metadata

tags:
  - generated_from_trainer
datasets:
  - go_emotions
metrics:
  - accuracy
  - f1
model-index:
  - name: electricidad-base-finetuned-go_emotions-es-2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: go_emotions
          type: go_emotions
          config: simplified
          split: train
          args: simplified
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5591468777484608
          - name: F1
            type: f1
            value: 0.5581665299693344

electricidad-base-finetuned-go_emotions-es-2

This model is a fine-tuned version of mrm8488/electricidad-base-discriminator on the go_emotions dataset. It achieves the following results on the evaluation set:

Loss: 2.0837
Accuracy: 0.5591
F1: 0.5582

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: 16
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.7525	1.0	2270	1.6088	0.5618	0.5076
1.4522	2.0	4540	1.4687	0.5807	0.5534
1.2798	3.0	6810	1.4550	0.5910	0.5773
1.0825	4.0	9080	1.5068	0.5873	0.5726
0.9214	5.0	11350	1.6168	0.5776	0.5743
0.7696	6.0	13620	1.7338	0.5776	0.5722
0.6688	7.0	15890	1.8733	0.5631	0.5596
0.553	8.0	18160	1.9571	0.5574	0.5591
0.4626	9.0	20430	2.0499	0.5646	0.5625
0.4399	10.0	22700	2.0837	0.5591	0.5582

Framework versions

Transformers 4.21.2
Pytorch 1.12.1+cu113
Datasets 2.4.0
Tokenizers 0.12.1