code-extraction

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

• Loss: 0.2910

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.1102	0.1064	10	0.9836
0.9563	0.2128	20	0.8361
0.8725	0.3191	30	0.7021
0.8441	0.4255	40	0.5871
0.6958	0.5319	50	0.5101
0.6931	0.6383	60	0.4598
0.5352	0.7447	70	0.4224
0.4966	0.8511	80	0.3931
0.6237	0.9574	90	0.3646
0.4289	1.0638	100	0.3423
0.5224	1.1702	110	0.3226
0.5532	1.2766	120	0.3140
0.3561	1.3830	130	0.3053
0.3985	1.4894	140	0.3027
0.39	1.5957	150	0.2992
0.3741	1.7021	160	0.2943
0.2028	1.8085	170	0.2898
0.3935	1.9149	180	0.2910

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1