bert_finetune_onearticle_microbiology

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

• Loss: nan

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: 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: 10000
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	1.0	1401	nan
0.0	2.0	2802	nan
6.1704	3.0	4203	nan
5.7235	4.0	5604	nan
0.0	5.0	7005	nan
5.8892	6.0	8406	nan
6.2034	7.0	9807	nan
6.0771	8.0	11208	nan
5.0591	9.0	12609	nan
5.4144	10.0	14010	nan
0.0	11.0	15411	nan
0.0	12.0	16812	nan
0.0	13.0	18213	nan
5.2497	14.0	19614	nan
5.3274	15.0	21015	nan
0.0	16.0	22416	nan
3.1963	17.0	23817	nan
0.0	18.0	25218	nan
5.9954	19.0	26619	nan
0.0	20.0	28020	nan

Framework versions

• Transformers 4.34.1
• Pytorch 2.0.0+cu117
• Datasets 2.14.5
• Tokenizers 0.14.1