<!-- 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. -->
gpt2-Mariia
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.3410
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
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 29 | 4.0311 |
| No log | 2.0 | 58 | 3.9367 |
| No log | 3.0 | 87 | 3.9125 |
| No log | 4.0 | 116 | 3.9026 |
| No log | 5.0 | 145 | 3.9160 |
| No log | 6.0 | 174 | 3.9224 |
| No log | 7.0 | 203 | 3.9454 |
| No log | 8.0 | 232 | 3.9610 |
| No log | 9.0 | 261 | 3.9786 |
| No log | 10.0 | 290 | 4.0058 |
| No log | 11.0 | 319 | 4.0150 |
| No log | 12.0 | 348 | 4.0421 |
| No log | 13.0 | 377 | 4.0640 |
| No log | 14.0 | 406 | 4.0809 |
| No log | 15.0 | 435 | 4.1040 |
| No log | 16.0 | 464 | 4.1216 |
| No log | 17.0 | 493 | 4.1395 |
| 2.7939 | 18.0 | 522 | 4.1626 |
| 2.7939 | 19.0 | 551 | 4.1772 |
| 2.7939 | 20.0 | 580 | 4.1991 |
| 2.7939 | 21.0 | 609 | 4.2156 |
| 2.7939 | 22.0 | 638 | 4.2221 |
| 2.7939 | 23.0 | 667 | 4.2483 |
| 2.7939 | 24.0 | 696 | 4.2537 |
| 2.7939 | 25.0 | 725 | 4.2675 |
| 2.7939 | 26.0 | 754 | 4.2860 |
| 2.7939 | 27.0 | 783 | 4.2955 |
| 2.7939 | 28.0 | 812 | 4.3114 |
| 2.7939 | 29.0 | 841 | 4.3186 |
| 2.7939 | 30.0 | 870 | 4.3206 |
| 2.7939 | 31.0 | 899 | 4.3260 |
| 2.7939 | 32.0 | 928 | 4.3331 |
| 2.7939 | 33.0 | 957 | 4.3404 |
| 2.7939 | 34.0 | 986 | 4.3408 |
| 2.1316 | 34.48 | 1000 | 4.3410 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
