|
|
--- |
|
|
license: apache-2.0 |
|
|
library_name: peft |
|
|
tags: |
|
|
- unsloth |
|
|
- generated_from_trainer |
|
|
base_model: mistralai/Mistral-7B-v0.3 |
|
|
model-index: |
|
|
- name: mistral_7b_v_Magiccoder_evol_10k |
|
|
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_v_Magiccoder_evol_10k |
|
|
|
|
|
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: 1.1499 |
|
|
|
|
|
## 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: 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_steps: 0.02 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 1.1885 | 0.0262 | 4 | 1.1900 | |
|
|
| 1.0966 | 0.0523 | 8 | 1.1442 | |
|
|
| 1.1468 | 0.0785 | 12 | 1.1514 | |
|
|
| 1.0845 | 0.1047 | 16 | 1.1671 | |
|
|
| 1.1413 | 0.1308 | 20 | 1.1635 | |
|
|
| 1.0557 | 0.1570 | 24 | 1.1689 | |
|
|
| 1.1949 | 0.1832 | 28 | 1.1682 | |
|
|
| 1.149 | 0.2093 | 32 | 1.1674 | |
|
|
| 1.0952 | 0.2355 | 36 | 1.1541 | |
|
|
| 1.1551 | 0.2617 | 40 | 1.1687 | |
|
|
| 1.1864 | 0.2878 | 44 | 1.1547 | |
|
|
| 1.119 | 0.3140 | 48 | 1.1576 | |
|
|
| 1.141 | 0.3401 | 52 | 1.1748 | |
|
|
| 1.118 | 0.3663 | 56 | 1.1625 | |
|
|
| 1.1186 | 0.3925 | 60 | 1.1571 | |
|
|
| 1.1766 | 0.4186 | 64 | 1.1620 | |
|
|
| 1.0801 | 0.4448 | 68 | 1.1534 | |
|
|
| 1.0816 | 0.4710 | 72 | 1.1579 | |
|
|
| 1.087 | 0.4971 | 76 | 1.1575 | |
|
|
| 1.1822 | 0.5233 | 80 | 1.1619 | |
|
|
| 1.0812 | 0.5495 | 84 | 1.1607 | |
|
|
| 1.1626 | 0.5756 | 88 | 1.1611 | |
|
|
| 1.21 | 0.6018 | 92 | 1.1624 | |
|
|
| 1.1947 | 0.6280 | 96 | 1.1555 | |
|
|
| 1.1154 | 0.6541 | 100 | 1.1518 | |
|
|
| 1.1488 | 0.6803 | 104 | 1.1587 | |
|
|
| 1.1402 | 0.7065 | 108 | 1.1595 | |
|
|
| 1.0249 | 0.7326 | 112 | 1.1574 | |
|
|
| 1.1102 | 0.7588 | 116 | 1.1472 | |
|
|
| 1.1072 | 0.7850 | 120 | 1.1464 | |
|
|
| 1.1382 | 0.8111 | 124 | 1.1473 | |
|
|
| 1.1457 | 0.8373 | 128 | 1.1477 | |
|
|
| 1.156 | 0.8635 | 132 | 1.1483 | |
|
|
| 1.1037 | 0.8896 | 136 | 1.1488 | |
|
|
| 1.2025 | 0.9158 | 140 | 1.1492 | |
|
|
| 1.0551 | 0.9419 | 144 | 1.1496 | |
|
|
| 1.0823 | 0.9681 | 148 | 1.1499 | |
|
|
| 1.2344 | 0.9943 | 152 | 1.1499 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.7.1 |
|
|
- Transformers 4.40.2 |
|
|
- Pytorch 2.3.0+cu121 |
|
|
- Datasets 2.19.1 |
|
|
- Tokenizers 0.19.1 |
