---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa_EVAL_gpqa
  results: []
---

<!-- 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. -->

# fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa_EVAL_gpqa

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 9.4859
- Accuracy: 0.6111

## 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
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 63   | 15.9159         | 0.2727   |
| No log        | 2.0   | 126  | 13.1758         | 0.3838   |
| No log        | 3.0   | 189  | 12.5917         | 0.4596   |
| No log        | 4.0   | 252  | 11.4595         | 0.4899   |
| No log        | 5.0   | 315  | 11.0792         | 0.5152   |
| No log        | 6.0   | 378  | 10.3175         | 0.5455   |
| No log        | 7.0   | 441  | 10.4051         | 0.5505   |
| 2.9311        | 8.0   | 504  | 10.6829         | 0.5556   |
| 2.9311        | 9.0   | 567  | 10.7602         | 0.5253   |
| 2.9311        | 10.0  | 630  | 10.2955         | 0.5707   |
| 2.9311        | 11.0  | 693  | 9.8900          | 0.5606   |
| 2.9311        | 12.0  | 756  | 9.5430          | 0.5960   |
| 2.9311        | 13.0  | 819  | 9.8694          | 0.5909   |
| 2.9311        | 14.0  | 882  | 9.6516          | 0.5758   |
| 2.9311        | 15.0  | 945  | 9.4962          | 0.6010   |
| 0.3764        | 16.0  | 1008 | 9.8449          | 0.5960   |
| 0.3764        | 17.0  | 1071 | 9.5987          | 0.6061   |
| 0.3764        | 18.0  | 1134 | 9.6737          | 0.6061   |
| 0.3764        | 19.0  | 1197 | 9.5190          | 0.6061   |
| 0.3764        | 20.0  | 1260 | 9.4859          | 0.6111   |


### Framework versions

- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0