ec_classfication_0502_bert_base_uncased

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

• Loss: 1.0262
• F1: 0.8132

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	59	0.5865	0.7238
No log	2.0	118	0.4017	0.8302
No log	3.0	177	0.4968	0.8182
No log	4.0	236	0.7651	0.7595
No log	5.0	295	0.6250	0.8276
No log	6.0	354	0.8580	0.7907
No log	7.0	413	0.8241	0.8182
No log	8.0	472	0.8875	0.8261
0.193	9.0	531	0.9314	0.8182
0.193	10.0	590	0.9188	0.8352
0.193	11.0	649	0.9721	0.8409
0.193	12.0	708	0.9929	0.8409
0.193	13.0	767	1.0092	0.8222
0.193	14.0	826	1.0261	0.8132
0.193	15.0	885	1.0262	0.8132

Framework versions

• Transformers 4.27.3
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.2