run2-babylm-shuffled-2345-gpt2-small
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0468
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 64
- eval_batch_size: 64
- seed: 2345
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_min_lr
- lr_scheduler_warmup_steps: 100
- num_epochs: 20.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.4976 | 0.5091 | 160 | 4.4576 |
| 4.2039 | 1.0159 | 320 | 4.1465 |
| 3.9040 | 1.5251 | 480 | 3.8557 |
| 3.7082 | 2.0318 | 640 | 3.6582 |
| 3.5832 | 2.5410 | 800 | 3.5348 |
| 3.4903 | 3.0477 | 960 | 3.4549 |
| 3.4357 | 3.5569 | 1120 | 3.3917 |
| 3.3763 | 4.0636 | 1280 | 3.3426 |
| 3.3317 | 4.5728 | 1440 | 3.3039 |
| 3.2963 | 5.0796 | 1600 | 3.2712 |
| 3.2715 | 5.5887 | 1760 | 3.2432 |
| 3.2372 | 6.0955 | 1920 | 3.2204 |
| 3.2201 | 6.6046 | 2080 | 3.2002 |
| 3.1907 | 7.1114 | 2240 | 3.1825 |
| 3.1840 | 7.6205 | 2400 | 3.1673 |
| 3.1547 | 8.1273 | 2560 | 3.1543 |
| 3.1521 | 8.6364 | 2720 | 3.1420 |
| 3.1223 | 9.1432 | 2880 | 3.1312 |
| 3.1226 | 9.6523 | 3040 | 3.1216 |
| 3.1053 | 10.1591 | 3200 | 3.1136 |
| 3.1080 | 10.6683 | 3360 | 3.1049 |
| 3.0848 | 11.1750 | 3520 | 3.0983 |
| 3.0851 | 11.6842 | 3680 | 3.0920 |
| 3.0642 | 12.1909 | 3840 | 3.0867 |
| 3.0673 | 12.7001 | 4000 | 3.0805 |
| 3.0537 | 13.2068 | 4160 | 3.0765 |
| 3.0541 | 13.7160 | 4320 | 3.0719 |
| 3.0402 | 14.2228 | 4480 | 3.0688 |
| 3.0400 | 14.7319 | 4640 | 3.0648 |
| 3.0271 | 15.2387 | 4800 | 3.0624 |
| 3.0360 | 15.7478 | 4960 | 3.0595 |
| 3.0293 | 16.2546 | 5120 | 3.0574 |
| 3.0258 | 16.7637 | 5280 | 3.0551 |
| 3.0182 | 17.2705 | 5440 | 3.0536 |
| 3.0256 | 17.7796 | 5600 | 3.0516 |
| 3.0113 | 18.2864 | 5760 | 3.0502 |
| 3.0133 | 18.7955 | 5920 | 3.0490 |
| 3.0106 | 19.3023 | 6080 | 3.0481 |
| 3.0115 | 19.8115 | 6240 | 3.0470 |
| 3.0096 | 20.0 | 6300 | 3.0468 |
Framework versions
- Transformers 5.13.0
- Pytorch 2.11.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2