|
--- |
|
base_model: unsloth/mistral-7b-v0.3-bnb-4bit |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral-7B-v0.3_pct_reverse |
|
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. --> |
|
|
|
# Mistral-7B-v0.3_pct_reverse |
|
|
|
This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 6.8605 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.1177 | 0.0206 | 8 | 2.6702 | |
|
| 8.9887 | 0.0413 | 16 | 9.0083 | |
|
| 7.777 | 0.0619 | 24 | 7.6913 | |
|
| 7.6327 | 0.0825 | 32 | 7.6181 | |
|
| 7.6585 | 0.1032 | 40 | 7.6409 | |
|
| 7.6813 | 0.1238 | 48 | 7.5593 | |
|
| 7.6016 | 0.1444 | 56 | 7.5868 | |
|
| 7.5595 | 0.1651 | 64 | 7.5960 | |
|
| 7.7069 | 0.1857 | 72 | 7.5984 | |
|
| 7.6285 | 0.2063 | 80 | 7.4589 | |
|
| 7.5374 | 0.2270 | 88 | 7.4251 | |
|
| 7.4161 | 0.2476 | 96 | 7.3111 | |
|
| 7.3713 | 0.2682 | 104 | 7.2864 | |
|
| 7.2921 | 0.2888 | 112 | 7.2224 | |
|
| 7.2529 | 0.3095 | 120 | 7.1938 | |
|
| 7.3559 | 0.3301 | 128 | 7.1139 | |
|
| 7.1657 | 0.3507 | 136 | 7.0930 | |
|
| 7.066 | 0.3714 | 144 | 7.0315 | |
|
| 7.1481 | 0.3920 | 152 | 7.0332 | |
|
| 7.0394 | 0.4126 | 160 | 7.0583 | |
|
| 7.0685 | 0.4333 | 168 | 7.0682 | |
|
| 6.9791 | 0.4539 | 176 | 6.9472 | |
|
| 7.1428 | 0.4745 | 184 | 7.0126 | |
|
| 7.1661 | 0.4952 | 192 | 6.9513 | |
|
| 6.9757 | 0.5158 | 200 | 7.0717 | |
|
| 6.9685 | 0.5364 | 208 | 6.9399 | |
|
| 7.0811 | 0.5571 | 216 | 6.8879 | |
|
| 7.0126 | 0.5777 | 224 | 6.9264 | |
|
| 6.9712 | 0.5983 | 232 | 6.8394 | |
|
| 6.9533 | 0.6190 | 240 | 6.9073 | |
|
| 6.9744 | 0.6396 | 248 | 6.9239 | |
|
| 7.1531 | 0.6602 | 256 | 6.9109 | |
|
| 6.9527 | 0.6809 | 264 | 6.8941 | |
|
| 7.1027 | 0.7015 | 272 | 6.9498 | |
|
| 7.1718 | 0.7221 | 280 | 6.9495 | |
|
| 7.0877 | 0.7427 | 288 | 6.9761 | |
|
| 6.9879 | 0.7634 | 296 | 6.9905 | |
|
| 6.9813 | 0.7840 | 304 | 6.9238 | |
|
| 7.0798 | 0.8046 | 312 | 6.8707 | |
|
| 7.0531 | 0.8253 | 320 | 6.8658 | |
|
| 7.0518 | 0.8459 | 328 | 6.8576 | |
|
| 7.127 | 0.8665 | 336 | 6.9017 | |
|
| 6.9259 | 0.8872 | 344 | 6.8581 | |
|
| 6.9477 | 0.9078 | 352 | 6.8727 | |
|
| 7.0367 | 0.9284 | 360 | 6.8629 | |
|
| 6.9114 | 0.9491 | 368 | 6.8469 | |
|
| 7.0537 | 0.9697 | 376 | 6.8627 | |
|
| 6.9656 | 0.9903 | 384 | 6.8605 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
