metadata

license: apache-2.0
base_model: alex-miller/ODABert
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: cva-quant-weighted-classifier
    results: []

cva-quant-weighted-classifier

This model is a fine-tuned version of alex-miller/ODABert on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2017
Accuracy: 0.9643
F1: 0.9630
Precision: 0.9286
Recall: 1.0

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: 1e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.6608	1.0	7	0.5726	0.7857	0.7857	0.7333	0.8462
0.5107	2.0	14	0.4116	0.8571	0.8462	0.8462	0.8462
0.35	3.0	21	0.3056	0.8929	0.8800	0.9167	0.8462
0.2166	4.0	28	0.2485	0.8571	0.8462	0.8462	0.8462
0.1356	5.0	35	0.1940	0.9286	0.9231	0.9231	0.9231
0.0705	6.0	42	0.1848	0.9286	0.9231	0.9231	0.9231
0.0491	7.0	49	0.1728	0.9643	0.9630	0.9286	1.0
0.0229	8.0	56	0.1725	0.9643	0.9630	0.9286	1.0
0.0129	9.0	63	0.1744	0.9643	0.9630	0.9286	1.0
0.0092	10.0	70	0.1793	0.9643	0.9630	0.9286	1.0
0.0075	11.0	77	0.1847	0.9643	0.9630	0.9286	1.0
0.0061	12.0	84	0.1890	0.9643	0.9630	0.9286	1.0
0.0058	13.0	91	0.1928	0.9643	0.9630	0.9286	1.0
0.0049	14.0	98	0.1954	0.9643	0.9630	0.9286	1.0
0.0045	15.0	105	0.1975	0.9643	0.9630	0.9286	1.0
0.0042	16.0	112	0.1990	0.9643	0.9630	0.9286	1.0
0.004	17.0	119	0.2001	0.9643	0.9630	0.9286	1.0
0.0038	18.0	126	0.2010	0.9643	0.9630	0.9286	1.0
0.0038	19.0	133	0.2015	0.9643	0.9630	0.9286	1.0
0.0038	20.0	140	0.2017	0.9643	0.9630	0.9286	1.0

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1