metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-sst2
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: 0.8990825688073395
distilbert-base-uncased-finetuned-sst2
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3077
- Accuracy: 0.8991
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: 512
- eval_batch_size: 512
- 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 | 132 | 0.2548 | 0.8888 |
| No log | 2.0 | 264 | 0.2657 | 0.8956 |
| No log | 3.0 | 396 | 0.2755 | 0.8968 |
| 0.1961 | 4.0 | 528 | 0.2946 | 0.8956 |
| 0.1961 | 5.0 | 660 | 0.3077 | 0.8991 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0