resultsrocogoogle_paligemma-3b-mix-448__quickrun__0111-165311

This model is a fine-tuned version of google/paligemma-3b-mix-448 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.7518

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.509	1.0	1	3.9997
1.1011	2.0	3	3.9437
2.3622	3.0	4	3.9107
1.7492	4.0	6	3.8786
0.5772	5.0	8	3.8138
2.3454	6.0	9	3.7833
0.8544	6.4	10	3.7518

Framework versions

• PEFT 0.13.0
• Transformers 4.45.1
• Pytorch 2.3.0.post101
• Datasets 2.19.1
• Tokenizers 0.20.0