image_caption_git-base_pokemon-blip-captions_finetune

This model is a fine-tuned version of microsoft/git-base on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0382
• Wer Score: 2.2973

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Score
7.1973	4.17	50	4.4470	21.4968
2.3075	8.33	100	0.4412	10.5882
0.1359	12.5	150	0.0328	1.5792
0.0188	16.67	200	0.0293	1.1776
0.0068	20.83	250	0.0329	2.0798
0.0023	25.0	300	0.0354	2.6898
0.0014	29.17	350	0.0365	2.5650
0.0012	33.33	400	0.0374	2.4118
0.0011	37.5	450	0.0377	2.4080
0.001	41.67	500	0.0381	2.3745
0.0009	45.83	550	0.0382	2.2857
0.0009	50.0	600	0.0382	2.2973

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.0+cu117
• Datasets 2.12.0
• Tokenizers 0.13.3