run2-babylm-shuffled-1234-gpt2-small
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0444
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: 1234
- 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 |
|---|---|---|---|
| 4.5012 | 0.5091 | 160 | 4.4572 |
| 4.1885 | 1.0159 | 320 | 4.1435 |
| 3.9136 | 1.5251 | 480 | 3.8584 |
| 3.7041 | 2.0318 | 640 | 3.6593 |
| 3.5891 | 2.5410 | 800 | 3.5359 |
| 3.4925 | 3.0477 | 960 | 3.4521 |
| 3.4323 | 3.5569 | 1120 | 3.3899 |
| 3.3703 | 4.0636 | 1280 | 3.3421 |
| 3.3361 | 4.5728 | 1440 | 3.3027 |
| 3.2942 | 5.0796 | 1600 | 3.2701 |
| 3.2769 | 5.5887 | 1760 | 3.2431 |
| 3.2298 | 6.0955 | 1920 | 3.2188 |
| 3.2202 | 6.6046 | 2080 | 3.1988 |
| 3.1894 | 7.1114 | 2240 | 3.1818 |
| 3.1819 | 7.6205 | 2400 | 3.1665 |
| 3.1501 | 8.1273 | 2560 | 3.1520 |
| 3.1475 | 8.6364 | 2720 | 3.1399 |
| 3.1245 | 9.1432 | 2880 | 3.1301 |
| 3.1225 | 9.6523 | 3040 | 3.1191 |
| 3.1036 | 10.1591 | 3200 | 3.1115 |
| 3.0988 | 10.6683 | 3360 | 3.1032 |
| 3.0867 | 11.1750 | 3520 | 3.0970 |
| 3.0810 | 11.6842 | 3680 | 3.0899 |
| 3.0676 | 12.1909 | 3840 | 3.0838 |
| 3.0685 | 12.7001 | 4000 | 3.0792 |
| 3.0493 | 13.2068 | 4160 | 3.0751 |
| 3.0476 | 13.7160 | 4320 | 3.0703 |
| 3.0426 | 14.2228 | 4480 | 3.0667 |
| 3.0387 | 14.7319 | 4640 | 3.0632 |
| 3.0279 | 15.2387 | 4800 | 3.0607 |
| 3.0290 | 15.7478 | 4960 | 3.0576 |
| 3.0271 | 16.2546 | 5120 | 3.0551 |
| 3.0236 | 16.7637 | 5280 | 3.0530 |
| 3.0178 | 17.2705 | 5440 | 3.0513 |
| 3.0215 | 17.7796 | 5600 | 3.0499 |
| 3.0103 | 18.2864 | 5760 | 3.0487 |
| 3.0118 | 18.7955 | 5920 | 3.0471 |
| 3.0093 | 19.3023 | 6080 | 3.0459 |
| 3.0078 | 19.8115 | 6240 | 3.0450 |
| 3.0101 | 20.0 | 6300 | 3.0444 |
Framework versions
- Transformers 5.13.0
- Pytorch 2.11.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2