metadata

license: apache-2.0
base_model: distilbert-base-cased
tags:
  - generated_from_trainer
datasets:
  - shipping_label_ner
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: ner_bert_model
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: shipping_label_ner
          type: shipping_label_ner
          config: shipping_label_ner
          split: validation
          args: shipping_label_ner
        metrics:
          - name: Precision
            type: precision
            value: 0.5178571428571429
          - name: Recall
            type: recall
            value: 0.7837837837837838
          - name: F1
            type: f1
            value: 0.6236559139784947
          - name: Accuracy
            type: accuracy
            value: 0.7796610169491526

ner_bert_model

This model is a fine-tuned version of distilbert-base-cased on the shipping_label_ner dataset. It achieves the following results on the evaluation set:

Loss: 0.7118
Precision: 0.5179
Recall: 0.7838
F1: 0.6237
Accuracy: 0.7797

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: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	7	1.8106	0.0	0.0	0.0	0.5169
No log	2.0	14	1.6175	0.5556	0.1351	0.2174	0.5932
No log	3.0	21	1.3124	0.6	0.2432	0.3462	0.6441
No log	4.0	28	1.1318	0.6471	0.5946	0.6197	0.8051
No log	5.0	35	0.9306	0.6176	0.5676	0.5915	0.7881
No log	6.0	42	0.8279	0.5476	0.6216	0.5823	0.7712
No log	7.0	49	0.7609	0.5952	0.6757	0.6329	0.7881
No log	8.0	56	0.7484	0.6327	0.8378	0.7209	0.8220
No log	9.0	63	0.7035	0.6596	0.8378	0.7381	0.8220
No log	10.0	70	0.7281	0.5741	0.8378	0.6813	0.7881
No log	11.0	77	0.6970	0.5741	0.8378	0.6813	0.7881
No log	12.0	84	0.6790	0.5	0.7568	0.6022	0.7881
No log	13.0	91	0.7124	0.4828	0.7568	0.5895	0.7712
No log	14.0	98	0.6770	0.5	0.7568	0.6022	0.7797
No log	15.0	105	0.7219	0.5179	0.7838	0.6237	0.7797
No log	16.0	112	0.6695	0.5273	0.7838	0.6304	0.7881
No log	17.0	119	0.6885	0.5179	0.7838	0.6237	0.7797
No log	18.0	126	0.7138	0.5088	0.7838	0.6170	0.7712
No log	19.0	133	0.7113	0.5179	0.7838	0.6237	0.7797
No log	20.0	140	0.7118	0.5179	0.7838	0.6237	0.7797

Framework versions

Transformers 4.39.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2