metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilbert-base-uncased-english-cefr-lexical-evaluation-dt-v6
results: []
distilbert-base-uncased-english-cefr-lexical-evaluation-dt-v6
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4919
- Accuracy: 0.7204
- F1: 0.7215
- Precision: 0.7239
- Recall: 0.7204
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.9855 | 1.0 | 937 | 1.0026 | 0.6225 | 0.6227 | 0.6604 | 0.6225 |
| 0.6191 | 2.0 | 1874 | 0.8113 | 0.7090 | 0.7056 | 0.7160 | 0.7090 |
| 0.2736 | 3.0 | 2811 | 0.9598 | 0.7084 | 0.7070 | 0.7099 | 0.7084 |
| 0.1399 | 4.0 | 3748 | 1.2784 | 0.7130 | 0.7126 | 0.7151 | 0.7130 |
| 0.0521 | 5.0 | 4685 | 1.5455 | 0.7152 | 0.7163 | 0.7182 | 0.7152 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3