README.md

metadata

license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
  - generated_from_trainer
metrics:
  - recall
  - accuracy
model-index:
  - name: MultiBERTBestModelOct11
    results: []

multibert0510_lrate7.5b16

This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5930
• Precisions: 0.8750
• Recall: 0.8217
• F-measure: 0.8450
• Accuracy: 0.9133

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: 7.5e-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: linear
• num_epochs: 14

Training results

Training Loss	Epoch	Step	Validation Loss	Precisions	Recall	F-measure	Accuracy
0.6022	1.0	236	0.4256	0.8484	0.6548	0.6844	0.8642
0.3396	2.0	472	0.3851	0.8046	0.7225	0.7312	0.8773
0.2116	3.0	708	0.3670	0.8311	0.7347	0.7560	0.8947
0.148	4.0	944	0.4016	0.8827	0.7716	0.8081	0.9021
0.0959	5.0	1180	0.4409	0.8338	0.8054	0.8166	0.8998
0.0809	6.0	1416	0.4964	0.8678	0.7356	0.7799	0.8980
0.056	7.0	1652	0.4894	0.8451	0.7520	0.7855	0.8931
0.038	8.0	1888	0.5008	0.8697	0.8024	0.8301	0.9104
0.031	9.0	2124	0.4813	0.8561	0.8172	0.8335	0.9122
0.02	10.0	2360	0.5857	0.8831	0.7946	0.8305	0.9115
0.0129	11.0	2596	0.5622	0.8667	0.8039	0.8308	0.9098
0.0113	12.0	2832	0.5861	0.8746	0.8015	0.8324	0.9104
0.0065	13.0	3068	0.5964	0.8752	0.8204	0.8443	0.9128
0.004	14.0	3304	0.5930	0.8750	0.8217	0.8450	0.9133

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.0