|
--- |
|
base_model: mistralai/Mistral-7B-v0.3 |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral-7B-v0.3_pct_reverse_r32 |
|
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_r32 |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0458 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 64 |
|
- 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.991 | 0.0206 | 8 | 2.0312 | |
|
| 2.0461 | 0.0413 | 16 | 2.0335 | |
|
| 2.0456 | 0.0619 | 24 | 2.0601 | |
|
| 2.0584 | 0.0825 | 32 | 2.0879 | |
|
| 2.1123 | 0.1032 | 40 | 2.0809 | |
|
| 2.0666 | 0.1238 | 48 | 2.0890 | |
|
| 2.0733 | 0.1444 | 56 | 2.0954 | |
|
| 2.1236 | 0.1651 | 64 | 2.0971 | |
|
| 2.1103 | 0.1857 | 72 | 2.1008 | |
|
| 2.0876 | 0.2063 | 80 | 2.1042 | |
|
| 2.1107 | 0.2270 | 88 | 2.1155 | |
|
| 2.0889 | 0.2476 | 96 | 2.1083 | |
|
| 2.097 | 0.2682 | 104 | 2.1186 | |
|
| 2.0962 | 0.2889 | 112 | 2.1202 | |
|
| 2.1415 | 0.3095 | 120 | 2.1305 | |
|
| 2.1294 | 0.3301 | 128 | 2.1169 | |
|
| 2.1476 | 0.3508 | 136 | 2.1300 | |
|
| 2.1725 | 0.3714 | 144 | 2.1245 | |
|
| 2.1159 | 0.3920 | 152 | 2.1172 | |
|
| 2.0921 | 0.4127 | 160 | 2.1221 | |
|
| 2.141 | 0.4333 | 168 | 2.1334 | |
|
| 2.1312 | 0.4539 | 176 | 2.1259 | |
|
| 2.106 | 0.4746 | 184 | 2.1269 | |
|
| 2.1015 | 0.4952 | 192 | 2.1197 | |
|
| 2.1368 | 0.5158 | 200 | 2.1164 | |
|
| 2.0751 | 0.5364 | 208 | 2.1104 | |
|
| 2.135 | 0.5571 | 216 | 2.1105 | |
|
| 2.0718 | 0.5777 | 224 | 2.1003 | |
|
| 2.0393 | 0.5983 | 232 | 2.1025 | |
|
| 2.1034 | 0.6190 | 240 | 2.0946 | |
|
| 2.045 | 0.6396 | 248 | 2.0939 | |
|
| 2.077 | 0.6602 | 256 | 2.0814 | |
|
| 2.0514 | 0.6809 | 264 | 2.0800 | |
|
| 2.0222 | 0.7015 | 272 | 2.0774 | |
|
| 2.075 | 0.7221 | 280 | 2.0749 | |
|
| 2.1013 | 0.7428 | 288 | 2.0705 | |
|
| 2.0929 | 0.7634 | 296 | 2.0643 | |
|
| 2.0996 | 0.7840 | 304 | 2.0692 | |
|
| 2.0507 | 0.8047 | 312 | 2.0588 | |
|
| 2.0353 | 0.8253 | 320 | 2.0574 | |
|
| 2.0128 | 0.8459 | 328 | 2.0570 | |
|
| 2.0508 | 0.8666 | 336 | 2.0503 | |
|
| 2.067 | 0.8872 | 344 | 2.0472 | |
|
| 2.0821 | 0.9078 | 352 | 2.0476 | |
|
| 2.0461 | 0.9285 | 360 | 2.0471 | |
|
| 2.0666 | 0.9491 | 368 | 2.0461 | |
|
| 2.0639 | 0.9697 | 376 | 2.0458 | |
|
| 1.9859 | 0.9904 | 384 | 2.0458 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
