You can deploy this model and start earning money today!

Kuongan/
DSC_bert-base-multilingual-uncased_finetuned

Name: DSC_bert-base-multilingual-uncased_finetuned
Rating: 2.5 (6 reviews)

Views

No views yet

DSC_bert-base-multilingual-uncased_finetuned

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:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 256
eval_batch_size: 256
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
No log	1.0	22	0.9784	0.5386	0.4735
No log	2.0	44	0.8138	0.665	0.6554
0.9159	3.0	66	0.7604	0.6886	0.6862
0.9159	4.0	88	0.7336	0.7157	0.7141
0.6825	5.0	110	0.7421	0.715	0.7102
0.6825	6.0	132	0.7100	0.7386	0.7392
0.5273	7.0	154	0.7326	0.7393	0.7385
0.5273	8.0	176	0.7543	0.7329	0.7320
0.5273	9.0	198	0.7807	0.7421	0.7417
0.3938	10.0	220	0.8103	0.7279	0.7286
0.3938	11.0	242	0.8120	0.7386	0.7386
0.317	12.0	264	0.8424	0.7386	0.7378
0.317	13.0	286	0.8441	0.7336	0.7341