metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-base_cola_moe_ex16_epochs-5_collected-stats
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: 0.8302972195589645
t5-base_cola_moe_ex16_epochs-5_collected-stats
This model is a fine-tuned version of t5-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5254
- Accuracy: 0.8303
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: 42
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5766 | 0.37 | 50 | 0.5459 | 0.7009 |
| 0.4641 | 0.75 | 100 | 0.4948 | 0.7996 |
| 0.3657 | 1.12 | 150 | 0.5502 | 0.8111 |
| 0.4043 | 1.49 | 200 | 0.4791 | 0.8198 |
| 0.3875 | 1.87 | 250 | 0.4936 | 0.8217 |
| 0.3507 | 2.24 | 300 | 0.4735 | 0.8217 |
| 0.3255 | 2.61 | 350 | 0.5022 | 0.8198 |
| 0.3407 | 2.99 | 400 | 0.5193 | 0.8265 |
| 0.2576 | 3.36 | 450 | 0.5292 | 0.8303 |
| 0.3138 | 3.73 | 500 | 0.5254 | 0.8303 |
| 0.2866 | 4.1 | 550 | 0.5132 | 0.8313 |
| 0.284 | 4.48 | 600 | 0.5314 | 0.8274 |
| 0.3607 | 4.85 | 650 | 0.5357 | 0.8293 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1