SOMD-train-bert-v4

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: 256
• 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	1243	0.0044	0.7365
No log	2.0	2486	0.0026	0.7936
No log	3.0	3729	0.0016	0.8910
No log	4.0	4972	0.0010	0.9318
No log	5.0	6215	0.0006	0.9507
No log	6.0	7458	0.0006	0.9425
No log	7.0	8701	0.0004	0.9724
No log	8.0	9944	0.0002	0.9829
No log	9.0	11187	0.0002	0.9903
No log	10.0	12430	0.0002	0.9864
No log	11.0	13673	0.0002	0.9874
No log	12.0	14916	0.0001	0.9945
No log	13.0	16159	0.0001	0.9978
No log	14.0	17402	0.0000	0.9981
No log	15.0	18645	0.0000	0.9981
No log	16.0	19888	0.0000	0.9991
No log	17.0	21131	0.0000	0.9992
No log	18.0	22374	0.0000	1.0
No log	19.0	23617	0.0000	1.0
No log	20.0	24860	0.0000	1.0

Framework versions

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