README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - accuracy
  - f1
model-index:
  - name: bertweet-base-finetuned-emotion
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          args: default
        metrics:
          - type: accuracy
            value: 0.929
            name: Accuracy
          - type: f1
            value: 0.9295613935787139
            name: F1
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: test
        metrics:
          - type: accuracy
            value: 0.925
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZThkYWEwYTdjY2IwMmE4NmM2Mzc3ZTVkNTNmNWYwNGUxYTM5ZDA5ODEwMGQ1ZGU0ZmJmY2U1ZDhjYWRlZjU2NSIsInZlcnNpb24iOjF9.QJYOUR_EPrYzbZGBb1N27BSlTQIdvd1hmUfnfPJdTGGrNoQwXBUA4amVsWh1txV_YtO8hcCx-b3pTqzpdy1FAw
          - type: precision
            value: 0.8722017563353339
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Y3ZGM2NDk5ZTQyNTNjZDdmNjk5Y2IwNzkxNmU3MDM0YTljMTJjMzFmMTlkN2ZjN2NhZjNhYTVlMWY5NWFjNCIsInZlcnNpb24iOjF9.cBYScC_c6g1ECi3rj6HiRI3AMuoxg8wp7JKha0UKh1Q2qjzTr5ml8JAByPL0iu-Ix5BO2Bsx0fZNFhUS82LiCg
          - type: precision
            value: 0.925
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjVjYjgwYjE2ZWUyM2Y5MzE0ODk4NDA5MGM2ODIxYTgxZDYyMTUxNzcwZWQ2MjZjZGYwODkyNzFkMjAxOTUzYyIsInZlcnNpb24iOjF9.phgA4BJcqp4ZUhecNeuGU8OAf6f_asN9Mf6JfFGd0cPORYltd_N4Wf6EXqu6z1ADqWeeibteEyIUwmmMEbjYBQ
          - type: precision
            value: 0.9283646705517916
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjE4MDUyYjU4YTc4Mzk4YmIwMGIzZWEyYmU5ZDQ0MjRhZDQ4OGMwZjVmZmEyNDM5NzYyZTMzMTJiMmRkZTU4NiIsInZlcnNpb24iOjF9.LbYjoga-JSCzHZAF1fhm1CfuaSSI-ok0yXj3gtd4QTWY1TjzOHoMG3Q6zEGz84l6ASoHsvi9wjS7_EaSQLB4Dw
          - type: recall
            value: 0.8982480793145559
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzFiY2JmYWRhYmE1YzA1MmRhODI0MGE1NTRiMWE3YmNjZWQ4OGExMDg3NmUzYmUzYTYyNTdkNjM1Y2M0ODJmMCIsInZlcnNpb24iOjF9.dAq2gloG0O-4z5Ng7RZkFO7e0og3wBQBmIDzic6onwjw83yaHPVfRd1e0j6mNhMUifOwPLEavnYkBYa9DVFqCw
          - type: recall
            value: 0.925
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjg5Y2M2NWIwZmI4YjEyMmIzYjNjZmQyMzhlYjg2ZDRmY2U1M2I1NzQzYjRmMzYxYzJkNTI5MDJjMmY5ZDVmNyIsInZlcnNpb24iOjF9.Z5hmQBUsoKAgqTXk47aUDNKf5jJ0mXzY9TAgM9vG8I3pgCT465PEfM-TOKfG_YcPMLd3tkB8AdwDpmVnNj5QCw
          - type: recall
            value: 0.925
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODIzMjY1YjgzYzAwNjk2NGI1ZjFhZTg4MGY1Mzg5NDhkM2EzY2JlMWM4MjZmNjg4ZmEyZDJmZTUwNDFkZmNiOCIsInZlcnNpb24iOjF9.S-9p04Lru9WTzm50mM5qGM4oA-TPgNw6uwxKr5AejU1iPKjyTDQvoumBs41T5OKL5zN_NyYXsFsCermSbirLAw
          - type: f1
            value: 0.883488774573809
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGMyMjc3NTkxNDNjNTJiNmRmMTA4NzY0MTgyMDc3ZDE4N2RlMTY1YzU4OGQ1YmM1NzY2OGQ4Y2I0MzVhOGU3OSIsInZlcnNpb24iOjF9.D65sLHNZGjp15ra4i5ccYyOX705Xq-hftZjDb6kqE5X-jhzA5VLev6FirhnhyYLBQmA6Q9T1eDYHKkVZG4CcBg
          - type: f1
            value: 0.925
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTNkMmUwNjYxNGE4M2E2MDA0NTI4ZjA1OTNkMWEwN2MzY2JmMWYxYThiYTZmM2MwZjM5YTIzMGIzMGI4ODJlZSIsInZlcnNpb24iOjF9.cB4WUQN_weyKdMZehH0ECaTcD9Jl1xzmrOzJZz27OJeCPjY0uW8O63HnJZ_LmBF2xqd7HDypT4s8hZBMT-6eDw
          - type: f1
            value: 0.9259820821054494
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTY3NDhjNmMzYzM1MjIyY2FkYjI5YTQ1NTdmODhmMGVlNjc2ZjQ3MWZmZWEyMDQ1OGI1NDllZTBhM2VjYzg2MSIsInZlcnNpb24iOjF9.Akd8PVgc2tyin_TaOZV1bio_b00g3QmlHA-GWV3rMX13B1imDLuPAuP-HWIwgqg-umQUkJzcUQlTqbcQ06v0DQ
          - type: loss
            value: 0.18158096075057983
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDZhODkzODQ2ZjYyMWQxYjEzNzRmMmQ0NjM3M2RiNDdlMTcwOGRhYjA0NWEwYTVjMmY0ZWY3NGQ3MzFhMTQ3ZSIsInZlcnNpb24iOjF9.jzv7qMmQuFmrsR3WoRAsCbrRJhNk0sfEcN07lCqhxUwYcO4rblVbBiePQtr0IDN067PbQmV6ES6W2cjHqvuHAA

bertweet-base-finetuned-emotion

This model is a fine-tuned version of vinai/bertweet-base on the emotion dataset. It achieves the following results on the evaluation set:

• Loss: 0.1737
• Accuracy: 0.929
• F1: 0.9296

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.9469	1.0	250	0.3643	0.895	0.8921
0.2807	2.0	500	0.2173	0.9245	0.9252
0.1749	3.0	750	0.1859	0.926	0.9266
0.1355	4.0	1000	0.1737	0.929	0.9296

Framework versions

• Transformers 4.13.0
• Pytorch 1.11.0+cu113
• Datasets 1.16.1
• Tokenizers 0.10.3