Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
greek-m2m100-5ep-384 – AI Model by chaido13 | AlphaNeural AI
You can deploy this model and start earning money today!
chaido13
/
greek-m2m100-5ep-384
like
0
transformers
pytorch
m2m_100
text2text-generation
generated_from_trainer
squad
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
greek-m2m100-5ep-384
This model is a fine-tuned version of
facebook/m2m100_418M
on the squad dataset. It achieves the following results on the evaluation set:
Loss: 1.2996
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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5
Training results
Training Loss
Epoch
Step
Validation Loss
1.903
0.67
100
1.4264
1.3766
1.35
200
1.3557
1.2595
2.03
300
1.3305
1.1093
2.7
400
1.3136
1.0445
3.38
500
1.3070
0.9852
4.05
600
1.3037
0.9114
4.73
700
1.2996
Framework versions
Transformers 4.27.0.dev0
Pytorch 1.13.0
Datasets 2.1.0
Tokenizers 0.13.2
