metadata

license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: result-colab
    results: []

result-colab

This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3751
Accuracy: 0.8853
Precision: 0.8785
Recall: 0.8773
F1: 0.8773

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: 1e-05
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: cosine
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.3635	1.0	48	1.1593	0.5963	0.4671	0.5259	0.4501
0.9895	2.0	96	0.7987	0.6881	0.6824	0.6271	0.6017
0.6845	3.0	144	0.6432	0.7523	0.7789	0.7076	0.7071
0.5856	4.0	192	0.5896	0.7844	0.8315	0.7457	0.7463
0.4328	5.0	240	0.4232	0.8716	0.8750	0.8585	0.8645
0.4298	6.0	288	0.4118	0.8853	0.8783	0.8810	0.8789
0.322	7.0	336	0.3988	0.8807	0.8824	0.8655	0.8712
0.3561	8.0	384	0.4169	0.8716	0.8630	0.8679	0.8637
0.27	9.0	432	0.3779	0.8991	0.8972	0.8913	0.8938
0.2472	10.0	480	0.3850	0.8991	0.8928	0.8942	0.8924
0.2349	11.0	528	0.3749	0.8945	0.8855	0.8919	0.8875
0.2491	12.0	576	0.3798	0.9037	0.8969	0.8992	0.8975
0.2239	13.0	624	0.3778	0.8853	0.8783	0.8810	0.8793
0.2276	14.0	672	0.3755	0.8899	0.8827	0.8823	0.8822
0.206	15.0	720	0.3751	0.8853	0.8785	0.8773	0.8773

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1