{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 695, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.028782155063860407, "grad_norm": 0.25469791889190674, "learning_rate": 0.00019453237410071942, "loss": 0.6626, "step": 20 }, { "epoch": 0.057564310127720814, "grad_norm": 0.26558175683021545, "learning_rate": 0.00018877697841726622, "loss": 0.53, "step": 40 }, { "epoch": 0.08634646519158122, "grad_norm": 0.2776390314102173, "learning_rate": 0.00018302158273381295, "loss": 0.5091, "step": 60 }, { "epoch": 0.11512862025544163, "grad_norm": 0.25934168696403503, "learning_rate": 0.00017726618705035972, "loss": 0.4938, "step": 80 }, { "epoch": 0.14391077531930202, "grad_norm": 0.24628081917762756, "learning_rate": 0.00017151079136690648, "loss": 0.4691, "step": 100 }, { "epoch": 0.17269293038316244, "grad_norm": 0.24218925833702087, "learning_rate": 0.00016575539568345325, "loss": 0.4648, "step": 120 }, { "epoch": 0.20147508544702283, "grad_norm": 0.2658531963825226, "learning_rate": 0.00016, "loss": 0.466, "step": 140 }, { "epoch": 0.23025724051088325, "grad_norm": 0.2526750862598419, "learning_rate": 0.00015424460431654678, "loss": 0.4569, "step": 160 }, { "epoch": 0.25903939557474365, "grad_norm": 0.2415703982114792, "learning_rate": 0.00014848920863309352, "loss": 0.4557, "step": 180 }, { "epoch": 0.28782155063860404, "grad_norm": 0.26834964752197266, "learning_rate": 0.0001427338129496403, "loss": 0.4517, "step": 200 }, { "epoch": 0.3166037057024645, "grad_norm": 0.26203978061676025, "learning_rate": 0.00013697841726618705, "loss": 0.4455, "step": 220 }, { "epoch": 0.3453858607663249, "grad_norm": 0.2680965065956116, "learning_rate": 0.00013122302158273384, "loss": 0.4492, "step": 240 }, { "epoch": 0.3741680158301853, "grad_norm": 0.2564185857772827, "learning_rate": 0.00012546762589928058, "loss": 0.4438, "step": 260 }, { "epoch": 0.40295017089404567, "grad_norm": 0.26110026240348816, "learning_rate": 0.00011971223021582734, "loss": 0.443, "step": 280 }, { "epoch": 0.4317323259579061, "grad_norm": 0.262195348739624, "learning_rate": 0.00011395683453237412, "loss": 0.4309, "step": 300 }, { "epoch": 0.4605144810217665, "grad_norm": 0.25222480297088623, "learning_rate": 0.00010820143884892087, "loss": 0.4405, "step": 320 }, { "epoch": 0.4892966360856269, "grad_norm": 0.27905553579330444, "learning_rate": 0.00010244604316546762, "loss": 0.4329, "step": 340 }, { "epoch": 0.5180787911494873, "grad_norm": 0.2416505217552185, "learning_rate": 9.66906474820144e-05, "loss": 0.4312, "step": 360 }, { "epoch": 0.5468609462133477, "grad_norm": 0.2609241008758545, "learning_rate": 9.093525179856116e-05, "loss": 0.4363, "step": 380 }, { "epoch": 0.5756431012772081, "grad_norm": 0.24666130542755127, "learning_rate": 8.517985611510792e-05, "loss": 0.4302, "step": 400 }, { "epoch": 0.6044252563410686, "grad_norm": 0.24873825907707214, "learning_rate": 7.942446043165468e-05, "loss": 0.4266, "step": 420 }, { "epoch": 0.633207411404929, "grad_norm": 0.2555878460407257, "learning_rate": 7.366906474820145e-05, "loss": 0.4287, "step": 440 }, { "epoch": 0.6619895664687894, "grad_norm": 0.2684342861175537, "learning_rate": 6.791366906474821e-05, "loss": 0.4243, "step": 460 }, { "epoch": 0.6907717215326498, "grad_norm": 0.26070982217788696, "learning_rate": 6.215827338129496e-05, "loss": 0.4259, "step": 480 }, { "epoch": 0.7195538765965102, "grad_norm": 0.27525463700294495, "learning_rate": 5.6402877697841726e-05, "loss": 0.4281, "step": 500 }, { "epoch": 0.7483360316603705, "grad_norm": 0.2588309347629547, "learning_rate": 5.064748201438849e-05, "loss": 0.4153, "step": 520 }, { "epoch": 0.7771181867242309, "grad_norm": 0.2782978415489197, "learning_rate": 4.489208633093525e-05, "loss": 0.4237, "step": 540 }, { "epoch": 0.8059003417880913, "grad_norm": 0.2572264075279236, "learning_rate": 3.9136690647482014e-05, "loss": 0.4224, "step": 560 }, { "epoch": 0.8346824968519518, "grad_norm": 0.2893691062927246, "learning_rate": 3.338129496402878e-05, "loss": 0.4234, "step": 580 }, { "epoch": 0.8634646519158122, "grad_norm": 0.2681804895401001, "learning_rate": 2.762589928057554e-05, "loss": 0.4204, "step": 600 }, { "epoch": 0.8922468069796726, "grad_norm": 0.2793126702308655, "learning_rate": 2.1870503597122302e-05, "loss": 0.423, "step": 620 }, { "epoch": 0.921028962043533, "grad_norm": 0.27879542112350464, "learning_rate": 1.6115107913669063e-05, "loss": 0.4158, "step": 640 }, { "epoch": 0.9498111171073934, "grad_norm": 0.2639375329017639, "learning_rate": 1.0359712230215828e-05, "loss": 0.419, "step": 660 }, { "epoch": 0.9785932721712538, "grad_norm": 0.25821879506111145, "learning_rate": 4.60431654676259e-06, "loss": 0.4172, "step": 680 } ], "logging_steps": 20, "max_steps": 695, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.5764131273375744e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }