fresh-8-layer-gpqa / README.md
afaji's picture
fresh-8-layer-gpqa
46a5104 verified
---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fresh-8-layer-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-8-layer-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: 0.2286
- Accuracy: 0.9141
## 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 | 13 | 1.3863 | 0.2374 |
| No log | 2.0 | 26 | 1.3859 | 0.2727 |
| No log | 3.0 | 39 | 1.3854 | 0.3131 |
| No log | 4.0 | 52 | 1.3852 | 0.3182 |
| No log | 5.0 | 65 | 1.3851 | 0.3081 |
| No log | 6.0 | 78 | 1.3843 | 0.2879 |
| No log | 7.0 | 91 | 1.3833 | 0.3232 |
| No log | 8.0 | 104 | 1.3796 | 0.3232 |
| No log | 9.0 | 117 | 1.3446 | 0.4091 |
| No log | 10.0 | 130 | 1.3817 | 0.6212 |
| No log | 11.0 | 143 | 1.3829 | 0.6616 |
| No log | 12.0 | 156 | 1.2989 | 0.6717 |
| No log | 13.0 | 169 | 1.0802 | 0.4848 |
| No log | 14.0 | 182 | 0.9971 | 0.6465 |
| No log | 15.0 | 195 | 0.8610 | 0.7020 |
| No log | 16.0 | 208 | 0.5707 | 0.7879 |
| No log | 17.0 | 221 | 0.4044 | 0.8333 |
| No log | 18.0 | 234 | 0.3185 | 0.8687 |
| No log | 19.0 | 247 | 0.2915 | 0.8788 |
| No log | 20.0 | 260 | 0.2286 | 0.9141 |
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0