metadata
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: albert-base-v2-finetuned-rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.7545126353790613
albert-base-v2-finetuned-rte
This model is a fine-tuned version of albert-base-v2 on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.3395
- Accuracy: 0.7545
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: 10
- eval_batch_size: 10
- 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 | 249 | 0.6305 | 0.6859 |
| No log | 2.0 | 498 | 0.6054 | 0.7040 |
| 0.5964 | 3.0 | 747 | 0.7142 | 0.7437 |
| 0.5964 | 4.0 | 996 | 1.2917 | 0.7437 |
| 0.2546 | 5.0 | 1245 | 1.3395 | 0.7545 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.0
- Tokenizers 0.10.3