KoAlpaca-Polyglot-5.8B-dialoguSum_ko_bySolar

This model is a fine-tuned version of beomi/KoAlpaca-Polyglot-5.8B on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.0898
• eval_runtime: 77.7261
• eval_samples_per_second: 6.42
• eval_steps_per_second: 0.811
• epoch: 2.0140
• step: 1568

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 20
• mixed_precision_training: Native AMP

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.1.0
• Datasets 2.21.0
• Tokenizers 0.19.1