<!-- 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-material-synthesis
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9500
- Precision: 0.5526
- Recall: 0.6798
- F1: 0.6096
- Accuracy: 0.7418
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: 40
- eval_batch_size: 40
- 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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 38 | 1.5404 | 0.3609 | 0.3896 | 0.3747 | 0.5695 |
No log | 2.0 | 76 | 1.2569 | 0.4426 | 0.5594 | 0.4942 | 0.6486 |
No log | 3.0 | 114 | 1.0935 | 0.4849 | 0.6015 | 0.5370 | 0.6872 |
No log | 4.0 | 152 | 1.0234 | 0.5060 | 0.6576 | 0.5719 | 0.7075 |
No log | 5.0 | 190 | 1.0119 | 0.5312 | 0.6473 | 0.5835 | 0.7202 |
No log | 6.0 | 228 | 0.9496 | 0.5376 | 0.6724 | 0.5975 | 0.7306 |
No log | 7.0 | 266 | 0.9676 | 0.5403 | 0.6829 | 0.6033 | 0.7311 |
No log | 8.0 | 304 | 0.9584 | 0.5501 | 0.6763 | 0.6067 | 0.7374 |
No log | 9.0 | 342 | 0.9456 | 0.5515 | 0.6821 | 0.6099 | 0.7419 |
No log | 10.0 | 380 | 0.9500 | 0.5526 | 0.6798 | 0.6096 | 0.7418 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2