metadata
base_model: unsloth/llama-3-8b-bnb-4bit
library_name: peft
license: llama3
tags:
- unsloth
- generated_from_trainer
model-index:
- name: Meta-Llama-3-8B_magiccoder_ortho
results: []
Meta-Llama-3-8B_magiccoder_ortho
This model is a fine-tuned version of unsloth/llama-3-8b-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2979
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 |
|---|---|---|---|
| 1.3729 | 0.0259 | 4 | 1.4553 |
| 1.4282 | 0.0518 | 8 | 1.4025 |
| 1.3582 | 0.0777 | 12 | 1.3661 |
| 1.3765 | 0.1036 | 16 | 1.3732 |
| 1.412 | 0.1296 | 20 | 1.3709 |
| 1.3139 | 0.1555 | 24 | 1.3703 |
| 1.3527 | 0.1814 | 28 | 1.3569 |
| 1.3366 | 0.2073 | 32 | 1.3696 |
| 1.3585 | 0.2332 | 36 | 1.3574 |
| 1.4341 | 0.2591 | 40 | 1.3561 |
| 1.3608 | 0.2850 | 44 | 1.3471 |
| 1.2669 | 0.3109 | 48 | 1.3583 |
| 1.3432 | 0.3368 | 52 | 1.3500 |
| 1.3825 | 0.3628 | 56 | 1.3465 |
| 1.3424 | 0.3887 | 60 | 1.3365 |
| 1.3974 | 0.4146 | 64 | 1.3424 |
| 1.2641 | 0.4405 | 68 | 1.3373 |
| 1.3123 | 0.4664 | 72 | 1.3308 |
| 1.2767 | 0.4923 | 76 | 1.3429 |
| 1.3543 | 0.5182 | 80 | 1.3270 |
| 1.3019 | 0.5441 | 84 | 1.3380 |
| 1.3383 | 0.5700 | 88 | 1.3378 |
| 1.4165 | 0.5960 | 92 | 1.3250 |
| 1.2437 | 0.6219 | 96 | 1.3246 |
| 1.32 | 0.6478 | 100 | 1.3234 |
| 1.2362 | 0.6737 | 104 | 1.3309 |
| 1.2529 | 0.6996 | 108 | 1.3166 |
| 1.2605 | 0.7255 | 112 | 1.3099 |
| 1.3089 | 0.7514 | 116 | 1.3075 |
| 1.2937 | 0.7773 | 120 | 1.3063 |
| 1.3127 | 0.8032 | 124 | 1.3017 |
| 1.308 | 0.8291 | 128 | 1.3033 |
| 1.2962 | 0.8551 | 132 | 1.3026 |
| 1.2542 | 0.8810 | 136 | 1.3004 |
| 1.2808 | 0.9069 | 140 | 1.2992 |
| 1.242 | 0.9328 | 144 | 1.2967 |
| 1.265 | 0.9587 | 148 | 1.2990 |
| 1.2364 | 0.9846 | 152 | 1.2979 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1