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: 0.6931407942238267

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: 0.7094
• Accuracy: 0.6931

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	16	0.6791	0.5596
No log	2.0	32	0.6203	0.6534
No log	3.0	48	0.6590	0.6751
No log	4.0	64	0.6888	0.6859
No log	5.0	80	0.7094	0.6931

Framework versions

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