You can deploy this model and start earning money today!

chechdop/
mbart-50-spa-shp-tokenized

Name: mbart-50-spa-shp-tokenized
Availability: InStock

Views

No views yet

mbart-50-spa-shp-tokenized

This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt 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: 4
eval_batch_size: 4
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: 50
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Chrf	Bleu
0.6541	1.0	5524	0.5420	31.7310	6.4789
0.4205	2.0	11048	0.4577	36.6741	9.5049
0.3272	3.0	16572	0.4245	40.0582	10.9536
0.2291	4.0	22096	0.4187	42.2137	12.3854
0.1883	5.0	27620	0.4225	43.3322	13.0691
0.1672	6.0	33144	0.4362	43.7028	13.0441
0.1445	7.0	38668	0.4565	44.2853	13.4968
0.1234	8.0	44192	0.4702	44.2726	13.4368
0.2053	9.0	49716	0.4908	44.9817	14.0797