<!-- 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-large_sst2_negation0.01_pretrainedFalse_epochs10
This model is a fine-tuned version of gpt2-large on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 4.0467
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 |
---|---|---|---|
1.9716 | 1.0 | 1323 | 3.0340 |
1.3263 | 2.0 | 2646 | 3.2788 |
1.075 | 3.0 | 3969 | 3.4934 |
0.9094 | 4.0 | 5292 | 3.6262 |
0.8177 | 5.0 | 6615 | 3.7459 |
0.7604 | 6.0 | 7938 | 3.8292 |
0.7198 | 7.0 | 9261 | 3.9058 |
0.6912 | 8.0 | 10584 | 3.9670 |
0.6662 | 9.0 | 11907 | 4.0187 |
0.6458 | 10.0 | 13230 | 4.0467 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.7.0
- Datasets 2.8.0
- Tokenizers 0.13.2