Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
falcon-rw-1b-translation-lora – AI Model by atulvik | AlphaNeural AI
You can deploy this model and start earning money today!
atulvik
/
falcon-rw-1b-translation-lora
like
0
peft
safetensors
generated_from_trainer
tiiuae/falcon-rw-1b
adapter
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
falcon-rw-1b-translation-lora
This model is a fine-tuned version of
tiiuae/falcon-rw-1b
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.4202
Bleu: 0.4517
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: 0.0002
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: 100
num_epochs: 6
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Bleu
0.5889
1.25
100
0.5665
0.4315
0.4177
2.5
200
0.4673
0.4041
0.327
3.75
300
0.4331
0.4301
0.2525
5.0
400
0.4202
0.4517
Framework versions
PEFT 0.15.2
Transformers 4.52.2
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1
