|
--- |
|
base_model: unsloth/mistral-7b-v0.3 |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral-7B-v0.3_pct_ortho |
|
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_ortho |
|
|
|
This model is a fine-tuned version of [unsloth/mistral-7b-v0.3](https://huggingface.co/unsloth/mistral-7b-v0.3) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 7.0729 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.1243 | 0.0206 | 8 | 2.2855 | |
|
| 9.1803 | 0.0413 | 16 | 12.8133 | |
|
| 9.137 | 0.0619 | 24 | 8.4567 | |
|
| 8.3645 | 0.0825 | 32 | 8.2606 | |
|
| 8.5251 | 0.1032 | 40 | 7.7564 | |
|
| 9.4881 | 0.1238 | 48 | 9.3070 | |
|
| 7.7111 | 0.1444 | 56 | 7.7363 | |
|
| 7.6126 | 0.1651 | 64 | 7.5948 | |
|
| 7.6789 | 0.1857 | 72 | 7.6147 | |
|
| 7.7404 | 0.2063 | 80 | 7.6322 | |
|
| 7.7173 | 0.2270 | 88 | 7.6740 | |
|
| 7.7113 | 0.2476 | 96 | 7.6742 | |
|
| 7.6961 | 0.2682 | 104 | 7.6422 | |
|
| 7.6729 | 0.2888 | 112 | 7.6076 | |
|
| 7.7225 | 0.3095 | 120 | 7.7171 | |
|
| 7.8259 | 0.3301 | 128 | 7.7724 | |
|
| 7.6611 | 0.3507 | 136 | 7.5974 | |
|
| 7.5696 | 0.3714 | 144 | 7.6032 | |
|
| 7.6786 | 0.3920 | 152 | 7.6163 | |
|
| 7.4746 | 0.4126 | 160 | 7.4268 | |
|
| 7.4383 | 0.4333 | 168 | 7.4069 | |
|
| 7.4469 | 0.4539 | 176 | 7.5225 | |
|
| 7.6465 | 0.4745 | 184 | 7.4849 | |
|
| 7.4025 | 0.4952 | 192 | 7.3099 | |
|
| 7.3473 | 0.5158 | 200 | 7.2623 | |
|
| 7.2821 | 0.5364 | 208 | 7.2484 | |
|
| 7.389 | 0.5571 | 216 | 7.7177 | |
|
| 7.2912 | 0.5777 | 224 | 7.1141 | |
|
| 7.1847 | 0.5983 | 232 | 7.1145 | |
|
| 7.2121 | 0.6190 | 240 | 7.1465 | |
|
| 7.1216 | 0.6396 | 248 | 7.1479 | |
|
| 7.2503 | 0.6602 | 256 | 7.1105 | |
|
| 7.1416 | 0.6809 | 264 | 7.1730 | |
|
| 7.2288 | 0.7015 | 272 | 7.1491 | |
|
| 7.3502 | 0.7221 | 280 | 7.1991 | |
|
| 7.2648 | 0.7427 | 288 | 7.1406 | |
|
| 7.1647 | 0.7634 | 296 | 7.1226 | |
|
| 7.1678 | 0.7840 | 304 | 7.0843 | |
|
| 7.1879 | 0.8046 | 312 | 7.1045 | |
|
| 7.2384 | 0.8253 | 320 | 7.1137 | |
|
| 7.2301 | 0.8459 | 328 | 7.0949 | |
|
| 7.2897 | 0.8665 | 336 | 7.1273 | |
|
| 7.1483 | 0.8872 | 344 | 7.1084 | |
|
| 7.1119 | 0.9078 | 352 | 7.0984 | |
|
| 7.2202 | 0.9284 | 360 | 7.0766 | |
|
| 7.1149 | 0.9491 | 368 | 7.0738 | |
|
| 7.1986 | 0.9697 | 376 | 7.0749 | |
|
| 7.155 | 0.9903 | 384 | 7.0729 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
