metadata

license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - anno_ctr
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: annoctr_bert_uncased
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: anno_ctr
          type: anno_ctr
          config: all_tags
          split: test
          args: all_tags
        metrics:
          - name: Precision
            type: precision
            value: 0.7928388746803069
          - name: Recall
            type: recall
            value: 0.7809920945182869
          - name: F1
            type: f1
            value: 0.7868708971553611
          - name: Accuracy
            type: accuracy
            value: 0.936522196415268

annoctr_bert_uncased

This model is a fine-tuned version of bert-base-uncased on the anno_ctr dataset. It achieves the following results on the evaluation set:

Loss: 0.3322
Precision: 0.7928
Recall: 0.7810
F1: 0.7869
Accuracy: 0.9365

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.54	1.0	474	0.3452	0.6983	0.6601	0.6786	0.9137
0.3013	2.0	948	0.3466	0.7774	0.7018	0.7376	0.9240
0.0392	3.0	1422	0.3071	0.7851	0.7517	0.7680	0.9303
0.5695	4.0	1896	0.2941	0.7810	0.7617	0.7712	0.9334
0.0021	5.0	2370	0.3109	0.7928	0.7720	0.7823	0.9351
0.0419	6.0	2844	0.3020	0.7772	0.7796	0.7784	0.9341
0.2979	7.0	3318	0.3169	0.8019	0.7814	0.7915	0.9374
0.0017	8.0	3792	0.3260	0.7972	0.7778	0.7874	0.9365
0.0166	9.0	4266	0.3349	0.7935	0.7789	0.7861	0.9364
0.0685	10.0	4740	0.3322	0.7928	0.7810	0.7869	0.9365

Framework versions

Transformers 4.40.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1