Model_G_P

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4719
• Wer: 0.5613
• Cer: 0.2386

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• 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: 500
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.447	4.17	400	2.1407	0.6004	0.2516
0.4338	8.33	800	2.1920	0.6033	0.2505
0.3209	12.5	1200	2.2978	0.6089	0.2601
0.2327	16.67	1600	2.3510	0.5871	0.2459
0.1735	20.83	2000	2.3828	0.5890	0.2480
0.1344	25.0	2400	2.3782	0.5647	0.2399
0.0909	29.17	2800	2.4719	0.5613	0.2386

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 1.18.3
• Tokenizers 0.13.3