You can deploy this model and start earning money today!

tirdodbehbehani/
yahoo-bert-05_balanced_2_mask_aug

Name: yahoo-bert-05_balanced_2_mask_aug
Availability: InStock

Views

No views yet

yahoo-bert-05_balanced_2_mask_aug

This model is a fine-tuned version of tirdodbehbehani/yahoo-bert-32shot_stratified_augm_2 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: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
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	Precision	Recall
1.226	1.0	492	1.0359	0.6692	0.6737	0.6657
0.7918	2.0	984	1.0909	0.6655	0.6654	0.6595
0.5589	3.0	1476	1.2076	0.6603	0.6555	0.6557
0.3879	4.0	1968	1.3394	0.6490	0.6531	0.6451