 27.24it/s, loss=0.282]
Epoch 28 [Train]: 10%|█ | 13/129 [00:00<00:04, 27.24it/s, loss=0.288]
Epoch 28 [Train]: 10%|█ | 13/129 [00:00<00:04, 27.24it/s, loss=0.283]
Epoch 28 [Train]: 10%|█ | 13/129 [00:00<00:04, 27.24it/s, loss=0.288]
Epoch 28 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 27.31it/s, loss=0.288]
Epoch 28 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 27.31it/s, loss=0.288]
Epoch 28 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 27.31it/s, loss=0.291]
Epoch 28 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 27.31it/s, loss=0.299]
Epoch 28 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 27.06it/s, loss=0.299]
Epoch 28 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 27.06it/s, loss=0.296]
Epoch 28 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 27.06it/s, loss=0.301]
Epoch 28 [Train]: 15%|█▍ | 19/129 [00:00<00:04, 27.06it/s, loss=0.3]
Epoch 28 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.92it/s, loss=0.3]
Epoch 28 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.92it/s, loss=0.298]
Epoch 28 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.92it/s, loss=0.304]
Epoch 28 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.92it/s, loss=0.305]
Epoch 28 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 27.83it/s, loss=0.305]
Epoch 28 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 27.83it/s, loss=0.304]
Epoch 28 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 27.83it/s, loss=0.305]
Epoch 28 [Train]: 19%|█▉ | 25/129 [00:01<00:03, 27.83it/s, loss=0.305]
Epoch 28 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.59it/s, loss=0.305]
Epoch 28 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.59it/s, loss=0.304]
Epoch 28 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.59it/s, loss=0.306]
Epoch 28 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.59it/s, loss=0.302]
Epoch 28 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.41it/s, loss=0.302]
Epoch 28 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.41it/s, loss=0.303]
Epoch 28 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.41it/s, loss=0.305]
Epoch 28 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 27.41it/s, loss=0.306]
Epoch 28 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.23it/s, loss=0.306]
Epoch 28 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.23it/s, loss=0.305]
Epoch 28 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.23it/s, loss=0.308]
Epoch 28 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 27.23it/s, loss=0.307]
Epoch 28 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.58it/s, loss=0.307]
Epoch 28 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.58it/s, loss=0.309]
Epoch 28 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.58it/s, loss=0.31]
Epoch 28 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 27.58it/s, loss=0.308]
Epoch 28 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.15it/s, loss=0.308]
Epoch 28 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.15it/s, loss=0.307]
Epoch 28 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.15it/s, loss=0.305]
Epoch 28 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.15it/s, loss=0.308]
Epoch 28 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.88it/s, loss=0.308]
Epoch 28 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.88it/s, loss=0.307]
Epoch 28 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.88it/s, loss=0.308]
Epoch 28 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 26.88it/s, loss=0.307]
Epoch 28 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.49it/s, loss=0.307]
Epoch 28 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.49it/s, loss=0.307]
Epoch 28 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.49it/s, loss=0.306]
Epoch 28 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 26.49it/s, loss=0.304]
Epoch 28 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.11it/s, loss=0.304]
Epoch 28 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.11it/s, loss=0.304]
Epoch 28 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.11it/s, loss=0.308]
Epoch 28 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.11it/s, loss=0.31]
Epoch 28 [Train]: 40%|████ | 52/129 [00:01<00:02, 26.64it/s, loss=0.31]
Epoch 28 [Train]: 40%|████ | 52/129 [00:01<00:02, 26.64it/s, loss=0.31]
Epoch 28 [Train]: 40%|████ | 52/129 [00:01<00:02, 26.64it/s, loss=0.31]
Epoch 28 [Train]: 40%|████ | 52/129 [00:02<00:02, 26.64it/s, loss=0.309]
Epoch 28 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.39it/s, loss=0.309]
Epoch 28 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.39it/s, loss=0.308]
Epoch 28 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.39it/s, loss=0.312]
Epoch 28 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 26.39it/s, loss=0.311]
Epoch 28 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.26it/s, loss=0.311]
Epoch 28 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.26it/s, loss=0.312]
Epoch 28 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.26it/s, loss=0.31]
Epoch 28 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 26.26it/s, loss=0.319]
Epoch 28 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 25.88it/s, loss=0.319]
Epoch 28 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 25.88it/s, loss=0.318]
Epoch 28 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 25.88it/s, loss=0.319]
Epoch 28 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 25.88it/s, loss=0.318]
Epoch 28 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.23it/s, loss=0.318]
Epoch 28 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.23it/s, loss=0.319]
Epoch 28 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.23it/s, loss=0.32]
Epoch 28 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 26.23it/s, loss=0.322]
Epoch 28 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.40it/s, loss=0.322]
Epoch 28 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.40it/s, loss=0.32]
Epoch 28 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.40it/s, loss=0.32]
Epoch 28 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.40it/s, loss=0.32]
Epoch 28 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.43it/s, loss=0.32]
Epoch 28 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.43it/s, loss=0.32]
Epoch 28 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.43it/s, loss=0.32]
Epoch 28 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.43it/s, loss=0.317]
Epoch 28 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.70it/s, loss=0.317]
Epoch 28 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.70it/s, loss=0.318]
Epoch 28 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.70it/s, loss=0.316]
Epoch 28 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.70it/s, loss=0.315]
Epoch 28 [Train]: 59%|█████▉ | 76/129 [00:02<00:02, 26.27it/s, loss=0.315]
Epoch 28 [Train]: 59%|█████▉ | 76/129 [00:02<00:02, 26.27it/s, loss=0.313]
Epoch 28 [Train]: 59%|█████▉ | 76/129 [00:02<00:02, 26.27it/s, loss=0.312]
Epoch 28 [Train]: 59%|█████▉ | 76/129 [00:02<00:02, 26.27it/s, loss=0.312]
Epoch 28 [Train]: 61%|██████ | 79/129 [00:02<00:01, 26.28it/s, loss=0.312]
Epoch 28 [Train]: 61%|██████ | 79/129 [00:02<00:01, 26.28it/s, loss=0.312]
Epoch 28 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.28it/s, loss=0.312]
Epoch 28 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.28it/s, loss=0.311]
Epoch 28 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.23it/s, loss=0.311]
Epoch 28 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.23it/s, loss=0.31]
Epoch 28 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.23it/s, loss=0.31]
Epoch 28 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.23it/s, loss=0.308]
Epoch 28 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.15it/s, loss=0.308]
Epoch 28 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.15it/s, loss=0.307]
Epoch 28 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.15it/s, loss=0.31]
Epoch 28 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.15it/s, loss=0.308]
Epoch 28 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.15it/s, loss=0.308]
Epoch 28 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.15it/s, loss=0.308]
Epoch 28 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.15it/s, loss=0.308]
Epoch 28 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.15it/s, loss=0.307]
Epoch 28 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.23it/s, loss=0.307]
Epoch 28 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.23it/s, loss=0.307]
Epoch 28 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.23it/s, loss=0.307]
Epoch 28 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.23it/s, loss=0.307]
Epoch 28 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.14it/s, loss=0.307]
Epoch 28 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.14it/s, loss=0.307]
Epoch 28 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.14it/s, loss=0.308]
Epoch 28 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 27.14it/s, loss=0.309]
Epoch 28 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.77it/s, loss=0.309]
Epoch 28 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.77it/s, loss=0.309]
Epoch 28 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.77it/s, loss=0.311]
Epoch 28 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.77it/s, loss=0.31]
Epoch 28 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.17it/s, loss=0.31]
Epoch 28 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.17it/s, loss=0.312]
Epoch 28 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.17it/s, loss=0.312]
Epoch 28 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 27.17it/s, loss=0.312]
Epoch 28 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 27.16it/s, loss=0.312]
Epoch 28 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 27.16it/s, loss=0.315]
Epoch 28 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 27.16it/s, loss=0.315]
Epoch 28 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 27.16it/s, loss=0.316]
Epoch 28 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.65it/s, loss=0.316]
Epoch 28 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 26.65it/s, loss=0.316]
Epoch 28 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 26.65it/s, loss=0.317]
Epoch 28 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 26.65it/s, loss=0.318]
Epoch 28 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.82it/s, loss=0.318]
Epoch 28 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.82it/s, loss=0.318]
Epoch 28 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.82it/s, loss=0.321]
Epoch 28 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 26.82it/s, loss=0.321]
Epoch 28 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.65it/s, loss=0.321]
Epoch 28 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.65it/s, loss=0.32]
Epoch 28 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.65it/s, loss=0.32]
Epoch 28 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 26.65it/s, loss=0.319]
Epoch 28 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.22it/s, loss=0.319]
Epoch 28 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.22it/s, loss=0.319]
Epoch 28 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.22it/s, loss=0.319]
Epoch 28 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 26.22it/s, loss=0.319]
Epoch 28 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.38it/s, loss=0.319]
Epoch 28 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.38it/s, loss=0.32]
Epoch 28 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.38it/s, loss=0.319]
Epoch 28 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.38it/s, loss=0.319]
Epoch 28 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.19it/s, loss=0.319]
Epoch 28 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.19it/s, loss=0.319]
Epoch 28 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.19it/s, loss=0.32]
Epoch 28 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 27.19it/s, loss=0.321]
Epoch 28 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.22it/s, loss=0.321]
Epoch 28 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.22it/s, loss=0.32]
Epoch 28 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.22it/s, loss=0.32]
Epoch 28 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 27.22it/s, loss=0.32]
Epoch 28 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.34it/s, loss=0.32]
Epoch 28 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.34it/s, loss=0.322]
Epoch 28 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.34it/s, loss=0.322]
2026-08-07 06:52:15.570 | INFO  | __main__:pretrain:180 - Epoch 28/50 | Train Loss: 0.3220 | Val Loss: 0.7306
Epoch 29 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 29 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.261]
Epoch 29 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.291]
Epoch 29 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.257]
Epoch 29 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.35it/s, loss=0.257]
Epoch 29 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.35it/s, loss=0.257]
Epoch 29 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.35it/s, loss=0.276]
Epoch 29 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.35it/s, loss=0.28]
Epoch 29 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.13it/s, loss=0.28]
Epoch 29 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.13it/s, loss=0.273]
Epoch 29 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.13it/s, loss=0.285]
Epoch 29 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.13it/s, loss=0.288]
Epoch 29 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.37it/s, loss=0.288]
Epoch 29 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.37it/s, loss=0.302]
Epoch 29 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.37it/s, loss=0.301]
Epoch 29 [Train]: 7%|▋ | 9/129 [00:00<00:04, 28.37it/s, loss=0.297]
Epoch 29 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.15it/s, loss=0.297]
Epoch 29 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.15it/s, loss=0.297]
Epoch 29 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.15it/s, loss=0.29]
Epoch 29 [Train]: 9%|▉ | 12/129 [00:00<00:04, 28.15it/s, loss=0.288]
Epoch 29 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.80it/s, loss=0.288]
Epoch 29 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.80it/s, loss=0.287]
Epoch 29 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.80it/s, loss=0.281]
Epoch 29 [Train]: 12%|█▏ | 15/129 [00:00<00:04, 27.80it/s, loss=0.282]
Epoch 29 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.16it/s, loss=0.282]
Epoch 29 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.16it/s, loss=0.28]
Epoch 29 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.16it/s, loss=0.276]
Epoch 29 [Train]: 14%|█▍ | 18/129 [00:00<00:04, 27.16it/s, loss=0.276]
Epoch 29 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.04it/s, loss=0.276]
Epoch 29 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.04it/s, loss=0.279]
Epoch 29 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.04it/s, loss=0.282]
Epoch 29 [Train]: 16%|█▋ | 21/129 [00:00<00:03, 27.04it/s, loss=0.281]
Epoch 29 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.06it/s, loss=0.281]
Epoch 29 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.06it/s, loss=0.287]
Epoch 29 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.06it/s, loss=0.285]
Epoch 29 [Train]: 19%|█▊ | 24/129 [00:00<00:03, 27.06it/s, loss=0.284]
Epoch 29 [Train]: 21%|██ | 27/129 [00:00<00:03, 26.54it/s, loss=0.284]
Epoch 29 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.54it/s, loss=0.283]
Epoch 29 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.54it/s, loss=0.285]
Epoch 29 [Train]: 21%|██ | 27/129 [00:01<00:03, 26.54it/s, loss=0.281]
Epoch 29 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.78it/s, loss=0.281]
Epoch 29 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.78it/s, loss=0.279]
Epoch 29 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.78it/s, loss=0.284]
Epoch 29 [Train]: 23%|██▎ | 30/129 [00:01<00:03, 26.78it/s, loss=0.284]
Epoch 29 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.31it/s, loss=0.284]
Epoch 29 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.31it/s, loss=0.287]
Epoch 29 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.31it/s, loss=0.288]
Epoch 29 [Train]: 26%|██▌ | 33/129 [00:01<00:03, 27.31it/s, loss=0.288]
Epoch 29 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.53it/s, loss=0.288]
Epoch 29 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.53it/s, loss=0.292]
Epoch 29 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.53it/s, loss=0.291]
Epoch 29 [Train]: 28%|██▊ | 36/129 [00:01<00:03, 27.53it/s, loss=0.289]
Epoch 29 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.39it/s, loss=0.289]
Epoch 29 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.39it/s, loss=0.291]
Epoch 29 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.39it/s, loss=0.291]
Epoch 29 [Train]: 30%|███ | 39/129 [00:01<00:03, 27.39it/s, loss=0.291]
Epoch 29 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.06it/s, loss=0.291]
Epoch 29 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.06it/s, loss=0.292]
Epoch 29 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.06it/s, loss=0.291]
Epoch 29 [Train]: 33%|███▎ | 42/129 [00:01<00:03, 27.06it/s, loss=0.303]
Epoch 29 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.55it/s, loss=0.303]
Epoch 29 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.55it/s, loss=0.304]
Epoch 29 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.55it/s, loss=0.302]
Epoch 29 [Train]: 35%|███▍ | 45/129 [00:01<00:03, 26.55it/s, loss=0.304]
Epoch 29 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.79it/s, loss=0.304]
Epoch 29 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.79it/s, loss=0.303]
Epoch 29 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.79it/s, loss=0.302]
Epoch 29 [Train]: 37%|███▋ | 48/129 [00:01<00:03, 26.79it/s, loss=0.302]
Epoch 29 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.91it/s, loss=0.302]
Epoch 29 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.91it/s, loss=0.302]
Epoch 29 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.91it/s, loss=0.303]
Epoch 29 [Train]: 40%|███▉ | 51/129 [00:01<00:02, 26.91it/s, loss=0.303]
Epoch 29 [Train]: 42%|████▏ | 54/129 [00:01<00:02, 27.28it/s, loss=0.303]
Epoch 29 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.28it/s, loss=0.305]
Epoch 29 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.28it/s, loss=0.305]
Epoch 29 [Train]: 42%|████▏ | 54/129 [00:02<00:02, 27.28it/s, loss=0.305]
Epoch 29 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.34it/s, loss=0.305]
Epoch 29 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.34it/s, loss=0.305]
Epoch 29 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.34it/s, loss=0.303]
Epoch 29 [Train]: 44%|████▍ | 57/129 [00:02<00:02, 27.34it/s, loss=0.305]
Epoch 29 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.85it/s, loss=0.305]
Epoch 29 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.85it/s, loss=0.306]
Epoch 29 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.85it/s, loss=0.304]
Epoch 29 [Train]: 47%|████▋ | 60/129 [00:02<00:02, 26.85it/s, loss=0.304]
Epoch 29 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.78it/s, loss=0.304]
Epoch 29 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.78it/s, loss=0.305]
Epoch 29 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.78it/s, loss=0.304]
Epoch 29 [Train]: 49%|████▉ | 63/129 [00:02<00:02, 26.78it/s, loss=0.308]
Epoch 29 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.85it/s, loss=0.308]
Epoch 29 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.85it/s, loss=0.308]
Epoch 29 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.85it/s, loss=0.309]
Epoch 29 [Train]: 51%|█████ | 66/129 [00:02<00:02, 26.85it/s, loss=0.308]
Epoch 29 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.95it/s, loss=0.308]
Epoch 29 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.95it/s, loss=0.307]
Epoch 29 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.95it/s, loss=0.307]
Epoch 29 [Train]: 53%|█████▎ | 69/129 [00:02<00:02, 26.95it/s, loss=0.306]
Epoch 29 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.03it/s, loss=0.306]
Epoch 29 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.03it/s, loss=0.306]
Epoch 29 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.03it/s, loss=0.307]
Epoch 29 [Train]: 56%|█████▌ | 72/129 [00:02<00:02, 27.03it/s, loss=0.306]
Epoch 29 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 27.00it/s, loss=0.306]
Epoch 29 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 27.00it/s, loss=0.306]
Epoch 29 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 27.00it/s, loss=0.307]
Epoch 29 [Train]: 58%|█████▊ | 75/129 [00:02<00:02, 27.00it/s, loss=0.308]
Epoch 29 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.18it/s, loss=0.308]
Epoch 29 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.18it/s, loss=0.307]
Epoch 29 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.18it/s, loss=0.309]
Epoch 29 [Train]: 60%|██████ | 78/129 [00:02<00:01, 27.18it/s, loss=0.309]
Epoch 29 [Train]: 63%|██████▎ | 81/129 [00:02<00:01, 27.39it/s, loss=0.309]
Epoch 29 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.39it/s, loss=0.308]
Epoch 29 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.39it/s, loss=0.31]
Epoch 29 [Train]: 63%|██████▎ | 81/129 [00:03<00:01, 27.39it/s, loss=0.31]
Epoch 29 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.52it/s, loss=0.31]
Epoch 29 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.52it/s, loss=0.309]
Epoch 29 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.52it/s, loss=0.308]
Epoch 29 [Train]: 65%|██████▌ | 84/129 [00:03<00:01, 27.52it/s, loss=0.308]
Epoch 29 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.33it/s, loss=0.308]
Epoch 29 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.33it/s, loss=0.308]
Epoch 29 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.33it/s, loss=0.308]
Epoch 29 [Train]: 67%|██████▋ | 87/129 [00:03<00:01, 27.33it/s, loss=0.307]
Epoch 29 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.20it/s, loss=0.307]
Epoch 29 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.20it/s, loss=0.307]
Epoch 29 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.20it/s, loss=0.306]
Epoch 29 [Train]: 70%|██████▉ | 90/129 [00:03<00:01, 27.20it/s, loss=0.307]
Epoch 29 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.29it/s, loss=0.307]
Epoch 29 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.29it/s, loss=0.306]
Epoch 29 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.29it/s, loss=0.307]
Epoch 29 [Train]: 72%|███████▏ | 93/129 [00:03<00:01, 27.29it/s, loss=0.306]
Epoch 29 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.29it/s, loss=0.306]
Epoch 29 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.29it/s, loss=0.307]
Epoch 29 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.29it/s, loss=0.306]
Epoch 29 [Train]: 74%|███████▍ | 96/129 [00:03<00:01, 27.29it/s, loss=0.306]
Epoch 29 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.37it/s, loss=0.306]
Epoch 29 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.37it/s, loss=0.307]
Epoch 29 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.37it/s, loss=0.307]
Epoch 29 [Train]: 77%|███████▋ | 99/129 [00:03<00:01, 27.37it/s, loss=0.307]
Epoch 29 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.26it/s, loss=0.307]
Epoch 29 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.26it/s, loss=0.306]
Epoch 29 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.26it/s, loss=0.305]
Epoch 29 [Train]: 79%|███████▉ | 102/129 [00:03<00:00, 27.26it/s, loss=0.305]
Epoch 29 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.26it/s, loss=0.305]
Epoch 29 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.26it/s, loss=0.306]
Epoch 29 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.26it/s, loss=0.307]
Epoch 29 [Train]: 81%|████████▏ | 105/129 [00:03<00:00, 27.26it/s, loss=0.307]
Epoch 29 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 27.81it/s, loss=0.307]
Epoch 29 [Train]: 84%|████████▎ | 108/129 [00:03<00:00, 27.81it/s, loss=0.307]
Epoch 29 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.81it/s, loss=0.308]
Epoch 29 [Train]: 84%|████████▎ | 108/129 [00:04<00:00, 27.81it/s, loss=0.307]
Epoch 29 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.53it/s, loss=0.307]
Epoch 29 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.53it/s, loss=0.307]
Epoch 29 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.53it/s, loss=0.307]
Epoch 29 [Train]: 86%|████████▌ | 111/129 [00:04<00:00, 27.53it/s, loss=0.306]
Epoch 29 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.42it/s, loss=0.306]
Epoch 29 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.42it/s, loss=0.306]
Epoch 29 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.42it/s, loss=0.306]
Epoch 29 [Train]: 88%|████████▊ | 114/129 [00:04<00:00, 27.42it/s, loss=0.306]
Epoch 29 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.34it/s, loss=0.306]
Epoch 29 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.34it/s, loss=0.305]
Epoch 29 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.34it/s, loss=0.305]
Epoch 29 [Train]: 91%|█████████ | 117/129 [00:04<00:00, 27.34it/s, loss=0.305]
Epoch 29 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.34it/s, loss=0.305]
Epoch 29 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.34it/s, loss=0.305]
Epoch 29 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.34it/s, loss=0.304]
Epoch 29 [Train]: 93%|█████████▎| 120/129 [00:04<00:00, 27.34it/s, loss=0.305]
Epoch 29 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.61it/s, loss=0.305]
Epoch 29 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.61it/s, loss=0.304]
Epoch 29 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.61it/s, loss=0.305]
Epoch 29 [Train]: 95%|█████████▌| 123/129 [00:04<00:00, 27.61it/s, loss=0.306]
Epoch 29 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.90it/s, loss=0.306]
Epoch 29 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.90it/s, loss=0.306]
Epoch 29 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.90it/s, loss=0.305]
Epoch 29 [Train]: 98%|█████████▊| 126/129 [00:04<00:00, 27.90it/s, loss=0.306]
Epoch 29 [Train]: 100%|██████████| 129/129 [00:04<00:00, 27.17it/s, loss=0.306]
2026-08-07 06:52:20.457 | INFO  | __main__:pretrain:180 - Epoch 29/50 | Train Loss: 0.3064 | Val Loss: 0.9027
Epoch 30 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 30 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.21]
Epoch 30 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.225]
Epoch 30 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.281]
Epoch 30 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.91it/s, loss=0.281]
Epoch 30 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.91it/s, loss=0.264]
Epoch 30 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.91it/s, loss=0.29]
Epoch 30 [Train]: 2%|▏ | 3/129 [00:00<00:04, 29.91it/s, loss=0.295]
Epoch 30 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.00it/s, loss=0.295]
Epoch 30 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.00it/s, loss=0.293]
Epoch 30 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.00it/s, loss=0.308]
Epoch 30 [Train]: 5%|▍ | 6/129 [00:00<00:04, 28.00it/s, loss=0.302]
Epoch 30 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.64it/s, loss=0.302]
Epoch 30 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.64it/s, loss=0.3]
Epoch 30 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.64it/s, loss=0.291]
Epoch 30 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.64it/s, loss=0.293]
Epoch 30 [Train]: 7%|▋ | 9/129 [00:00<00:04, 27.64it/s, loss=0.292]
Epoch 30 [Train]: 10%|█ | 13/129 [00:00<00:04, 28.77it/s, loss=0.292]
Epoch 30 [Train]: 10%|█ | 13/129 [00:00<00:04, 28.77it/s, loss=0.294]
Epoch 30 [Train]: 10%|█ | 13/129 [00:00<00:04, 28.77it/s, loss=0.292]
Epoch 30 [Train]: 10%|█ | 13/129 [00:00<00:04, 28.77it/s, loss=0.292]
Epoch 30 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 27.97it/s, loss=0.292]
Epoch 30 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 27.97it/s, loss=0.288]
Epoch 30 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 27.97it/s, loss=0.286]
Epoch 30 [Train]: 12%|█▏ | 16/129 [00:00<00:04, 27.97it/s, loss=0.287]
Epoch 30 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 28.10it/s, loss=0.287]
Epoch 30 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 28.10it/s, loss=0.286]
Epoch 30 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 28.10it/s, loss=0.286]
Epoch 30 [Train]: 15%|█▍ | 19/129 [00:00<00:03, 28.10it/s, loss=0.288]
Epoch 30 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.14it/s, loss=0.288]
Epoch 30 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.14it/s, loss=0.287]
Epoch 30 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.14it/s, loss=0.282]
Epoch 30 [Train]: 17%|█▋ | 22/129 [00:00<00:03, 27.14it/s, loss=0.281]
Epoch 30 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 27.08it/s, loss=0.281]
Epoch 30 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 27.08it/s, loss=0.281]
Epoch 30 [Train]: 19%|█▉ | 25/129 [00:00<00:03, 27.08it/s, loss=0.281]
Epoch 30 [Train]: 19%|█▉ | 25/129 [00:01<00:03, 27.08it/s, loss=0.28]
Epoch 30 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.01it/s, loss=0.28]
Epoch 30 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.01it/s, loss=0.278]
Epoch 30 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.01it/s, loss=0.284]
Epoch 30 [Train]: 22%|██▏ | 28/129 [00:01<00:03, 27.01it/s, loss=0.284]
Epoch 30 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.28it/s, loss=0.284]
Epoch 30 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.28it/s, loss=0.283]
Epoch 30 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.28it/s, loss=0.285]
Epoch 30 [Train]: 24%|██▍ | 31/129 [00:01<00:03, 26.28it/s, loss=0.285]
Epoch 30 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 25.91it/s, loss=0.285]
Epoch 30 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 25.91it/s, loss=0.282]
Epoch 30 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 25.91it/s, loss=0.283]
Epoch 30 [Train]: 26%|██▋ | 34/129 [00:01<00:03, 25.91it/s, loss=0.282]
Epoch 30 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.08it/s, loss=0.282]
Epoch 30 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.08it/s, loss=0.279]
Epoch 30 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.08it/s, loss=0.278]
Epoch 30 [Train]: 29%|██▊ | 37/129 [00:01<00:03, 26.08it/s, loss=0.278]
Epoch 30 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.05it/s, loss=0.278]
Epoch 30 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.05it/s, loss=0.278]
Epoch 30 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.05it/s, loss=0.278]
Epoch 30 [Train]: 31%|███ | 40/129 [00:01<00:03, 27.05it/s, loss=0.278]
Epoch 30 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.16it/s, loss=0.278]
Epoch 30 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.16it/s, loss=0.279]
Epoch 30 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.16it/s, loss=0.281]
Epoch 30 [Train]: 33%|███▎ | 43/129 [00:01<00:03, 27.16it/s, loss=0.28]
Epoch 30 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.31it/s, loss=0.28]
Epoch 30 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.31it/s, loss=0.282]
Epoch 30 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.31it/s, loss=0.281]
Epoch 30 [Train]: 36%|███▌ | 46/129 [00:01<00:03, 27.31it/s, loss=0.282]
Epoch 30 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.93it/s, loss=0.282]
Epoch 30 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.93it/s, loss=0.282]
Epoch 30 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.93it/s, loss=0.284]
Epoch 30 [Train]: 38%|███▊ | 49/129 [00:01<00:02, 27.93it/s, loss=0.284]
Epoch 30 [Train]: 40%|████ | 52/129 [00:01<00:02, 27.65it/s, loss=0.284]
Epoch 30 [Train]: 40%|████ | 52/129 [00:01<00:02, 27.65it/s, loss=0.286]
Epoch 30 [Train]: 40%|████ | 52/129 [00:01<00:02, 27.65it/s, loss=0.287]
Epoch 30 [Train]: 40%|████ | 52/129 [00:02<00:02, 27.65it/s, loss=0.287]
Epoch 30 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.62it/s, loss=0.287]
Epoch 30 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.62it/s, loss=0.288]
Epoch 30 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.62it/s, loss=0.289]
Epoch 30 [Train]: 43%|████▎ | 55/129 [00:02<00:02, 27.62it/s, loss=0.29]
Epoch 30 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.94it/s, loss=0.29]
Epoch 30 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.94it/s, loss=0.291]
Epoch 30 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.94it/s, loss=0.29]
Epoch 30 [Train]: 45%|████▍ | 58/129 [00:02<00:02, 27.94it/s, loss=0.289]
Epoch 30 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.22it/s, loss=0.289]
Epoch 30 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.22it/s, loss=0.29]
Epoch 30 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.22it/s, loss=0.29]
Epoch 30 [Train]: 47%|████▋ | 61/129 [00:02<00:02, 27.22it/s, loss=0.292]
Epoch 30 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.36it/s, loss=0.292]
Epoch 30 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.36it/s, loss=0.292]
Epoch 30 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.36it/s, loss=0.291]
Epoch 30 [Train]: 50%|████▉ | 64/129 [00:02<00:02, 27.36it/s, loss=0.292]
Epoch 30 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.95it/s, loss=0.292]
Epoch 30 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.95it/s, loss=0.294]
Epoch 30 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.95it/s, loss=0.293]
Epoch 30 [Train]: 52%|█████▏ | 67/129 [00:02<00:02, 26.95it/s, loss=0.296]
Epoch 30 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.84it/s, loss=0.296]
Epoch 30 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.84it/s, loss=0.295]
Epoch 30 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.84it/s, loss=0.295]
Epoch 30 [Train]: 54%|█████▍ | 70/129 [00:02<00:02, 26.84it/s, loss=0.295]
Epoch 30 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.34it/s, loss=0.295]
Epoch 30 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.34it/s, loss=0.294]
Epoch 30 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.34it/s, loss=0.295]
Epoch 30 [Train]: 57%|█████▋ | 73/129 [00:02<00:02, 26.34it/s, loss=0.294]
Epoch 30 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 26.53it/s, loss=0.294]
Epoch 30 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 26.53it/s, loss=0.293]
Epoch 30 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 26.53it/s, loss=0.292]
Epoch 30 [Train]: 59%|█████▉ | 76/129 [00:02<00:01, 26.53it/s, loss=0.292]
Epoch 30 [Train]: 61%|██████ | 79/129 [00:02<00:01, 26.06it/s, loss=0.292]
Epoch 30 [Train]: 61%|██████ | 79/129 [00:02<00:01, 26.06it/s, loss=0.291]
Epoch 30 [Train]: 61%|██████ | 79/129 [00:02<00:01, 26.06it/s, loss=0.29]
Epoch 30 [Train]: 61%|██████ | 79/129 [00:03<00:01, 26.06it/s, loss=0.292]
Epoch 30 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.39it/s, loss=0.292]
Epoch 30 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.39it/s, loss=0.295]
Epoch 30 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.39it/s, loss=0.296]
Epoch 30 [Train]: 64%|██████▎ | 82/129 [00:03<00:01, 26.39it/s, loss=0.297]
Epoch 30 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.54it/s, loss=0.297]
Epoch 30 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.54it/s, loss=0.296]
Epoch 30 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.54it/s, loss=0.301]
Epoch 30 [Train]: 66%|██████▌ | 85/129 [00:03<00:01, 26.54it/s, loss=0.301]
Epoch 30 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.25it/s, loss=0.301]
Epoch 30 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.25it/s, loss=0.305]
Epoch 30 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.25it/s, loss=0.304]
Epoch 30 [Train]: 68%|██████▊ | 88/129 [00:03<00:01, 27.25it/s, loss=0.304]
Epoch 30 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.03it/s, loss=0.304]
Epoch 30 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.03it/s, loss=0.304]
Epoch 30 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.03it/s, loss=0.304]
Epoch 30 [Train]: 71%|███████ | 91/129 [00:03<00:01, 27.03it/s, loss=0.303]
Epoch 30 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.61it/s, loss=0.303]
Epoch 30 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.61it/s, loss=0.303]
Epoch 30 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.61it/s, loss=0.303]
Epoch 30 [Train]: 73%|███████▎ | 94/129 [00:03<00:01, 26.61it/s, loss=0.302]
Epoch 30 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.75it/s, loss=0.302]
Epoch 30 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.75it/s, loss=0.301]
Epoch 30 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.75it/s, loss=0.303]
Epoch 30 [Train]: 75%|███████▌ | 97/129 [00:03<00:01, 26.75it/s, loss=0.303]
Epoch 30 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.94it/s, loss=0.303]
Epoch 30 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.94it/s, loss=0.303]
Epoch 30 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.94it/s, loss=0.303]
Epoch 30 [Train]: 78%|███████▊ | 100/129 [00:03<00:01, 26.94it/s, loss=0.302]
Epoch 30 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.21it/s, loss=0.302]
Epoch 30 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.21it/s, loss=0.303]
Epoch 30 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.21it/s, loss=0.302]
Epoch 30 [Train]: 80%|███████▉ | 103/129 [00:03<00:00, 26.21it/s, loss=0.301]
Epoch 30 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 25.86it/s, loss=0.301]
Epoch 30 [Train]: 82%|████████▏ | 106/129 [00:03<00:00, 25.86it/s, loss=0.3]
Epoch 30 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 25.86it/s, loss=0.3]
Epoch 30 [Train]: 82%|████████▏ | 106/129 [00:04<00:00, 25.86it/s, loss=0.301]
Epoch 30 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 25.55it/s, loss=0.301]
Epoch 30 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 25.55it/s, loss=0.301]
Epoch 30 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 25.55it/s, loss=0.301]
Epoch 30 [Train]: 84%|████████▍ | 109/129 [00:04<00:00, 25.55it/s, loss=0.303]
Epoch 30 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 25.98it/s, loss=0.303]
Epoch 30 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 25.98it/s, loss=0.303]
Epoch 30 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 25.98it/s, loss=0.304]
Epoch 30 [Train]: 87%|████████▋ | 112/129 [00:04<00:00, 25.98it/s, loss=0.302]
Epoch 30 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 25.74it/s, loss=0.302]
Epoch 30 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 25.74it/s, loss=0.303]
Epoch 30 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 25.74it/s, loss=0.303]
Epoch 30 [Train]: 89%|████████▉ | 115/129 [00:04<00:00, 25.74it/s, loss=0.304]
Epoch 30 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.36it/s, loss=0.304]
Epoch 30 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.36it/s, loss=0.304]
Epoch 30 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.36it/s, loss=0.304]
Epoch 30 [Train]: 91%|█████████▏| 118/129 [00:04<00:00, 26.36it/s, loss=0.303]
Epoch 30 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.83it/s, loss=0.303]
Epoch 30 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.83it/s, loss=0.304]
Epoch 30 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.83it/s, loss=0.305]
Epoch 30 [Train]: 94%|█████████▍| 121/129 [00:04<00:00, 26.83it/s, loss=0.306]
Epoch 30 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.89it/s, loss=0.306]
Epoch 30 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.89it/s, loss=0.31]
Epoch 30 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.89it/s, loss=0.31]
Epoch 30 [Train]: 96%|█████████▌| 124/129 [00:04<00:00, 26.89it/s, loss=0.31]
Epoch 30 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.14it/s, loss=0.31]
Epoch 30 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.14it/s, loss=0.31]
Epoch 30 [Train]: 98%|█████████▊| 127/129 [00:04<00:00, 27.14it/s, loss=0.31]
2026-08-07 06:52:25.410 | INFO  | __main__:pretrain:180 - Epoch 30/50 | Train Loss: 0.3101 | Val Loss: 0.6749
Epoch 31 [Train]: 0%| | 0/129 [00:00<?, ?it/s]
Epoch 31 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.195]
Epoch 31 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.182]
Epoch 31 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.19]
Epoch 31 [Train]: 0%| | 0/129 [00:00<?, ?it/s, loss=0.278]
Epoch 31 [Train]: 3%|▎ | 4/129 [00:00<00:03, 32.58it/s, loss=0.278]
Epoch 31 [Train]: 3%|▎ | 4/129 [00:00<00:03, 32.58it/s, loss=0.276]
Epoch 31 [Train]: 3%|▎ | 4/129 [00:00<00:03, 32.58it/s, loss=0.273]
Epoch 31 [Train]: 3%|▎ | 4/129 [00:00<00:03, 32.58it/s, loss=0.277]
Epoch 31 [Train]: 3%|▎ | 4/129 [00:00<00:03, 32.58it/s, loss=0.277]
Epoch 31 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.00it/s, loss=0.277]
Epoch 31 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.00it/s, loss=0.271]
Epoch 31 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.00it/s, loss=0.295]
Epoch 31 [Train]: 6%|▌ | 8/129 [00:00<00:04, 29.00it/s, loss=0.307]
Epoch 31 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.52it/s, loss=0.307]
Epoch 31 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.52it/s, loss=0.306]
Epoch 31 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.52it/s, loss=0.299]
Epoch 31 [Train]: 9%|▊ | 11/129 [00:00<00:04, 27.52it/s, loss=0.292]
Epoch 31 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.26it/s, loss=0.292]
Epoch 31 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.26it/s, loss=0.287]
Epoch 31 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.26it/s, loss=0.285]
Epoch 31 [Train]: 11%|█ | 14/129 [00:00<00:04, 27.26it/s, loss=0.279]
Epoch 31 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.31it/s, loss=0.279]
Epoch 31 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.31it/s, loss=0.291]
Epoch 31 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.31it/s, loss=0.292]
Epoch 31 [Train]: 13%|█▎ | 17/129 [00:00<00:04, 27.31it/s, loss=0.287]
Epoch 31 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.95it/s, loss=0.287]
Epoch 31 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.95it/s, loss=0.295]
Epoch 31 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.95it/s, loss=0.306]
Epoch 31 [Train]: 16%|█▌ | 20/129 [00:00<00:04, 26.95it/s, loss=0.33]
Epoch 31 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.03it/s, loss=0.33]
Epoch 31 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.03it/s, loss=0.331]
Epoch 31 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.03it/s, loss=0.332]
Epoch 31 [Train]: 18%|█▊ | 23/129 [00:00<00:03, 27.03it/s, loss=0.332]
Epoch 31 [Train]: 20%|██ | 26/129 [00:00<00:03, 27.13it/s, loss=0.332]
Epoch 31 [Train]: 20%|██ | 26/129 [00:00<00:03, 27.13it/s, loss=0.329]
Epoch 31 [Train]: 20%|██ | 26/129 [00:01<00:03, 27.13it/s, loss=0.327]
Epoch 31 [Train]: 20%|██ | 26/129 [00:01<00:03, 27.13it/s, loss=0.326]
Epoch 31 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 27.11it/s, loss=0.326]
Epoch 31 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 27.11it/s, loss=0.327]
Epoch 31 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 27.11it/s, loss=0.326]
Epoch 31 [Train]: 22%|██▏ | 29/129 [00:01<00:03, 27.11it/s, loss=0.325]
Epoch 31 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.39it/s, loss=0.325]
Epoch 31 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.39it/s, loss=0.323]
Epoch 31 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.39it/s, loss=0.321]
Epoch 31 [Train]: 25%|██▍ | 32/129 [00:01<00:03, 26.39it/s, loss=0.323]
Epoch 31 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.69it/s, loss=0.323]
Epoch 31 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.69it/s, loss=0.32]
Epoch 31 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.69it/s, loss=0.318]
Epoch 31 [Train]: 27%|██▋ | 35/129 [00:01<00:03, 26.69it/s, loss=0.323]
Epoch 31 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.00it/s, loss=0.323]
Epoch 31 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.00it/s, loss=0.321]
Epoch 31 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.00it/s, loss=0.321]
Epoch 31 [Train]: 29%|██▉ | 38/129 [00:01<00:03, 26.00it/s, loss=0.321]
Epoch 31 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.22it/s, loss=0.321]
Epoch 31 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.22it/s, loss=0.322]
Epoch 31 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.22it/s, loss=0.323]
Epoch 31 [Train]: 32%|███▏ | 41/129 [00:01<00:03, 26.22it/s, loss=0.321]
Epoch 31 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.65it/s, loss=0.321]
Epoch 31 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.65it/s, loss=0.322]
Epoch 31 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.65it/s, loss=0.326]
Epoch 31 [Train]: 34%|███▍ | 44/129 [00:01<00:03, 26.65it/s, loss=0.325]
Epoch 31 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.11it/s, loss=0.325]
Epoch 31 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.11it/s, loss=0.325]
Epoch 31 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.11it/s, loss=0.325]
Epoch 31 [Train]: 36%|███▋ | 47/129 [00:01<00:03, 26.11it/s, loss=0.325]
Epoch 31 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 25.85it/s, loss=0.325]
Epoch 31 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 25.85it/s, loss=0.324]
Epoch 31 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 25.85it/s, loss=0.323]
Epoch 31 [Train]: 39%|███▉ | 50/129 [00:01<00:03, 25.85it/s, loss=0.323]
Epoch 31 [Train]: 41%|████ | 53/129 [00:01<00:02, 26.31it/s, loss=0.323]
Epoch 31 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.31it/s, loss=0.32]
Epoch 31 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.31it/s, loss=0.32]
Epoch 31 [Train]: 41%|████ | 53/129 [00:02<00:02, 26.31it/s, loss=0.318]
Epoch 31 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.83it/s, loss=0.318]
Epoch 31 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.83it/s, loss=0.316]
Epoch 31 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.83it/s, loss=0.317]
Epoch 31 [Train]: 43%|████▎ | 56/129 [00:02<00:02, 26.83it/s, loss=0.318]
Epoch 31 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.37it/s, loss=0.318]
Epoch 31 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.37it/s, loss=0.316]
Epoch 31 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.37it/s, loss=0.315]
Epoch 31 [Train]: 46%|████▌ | 59/129 [00:02<00:02, 26.37it/s, loss=0.314]
Epoch 31 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.34it/s, loss=0.314]
Epoch 31 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.34it/s, loss=0.313]
Epoch 31 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.34it/s, loss=0.313]
Epoch 31 [Train]: 48%|████▊ | 62/129 [00:02<00:02, 26.34it/s, loss=0.312]
Epoch 31 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.03it/s, loss=0.312]
Epoch 31 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.03it/s, loss=0.314]
Epoch 31 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.03it/s, loss=0.315]
Epoch 31 [Train]: 50%|█████ | 65/129 [00:02<00:02, 26.03it/s, loss=0.314]
Epoch 31 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 25.79it/s, loss=0.314]
Epoch 31 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 25.79it/s, loss=0.315]
Epoch 31 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 25.79it/s, loss=0.314]
Epoch 31 [Train]: 53%|█████▎ | 68/129 [00:02<00:02, 25.79it/s, loss=0.314]
Epoch 31 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.57it/s, loss=0.314]
Epoch 31 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.57it/s, loss=0.312]
Epoch 31 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.57it/s, loss=0.313]
Epoch 31 [Train]: 55%|█████▌ | 71/129 [00:02<00:02, 26.57it/s, loss=0.313]
Epoch 31 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.26it/s, loss=0.313]
Epoch 31 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.26it/s, loss=0.312]
Epoch 31 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.26it/s, loss=0.312]
Epoch 31 [Train]: 57%|█████▋ | 74/129 [00:02<00:02, 26.26it/s, loss=0.315]
Epoch 31 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.54it/s, loss=0.315]
Epoch 31 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.54it/s, loss=0.316]
Epoch 31 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.54it/s, loss=0.315]
Epoch 31 [Train]: 60%|█████▉ | 77/129 [00:02<00:01, 26.54it/s, loss=0.315]
Epoch 31 [Train]: 62%|██████▏ | 80/129 [00:02<00:01, 26.69it/s, loss=0.315]
Epoch 31 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.69it/s, loss=0.316]
Epoch 31 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.69it/s, loss=0.316]
Epoch 31 [Train]: 62%|██████▏ | 80/129 [00:03<00:01, 26.69it/s, loss=0.314]
Epoch 31 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.42it/s, loss=0.314]
Epoch 31 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.42it/s, loss=0.315]
Epoch 31 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.42it/s, loss=0.316]
Epoch 31 [Train]: 64%|██████▍ | 83/129 [00:03<00:01, 27.42it/s, loss=0.314]
Epoch 31 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 28.05it/s, loss=0.314]
Epoch 31 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 28.05it/s, loss=0.316]
Epoch 31 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 28.05it/s, loss=0.318]
Epoch 31 [Train]: 67%|██████▋ | 86/129 [00:03<00:01, 28.05it/s, loss=0.317]
Epoch 31 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.90it/s, loss=0.317]
Epoch 31 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.90it/s, loss=0.316]
Epoch 31 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.90it/s, loss=0.317]
Epoch 31 [Train]: 69%|██████▉ | 89/129 [00:03<00:01, 27.90it/s, loss=0.319]
Epoch 31 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.42it/s, loss=0.319]
Epoch 31 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.42it/s, loss=0.318]
Epoch 31 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.42it/s, loss=0.317]
Epoch 31 [Train]: 71%|███████▏ | 92/129 [00:03<00:01, 27.42it/s, loss=0.316]
Epoch 31 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.95it/s, loss=0.316]
Epoch 31 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.95it/s, loss=0.316]
Epoch 31 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.95it/s, loss=0.316]
Epoch 31 [Train]: 74%|███████▎ | 95/129 [00:03<00:01, 26.95it/s, loss=0.316]
Epoch 31 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.00it/s, loss=0.316]
Epoch 31 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.00it/s, loss=0.317]
Epoch 31 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.00it/s, loss=0.317]
Epoch 31 [Train]: 76%|███████▌ | 98/129 [00:03<00:01, 27.00it/s, loss=0.318]
Epoch 31 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.89it/s, loss=0.318]
Epoch 31 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.89it/s, loss=0.318]
Epoch 31 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.89it/s, loss=0.317]
Epoch 31 [Train]: 78%|███████▊ | 101/129 [00:03<00:01, 26.89it/s, loss=0.317]
Epoch 31 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.97it/s, loss=0.317]
Epoch 31 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.97it/s, loss=0.317]
Epoch 31 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.97it/s, loss=0.316]
Epoch 31 [Train]: 81%|████████ | 104/129 [00:03<00:00, 26.97it/s, loss=0.315]
Epoch 31 [Train]: 83%|████████▎ | 107/129 [00:03<00:00, 27.27it/s, loss=0.315]
Epoch 31 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.27it/s, loss=0.316]
Epoch 31 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.27it/s, loss=0.316]
Epoch 31 [Train]: 83%|████████▎ | 107/129 [00:04<00:00, 27.27it/s, loss=0.316]
Epoch 31 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 27.23it/s, loss=0.316]
Epoch 31 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 27.23it/s, loss=0.315]
Epoch 31 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 27.23it/s, loss=0.316]
Epoch 31 [Train]: 85%|████████▌ | 110/129 [00:04<00:00, 27.23it/s, loss=0.315]
Epoch 31 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.64it/s, loss=0.315]
Epoch 31 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.64it/s, loss=0.315]
Epoch 31 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.64it/s, loss=0.314]
Epoch 31 [Train]: 88%|████████▊ | 113/129 [00:04<00:00, 27.64it/s, loss=0.316]
Epoch 31 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.45it/s, loss=0.316]
Epoch 31 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.45it/s, loss=0.316]
Epoch 31 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.45it/s, loss=0.317]
Epoch 31 [Train]: 90%|████████▉ | 116/129 [00:04<00:00, 27.45it/s, loss=0.316]
Epoch 31 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.50it/s, loss=0.316]
Epoch 31 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.50it/s, loss=0.316]
Epoch 31 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.50it/s, loss=0.316]
Epoch 31 [Train]: 92%|█████████▏| 119/129 [00:04<00:00, 27.50it/s, loss=0.316]
Epoch 31 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.39it/s, loss=0.316]
Epoch 31 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.39it/s, loss=0.317]
Epoch 31 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.39it/s, loss=0.317]
Epoch 31 [Train]: 95%|█████████▍| 122/129 [00:04<00:00, 27.39it/s, loss=0.316]
Epoch 31 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 27.20it/s, loss=0.316]
Epoch 31 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 27.20it/s, loss=0.317]
Epoch 31 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 27.20it/s, loss=0.317]
Epoch 31 [Train]: 97%|█████████▋| 125/129 [00:04<00:00, 27.20it/s, loss=0.317]
Epoch 31 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 27.25it/s, loss=0.317]
Epoch 31 [Train]: 99%|█████████▉| 128/129 [00:04<00:00, 27.25it/s, loss=0.316]
2026-08-07 06:52:30.355 | INFO  | __main__:pretrain:180 - Epoch 31/50 | Train Loss: 0.3163 | Val Loss: 0.7611
2026-08-07 06:52:30.355 | INFO  | __main__:pretrain:200 - Early stopping at epoch 31
2026-08-07 06:52:30.406 | SUCCESS  | __main__:main:401 - Saved pretrain checkpoint to models/pretrain/mpnn/pretrain_delivery.pt
2026-08-07 06:52:30.407 | SUCCESS  | __main__:main:407 - Saved pretrain history to models/pretrain/mpnn/pretrain_history.json
2026-08-07 06:52:30.973 | SUCCESS  | __main__:main:416 - Saved loss curves plot to models/pretrain/mpnn/pretrain_loss_curves.png
2026-08-07 06:52:30.973 | SUCCESS  | __main__:main:418 - Pretraining complete! Best val_loss: 0.6451