|
|
--- |
|
|
license: other |
|
|
library_name: peft |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
base_model: google/gemma-2b-it |
|
|
model-index: |
|
|
- name: outputs-82 |
|
|
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-82 |
|
|
|
|
|
This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.7601 |
|
|
|
|
|
## 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: 0.0002 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 16 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 10 |
|
|
- num_epochs: 10 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 2.7165 | 1.0 | 15 | 1.7252 | |
|
|
| 1.4588 | 2.0 | 30 | 1.5242 | |
|
|
| 1.0786 | 3.0 | 45 | 1.5330 | |
|
|
| 0.7402 | 4.0 | 60 | 1.6618 | |
|
|
| 0.457 | 5.0 | 75 | 1.8911 | |
|
|
| 0.2542 | 6.0 | 90 | 2.1658 | |
|
|
| 0.1315 | 7.0 | 105 | 2.4128 | |
|
|
| 0.0753 | 8.0 | 120 | 2.5541 | |
|
|
| 0.0532 | 9.0 | 135 | 2.6873 | |
|
|
| 0.0406 | 10.0 | 150 | 2.7601 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.9.0 |
|
|
- Transformers 4.38.2 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
