idefics2-mmsd2-output

This model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7404

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: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
11.4109	0.0024	3	11.5141
10.8078	0.0048	6	10.5794
9.2349	0.0073	9	8.9413
7.1834	0.0097	12	6.4457
3.4013	0.0121	15	2.6901
1.3851	0.0145	18	1.9793
1.0381	0.0170	21	1.8684
1.1443	0.0194	24	1.7980
1.1719	0.0218	27	1.7651
1.1844	0.0242	30	1.7404

Framework versions

• Transformers 4.53.0.dev0
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1