You can deploy this model and start earning money today!

jab11769/
scb-finetune-wangchan

Name: scb-finetune-wangchan
Availability: InStock

Views

No views yet

scb-finetune-wangchan

This model is a fine-tuned version of airesearch/wangchanberta-base-att-spm-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: 16
eval_batch_size: 16
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: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	15	1.0952	0.3654	0.3585	0.3654	0.2166
No log	2.0	30	1.1041	0.375	0.4350	0.375	0.2372
No log	3.0	45	1.0529	0.4615	0.3788	0.4615	0.4159
No log	4.0	60	1.0521	0.4327	0.3595	0.4327	0.3926
No log	5.0	75	1.0588	0.4231	0.4274	0.4231	0.4044
No log	6.0	90	1.0569	0.3942	0.3438	0.3942	0.3559
No log	7.0	105	1.0688	0.3846	0.4001	0.3846	0.3436
No log	8.0	120	1.0860	0.3558	0.3639	0.3558	0.2916