metadata

license: apache-2.0
base_model: t5-large
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: t5-large_cola_dense_epochs-5
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          config: cola
          split: train
          args: cola
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8813559322033898

t5-large_cola_dense_epochs-5

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

Loss: 0.4167
Accuracy: 0.8814

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: 64
eval_batch_size: 64
seed: 0
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 20
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6749	0.19	10	0.6270	0.7095
0.5772	0.37	20	0.5947	0.7101
0.6066	0.56	30	0.5545	0.7101
0.5355	0.75	40	0.4788	0.7475
0.4398	0.93	50	0.3992	0.8469
0.3932	1.12	60	0.3737	0.8638
0.3756	1.31	70	0.3606	0.8650
0.4004	1.5	80	0.3645	0.8603
0.3198	1.68	90	0.3201	0.8749
0.3129	1.87	100	0.3638	0.8697
0.2763	2.06	110	0.3091	0.8819
0.3207	2.24	120	0.3781	0.8673
0.2614	2.43	130	0.3351	0.8773
0.2909	2.62	140	0.3404	0.8662
0.2899	2.8	150	0.3277	0.8796
0.2687	2.99	160	0.3520	0.8679
0.1993	3.18	170	0.3319	0.8854
0.2584	3.36	180	0.3901	0.8732
0.2502	3.55	190	0.3766	0.8773
0.2234	3.74	200	0.3360	0.8895
0.2101	3.93	210	0.3334	0.8849
0.1708	4.11	220	0.3819	0.8714
0.1664	4.3	230	0.3690	0.8773
0.2217	4.49	240	0.4181	0.8814
0.2034	4.67	250	0.3607	0.8796
0.1948	4.86	260	0.4167	0.8814

Framework versions

Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1