pairwise-reward-gemma-2b-it-ultrafeedback-binarized-20240908-173848
This model is a fine-tuned version of google/gemma-2b-it on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5560
- Accuracy: 0.7067
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: 5e-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5703 | 0.0891 | 100 | 0.6093 | 0.6743 |
0.5614 | 0.1783 | 200 | 0.5986 | 0.6820 |
0.6027 | 0.2674 | 300 | 0.5895 | 0.6897 |
0.556 | 0.3565 | 400 | 0.5762 | 0.6974 |
0.546 | 0.4456 | 500 | 0.5686 | 0.7076 |
0.5775 | 0.5348 | 600 | 0.5619 | 0.7042 |
0.5787 | 0.6239 | 700 | 0.5606 | 0.7042 |
0.5608 | 0.7130 | 800 | 0.5574 | 0.7144 |
0.5183 | 0.8021 | 900 | 0.5564 | 0.7093 |
0.5252 | 0.8913 | 1000 | 0.5559 | 0.7136 |
0.5594 | 0.9804 | 1100 | 0.5560 | 0.7067 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 11
Inference API (serverless) is not available, repository is disabled.
Model tree for sahandrez/pairwise-reward-gemma-2b-it-ultrafeedback
Base model
google/gemma-2b-it
Finetuned
this model