Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
kurdish_mms_1b_final_safe – AI Model by kamalaziz | AlphaNeural AI
You can deploy this model and start earning money today!
kamalaziz
/
kurdish_mms_1b_final_safe
like
0
peft
safetensors
adapter
lora
transformers
facebook/mms-1b-all
cc-by-nc-4.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
kurdish_mms_1b_final_safe
This model is a fine-tuned version of
facebook/mms-1b-all
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.1168
Wer: 0.2834
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: 0.0003
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.1983
0.7323
500
0.1608
0.3344
0.1744
1.4643
1000
0.1375
0.3003
0.1522
2.1963
1500
0.1233
0.2868
0.1535
2.9286
2000
0.1168
0.2834
Framework versions
PEFT 0.18.0
Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 2.19.0
Tokenizers 0.22.1
