metadata

language: en
license: mit
base_model: google-bert/bert-large-uncased
tags:
  - token-classification
  - bert-large-uncased
datasets:
  - disham993/ElectricalNER
metrics:
  - epoch: 1
  - eval_precision: 0.9082058414464534
  - eval_recall: 0.928949656208014
  - eval_f1: 0.9184606368431334
  - eval_accuracy: 0.9632122370936902
  - eval_runtime: 2.7169
  - eval_samples_per_second: 555.414
  - eval_steps_per_second: 8.834

disham993/electrical-ner-bert-large

Model description

This model is fine-tuned from google-bert/bert-large-uncased for token-classification tasks.

Training Data

The model was trained on the disham993/ElectricalNER dataset.

Model Details

Base Model: google-bert/bert-large-uncased
Task: token-classification
Language: en
Dataset: disham993/ElectricalNER

Training procedure

Training hyperparameters

[Please add your training hyperparameters here]

Evaluation results

Metrics\n- epoch: 1.0\n- eval_precision: 0.9082058414464534\n- eval_recall: 0.928949656208014\n- eval_f1: 0.9184606368431334\n- eval_accuracy: 0.9632122370936902\n- eval_runtime: 2.7169\n- eval_samples_per_second: 555.414\n- eval_steps_per_second: 8.834

Usage

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("disham993/electrical-ner-bert-large")
model = AutoModel.from_pretrained("disham993/electrical-ner-bert-large")

Limitations and bias

[Add any known limitations or biases of the model]

Training Infrastructure

[Add details about training infrastructure used]

Last update

2024-12-30