metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fresh-2-layer-medmcqa5000-distill-of-fresh-2-layer-gpqa_EVAL_gpqa
results: []
fresh-2-layer-medmcqa5000-distill-of-fresh-2-layer-gpqa_EVAL_gpqa
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 8.7386
- Accuracy: 0.6465
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: 32
- eval_batch_size: 32
- seed: 321
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.64 | 100 | 13.7722 | 0.3384 |
| No log | 1.27 | 200 | 11.9604 | 0.4293 |
| No log | 1.91 | 300 | 10.3469 | 0.5253 |
| No log | 2.55 | 400 | 10.4306 | 0.5657 |
| 3.3633 | 3.18 | 500 | 9.3915 | 0.6414 |
| 3.3633 | 3.82 | 600 | 8.7386 | 0.6465 |
| 3.3633 | 4.46 | 700 | 8.8047 | 0.6212 |
| 3.3633 | 5.1 | 800 | 9.3199 | 0.5960 |
| 3.3633 | 5.73 | 900 | 8.1435 | 0.6364 |
| 0.7294 | 6.37 | 1000 | 8.3517 | 0.6313 |
| 0.7294 | 7.01 | 1100 | 8.8800 | 0.6111 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0