Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
train_run-qwen2.5-0.5b-instruct-arabic-diacritization-fadel-10k-left – AI Model by Bisher | AlphaNeural AI
You can deploy this model and start earning money today!
Bisher
/
train_run-qwen2.5-0.5b-instruct-arabic-diacritization-fadel-10k-left
like
0
peft
safetensors
generated_from_trainer
Qwen/Qwen2.5-0.5B-Instruct
adapter
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
train_run-qwen2.5-0.5b-instruct-arabic-diacritization-fadel-10k-left
This model is a fine-tuned version of
Qwen/Qwen2.5-0.5B-Instruct
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.1130
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1
Training results
Training Loss
Epoch
Step
Validation Loss
0.2675
0.16
100
0.2502
0.1788
0.32
200
0.1742
0.1496
0.48
300
0.1526
0.1349
0.64
400
0.1319
0.1195
0.8
500
0.1194
0.1105
0.96
600
0.1130
Framework versions
PEFT 0.14.0
Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0
