bert-base-uncased-coffee20230113

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.9112

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	86	4.5257
5.3762	2.0	172	3.1774
3.2552	3.0	258	2.7228
2.227	4.0	344	2.5844
1.6128	5.0	430	2.8589
1.098	6.0	516	2.8712
0.7646	7.0	602	3.4380
0.7646	8.0	688	3.6037
0.4805	9.0	774	4.1493
0.3258	10.0	860	4.2875
0.2224	11.0	946	4.7041
0.1477	12.0	1032	4.3993
0.0699	13.0	1118	4.7922
0.0377	14.0	1204	5.0445
0.0377	15.0	1290	4.9112

Framework versions

• Transformers 4.25.1
• Pytorch 1.11.0+cu113
• Datasets 2.8.0
• Tokenizers 0.13.2