metadata

tags:
  - generated_from_trainer
datasets:
  - null
metrics:
  - precision
  - recall
  - f1
  - accuracy
model_index:
  - name: electra-srb-ner-setimes
    results:
      - task:
          name: Token Classification
          type: token-classification
        metric:
          name: Accuracy
          type: accuracy
          value: 0.951370041268543

electra-srb-ner-setimes

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2619
Precision: 0.8157
Recall: 0.7934
F1: 0.8044
Accuracy: 0.9514

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: 16
eval_batch_size: 8
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	207	0.2845	0.7431	0.6314	0.6827	0.9225
No log	2.0	414	0.2082	0.7766	0.7134	0.7436	0.9396
0.2949	3.0	621	0.1992	0.7699	0.7596	0.7647	0.9439
0.2949	4.0	828	0.2044	0.7485	0.7908	0.7691	0.9456
0.0896	5.0	1035	0.2129	0.7827	0.7778	0.7802	0.9476
0.0896	6.0	1242	0.2330	0.7893	0.7882	0.7887	0.9485
0.0896	7.0	1449	0.2337	0.8026	0.7947	0.7986	0.9504
0.0334	8.0	1656	0.2579	0.8111	0.7850	0.7978	0.9503
0.0334	9.0	1863	0.2792	0.8263	0.7830	0.8041	0.9510
0.0152	10.0	2070	0.2619	0.8157	0.7934	0.8044	0.9514

Framework versions

Transformers 4.9.2
Pytorch 1.9.0
Datasets 1.11.0
Tokenizers 0.10.1