metadata
library_name: transformers
base_model: IVN-RIN/bioBIT
tags:
- token-classification
- generated_from_trainer
datasets:
- Rodrigo1771/drugtemist-it-fasttext-8-ner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: output
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: Rodrigo1771/drugtemist-it-fasttext-8-ner
type: Rodrigo1771/drugtemist-it-fasttext-8-ner
config: DrugTEMIST Italian NER
split: validation
args: DrugTEMIST Italian NER
metrics:
- name: Precision
type: precision
value: 0.9162702188392008
- name: Recall
type: recall
value: 0.9322362052274927
- name: F1
type: f1
value: 0.9241842610364683
- name: Accuracy
type: accuracy
value: 0.9987276032199429
output
This model is a fine-tuned version of IVN-RIN/bioBIT on the Rodrigo1771/drugtemist-it-fasttext-8-ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0064
- Precision: 0.9163
- Recall: 0.9322
- F1: 0.9242
- Accuracy: 0.9987
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-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 470 | 0.0044 | 0.9108 | 0.8993 | 0.9050 | 0.9985 |
0.0122 | 2.0 | 940 | 0.0051 | 0.9050 | 0.8848 | 0.8948 | 0.9984 |
0.0032 | 3.0 | 1410 | 0.0049 | 0.9144 | 0.8993 | 0.9068 | 0.9985 |
0.0017 | 4.0 | 1880 | 0.0060 | 0.9213 | 0.9177 | 0.9195 | 0.9986 |
0.0011 | 5.0 | 2350 | 0.0071 | 0.9280 | 0.8858 | 0.9064 | 0.9985 |
0.0007 | 6.0 | 2820 | 0.0060 | 0.9078 | 0.9245 | 0.9161 | 0.9986 |
0.0005 | 7.0 | 3290 | 0.0059 | 0.9260 | 0.9206 | 0.9233 | 0.9988 |
0.0004 | 8.0 | 3760 | 0.0064 | 0.9163 | 0.9322 | 0.9242 | 0.9987 |
0.0002 | 9.0 | 4230 | 0.0067 | 0.9177 | 0.9284 | 0.9230 | 0.9986 |
0.0001 | 10.0 | 4700 | 0.0069 | 0.9152 | 0.9303 | 0.9227 | 0.9987 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1