|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: cot_method2test-mistral-7B_v1 |
|
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. --> |
|
|
|
# cot_method2test-mistral-7B_v1 |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7463 |
|
|
|
## 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: 2.5e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 5 |
|
- training_steps: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.0057 | 0.48 | 5 | 1.2410 | |
|
| 0.9781 | 0.95 | 10 | 1.1410 | |
|
| 0.8181 | 1.43 | 15 | 1.0440 | |
|
| 0.7273 | 1.9 | 20 | 0.9502 | |
|
| 0.6721 | 2.38 | 25 | 0.8735 | |
|
| 0.5397 | 2.86 | 30 | 0.8148 | |
|
| 0.4642 | 3.33 | 35 | 0.7771 | |
|
| 0.4328 | 3.81 | 40 | 0.7565 | |
|
| 0.3788 | 4.29 | 45 | 0.7490 | |
|
| 0.4171 | 4.76 | 50 | 0.7463 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.2.dev0 |
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
