bart-with-asr-noise-sub-0.4

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

• Loss: 0.0985

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.3216	0.62	500	0.2307
0.1661	1.24	1000	0.1390
0.0787	1.86	1500	0.1089
0.0304	2.48	2000	0.0985

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.2+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2