metadata
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-large_cola_dense_epochs-5
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: 0.837967401725791
t5-large_cola_dense_epochs-5
This model is a fine-tuned version of t5-large on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.9474
- Accuracy: 0.8380
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: 32
- seed: 0
- 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 |
|---|---|---|---|---|
| 0.4193 | 0.37 | 50 | 0.6334 | 0.7996 |
| 0.3251 | 0.75 | 100 | 0.5550 | 0.8092 |
| 0.2903 | 1.12 | 150 | 0.5062 | 0.8255 |
| 0.2551 | 1.49 | 200 | 0.4837 | 0.8341 |
| 0.2893 | 1.87 | 250 | 0.4571 | 0.8360 |
| 0.175 | 2.24 | 300 | 1.0091 | 0.8351 |
| 0.17 | 2.61 | 350 | 0.6112 | 0.8418 |
| 0.1838 | 2.99 | 400 | 0.5199 | 0.8389 |
| 0.1342 | 3.36 | 450 | 1.7694 | 0.8408 |
| 0.1458 | 3.73 | 500 | 1.9474 | 0.8380 |
| 0.0828 | 4.1 | 550 | 1.6033 | 0.8428 |
| 0.096 | 4.48 | 600 | 1.9796 | 0.8418 |
| 0.2999 | 4.85 | 650 | 1.7943 | 0.8456 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1