Sailor2-8B-Chat_sft_sg_values_resp_split

This model is a fine-tuned version of sail/Sailor2-8B-Chat on the sft_sg_values_res_split dataset. It achieves the following results on the evaluation set:

• Loss: 0.1357

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-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.3715	0.1710	250	0.2821
0.1642	0.3419	500	0.1734
0.1431	0.5129	750	0.1512
0.1257	0.6839	1000	0.1415
0.1281	0.8548	1250	0.1359

Framework versions

• PEFT 0.15.2
• Transformers 4.51.1
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.1