You can deploy this model and start earning money today!

andyc03/
Qwen3.5-9B-attack-v2.2

Name: Qwen3.5-9B-attack-v2.2
Availability: InStock

generated_from_trainer

conversational

other

endpoints_compatible

Views

No views yet

output_saber_v11

This model is a fine-tuned version of /scratch/aszalay1/nanxi/Models/Qwen3.5-9B on the saber_attack_train dataset. It achieves the following results on the evaluation set:

Loss: 0.9677

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: 2e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 16
total_train_batch_size: 64
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.03
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.1118	0.2237	100	1.0411
1.0345	0.4474	200	0.9948
1.0231	0.6710	300	0.9750
1.0113	0.8947	400	0.9682
1.0287	1.0	448	0.9677

Framework versions

Transformers 5.5.3
Pytorch 2.11.0+cu129
Datasets 3.6.0
Tokenizers 0.22.2

andyc03/Qwen3.5-9B-attack-v2.2

output_saber_v11

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

andyc03/
Qwen3.5-9B-attack-v2.2