autoevaluator's picture
Add evaluation results on the default config and test split of banking77
1972af6
|
raw
history blame
5.64 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - banking77
metrics:
  - f1
model-index:
  - name: test-bert-base-banking77
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: banking77
          type: banking77
          config: default
          split: test
          args: default
        metrics:
          - type: f1
            value: 0.9307471722060918
            name: F1
          - type: accuracy
            value: 0.9308441558441558
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTM0ZTdlMTEyZDdmYjlkMDYxNTBhZWZhM2RhNGU4ZTQ1M2FkYTA0ZWY0YTQ5NGI2ZGI3MzYxN2U4NzU4ZDQ4MyIsInZlcnNpb24iOjF9.t08jN9Qz_SSJgwdiGsppTTUFLSyRBkzCJt9CVdlSqc5h0rLnZgbVufOsnHI25Tm8-Rm3qB6T7SbX5ferq580BQ
          - type: f1
            value: 0.9307471722060919
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTc4YmJhN2NmMDVkZWFjNDYxZDkwNDVhOGYwNGU5MTBlN2IxNjI2ZDE0MjlmYjhjYmFjNTJjMDAyNWIwOTgwOCIsInZlcnNpb24iOjF9.fqkSUE1FVWpktTMPGaK6ZzaxFMwLe9iNxnLK17IcrPy0Z-qmBUTdVWh0EWR6q0D9nLKU8R473dnjXRZItC7jAg
          - type: f1
            value: 0.9308441558441558
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWMzOWYyYWYxNzQyZjQzMmEzNGJjNGEyZjA1ODIzZWZjYjg5NTZlZjg3OWRlM2ZmMmQ3MTRhMmM4MzY2OGI4MCIsInZlcnNpb24iOjF9.mj4Aq3ghwmSF6PRNjWE0LZExreSXnUTHZH439Oli07aTQ88fneWEQGJPpQdcF3QbU4qZkza3AuZafnp22N1dAQ
          - type: f1
            value: 0.9307471722060918
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDU1ZWE5ZGQ0NDZjNzgwMDViNTA1NTljNjcwN2I0ZTJhYzU5NTI3NGM5MTVhMTI3NzZlOWM4YTJmMWU2Y2U2MSIsInZlcnNpb24iOjF9.AqnMi5aFj3TUVhRFYov4mxIf8UDZen_mM-zckwhJknZMSCdIMV7mCAr7jdf6sITfxboRMbRRkEw3YwTM-HBNAw
          - type: precision
            value: 0.9341498488099387
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODc0N2I4MGZjNGZiYTBiNjNjODg5NTRlMjY4ZDA5N2Y0NzhiOWQ5ZTY0OWQxNzQzMmJmMTA5ZTc5YWM3Mjg0YyIsInZlcnNpb24iOjF9.XkgYp66UTQWgRanoiBx-2RDklSkxvq_rbq35peSV0oNcumnM9O6FPGg7CxG3eFXqmVu6vUSoEds1a-h8JY6EAg
          - type: precision
            value: 0.9308441558441558
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDQxZmFlNjBjYjI4ZGZmNzQyYzA3M2YwZWEzNmFjOTExNjIwYmU1YzQxMjMxYTg4OWJlMTUyODc1MzIxMTI1ZCIsInZlcnNpb24iOjF9.vMoc6hUWTARBt8lswWhRlB7VRgh63HvndvWvLrsx0KgsLwf5P7l2v7YI4VzKQuaExHPYKP4dQqyQsPwaK6nrCw
          - type: precision
            value: 0.9341498488099383
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzFmOWZmN2U1MmViYWU3OWY2YThhYWU5Yzg0MzBjMTlmNTljNjQ0ODUzY2RkNzQzNzFhODM5MjkzMjM5YjczMSIsInZlcnNpb24iOjF9.OMGuEPM69TbMV_kCP2Pc9tPvgxqrPZhcTeAlN6sGHNYE8ABp6FDNI4KhJkLjPGlRkxHQa0LGuDLyaF3ZQoZiAg
          - type: recall
            value: 0.9308441558441556
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjY2NGRjYzM4YzNlMWQ5NzdkOTM2MGNjZmM1ODgzODVkN2JhZTRkODE1ZjVkNWZhM2ViMjIwMmYzNGZiZjcyOSIsInZlcnNpb24iOjF9.zU_VwdZ6gtDnw_hU8d1n4PZPM9spKjNxfyvKbuMjLhazeGQdKL1MHO-iE6Azf-oKUFW-EYknFQtfUOb3yf0tCQ
          - type: recall
            value: 0.9308441558441558
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDEyOWFlODk1OGMwZjliNjEzZmU5MjFhY2Y0MzhlZjc1ZGQxN2M2OTNlOGVlOTUyMTg0Yzc3ZDZhOWY4NTU5ZSIsInZlcnNpb24iOjF9.8adEXv-AFcZt9l_iLz8y8lnV5NhjwCjquJFDXxzVSPCAaTY3A4pY_bizCcuJRYJ1vSn9r1FuWMF-i3IcXYeaBQ
          - type: recall
            value: 0.9308441558441558
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTNmYzZiZjE5Y2VkYmYwNzA2YmQyYjA1YjZmZjgzNmQ3MzE5MzFlY2JkMjMxZmMyZGNmODM5NTNjN2FlZGJiNCIsInZlcnNpb24iOjF9.Vp-bJw2wu7L28mmmyBonppxeKzt6gGrYBdKGcODERO-K6W7irBDvN52pbzi7e8ZiOBvKFOcw_zbkNWacT9xsCw
          - type: loss
            value: 0.2827721834182739
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNThiYzMzYzVmMTIzZDU3ZTM4NzRmOGE5OTk5MzJmYTYwY2Y5ZjRjNzZmNzhkZWZjMzlmZDRiM2MyMWMyZjg3NiIsInZlcnNpb24iOjF9._BHTKVFr7-_nULYWfZjt6L36cBAwi_l86o1ldEt8mIgrdApsrp74dvASQp3aITgyg7Tv5XDnuMBRWOCGqTxQCQ

test-bert-base-banking77

This model is a fine-tuned version of bert-base-uncased on the banking77 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2828
  • F1: 0.9307

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss F1
1.0786 1.0 626 0.7667 0.8429
0.3836 2.0 1252 0.3487 0.9223
0.1855 3.0 1878 0.2828 0.9307

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1
  • Datasets 2.14.2
  • Tokenizers 0.13.2