metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - tweet_eval
metrics:
  - precision
  - recall
model-index:
  - name: bert-emotion
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: tweet_eval
          type: tweet_eval
          args: emotion
        metrics:
          - type: precision
            value: 0.7262254187805659
            name: Precision
          - type: recall
            value: 0.725549671319356
            name: Recall
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: tweet_eval
          type: tweet_eval
          config: emotion
          split: test
        metrics:
          - type: accuracy
            value: 0.7825475017593244
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTZhOTE5NjRlODcxNzEzMGUzNTllMWFlNjRkNzRmNTRmYmU1YjU2MDE1YWIyZDcwYTdjZGI0MjIxMDQ2OTgwMCIsInZlcnNpb24iOjF9.3D-oFO-DjRIHTob3DtWsu_hsLNted2Av5eZLg8LoCYIi_9oAcymIikHcSS4Hr-cDmpF4C7DsmaH3HPYdN-MJCw
          - type: f1
            value: 0.7373078325463487
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDEwMTAyOWQ4ZjA0MGVhODFhODE3OGViNWU2MDM5YmM0ODNmMTVmYWE0Mjc4ZTI0YzE4NzIwODU1YWI4YWY1YSIsInZlcnNpb24iOjF9.CuhYKHUD7nI0Fcrh9ogQWqkM4iwvcdHoG1Xoi1fdcn7aD5CyVevqPKO4hxIzxpBcxaSaVFlkAa_rJzpB0pKqDw
          - type: f1
            value: 0.7825475017593244
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWM1ODA3ZDJhYTJhMGJkYmU1ODYyZDNhMTM4ZTY3YmIwNjlhOGZiNDdlMWU2ZTg5MzgwYWM5YjA1OTAyZDA0NSIsInZlcnNpb24iOjF9.092oASK0jrq4j-pgNwXOCmKpR0s57T2aAIJepLJnFUd7wie3bmoT7MqlrALqGifrYe-t8UlSHdmSGNUrWfIFBA
          - type: f1
            value: 0.7800585587569513
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmU4MTIyMGI1YjNlNmJhNTQ1MDdjZjVjOGNiNWVkZjk4NmRiZDczNDIwOWYyZWI4MTExNmQwZWY3NGU3N2RjYiIsInZlcnNpb24iOjF9.LqDQwwJoDAt4wTQmGWv5sZfZjFLTr2dBG6LtIXwA7m4SsOER6GKg1L1RmlkHRrHgTxBrMgF9WbSQOCdOJXByCg
          - type: precision
            value: 0.757828822693908
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTM1Yzg2ODY0ZTU0ZWJjODg1YjI4OGZkMDc3ZDMwZWY5ZTBhMDY4NDFmMTgxMmJiNDJjMGIyNWQ4YzFmZWVhYyIsInZlcnNpb24iOjF9.xbsTcqN3-vDUtoXd7by8F96pAfAel6aenJ5Vz5UvIxQmlI88orIg5DkrT_MIl8LOcIZkF9TFhz5RJGytnZNGBw
          - type: precision
            value: 0.7825475017593244
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjM1ZjVlYjk1NWM0NzgyZTAxMTU3OWY3ZjBlYTJlZjcxMzViYzVjM2IzZDM4M2ZlZTA0MmZkYzFhMTAxMWViYSIsInZlcnNpb24iOjF9._hUo-MVxie-qEfO0QUKdJVwMV0dOoxkyGptEQoW7gx1r05p5FAFPt3vmuU9JjJlxhDaw-0seKooh39HU-7xyBw
          - type: precision
            value: 0.7817085293090495
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWM0MWE0MmRiNzczMDY5YzdlOTZiY2Q2OWU5NWQ4MTA1M2U2YWMxZTlmZmIxYzg3MTgzNDgxZWUxNmJjYjdhNyIsInZlcnNpb24iOjF9.W7DlBHfESzF3lYrf4Buurq4Fxx1_YOzAEspsdkZr93H1Ih-DRRQaDZbk8KCrQOJaI83XzHfL_6XaQ_SyH3qpAg
          - type: recall
            value: 0.7268372321658545
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDFiY2QxOGUxZDlkNGQ1NTM5ODljZjExZWM3ZGI0Y2YyN2E4NmU0Y2M0NWZiOGJjZTBmNGM2MWVmNzNiZWM3NCIsInZlcnNpb24iOjF9.Hig3mlWTnWSAKHouNistpgzwB5smK2piaUtf6AfeJEhUS-tUQYEbxQsK6Np_E799bCe-yi7bU_M9NZW8qAAcDg
          - type: recall
            value: 0.7825475017593244
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGUzMjc4YTczYmFhZTI4ZTcwOTc1NmYwYWExMzFiOGIzOTBhNmQ2ZGNmZDc3NDljNDY0N2UwOGZlMGJhNmRlOSIsInZlcnNpb24iOjF9.ljZ9Wsn-942EqvfOVpAO6ZnWTHUdp0CbOMEGgJNeanXkk1jVL4rc7MQ6SSupEF_9jW2apl7no68CII__UUeiAw
          - type: recall
            value: 0.7825475017593244
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTIxZmQwMWNlOTljYjBhMzBjZTRjODFjODAxNWMwOTAyYWRhNWVjZTkxZDJjOTUxNzg4YjMxMDQ1MDFkNWMwMiIsInZlcnNpb24iOjF9.Q8V3qy0CLGZuWOAp5WE4eOGJT12zeDO0CRZByGtx2KyU8ikcQ_TZ1WVlUQgFVnWoiqqmkfsIEtyQBl6axEE5BQ
          - type: loss
            value: 0.8246609568595886
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGQzZTk4YzM3OTI0MGUxYmY1YTU5YjUzOWIzMGVlN2Q1NTdjZmNhZjAxZGVmNTg3MTAyYzg3ODI1MmU3ZWM5ZSIsInZlcnNpb24iOjF9.feU19daDdE7OKkcop-Vq42FV2bZnHYVgBzsq6RM-823fZjdlgNZCWHFaEec2PF_HxIAnFDqsH6fJ7a1VhmTFCA

bert-emotion

This model is a fine-tuned version of distilbert-base-cased on the tweet_eval dataset. It achieves the following results on the evaluation set:

Loss: 1.1670
Precision: 0.7262
Recall: 0.7255
Fscore: 0.7253

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: 4
eval_batch_size: 4
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	Precision	Recall	Fscore
0.8561	1.0	815	0.7844	0.7575	0.6081	0.6253
0.5337	2.0	1630	0.9080	0.7567	0.7236	0.7325
0.2573	3.0	2445	1.1670	0.7262	0.7255	0.7253

Framework versions

Transformers 4.19.2
Pytorch 1.11.0+cu113
Datasets 2.2.2
Tokenizers 0.12.1