|
--- |
|
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: 1.1558 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.3236 | 0.0261 | 4 | 1.3076 | |
|
| 1.2244 | 0.0523 | 8 | 1.2947 | |
|
| 1.5369 | 0.0784 | 12 | 1.4240 | |
|
| 5.2765 | 0.1046 | 16 | 3.1163 | |
|
| 3.5831 | 0.1307 | 20 | 1.7562 | |
|
| 1.7895 | 0.1569 | 24 | 1.7124 | |
|
| 1.914 | 0.1830 | 28 | 1.7797 | |
|
| 2.9106 | 0.2092 | 32 | 2.3285 | |
|
| 1.5011 | 0.2353 | 36 | 1.4598 | |
|
| 1.4755 | 0.2614 | 40 | 1.4380 | |
|
| 1.4568 | 0.2876 | 44 | 1.3801 | |
|
| 1.2952 | 0.3137 | 48 | 1.3155 | |
|
| 1.3008 | 0.3399 | 52 | 1.2782 | |
|
| 1.2098 | 0.3660 | 56 | 1.2382 | |
|
| 1.2073 | 0.3922 | 60 | 1.2299 | |
|
| 1.2424 | 0.4183 | 64 | 1.2237 | |
|
| 1.1401 | 0.4444 | 68 | 1.2220 | |
|
| 1.1368 | 0.4706 | 72 | 1.2071 | |
|
| 1.1203 | 0.4967 | 76 | 1.2119 | |
|
| 1.21 | 0.5229 | 80 | 1.2026 | |
|
| 1.12 | 0.5490 | 84 | 1.1905 | |
|
| 1.199 | 0.5752 | 88 | 1.1893 | |
|
| 1.2302 | 0.6013 | 92 | 1.1889 | |
|
| 1.2382 | 0.6275 | 96 | 1.1797 | |
|
| 1.1521 | 0.6536 | 100 | 1.1765 | |
|
| 1.1563 | 0.6797 | 104 | 1.1728 | |
|
| 1.1676 | 0.7059 | 108 | 1.1718 | |
|
| 1.0429 | 0.7320 | 112 | 1.1642 | |
|
| 1.1303 | 0.7582 | 116 | 1.1660 | |
|
| 1.126 | 0.7843 | 120 | 1.1641 | |
|
| 1.1603 | 0.8105 | 124 | 1.1598 | |
|
| 1.146 | 0.8366 | 128 | 1.1587 | |
|
| 1.1689 | 0.8627 | 132 | 1.1547 | |
|
| 1.1046 | 0.8889 | 136 | 1.1533 | |
|
| 1.201 | 0.9150 | 140 | 1.1565 | |
|
| 1.0665 | 0.9412 | 144 | 1.1566 | |
|
| 1.0795 | 0.9673 | 148 | 1.1561 | |
|
| 1.2229 | 0.9935 | 152 | 1.1558 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
