This model is a fine-tuned version of distilbert-base-uncased on the shipping_label_ner dataset.
It achieves the following results on the evaluation set:
eval_loss: 0.0550
eval_precision: 0.9286
eval_recall: 0.9630
eval_f1: 0.9455
eval_accuracy: 0.9904
eval_runtime: 0.046
eval_samples_per_second: 108.697
eval_steps_per_second: 21.739
epoch: 55.0
step: 110
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: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
