Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
m2m100-lg-to-en-v5 – AI Model by MubarakB | AlphaNeural AI
You can deploy this model and start earning money today!
MubarakB
/
m2m100-lg-to-en-v5
like
0
transformers
tensorboard
safetensors
m2m_100
text2text-generation
generated_from_trainer
MubarakB/m2m100-lg-to-en-v2
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
m2m100-lg-to-en-v5
This model is a fine-tuned version of
MubarakB/m2m100-lg-to-en-v2
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.5196
Bleu: 0.1371
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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Bleu
2.6476
1.0
237
0.7225
0.3822
0.5312
2.0
474
0.5011
0.0973
0.4211
3.0
711
0.4924
0.3545
0.4015
4.0
948
0.4957
0.1006
0.3431
5.0
1185
0.5096
0.1953
0.2992
6.0
1422
0.5196
0.1371
Framework versions
Transformers 4.41.1
Pytorch 2.1.2
Datasets 2.19.1
Tokenizers 0.19.1
