learning_rate: 5e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 256
total_eval_batch_size: 64
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_ratio: 0.05
num_epochs: 1.0

Training Loss	Epoch	Step	Validation Loss
1.3348	0.0551	200	1.2704
1.0411	0.1101	400	1.0435
1.0483	0.1652	600	0.9694
0.8801	0.2202	800	0.9227
0.8996	0.2753	1000	0.8888
0.8682	0.3303	1200	0.8648
0.8757	0.3854	1400	0.8468
0.8441	0.4404	1600	0.8311
0.8197	0.4955	1800	0.8206
0.7807	0.5505	2000	0.8090
0.7757	0.6056	2200	0.8015
0.7818	0.6607	2400	0.7957
0.8235	0.7157	2600	0.7915
0.7854	0.7708	2800	0.7883
0.7958	0.8258	3000	0.7863
0.8192	0.8809	3200	0.7829
0.765	0.9359	3400	0.7824
0.7939	0.9910	3600	0.7824

yakazimir/smollm_1_7B_tulu3

HuggingFaceTB/SmolLM2-1.7B