You can deploy this model and start earning money today!

sercetexam9/
cs221-bert-base-multilingual-cased-finetuned-amharic-amh-finetuned-10-epochs

Name: cs221-bert-base-multilingual-cased-finetuned-amharic-amh-finetuned-10-epochs
Availability: InStock

Views

No views yet

cs221-bert-base-multilingual-cased-finetuned-amharic-amh-finetuned-10-epochs

This model is a fine-tuned version of Davlan/bert-base-multilingual-cased-finetuned-amharic 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: 32
eval_batch_size: 32
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.4369	1.0	89	0.4209	0.0122	0.5025	0.1690
0.3981	2.0	178	0.3966	0.3054	0.5868	0.2451
0.3496	3.0	267	0.3501	0.5467	0.7089	0.3704
0.293	4.0	356	0.3508	0.5879	0.7437	0.3761
0.2521	5.0	445	0.3594	0.6054	0.7628	0.3845
0.2171	6.0	534	0.3533	0.6031	0.7526	0.3986
0.1862	7.0	623	0.3657	0.5971	0.7470	0.4014
0.156	8.0	712	0.3784	0.5945	0.7468	0.4070
0.1509	9.0	801	0.3818	0.5861	0.7397	0.3958
0.1502	10.0	890	0.3845	0.5879	0.7410	0.4028