0721_211205-google-gemma-2b

This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0008
• Accuracy: 1.0

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-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1742	5.0	5	0.3139	1.0
0.101	10.0	10	0.1813	1.0
0.0568	15.0	15	0.0998	1.0
0.0294	20.0	20	0.0514	1.0
0.0145	25.0	25	0.0252	1.0
0.0071	30.0	30	0.0127	1.0
0.0039	35.0	35	0.0070	1.0
0.0024	40.0	40	0.0042	1.0
0.0016	45.0	45	0.0028	1.0
0.0011	50.0	50	0.0021	1.0
0.0009	55.0	55	0.0016	1.0
0.0007	60.0	60	0.0014	1.0
0.0006	65.0	65	0.0012	1.0
0.0005	70.0	70	0.0011	1.0
0.0005	75.0	75	0.0010	1.0
0.0005	80.0	80	0.0009	1.0
0.0005	85.0	85	0.0009	1.0
0.0004	90.0	90	0.0009	1.0
0.0004	95.0	95	0.0008	1.0
0.0004	100.0	100	0.0008	1.0

Framework versions

• PEFT 0.11.1
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1