metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-medical-ner
    results: []

bert-medical-ner

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4000
Precision: 0.7565
Recall: 0.6791
F1: 0.7157
Accuracy: 0.9405

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: 64
eval_batch_size: 64
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	Precision	Recall	F1	Accuracy
No log	1.0	63	0.4610	0.6626	0.3672	0.4726	0.9098
No log	2.0	126	0.3464	0.6908	0.5113	0.5877	0.9245
No log	3.0	189	0.3237	0.6658	0.5898	0.6255	0.9268
No log	4.0	252	0.3029	0.6965	0.6147	0.6531	0.9322
No log	5.0	315	0.3327	0.7542	0.6102	0.6746	0.9341
No log	6.0	378	0.3239	0.7371	0.6305	0.6797	0.9364
No log	7.0	441	0.3318	0.6975	0.6825	0.6899	0.9353
0.2658	8.0	504	0.3478	0.7440	0.6667	0.7032	0.9380
0.2658	9.0	567	0.3835	0.7536	0.6548	0.7007	0.9381
0.2658	10.0	630	0.3662	0.7455	0.6718	0.7067	0.9389
0.2658	11.0	693	0.3732	0.7394	0.6588	0.6967	0.9388
0.2658	12.0	756	0.3739	0.7505	0.6695	0.7077	0.9403
0.2658	13.0	819	0.3884	0.7513	0.6655	0.7058	0.9397
0.2658	14.0	882	0.3955	0.7609	0.6616	0.7078	0.9398
0.2658	15.0	945	0.3986	0.7689	0.6599	0.7102	0.9401
0.0369	16.0	1008	0.3975	0.7633	0.6723	0.7149	0.9408
0.0369	17.0	1071	0.3955	0.7437	0.6819	0.7115	0.9401
0.0369	18.0	1134	0.3968	0.7555	0.6808	0.7162	0.9408
0.0369	19.0	1197	0.3999	0.7527	0.6791	0.7140	0.9405
0.0369	20.0	1260	0.4000	0.7565	0.6791	0.7157	0.9405

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.13.3