bert-tomi

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: 0.4198

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	20	1.5815
No log	2.0	40	0.7518
No log	3.0	60	0.7153
No log	4.0	80	0.6354
No log	5.0	100	0.5895
No log	6.0	120	0.4882
No log	7.0	140	0.4590
No log	8.0	160	0.4303
No log	9.0	180	0.4644
No log	10.0	200	0.4416
No log	11.0	220	0.4348
No log	12.0	240	0.5306
No log	13.0	260	0.4412
No log	14.0	280	0.4053
No log	15.0	300	0.4185
No log	16.0	320	0.3982
No log	17.0	340	0.4291
No log	18.0	360	0.4316
No log	19.0	380	0.4328
No log	20.0	400	0.4198

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0
• Datasets 2.10.1
• Tokenizers 0.12.1