Hugging Face's logo

Flamenco43
/
bert_800-abstracts_NER

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
bert_800-abstracts_NER / README.md
Flamenco43's picture
Flamenco43
End of training
236916a verified
preview code
|
raw
history blame contribute delete
11 kB
metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert_800-abstracts_NER
    results: []

bert_800-abstracts_NER

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

  • Loss: 0.2237
  • Precision: 0.7742
  • Recall: 0.8411
  • F1: 0.8063
  • Accuracy: 0.9326
  • Per Tag Metrics: {'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9947855794300099}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9965387035871618}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9979322125325901}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9936168299919087}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9905151487907938}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9960891845725074}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9938865414007012}, 'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9994156252809494}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9571608379034433}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9826485660343433}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9966286073900926}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9933920704845814}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9840870268812371}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9959093769666457}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9925379843567383}}

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy Per Tag Metrics
No log 1.0 221 0.3104 0.6677 0.7690 0.7148 0.9032 {'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9922682729479457}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9951002427402679}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9965387035871618}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9910096197069136}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9846714016002877}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9946956756270791}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9921783691450148}, 'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9993706733794839}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9413827204890767}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.975231502292547}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9944709161197519}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9913242830171717}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9791423177200396}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9936617818933741}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9853906320237346}}
No log 2.0 442 0.2425 0.7502 0.7993 0.7739 0.9224 {'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9941113009080285}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9962240402769037}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9972129821091432}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9883125056189876}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9872336599838173}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9952800503461297}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9934819742875124}, 'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9993706733794839}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9508675716982828}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9819742875123618}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9962240402769037}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.993032455272858}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9837723635709791}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9958194731637148}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9919086577362223}}
0.4237 3.0 663 0.2237 0.7666 0.8362 0.7999 0.9301 {'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9946057718241481}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9962240402769037}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9976625011237975}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9933021666816506}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9899307740717432}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9955497617549223}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9935718780904432}, 'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9993706733794839}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9560370403668075}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9823788546255506}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9964487997842308}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9928975995684618}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9842218825856334}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9959543288681111}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9920435134406186}}
0.4237 4.0 884 0.2237 0.7742 0.8411 0.8063 0.9326 {'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9947855794300099}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9965387035871618}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9979322125325901}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9936168299919087}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9905151487907938}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9960891845725074}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9938865414007012}, 'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9994156252809494}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9571608379034433}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9826485660343433}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9966286073900926}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9933920704845814}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9840870268812371}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9959093769666457}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9925379843567383}}

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.2.1+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1