metadata
license: mit
base_model: gpt2-medium
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: gmra_model_gpt2-medium_15082023T113143
results: []
gmra_model_gpt2-medium_15082023T113143
This model is a fine-tuned version of gpt2-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2694
- Accuracy: 0.9464
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 | 142 | 0.4750 | 0.8409 |
| No log | 2.0 | 284 | 0.2932 | 0.9033 |
| No log | 2.99 | 426 | 0.2850 | 0.9192 |
| 0.5761 | 4.0 | 569 | 0.2622 | 0.9279 |
| 0.5761 | 5.0 | 711 | 0.2580 | 0.9367 |
| 0.5761 | 6.0 | 853 | 0.2768 | 0.9394 |
| 0.5761 | 6.99 | 995 | 0.2640 | 0.9473 |
| 0.0682 | 8.0 | 1138 | 0.2493 | 0.9464 |
| 0.0682 | 9.0 | 1280 | 0.2739 | 0.9446 |
| 0.0682 | 9.98 | 1420 | 0.2694 | 0.9464 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3