|
|
--- |
|
|
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_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_v_Magiccoder_evol_10k_ortho |
|
|
|
|
|
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: 1.1371 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 1.1548 | 0.0262 | 4 | 1.1975 | |
|
|
| 1.1117 | 0.0523 | 8 | 1.1750 | |
|
|
| 1.1638 | 0.0785 | 12 | 1.1670 | |
|
|
| 1.0902 | 0.1047 | 16 | 1.1675 | |
|
|
| 1.1292 | 0.1308 | 20 | 1.1671 | |
|
|
| 1.0469 | 0.1570 | 24 | 1.1621 | |
|
|
| 1.2005 | 0.1832 | 28 | 1.1638 | |
|
|
| 1.1491 | 0.2093 | 32 | 1.1638 | |
|
|
| 1.0749 | 0.2355 | 36 | 1.1475 | |
|
|
| 1.1758 | 0.2617 | 40 | 1.1525 | |
|
|
| 1.1511 | 0.2878 | 44 | 1.1410 | |
|
|
| 1.1229 | 0.3140 | 48 | 1.1532 | |
|
|
| 1.1349 | 0.3401 | 52 | 1.1592 | |
|
|
| 1.1116 | 0.3663 | 56 | 1.1465 | |
|
|
| 1.1127 | 0.3925 | 60 | 1.1517 | |
|
|
| 1.1709 | 0.4186 | 64 | 1.1460 | |
|
|
| 1.0574 | 0.4448 | 68 | 1.1504 | |
|
|
| 1.0794 | 0.4710 | 72 | 1.1414 | |
|
|
| 1.0711 | 0.4971 | 76 | 1.1485 | |
|
|
| 1.1984 | 0.5233 | 80 | 1.1544 | |
|
|
| 1.0625 | 0.5495 | 84 | 1.1346 | |
|
|
| 1.151 | 0.5756 | 88 | 1.1728 | |
|
|
| 1.1977 | 0.6018 | 92 | 1.1364 | |
|
|
| 1.1757 | 0.6280 | 96 | 1.1418 | |
|
|
| 1.1191 | 0.6541 | 100 | 1.1487 | |
|
|
| 1.1415 | 0.6803 | 104 | 1.1431 | |
|
|
| 1.1272 | 0.7065 | 108 | 1.1399 | |
|
|
| 1.0134 | 0.7326 | 112 | 1.1431 | |
|
|
| 1.09 | 0.7588 | 116 | 1.1261 | |
|
|
| 1.0848 | 0.7850 | 120 | 1.1346 | |
|
|
| 1.1346 | 0.8111 | 124 | 1.1401 | |
|
|
| 1.1336 | 0.8373 | 128 | 1.1371 | |
|
|
| 1.1458 | 0.8635 | 132 | 1.1338 | |
|
|
| 1.0835 | 0.8896 | 136 | 1.1334 | |
|
|
| 1.1795 | 0.9158 | 140 | 1.1345 | |
|
|
| 1.0422 | 0.9419 | 144 | 1.1359 | |
|
|
| 1.0608 | 0.9681 | 148 | 1.1367 | |
|
|
| 1.2045 | 0.9943 | 152 | 1.1371 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.7.1 |
|
|
- Transformers 4.40.2 |
|
|
- Pytorch 2.3.0+cu121 |
|
|
- Datasets 2.19.1 |
|
|
- Tokenizers 0.19.1 |
