<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
t5-base_cola_mare_ar38_ex0_size-16_epochs-2_decoder_all_sparsity10_mare_mlp
This model is a fine-tuned version of t5-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5689
- Accuracy: 0.8178
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: 32
- eval_batch_size: 64
- seed: 1
- gradient_accumulation_steps: 2
- total_train_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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5508 | 0.37 | 50 | 0.7416 | 0.8178 |
| 0.4052 | 0.75 | 100 | 0.5891 | 0.8159 |
| 0.3422 | 1.12 | 150 | 0.5587 | 0.8198 |
| 0.3654 | 1.49 | 200 | 0.5878 | 0.8130 |
| 0.3213 | 1.87 | 250 | 0.5741 | 0.8188 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- Tokenizers 0.14.1
