<!-- 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_ar28_ex10_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: 0.5162
- Accuracy: 0.8284
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 |
---|---|---|---|---|
0.4928 | 0.19 | 50 | 0.6787 | 0.8245 |
0.364 | 0.37 | 100 | 0.5651 | 0.8245 |
0.3724 | 0.56 | 150 | 0.5438 | 0.8274 |
0.3962 | 0.75 | 200 | 0.5329 | 0.8274 |
0.4339 | 0.93 | 250 | 0.5243 | 0.8274 |
0.3771 | 1.12 | 300 | 0.5254 | 0.8274 |
0.3258 | 1.31 | 350 | 0.5245 | 0.8293 |
0.4213 | 1.5 | 400 | 0.5233 | 0.8293 |
0.3511 | 1.68 | 450 | 0.5222 | 0.8284 |
0.3318 | 1.87 | 500 | 0.5176 | 0.8284 |
0.3519 | 2.06 | 550 | 0.5170 | 0.8284 |
0.4165 | 2.24 | 600 | 0.5186 | 0.8284 |
0.3326 | 2.43 | 650 | 0.5182 | 0.8284 |
0.3877 | 2.62 | 700 | 0.5208 | 0.8284 |
0.2824 | 2.8 | 750 | 0.5174 | 0.8284 |
0.4276 | 2.99 | 800 | 0.5198 | 0.8284 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- Tokenizers 0.14.1