metadata

license: apache-2.0
base_model: t5-large
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: t5-large_rte_sp0_ar0
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          config: rte
          split: validation
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.853515625

t5-large_rte_sp0_ar0

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

Loss: 53.5781
Accuracy: 0.8535

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: 16
eval_batch_size: 32
seed: 1
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 32
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 20
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
21.7037	1.09	50	50.2626	0.7365
19.7544	2.17	100	48.4847	0.8375
18.2538	3.26	150	48.2347	0.8484
18.8494	4.35	200	48.5903	0.8195
18.9237	5.43	250	48.2256	0.8520
19.01	6.52	300	48.6390	0.8375
18.8412	7.61	350	48.3700	0.8412

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.11.6