fineturning-with-pretraining

This model is a fine-tuned version of Aviral2412/mini_model on the common_voice_1_0 dataset. It achieves the following results on the evaluation set:

• Loss: 2.3739
• Wer: 1.0011

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: 16
• 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: 500
• num_epochs: 25
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.3381	2.15	500	2.5389	1.0011
2.4622	4.29	1000	2.4761	1.0011
2.4477	6.44	1500	2.5567	1.0011
2.4325	8.58	2000	2.4334	1.0011
2.4205	10.73	2500	2.4067	1.0011
2.3995	12.88	3000	2.3828	1.0011
2.3869	15.02	3500	2.3752	1.0011
2.3857	17.17	4000	2.3759	1.0011
2.3717	19.31	4500	2.3684	1.0011
2.3625	21.46	5000	2.3601	1.0011
2.3648	23.61	5500	2.3739	1.0011

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2