|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- sst2 |
|
model-index: |
|
- name: finetuned_gpt2-medium_sst2_negation0.0_pretrainedFalse_epochs30 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# finetuned_gpt2-medium_sst2_negation0.0_pretrainedFalse_epochs30 |
|
|
|
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the sst2 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 5.8610 |
|
|
|
## 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: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 2.7927 | 1.0 | 1059 | 3.3242 | |
|
| 2.4065 | 2.0 | 2118 | 3.5353 | |
|
| 2.0753 | 3.0 | 3177 | 3.8060 | |
|
| 1.8186 | 4.0 | 4236 | 4.0682 | |
|
| 1.6246 | 5.0 | 5295 | 4.3559 | |
|
| 1.4789 | 6.0 | 6354 | 4.5638 | |
|
| 1.367 | 7.0 | 7413 | 4.6723 | |
|
| 1.2762 | 8.0 | 8472 | 4.8568 | |
|
| 1.2058 | 9.0 | 9531 | 4.9660 | |
|
| 1.1499 | 10.0 | 10590 | 5.0804 | |
|
| 1.1047 | 11.0 | 11649 | 5.1751 | |
|
| 1.0641 | 12.0 | 12708 | 5.2775 | |
|
| 1.0287 | 13.0 | 13767 | 5.3404 | |
|
| 1.0026 | 14.0 | 14826 | 5.4163 | |
|
| 0.9781 | 15.0 | 15885 | 5.4508 | |
|
| 0.9559 | 16.0 | 16944 | 5.4982 | |
|
| 0.945 | 17.0 | 18003 | 5.5577 | |
|
| 0.9267 | 18.0 | 19062 | 5.5923 | |
|
| 0.9153 | 19.0 | 20121 | 5.6331 | |
|
| 0.8998 | 20.0 | 21180 | 5.6636 | |
|
| 0.8864 | 21.0 | 22239 | 5.7158 | |
|
| 0.8802 | 22.0 | 23298 | 5.7324 | |
|
| 0.8727 | 23.0 | 24357 | 5.7652 | |
|
| 0.8586 | 24.0 | 25416 | 5.7807 | |
|
| 0.8565 | 25.0 | 26475 | 5.7954 | |
|
| 0.851 | 26.0 | 27534 | 5.8253 | |
|
| 0.8457 | 27.0 | 28593 | 5.8330 | |
|
| 0.8432 | 28.0 | 29652 | 5.8485 | |
|
| 0.8405 | 29.0 | 30711 | 5.8505 | |
|
| 0.8354 | 30.0 | 31770 | 5.8610 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.7.0 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.13.2 |
|
|
