|
--- |
|
library_name: transformers |
|
license: gemma |
|
base_model: google/gemma-2-2b |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: sft-gemma-2-2b-ultrafeedback-binarized-20240920-114857 |
|
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. --> |
|
|
|
# sft-gemma-2-2b-ultrafeedback-binarized-20240920-114857 |
|
|
|
This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2499 |
|
|
|
## 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: 1.41e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 128 |
|
- total_train_batch_size: 1024 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.3539 | 0.3350 | 20 | 1.3197 | |
|
| 1.3073 | 0.6700 | 40 | 1.2901 | |
|
| 1.307 | 1.0050 | 60 | 1.2739 | |
|
| 1.2327 | 1.3400 | 80 | 1.2642 | |
|
| 1.2515 | 1.6750 | 100 | 1.2567 | |
|
| 1.2139 | 2.0099 | 120 | 1.2523 | |
|
| 1.2023 | 2.3449 | 140 | 1.2509 | |
|
| 1.2031 | 2.6799 | 160 | 1.2499 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|