learning_rate: 0.0001
train_batch_size: 2
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 3.0

Training Loss	Epoch	Step	Validation Loss	Token Acc
0.8879	0.1112	50	0.9205	0.7307
0.9361	0.2223	100	0.9695	0.7251
0.9143	0.3335	150	0.9582	0.7284
0.9061	0.4447	200	0.9360	0.7338
0.9164	0.5559	250	0.9249	0.7373
0.8928	0.6670	300	0.9032	0.7426
0.8861	0.7782	350	0.9465	0.7387
0.8532	0.8894	400	0.8842	0.7466
0.8425	1.0	450	0.8555	0.7530
0.7430	1.1112	500	0.8398	0.7562
0.7212	1.2223	550	0.8253	0.7598
0.7343	1.3335	600	0.8107	0.7628
0.7036	1.4447	650	0.7920	0.7658
0.6966	1.5559	700	0.7733	0.7702
0.6805	1.6670	750	0.7599	0.7727
0.6592	1.7782	800	0.7404	0.7773
0.6510	1.8894	850	0.7213	0.7818
0.6150	2.0	900	0.7080	0.7849
0.5527	2.1112	950	0.6994	0.7874
0.5414	2.2223	1000	0.6898	0.7909
0.5015	2.3335	1050	0.6823	0.7930
0.5122	2.4447	1100	0.6704	0.7955
0.5033	2.5559	1150	0.6639	0.7968
0.4931	2.6670	1200	0.6587	0.7981
0.5119	2.7782	1250	0.6563	0.7990
0.5115	2.8894	1300	0.6549	0.7989
0.5185	3.0	1350	0.6546	0.7991

boyuzhuGPT/qwen2_5_omni_all_1016

qwen2_5_omni_all_1016