Hugging Face's logo

morenolq
/
distilbert-base-cased-emotion

Text Classification
Transformers
PyTorch
Safetensors
English
distilbert
Generated from Trainer
emotion
Eval Results
Inference Endpoints
Model card Files Community
5
distilbert-base-cased-emotion / README.md
morenolq's picture
morenolq
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#3)
31b8760
preview code
|
raw
history blame
12.1 kB
metadata
language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
  - text-classification
  - emotion
  - pytorch
datasets:
  - emotion
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: distilbert-base-cased-emotion
    results:
      - task:
          type: text-classification
          name: text-classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: validation
        metrics:
          - type: accuracy
            value: 0.9235
            name: accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTI0NGY1MTgwMzViYzY2NzdmOTk2NGM0YjRjMDExYjRkNDY3YmQzZmY4Y2JlMGQ3ZThlNjNjMjQ1OTI4MjdlOSIsInZlcnNpb24iOjF9.jJ8RC2HTtWrq3_b592HIFBlKuGavgSMrp--gwLFLZ66Uuz44gnouotoYpsqMtgUt-S3lkcCUs2ZFOPo6xR2EAA
          - type: accuracy
            value: 0.938
            name: Accuracy
            verified: true
          - type: precision
            value: 0.9281100797474869
            name: Precision Macro
            verified: true
          - type: precision
            value: 0.938
            name: Precision Micro
            verified: true
          - type: precision
            value: 0.9376891512759605
            name: Precision Weighted
            verified: true
          - type: recall
            value: 0.9029821552608664
            name: Recall Macro
            verified: true
          - type: recall
            value: 0.938
            name: Recall Micro
            verified: true
          - type: recall
            value: 0.938
            name: Recall Weighted
            verified: true
          - type: f1
            value: 0.9147207975135915
            name: F1 Macro
            verified: true
          - type: f1
            value: 0.938
            name: F1 Micro
            verified: true
          - type: f1
            value: 0.9373403463117288
            name: F1 Weighted
            verified: true
          - type: loss
            value: 0.23682540655136108
            name: loss
            verified: true
          - type: accuracy
            value: 0.938
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTUwM2MxN2Q0MGY2MjM5N2IyNjM1Y2Q5ZTM3YzRjYzU1NWQ3MGM1M2E2OWY5YTYyOGVjNTRmODc2ZDkxYzRlMyIsInZlcnNpb24iOjF9.vUgzbI8tmXYBL4OmW3y9GJx_J_j_o6hs1fmxgc-SgaF7B6Qr0qxVwTahvxKnJjad8KnA-aEfQWRYhwVpAr44Dw
          - type: precision
            value: 0.9281100797474869
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjQ1Mzg5NmI2MjU0MjA1N2EzNmQ1MGVhYjgyYTg5YmVjMGY5ZDhkMmJmNmVhZDI0ZDNmZDJhZjg0NDUzNzEzMiIsInZlcnNpb24iOjF9.kK_Lg1Vy1dXCSzEik-0vfP15icUf1RNYNs_dcXc46PAXU1TWF1t4CKUXmu6FFyRyAWKMp90dH_Ss7VIMj1-OAw
          - type: precision
            value: 0.938
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTdiNWE1ZmFmYmE3NDc0YmUyYjRiNGZmMDk5NTg5YWUyOTQyYmNkOWM3M2Y4ZjI4ZWU3Mzk2NTU1YjQxM2QzMiIsInZlcnNpb24iOjF9.9UVnzkkjthoZML84FS8cWbr88JPgG2RQtC7k_I4a3rCC0T6LMsJSoMWCOIz6a6tnpO26q-_x-wM70GzzSanmCg
          - type: precision
            value: 0.9376891512759605
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTU2ZDVjYjk5YTMwYWY2YmZjNDdkMTFkMWI5NjI3YjQ3Njk2NWQ0OGM2ZjYyZWRhZjE2YzM5YjA3NjU1YmFlNiIsInZlcnNpb24iOjF9.fixCk6zcIOYsk3LgfCHeSQ5YNoJ-ZWxvvW76g1-s2yjrI5Qmf_VQcNlyDr_pmHtZ7mc3yykCPaD6k2oMKZ5QBw
          - type: recall
            value: 0.9029821552608664
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjA0NTc4MGExMmExNWZjNjc1MDA3MDI4MmMwMTNjYWQ0YmVkZjExNzdkZTJkNmMwZWIyNjA4MTNlMDRmODkwNiIsInZlcnNpb24iOjF9.rAq4wFgCo6Q3mxElGdnbXlzVyUvSYOFW-m1KHzDFTydt-4Re-SUVjeh2y8HFf5H0Te5Jj5SiXfszJUmwFXh1Ag
          - type: recall
            value: 0.938
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDk4NTE4YjZmZDdlNmI1NDkxYmU4ZjAzODhiNGFhYTAxNGEyNjY2MGE3MWQwNGFkMDhkZjNkYjkzNWQxZDQ1YiIsInZlcnNpb24iOjF9.l2JP6XY0XWRFB6G5A82CQy9-Isn48vAGickkwvhMhcW7cZsPjDTLHg2wyBjD8etcYzU99RdfR9nusSnWxBvxAQ
          - type: recall
            value: 0.938
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTEwNGQ0NDc0NWE2OGUzMjkwMWM2MGRhODViNmIwMDU1NDk3OTdlOWI1N2VlN2JmY2MzYWI4YjJhNDFhYWVhNCIsInZlcnNpb24iOjF9.IV35Ctc1lhxXGP5J3PQxWi6IpWH1ZyZ95yrrca6-EzlF0w3AYL1Bk8q_glolpmrBqUBrJH8AJ07MFN3g77UzCA
          - type: f1
            value: 0.9147207975135915
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDFlNDk2OWUxOWQ5MTY1MTg3MDU2MzA5OGVmYTk2ODgyNDRiNWU5ZDZmYWYzYmMyMTcyZGExMWE1MGQ2Mzk2MyIsInZlcnNpb24iOjF9.GdxhM7wmt4DQucMB21z0ZZx-iOSlf7wYIs01U6dERhXHX4gsDaFIuIFCVNPFZpwerUYUz6Xtsl6jK1v9kkjqBA
          - type: f1
            value: 0.938
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTFlM2JlYWFhZjQzNGVjNjhhMTQ3MWZlNGFlMDI5YjEyYWQzMmY3MzQ4MmEzYzg0ZjIyZTZlODNmMTRlZWI5OSIsInZlcnNpb24iOjF9.EKJExY6JPzTwnnPzBPTCoDTowYYly6jKw4Qypsj3GKEpzwmqG-hoo5yhyZaoWsRL2hb1W6eHbsZtPdy1HqGLDQ
          - type: f1
            value: 0.9373403463117288
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzU1MjI3NTc4N2MxYTI5MjI1OTc3YjFhYjdkZDZmY2MxOTkyYzMzMWIxY2JmNGRkNDg2MTk0YTRiOWJhMTBhNCIsInZlcnNpb24iOjF9.bqFLqztywdiWTm-r7oeQ_R3_VKOTBkyxbL_sZktEE3hsJHYhwLOEVeKD7sqt56gQu_JNYMCz6WGWKRECFKH3Cw
          - type: loss
            value: 0.23682540655136108
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWZlZjkwNmJjYjAzYzk4ZjU4NzNiYzg1NTU1MGQ3OTFjYmE4MjE5NzNkYzZiZDI0ZmNkM2Y2NGU4ZjJlOThlOSIsInZlcnNpb24iOjF9.mYcz4sdJOmXXMBGW01OSJiKCouKh28AuExj1E7JiPCz-9ri3oRXPkT2fBHgrf0I2ifVEGVSFYckoC8Ymg-cMAw
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: test
        metrics:
          - type: accuracy
            value: 0.9235
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDdiOWE5ZjI4NmVjN2Y0OWFmNGI2NWU4MTYwMTA5MTFmMjEzOTkyODhhOTEzMzg0OTJmOTM2NGM3YzMxMDAyNCIsInZlcnNpb24iOjF9.SzWJe5bMitRlUb4d0gIX49k_mTC1ADWKDOLdS6TMx3ZGmkMdD6F9-IlmmTunbfVEDQSjweVpv7H7TUcHsBeIBQ
          - type: precision
            value: 0.89608475565062
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjZlMjk2ZTZkNzJiZTgwNDczNzRjMDkzYTcwNmM2YjdjODE1NzI2NTFmNjRkYTBjMDg2NzMzNmE0MGY1NWRiYyIsInZlcnNpb24iOjF9.qlIfR61-QTw9M71mMGOjN2UPs3Pjz-DVtq094BFtVkFQVllN5vPZLkkqVTkQlX1WdnY70JHpYv-qM_Kpv1h3Cw
          - type: precision
            value: 0.9235
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjUwMDIwMGEwMmE2NmEzMjQxMjM5MWI5MDRlYjhmODE1NjliMjkwMTU5YTg3ZWJiMjI2MGQxMWU4MmJiYTljNiIsInZlcnNpb24iOjF9.rFJQ1Q6aPlncwReXR2jciz3UEIArJS_nTwHAuTNXZKKQSvTM1zBN7x7EdSDeEIf8JDFfEimvv282wgnCPVmkAw
          - type: precision
            value: 0.9224273416855945
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDNmYWE4MTQxY2FkNTcxMzMyMmQyNmViN2FhMGQxOWYzNGU0MmIyMjhiZmE5ZmYyOWQwMzExZWRiMjRkNzliMyIsInZlcnNpb24iOjF9.6kD-hmPbjJrpAHZY-tFULnufxw118PfMCwj8PBjDKTtSQ_MCTP7iU3KtNe5essy5vDpdBFuA9E9SbrtjW3vnBA
          - type: recall
            value: 0.8581097243584549
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjZjMGJlZmI2NGVmYWIxZjdlYzg1ZjAyNmYwOWQ0NGE2OWI5OGIzMzE5Zjg5Yzg2NTlhZjRkMzE0ZTZjOGUyMCIsInZlcnNpb24iOjF9._r5lQK7hSPCyM9Bz9H5AVactjXzpF3hKW-iB5dco_kmVMhdy_-N00aFQg8XMKa4sL9lmJs0svINUwL5q55vmCw
          - type: recall
            value: 0.9235
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTQyMmZiNDQ1ZDMyZGY5ZWVlOGM0OWMzODhiNWI1NGUzNDJmOWEyM2VjYjhkNGQ4Y2ZmYzMwYjc1NTU4YjY0ZCIsInZlcnNpb24iOjF9.N7SJCOKlRa_3sRFYqiuPZpXmikQ9xuA4uDsKldGVNG6Tg6dffT2fLE9kkTCOQmG3BQzoP-xxjbhjG1gDPe_KCw
          - type: recall
            value: 0.9235
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGZkZmU4OTRhNDc3MzdiMDQwYzg4NmI5MTNlOWNjODk1ZGNmODZmZjk2MmY2NmU1Y2QyNGExNTkyNDUyZWJhYyIsInZlcnNpb24iOjF9.SvIJpc0dCvtMeaRZ0yQinV3FKftMiHLbhvalrVDT0uLnQ-wGL3HOkj9i9lO53kLrunxbswPjhKmR4bY1P6LUCQ
          - type: f1
            value: 0.8746813002250796
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDcxMTE4YzIyOWM5YmU0YTI4NzliMjM5YzBkYTJjODY3NjdkOWMwNmJhOTJiY2Y3MDM4NDNkYjljOGMxN2I2YyIsInZlcnNpb24iOjF9.41XMqnkXPjeoKiUmOuMhitX-624vXLmz6QMeNsOx_yFDhkugYP5ox5xq9PhC3cQIxn0SD71AusaN7YOnfKOaDA
          - type: f1
            value: 0.9235
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjE0MDU4YjY4MzlkMjQyZmI3ODUwODUyYzIyMDFhNjIyZjcwZjNkZTI0NmFiYTA4YWJlMzdmNDMxZGY0MTVhZCIsInZlcnNpb24iOjF9.a1Nh5T-g74Ol-ElZhu2O7yg4tJrBRGCJYeVYUsZd7AkXPR_e0jyOwVx16J2t7gOVTp512HEK5u2wIpns8qWrAA
          - type: f1
            value: 0.9217456925724525
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2YyODE0NjIzOGI4OTExYTlhMTUxNzBkZWE5ZGIzZTNkOThjZTRiYmM5NDEzYjZlYTY2MzY1ZmVkY2IyZDA4MyIsInZlcnNpb24iOjF9.XEhuUaY3E5FwXunSiRNMW_Rnu9B176mu7wr8jXvISdPovno1ANhliK276GeLgS_suAjjpPQPTwMK-ntJ9PHuCA
          - type: loss
            value: 0.32714536786079407
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDdhOTRiNjI5Y2FmYmQ0MGNmNjM5NWQzN2Y0ZWJhNmYyZDgwYzRhOWE0YmNiMjIyNjYyMWE2NTczMTA3NDM1YiIsInZlcnNpb24iOjF9.tmWAsH0fU7QUztbh3PfbBL1aSigZge0iQgYQIHsULZMCD9M98l8DXeLpZl-dehWruVY9Lkr4PJKTn9ba35vKCg

distilbert-base-cased-emotion

Training: The model has been trained using the script provided in the following repository https://github.com/MorenoLaQuatra/transformers-tasks-templates

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

  • Loss: 0.3272
  • Accuracy: 0.9235
  • F1: 0.9217
  • Precision: 0.9224
  • Recall: 0.9235

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.2776 1.0 500 0.2954 0.9 0.8957 0.9031 0.9
0.1887 2.0 1000 0.1716 0.934 0.9344 0.9370 0.934
0.119 3.0 1500 0.1614 0.9345 0.9342 0.9377 0.9345
0.1001 4.0 2000 0.2018 0.936 0.9353 0.9359 0.936
0.0704 5.0 2500 0.1925 0.935 0.9349 0.9354 0.935
0.0471 6.0 3000 0.2369 0.938 0.9373 0.9377 0.938
0.0322 7.0 3500 0.2693 0.938 0.9382 0.9392 0.938
0.0137 8.0 4000 0.2926 0.937 0.9371 0.9372 0.937
0.0099 9.0 4500 0.2964 0.9365 0.9362 0.9362 0.9365
0.0114 10.0 5000 0.3044 0.935 0.9349 0.9350 0.935

Framework versions

  • Transformers 4.22.1
  • Pytorch 1.11.0+cu113
  • Datasets 2.0.0
  • Tokenizers 0.11.6