seallm-v3-4bit-qlora

This model is a fine-tuned version of SeaLLMs/SeaLLMs-v3-7B-Chat on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3075

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: 0.0003
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.4404	0.2036	50	1.4168
1.3317	0.4072	100	1.3570
1.3188	0.6108	150	1.3248
1.3048	0.8144	200	1.3075

Framework versions

• PEFT 0.13.0
• Transformers 4.45.1
• Pytorch 2.4.1
• Datasets 2.19.1
• Tokenizers 0.20.0