mbart50-ft-si-en

aloka/mbart50-ft-si-en

mbart50-ft-si-en is a machine learning model from aloka. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

700

Public

Repo size

7.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin2.4 GB · 99%

At a glance

Library: transformers
Model type: mbart
Access: Public
Created: Mar 2, 2022
Updated: Aug 29, 2021
SHA: 1c9a9b49

Model card

From the Hugging Face model README

mbart50-ft-si-en

This model was trained from scratch on an unkown dataset. It achieves the following results on the evaluation set:

Loss: 5.0476

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0005
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.98	30	5.6367
No log	1.98	60	4.1221
No log	2.98	90	3.1880
No log	3.98	120	3.1175
No log	4.98	150	3.3575
No log	5.98	180	3.7855
No log	6.98	210	4.3530
No log	7.98	240	4.7216
No log	8.98	270	4.9202
No log	9.98	300	5.0476

Framework versions

Transformers 4.9.2
Pytorch 1.6.0
Datasets 1.11.0
Tokenizers 0.10.3

Library: transformers
Type: mbart
Created: Mar 2, 2022
Updated: Aug 29, 2021