Mit1208/Florence-2-large-DocLayNet

<!-- 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. -->

Florence-2-large-DocLayNet

This model is a fine-tuned version of microsoft/Florence-2-large on the doclaynet-small dataset. It achieves the following results on the evaluation set:

• —eval_loss: 1.4130
• —eval_runtime: 10.2586
• —evalsamplesper_second: 4.776
• —evalstepsper_second: 2.437
• —epoch: 5.0
• —step: 3440

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: 1e-06
• —trainbatchsize: 1
• —evalbatchsize: 2
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 10

Framework versions

• —Transformers 4.42.4
• —Pytorch 2.2.1+cu121
• —Datasets 2.19.2
• —Tokenizers 0.19.1