SOMD-bert-3stage-stage1-v1

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: 0.0000
• F1: 1.0

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: 32
• eval_batch_size: 32
• 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	F1
No log	1.0	74	0.0259	0.9047
No log	2.0	148	0.0059	0.9759
No log	3.0	222	0.0020	0.9921
No log	4.0	296	0.0009	0.9972
No log	5.0	370	0.0004	0.9988
No log	6.0	444	0.0003	0.9986
No log	7.0	518	0.0001	1.0
No log	8.0	592	0.0001	0.9995
No log	9.0	666	0.0001	0.9997
No log	10.0	740	0.0000	1.0
No log	11.0	814	0.0001	0.9998
No log	12.0	888	0.0001	0.9995
No log	13.0	962	0.0001	0.9998
No log	14.0	1036	0.0000	1.0
No log	15.0	1110	0.0000	1.0
No log	16.0	1184	0.0001	0.9997
No log	17.0	1258	0.0000	1.0
No log	18.0	1332	0.0000	1.0
No log	19.0	1406	0.0000	1.0
No log	20.0	1480	0.0000	1.0

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.1