|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: genProj_mistral-7B |
|
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. --> |
|
|
|
# genProj_mistral-7B |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6692 |
|
|
|
## 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: 0.00025 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.0215 | 0.0634 | 100 | 1.2005 | |
|
| 0.9657 | 0.1267 | 200 | 0.9706 | |
|
| 0.8585 | 0.1901 | 300 | 0.9458 | |
|
| 0.842 | 0.2535 | 400 | 0.8757 | |
|
| 0.8587 | 0.3169 | 500 | 0.8758 | |
|
| 0.8501 | 0.3802 | 600 | 0.7813 | |
|
| 0.8453 | 0.4436 | 700 | 0.9362 | |
|
| 0.789 | 0.5070 | 800 | 0.7702 | |
|
| 0.7213 | 0.5703 | 900 | 0.7641 | |
|
| 0.7335 | 0.6337 | 1000 | 0.7707 | |
|
| 0.6989 | 0.6971 | 1100 | 0.7480 | |
|
| 0.7739 | 0.7605 | 1200 | 0.7210 | |
|
| 0.6785 | 0.8238 | 1300 | 0.7150 | |
|
| 0.7198 | 0.8872 | 1400 | 0.7126 | |
|
| 0.7726 | 0.9506 | 1500 | 0.6919 | |
|
| 0.495 | 1.0139 | 1600 | 0.6501 | |
|
| 0.5318 | 1.0773 | 1700 | 0.6376 | |
|
| 0.5124 | 1.1407 | 1800 | 0.6373 | |
|
| 0.5404 | 1.2041 | 1900 | 0.6379 | |
|
| 0.5133 | 1.2674 | 2000 | 0.6633 | |
|
| 0.516 | 1.3308 | 2100 | 0.6579 | |
|
| 0.5092 | 1.3942 | 2200 | 0.6525 | |
|
| 0.6288 | 1.4575 | 2300 | 0.6438 | |
|
| 0.4935 | 1.5209 | 2400 | 0.6255 | |
|
| 0.5334 | 1.5843 | 2500 | 0.6246 | |
|
| 0.6021 | 1.6477 | 2600 | 0.6102 | |
|
| 0.5625 | 1.7110 | 2700 | 0.6191 | |
|
| 0.5425 | 1.7744 | 2800 | 0.6301 | |
|
| 0.5302 | 1.8378 | 2900 | 0.6058 | |
|
| 0.5443 | 1.9011 | 3000 | 0.6218 | |
|
| 0.5023 | 1.9645 | 3100 | 0.6129 | |
|
| 0.3902 | 2.0279 | 3200 | 0.6478 | |
|
| 0.4046 | 2.0913 | 3300 | 0.6345 | |
|
| 0.424 | 2.1546 | 3400 | 0.6489 | |
|
| 0.47 | 2.2180 | 3500 | 0.6729 | |
|
| 0.419 | 2.2814 | 3600 | 0.6524 | |
|
| 0.433 | 2.3447 | 3700 | 0.6450 | |
|
| 0.3993 | 2.4081 | 3800 | 0.6598 | |
|
| 0.469 | 2.4715 | 3900 | 0.6608 | |
|
| 0.4909 | 2.5349 | 4000 | 0.6856 | |
|
| 0.4797 | 2.5982 | 4100 | 0.6924 | |
|
| 0.4186 | 2.6616 | 4200 | 0.6857 | |
|
| 0.5057 | 2.7250 | 4300 | 0.6717 | |
|
| 0.4601 | 2.7883 | 4400 | 0.6723 | |
|
| 0.4862 | 2.8517 | 4500 | 0.7063 | |
|
| 0.4926 | 2.9151 | 4600 | 0.6399 | |
|
| 0.4886 | 2.9785 | 4700 | 0.6538 | |
|
| 0.4015 | 3.0418 | 4800 | 0.6485 | |
|
| 0.3844 | 3.1052 | 4900 | 0.6756 | |
|
| 0.4271 | 3.1686 | 5000 | 0.6801 | |
|
| 0.4245 | 3.2319 | 5100 | 0.6789 | |
|
| 0.4393 | 3.2953 | 5200 | 0.6881 | |
|
| 0.436 | 3.3587 | 5300 | 0.6710 | |
|
| 0.4717 | 3.4221 | 5400 | 0.6746 | |
|
| 0.4221 | 3.4854 | 5500 | 0.7194 | |
|
| 0.487 | 3.5488 | 5600 | 0.6693 | |
|
| 0.4547 | 3.6122 | 5700 | 0.6742 | |
|
| 0.4949 | 3.6755 | 5800 | 0.6795 | |
|
| 0.4865 | 3.7389 | 5900 | 0.7108 | |
|
| 0.5139 | 3.8023 | 6000 | 0.6612 | |
|
| 0.4512 | 3.8657 | 6100 | 0.6799 | |
|
| 0.5094 | 3.9290 | 6200 | 0.6759 | |
|
| 0.4989 | 3.9924 | 6300 | 0.6649 | |
|
| 0.3635 | 4.0558 | 6400 | 0.6683 | |
|
| 0.3599 | 4.1191 | 6500 | 0.6765 | |
|
| 0.3789 | 4.1825 | 6600 | 0.7041 | |
|
| 0.3897 | 4.2459 | 6700 | 0.6771 | |
|
| 0.3753 | 4.3093 | 6800 | 0.6831 | |
|
| 0.389 | 4.3726 | 6900 | 0.6954 | |
|
| 0.4111 | 4.4360 | 7000 | 0.7050 | |
|
| 0.4016 | 4.4994 | 7100 | 0.6762 | |
|
| 0.3798 | 4.5627 | 7200 | 0.7055 | |
|
| 0.4121 | 4.6261 | 7300 | 0.6707 | |
|
| 0.4127 | 4.6895 | 7400 | 0.6976 | |
|
| 0.4523 | 4.7529 | 7500 | 0.6520 | |
|
| 0.4035 | 4.8162 | 7600 | 0.7363 | |
|
| 0.4152 | 4.8796 | 7700 | 0.7270 | |
|
| 0.4615 | 4.9430 | 7800 | 0.6692 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.0 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
