33333fwfwfw

This model is a fine-tuned version of joohwan/22221fwfwfw on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2379
• Cer: 0.1817

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: 0.0004
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 400
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0905	3.25	500	1.1914	0.2485
0.1354	6.49	1000	1.2372	0.2335
0.0981	9.74	1500	1.3565	0.2395
0.0827	12.99	2000	1.1879	0.2158
0.0626	16.23	2500	1.3100	0.2211
0.0517	19.48	3000	1.1448	0.1977
0.0382	22.73	3500	1.1920	0.1919
0.0291	25.97	4000	1.2770	0.1863
0.0217	29.22	4500	1.2379	0.1817

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3