salaheddine666/gemma-2b-heart
<!-- 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. -->
gemma-2b-heart
This model is a fine-tuned version of google/gemma-2b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4600
- Accuracy: 0.7944
- Report: precision recall f1-score support
absence 0.80 0.79 0.80 92 presence 0.79 0.80 0.79 88
accuracy 0.79 180 macro avg 0.79 0.79 0.79 180 weighted avg 0.79 0.79 0.79 180
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: 2e-05
- trainbatchsize: 4
- evalbatchsize: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
- lrschedulertype: linear
- num_epochs: 5
Training results
absence 0.77 0.82 0.79 92 presence 0.80 0.75 0.77 88
accuracy 0.78 180 macro avg 0.78 0.78 0.78 180 weighted avg 0.78 0.78 0.78 180 | | No log | 2.0 | 210 | 0.5303 | 0.7778 | precision recall f1-score support
absence 0.78 0.79 0.78 92 presence 0.78 0.76 0.77 88
accuracy 0.78 180 macro avg 0.78 0.78 0.78 180 weighted avg 0.78 0.78 0.78 180 | | No log | 3.0 | 315 | 0.5015 | 0.7722 | precision recall f1-score support
absence 0.74 0.86 0.79 92 presence 0.82 0.68 0.75 88
accuracy 0.77 180 macro avg 0.78 0.77 0.77 180 weighted avg 0.78 0.77 0.77 180 | | No log | 4.0 | 420 | 0.4662 | 0.7833 | precision recall f1-score support
absence 0.78 0.79 0.79 92 presence 0.78 0.77 0.78 88
accuracy 0.78 180 macro avg 0.78 0.78 0.78 180 weighted avg 0.78 0.78 0.78 180 | | 0.566 | 5.0 | 525 | 0.4600 | 0.7944 | precision recall f1-score support
absence 0.80 0.79 0.80 92 presence 0.79 0.80 0.79 88
accuracy 0.79 180 macro avg 0.79 0.79 0.79 180 weighted avg 0.79 0.79 0.79 180 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
