e5e4c583-0353-4806-8dd1-75a503917270

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: 0.1520

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: 0.000208
• 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	0.0002	1	1.0450
0.7387	0.0092	50	0.5133
0.3546	0.0184	100	0.5435
0.3181	0.0276	150	0.7581
0.2833	0.0368	200	0.3113
0.2092	0.0460	250	0.2374
0.201	0.0552	300	0.2157
0.1952	0.0644	350	0.1693
0.185	0.0736	400	0.1573
0.1387	0.0828	450	0.1521
0.1649	0.0920	500	0.1520

Framework versions

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