Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
InkubaLM-0.4B_Kumshe_English-Chinese-Hausa_Dataset_test_size_0.0002 – AI Model by danielbyiringiro | AlphaNeural AI
You can deploy this model and start earning money today!
danielbyiringiro
/
InkubaLM-0.4B_Kumshe_English-Chinese-Hausa_Dataset_test_size_0.0002
like
0
transformers
safetensors
llama
text-generation
generated_from_trainer
custom_code
lelapa/InkubaLM-0.4B
finetune
cc-by-nc-4.0
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
InkubaLM-0.4B_Kumshe_English-Chinese-Hausa_Dataset_test_size_0.0002
This model is a fine-tuned version of
lelapa/InkubaLM-0.4B
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 3.9616
Chrf: 0.2646
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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH 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
Chrf
No log
1.0
18
4.3709
0.2616
No log
2.0
36
4.0676
0.2657
No log
3.0
54
3.9616
0.2646
Framework versions
Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.1
Tokenizers 0.21.0
