metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - f1
model-index:
  - name: deberta-finetuned-answer-polarity-1e6
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          config: answer_pol
          split: validation
          args: answer_pol
        metrics:
          - name: F1
            type: f1
            value: 0.8586364216686151

deberta-finetuned-answer-polarity-1e6

This model is a fine-tuned version of microsoft/deberta-large on the glue dataset. It achieves the following results on the evaluation set:

Loss: 0.7823
F1: 0.8586

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: 1e-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	262	0.7424	0.4877
0.8987	2.0	524	0.3792	0.8774
0.2993	3.0	786	0.5936	0.8413
0.1483	4.0	1048	0.4211	0.8859
0.1175	5.0	1310	0.4684	0.8959
0.0816	6.0	1572	0.6284	0.8712
0.0624	7.0	1834	0.7823	0.8586

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.13.3