bert-medium-mlm-finetuned-emotion

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

• Loss: 2.6285

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
2.6294	22.73	500	2.5331
2.3406	45.45	1000	2.5577
2.1686	68.18	1500	2.5537
2.0196	90.91	2000	2.6285

Framework versions

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