|
--- |
|
base_model: unsloth/llama-3-8b |
|
library_name: peft |
|
license: llama3 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Meta-Llama-3-8B_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. --> |
|
|
|
# Meta-Llama-3-8B_magiccoder_reverse |
|
|
|
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: 1.2663 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.2593 | 0.0259 | 4 | 1.4180 | |
|
| 1.4127 | 0.0518 | 8 | 1.3958 | |
|
| 1.3964 | 0.0777 | 12 | 1.3814 | |
|
| 1.3824 | 0.1036 | 16 | 1.3679 | |
|
| 1.4044 | 0.1296 | 20 | 1.3733 | |
|
| 1.3092 | 0.1555 | 24 | 1.3639 | |
|
| 1.3823 | 0.1814 | 28 | 1.4075 | |
|
| 1.3878 | 0.2073 | 32 | 1.3768 | |
|
| 1.3653 | 0.2332 | 36 | 1.3592 | |
|
| 1.4395 | 0.2591 | 40 | 1.3594 | |
|
| 1.3805 | 0.2850 | 44 | 1.3444 | |
|
| 1.2631 | 0.3109 | 48 | 1.3354 | |
|
| 1.3346 | 0.3368 | 52 | 1.3409 | |
|
| 1.3776 | 0.3628 | 56 | 1.3367 | |
|
| 1.3407 | 0.3887 | 60 | 1.3291 | |
|
| 1.3939 | 0.4146 | 64 | 1.3307 | |
|
| 1.2555 | 0.4405 | 68 | 1.3257 | |
|
| 1.3227 | 0.4664 | 72 | 1.3216 | |
|
| 1.2664 | 0.4923 | 76 | 1.3238 | |
|
| 1.3542 | 0.5182 | 80 | 1.3157 | |
|
| 1.2873 | 0.5441 | 84 | 1.3167 | |
|
| 1.3065 | 0.5700 | 88 | 1.3109 | |
|
| 1.4021 | 0.5960 | 92 | 1.3056 | |
|
| 1.2277 | 0.6219 | 96 | 1.3021 | |
|
| 1.3014 | 0.6478 | 100 | 1.3000 | |
|
| 1.2138 | 0.6737 | 104 | 1.2911 | |
|
| 1.2367 | 0.6996 | 108 | 1.2903 | |
|
| 1.2501 | 0.7255 | 112 | 1.2844 | |
|
| 1.2942 | 0.7514 | 116 | 1.2819 | |
|
| 1.2762 | 0.7773 | 120 | 1.2780 | |
|
| 1.2871 | 0.8032 | 124 | 1.2753 | |
|
| 1.2829 | 0.8291 | 128 | 1.2724 | |
|
| 1.272 | 0.8551 | 132 | 1.2695 | |
|
| 1.2242 | 0.8810 | 136 | 1.2685 | |
|
| 1.253 | 0.9069 | 140 | 1.2678 | |
|
| 1.2116 | 0.9328 | 144 | 1.2671 | |
|
| 1.2356 | 0.9587 | 148 | 1.2666 | |
|
| 1.2087 | 0.9846 | 152 | 1.2663 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |