gpt2_small_expandedbabyLM_5M_42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3198
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: 0.0001
- train_batch_size: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 4000
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.6343 | 1.0 | 255 | 6.3154 |
| 6.6105 | 2.0 | 510 | 4.9844 |
| 5.59 | 3.0 | 765 | 4.4641 |
| 4.8464 | 4.0 | 1020 | 4.2016 |
| 4.6402 | 5.0 | 1275 | 4.0094 |
| 4.4846 | 6.0 | 1530 | 3.8675 |
| 4.3564 | 7.0 | 1785 | 3.7591 |
| 4.1421 | 8.0 | 2040 | 3.6657 |
| 4.052 | 9.0 | 2295 | 3.5956 |
| 3.9752 | 10.0 | 2550 | 3.5333 |
| 3.8353 | 11.0 | 2805 | 3.4821 |
| 3.7627 | 12.0 | 3060 | 3.4423 |
| 3.7051 | 13.0 | 3315 | 3.4083 |
| 3.6518 | 14.0 | 3570 | 3.3836 |
| 3.5455 | 15.0 | 3825 | 3.3622 |
| 3.4851 | 16.0 | 4080 | 3.3433 |
| 3.4218 | 17.0 | 4335 | 3.3274 |
| 3.3583 | 18.0 | 4590 | 3.3229 |
| 3.2111 | 19.0 | 4845 | 3.3198 |
| 3.1609 | 20.0 | 5100 | 3.3266 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.11.0+cu130
- Datasets 4.1.1
- Tokenizers 0.13.3
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support