ahmed792002's picture
Upload tokenizer
a18a1ee verified
metadata
base_model: bert-base-uncased
library_name: transformers
license: apache-2.0
metrics:
  - accuracy
  - f1
tags:
  - generated_from_trainer
model-index:
  - name: Finetuning_Bert_ClinicalNotes_Diagnosis_Classification
    results: []

Finetuning_Bert_ClinicalNotes_Diagnosis_Classification

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0028
  • Accuracy: 1.0
  • F1: 1.0

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
  • 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 Accuracy F1
No log 1.0 438 0.0226 1.0 1.0
0.6724 2.0 876 0.0069 1.0 1.0
0.0134 3.0 1314 0.0041 1.0 1.0
0.0062 4.0 1752 0.0031 1.0 1.0
0.0044 5.0 2190 0.0028 1.0 1.0

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.19.1