|
--- |
|
license: gemma |
|
base_model: google/gemma-2-2b |
|
tags: |
|
- easylm |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: easylm-helpsteer-sft-gemma-2-2b |
|
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. --> |
|
|
|
# easylm-helpsteer-sft-gemma-2-2b |
|
|
|
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: 1.1448 |
|
|
|
## 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: 3e-06 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- total_train_batch_size: 4 |
|
- total_eval_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.1281 | 0.2864 | 500 | 1.1230 | |
|
| 1.183 | 0.5727 | 1000 | 1.1017 | |
|
| 1.1009 | 0.8591 | 1500 | 1.0869 | |
|
| 0.6901 | 1.1455 | 2000 | 1.1486 | |
|
| 0.7377 | 1.4318 | 2500 | 1.1488 | |
|
| 0.6947 | 1.7182 | 3000 | 1.1501 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
