|
--- |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
library_name: peft |
|
license: llama3.1 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: l3.1-8b-ins-magiccoder |
|
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. --> |
|
|
|
# l3.1-8b-ins-magiccoder |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2331 |
|
|
|
## 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_ratio: 0.02 |
|
- num_epochs: 0.45 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.4834 | 0.0130 | 2 | 1.3970 | |
|
| 1.2584 | 0.0259 | 4 | 1.3753 | |
|
| 1.2988 | 0.0389 | 6 | 1.3373 | |
|
| 1.3458 | 0.0518 | 8 | 1.3058 | |
|
| 1.2461 | 0.0648 | 10 | 1.2893 | |
|
| 1.263 | 0.0777 | 12 | 1.2828 | |
|
| 1.2758 | 0.0907 | 14 | 1.2782 | |
|
| 1.2802 | 0.1036 | 16 | 1.2702 | |
|
| 1.137 | 0.1166 | 18 | 1.2617 | |
|
| 1.336 | 0.1296 | 20 | 1.2531 | |
|
| 1.1811 | 0.1425 | 22 | 1.2466 | |
|
| 1.1447 | 0.1555 | 24 | 1.2441 | |
|
| 1.177 | 0.1684 | 26 | 1.2426 | |
|
| 1.2585 | 0.1814 | 28 | 1.2404 | |
|
| 1.1993 | 0.1943 | 30 | 1.2381 | |
|
| 1.1566 | 0.2073 | 32 | 1.2370 | |
|
| 1.2826 | 0.2202 | 34 | 1.2364 | |
|
| 1.1512 | 0.2332 | 36 | 1.2356 | |
|
| 1.1779 | 0.2462 | 38 | 1.2352 | |
|
| 1.261 | 0.2591 | 40 | 1.2346 | |
|
| 1.1998 | 0.2721 | 42 | 1.2341 | |
|
| 1.1847 | 0.2850 | 44 | 1.2335 | |
|
| 1.1266 | 0.2980 | 46 | 1.2336 | |
|
| 1.1699 | 0.3109 | 48 | 1.2336 | |
|
| 1.283 | 0.3239 | 50 | 1.2332 | |
|
| 1.2469 | 0.3368 | 52 | 1.2331 | |
|
| 1.1653 | 0.3498 | 54 | 1.2330 | |
|
| 1.2752 | 0.3628 | 56 | 1.2332 | |
|
| 1.2077 | 0.3757 | 58 | 1.2331 | |
|
| 1.1729 | 0.3887 | 60 | 1.2330 | |
|
| 1.2643 | 0.4016 | 62 | 1.2331 | |
|
| 1.3324 | 0.4146 | 64 | 1.2331 | |
|
| 1.2215 | 0.4275 | 66 | 1.2332 | |
|
| 1.2623 | 0.4405 | 68 | 1.2332 | |
|
| 1.2845 | 0.4534 | 70 | 1.2331 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
