|
--- |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
library_name: peft |
|
license: llama3.1 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: lora_final |
|
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. --> |
|
|
|
# lora_final |
|
|
|
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: 1.2166 |
|
|
|
## 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: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.2611 | 0.0259 | 4 | 1.3885 | |
|
| 1.3239 | 0.0518 | 8 | 1.3166 | |
|
| 1.2605 | 0.0777 | 12 | 1.2847 | |
|
| 1.2849 | 0.1036 | 16 | 1.2750 | |
|
| 1.2928 | 0.1296 | 20 | 1.2562 | |
|
| 1.1904 | 0.1555 | 24 | 1.2448 | |
|
| 1.2444 | 0.1814 | 28 | 1.2414 | |
|
| 1.2182 | 0.2073 | 32 | 1.2368 | |
|
| 1.2447 | 0.2332 | 36 | 1.2359 | |
|
| 1.2958 | 0.2591 | 40 | 1.2332 | |
|
| 1.2491 | 0.2850 | 44 | 1.2297 | |
|
| 1.1667 | 0.3109 | 48 | 1.2305 | |
|
| 1.2285 | 0.3368 | 52 | 1.2287 | |
|
| 1.2667 | 0.3628 | 56 | 1.2263 | |
|
| 1.2466 | 0.3887 | 60 | 1.2270 | |
|
| 1.3088 | 0.4146 | 64 | 1.2266 | |
|
| 1.1579 | 0.4405 | 68 | 1.2262 | |
|
| 1.2358 | 0.4664 | 72 | 1.2229 | |
|
| 1.1688 | 0.4923 | 76 | 1.2220 | |
|
| 1.2594 | 0.5182 | 80 | 1.2215 | |
|
| 1.1863 | 0.5441 | 84 | 1.2196 | |
|
| 1.229 | 0.5700 | 88 | 1.2200 | |
|
| 1.3299 | 0.5960 | 92 | 1.2196 | |
|
| 1.1395 | 0.6219 | 96 | 1.2187 | |
|
| 1.2305 | 0.6478 | 100 | 1.2189 | |
|
| 1.1493 | 0.6737 | 104 | 1.2192 | |
|
| 1.1693 | 0.6996 | 108 | 1.2191 | |
|
| 1.1856 | 0.7255 | 112 | 1.2189 | |
|
| 1.2429 | 0.7514 | 116 | 1.2183 | |
|
| 1.2234 | 0.7773 | 120 | 1.2181 | |
|
| 1.243 | 0.8032 | 124 | 1.2178 | |
|
| 1.2387 | 0.8291 | 128 | 1.2172 | |
|
| 1.2366 | 0.8551 | 132 | 1.2168 | |
|
| 1.1838 | 0.8810 | 136 | 1.2167 | |
|
| 1.1884 | 0.9069 | 140 | 1.2167 | |
|
| 1.1714 | 0.9328 | 144 | 1.2167 | |
|
| 1.2058 | 0.9587 | 148 | 1.2166 | |
|
| 1.1725 | 0.9846 | 152 | 1.2166 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
