1

This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: nan
• F1: 0.0032

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss	F1
9.5074	0.18	10	nan	0.0060
8.5442	0.37	20	nan	0.0102
6.6803	0.55	30	nan	0.0
7.1123	0.73	40	nan	0.0040
9.1525	0.92	50	nan	0.0044
7.3704	1.1	60	nan	0.0
6.0446	1.28	70	nan	0.0
6.8367	1.47	80	nan	0.0
6.3409	1.65	90	nan	0.0144
7.3165	1.83	100	nan	0.0
6.2659	2.02	110	nan	0.0
5.7613	2.2	120	nan	0.0
6.3813	2.39	130	nan	0.0044
6.977	2.57	140	nan	0.0102
6.1388	2.75	150	nan	0.0063
8.3673	2.94	160	nan	0.0013
6.9132	3.12	170	nan	0.0059
7.4859	3.3	180	nan	0.0
6.5924	3.49	190	nan	0.0061
6.3331	3.67	200	nan	0.0032

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1