metadata
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-large_sst2_dense_epochs-5
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: sst2
split: validation
args: sst2
metrics:
- name: Accuracy
type: accuracy
value: 0.9575688073394495
t5-large_sst2_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: 0.6867
- Accuracy: 0.9576
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: 256
- eval_batch_size: 256
- seed: 0
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 512
- 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 |
|---|---|---|---|---|
| 0.2069 | 0.38 | 50 | 0.4171 | 0.9438 |
| 0.1627 | 0.76 | 100 | 0.3713 | 0.9518 |
| 0.1641 | 1.14 | 150 | 0.4802 | 0.9553 |
| 0.1261 | 1.52 | 200 | 0.2517 | 0.9541 |
| 0.128 | 1.89 | 250 | 0.2427 | 0.9633 |
| 0.0765 | 2.27 | 300 | 0.5854 | 0.9622 |
| 0.1547 | 2.65 | 350 | 0.6896 | 0.9507 |
| 0.0705 | 3.03 | 400 | 0.5790 | 0.9484 |
| 0.0683 | 3.41 | 450 | 0.3680 | 0.9564 |
| 0.0889 | 3.79 | 500 | 0.6867 | 0.9576 |
| 0.1541 | 4.17 | 550 | 0.6979 | 0.9576 |
| 0.0689 | 4.55 | 600 | 0.9328 | 0.9507 |
| 0.0964 | 4.92 | 650 | 0.6852 | 0.9587 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1