{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.2559508574353724, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.012797542871768621, "grad_norm": 2.0586953163146973, "learning_rate": 2.9872024571282313e-05, "loss": 2.972, "step": 50 }, { "epoch": 0.025595085743537242, "grad_norm": 6.272576808929443, "learning_rate": 2.974404914256463e-05, "loss": 0.2881, "step": 100 }, { "epoch": 0.03839262861530586, "grad_norm": 1.1563491821289062, "learning_rate": 2.9616073713846942e-05, "loss": 0.0381, "step": 150 }, { "epoch": 0.051190171487074485, "grad_norm": 0.1215643510222435, "learning_rate": 2.9488098285129255e-05, "loss": 0.0111, "step": 200 }, { "epoch": 0.0639877143588431, "grad_norm": 0.5516662001609802, "learning_rate": 2.9360122856411568e-05, "loss": 0.0069, "step": 250 }, { "epoch": 0.07678525723061172, "grad_norm": 0.05641397088766098, "learning_rate": 2.9232147427693884e-05, "loss": 0.0044, "step": 300 }, { "epoch": 0.08958280010238034, "grad_norm": 0.0993661880493164, "learning_rate": 2.9104171998976196e-05, "loss": 0.0058, "step": 350 }, { "epoch": 0.10238034297414897, "grad_norm": 0.30727025866508484, "learning_rate": 2.897619657025851e-05, "loss": 0.0039, "step": 400 }, { "epoch": 0.11517788584591758, "grad_norm": 0.2906234860420227, "learning_rate": 2.8848221141540825e-05, "loss": 0.0028, "step": 450 }, { "epoch": 0.1279754287176862, "grad_norm": 0.04104916378855705, "learning_rate": 2.872024571282314e-05, "loss": 0.0025, "step": 500 }, { "epoch": 0.14077297158945482, "grad_norm": 0.32165050506591797, "learning_rate": 2.8592270284105454e-05, "loss": 0.0036, "step": 550 }, { "epoch": 0.15357051446122344, "grad_norm": 0.27632883191108704, "learning_rate": 2.8464294855387767e-05, "loss": 0.0026, "step": 600 }, { "epoch": 0.16636805733299206, "grad_norm": 0.0463576540350914, "learning_rate": 2.833631942667008e-05, "loss": 0.0036, "step": 650 }, { "epoch": 0.1791656002047607, "grad_norm": 0.001918585505336523, "learning_rate": 2.8208343997952395e-05, "loss": 0.0025, "step": 700 }, { "epoch": 0.1919631430765293, "grad_norm": 0.01721811108291149, "learning_rate": 2.8080368569234708e-05, "loss": 0.002, "step": 750 }, { "epoch": 0.20476068594829794, "grad_norm": 0.013624100014567375, "learning_rate": 2.795239314051702e-05, "loss": 0.0012, "step": 800 }, { "epoch": 0.21755822882006653, "grad_norm": 1.1703804731369019, "learning_rate": 2.7824417711799333e-05, "loss": 0.0017, "step": 850 }, { "epoch": 0.23035577169183516, "grad_norm": 0.0006212255684658885, "learning_rate": 2.769644228308165e-05, "loss": 0.0031, "step": 900 }, { "epoch": 0.24315331456360378, "grad_norm": 0.35954833030700684, "learning_rate": 2.7568466854363962e-05, "loss": 0.002, "step": 950 }, { "epoch": 0.2559508574353724, "grad_norm": 0.0013237381353974342, "learning_rate": 2.7440491425646275e-05, "loss": 0.0014, "step": 1000 } ], "logging_steps": 50, "max_steps": 11721, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }