Modelpublic

freya1101/lab1_random

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face

0likes7downloads

Model Card

lab1_random

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-fr on the kde4 dataset. It achieves the following results on the evaluation set:

—Loss: 5.2440
—Model Preparation Time: 0.0028
—Bleu: 6.0520

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
—trainbatchsize: 16
—evalbatchsize: 32
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—training_steps: 5000
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Bleu
6.7996	0.0476	500	6.7513	0.0028	3.5511
6.1464	0.0952	1000	6.2017	0.0028	5.0638
5.927	0.1427	1500	5.9045	0.0028	5.1608
5.7975	0.1903	2000	5.6937	0.0028	5.1830
5.4751	0.2379	2500	5.5416	0.0028	4.7912
5.4717	0.2855	3000	5.4346	0.0028	6.3369
5.2174	0.3330	3500	5.3458	0.0028	4.9379
5.5536	0.3806	4000	5.2918	0.0028	5.7794
5.3342	0.4282	4500	5.2603	0.0028	6.3629
5.4492	0.4758	5000	5.2440	0.0028	6.0904

Framework versions

—Transformers 4.57.6
—Pytorch 2.10.0+cu128
—Datasets 3.6.0
—Tokenizers 0.22.2