|
--- |
|
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: 4.6855 |
|
- Accuracy: 0.7828 |
|
|
|
## 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 | 14.3260 | 0.3333 | |
|
| No log | 0.13 | 200 | 12.1073 | 0.4899 | |
|
| No log | 0.19 | 300 | 11.0435 | 0.5101 | |
|
| No log | 0.26 | 400 | 9.6543 | 0.5808 | |
|
| 3.466 | 0.32 | 500 | 9.4758 | 0.5960 | |
|
| 3.466 | 0.38 | 600 | 8.5372 | 0.6263 | |
|
| 3.466 | 0.45 | 700 | 8.3611 | 0.6566 | |
|
| 3.466 | 0.51 | 800 | 7.3273 | 0.6919 | |
|
| 3.466 | 0.58 | 900 | 8.0522 | 0.6414 | |
|
| 1.1408 | 0.64 | 1000 | 7.5545 | 0.6515 | |
|
| 1.1408 | 0.7 | 1100 | 6.9424 | 0.7020 | |
|
| 1.1408 | 0.77 | 1200 | 6.5618 | 0.6869 | |
|
| 1.1408 | 0.83 | 1300 | 6.1301 | 0.7121 | |
|
| 1.1408 | 0.9 | 1400 | 7.3708 | 0.7121 | |
|
| 0.7156 | 0.96 | 1500 | 5.9791 | 0.7172 | |
|
| 0.7156 | 1.02 | 1600 | 6.0925 | 0.7172 | |
|
| 0.7156 | 1.09 | 1700 | 6.1228 | 0.7121 | |
|
| 0.7156 | 1.15 | 1800 | 6.2473 | 0.7222 | |
|
| 0.7156 | 1.22 | 1900 | 6.3483 | 0.7172 | |
|
| 0.4805 | 1.28 | 2000 | 5.6959 | 0.7071 | |
|
| 0.4805 | 1.34 | 2100 | 5.5578 | 0.7424 | |
|
| 0.4805 | 1.41 | 2200 | 5.2385 | 0.7626 | |
|
| 0.4805 | 1.47 | 2300 | 5.6583 | 0.7374 | |
|
| 0.4805 | 1.54 | 2400 | 5.1442 | 0.7475 | |
|
| 0.3914 | 1.6 | 2500 | 5.0866 | 0.7677 | |
|
| 0.3914 | 1.66 | 2600 | 5.0077 | 0.7626 | |
|
| 0.3914 | 1.73 | 2700 | 4.6813 | 0.7778 | |
|
| 0.3914 | 1.79 | 2800 | 4.8810 | 0.7677 | |
|
| 0.3914 | 1.86 | 2900 | 4.6941 | 0.7626 | |
|
| 0.3368 | 1.92 | 3000 | 4.8332 | 0.7727 | |
|
| 0.3368 | 1.98 | 3100 | 4.6855 | 0.7828 | |
|
| 0.3368 | 2.05 | 3200 | 4.7359 | 0.7778 | |
|
| 0.3368 | 2.11 | 3300 | 4.5992 | 0.7778 | |
|
| 0.3368 | 2.18 | 3400 | 4.5406 | 0.7677 | |
|
| 0.2459 | 2.24 | 3500 | 4.8480 | 0.7828 | |
|
| 0.2459 | 2.3 | 3600 | 4.6215 | 0.7677 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.0 |
|
|