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: 0.8193
- Recall: 0.9067
- F1: 0.8608
- Accuracy: 0.9040
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: 30
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 7 | 1.9567 | 0.0 | 0.0 | 0.0 | 0.4294 |
No log | 2.0 | 14 | 1.7382 | 1.0 | 0.0133 | 0.0263 | 0.4350 |
No log | 3.0 | 21 | 1.5156 | 0.56 | 0.1867 | 0.28 | 0.5424 |
No log | 4.0 | 28 | 1.3070 | 0.5185 | 0.3733 | 0.4341 | 0.6215 |
No log | 5.0 | 35 | 1.1073 | 0.6792 | 0.48 | 0.5625 | 0.6667 |
No log | 6.0 | 42 | 0.9590 | 0.6970 | 0.6133 | 0.6525 | 0.7288 |
No log | 7.0 | 49 | 0.8036 | 0.7324 | 0.6933 | 0.7123 | 0.7853 |
No log | 8.0 | 56 | 0.7173 | 0.6860 | 0.7867 | 0.7329 | 0.8305 |
No log | 9.0 | 63 | 0.5963 | 0.7778 | 0.84 | 0.8077 | 0.8814 |
No log | 10.0 | 70 | 0.5354 | 0.7901 | 0.8533 | 0.8205 | 0.8870 |
No log | 11.0 | 77 | 0.5048 | 0.8 | 0.8533 | 0.8258 | 0.8814 |
No log | 12.0 | 84 | 0.4992 | 0.8293 | 0.9067 | 0.8662 | 0.9096 |
No log | 13.0 | 91 | 0.4745 | 0.8205 | 0.8533 | 0.8366 | 0.8927 |
No log | 14.0 | 98 | 0.4489 | 0.8608 | 0.9067 | 0.8831 | 0.9153 |
No log | 15.0 | 105 | 0.4236 | 0.8608 | 0.9067 | 0.8831 | 0.9153 |
No log | 16.0 | 112 | 0.4621 | 0.8193 | 0.9067 | 0.8608 | 0.9096 |
No log | 17.0 | 119 | 0.4417 | 0.85 | 0.9067 | 0.8774 | 0.9209 |
No log | 18.0 | 126 | 0.4642 | 0.8095 | 0.9067 | 0.8553 | 0.9040 |
No log | 19.0 | 133 | 0.4244 | 0.85 | 0.9067 | 0.8774 | 0.9096 |
No log | 20.0 | 140 | 0.4731 | 0.8193 | 0.9067 | 0.8608 | 0.9096 |
No log | 21.0 | 147 | 0.4697 | 0.8193 | 0.9067 | 0.8608 | 0.9040 |
No log | 22.0 | 154 | 0.4330 | 0.8293 | 0.9067 | 0.8662 | 0.9096 |
No log | 23.0 | 161 | 0.4531 | 0.8193 | 0.9067 | 0.8608 | 0.9040 |
No log | 24.0 | 168 | 0.4433 | 0.8193 | 0.9067 | 0.8608 | 0.9040 |
No log | 25.0 | 175 | 0.4477 | 0.8095 | 0.9067 | 0.8553 | 0.9040 |
No log | 26.0 | 182 | 0.4446 | 0.8293 | 0.9067 | 0.8662 | 0.9096 |
No log | 27.0 | 189 | 0.4578 | 0.8293 | 0.9067 | 0.8662 | 0.9096 |
No log | 28.0 | 196 | 0.4640 | 0.8293 | 0.9067 | 0.8662 | 0.9096 |
No log | 29.0 | 203 | 0.4683 | 0.8193 | 0.9067 | 0.8608 | 0.9040 |
No log | 30.0 | 210 | 0.4675 | 0.8193 | 0.9067 | 0.8608 | 0.9040 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for harsh13333/ner_bert_model
Base model
distilbert/distilbert-base-casedEvaluation results
- Precision on shipping_label_nervalidation set self-reported0.819
- Recall on shipping_label_nervalidation set self-reported0.907
- F1 on shipping_label_nervalidation set self-reported0.861
- Accuracy on shipping_label_nervalidation set self-reported0.904