|
--- |
|
base_model: unsloth/llama-3-8b |
|
library_name: peft |
|
license: llama3 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Meta-Llama-3-8B_pct_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_pct_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: 2.1917 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.2547 | 0.0206 | 8 | 2.2652 | |
|
| 2.2857 | 0.0412 | 16 | 2.2722 | |
|
| 2.217 | 0.0618 | 24 | 2.2663 | |
|
| 2.2942 | 0.0824 | 32 | 2.2549 | |
|
| 2.281 | 0.1030 | 40 | 2.2508 | |
|
| 2.2541 | 0.1236 | 48 | 2.2708 | |
|
| 2.2672 | 0.1442 | 56 | 2.2648 | |
|
| 2.2887 | 0.1648 | 64 | 2.2698 | |
|
| 2.2464 | 0.1854 | 72 | 2.2654 | |
|
| 2.2805 | 0.2060 | 80 | 2.2734 | |
|
| 2.3111 | 0.2266 | 88 | 2.2742 | |
|
| 2.361 | 0.2472 | 96 | 2.2808 | |
|
| 2.3418 | 0.2678 | 104 | 2.2802 | |
|
| 2.3064 | 0.2884 | 112 | 2.2952 | |
|
| 2.3509 | 0.3090 | 120 | 2.2841 | |
|
| 2.3507 | 0.3296 | 128 | 2.2786 | |
|
| 2.3 | 0.3502 | 136 | 2.2801 | |
|
| 2.2953 | 0.3708 | 144 | 2.2772 | |
|
| 2.3224 | 0.3914 | 152 | 2.2823 | |
|
| 2.3055 | 0.4120 | 160 | 2.2739 | |
|
| 2.3519 | 0.4326 | 168 | 2.2795 | |
|
| 2.2988 | 0.4532 | 176 | 2.2694 | |
|
| 2.3046 | 0.4738 | 184 | 2.2648 | |
|
| 2.296 | 0.4944 | 192 | 2.2661 | |
|
| 2.2908 | 0.5150 | 200 | 2.2650 | |
|
| 2.2923 | 0.5356 | 208 | 2.2633 | |
|
| 2.3062 | 0.5562 | 216 | 2.2469 | |
|
| 2.289 | 0.5768 | 224 | 2.2516 | |
|
| 2.2736 | 0.5974 | 232 | 2.2452 | |
|
| 2.2414 | 0.6180 | 240 | 2.2406 | |
|
| 2.2667 | 0.6386 | 248 | 2.2355 | |
|
| 2.2595 | 0.6592 | 256 | 2.2354 | |
|
| 2.2175 | 0.6798 | 264 | 2.2276 | |
|
| 2.277 | 0.7004 | 272 | 2.2221 | |
|
| 2.2576 | 0.7210 | 280 | 2.2161 | |
|
| 2.2604 | 0.7416 | 288 | 2.2123 | |
|
| 2.2526 | 0.7621 | 296 | 2.2118 | |
|
| 2.2838 | 0.7827 | 304 | 2.2033 | |
|
| 2.2214 | 0.8033 | 312 | 2.2009 | |
|
| 2.2034 | 0.8239 | 320 | 2.2015 | |
|
| 2.235 | 0.8445 | 328 | 2.1954 | |
|
| 2.2444 | 0.8651 | 336 | 2.1971 | |
|
| 2.2593 | 0.8857 | 344 | 2.1939 | |
|
| 2.2222 | 0.9063 | 352 | 2.1929 | |
|
| 2.1894 | 0.9269 | 360 | 2.1944 | |
|
| 2.2138 | 0.9475 | 368 | 2.1927 | |
|
| 2.2543 | 0.9681 | 376 | 2.1918 | |
|
| 2.2462 | 0.9887 | 384 | 2.1917 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
