gemma_hg

This model is a fine-tuned version of google/paligemma-3b-pt-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 5.1803

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
3.2946	7.6923	25	2.8461
2.4688	15.3846	50	3.0570
1.7313	23.0769	75	4.2260
1.1646	30.7692	100	4.8145
0.8469	38.4615	125	5.0539
0.7022	46.1538	150	5.1803

Framework versions

• PEFT 0.9.0
• Transformers 4.41.2
• Pytorch 2.1.2.post300
• Datasets 2.18.0
• Tokenizers 0.19.1