|
--- |
|
base_model: unsloth/llama-3-8b |
|
library_name: peft |
|
license: llama3 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Meta-Llama-3-8B_magiccoder_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. --> |
|
|
|
# Meta-Llama-3-8B_magiccoder_ortho |
|
|
|
This model is a fine-tuned version of [unsloth/llama-3-8b](https://huggingface.co/unsloth/llama-3-8b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2651 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.2463 | 0.0259 | 4 | 1.4033 | |
|
| 1.3247 | 0.0518 | 8 | 1.3322 | |
|
| 1.2964 | 0.0777 | 12 | 1.3196 | |
|
| 1.3289 | 0.1036 | 16 | 1.3224 | |
|
| 1.3483 | 0.1296 | 20 | 1.3100 | |
|
| 1.2491 | 0.1555 | 24 | 1.3194 | |
|
| 1.3072 | 0.1814 | 28 | 1.3144 | |
|
| 1.2865 | 0.2073 | 32 | 1.3123 | |
|
| 1.3102 | 0.2332 | 36 | 1.3171 | |
|
| 1.3752 | 0.2591 | 40 | 1.3158 | |
|
| 1.3244 | 0.2850 | 44 | 1.3114 | |
|
| 1.2311 | 0.3109 | 48 | 1.3118 | |
|
| 1.2911 | 0.3368 | 52 | 1.3135 | |
|
| 1.3409 | 0.3628 | 56 | 1.3079 | |
|
| 1.3069 | 0.3887 | 60 | 1.3043 | |
|
| 1.362 | 0.4146 | 64 | 1.3125 | |
|
| 1.2206 | 0.4405 | 68 | 1.3051 | |
|
| 1.2838 | 0.4664 | 72 | 1.2986 | |
|
| 1.2348 | 0.4923 | 76 | 1.3073 | |
|
| 1.3171 | 0.5182 | 80 | 1.2922 | |
|
| 1.2556 | 0.5441 | 84 | 1.2965 | |
|
| 1.2803 | 0.5700 | 88 | 1.2911 | |
|
| 1.3796 | 0.5960 | 92 | 1.2854 | |
|
| 1.2047 | 0.6219 | 96 | 1.2871 | |
|
| 1.2821 | 0.6478 | 100 | 1.2866 | |
|
| 1.2012 | 0.6737 | 104 | 1.2838 | |
|
| 1.2116 | 0.6996 | 108 | 1.2799 | |
|
| 1.23 | 0.7255 | 112 | 1.2750 | |
|
| 1.2679 | 0.7514 | 116 | 1.2715 | |
|
| 1.2573 | 0.7773 | 120 | 1.2714 | |
|
| 1.2802 | 0.8032 | 124 | 1.2692 | |
|
| 1.2772 | 0.8291 | 128 | 1.2681 | |
|
| 1.2594 | 0.8551 | 132 | 1.2669 | |
|
| 1.218 | 0.8810 | 136 | 1.2666 | |
|
| 1.2391 | 0.9069 | 140 | 1.2658 | |
|
| 1.2084 | 0.9328 | 144 | 1.2656 | |
|
| 1.2245 | 0.9587 | 148 | 1.2651 | |
|
| 1.1995 | 0.9846 | 152 | 1.2651 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
