README.md

metadata

language:
  - en
license: mit
base_model: mobilebert-uncased
tags:
  - low-resource NER
  - token_classification
  - biomedicine
  - medical NER
  - generated_from_trainer
datasets:
  - medicine
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: Dagobert42/mobilebert-uncased-biored-finetuned
    results: []

Dagobert42/mobilebert-uncased-biored-finetuned

This model is a fine-tuned version of mobilebert-uncased on the bigbio/biored dataset. It achieves the following results on the evaluation set:

• Loss: 0.7686
• Accuracy: 0.7387
• Precision: 0.2041
• Recall: 0.2219
• F1: 0.1908
• Weighted F1: 0.683

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: 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Weighted F1
No log	1.0	25	1.2311	0.7114	0.1016	0.1429	0.1188	0.5914
No log	2.0	50	1.0356	0.7114	0.1016	0.1429	0.1188	0.5914
No log	3.0	75	1.0300	0.7114	0.1016	0.1429	0.1188	0.5914
No log	4.0	100	1.0246	0.7114	0.1016	0.1429	0.1188	0.5914
No log	5.0	125	1.0162	0.7114	0.1016	0.1429	0.1188	0.5914
No log	6.0	150	1.0039	0.7114	0.1016	0.1429	0.1188	0.5914
No log	7.0	175	0.9806	0.7114	0.1016	0.1429	0.1188	0.5914
No log	8.0	200	0.9148	0.7114	0.1016	0.1429	0.1188	0.5914
No log	9.0	225	0.8715	0.7187	0.2116	0.1604	0.1484	0.6172
No log	10.0	250	0.8303	0.7261	0.1555	0.1972	0.1737	0.6508
No log	11.0	275	0.8216	0.7292	0.1572	0.2018	0.1764	0.6554
No log	12.0	300	0.8044	0.7299	0.2295	0.2081	0.1786	0.6605
No log	13.0	325	0.8108	0.732	0.2304	0.2091	0.1797	0.662
No log	14.0	350	0.7920	0.7306	0.2062	0.22	0.1877	0.6711
No log	15.0	375	0.8025	0.7332	0.2164	0.2153	0.1836	0.6674
No log	16.0	400	0.7937	0.7335	0.1982	0.2248	0.2039	0.6813

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.15.0