tiny-mlm-tweet

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.5627

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
4.832	11.11	500	4.4717
4.3993	22.22	1000	4.3088
4.2588	33.33	1500	4.4458
4.1304	44.44	2000	4.2552
4.0193	55.56	2500	4.4867
3.9369	66.67	3000	4.3410
3.8675	77.78	3500	4.5627

Framework versions

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