<!-- 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_ar34_ex4_size-16_epochs-3_decoder_router_sparsity20_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: 0.4997
- Accuracy: 0.8255
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 |
|---|---|---|---|---|
| 0.486 | 0.19 | 50 | 0.6601 | 0.8274 |
| 0.3451 | 0.37 | 100 | 0.5393 | 0.8255 |
| 0.3619 | 0.56 | 150 | 0.5216 | 0.8265 |
| 0.3973 | 0.75 | 200 | 0.5133 | 0.8265 |
| 0.4313 | 0.93 | 250 | 0.5058 | 0.8265 |
| 0.3826 | 1.12 | 300 | 0.5070 | 0.8274 |
| 0.3233 | 1.31 | 350 | 0.5058 | 0.8265 |
| 0.4105 | 1.5 | 400 | 0.5045 | 0.8245 |
| 0.3443 | 1.68 | 450 | 0.5045 | 0.8245 |
| 0.3283 | 1.87 | 500 | 0.5007 | 0.8255 |
| 0.3552 | 2.06 | 550 | 0.4998 | 0.8245 |
| 0.4139 | 2.24 | 600 | 0.5016 | 0.8255 |
| 0.3241 | 2.43 | 650 | 0.5017 | 0.8265 |
| 0.3805 | 2.62 | 700 | 0.5036 | 0.8255 |
| 0.2771 | 2.8 | 750 | 0.5007 | 0.8265 |
| 0.4257 | 2.99 | 800 | 0.5025 | 0.8265 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- Tokenizers 0.14.1
