resultsrocogoogle_paligemma-3b-mix-448__fullrun__0111-165804

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: 2.0471

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• 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
2.1353	0.9998	2044	2.1582
2.0695	1.9996	4088	2.0904
2.0833	2.9999	6133	2.0631
1.9914	3.9998	8177	2.0488
1.9621	4.9996	10221	2.0409
1.8801	5.9999	12266	2.0344
1.9081	6.9997	14310	2.0336
1.8805	8.0	16355	2.0353
1.909	8.9998	18399	2.0369
1.8255	9.9982	20440	2.0471

Framework versions

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