Vishveshwara's picture
Vishveshwara/NER-Contract
5a687dc verified
metadata
license: mit
library_name: peft
tags:
  - generated_from_trainer
base_model: roberta-large
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-large-token-classification
    results: []

bert-large-token-classification

This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2157
  • Precision: 0.4271
  • Recall: 0.5155
  • F1: 0.4671
  • Accuracy: 0.9481

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: 0.001
  • 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: 5

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.3642 1.0 741 0.2888 0.2211 0.2315 0.2262 0.9264
0.2508 2.0 1482 0.2862 0.3301 0.3645 0.3465 0.9217
0.1609 3.0 2223 0.2247 0.3109 0.4309 0.3612 0.9411
0.1404 4.0 2964 0.2391 0.3563 0.4669 0.4042 0.9303
0.0937 5.0 3705 0.2157 0.4271 0.5155 0.4671 0.9481

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.2
  • Pytorch 2.1.2
  • Datasets 2.19.2
  • Tokenizers 0.19.1