|
--- |
|
license: apache-2.0 |
|
base_model: mistralai/Mistral-7B-Instruct-v0.1 |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: v1_1000_STEPS_1e6_SFT_SFT |
|
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. --> |
|
|
|
# v1_1000_STEPS_1e6_SFT_SFT |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2933 |
|
|
|
## 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-06 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 1000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.3991 | 0.05 | 50 | 0.3739 | |
|
| 0.3268 | 0.1 | 100 | 0.3451 | |
|
| 0.3446 | 0.15 | 150 | 0.3264 | |
|
| 0.3487 | 0.2 | 200 | 0.3183 | |
|
| 0.3122 | 0.24 | 250 | 0.3140 | |
|
| 0.3208 | 0.29 | 300 | 0.3103 | |
|
| 0.307 | 0.34 | 350 | 0.3073 | |
|
| 0.2965 | 0.39 | 400 | 0.3053 | |
|
| 0.3101 | 0.44 | 450 | 0.3030 | |
|
| 0.305 | 0.49 | 500 | 0.3001 | |
|
| 0.2937 | 0.54 | 550 | 0.2985 | |
|
| 0.3034 | 0.59 | 600 | 0.2967 | |
|
| 0.2898 | 0.64 | 650 | 0.2953 | |
|
| 0.282 | 0.68 | 700 | 0.2946 | |
|
| 0.2846 | 0.73 | 750 | 0.2938 | |
|
| 0.2969 | 0.78 | 800 | 0.2935 | |
|
| 0.3073 | 0.83 | 850 | 0.2933 | |
|
| 0.2792 | 0.88 | 900 | 0.2933 | |
|
| 0.2837 | 0.93 | 950 | 0.2933 | |
|
| 0.299 | 0.98 | 1000 | 0.2933 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.0.0+cu117 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|