results_final_fold_1

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: 0.1972

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.2713	1.0	2091	0.2417
0.2592	2.0	4182	0.2189
0.2431	3.0	6273	0.2139
0.2258	4.0	8364	0.2072
0.2349	5.0	10455	0.2064
0.2307	6.0	12546	0.2013
0.2146	7.0	14637	0.2011
0.2176	8.0	16728	0.2001
0.2222	9.0	18819	0.2000
0.2195	10.0	20910	0.1980
0.2237	11.0	23001	0.1985
0.2133	12.0	25092	0.1980
0.223	13.0	27183	0.1972
0.2191	14.0	29274	0.1976
0.2369	15.0	31365	0.1974

Framework versions

• Transformers 4.51.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 3.5.0
• Tokenizers 0.21.1