colsmol256M_ufo

This model is a fine-tuned version of vidore/ColSmolVLM-Instruct-256M-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1362

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• 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: 100
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.1523	0.2	80	0.2213
0.1217	0.4	160	0.1516
0.0996	0.6	240	0.1418
0.0503	0.8	320	0.1347
0.0698	1.0	400	0.1362

Framework versions

• PEFT 0.14.0
• Transformers 4.49.0
• Pytorch 2.3.0+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0