distilbert-base-uncased-mlm-ta-local

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

• Loss: 2.0658

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.4431	1.0	3125	2.1817
2.2197	2.0	6250	2.0929
2.1519	3.0	9375	2.0696

Framework versions

• Transformers 4.17.0
• Pytorch 1.10.1
• Datasets 2.0.0
• Tokenizers 0.11.6