Instructions to use dtorber/bert-base-cased_K4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dtorber/bert-base-cased_K4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="dtorber/bert-base-cased_K4")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("dtorber/bert-base-cased_K4") model = AutoModelForSequenceClassification.from_pretrained("dtorber/bert-base-cased_K4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from dtorber/bert-base-cased_K4: direct link, hf CLI and curl.
- Browser
- Download file 1.36 kB
-
https://huggingface.co/dtorber/bert-base-cased_K4/resolve/5d4bcb3c908bcd395fe3cfea53d7bd678ee57504/README.md
- Command line
-
hf download hf://dtorber/bert-base-cased_K4@5d4bcb3c908bcd395fe3cfea53d7bd678ee57504/README.md
-
curl -L -o README.md https://huggingface.co/dtorber/bert-base-cased_K4/resolve/5d4bcb3c908bcd395fe3cfea53d7bd678ee57504/README.md
1.36 kB
metadata
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
metrics:
- f1
- recall
model-index:
- name: bert-base-cased_K4
results: []
bert-base-cased_K4
This model is a fine-tuned version of google-bert/bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4212
- F1 Macro: 0.8770
- F1: 0.9170
- F1 Neg: 0.8370
- Acc: 0.89
- Prec: 0.9067
- Recall: 0.9275
- Mcc: 0.7545
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2