<!-- 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_negation0.1_pretrainedFalse_epochs10
This model is a fine-tuned version of gpt2-medium on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 4.0780
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2694 | 1.0 | 1329 | 2.9075 |
| 1.8892 | 2.0 | 2658 | 3.0947 |
| 1.6728 | 3.0 | 3987 | 3.3248 |
| 1.4683 | 4.0 | 5316 | 3.5732 |
| 1.3375 | 5.0 | 6645 | 3.7248 |
| 1.2545 | 6.0 | 7974 | 3.8060 |
| 1.1868 | 7.0 | 9303 | 3.9507 |
| 1.1398 | 8.0 | 10632 | 4.0056 |
| 1.1107 | 9.0 | 11961 | 4.0431 |
| 1.0932 | 10.0 | 13290 | 4.0780 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.7.0
- Datasets 2.8.0
- Tokenizers 0.13.2
