testing_pretrained_tamasheq_only_FE

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

• Loss: 1.8742
• Wer: 0.8333
• Cer: 0.3145

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: 3e-05
• 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: 350

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
6.3383	35.29	300	2.9420	1.0	1.0
2.8426	70.59	600	2.7381	1.0	1.0
2.7564	105.88	900	2.7200	1.0	1.0
2.5802	141.18	1200	1.9677	1.0	0.7640
1.556	176.47	1500	1.4901	0.8481	0.3166
0.9319	211.76	1800	1.6803	0.8481	0.3067
0.7365	247.06	2100	1.7447	0.8481	0.3110
0.6363	282.35	2400	1.8439	0.8370	0.3110
0.5882	317.65	2700	1.8742	0.8333	0.3145

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3