README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: IKT_classifier_netzero_best
    results: []

IKT_classifier_netzero_best

This model is a fine-tuned version of sentence-transformers/all-mpnet-base-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9526
• Precision Macro: 0.7813
• Precision Weighted: 0.8164
• Recall Macro: 0.7734
• Recall Weighted: 0.7812
• F1-score: 0.7644
• Accuracy: 0.7812

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: 9.588722322096848e-05
• train_batch_size: 3
• eval_batch_size: 3
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 400.0
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Precision Macro	Precision Weighted	Recall Macro	Recall Weighted	F1-score	Accuracy
No log	1.0	114	0.8267	0.8056	0.8151	0.6601	0.6875	0.6418	0.6875
No log	2.0	228	0.4916	0.8095	0.8371	0.8290	0.8125	0.8113	0.8125
No log	3.0	342	0.4784	0.8535	0.8920	0.8682	0.875	0.8569	0.875
No log	4.0	456	0.8909	0.7813	0.8164	0.7734	0.7812	0.7644	0.7812
0.6167	5.0	570	0.6673	0.8242	0.8650	0.8649	0.8125	0.8260	0.8125
0.6167	6.0	684	0.7110	0.8413	0.8795	0.8845	0.8438	0.8505	0.8438
0.6167	7.0	798	1.3731	0.7778	0.8281	0.7702	0.7188	0.7380	0.7188
0.6167	8.0	912	0.9526	0.7813	0.8164	0.7734	0.7812	0.7644	0.7812

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3