<!-- 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_ar9_ex10_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: 0.6011
- Accuracy: 0.8351
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 |
|---|---|---|---|---|
| 0.5522 | 0.19 | 50 | 0.9087 | 0.8188 |
| 0.4998 | 0.37 | 100 | 0.6672 | 0.8322 |
| 0.4765 | 0.56 | 150 | 0.6528 | 0.8236 |
| 0.438 | 0.75 | 200 | 0.6146 | 0.8293 |
| 0.4772 | 0.93 | 250 | 0.5497 | 0.8265 |
| 0.3387 | 1.12 | 300 | 0.6836 | 0.8236 |
| 0.3269 | 1.31 | 350 | 0.5889 | 0.8370 |
| 0.3611 | 1.5 | 400 | 0.5666 | 0.8351 |
| 0.3141 | 1.68 | 450 | 0.5999 | 0.8303 |
| 0.3203 | 1.87 | 500 | 0.5571 | 0.8322 |
| 0.2492 | 2.06 | 550 | 0.5951 | 0.8313 |
| 0.3504 | 2.24 | 600 | 0.5779 | 0.8332 |
| 0.2929 | 2.43 | 650 | 0.5732 | 0.8370 |
| 0.3319 | 2.62 | 700 | 0.6364 | 0.8341 |
| 0.2118 | 2.8 | 750 | 0.6144 | 0.8360 |
| 0.3609 | 2.99 | 800 | 0.6081 | 0.8360 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- Tokenizers 0.14.1
