|
--- |
|
license: apache-2.0 |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: Summary4500_M2_1000steps_1e6rate_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_1000steps_1e6rate_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: 0.0522 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.0157 | 0.0112 | 50 | 0.0527 | |
|
| 0.0045 | 0.0224 | 100 | 0.0527 | |
|
| 0.0005 | 0.0336 | 150 | 0.0500 | |
|
| 0.0001 | 0.0448 | 200 | 0.0503 | |
|
| 0.0 | 0.0559 | 250 | 0.0509 | |
|
| 0.0 | 0.0671 | 300 | 0.0515 | |
|
| 0.0 | 0.0783 | 350 | 0.0514 | |
|
| 0.0 | 0.0895 | 400 | 0.0519 | |
|
| 0.0 | 0.1007 | 450 | 0.0518 | |
|
| 0.0 | 0.1119 | 500 | 0.0521 | |
|
| 0.0 | 0.1231 | 550 | 0.0522 | |
|
| 0.0 | 0.1343 | 600 | 0.0519 | |
|
| 0.0 | 0.1454 | 650 | 0.0524 | |
|
| 0.0 | 0.1566 | 700 | 0.0522 | |
|
| 0.0 | 0.1678 | 750 | 0.0523 | |
|
| 0.0 | 0.1790 | 800 | 0.0520 | |
|
| 0.0 | 0.1902 | 850 | 0.0523 | |
|
| 0.0 | 0.2014 | 900 | 0.0522 | |
|
| 0.0 | 0.2126 | 950 | 0.0522 | |
|
| 0.0 | 0.2238 | 1000 | 0.0522 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.0.0+cu117 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
