metadata
license: gemma
base_model: google/gemma-2-2b
tags:
- easylm
- trl
- reward-trainer
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: easylm-helpsteer-rm-gemma-2-2b
results: []
easylm-helpsteer-rm-gemma-2-2b
This model is a fine-tuned version of google/gemma-2-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9694
- Accuracy: 0.6265
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-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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5003 | 0.3115 | 500 | 2.7140 | 0.6294 |
| 0.3939 | 0.6231 | 1000 | 3.3430 | 0.65 |
| 0.065 | 0.9346 | 1500 | 2.9740 | 0.6324 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1