VF_BERT_ST_1800

This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2457
• Precision: 0.9489
• Recall: 0.9480
• F1: 0.9485
• Accuracy: 0.9405

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	30	0.4723	0.8973	0.9212	0.9091	0.8971
No log	2.0	60	0.3328	0.9146	0.9288	0.9217	0.9076
No log	3.0	90	0.3022	0.9316	0.9301	0.9308	0.9168
No log	4.0	120	0.2758	0.9207	0.9398	0.9301	0.9169
No log	5.0	150	0.2592	0.9392	0.9431	0.9411	0.9322
No log	6.0	180	0.2586	0.9445	0.9449	0.9447	0.9366
No log	7.0	210	0.2519	0.9476	0.9447	0.9461	0.9372
No log	8.0	240	0.2468	0.9464	0.9474	0.9469	0.9394
No log	9.0	270	0.2475	0.9486	0.9476	0.9481	0.9399
No log	10.0	300	0.2457	0.9489	0.9480	0.9485	0.9405

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1