|
|
--- |
|
|
base_model: google/gemma-2b |
|
|
library_name: peft |
|
|
license: gemma |
|
|
metrics: |
|
|
- accuracy |
|
|
tags: |
|
|
- trl |
|
|
- reward-trainer |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: 0721_222324-google-gemma-2b |
|
|
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. --> |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/6-5940/huggingface/runs/sqce7ion) |
|
|
# 0721_222324-google-gemma-2b |
|
|
|
|
|
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2063 |
|
|
- Accuracy: 1.0 |
|
|
|
|
|
## 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: 1e-05 |
|
|
- 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 |
|
|
- num_epochs: 100.0 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
|
| 0.6308 | 3.3333 | 5 | 0.6551 | 0.7 | |
|
|
| 0.6283 | 6.6667 | 10 | 0.6179 | 0.75 | |
|
|
| 0.5927 | 10.0 | 15 | 0.5822 | 0.75 | |
|
|
| 0.6668 | 13.3333 | 20 | 0.5473 | 0.8 | |
|
|
| 0.5427 | 16.6667 | 25 | 0.5125 | 0.85 | |
|
|
| 0.5109 | 20.0 | 30 | 0.4783 | 0.85 | |
|
|
| 0.4731 | 23.3333 | 35 | 0.4456 | 0.95 | |
|
|
| 0.4261 | 26.6667 | 40 | 0.4137 | 0.95 | |
|
|
| 0.3719 | 30.0 | 45 | 0.3832 | 0.95 | |
|
|
| 0.4027 | 33.3333 | 50 | 0.3542 | 0.95 | |
|
|
| 0.3231 | 36.6667 | 55 | 0.3276 | 1.0 | |
|
|
| 0.3292 | 40.0 | 60 | 0.3032 | 1.0 | |
|
|
| 0.3517 | 43.3333 | 65 | 0.2810 | 1.0 | |
|
|
| 0.2759 | 46.6667 | 70 | 0.2618 | 1.0 | |
|
|
| 0.2743 | 50.0 | 75 | 0.2448 | 1.0 | |
|
|
| 0.2651 | 53.3333 | 80 | 0.2310 | 1.0 | |
|
|
| 0.2181 | 56.6667 | 85 | 0.2203 | 1.0 | |
|
|
| 0.2067 | 60.0 | 90 | 0.2127 | 1.0 | |
|
|
| 0.2268 | 63.3333 | 95 | 0.2081 | 1.0 | |
|
|
| 0.2014 | 66.6667 | 100 | 0.2063 | 1.0 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.11.1 |
|
|
- Transformers 4.42.4 |
|
|
- Pytorch 2.3.1+cu121 |
|
|
- Datasets 2.20.0 |
|
|
- Tokenizers 0.19.1 |
