financeLM_outputpath_Named_Entity_Recognition__25
This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4197
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4626 | 1.0 | 79 | 0.8903 |
| 0.5584 | 2.0 | 158 | 0.8643 |
| 0.475 | 3.0 | 237 | 0.8847 |
| 0.4189 | 4.0 | 316 | 0.9137 |
| 0.3638 | 5.0 | 395 | 0.9503 |
| 0.3165 | 6.0 | 474 | 1.0050 |
| 0.2808 | 7.0 | 553 | 1.0548 |
| 0.245 | 8.0 | 632 | 1.1044 |
| 0.2139 | 9.0 | 711 | 1.1267 |
| 0.1863 | 10.0 | 790 | 1.1825 |
| 0.163 | 11.0 | 869 | 1.2317 |
| 0.1444 | 12.0 | 948 | 1.2644 |
| 0.1285 | 13.0 | 1027 | 1.2872 |
| 0.1145 | 14.0 | 1106 | 1.3196 |
| 0.1047 | 15.0 | 1185 | 1.3310 |
| 0.0961 | 16.0 | 1264 | 1.3431 |
| 0.0888 | 17.0 | 1343 | 1.3495 |
| 0.0832 | 18.0 | 1422 | 1.3685 |
| 0.078 | 19.0 | 1501 | 1.3946 |
| 0.0747 | 20.0 | 1580 | 1.3961 |
| 0.0716 | 21.0 | 1659 | 1.3997 |
| 0.0691 | 22.0 | 1738 | 1.4063 |
| 0.0673 | 23.0 | 1817 | 1.4143 |
| 0.0653 | 24.0 | 1896 | 1.4201 |
| 0.0652 | 25.0 | 1975 | 1.4197 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1