bert-small-mlm-finetuned-emotion

This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.7413

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: 3e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss
2.8418	22.73	500	2.7035
2.5706	45.45	1000	2.6968
2.4199	68.18	1500	2.6595
2.2901	90.91	2000	2.7323
2.1793	113.64	2500	2.7560
2.0651	136.36	3000	2.7413

Framework versions

• Transformers 4.25.0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2