|
|
--- |
|
|
library_name: peft |
|
|
tags: |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
base_model: LLama_weights/tmp |
|
|
model-index: |
|
|
- name: outputs |
|
|
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. --> |
|
|
|
|
|
# outputs |
|
|
|
|
|
This model was trained from scratch on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.4939 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 16 |
|
|
- total_train_batch_size: 16 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 5 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 2.0181 | 0.24 | 4 | 1.9684 | |
|
|
| 2.0616 | 0.47 | 8 | 1.8863 | |
|
|
| 1.8467 | 0.71 | 12 | 1.8116 | |
|
|
| 1.707 | 0.94 | 16 | 1.7309 | |
|
|
| 1.7886 | 1.18 | 20 | 1.6529 | |
|
|
| 1.6539 | 1.41 | 24 | 1.5884 | |
|
|
| 1.5149 | 1.65 | 28 | 1.5568 | |
|
|
| 1.4526 | 1.88 | 32 | 1.5390 | |
|
|
| 1.5335 | 2.12 | 36 | 1.5283 | |
|
|
| 1.5668 | 2.35 | 40 | 1.5211 | |
|
|
| 1.3914 | 2.59 | 44 | 1.5158 | |
|
|
| 1.5769 | 2.82 | 48 | 1.5113 | |
|
|
| 1.3794 | 3.06 | 52 | 1.5075 | |
|
|
| 1.5274 | 3.29 | 56 | 1.5043 | |
|
|
| 1.5247 | 3.53 | 60 | 1.5016 | |
|
|
| 1.4291 | 3.76 | 64 | 1.4993 | |
|
|
| 1.4233 | 4.0 | 68 | 1.4974 | |
|
|
| 1.4353 | 4.24 | 72 | 1.4960 | |
|
|
| 1.6016 | 4.47 | 76 | 1.4949 | |
|
|
| 1.4416 | 4.71 | 80 | 1.4942 | |
|
|
| 1.4654 | 4.94 | 84 | 1.4939 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.8.2 |
|
|
- Transformers 4.37.2 |
|
|
- Pytorch 2.2.0+cu118 |
|
|
- Datasets 2.17.0 |
|
|
- Tokenizers 0.15.1 |
