base-model-with-warmup-fairseq-V1

This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.7695

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
15.5458	4.04	200	4.3505
3.9186	8.08	400	4.4677
3.7954	12.12	600	4.8597
3.8846	16.16	800	4.6803
3.7918	20.2	1000	4.6823
3.8406	24.24	1200	4.8027
3.7933	28.28	1400	4.7320
3.7851	32.32	1600	4.8768
3.7886	36.36	1800	4.7657
3.7775	40.4	2000	4.8205
3.8297	44.44	2200	4.7835
3.7944	48.48	2400	4.7695

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1
• Datasets 2.12.0
• Tokenizers 0.13.2