|
--- |
|
license: other |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: opt-model |
|
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. --> |
|
|
|
# opt-model |
|
|
|
This model is a fine-tuned version of [facebook/opt-13b](https://huggingface.co/facebook/opt-13b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.3965 |
|
- Accuracy: 0.5020 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 24 |
|
- eval_batch_size: 24 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 3 |
|
- total_train_batch_size: 72 |
|
- total_eval_batch_size: 72 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 3.6363 | 1.0 | 3 | 3.2090 | 0.4082 | |
|
| 2.8168 | 2.0 | 6 | 2.4805 | 0.4874 | |
|
| 2.3529 | 3.0 | 9 | 2.4219 | 0.4915 | |
|
| 2.1842 | 4.0 | 12 | 2.4023 | 0.4991 | |
|
| 2.0765 | 5.0 | 15 | 2.3965 | 0.5020 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.12.0+cu102 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
