Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
res_nw_egy – AI Model by nlparabic | AlphaNeural AI
You can deploy this model and start earning money today!
nlparabic
/
res_nw_egy
like
0
safetensors
gpt2
generated_from_trainer
riotu-lab/ArabianGPT-01B
finetune
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
res_nw_egy
This model is a fine-tuned version of
riotu-lab/ArabianGPT-01B
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.7587
Bleu: 0.2247
Rouge1: 0.5688
Rouge2: 0.3117
Rougel: 0.5649
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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 3.0
Training results
Training Loss
Epoch
Step
Validation Loss
Bleu
Rouge1
Rouge2
Rougel
1.148
1.0
7107
0.8351
0.1872
0.5143
0.2506
0.5097
0.7647
2.0
14214
0.7705
0.2146
0.5552
0.2966
0.5514
0.6812
3.0
21321
0.7587
0.2247
0.5688
0.3117
0.5649
Framework versions
Transformers 4.45.0.dev0
Pytorch 2.3.1+cu121
Datasets 2.19.2
Tokenizers 0.19.1
