|
--- |
|
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: 1.1790 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.173 | 0.0261 | 4 | 1.2153 | |
|
| 1.1501 | 0.0523 | 8 | 1.1905 | |
|
| 1.19 | 0.0784 | 12 | 1.1831 | |
|
| 1.0875 | 0.1046 | 16 | 1.1805 | |
|
| 1.1648 | 0.1307 | 20 | 1.1844 | |
|
| 1.077 | 0.1569 | 24 | 1.1861 | |
|
| 1.2251 | 0.1830 | 28 | 1.1925 | |
|
| 1.1615 | 0.2092 | 32 | 1.1922 | |
|
| 1.1153 | 0.2353 | 36 | 1.1763 | |
|
| 1.2024 | 0.2614 | 40 | 1.1803 | |
|
| 1.2181 | 0.2876 | 44 | 1.1724 | |
|
| 1.1503 | 0.3137 | 48 | 1.2055 | |
|
| 1.1639 | 0.3399 | 52 | 1.1896 | |
|
| 1.1405 | 0.3660 | 56 | 1.1827 | |
|
| 1.177 | 0.3922 | 60 | 1.2037 | |
|
| 1.1958 | 0.4183 | 64 | 1.1796 | |
|
| 1.1044 | 0.4444 | 68 | 1.1970 | |
|
| 1.1115 | 0.4706 | 72 | 1.1735 | |
|
| 1.1152 | 0.4967 | 76 | 1.2061 | |
|
| 1.2009 | 0.5229 | 80 | 1.1671 | |
|
| 1.1154 | 0.5490 | 84 | 1.1960 | |
|
| 1.1739 | 0.5752 | 88 | 1.1892 | |
|
| 1.2224 | 0.6013 | 92 | 1.1764 | |
|
| 1.2229 | 0.6275 | 96 | 1.1926 | |
|
| 1.1573 | 0.6536 | 100 | 1.1849 | |
|
| 1.1629 | 0.6797 | 104 | 1.1787 | |
|
| 1.1855 | 0.7059 | 108 | 1.1955 | |
|
| 1.0586 | 0.7320 | 112 | 1.1814 | |
|
| 1.1258 | 0.7582 | 116 | 1.1631 | |
|
| 1.1273 | 0.7843 | 120 | 1.1787 | |
|
| 1.1869 | 0.8105 | 124 | 1.1873 | |
|
| 1.1765 | 0.8366 | 128 | 1.1852 | |
|
| 1.1954 | 0.8627 | 132 | 1.1809 | |
|
| 1.1277 | 0.8889 | 136 | 1.1763 | |
|
| 1.2109 | 0.9150 | 140 | 1.1747 | |
|
| 1.0842 | 0.9412 | 144 | 1.1771 | |
|
| 1.0941 | 0.9673 | 148 | 1.1787 | |
|
| 1.2413 | 0.9935 | 152 | 1.1790 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
