fine_tuned_cb_bert

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

• Loss: 4.2169
• Accuracy: 0.3636
• F1: 0.2430

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
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.7239	3.5714	50	1.2945	0.3182	0.1536
0.3879	7.1429	100	1.6236	0.4545	0.4158
0.1546	10.7143	150	3.1975	0.3636	0.2430
0.0741	14.2857	200	2.9703	0.4545	0.3895
0.0323	17.8571	250	3.8104	0.3636	0.2430
0.0073	21.4286	300	4.0583	0.3636	0.2430
0.0037	25.0	350	4.3166	0.3636	0.2430
0.0032	28.5714	400	4.2169	0.3636	0.2430

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0
• Datasets 2.19.0
• Tokenizers 0.19.1