idefics2-frozenlake

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

idefics2-frozenlake

This model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown dataset.

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: 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: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.16.1
• Tokenizers 0.19.1 Vanilla model performance on frozenlake prompts dataset:
• Exact match: 0.00%
• F1: 17.75%

Fine-tuned model performance on frozenlake prompts dataset:

• Exact match: 21.00%
• F1: 63.13%

Model performance on frozenlake prompts dataset

Vanilla model performance:

• Exact match: 0.00%
• F1: 17.75%

Fine-tuned model performance:

• Exact match: 21.00%
• F1: 63.13%