<!-- 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_distilgpt2_sst2_negation0.001_pretrainedTrue_epochs3
This model is a fine-tuned version of distilgpt2 on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 3.2638
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6836 | 1.0 | 1322 | 3.2638 |
| 2.5043 | 2.0 | 2644 | 3.2590 |
| 2.4514 | 3.0 | 3966 | 3.2638 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.7.0
- Datasets 2.8.0
- Tokenizers 0.13.2
