|
--- |
|
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_default |
|
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_default |
|
|
|
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: 6.8426 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.2574 | 0.0206 | 8 | 8.1127 | |
|
| 12.0384 | 0.0413 | 16 | 8.6074 | |
|
| 8.2422 | 0.0619 | 24 | 8.1200 | |
|
| 7.6855 | 0.0825 | 32 | 7.6217 | |
|
| 7.676 | 0.1032 | 40 | 7.6368 | |
|
| 7.636 | 0.1238 | 48 | 7.5536 | |
|
| 7.5027 | 0.1444 | 56 | 7.4853 | |
|
| 7.393 | 0.1651 | 64 | 7.3495 | |
|
| 7.4878 | 0.1857 | 72 | 7.3829 | |
|
| 7.4503 | 0.2063 | 80 | 7.2955 | |
|
| 7.4405 | 0.2270 | 88 | 7.2849 | |
|
| 7.3525 | 0.2476 | 96 | 7.2125 | |
|
| 7.3442 | 0.2682 | 104 | 7.2516 | |
|
| 7.292 | 0.2888 | 112 | 7.2813 | |
|
| 7.2845 | 0.3095 | 120 | 7.2147 | |
|
| 7.3309 | 0.3301 | 128 | 7.1448 | |
|
| 7.165 | 0.3507 | 136 | 7.1427 | |
|
| 7.1362 | 0.3714 | 144 | 7.0595 | |
|
| 7.1956 | 0.3920 | 152 | 7.2333 | |
|
| 7.1047 | 0.4126 | 160 | 7.0622 | |
|
| 7.1466 | 0.4333 | 168 | 7.0642 | |
|
| 7.0243 | 0.4539 | 176 | 7.0605 | |
|
| 7.1814 | 0.4745 | 184 | 7.0207 | |
|
| 7.1579 | 0.4952 | 192 | 7.0191 | |
|
| 6.9988 | 0.5158 | 200 | 7.0403 | |
|
| 7.0306 | 0.5364 | 208 | 6.9673 | |
|
| 7.2037 | 0.5571 | 216 | 6.9458 | |
|
| 7.0632 | 0.5777 | 224 | 6.8305 | |
|
| 6.8916 | 0.5983 | 232 | 6.8760 | |
|
| 6.929 | 0.6190 | 240 | 6.8567 | |
|
| 6.927 | 0.6396 | 248 | 6.9211 | |
|
| 7.0534 | 0.6602 | 256 | 6.9313 | |
|
| 6.8807 | 0.6809 | 264 | 7.0025 | |
|
| 7.0768 | 0.7015 | 272 | 6.8808 | |
|
| 7.042 | 0.7221 | 280 | 6.9264 | |
|
| 7.027 | 0.7427 | 288 | 6.8833 | |
|
| 6.9575 | 0.7634 | 296 | 6.8925 | |
|
| 6.9509 | 0.7840 | 304 | 6.8662 | |
|
| 7.0361 | 0.8046 | 312 | 6.9178 | |
|
| 7.0065 | 0.8253 | 320 | 6.8844 | |
|
| 7.0016 | 0.8459 | 328 | 6.8536 | |
|
| 7.0667 | 0.8665 | 336 | 6.9255 | |
|
| 6.9046 | 0.8872 | 344 | 6.8849 | |
|
| 6.8891 | 0.9078 | 352 | 6.8567 | |
|
| 7.0118 | 0.9284 | 360 | 6.8438 | |
|
| 6.901 | 0.9491 | 368 | 6.8571 | |
|
| 7.0057 | 0.9697 | 376 | 6.8454 | |
|
| 6.9415 | 0.9903 | 384 | 6.8426 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
