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: 3.0497
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: 32
- eval_batch_size: 32
- seed: 1234
- gradient_accumulation_steps: 16
- 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: 20
- num_epochs: 20.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.4359 | 0.5093 | 160 | 4.4026 |
| 4.1717 | 1.0159 | 320 | 4.1260 |
| 3.9105 | 1.5252 | 480 | 3.8558 |
| 3.7045 | 2.0318 | 640 | 3.6607 |
| 3.5932 | 2.5411 | 800 | 3.5438 |
| 3.4981 | 3.0477 | 960 | 3.4575 |
| 3.4385 | 3.5570 | 1120 | 3.3964 |
| 3.3762 | 4.0637 | 1280 | 3.3490 |
| 3.3421 | 4.5729 | 1440 | 3.3094 |
| 3.2997 | 5.0796 | 1600 | 3.2757 |
| 3.2825 | 5.5888 | 1760 | 3.2482 |
| 3.2358 | 6.0955 | 1920 | 3.2249 |
| 3.2258 | 6.6047 | 2080 | 3.2049 |
| 3.1956 | 7.1114 | 2240 | 3.1878 |
| 3.1880 | 7.6206 | 2400 | 3.1729 |
| 3.1567 | 8.1273 | 2560 | 3.1592 |
| 3.1528 | 8.6366 | 2720 | 3.1455 |
| 3.1307 | 9.1432 | 2880 | 3.1360 |
| 3.1283 | 9.6525 | 3040 | 3.1253 |
| 3.1094 | 10.1591 | 3200 | 3.1170 |
| 3.1045 | 10.6684 | 3360 | 3.1090 |
| 3.0929 | 11.1751 | 3520 | 3.1022 |
| 3.0869 | 11.6843 | 3680 | 3.0953 |
| 3.0737 | 12.1910 | 3840 | 3.0901 |
| 3.0747 | 12.7002 | 4000 | 3.0847 |
| 3.0552 | 13.2069 | 4160 | 3.0805 |
| 3.0534 | 13.7161 | 4320 | 3.0758 |
| 3.0487 | 14.2228 | 4480 | 3.0726 |
| 3.0451 | 14.7320 | 4640 | 3.0688 |
| 3.0341 | 15.2387 | 4800 | 3.0659 |
| 3.0351 | 15.7480 | 4960 | 3.0630 |
| 3.0336 | 16.2546 | 5120 | 3.0606 |
| 3.0295 | 16.7639 | 5280 | 3.0585 |
| 3.0240 | 17.2705 | 5440 | 3.0567 |
| 3.0272 | 17.7798 | 5600 | 3.0552 |
| 3.0164 | 18.2865 | 5760 | 3.0537 |
| 3.0176 | 18.7957 | 5920 | 3.0525 |
| 3.0153 | 19.3024 | 6080 | 3.0512 |
| 3.0139 | 19.8116 | 6240 | 3.0500 |
| 3.0160 | 20.0 | 6300 | 3.0497 |
Framework versions
- Transformers 5.13.0
- Pytorch 2.11.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2