metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - f1
model-index:
  - name: minilm-finetuned-emotion
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          args: default
        metrics:
          - type: f1
            value: 0.9117582218338629
            name: F1
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: test
        metrics:
          - type: accuracy
            value: 0.9135
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGUyODMzMjBmZWE4M2Y3OTRkOThhYjY5MGNiNzc3YTVhMjhjYWU5Nzc3Y2I2ZmM3ZmY4MTg5Mjg5ZWQyNjRjMSIsInZlcnNpb24iOjF9.fg4k9vFS45061Sfds1QysUVXohn78EA67kFdR9dS3mD6YEivYvJJhtg-HxwB85tCK3HKG9kJ8fZDBZpl80VHBQ
          - type: f1
            value: 0.8605041780075561
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzU1MjAyYTNiYWQ3YmIzMjM1YWY0YTliNDA3NzkwZGM4NzIwMTI0OGE1MGFjNDZmZTgxMGMyYjE5Yjk0ZWI2OSIsInZlcnNpb24iOjF9.tvCoRtiOJZK-aj1NTguVTgalYv7dpr53HltxIaHSK8RYiOGTtTPWyoD2S6HNr6TcyG_xpiAGSvAX8aPB7BrPAA
          - type: f1
            value: 0.9135
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGZiZDczYzA3ZTlhYzhmY2U0MjU1NTQyNjUzMDQ4MzNjNDE5YmFjMzVlNDA3ZDE5ZGQ1ZDM4ODk2MDBhMGRkOSIsInZlcnNpb24iOjF9._jIY8LU8dEQtvxfWkFEZqwGCdnz2T7GFAOVIj2yonoQkRc49gUhjPuwVjW_0B4N420omnCc6HaNEgEdf9MvICw
          - type: f1
            value: 0.9137710447678835
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTEzZTA2MWZlMTVkMWEwZTU5YzBhZjE5MmVjM2RhNGQ0NzFmNmQ0NTg1Njk5OGU3OWNmODhjNDZmMzdkNzk2MCIsInZlcnNpb24iOjF9.nuj-Ek1A_ol3VHdTMUfSr91PNQ_SA7XkIXplIRVg-f77DpUChzvxZPfGYo8Epvz8F5KNW7NKEZI-DWxhgftRDg
          - type: precision
            value: 0.8837842447434209
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTcxODM5NWY0Yjk4NjNhOWYyNjhhMWE2MGE2MjBjMmQxZjkxMmVlM2JiMTkxMTRmZTU5Zjk5YzM3NmZjOTJmNSIsInZlcnNpb24iOjF9.FSHEuPvH2dVPlmeXrTb5UbVNCuHzo_nOwMS644pPC12VhguiPPFoYX9VzNf7i_yG5bRK6rvo3gGu8kbQpm6qCg
          - type: precision
            value: 0.9135
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTM5ZjVkYmMxYjQ4NWNkOTZhZjgwYzVjNDFjOTQxZGU5YTQ0YzVjNTJlMGQyOGIyYzgzN2MyODA3ZTRmNmMyZSIsInZlcnNpb24iOjF9.yo1fZWoORSRyrpuEwHqe2qEW_c50ljfMHN0QonCjP2dtjcVMj7vK8_AsT6jLNK2fts9zC2D_Mrx0pJKtxV8MDg
          - type: precision
            value: 0.9214108255847144
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmFkZjllYTZkMzkxOTVjYmRkMjgzM2ZjYzZmMWI3YWQ0ZDliMWI2YTJiODdiZmQ0MTU0NjMzZWJlNjUyODYyNyIsInZlcnNpb24iOjF9.In5jOw4QujbpBv3RRnxwuyDE9TwvWqgqV5W-3zgB5vUUimjYCF7DGePyEYW1UGu1VZ8p7GvX2VYkR-d84y72Cg
          - type: recall
            value: 0.8615717630413814
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDkyNWNlMTA3MjEzNDBmYWIxYjg1MDJmNjdhNTA0YWUwMDg5NTAzNzE5ZmM3OTdkNDc5ZTQxYTRhYTE2NzAyOCIsInZlcnNpb24iOjF9.ilrr0PKUcVwUUT3ouhurmZpB3F_xv-5bZlNiYGtZbR0CrKUlp2nXWYvt9bda7V6WIY2VHirQ6n_n5Q9eZrN2AA
          - type: recall
            value: 0.9135
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWMyOGJkNmY5OWI5YTk3NDY4ZGU4OTNkYzRkMDM5YjBhYWM4OWYyNWIwMmUyNDBkZWI3OGFmMjM1ZDI4NjIwNyIsInZlcnNpb24iOjF9.gRhGm18KDj9G2iC097Y8qhnMFryrfuMZROGce-eQTkeeogA1jYMq-iYge5wXkDyNFANe7K7Tgl07uLOFYDXoCQ
          - type: recall
            value: 0.9135
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGQ1MzgxMGIzYmI5Njc2N2VjYTVlNWIzYmQ1MmRmYTc4YmI0NGM0MWZmOGZkZTkyMDM3OWJhMDNiZjE2ZDY2ZCIsInZlcnNpb24iOjF9.CeoluasKQgxZ2xj6DLE3XboZTNmVl1-ArG_f5Chw-eM8QhcyrIhTfCbzqX5bCop3OAccUQRXzAOjao1DAMblDQ
          - type: loss
            value: 0.3407318592071533
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGU2ZTVhZjFlZDU5NmM0NWE4ZWEzMjZjY2QwOWMxZWVkYmMzZjU3NmY0N2MwOWM4OTFkODY0MTE4NzliNGZhMiIsInZlcnNpb24iOjF9.A2VEIKr0YfKr6IJfMbtCLTKrY724QxFJ-bx4ZAJS4lG087Zl2ngjEZhsHEArvCWygaMt9nS9Eu07qVs3DeAADA

minilm-finetuned-emotion

This model is a fine-tuned version of microsoft/MiniLM-L12-H384-uncased on the emotion dataset. It achieves the following results on the evaluation set:

Loss: 0.3891
F1: 0.9118

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: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
1.3957	1.0	250	1.0134	0.6088
0.8715	2.0	500	0.6892	0.8493
0.6085	3.0	750	0.4943	0.8920
0.4626	4.0	1000	0.4096	0.9078
0.3961	5.0	1250	0.3891	0.9118

Framework versions

Transformers 4.12.3
Pytorch 1.6.0
Datasets 1.15.1
Tokenizers 0.10.3