18-24-finetuned-eng-to-para

Tri1/18-24-finetuned-eng-to-para

18-24-finetuned-eng-to-para is a machine learning model from Tri1. 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. The card lists the license as apache-2.0.

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

Downloads · 30 days

69% of all-time downloads

All-time downloads

Public

Repo size

45.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin299 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: marian
Access: Public
Created: Jun 28, 2023
Updated: Jun 29, 2023
SHA: c635670c

Model card

From the Hugging Face model README

18-24-finetuned-eng-to-para

This model is a fine-tuned version of Tri1/12-18-finetuned-eng-to-para on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3257
Bleu: 17.0341
Gen Len: 24.16

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.1696	1.0	6250	0.3216	18.5922	24.048
0.1554	2.0	12500	0.3225	17.7026	23.992
0.1474	3.0	18750	0.3242	17.2459	24.176
0.1387	4.0	25000	0.3243	17.3668	23.856
0.1314	5.0	31250	0.3247	17.4414	24.416
0.1277	6.0	37500	0.3257	17.0341	24.16

Framework versions

Transformers 4.30.1
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.13.3

Library: transformers
Type: marian
License: apache-2.0
Created: Jun 28, 2023
Updated: Jun 29, 2023