results
This model is a fine-tuned version of EleutherAI/pythia-70m-deduped on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2691
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: 5e-05
- train_batch_size: 100
- eval_batch_size: 100
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.852 | 0.1 | 1 | 3.1074 |
| 3.0923 | 0.2 | 2 | 2.3879 |
| 2.3371 | 0.3 | 3 | 2.1025 |
| 2.1166 | 0.4 | 4 | 1.9761 |
| 2.0538 | 0.5 | 5 | 1.8446 |
| 1.8972 | 0.6 | 6 | 1.7470 |
| 1.8356 | 0.7 | 7 | 1.6615 |
| 1.702 | 0.8 | 8 | 1.6187 |
| 1.6907 | 0.9 | 9 | 1.6626 |
| 1.5877 | 1.0 | 10 | 1.6192 |
| 1.6332 | 1.1 | 11 | 1.5464 |
| 1.4906 | 1.2 | 12 | 1.5091 |
| 1.5267 | 1.3 | 13 | 1.4850 |
| 1.4857 | 1.4 | 14 | 1.4572 |
| 1.4247 | 1.5 | 15 | 1.4319 |
| 1.4815 | 1.6 | 16 | 1.4207 |
| 1.3584 | 1.7 | 17 | 1.4092 |
| 1.4812 | 1.8 | 18 | 1.4196 |
| 1.4381 | 1.9 | 19 | 1.4021 |
| 1.453 | 2.0 | 20 | 1.4013 |
| 1.3468 | 2.1 | 21 | 1.3781 |
| 1.3327 | 2.2 | 22 | 1.3598 |
| 1.3623 | 2.3 | 23 | 1.3516 |
| 1.2876 | 2.4 | 24 | 1.3384 |
| 1.374 | 2.5 | 25 | 1.3366 |
| 1.3863 | 2.6 | 26 | 1.3265 |
| 1.3327 | 2.7 | 27 | 1.3186 |
| 1.2886 | 2.8 | 28 | 1.3130 |
| 1.3842 | 2.9 | 29 | 1.3024 |
| 1.3105 | 3.0 | 30 | 1.2986 |
| 1.2331 | 3.1 | 31 | 1.2966 |
| 1.3227 | 3.2 | 32 | 1.2954 |
| 1.2923 | 3.3 | 33 | 1.2928 |
| 1.2976 | 3.4 | 34 | 1.2901 |
| 1.3207 | 3.5 | 35 | 1.2879 |
| 1.2455 | 3.6 | 36 | 1.2834 |
| 1.2546 | 3.7 | 37 | 1.2779 |
| 1.2999 | 3.8 | 38 | 1.2744 |
| 1.2484 | 3.9 | 39 | 1.2723 |
| 1.281 | 4.0 | 40 | 1.2720 |
| 1.2134 | 4.1 | 41 | 1.2722 |
| 1.214 | 4.2 | 42 | 1.2721 |
| 1.3031 | 4.3 | 43 | 1.2715 |
| 1.2174 | 4.4 | 44 | 1.2708 |
| 1.2359 | 4.5 | 45 | 1.2703 |
| 1.2578 | 4.6 | 46 | 1.2699 |
| 1.2815 | 4.7 | 47 | 1.2695 |
| 1.2866 | 4.8 | 48 | 1.2693 |
| 1.2878 | 4.9 | 49 | 1.2691 |
| 1.2214 | 5.0 | 50 | 1.2691 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0