metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - go_emotions
metrics:
  - f1
base_model: roberta-large
model-index:
  - name: roberta-large-go-emotions-3
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: go_emotions
          type: multilabel_classification
          config: simplified
          split: test
          args: simplified
        metrics:
          - type: f1
            value: 0.5204
            name: F1
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: go_emotions
          type: multilabel_classification
          config: simplified
          split: validation
          args: simplified
        metrics:
          - type: f1
            value: 0.5208
            name: F1

roberta-large-go-emotions-2

This model is a fine-tuned version of roberta-large on the go_emotions dataset. It achieves the following results on the test set (with a threshold of 0.15):

Accuracy: 0.4363
Precision: 0.4955
Recall: 0.5655
F1: 0.5204

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: 128
eval_batch_size: 128
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 6

Training results

Training Loss	Epoch	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	0.0889	0.4043	0.4807	0.4568	0.4446
0.1062	2.0	0.0828	0.4113	0.4608	0.5363	0.4868
0.1062	3.0	0.0813	0.4201	0.5198	0.5612	0.5227
No log	4.0	0.0862	0.4292	0.5012	0.5558	0.5208
0.0597	5.0	0.0924	0.4329	0.5164	0.5362	0.5151
0.0597	6.0	0.0956	0.4445	0.5241	0.5328	0.5161

Framework versions

Transformers 4.20.1
Pytorch 1.12.0
Datasets 2.1.0
Tokenizers 0.12.1