myBit-Llama2-jp-127M-2B4TLike-aozora

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.3144

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: 0.0024
• train_batch_size: 24
• eval_batch_size: 24
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 96
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
7.0941	0.0883	100	5.6975
5.3346	0.1765	200	5.1802
5.1111	0.2648	300	5.0230
4.9794	0.3530	400	4.8783
4.8274	0.4413	500	4.7476
4.6969	0.5296	600	4.6465
4.6092	0.6178	700	4.5655
4.5154	0.7061	800	4.4905
4.4336	0.7944	900	4.4462
4.4034	0.8826	1000	4.3721
4.2916	0.9709	1100	4.3144

Framework versions

• Transformers 4.47.1
• Pytorch 2.6.0+cu124
• Datasets 3.5.1
• Tokenizers 0.21.1