Push distilbert-base-uncased trained on biored-original_splits.pt

03410d0 verified over 2 years ago

2.73 kB

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

Dagobert42/distilbert-base-uncased-biored-finetuned

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

Loss: 0.6976
Accuracy: 0.7703
Precision: 0.5335
Recall: 0.424
F1: 0.4652
Weighted F1: 0.7512

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	0.9181	0.7144	0.4183	0.1593	0.151	0.6108
No log	2.0	50	0.8580	0.7283	0.5273	0.2252	0.2508	0.6404
No log	3.0	75	0.8232	0.7369	0.5603	0.2769	0.3173	0.6638
No log	4.0	100	0.7814	0.7476	0.5184	0.3618	0.4085	0.7031
No log	5.0	125	0.7691	0.7507	0.5306	0.3929	0.4283	0.7173
No log	6.0	150	0.7492	0.7607	0.5494	0.3919	0.4396	0.7244
No log	7.0	175	0.7616	0.7622	0.5553	0.4048	0.4481	0.728
No log	8.0	200	0.7256	0.7657	0.5437	0.4306	0.4717	0.7426
No log	9.0	225	0.7413	0.7684	0.5565	0.4315	0.4739	0.7422
No log	10.0	250	0.7497	0.7721	0.5606	0.4364	0.4789	0.7446

Framework versions

Transformers 4.35.2
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.15.0