This model is a fine-tuned version of Qwen/Qwen3-8B on the APIGen_5k_arguments_fixed_hermes_corrected dataset. It achieves the following results on the evaluation set:

Loss: 0.2957

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: 4
gradient_accumulation_steps: 2
total_train_batch_size: 8
total_eval_batch_size: 4
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: 12

Training results

Training Loss	Epoch	Step	Validation Loss
0.1318	1.4161	300	0.1014
0.0912	2.8322	600	0.1015
0.0366	4.2459	900	0.1316
0.0223	5.6619	1200	0.1434
0.005	7.0757	1500	0.1968
0.0016	8.4917	1800	0.2467
0.0012	9.9078	2100	0.2794
0.001	11.3215	2400	0.2928

Framework versions

Transformers 4.51.0
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

lemonhat/Qwen3-8B-APIGen_5k_arguments_fixed_hermes_corrected

APIGen_5k_arguments_fixed_hermes_corrected

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

lemonhat/
Qwen3-8B-APIGen_5k_arguments_fixed_hermes_corrected