|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: fresh-2-layer-medmcqa50000-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-medmcqa50000-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: 6.3481 |
|
- Accuracy: 0.7677 |
|
|
|
## 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 | 0.06 | 100 | 14.8949 | 0.4141 | |
|
| No log | 0.13 | 200 | 11.8675 | 0.4697 | |
|
| No log | 0.19 | 300 | 10.6894 | 0.5556 | |
|
| No log | 0.26 | 400 | 9.8194 | 0.5404 | |
|
| 3.5537 | 0.32 | 500 | 9.0542 | 0.5556 | |
|
| 3.5537 | 0.38 | 600 | 9.0155 | 0.6061 | |
|
| 3.5537 | 0.45 | 700 | 8.1758 | 0.6768 | |
|
| 3.5537 | 0.51 | 800 | 7.6983 | 0.6970 | |
|
| 3.5537 | 0.58 | 900 | 7.6211 | 0.6818 | |
|
| 1.0971 | 0.64 | 1000 | 7.1361 | 0.6919 | |
|
| 1.0971 | 0.7 | 1100 | 7.1059 | 0.6717 | |
|
| 1.0971 | 0.77 | 1200 | 6.9443 | 0.6919 | |
|
| 1.0971 | 0.83 | 1300 | 6.7089 | 0.7273 | |
|
| 1.0971 | 0.9 | 1400 | 6.5064 | 0.7172 | |
|
| 0.699 | 0.96 | 1500 | 5.9161 | 0.7273 | |
|
| 0.699 | 1.02 | 1600 | 6.6374 | 0.7525 | |
|
| 0.699 | 1.09 | 1700 | 6.3481 | 0.7677 | |
|
| 0.699 | 1.15 | 1800 | 5.9385 | 0.7323 | |
|
| 0.699 | 1.22 | 1900 | 6.2063 | 0.7374 | |
|
| 0.4733 | 1.28 | 2000 | 5.9173 | 0.7273 | |
|
| 0.4733 | 1.34 | 2100 | 5.8466 | 0.7626 | |
|
| 0.4733 | 1.41 | 2200 | 5.6702 | 0.7374 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.0 |
|
|
