latterworks's picture
End of training
11a8ea8 verified
|
raw
history blame
2.46 kB
metadata
library_name: transformers
license: apache-2.0
base_model: latterworks/highlightedreport-classifier-test
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: highlightedreport-classifier-test
    results: []

highlightedreport-classifier-test

This model is a fine-tuned version of latterworks/highlightedreport-classifier-test on the None dataset. It achieves the following results on the evaluation set:

  • Accuracy: 0.92
  • Loss: 0.2358
  • F1: 0.9184
  • Precision: 0.9
  • Recall: 0.9375

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: 1e-05
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Accuracy Validation Loss F1 Precision Recall
No log 1.25 10 0.92 0.2239 0.9184 0.9 0.9375
No log 2.5 20 0.92 0.2234 0.9184 0.9 0.9375
No log 3.75 30 0.92 0.2287 0.9184 0.9 0.9375
No log 5.0 40 0.93 0.2174 0.9278 0.9184 0.9375
No log 6.25 50 0.92 0.2321 0.9184 0.9 0.9375
No log 7.5 60 0.93 0.2208 0.9278 0.9184 0.9375
No log 8.75 70 0.92 0.2357 0.9184 0.9 0.9375
No log 10.0 80 0.92 0.2358 0.9184 0.9 0.9375

Framework versions

  • Transformers 4.48.3
  • Pytorch 2.6.0+cu124
  • Datasets 3.4.1
  • Tokenizers 0.21.1