metadata
license: apache-2.0
base_model: distilbert/distilbert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: >-
distilbert-base-multilingual-cased_classification_finetuned_news_all_adptive
results: []
distilbert-base-multilingual-cased_classification_finetuned_news_all_adptive
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5638
- F1: 0.8525
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.3636 | 1.0 | 2384 | 0.3592 | 0.8071 |
| 0.3492 | 2.0 | 4768 | 0.3220 | 0.8233 |
| 0.3052 | 3.0 | 7152 | 0.3036 | 0.8378 |
| 0.2627 | 4.0 | 9536 | 0.3304 | 0.8404 |
| 0.1948 | 5.0 | 11920 | 0.3458 | 0.8434 |
| 0.1536 | 6.0 | 14304 | 0.4380 | 0.8524 |
| 0.164 | 7.0 | 16688 | 0.5638 | 0.8525 |
| 0.136 | 8.0 | 19072 | 0.7250 | 0.8503 |
| 0.076 | 9.0 | 21456 | 0.8166 | 0.8510 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2