Hugging Face's logo

Flamenco43
/
MatSciBERT800abstractsNER

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
MatSciBERT800abstractsNER / README.md
Flamenco43's picture
Flamenco43
End of training
3744bbb verified
preview code
|
raw
history blame contribute delete
11 kB
metadata
license: mit
base_model: m3rg-iitd/matscibert
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: MatSciBERT800abstractsNER
    results: []

MatSciBERT800abstractsNER

This model is a fine-tuned version of m3rg-iitd/matscibert on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1791
  • Precision: 0.8328
  • Recall: 0.8789
  • F1: 0.8552
  • Accuracy: 0.9475
  • Per Tag Metrics: {'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9997280021759826}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9878507638605558}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9960560315517476}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9966000271997824}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9955120359037127}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9975066866131738}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.996010698581078}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9945600435196519}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9957840337277302}, 'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9951493721383562}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9928373906342083}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.998730676821252}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.96432295208305}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9967360261117911}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9876240990072079}}

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 0.2243 0.7438 0.8398 0.7889 0.9267 {'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9990026746452695}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.984994786708373}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9942427127249649}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9946960424316605}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9949227072850084}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9961466974930867}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9953760369917041}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9910240718074256}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9943787116369736}, 'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9946053764903214}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.986672106623147}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9976426855251824}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9507230608821796}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9953307040210345}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9835441316469469}}
No log 2.0 442 0.1870 0.8015 0.8596 0.8295 0.9400 {'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9994560043519651}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9868987714764949}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9959200326397388}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9958293666983997}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9956933677863911}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9967813590824607}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9955573688743823}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9936080511355909}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9951040391676866}, 'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9951493721383562}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9898454145700167}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9984586789972347}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9597896550160933}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9961920304637563}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9857654472097557}}
0.2883 3.0 663 0.1792 0.8267 0.8782 0.8517 0.9464 {'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.999682669205313}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9878054308898863}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9962373634344258}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9961466974930867}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9955120359037127}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9973253547304954}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9958746996690693}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9941973797542953}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9955573688743823}, 'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9953307040210345}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9922480620155039}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9986400108799129}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.964640282877737}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9965093612584432}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9871254363298427}}
0.2883 4.0 884 0.1791 0.8328 0.8789 0.8552 0.9475 {'I-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9997280021759826}, 'I-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9878507638605558}, 'B-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9960560315517476}, 'I-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9966000271997824}, 'I-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9955120359037127}, 'B-CMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9975066866131738}, 'I-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.996010698581078}, 'B-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9945600435196519}, 'I-MAT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9957840337277302}, 'I-SMT': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9951493721383562}, 'B-DSC': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9928373906342083}, 'B-SPL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.998730676821252}, 'O': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.96432295208305}, 'B-APL': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9967360261117911}, 'B-PRO': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'accuracy': 0.9876240990072079}}

Framework versions

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