|
--- |
|
base_model: unsloth/llama-3-8b |
|
library_name: peft |
|
license: llama3 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Meta-Llama-3-8B_pct_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_pct_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: 2.2219 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.2594 | 0.0206 | 8 | 2.2433 | |
|
| 2.2616 | 0.0412 | 16 | 2.2377 | |
|
| 2.2041 | 0.0618 | 24 | 2.2343 | |
|
| 2.2802 | 0.0824 | 32 | 2.2533 | |
|
| 2.2832 | 0.1030 | 40 | 2.2618 | |
|
| 2.2484 | 0.1236 | 48 | 2.2566 | |
|
| 2.2735 | 0.1442 | 56 | 2.2577 | |
|
| 2.293 | 0.1648 | 64 | 2.2784 | |
|
| 2.2518 | 0.1854 | 72 | 2.2818 | |
|
| 2.2922 | 0.2060 | 80 | 2.2914 | |
|
| 2.3199 | 0.2266 | 88 | 2.2720 | |
|
| 2.3807 | 0.2472 | 96 | 2.2788 | |
|
| 2.3528 | 0.2678 | 104 | 2.2831 | |
|
| 2.3144 | 0.2884 | 112 | 2.2958 | |
|
| 2.3652 | 0.3090 | 120 | 2.2950 | |
|
| 2.3637 | 0.3296 | 128 | 2.2845 | |
|
| 2.3014 | 0.3502 | 136 | 2.2781 | |
|
| 2.3067 | 0.3708 | 144 | 2.2830 | |
|
| 2.3242 | 0.3914 | 152 | 2.2788 | |
|
| 2.3184 | 0.4120 | 160 | 2.2659 | |
|
| 2.3574 | 0.4326 | 168 | 2.2782 | |
|
| 2.3006 | 0.4532 | 176 | 2.2733 | |
|
| 2.3082 | 0.4738 | 184 | 2.2699 | |
|
| 2.3097 | 0.4944 | 192 | 2.2615 | |
|
| 2.3003 | 0.5150 | 200 | 2.2649 | |
|
| 2.3027 | 0.5356 | 208 | 2.2594 | |
|
| 2.3262 | 0.5562 | 216 | 2.2491 | |
|
| 2.3118 | 0.5768 | 224 | 2.2599 | |
|
| 2.2904 | 0.5974 | 232 | 2.2623 | |
|
| 2.2519 | 0.6180 | 240 | 2.2495 | |
|
| 2.2907 | 0.6386 | 248 | 2.2526 | |
|
| 2.2864 | 0.6592 | 256 | 2.2512 | |
|
| 2.242 | 0.6798 | 264 | 2.2492 | |
|
| 2.2941 | 0.7004 | 272 | 2.2415 | |
|
| 2.2799 | 0.7210 | 280 | 2.2383 | |
|
| 2.2881 | 0.7416 | 288 | 2.2358 | |
|
| 2.2797 | 0.7621 | 296 | 2.2381 | |
|
| 2.3197 | 0.7827 | 304 | 2.2255 | |
|
| 2.2507 | 0.8033 | 312 | 2.2284 | |
|
| 2.236 | 0.8239 | 320 | 2.2313 | |
|
| 2.2667 | 0.8445 | 328 | 2.2200 | |
|
| 2.2763 | 0.8651 | 336 | 2.2255 | |
|
| 2.2915 | 0.8857 | 344 | 2.2229 | |
|
| 2.2554 | 0.9063 | 352 | 2.2211 | |
|
| 2.2237 | 0.9269 | 360 | 2.2241 | |
|
| 2.2446 | 0.9475 | 368 | 2.2229 | |
|
| 2.2926 | 0.9681 | 376 | 2.2224 | |
|
| 2.2813 | 0.9887 | 384 | 2.2219 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
