You can deploy this model and start earning money today!

usyk/
distilbert_sharetask-batchsize_l16

Name: distilbert_sharetask-batchsize_l16
Availability: InStock

Views

No views yet

distilbert_sharetask-batchsize_l16

This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased 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: 3e-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: linear
lr_scheduler_warmup_steps: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	F1	Precision	Recall
0.6828	1.0	173	0.6750	0.5399	0.5754	0.5743
0.6702	2.0	346	0.6565	0.5514	0.6259	0.6098
0.5865	3.0	519	0.5886	0.6927	0.7200	0.6863
0.4011	4.0	692	0.6880	0.6517	0.6823	0.6850
0.1909	5.0	865	0.6958	0.7513	0.7617	0.7457
0.2072	6.0	1038	0.7636	0.7555	0.7533	0.7585
0.0514	7.0	1211	0.8919	0.7594	0.7596	0.7592
0.0842	8.0	1384	1.1276	0.7561	0.7555	0.7568
0.0163	9.0	1557	1.1865	0.7582	0.7582	0.7582
0.0266	10.0	1730	1.2120	0.7639	0.7636	0.7642