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-dp-v3
results: []
distilbert-base-uncased-english-cefr-lexical-evaluation-dp-v3
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: 1.4726
- Accuracy: 0.5877
- F1: 0.5893
- Precision: 0.5974
- Recall: 0.5877
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 |
|---|---|---|---|---|---|---|---|
| 1.5441 | 1.0 | 139 | 1.2777 | 0.5136 | 0.5044 | 0.5164 | 0.5136 |
| 1.1611 | 2.0 | 278 | 1.1085 | 0.6058 | 0.5976 | 0.6336 | 0.6058 |
| 0.4865 | 3.0 | 417 | 1.2582 | 0.6058 | 0.6045 | 0.6216 | 0.6058 |
| 0.2134 | 4.0 | 556 | 1.4254 | 0.6239 | 0.6261 | 0.6295 | 0.6239 |
| 0.1313 | 5.0 | 695 | 1.5587 | 0.6239 | 0.6251 | 0.6277 | 0.6239 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3