README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: albert-large-v2-finetuned-rte
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.631768953068592

albert-large-v2-finetuned-rte

This model is a fine-tuned version of albert-large-v2 on the glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.6843
• Accuracy: 0.6318

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	13	0.6771	0.5740
No log	2.0	26	0.6675	0.6029
No log	3.0	39	0.7132	0.5632
No log	4.0	52	0.6843	0.6318
No log	5.0	65	0.7010	0.6282

Framework versions

• Transformers 4.15.0
• Pytorch 1.10.0+cu111
• Datasets 1.18.1
• Tokenizers 0.10.3