metadata
license: mit
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: xlnet-base-cased-finetuned-rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.6823104693140795
xlnet-base-cased-finetuned-rte
This model is a fine-tuned version of xlnet-base-cased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.6572
- Accuracy: 0.6823
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 156 | 0.6915 | 0.4946 |
No log | 2.0 | 312 | 0.6029 | 0.6643 |
No log | 3.0 | 468 | 0.6572 | 0.6823 |
0.6058 | 4.0 | 624 | 0.7877 | 0.6751 |
0.6058 | 5.0 | 780 | 0.8799 | 0.6751 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3