This model is a fine-tuned version of Qwen/Qwen3-8B on the mixed_agenttuning_2and3_apps_C2re dataset. It achieves the following results on the evaluation set:

Loss: 0.2215

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: 2
total_train_batch_size: 16
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
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.2743	0.1569	300	0.2606
0.2532	0.3137	600	0.2456
0.2461	0.4706	900	0.2394
0.2265	0.6275	1200	0.2349
0.2532	0.7843	1500	0.2318
0.2276	0.9412	1800	0.2287
0.2174	1.0978	2100	0.2270
0.2031	1.2546	2400	0.2251
0.2174	1.4115	2700	0.2235
0.2015	1.5684	3000	0.2223
0.2263	1.7252	3300	0.2218
0.2155	1.8821	3600	0.2215

Framework versions

Transformers 4.51.0
Pytorch 2.8.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1

lemonhat/Qwen3-8B-mixed_agenttuning_2and3_apps_C2re

mixed_agenttuning_2and3_apps_C2re

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

lemonhat/
Qwen3-8B-mixed_agenttuning_2and3_apps_C2re