Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mbart50-hints-qlora – AI Model by ifti-77 | AlphaNeural AI
You can deploy this model and start earning money today!
ifti-77
/
mbart50-hints-qlora
like
0
peft
safetensors
adapter
lora
transformers
facebook/mbart-large-50
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mbart50-hints-qlora
This model is a fine-tuned version of
facebook/mbart-large-50
on an unknown dataset. It achieves the following results on the evaluation set:
eval_loss: 2.7234
eval_rouge1: 0.9342
eval_rouge2: 0.8538
eval_rougeL: 0.9329
eval_rougeLsum: 0.9337
eval_chrf: 17.0773
eval_leakage_rate: 0.0
eval_accuracy: 0.0
eval_runtime: 2851.4331
eval_samples_per_second: 0.196
eval_steps_per_second: 0.196
epoch: 6.7673
step: 4500
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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15
mixed_precision_training: Native AMP
Framework versions
PEFT 0.17.1
Transformers 4.57.1
Pytorch 2.9.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1
