{ "best_global_step": 500, "best_metric": 0.4887394309043884, "best_model_checkpoint": "./qwen3-4b-2507-ru-lora/checkpoint-500", "epoch": 0.5710206995003569, "eval_steps": 500, "global_step": 500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.11420413990007137, "grad_norm": 0.1101919561624527, "learning_rate": 9.900000000000001e-05, "loss": 1.1473062133789063, "step": 100 }, { "epoch": 0.22840827980014275, "grad_norm": 0.09405623376369476, "learning_rate": 9.832203389830509e-05, "loss": 0.797086181640625, "step": 200 }, { "epoch": 0.3426124197002141, "grad_norm": 0.1505233645439148, "learning_rate": 9.66271186440678e-05, "loss": 0.8210951232910156, "step": 300 }, { "epoch": 0.4568165596002855, "grad_norm": 0.09275370091199875, "learning_rate": 9.493220338983051e-05, "loss": 0.7762732696533203, "step": 400 }, { "epoch": 0.5710206995003569, "grad_norm": 0.15582314133644104, "learning_rate": 9.323728813559323e-05, "loss": 0.79928955078125, "step": 500 }, { "epoch": 0.5710206995003569, "eval_loss": 0.4887394309043884, "eval_runtime": 85.2625, "eval_samples_per_second": 4.328, "eval_steps_per_second": 4.328, "step": 500 } ], "logging_steps": 100, "max_steps": 6000, "num_input_tokens_seen": 0, "num_train_epochs": 7, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.60682342187008e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }