You can deploy this model and start earning money today!

phunganhsang/
Revision_PhoBert_Lexical_MetaPho_relabel

Views

No views yet

Revision_PhoBert_Lexical_MetaPho_relabel

This model is a fine-tuned version of ttqdunggg/Revision_PhoBert_Lexical_Dataset_46k on an unknown 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: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.2778	100	0.3167	0.8712	0.8650
No log	0.5556	200	0.3067	0.8817	0.8757
No log	0.8333	300	0.3095	0.8706	0.8650
0.2409	1.1111	400	0.3250	0.8693	0.8628
0.2409	1.3889	500	0.3618	0.8647	0.8587
0.2409	1.6667	600	0.3916	0.8596	0.8544
0.2409	1.9444	700	0.4582	0.8362	0.8322
0.1685	2.2222	800	0.4386	0.8486	0.8441
0.1685	2.5	900	0.4816	0.8399	0.8356
0.1685	2.7778	1000	0.3863	0.8571	0.8518
0.1183	3.0556	1100	0.4251	0.8585	0.8534
0.1183	3.3333	1200	0.4601	0.8541	0.8494
0.1183	3.6111	1300	0.4638	0.8537	0.8489
0.1183	3.8889	1400	0.4931	0.8440	0.8397
0.0822	4.1667	1500	0.4840	0.8532	0.8485
0.0822	4.4444	1600	0.4648	0.8557	0.8509
0.0822	4.7222	1700	0.5088	0.8476	0.8432
0.0627	5.0	1800	0.4972	0.8502	0.8457