gptoss_20b_all_zhtw_lr1e-5_ep1_16_32_128

This model is a fine-tuned version of openai/gpt-oss-20b on the multi_turn_miss_func_zh_tw_function_mix_sharegpt_clean1, the multi_turn_miss_param_zh_tw_function_mix_sharegpt_clean1, the multi_turn_zh_tw_function_mix_sharegpt, the irrelevance_zh_tw_sharegpt3000 and the apigen_zhtwV3_remove_sys_sharegpt datasets. It achieves the following results on the evaluation set:

• Loss: 0.3610

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 128
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 15
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.2826	0.0673	10	1.3290
1.0403	0.1347	20	1.0828
0.8251	0.2020	30	0.8174
0.6385	0.2694	40	0.6514
0.4855	0.3367	50	0.5241
0.4232	0.4040	60	0.4420
0.4117	0.4714	70	0.4013
0.3962	0.5387	80	0.3845
0.3664	0.6061	90	0.3749
0.4096	0.6734	100	0.3687
0.3685	0.7407	110	0.3648
0.3793	0.8081	120	0.3627
0.401	0.8754	130	0.3614
0.3497	0.9428	140	0.3614

Framework versions

• PEFT 0.18.1
• Transformers 4.57.6
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2