README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-sla
    results: []

bert-finetuned-sla

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: 0.2965
• F1: 0.7121
• Roc Auc: 0.8162
• Accuracy: 0.5098

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: 4
• eval_batch_size: 4
• 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	Roc Auc	Accuracy
No log	1.0	30	0.5013	0.1842	0.5497	0.0784
No log	2.0	60	0.4369	0.15	0.5337	0.0784
No log	3.0	90	0.3724	0.5794	0.7141	0.4118
No log	4.0	120	0.3463	0.6560	0.7738	0.4314
No log	5.0	150	0.3212	0.6452	0.7664	0.4314
No log	6.0	180	0.3092	0.6190	0.7539	0.4510
No log	7.0	210	0.3096	0.6772	0.7885	0.4902
No log	8.0	240	0.3025	0.6870	0.7997	0.4706
No log	9.0	270	0.3118	0.6875	0.7958	0.4902
No log	10.0	300	0.2965	0.7121	0.8162	0.5098
No log	11.0	330	0.2971	0.7023	0.8088	0.4902
No log	12.0	360	0.3071	0.6866	0.8036	0.4510
No log	13.0	390	0.3015	0.6718	0.7907	0.4510
No log	14.0	420	0.3087	0.6718	0.7907	0.4314
No log	15.0	450	0.2978	0.6970	0.8071	0.4706
No log	16.0	480	0.3058	0.6718	0.7907	0.4510
0.219	17.0	510	0.3039	0.6769	0.7924	0.4510
0.219	18.0	540	0.3015	0.6870	0.7997	0.4706
0.219	19.0	570	0.3011	0.6870	0.7997	0.4706
0.219	20.0	600	0.3014	0.6870	0.7997	0.4706

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2