|
--- |
|
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_reverse |
|
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_reverse |
|
|
|
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: 1.1146 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.1799 | 0.0262 | 4 | 1.1888 | |
|
| 1.1193 | 0.0523 | 8 | 1.1757 | |
|
| 1.1603 | 0.0785 | 12 | 1.1751 | |
|
| 1.0847 | 0.1047 | 16 | 1.1702 | |
|
| 1.1304 | 0.1308 | 20 | 1.1674 | |
|
| 1.042 | 0.1570 | 24 | 1.1582 | |
|
| 1.1863 | 0.1832 | 28 | 1.1633 | |
|
| 1.14 | 0.2093 | 32 | 1.1597 | |
|
| 1.0763 | 0.2355 | 36 | 1.1503 | |
|
| 1.135 | 0.2617 | 40 | 1.1458 | |
|
| 1.1623 | 0.2878 | 44 | 1.1393 | |
|
| 1.1173 | 0.3140 | 48 | 1.1423 | |
|
| 1.1283 | 0.3401 | 52 | 1.1482 | |
|
| 1.0967 | 0.3663 | 56 | 1.1356 | |
|
| 1.1131 | 0.3925 | 60 | 1.1338 | |
|
| 1.1613 | 0.4186 | 64 | 1.1419 | |
|
| 1.0548 | 0.4448 | 68 | 1.1454 | |
|
| 1.0629 | 0.4710 | 72 | 1.1320 | |
|
| 1.0679 | 0.4971 | 76 | 1.1355 | |
|
| 1.16 | 0.5233 | 80 | 1.1287 | |
|
| 1.0579 | 0.5495 | 84 | 1.1295 | |
|
| 1.1214 | 0.5756 | 88 | 1.1392 | |
|
| 1.1681 | 0.6018 | 92 | 1.1242 | |
|
| 1.1667 | 0.6280 | 96 | 1.1223 | |
|
| 1.0871 | 0.6541 | 100 | 1.1221 | |
|
| 1.1147 | 0.6803 | 104 | 1.1243 | |
|
| 1.1075 | 0.7065 | 108 | 1.1254 | |
|
| 0.9958 | 0.7326 | 112 | 1.1186 | |
|
| 1.0718 | 0.7588 | 116 | 1.1085 | |
|
| 1.0748 | 0.7850 | 120 | 1.1193 | |
|
| 1.1082 | 0.8111 | 124 | 1.1138 | |
|
| 1.0981 | 0.8373 | 128 | 1.1102 | |
|
| 1.1231 | 0.8635 | 132 | 1.1133 | |
|
| 1.0687 | 0.8896 | 136 | 1.1143 | |
|
| 1.1568 | 0.9158 | 140 | 1.1139 | |
|
| 1.0177 | 0.9419 | 144 | 1.1140 | |
|
| 1.0401 | 0.9681 | 148 | 1.1145 | |
|
| 1.1827 | 0.9943 | 152 | 1.1146 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
