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: 0.8095238095238095
          - name: Recall
            type: recall
            value: 0.9066666666666666
          - name: F1
            type: f1
            value: 0.8553459119496856
          - name: Accuracy
            type: accuracy
            value: 0.8926553672316384

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: 0.4675
Precision: 0.8095
Recall: 0.9067
F1: 0.8553
Accuracy: 0.8927

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	1.9550	0.0	0.0	0.0	0.4294
No log	2.0	14	1.7431	0.0	0.0	0.0	0.4407
No log	3.0	21	1.5315	0.2632	0.0667	0.1064	0.5198
No log	4.0	28	1.3289	0.5490	0.3733	0.4444	0.6215
No log	5.0	35	1.1498	0.5246	0.4267	0.4706	0.6497
No log	6.0	42	1.0278	0.5921	0.6	0.5960	0.7175
No log	7.0	49	0.8915	0.6579	0.6667	0.6623	0.7684
No log	8.0	56	0.8158	0.6786	0.76	0.7170	0.8023
No log	9.0	63	0.7012	0.7342	0.7733	0.7532	0.8249
No log	10.0	70	0.6421	0.7590	0.84	0.7975	0.8475
No log	11.0	77	0.5944	0.8025	0.8667	0.8333	0.8757
No log	12.0	84	0.5570	0.7976	0.8933	0.8428	0.8870
No log	13.0	91	0.5088	0.8148	0.88	0.8462	0.8927
No log	14.0	98	0.5156	0.8193	0.9067	0.8608	0.8983
No log	15.0	105	0.4958	0.8171	0.8933	0.8535	0.8927
No log	16.0	112	0.4646	0.8171	0.8933	0.8535	0.8927
No log	17.0	119	0.4745	0.8095	0.9067	0.8553	0.8927
No log	18.0	126	0.4749	0.8095	0.9067	0.8553	0.8927
No log	19.0	133	0.4720	0.8095	0.9067	0.8553	0.8927
No log	20.0	140	0.4675	0.8095	0.9067	0.8553	0.8927

Framework versions

Transformers 4.39.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2