metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-base_cola_densedense_baseline
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: 0.835091083413231
t5-base_cola_densedense_baseline
This model is a fine-tuned version of t5-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5187
- Accuracy: 0.8351
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: 64
- eval_batch_size: 128
- seed: 42
- distributed_type: tpu
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- total_eval_batch_size: 256
- 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 |
|---|---|---|---|---|
| 0.5117 | 1.49 | 50 | 0.5002 | 0.7977 |
| 0.3559 | 2.99 | 100 | 0.4575 | 0.8207 |
| 0.3103 | 4.48 | 150 | 0.4466 | 0.8255 |
| 0.2928 | 5.97 | 200 | 0.5051 | 0.8303 |
| 0.2085 | 7.46 | 250 | 0.5187 | 0.8351 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3