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: 750
num_epochs: 1

Training Loss	Epoch	Step	Validation Loss
5.0217	0.0437	500	5.5967
3.8655	0.0875	1000	4.9636
3.5798	0.1312	1500	4.5889
3.4331	0.1749	2000	4.3685
3.3371	0.2187	2500	4.2415
3.2912	0.2624	3000	4.1319
3.2255	0.3061	3500	4.0167
3.1863	0.3499	4000	3.9057
3.1549	0.3936	4500	3.7257
3.1237	0.4373	5000	3.6422
3.1066	0.4811	5500	3.5338
3.0786	0.5248	6000	3.4784
3.051	0.5686	6500	3.4182
3.0279	0.6123	7000	3.3684
3.0516	0.6560	7500	3.3032
3.1796	0.6998	8000	3.2376
3.1997	0.7435	8500	3.2020
3.172	0.7872	9000	3.1750
3.1487	0.8310	9500	3.1502
3.1296	0.8747	10000	3.1273
3.0886	0.9184	10500	3.1030
3.0402	0.9622	11000	3.0804

yusuke111/myBit-Llama2-jp-127M-2B4TLike-wiki-aozora-sort-swallow-tokenizer

myBit-Llama2-jp-127M-2B4TLike-wiki-aozora-sort-swallow-tokenizer