|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: google/gemma-7b |
|
model-index: |
|
- name: gemma-7b-prompts |
|
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. --> |
|
|
|
# gemma-7b-prompts |
|
|
|
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3761 |
|
|
|
## 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: 0.0004 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 2 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 2000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.7687 | 0.09 | 100 | 1.1701 | |
|
| 0.7207 | 0.19 | 200 | 1.0388 | |
|
| 0.7185 | 0.28 | 300 | 0.9201 | |
|
| 0.9138 | 0.38 | 400 | 0.8356 | |
|
| 0.6879 | 0.47 | 500 | 0.7887 | |
|
| 0.559 | 0.56 | 600 | 0.7439 | |
|
| 0.5832 | 0.66 | 700 | 0.7136 | |
|
| 0.556 | 0.75 | 800 | 0.6738 | |
|
| 0.5783 | 0.85 | 900 | 0.6341 | |
|
| 0.6397 | 0.94 | 1000 | 0.6029 | |
|
| 0.3719 | 1.03 | 1100 | 0.5467 | |
|
| 0.5698 | 1.13 | 1200 | 0.5181 | |
|
| 0.6411 | 1.22 | 1300 | 0.4972 | |
|
| 0.6049 | 1.32 | 1400 | 0.4737 | |
|
| 0.5309 | 1.41 | 1500 | 0.4417 | |
|
| 0.4735 | 1.5 | 1600 | 0.4218 | |
|
| 0.5055 | 1.6 | 1700 | 0.4065 | |
|
| 0.5309 | 1.69 | 1800 | 0.3900 | |
|
| 0.5644 | 1.79 | 1900 | 0.3792 | |
|
| 0.3979 | 1.88 | 2000 | 0.3761 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
