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-ep-v4
results: []
distilbert-base-uncased-english-cefr-lexical-evaluation-ep-v4
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: 1.9206
- Accuracy: 0.6093
- F1: 0.6095
- Precision: 0.6174
- Recall: 0.6093
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: 8
- eval_batch_size: 8
- 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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.2735 | 1.0 | 346 | 1.4207 | 0.4721 | 0.4451 | 0.4941 | 0.4721 |
| 1.0356 | 2.0 | 692 | 1.2296 | 0.5380 | 0.5399 | 0.5786 | 0.5380 |
| 0.3684 | 3.0 | 1038 | 1.6360 | 0.5590 | 0.5619 | 0.5712 | 0.5590 |
| 0.1539 | 4.0 | 1384 | 2.1402 | 0.5844 | 0.5846 | 0.5901 | 0.5844 |
| 0.2342 | 5.0 | 1730 | 2.4715 | 0.5807 | 0.5828 | 0.5915 | 0.5807 |
| 0.0022 | 6.0 | 2076 | 2.4647 | 0.5742 | 0.5763 | 0.5802 | 0.5742 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3