|
--- |
|
base_model: unsloth/mistral-7b-v0.3-bnb-4bit |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral-7B-v0.3_magiccoder_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-v0.3_magiccoder_reverse |
|
|
|
This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 7.2545 |
|
|
|
## 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: 0.0003 |
|
- 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_ratio: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.6277 | 0.0262 | 4 | 2.6769 | |
|
| 9.6471 | 0.0523 | 8 | 9.0033 | |
|
| 10.5155 | 0.0785 | 12 | 8.9102 | |
|
| 8.2554 | 0.1047 | 16 | 8.4103 | |
|
| 7.9575 | 0.1308 | 20 | 7.8467 | |
|
| 7.7793 | 0.1570 | 24 | 7.7779 | |
|
| 7.8343 | 0.1832 | 28 | 7.8376 | |
|
| 7.7751 | 0.2093 | 32 | 7.7518 | |
|
| 7.7596 | 0.2355 | 36 | 7.8731 | |
|
| 7.8576 | 0.2617 | 40 | 7.7542 | |
|
| 7.8192 | 0.2878 | 44 | 7.6664 | |
|
| 7.6969 | 0.3140 | 48 | 7.6550 | |
|
| 7.6456 | 0.3401 | 52 | 7.6300 | |
|
| 7.5219 | 0.3663 | 56 | 7.5777 | |
|
| 7.5785 | 0.3925 | 60 | 7.5343 | |
|
| 7.5603 | 0.4186 | 64 | 7.5427 | |
|
| 7.6511 | 0.4448 | 68 | 7.4908 | |
|
| 7.5751 | 0.4710 | 72 | 7.4379 | |
|
| 7.5561 | 0.4971 | 76 | 7.5841 | |
|
| 7.4865 | 0.5233 | 80 | 7.5991 | |
|
| 7.4538 | 0.5495 | 84 | 7.4216 | |
|
| 7.4582 | 0.5756 | 88 | 7.3826 | |
|
| 7.5413 | 0.6018 | 92 | 7.3876 | |
|
| 7.4509 | 0.6280 | 96 | 7.3721 | |
|
| 7.4923 | 0.6541 | 100 | 7.4695 | |
|
| 7.365 | 0.6803 | 104 | 7.4247 | |
|
| 7.3943 | 0.7065 | 108 | 7.3939 | |
|
| 7.3449 | 0.7326 | 112 | 7.3569 | |
|
| 7.2922 | 0.7588 | 116 | 7.3034 | |
|
| 7.3824 | 0.7850 | 120 | 7.2675 | |
|
| 7.4081 | 0.8111 | 124 | 7.3202 | |
|
| 7.3249 | 0.8373 | 128 | 7.2621 | |
|
| 7.3576 | 0.8635 | 132 | 7.2639 | |
|
| 7.2845 | 0.8896 | 136 | 7.2773 | |
|
| 7.2098 | 0.9158 | 140 | 7.2565 | |
|
| 7.2525 | 0.9419 | 144 | 7.2417 | |
|
| 7.2333 | 0.9681 | 148 | 7.2520 | |
|
| 7.2556 | 0.9943 | 152 | 7.2545 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
