EngTig's picture
Update README.md
c6923d7 verified
metadata
license: mit
base_model: romainlhardy/roberta-large-finetuned-ner
tags:
  - generated_from_trainer
model-index:
  - name: roberta-large-finetuned-ner-finetuned-ner
    results: []
datasets:
  - surrey-nlp/PLOD-filtered

roberta-large-finetuned-ner-finetuned-ner

This model is a fine-tuned version of romainlhardy/roberta-large-finetuned-ner on surrey-nlp/PLOD-filtered dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.1264
  • eval_precision: 0.9593
  • eval_recall: 0.9473
  • eval_f1: 0.9533
  • eval_accuracy: 0.9488
  • eval_runtime: 588.3236
  • eval_samples_per_second: 41.032
  • eval_steps_per_second: 10.258
  • epoch: 0.59
  • step: 16493

label description

['B-O', 'B-AC', 'I-AC', 'B-LF', 'I-LF']

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: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2