metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-base-multilingual-cased-IDMGSP-danish
results: []
bert-base-multilingual-cased-IDMGSP-danish
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9588
- Accuracy: {'accuracy': 0.8393768817908103}
- F1: {'f1': 0.8521508615495843}
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_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4777 | 1.0 | 480 | 0.3597 | {'accuracy': 0.8594056813719073} | {'f1': 0.8543926247288504} |
| 0.3642 | 2.0 | 960 | 0.5526 | {'accuracy': 0.8147663306715539} | {'f1': 0.8337836250440502} |
| 0.3087 | 3.0 | 1440 | 0.3296 | {'accuracy': 0.8677837413273989} | {'f1': 0.8711077080142932} |
| 0.1919 | 4.0 | 1920 | 0.4540 | {'accuracy': 0.8287733996596414} | {'f1': 0.8453169347209082} |
| 0.1592 | 5.0 | 2400 | 0.3791 | {'accuracy': 0.8701400706898809} | {'f1': 0.8696794534944824} |
| 0.1324 | 6.0 | 2880 | 0.5328 | {'accuracy': 0.8294279355936641} | {'f1': 0.8443435670768128} |
| 0.1271 | 7.0 | 3360 | 0.7168 | {'accuracy': 0.8440895405157743} | {'f1': 0.8535955746773203} |
| 0.0227 | 8.0 | 3840 | 0.8978 | {'accuracy': 0.8253698128027229} | {'f1': 0.8424285376801323} |
| 0.0019 | 9.0 | 4320 | 0.8289 | {'accuracy': 0.8507658070428067} | {'f1': 0.8595367175948743} |
| 0.0046 | 10.0 | 4800 | 0.9588 | {'accuracy': 0.8393768817908103} | {'f1': 0.8521508615495843} |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.1
- Datasets 2.14.6
- Tokenizers 0.14.1