metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-base_cola_moe_ex9_sp0_05_ar0_0_mare_mlp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: cola
split: validation
args: cola
metrics:
- name: Accuracy
type: accuracy
value: 0
t5-base_cola_moe_ex9_sp0_05_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: 4.3499
- 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 |
|---|---|---|---|---|
| 0.387 | 0.09 | 25 | 0.5450 | 0.8293 |
| 0.2475 | 0.19 | 50 | 0.5868 | 0.8188 |
| 0.3632 | 0.28 | 75 | 0.4910 | 0.8178 |
| 0.3274 | 0.37 | 100 | 0.4657 | 0.8169 |
| 0.3411 | 0.47 | 125 | 0.5840 | 0.8188 |
| 0.3016 | 0.56 | 150 | 0.5476 | 0.8169 |
| 0.2658 | 0.65 | 175 | 0.5822 | 0.8130 |
| 0.3412 | 0.75 | 200 | 0.5156 | 0.8188 |
| 0.2783 | 0.84 | 225 | 0.4850 | 0.8245 |
| 0.3596 | 0.93 | 250 | 0.5406 | 0.8284 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.11.6