mms-1b-all-archimob-100

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

• Loss: 4.6713
• Wer: 1.0

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: 0.001
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.0	3	6.4551	1.3270
No log	2.0	6	3.6504	0.9937
No log	3.0	9	4.8854	1.0
No log	4.0	12	4.6713	1.0

Framework versions

• Transformers 4.38.2
• Pytorch 1.10.0a0+0aef44c
• Datasets 2.18.0
• Tokenizers 0.15.2