This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the 2and3_apps_15k_v4_tag4o_processed dataset. It achieves the following results on the evaluation set:

Loss: 0.2511

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-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 8
optimizer: Use adamw_torch 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: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.24	0.5797	100	0.2540

Framework versions

Transformers 4.52.4
Pytorch 2.8.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1

huseyinatahaninan/2and3_apps_15k_v4_tag4o_processed-SFT-Qwen2.5-7B-Instruct

2and3_apps_15k_v4_tag4o_processed-SFT-Qwen2.5-7B-Instruct

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

huseyinatahaninan/
2and3_apps_15k_v4_tag4o_processed-SFT-Qwen2.5-7B-Instruct