|
--- |
|
license: apache-2.0 |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: Summary4500_M2_750steps_1e5rate_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. --> |
|
|
|
# Summary4500_M2_750steps_1e5rate_SFT |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4197 |
|
|
|
## 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: 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: 750 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.4687 | 0.0447 | 50 | 0.5176 | |
|
| 0.5069 | 0.0895 | 100 | 0.5367 | |
|
| 0.5289 | 0.1342 | 150 | 0.5178 | |
|
| 0.4896 | 0.1790 | 200 | 0.5124 | |
|
| 0.4982 | 0.2237 | 250 | 0.5096 | |
|
| 0.4595 | 0.2685 | 300 | 0.5040 | |
|
| 0.4998 | 0.3132 | 350 | 0.4854 | |
|
| 0.4571 | 0.3579 | 400 | 0.4713 | |
|
| 0.4477 | 0.4027 | 450 | 0.4577 | |
|
| 0.4286 | 0.4474 | 500 | 0.4466 | |
|
| 0.4113 | 0.4922 | 550 | 0.4338 | |
|
| 0.4044 | 0.5369 | 600 | 0.4262 | |
|
| 0.3802 | 0.5817 | 650 | 0.4213 | |
|
| 0.4059 | 0.6264 | 700 | 0.4199 | |
|
| 0.4289 | 0.6711 | 750 | 0.4197 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.0.0+cu117 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
