README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - accuracy
model-index:
  - name: sagemaker-distilbert-emotion
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          args: default
        metrics:
          - type: accuracy
            value: 0.921
            name: Accuracy
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: test
        metrics:
          - type: accuracy
            value: 0.921
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGRkMDBjODEwZWI2OTlhZmQ4ZGQ2MjRhZDMzZjA1ZTNkMWU0OTdhZTA3NjAzZGI1ZGFiMjFlNGQxY2MyM2Y2NiIsInZlcnNpb24iOjF9.lk_zOxIIclaySp7edHaCoBD4hSHBJkUNcv1z-2vhO_8Af5JYOgRjlNloztRJd9SuRISEyH4srmqsRx8hqiivAA
          - type: precision
            value: 0.8870419502496194
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTZhNTg0ODU0YmYxZGMxNDZhOTg4M2Y2OTUzZGZmZmQ3ZDdmMmQyMWQ1MTc3ZDIzM2ZlYjg3NGVhOTBhNzJiMiIsInZlcnNpb24iOjF9._ZojNfDN63jqrciNdn8xWhJ38IkaeIy_y8gOU0r9Wf3Ki06ZcrX4qAz8KVF9LIQffmK4EupUAlNFycxf3SZYBA
          - type: precision
            value: 0.921
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2Y0ZGRhYWMxYTIwOGQzYzQ1MGIxOGZkMzM5YWYxN2RhZTgyZjJiNzc2MDY3YTk4YWYyOGI0MDE0M2JiYTk0NCIsInZlcnNpb24iOjF9.tPd-tWnKPt13vGMXk_OGpCgllvinP0Pry5YAvvcjnIKo33eJ5RCKay8u5Q2TTLCU71Lndf_x-A2qWInLXEk-AA
          - type: precision
            value: 0.9208079974712109
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGUxYjkzM2MzOWNhYjIyZGE4ODYyY2E1MTRiMGNiMGM3NDk1Y2Q3ZjEyZDAzY2ZhZTFjYmE3YzY1MjM0YWMzZiIsInZlcnNpb24iOjF9.XNf83HOOYCJmb_BKpNM-ullwiqLoRBQLbA4FAa6v3bfH_BLwK3vve_Ym3xa7uNRkuJGM-clvkeXEaEqAz99JBA
          - type: recall
            value: 0.8688429370077566
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2U0MmYzNTkyY2U0MDNiMDBjY2I3YWI0OGViZDBlZjJhNDBmZWE3NGYxMWFjMDFmMmVhM2RhZmY4ZWVlNzNkMiIsInZlcnNpb24iOjF9.J3qsAJm9T7kqmuOFs67Fq7RLEN2-cQ2RgUhqvvyO_OWXu3JVucTgCqQhpoKa1GHWVX0illbbozmAQ5OK5wBXCg
          - type: recall
            value: 0.921
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGQ2NGNkYWQwMWY3ZmIyNzBiMTEwM2M4MWVlNzJiMGExMjk5MmY4ODgxYjM1YjUwNGIwMjNkZDk3NTBlNjI5NCIsInZlcnNpb24iOjF9.iZgzAfNdWlyEKAWwE32o3D6Ely76ZJ2ySVxl0jBetL4YGWgOHSybrYvcZ2kB8sx3QfOc5L_vWyWNSbY5HAVeAA
          - type: recall
            value: 0.921
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODcwOWIxMzFjM2VmM2E1MmZlOGM1N2JiNjQwMGM0MzEzNzQ5NzJlM2I3MDdkYTMzN2NlYzU5ZDQwODBjYWFmZiIsInZlcnNpb24iOjF9.PlvoxtJ9Bj5G2w_E6Cx5VG5maRPP5dn4YzOX0xYPu_J7iiXRRLvwp12Q6vIUwsZMoBM4jACrh-rQKZ_g_yyHCw
          - type: f1
            value: 0.87642650638535
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2RiMzFkMGVhYjc3MmJjOGFkYTZiYzAxMGUyOTBmYWJhYmQ3NTg2M2MxZGExOGI4NTkwOWM2ODRlMGJjZjM3ZSIsInZlcnNpb24iOjF9.hVbjwMlCeyjJ-0BEhGuaI5T8MOsAkAgLTnp7zlhUEi2cireIEfAkpdsmBPuQJyZYaGZ5ZXmSybAP08X1ouNoBw
          - type: f1
            value: 0.9209999999999999
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTk0ODExMTliNTJlYjExNWExNDQ2NDUwNjkyMjA3ODg5YTk0NmFhNmMxZGQ0MzMxZjgxNGFjMmNkZWI1MTMzOCIsInZlcnNpb24iOjF9.dqucaDtPQ0A1KZkT4q9Ojfgtf2wZiJmjaKrvTdbhsvf7gNfYnJsMGaDIOxp_YoCEXGRMXKsknANx_VA7mOKSDA
          - type: f1
            value: 0.9203938811554648
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDQ1MTYxMTFiNWYwZDExYThjMDVmODdiMmRjMmQzMzJmMWY5MWE0M2VhZmExZTEwMzFlMDQ2MWIyOTFjZDc4MyIsInZlcnNpb24iOjF9.T-HlP7Fl6NuPmqps7wHkTuGi_8wF6u6BuulCxX0sp8ocEP3j8GNH9goydsKTEHyLMmch9QuCrzqFmmGAW-wVAA
          - type: loss
            value: 0.23216550052165985
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzVhNzYwZWIyN2QzMjU2OThiZjRmMjFlYTQ2MDA3ZTVmNmFkYzE1NDA1OWQzOTM4ZmRiMmQ0OGE2MzY4ZTY1ZCIsInZlcnNpb24iOjF9.Zj38hE02ePkNK7m1dhPq_N25CC9p0ZekFyCSBAS534GfhFuNhtUFhcgr6DDjyPTbn906RJDmVNxu7g01eCarAw

sagemaker-distilbert-emotion

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

• Loss: 0.2322
• Accuracy: 0.921

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 64
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9306	1.0	500	0.2322	0.921

Framework versions

• Transformers 4.12.3
• Pytorch 1.9.1
• Datasets 1.15.1
• Tokenizers 0.10.3