metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fresh-4-layer-swag-distill-of-fresh-4-layer-gpqa
results: []
fresh-4-layer-swag-distill-of-fresh-4-layer-gpqa
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 13.7243
- Accuracy: 0.4141
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 321
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 63 | 12.7754 | 0.2879 |
| No log | 2.0 | 126 | 15.8531 | 0.3333 |
| No log | 3.0 | 189 | 14.6240 | 0.3636 |
| No log | 4.0 | 252 | 14.4419 | 0.3737 |
| No log | 5.0 | 315 | 14.0280 | 0.4091 |
| No log | 6.0 | 378 | 13.7243 | 0.4141 |
| No log | 7.0 | 441 | 13.9530 | 0.3838 |
| 1.7783 | 8.0 | 504 | 12.1750 | 0.3737 |
| 1.7783 | 9.0 | 567 | 13.5994 | 0.3889 |
| 1.7783 | 10.0 | 630 | 12.8507 | 0.3586 |
| 1.7783 | 11.0 | 693 | 13.4322 | 0.3838 |
| 1.7783 | 12.0 | 756 | 11.9978 | 0.3990 |
| 1.7783 | 13.0 | 819 | 13.3436 | 0.3939 |
| 1.7783 | 14.0 | 882 | 12.3388 | 0.4040 |
| 1.7783 | 15.0 | 945 | 12.5646 | 0.4141 |
| 0.2705 | 16.0 | 1008 | 13.2618 | 0.3838 |
| 0.2705 | 17.0 | 1071 | 12.4800 | 0.3990 |
| 0.2705 | 18.0 | 1134 | 12.5251 | 0.3838 |
| 0.2705 | 19.0 | 1197 | 12.8962 | 0.3990 |
| 0.2705 | 20.0 | 1260 | 12.5932 | 0.3990 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0