<!-- 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_negation0.1_pretrainedFalse_epochs10
This model is a fine-tuned version of distilgpt2 on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 3.5480
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 |
---|---|---|---|
2.6705 | 1.0 | 1329 | 3.2639 |
2.4693 | 2.0 | 2658 | 3.2593 |
2.3592 | 3.0 | 3987 | 3.2837 |
2.2476 | 4.0 | 5316 | 3.3442 |
2.1698 | 5.0 | 6645 | 3.3836 |
2.1115 | 6.0 | 7974 | 3.4261 |
2.06 | 7.0 | 9303 | 3.4804 |
2.012 | 8.0 | 10632 | 3.5077 |
1.9914 | 9.0 | 11961 | 3.5341 |
1.9781 | 10.0 | 13290 | 3.5480 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.7.0
- Datasets 2.8.0
- Tokenizers 0.13.2