<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
hebrew-holy-language-model
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3370
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7611 | 1.0 | 1086 | 1.6307 |
| 1.6165 | 2.0 | 2172 | 1.5228 |
| 1.5458 | 3.0 | 3258 | 1.4681 |
| 1.497 | 4.0 | 4344 | 1.4367 |
| 1.4525 | 5.0 | 5430 | 1.4102 |
| 1.4185 | 6.0 | 6516 | 1.3920 |
| 1.4036 | 7.0 | 7602 | 1.3786 |
| 1.3786 | 8.0 | 8688 | 1.3667 |
| 1.3658 | 9.0 | 9774 | 1.3603 |
| 1.356 | 10.0 | 10860 | 1.3513 |
| 1.3414 | 11.0 | 11946 | 1.3493 |
| 1.3359 | 12.0 | 13032 | 1.3427 |
| 1.3306 | 13.0 | 14118 | 1.3394 |
| 1.3238 | 14.0 | 15204 | 1.3378 |
| 1.3191 | 15.0 | 16290 | 1.3370 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
