{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.036751194413818446, "eval_steps": 9, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0003675119441381845, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0003675119441381845, "eval_loss": NaN, "eval_runtime": 67.0217, "eval_samples_per_second": 34.183, "eval_steps_per_second": 4.282, "step": 1 }, { "epoch": 0.000735023888276369, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0011025358324145535, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.001470047776552738, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0018375597206909224, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.002205071664829107, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.0025725836089672913, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.002940095553105476, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.0033076074972436605, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.0033076074972436605, "eval_loss": NaN, "eval_runtime": 66.1189, "eval_samples_per_second": 34.65, "eval_steps_per_second": 4.341, "step": 9 }, { "epoch": 0.003675119441381845, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.00404263138552003, "grad_norm": NaN, "learning_rate": 9.99695413509548e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.004410143329658214, "grad_norm": NaN, "learning_rate": 9.987820251299122e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.004777655273796398, "grad_norm": NaN, "learning_rate": 9.972609476841367e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.005145167217934583, "grad_norm": NaN, "learning_rate": 9.951340343707852e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.005512679162072767, "grad_norm": NaN, "learning_rate": 9.924038765061042e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.005880191106210952, "grad_norm": NaN, "learning_rate": 9.890738003669029e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.006247703050349137, "grad_norm": NaN, "learning_rate": 9.851478631379982e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.006615214994487321, "grad_norm": NaN, "learning_rate": 9.806308479691595e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.006615214994487321, "eval_loss": NaN, "eval_runtime": 66.0631, "eval_samples_per_second": 34.679, "eval_steps_per_second": 4.344, "step": 18 }, { "epoch": 0.006982726938625505, "grad_norm": NaN, "learning_rate": 9.755282581475769e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.00735023888276369, "grad_norm": NaN, "learning_rate": 9.698463103929542e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.007717750826901874, "grad_norm": NaN, "learning_rate": 9.635919272833938e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.00808526277104006, "grad_norm": NaN, "learning_rate": 9.567727288213005e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.008452774715178243, "grad_norm": NaN, "learning_rate": 9.493970231495835e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.008820286659316428, "grad_norm": NaN, "learning_rate": 9.414737964294636e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.009187798603454611, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.009555310547592797, "grad_norm": NaN, "learning_rate": 9.24024048078213e-05, "loss": 0.0, "step": 26 }, { "epoch": 0.009922822491730982, "grad_norm": NaN, "learning_rate": 9.145187862775209e-05, "loss": 0.0, "step": 27 }, { "epoch": 0.009922822491730982, "eval_loss": NaN, "eval_runtime": 66.0896, "eval_samples_per_second": 34.665, "eval_steps_per_second": 4.343, "step": 27 }, { "epoch": 0.010290334435869165, "grad_norm": NaN, "learning_rate": 9.045084971874738e-05, "loss": 0.0, "step": 28 }, { "epoch": 0.01065784638000735, "grad_norm": NaN, "learning_rate": 8.940053768033609e-05, "loss": 0.0, "step": 29 }, { "epoch": 0.011025358324145534, "grad_norm": NaN, "learning_rate": 8.83022221559489e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.01139287026828372, "grad_norm": NaN, "learning_rate": 8.715724127386972e-05, "loss": 0.0, "step": 31 }, { "epoch": 0.011760382212421904, "grad_norm": NaN, "learning_rate": 8.596699001693255e-05, "loss": 0.0, "step": 32 }, { "epoch": 0.012127894156560088, "grad_norm": NaN, "learning_rate": 8.473291852294987e-05, "loss": 0.0, "step": 33 }, { "epoch": 0.012495406100698273, "grad_norm": NaN, "learning_rate": 8.345653031794292e-05, "loss": 0.0, "step": 34 }, { "epoch": 0.012862918044836457, "grad_norm": NaN, "learning_rate": 8.213938048432697e-05, "loss": 0.0, "step": 35 }, { "epoch": 0.013230429988974642, "grad_norm": NaN, "learning_rate": 8.07830737662829e-05, "loss": 0.0, "step": 36 }, { "epoch": 0.013230429988974642, "eval_loss": NaN, "eval_runtime": 66.0752, "eval_samples_per_second": 34.673, "eval_steps_per_second": 4.344, "step": 36 }, { "epoch": 0.013597941933112825, "grad_norm": NaN, "learning_rate": 7.938926261462366e-05, "loss": 0.0, "step": 37 }, { "epoch": 0.01396545387725101, "grad_norm": NaN, "learning_rate": 7.795964517353735e-05, "loss": 0.0, "step": 38 }, { "epoch": 0.014332965821389196, "grad_norm": NaN, "learning_rate": 7.649596321166024e-05, "loss": 0.0, "step": 39 }, { "epoch": 0.01470047776552738, "grad_norm": NaN, "learning_rate": 7.500000000000001e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.015067989709665565, "grad_norm": NaN, "learning_rate": 7.347357813929454e-05, "loss": 0.0, "step": 41 }, { "epoch": 0.015435501653803748, "grad_norm": NaN, "learning_rate": 7.191855733945387e-05, "loss": 0.0, "step": 42 }, { "epoch": 0.015803013597941933, "grad_norm": NaN, "learning_rate": 7.033683215379002e-05, "loss": 0.0, "step": 43 }, { "epoch": 0.01617052554208012, "grad_norm": NaN, "learning_rate": 6.873032967079561e-05, "loss": 0.0, "step": 44 }, { "epoch": 0.016538037486218304, "grad_norm": NaN, "learning_rate": 6.710100716628344e-05, "loss": 0.0, "step": 45 }, { "epoch": 0.016538037486218304, "eval_loss": NaN, "eval_runtime": 66.0779, "eval_samples_per_second": 34.671, "eval_steps_per_second": 4.343, "step": 45 }, { "epoch": 0.016905549430356485, "grad_norm": NaN, "learning_rate": 6.545084971874738e-05, "loss": 0.0, "step": 46 }, { "epoch": 0.01727306137449467, "grad_norm": NaN, "learning_rate": 6.378186779084995e-05, "loss": 0.0, "step": 47 }, { "epoch": 0.017640573318632856, "grad_norm": NaN, "learning_rate": 6.209609477998338e-05, "loss": 0.0, "step": 48 }, { "epoch": 0.01800808526277104, "grad_norm": NaN, "learning_rate": 6.0395584540887963e-05, "loss": 0.0, "step": 49 }, { "epoch": 0.018375597206909223, "grad_norm": NaN, "learning_rate": 5.868240888334653e-05, "loss": 0.0, "step": 50 }, { "epoch": 0.018743109151047408, "grad_norm": NaN, "learning_rate": 5.695865504800327e-05, "loss": 0.0, "step": 51 }, { "epoch": 0.019110621095185593, "grad_norm": NaN, "learning_rate": 5.522642316338268e-05, "loss": 0.0, "step": 52 }, { "epoch": 0.01947813303932378, "grad_norm": NaN, "learning_rate": 5.348782368720626e-05, "loss": 0.0, "step": 53 }, { "epoch": 0.019845644983461964, "grad_norm": NaN, "learning_rate": 5.174497483512506e-05, "loss": 0.0, "step": 54 }, { "epoch": 0.019845644983461964, "eval_loss": NaN, "eval_runtime": 66.1727, "eval_samples_per_second": 34.622, "eval_steps_per_second": 4.337, "step": 54 }, { "epoch": 0.020213156927600145, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 55 }, { "epoch": 0.02058066887173833, "grad_norm": NaN, "learning_rate": 4.825502516487497e-05, "loss": 0.0, "step": 56 }, { "epoch": 0.020948180815876516, "grad_norm": NaN, "learning_rate": 4.6512176312793736e-05, "loss": 0.0, "step": 57 }, { "epoch": 0.0213156927600147, "grad_norm": NaN, "learning_rate": 4.477357683661734e-05, "loss": 0.0, "step": 58 }, { "epoch": 0.021683204704152886, "grad_norm": NaN, "learning_rate": 4.3041344951996746e-05, "loss": 0.0, "step": 59 }, { "epoch": 0.022050716648291068, "grad_norm": NaN, "learning_rate": 4.131759111665349e-05, "loss": 0.0, "step": 60 }, { "epoch": 0.022418228592429253, "grad_norm": NaN, "learning_rate": 3.960441545911204e-05, "loss": 0.0, "step": 61 }, { "epoch": 0.02278574053656744, "grad_norm": NaN, "learning_rate": 3.790390522001662e-05, "loss": 0.0, "step": 62 }, { "epoch": 0.023153252480705624, "grad_norm": NaN, "learning_rate": 3.6218132209150045e-05, "loss": 0.0, "step": 63 }, { "epoch": 0.023153252480705624, "eval_loss": NaN, "eval_runtime": 66.173, "eval_samples_per_second": 34.621, "eval_steps_per_second": 4.337, "step": 63 }, { "epoch": 0.02352076442484381, "grad_norm": NaN, "learning_rate": 3.4549150281252636e-05, "loss": 0.0, "step": 64 }, { "epoch": 0.02388827636898199, "grad_norm": NaN, "learning_rate": 3.289899283371657e-05, "loss": 0.0, "step": 65 }, { "epoch": 0.024255788313120176, "grad_norm": NaN, "learning_rate": 3.12696703292044e-05, "loss": 0.0, "step": 66 }, { "epoch": 0.02462330025725836, "grad_norm": NaN, "learning_rate": 2.9663167846209998e-05, "loss": 0.0, "step": 67 }, { "epoch": 0.024990812201396546, "grad_norm": NaN, "learning_rate": 2.8081442660546125e-05, "loss": 0.0, "step": 68 }, { "epoch": 0.025358324145534728, "grad_norm": NaN, "learning_rate": 2.6526421860705473e-05, "loss": 0.0, "step": 69 }, { "epoch": 0.025725836089672913, "grad_norm": NaN, "learning_rate": 2.500000000000001e-05, "loss": 0.0, "step": 70 }, { "epoch": 0.0260933480338111, "grad_norm": NaN, "learning_rate": 2.350403678833976e-05, "loss": 0.0, "step": 71 }, { "epoch": 0.026460859977949284, "grad_norm": NaN, "learning_rate": 2.2040354826462668e-05, "loss": 0.0, "step": 72 }, { "epoch": 0.026460859977949284, "eval_loss": NaN, "eval_runtime": 66.082, "eval_samples_per_second": 34.669, "eval_steps_per_second": 4.343, "step": 72 }, { "epoch": 0.02682837192208747, "grad_norm": NaN, "learning_rate": 2.061073738537635e-05, "loss": 0.0, "step": 73 }, { "epoch": 0.02719588386622565, "grad_norm": NaN, "learning_rate": 1.9216926233717085e-05, "loss": 0.0, "step": 74 }, { "epoch": 0.027563395810363836, "grad_norm": NaN, "learning_rate": 1.7860619515673033e-05, "loss": 0.0, "step": 75 }, { "epoch": 0.02793090775450202, "grad_norm": NaN, "learning_rate": 1.6543469682057106e-05, "loss": 0.0, "step": 76 }, { "epoch": 0.028298419698640206, "grad_norm": NaN, "learning_rate": 1.526708147705013e-05, "loss": 0.0, "step": 77 }, { "epoch": 0.02866593164277839, "grad_norm": NaN, "learning_rate": 1.4033009983067452e-05, "loss": 0.0, "step": 78 }, { "epoch": 0.029033443586916573, "grad_norm": NaN, "learning_rate": 1.2842758726130283e-05, "loss": 0.0, "step": 79 }, { "epoch": 0.02940095553105476, "grad_norm": NaN, "learning_rate": 1.1697777844051105e-05, "loss": 0.0, "step": 80 }, { "epoch": 0.029768467475192944, "grad_norm": NaN, "learning_rate": 1.0599462319663905e-05, "loss": 0.0, "step": 81 }, { "epoch": 0.029768467475192944, "eval_loss": NaN, "eval_runtime": 66.08, "eval_samples_per_second": 34.67, "eval_steps_per_second": 4.343, "step": 81 }, { "epoch": 0.03013597941933113, "grad_norm": NaN, "learning_rate": 9.549150281252633e-06, "loss": 0.0, "step": 82 }, { "epoch": 0.030503491363469314, "grad_norm": NaN, "learning_rate": 8.548121372247918e-06, "loss": 0.0, "step": 83 }, { "epoch": 0.030871003307607496, "grad_norm": NaN, "learning_rate": 7.597595192178702e-06, "loss": 0.0, "step": 84 }, { "epoch": 0.03123851525174568, "grad_norm": NaN, "learning_rate": 6.698729810778065e-06, "loss": 0.0, "step": 85 }, { "epoch": 0.031606027195883866, "grad_norm": NaN, "learning_rate": 5.852620357053651e-06, "loss": 0.0, "step": 86 }, { "epoch": 0.03197353914002205, "grad_norm": NaN, "learning_rate": 5.060297685041659e-06, "loss": 0.0, "step": 87 }, { "epoch": 0.03234105108416024, "grad_norm": NaN, "learning_rate": 4.322727117869951e-06, "loss": 0.0, "step": 88 }, { "epoch": 0.03270856302829842, "grad_norm": NaN, "learning_rate": 3.6408072716606346e-06, "loss": 0.0, "step": 89 }, { "epoch": 0.03307607497243661, "grad_norm": NaN, "learning_rate": 3.0153689607045845e-06, "loss": 0.0, "step": 90 }, { "epoch": 0.03307607497243661, "eval_loss": NaN, "eval_runtime": 66.0752, "eval_samples_per_second": 34.673, "eval_steps_per_second": 4.344, "step": 90 }, { "epoch": 0.033443586916574786, "grad_norm": NaN, "learning_rate": 2.4471741852423237e-06, "loss": 0.0, "step": 91 }, { "epoch": 0.03381109886071297, "grad_norm": NaN, "learning_rate": 1.9369152030840556e-06, "loss": 0.0, "step": 92 }, { "epoch": 0.034178610804851156, "grad_norm": NaN, "learning_rate": 1.4852136862001764e-06, "loss": 0.0, "step": 93 }, { "epoch": 0.03454612274898934, "grad_norm": NaN, "learning_rate": 1.0926199633097157e-06, "loss": 0.0, "step": 94 }, { "epoch": 0.03491363469312753, "grad_norm": NaN, "learning_rate": 7.596123493895991e-07, "loss": 0.0, "step": 95 }, { "epoch": 0.03528114663726571, "grad_norm": NaN, "learning_rate": 4.865965629214819e-07, "loss": 0.0, "step": 96 }, { "epoch": 0.0356486585814039, "grad_norm": NaN, "learning_rate": 2.7390523158633554e-07, "loss": 0.0, "step": 97 }, { "epoch": 0.03601617052554208, "grad_norm": NaN, "learning_rate": 1.2179748700879012e-07, "loss": 0.0, "step": 98 }, { "epoch": 0.03638368246968027, "grad_norm": NaN, "learning_rate": 3.04586490452119e-08, "loss": 0.0, "step": 99 }, { "epoch": 0.03638368246968027, "eval_loss": NaN, "eval_runtime": 66.0834, "eval_samples_per_second": 34.668, "eval_steps_per_second": 4.343, "step": 99 }, { "epoch": 0.036751194413818446, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 100 } ], "logging_steps": 1, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.02936877203456e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }