metadata

tags:
  - generated_from_trainer
datasets:
  - null
metrics:
  - precision
  - recall
  - f1
  - accuracy
model_index:
  - name: electra-srb-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        metric:
          name: Accuracy
          type: accuracy
          value: 0.9509610737256943

electra-srb-ner

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

Loss: 0.2686
Precision: 0.8132
Recall: 0.7889
F1: 0.8009
Accuracy: 0.9510

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	0.2887	0.7392	0.6269	0.6784	0.9221
No log	2.0	414	0.2076	0.7690	0.7147	0.7409	0.9397
0.2949	3.0	621	0.2011	0.7698	0.7583	0.7640	0.9441
0.2949	4.0	828	0.2077	0.7600	0.7807	0.7702	0.9451
0.089	5.0	1035	0.2198	0.7884	0.7684	0.7783	0.9465
0.089	6.0	1242	0.2437	0.7885	0.7824	0.7854	0.9474
0.089	7.0	1449	0.2394	0.7986	0.7970	0.7978	0.9511
0.0322	8.0	1656	0.2675	0.8135	0.7775	0.7951	0.9497
0.0322	9.0	1863	0.2832	0.8161	0.7798	0.7975	0.9508
0.0141	10.0	2070	0.2686	0.8132	0.7889	0.8009	0.9510

Framework versions

Transformers 4.9.2
Pytorch 1.9.0
Datasets 1.11.0
Tokenizers 0.10.1