learning_rate: 0.0005
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 16
total_train_batch_size: 64
total_eval_batch_size: 4
optimizer: Use adamw_torch 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: 1000
num_epochs: 1

Training Loss	Epoch	Step	Validation Loss
4.6741	0.0552	1000	4.6001
3.6587	0.1105	2000	3.7151
3.2297	0.1657	3000	3.2263
3.0288	0.2210	4000	3.0349
2.9584	0.2762	5000	2.9393
2.9657	0.3315	6000	2.9893
2.8654	0.3867	7000	2.8074
2.6982	0.4420	8000	2.7580
2.7292	0.4972	9000	2.7214
2.7568	0.5525	10000	2.6956
2.6141	0.6077	11000	2.6669
2.631	0.6630	12000	2.6421
2.6837	0.7182	13000	2.6185
2.6257	0.7734	14000	2.6032
2.5669	0.8287	15000	2.5918
2.6383	0.8839	16000	2.5836
2.5749	0.9392	17000	2.5796
2.613	0.9944	18000	2.5784

deqing/llama-3.2-350M-fourier

llama-3.2-350M-fourier