ChatGLM3-6B-Chat-DcardStylePost-SFT

This model is a fine-tuned version of THUDM/chatglm3-6b on the dcardwom_zhcn_train dataset.

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-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.2.0a0+81ea7a4
• Datasets 2.19.0
• Tokenizers 0.19.1