ko-opt-350m

This model is a fine-tuned version of facebook/opt-350m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.3817

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
3.8648	0.1902	500	2.7538
2.4309	0.3804	1000	2.5691
1.9572	0.5706	1500	2.4733
1.788	0.7608	2000	2.4221
1.7197	0.9510	2500	2.3817

Framework versions

• Transformers 4.42.4
• Pytorch 2.2.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1