metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
base_model: google/electra-base-discriminator
model-index:
  - name: electra-base-discriminator-ner-food-combined-v2
    results: []

electra-base-discriminator-ner-food-combined-v2

This model is a fine-tuned version of google/electra-base-discriminator on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1277
Precision: 0.8006
Recall: 0.8959
F1: 0.8456
Accuracy: 0.9685

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: 5e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.45	400	0.1279	0.7429	0.8888	0.8093	0.9603
0.2005	0.9	800	0.1306	0.8145	0.8901	0.8506	0.9704
0.1305	1.35	1200	0.1197	0.7847	0.8951	0.8363	0.9667
0.1143	1.8	1600	0.1118	0.7876	0.8922	0.8366	0.9661
0.1169	2.25	2000	0.1125	0.7724	0.8959	0.8296	0.9647
0.1169	2.7	2400	0.1167	0.7964	0.8922	0.8415	0.9674
0.1007	3.15	2800	0.1222	0.8170	0.8905	0.8522	0.9708
0.1008	3.6	3200	0.1164	0.7732	0.8913	0.8281	0.9640
0.0973	4.04	3600	0.1190	0.8093	0.8993	0.8519	0.9697
0.0948	4.49	4000	0.1221	0.7977	0.8947	0.8434	0.9676
0.0948	4.94	4400	0.1220	0.8009	0.8993	0.8472	0.9684
0.0857	5.39	4800	0.1292	0.8085	0.8963	0.8501	0.9694
0.0845	5.84	5200	0.1318	0.8236	0.8943	0.8575	0.9710
0.0877	6.29	5600	0.1246	0.7940	0.8972	0.8425	0.9674
0.0825	6.74	6000	0.1277	0.8006	0.8959	0.8456	0.9685

Framework versions

Transformers 4.27.4
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3