metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: gmra_model_gpt2_14082023T103028
results: []
gmra_model_gpt2_14082023T103028
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2685
- Accuracy: 0.9192
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: 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 71 | 0.6906 | 0.7742 |
| No log | 1.99 | 142 | 0.4773 | 0.8286 |
| No log | 2.99 | 213 | 0.3916 | 0.8708 |
| No log | 4.0 | 285 | 0.3393 | 0.8849 |
| No log | 5.0 | 356 | 0.3144 | 0.9007 |
| No log | 5.99 | 427 | 0.2959 | 0.9112 |
| No log | 6.99 | 498 | 0.2825 | 0.9165 |
| 0.538 | 8.0 | 570 | 0.2803 | 0.9069 |
| 0.538 | 9.0 | 641 | 0.2612 | 0.9192 |
| 0.538 | 9.96 | 710 | 0.2685 | 0.9192 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3