<!-- 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_ar19_ex0_size-16_epochs-3_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: 0.5842
- Accuracy: 0.8370
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5332 | 0.19 | 50 | 0.9078 | 0.8178 |
| 0.421 | 0.37 | 100 | 0.5844 | 0.8303 |
| 0.402 | 0.56 | 150 | 0.5743 | 0.8226 |
| 0.3883 | 0.75 | 200 | 0.5821 | 0.8284 |
| 0.4407 | 0.93 | 250 | 0.4851 | 0.8274 |
| 0.2989 | 1.12 | 300 | 0.6448 | 0.8188 |
| 0.2889 | 1.31 | 350 | 0.5688 | 0.8360 |
| 0.3634 | 1.5 | 400 | 0.5505 | 0.8380 |
| 0.2823 | 1.68 | 450 | 0.5605 | 0.8322 |
| 0.2769 | 1.87 | 500 | 0.5515 | 0.8322 |
| 0.2445 | 2.06 | 550 | 0.5615 | 0.8293 |
| 0.3332 | 2.24 | 600 | 0.5652 | 0.8399 |
| 0.2606 | 2.43 | 650 | 0.5644 | 0.8389 |
| 0.2857 | 2.62 | 700 | 0.6029 | 0.8351 |
| 0.1871 | 2.8 | 750 | 0.5940 | 0.8370 |
| 0.3127 | 2.99 | 800 | 0.5899 | 0.8370 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- Tokenizers 0.14.1
