distilbert-base-uncased-becas-1

This model is a fine-tuned version of distilbert-base-uncased on the becasv2 dataset. It achieves the following results on the evaluation set:

• Loss: 3.8655

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: 2e-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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	5	5.4379
No log	2.0	10	4.9216
No log	3.0	15	4.5533
No log	4.0	20	4.2022
No log	5.0	25	3.9714
No log	6.0	30	3.8209
No log	7.0	35	3.7916
No log	8.0	40	3.7497
No log	9.0	45	3.8372
No log	10.0	50	3.8655

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1