medium-mlm-tweet

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: 3.3983

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: 32
• eval_batch_size: 32
• 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
3.1681	11.11	500	3.2485
2.6193	22.22	1000	3.2971
2.286	33.33	1500	3.5000
1.9916	44.44	2000	3.3983

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.7.1
• Tokenizers 0.13.2