{"loss": 4.14815474, "token_acc": 0.33333333, "grad_norm": 225.0, "learning_rate": 9.7e-06, "memory(GiB)": 36.91, "train_speed(iter/s)": 0.020994, "epoch": 0.26666667, "global_step/max_steps": "1/9", "percentage": "11.11%", "elapsed_time": "47s", "remaining_time": "6m 18s"}
{"loss": 1.02935803, "token_acc": 0.88571429, "grad_norm": 35.0, "learning_rate": 4.13e-06, "memory(GiB)": 48.99, "train_speed(iter/s)": 0.020757, "epoch": 1.53333333, "global_step/max_steps": "5/9", "percentage": "55.56%", "elapsed_time": "4m 0s", "remaining_time": "3m 12s"}
{"eval_loss": 0.0812883, "eval_token_acc": 1.0, "eval_runtime": 0.8682, "eval_samples_per_second": 1.152, "eval_steps_per_second": 1.152, "epoch": 2.8, "global_step/max_steps": "9/9", "percentage": "100.00%", "elapsed_time": "7m 14s", "remaining_time": "0s"}
{"train_runtime": 503.9147, "train_samples_per_second": 0.351, "train_steps_per_second": 0.018, "total_flos": 9094847188497408.0, "train_loss": 0.97334064, "epoch": 2.8, "global_step/max_steps": "9/9", "percentage": "100.00%", "elapsed_time": "8m 23s", "remaining_time": "0s"}
{"model_parameter_info": "Qwen2_5OmniForConditionalGeneration: 5537.1206M Params (3397.1036M Trainable [61.3514%]), 1.9258M Buffers.", "last_model_checkpoint": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424/checkpoint-9", "best_model_checkpoint": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424/checkpoint-9", "best_metric": 0.0812883, "global_step": 9, "log_history": [{"loss": 4.1481547355651855, "token_acc": 0.3333333333333333, "grad_norm": 225.0, "learning_rate": 9.698463103929542e-06, "memory(GiB)": 36.91, "train_speed(iter/s)": 0.020994, "epoch": 0.26666666666666666, "step": 1}, {"loss": 1.0293580293655396, "token_acc": 0.8857142857142857, "grad_norm": 35.0, "learning_rate": 4.131759111665349e-06, "memory(GiB)": 48.99, "train_speed(iter/s)": 0.020757, "epoch": 1.5333333333333332, "step": 5}, {"eval_loss": 0.08128830045461655, "eval_token_acc": 1.0, "eval_runtime": 0.8682, "eval_samples_per_second": 1.152, "eval_steps_per_second": 1.152, "epoch": 2.8, "step": 9}, {"train_runtime": 503.9147, "train_samples_per_second": 0.351, "train_steps_per_second": 0.018, "total_flos": 9094847188497408.0, "train_loss": 0.9733406371540494, "epoch": 2.8, "step": 9}], "memory": 48.986328125}