babac902-74e0-4bde-a637-dafeb8b8482d

This model is a fine-tuned version of elyza/Llama-3-ELYZA-JP-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1751

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: 0.000206
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0004	1	3.2539
2.3008	0.0181	50	2.5440
2.1869	0.0362	100	2.7194
2.2702	0.0544	150	2.7566
2.2174	0.0725	200	2.4249
2.17	0.0906	250	2.3869
2.2559	0.1087	300	2.2846
2.2087	0.1268	350	2.2185
2.2695	0.1450	400	2.1837
2.0524	0.1631	450	2.1747
2.0353	0.1812	500	2.1751

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1