<!-- 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. -->
gmra_model_gpt2-medium_14082023T183423
This model is a fine-tuned version of gpt2-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4556
- Accuracy: 0.8787
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: 0.002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 284 | 0.5844 | 0.7838 |
0.9589 | 2.0 | 568 | 0.4399 | 0.8480 |
0.9589 | 3.0 | 852 | 0.4556 | 0.8787 |
0.2653 | 4.0 | 1137 | 0.4556 | 0.8787 |
0.2653 | 5.0 | 1421 | 0.4556 | 0.8787 |
0.2143 | 6.0 | 1705 | 0.4556 | 0.8787 |
0.2143 | 7.0 | 1989 | 0.4556 | 0.8787 |
0.2216 | 8.0 | 2274 | 0.4556 | 0.8787 |
0.2179 | 9.0 | 2558 | 0.4556 | 0.8787 |
0.2179 | 9.99 | 2840 | 0.4556 | 0.8787 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.2