<!-- 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_mrpc_dense_sp0_ar0
This model is a fine-tuned version of t5-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.0325
- 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
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.717 | 0.64 | 25 | 0.6894 | 0.5307 |
| 0.6467 | 1.28 | 50 | 0.6510 | 0.6173 |
| 0.6062 | 1.92 | 75 | 0.5660 | 0.7292 |
| 0.503 | 2.56 | 100 | 0.5416 | 0.7473 |
| 0.4691 | 3.21 | 125 | 0.5493 | 0.7220 |
| 0.4518 | 3.85 | 150 | 0.5516 | 0.7509 |
| 0.4087 | 4.49 | 175 | 0.5405 | 0.7690 |
| 0.3352 | 5.13 | 200 | 0.5216 | 0.7870 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.11.6
