<!-- 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_moe_ex96_sp0_5_ar0_0_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: 1.5584
- Accuracy: 0.0
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5167 | 0.32 | 25 | 0.5671 | 0.7256 |
| 0.4993 | 0.64 | 50 | 0.5301 | 0.7690 |
| 0.468 | 0.96 | 75 | 0.5379 | 0.7617 |
| 0.4041 | 1.28 | 100 | 0.5564 | 0.7762 |
| 0.4419 | 1.6 | 125 | 0.5647 | 0.7726 |
| 0.4651 | 1.92 | 150 | 0.5805 | 0.7581 |
| 0.3326 | 2.24 | 175 | 0.5594 | 0.7798 |
| 0.2574 | 2.56 | 200 | 0.5971 | 0.7798 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.11.6
