|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: mistral-7b-autextification2024 |
|
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-autextification2024 |
|
|
|
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: 1.6422 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- training_steps: 500 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.4251 | 0.0 | 10 | 1.7924 | |
|
| 1.3175 | 0.01 | 20 | 1.7542 | |
|
| 1.7841 | 0.01 | 30 | 1.7322 | |
|
| 2.0421 | 0.01 | 40 | 1.7294 | |
|
| 2.669 | 0.02 | 50 | 1.7471 | |
|
| 1.314 | 0.02 | 60 | 1.7153 | |
|
| 1.4678 | 0.02 | 70 | 1.6989 | |
|
| 1.7679 | 0.03 | 80 | 1.6928 | |
|
| 2.0057 | 0.03 | 90 | 1.7002 | |
|
| 2.5086 | 0.03 | 100 | 1.7053 | |
|
| 1.3326 | 0.04 | 110 | 1.6931 | |
|
| 1.3984 | 0.04 | 120 | 1.6823 | |
|
| 1.8045 | 0.04 | 130 | 1.6807 | |
|
| 1.8764 | 0.05 | 140 | 1.6812 | |
|
| 2.5524 | 0.05 | 150 | 1.6825 | |
|
| 1.2854 | 0.05 | 160 | 1.6766 | |
|
| 1.3712 | 0.06 | 170 | 1.6709 | |
|
| 1.8211 | 0.06 | 180 | 1.6660 | |
|
| 2.0365 | 0.06 | 190 | 1.6778 | |
|
| 2.4664 | 0.07 | 200 | 1.6938 | |
|
| 1.3405 | 0.07 | 210 | 1.6712 | |
|
| 1.3856 | 0.07 | 220 | 1.6666 | |
|
| 1.5553 | 0.08 | 230 | 1.6586 | |
|
| 1.8616 | 0.08 | 240 | 1.6613 | |
|
| 2.4064 | 0.09 | 250 | 1.6666 | |
|
| 1.3446 | 0.09 | 260 | 1.6681 | |
|
| 1.386 | 0.09 | 270 | 1.6645 | |
|
| 1.6508 | 0.1 | 280 | 1.6582 | |
|
| 1.8588 | 0.1 | 290 | 1.6600 | |
|
| 2.3148 | 0.1 | 300 | 1.6524 | |
|
| 1.2785 | 0.11 | 310 | 1.6549 | |
|
| 1.2727 | 0.11 | 320 | 1.6517 | |
|
| 1.5971 | 0.11 | 330 | 1.6486 | |
|
| 1.7811 | 0.12 | 340 | 1.6540 | |
|
| 2.3368 | 0.12 | 350 | 1.6596 | |
|
| 1.2513 | 0.12 | 360 | 1.6578 | |
|
| 1.4403 | 0.13 | 370 | 1.6429 | |
|
| 1.8051 | 0.13 | 380 | 1.6462 | |
|
| 1.8214 | 0.13 | 390 | 1.6469 | |
|
| 2.4691 | 0.14 | 400 | 1.6654 | |
|
| 1.2895 | 0.14 | 410 | 1.6543 | |
|
| 1.3192 | 0.14 | 420 | 1.6435 | |
|
| 1.7031 | 0.15 | 430 | 1.6438 | |
|
| 1.8647 | 0.15 | 440 | 1.6402 | |
|
| 2.398 | 0.15 | 450 | 1.6444 | |
|
| 1.3195 | 0.16 | 460 | 1.6445 | |
|
| 1.4008 | 0.16 | 470 | 1.6407 | |
|
| 1.6925 | 0.16 | 480 | 1.6380 | |
|
| 1.8432 | 0.17 | 490 | 1.6396 | |
|
| 2.5103 | 0.17 | 500 | 1.6422 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
