metadata

license: apache-2.0
base_model: t5-base
tags:
  - generated_from_trainer
datasets:
  - super_glue
metrics:
  - accuracy
model-index:
  - name: superglue_rte-t5-base
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: super_glue
          type: super_glue
          config: rte
          split: validation
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7725631768953068

superglue_rte-t5-base

This model is a fine-tuned version of t5-base on the super_glue dataset. It achieves the following results on the evaluation set:

Loss: 2.5687
Accuracy: 0.7726

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: 4
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7109	1.0	623	0.6765	0.5740
0.6562	2.0	1246	0.6030	0.6968
0.548	3.0	1869	0.8049	0.7617
0.4129	4.0	2492	1.3536	0.7329
0.2189	5.0	3115	1.3886	0.7834
0.1378	6.0	3738	1.7001	0.7690
0.0905	7.0	4361	2.0587	0.7545
0.0434	8.0	4984	2.1796	0.7798
0.0715	9.0	5607	1.9936	0.7978
0.0616	10.0	6230	1.9794	0.7762
0.0609	11.0	6853	2.5575	0.7509
0.0108	12.0	7476	2.1022	0.7834
0.0142	13.0	8099	2.0628	0.7834
0.03	14.0	8722	2.1540	0.7726
0.0163	15.0	9345	2.3830	0.7653
0.0152	16.0	9968	2.5031	0.7617
0.0092	17.0	10591	2.4850	0.7653
0.0069	18.0	11214	2.4939	0.7726
0.0184	19.0	11837	2.4949	0.7690
0.0204	20.0	12460	2.5687	0.7726

Framework versions

Transformers 4.32.1
Pytorch 1.13.0+cu117
Datasets 2.15.0
Tokenizers 0.13.3