<!-- 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. -->
gpt2-finetuned-comp2
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7788
- Precision: 0.3801
- Recall: 0.6854
- F1: 0.4800
- Accuracy: 0.4800
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.0962 | 1.0 | 1012 | 0.7528 | 0.3793 | 0.6109 | 0.4411 | 0.4411 |
| 0.7022 | 2.0 | 2024 | 0.6763 | 0.3992 | 0.6557 | 0.4799 | 0.4799 |
| 0.6136 | 3.0 | 3036 | 0.6751 | 0.3995 | 0.6597 | 0.4824 | 0.4824 |
| 0.5444 | 4.0 | 4048 | 0.6799 | 0.3891 | 0.6817 | 0.4854 | 0.4854 |
| 0.4846 | 5.0 | 5060 | 0.7371 | 0.4030 | 0.6701 | 0.4906 | 0.4906 |
| 0.4379 | 6.0 | 6072 | 0.7520 | 0.3956 | 0.6788 | 0.4887 | 0.4887 |
| 0.404 | 7.0 | 7084 | 0.7788 | 0.3801 | 0.6854 | 0.4800 | 0.4800 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
