gpt2_small_expandedbabyLM_10M_44
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1547
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: 44
- 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 |
|---|---|---|---|
| 6.5673 | 1.0 | 509 | 4.9693 |
| 4.8448 | 2.0 | 1018 | 4.1971 |
| 4.4997 | 3.0 | 1527 | 3.8602 |
| 4.163 | 4.0 | 2036 | 3.6572 |
| 4.0111 | 5.0 | 2545 | 3.5189 |
| 3.8361 | 6.0 | 3054 | 3.4181 |
| 3.743 | 7.0 | 3563 | 3.3460 |
| 3.6272 | 8.0 | 4072 | 3.2891 |
| 3.5362 | 9.0 | 4581 | 3.2386 |
| 3.4533 | 10.0 | 5090 | 3.2086 |
| 3.3777 | 11.0 | 5599 | 3.1844 |
| 3.3088 | 12.0 | 6108 | 3.1709 |
| 3.2436 | 13.0 | 6617 | 3.1626 |
| 3.1912 | 14.0 | 7126 | 3.1571 |
| 3.1343 | 15.0 | 7635 | 3.1547 |
| 3.0783 | 16.0 | 8144 | 3.1561 |
| 3.0323 | 17.0 | 8653 | 3.1599 |
| 2.9926 | 18.0 | 9162 | 3.1639 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.11.0+cu130
- Datasets 4.1.1
- Tokenizers 0.13.3
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support