idefics2-8b-lrr-finetuned-2

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

• eval_loss: 0.0820
• eval_runtime: 80.0346
• eval_samples_per_second: 5.098
• eval_steps_per_second: 0.737
• epoch: 1.9048
• step: 200

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: 7
• eval_batch_size: 7
• seed: 42
• gradient_accumulation_steps: 5
• total_train_batch_size: 35
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 10
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.1+cu124
• Datasets 3.0.0
• Tokenizers 0.19.1