{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.060802594244021076, "eval_steps": 25, "global_step": 75, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0008107012565869477, "grad_norm": NaN, "learning_rate": 3.3333333333333335e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0008107012565869477, "eval_loss": NaN, "eval_runtime": 114.6733, "eval_samples_per_second": 9.061, "eval_steps_per_second": 4.535, "step": 1 }, { "epoch": 0.0016214025131738954, "grad_norm": NaN, "learning_rate": 6.666666666666667e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0024321037697608433, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 3 }, { "epoch": 0.0032428050263477908, "grad_norm": NaN, "learning_rate": 9.99524110790929e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.004053506282934738, "grad_norm": NaN, "learning_rate": 9.980973490458728e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.004864207539521687, "grad_norm": NaN, "learning_rate": 9.957224306869053e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.005674908796108634, "grad_norm": NaN, "learning_rate": 9.924038765061042e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.0064856100526955816, "grad_norm": NaN, "learning_rate": 9.881480035599667e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.007296311309282529, "grad_norm": NaN, "learning_rate": 9.829629131445342e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.008107012565869477, "grad_norm": NaN, "learning_rate": 9.768584753741134e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.008917713822456425, "grad_norm": NaN, "learning_rate": 9.698463103929542e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.009728415079043373, "grad_norm": NaN, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.01053911633563032, "grad_norm": NaN, "learning_rate": 9.53153893518325e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.011349817592217268, "grad_norm": NaN, "learning_rate": 9.435054165891109e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.012160518848804215, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.012971220105391163, "grad_norm": NaN, "learning_rate": 9.21695722906443e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.013781921361978111, "grad_norm": NaN, "learning_rate": 9.09576022144496e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.014592622618565058, "grad_norm": NaN, "learning_rate": 8.966766701456177e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.015403323875152006, "grad_norm": NaN, "learning_rate": 8.83022221559489e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.016214025131738953, "grad_norm": NaN, "learning_rate": 8.68638668405062e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.017024726388325903, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.01783542764491285, "grad_norm": NaN, "learning_rate": 8.377951038078302e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.018646128901499796, "grad_norm": NaN, "learning_rate": 8.213938048432697e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.019456830158086746, "grad_norm": NaN, "learning_rate": 8.043807145043604e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.020267531414673693, "grad_norm": NaN, "learning_rate": 7.86788218175523e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.020267531414673693, "eval_loss": NaN, "eval_runtime": 114.2701, "eval_samples_per_second": 9.092, "eval_steps_per_second": 4.551, "step": 25 }, { "epoch": 0.02107823267126064, "grad_norm": NaN, "learning_rate": 7.68649804173412e-05, "loss": 0.0, "step": 26 }, { "epoch": 0.02188893392784759, "grad_norm": NaN, "learning_rate": 7.500000000000001e-05, "loss": 0.0, "step": 27 }, { "epoch": 0.022699635184434536, "grad_norm": NaN, "learning_rate": 7.308743066175172e-05, "loss": 0.0, "step": 28 }, { "epoch": 0.023510336441021483, "grad_norm": NaN, "learning_rate": 7.113091308703498e-05, "loss": 0.0, "step": 29 }, { "epoch": 0.02432103769760843, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.02513173895419538, "grad_norm": NaN, "learning_rate": 6.710100716628344e-05, "loss": 0.0, "step": 31 }, { "epoch": 0.025942440210782326, "grad_norm": NaN, "learning_rate": 6.503528997521366e-05, "loss": 0.0, "step": 32 }, { "epoch": 0.026753141467369273, "grad_norm": NaN, "learning_rate": 6.294095225512603e-05, "loss": 0.0, "step": 33 }, { "epoch": 0.027563842723956223, "grad_norm": NaN, "learning_rate": 6.0821980696905146e-05, "loss": 0.0, "step": 34 }, { "epoch": 0.02837454398054317, "grad_norm": NaN, "learning_rate": 5.868240888334653e-05, "loss": 0.0, "step": 35 }, { "epoch": 0.029185245237130116, "grad_norm": NaN, "learning_rate": 5.6526309611002594e-05, "loss": 0.0, "step": 36 }, { "epoch": 0.029995946493717066, "grad_norm": NaN, "learning_rate": 5.435778713738292e-05, "loss": 0.0, "step": 37 }, { "epoch": 0.030806647750304013, "grad_norm": NaN, "learning_rate": 5.218096936826681e-05, "loss": 0.0, "step": 38 }, { "epoch": 0.03161734900689096, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 39 }, { "epoch": 0.032428050263477906, "grad_norm": NaN, "learning_rate": 4.781903063173321e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.033238751520064856, "grad_norm": NaN, "learning_rate": 4.564221286261709e-05, "loss": 0.0, "step": 41 }, { "epoch": 0.034049452776651806, "grad_norm": NaN, "learning_rate": 4.347369038899744e-05, "loss": 0.0, "step": 42 }, { "epoch": 0.03486015403323875, "grad_norm": NaN, "learning_rate": 4.131759111665349e-05, "loss": 0.0, "step": 43 }, { "epoch": 0.0356708552898257, "grad_norm": NaN, "learning_rate": 3.917801930309486e-05, "loss": 0.0, "step": 44 }, { "epoch": 0.03648155654641265, "grad_norm": NaN, "learning_rate": 3.705904774487396e-05, "loss": 0.0, "step": 45 }, { "epoch": 0.03729225780299959, "grad_norm": NaN, "learning_rate": 3.4964710024786354e-05, "loss": 0.0, "step": 46 }, { "epoch": 0.03810295905958654, "grad_norm": NaN, "learning_rate": 3.289899283371657e-05, "loss": 0.0, "step": 47 }, { "epoch": 0.03891366031617349, "grad_norm": NaN, "learning_rate": 3.086582838174551e-05, "loss": 0.0, "step": 48 }, { "epoch": 0.039724361572760436, "grad_norm": NaN, "learning_rate": 2.886908691296504e-05, "loss": 0.0, "step": 49 }, { "epoch": 0.040535062829347386, "grad_norm": NaN, "learning_rate": 2.6912569338248315e-05, "loss": 0.0, "step": 50 }, { "epoch": 0.040535062829347386, "eval_loss": NaN, "eval_runtime": 113.9853, "eval_samples_per_second": 9.115, "eval_steps_per_second": 4.562, "step": 50 }, { "epoch": 0.041345764085934336, "grad_norm": NaN, "learning_rate": 2.500000000000001e-05, "loss": 0.0, "step": 51 }, { "epoch": 0.04215646534252128, "grad_norm": NaN, "learning_rate": 2.3135019582658802e-05, "loss": 0.0, "step": 52 }, { "epoch": 0.04296716659910823, "grad_norm": NaN, "learning_rate": 2.132117818244771e-05, "loss": 0.0, "step": 53 }, { "epoch": 0.04377786785569518, "grad_norm": NaN, "learning_rate": 1.9561928549563968e-05, "loss": 0.0, "step": 54 }, { "epoch": 0.04458856911228212, "grad_norm": NaN, "learning_rate": 1.7860619515673033e-05, "loss": 0.0, "step": 55 }, { "epoch": 0.04539927036886907, "grad_norm": NaN, "learning_rate": 1.622048961921699e-05, "loss": 0.0, "step": 56 }, { "epoch": 0.04620997162545602, "grad_norm": NaN, "learning_rate": 1.4644660940672627e-05, "loss": 0.0, "step": 57 }, { "epoch": 0.047020672882042966, "grad_norm": NaN, "learning_rate": 1.3136133159493802e-05, "loss": 0.0, "step": 58 }, { "epoch": 0.047831374138629916, "grad_norm": NaN, "learning_rate": 1.1697777844051105e-05, "loss": 0.0, "step": 59 }, { "epoch": 0.04864207539521686, "grad_norm": NaN, "learning_rate": 1.0332332985438248e-05, "loss": 0.0, "step": 60 }, { "epoch": 0.04945277665180381, "grad_norm": NaN, "learning_rate": 9.042397785550405e-06, "loss": 0.0, "step": 61 }, { "epoch": 0.05026347790839076, "grad_norm": NaN, "learning_rate": 7.830427709355725e-06, "loss": 0.0, "step": 62 }, { "epoch": 0.0510741791649777, "grad_norm": NaN, "learning_rate": 6.698729810778065e-06, "loss": 0.0, "step": 63 }, { "epoch": 0.05188488042156465, "grad_norm": NaN, "learning_rate": 5.649458341088915e-06, "loss": 0.0, "step": 64 }, { "epoch": 0.0526955816781516, "grad_norm": NaN, "learning_rate": 4.684610648167503e-06, "loss": 0.0, "step": 65 }, { "epoch": 0.053506282934738546, "grad_norm": NaN, "learning_rate": 3.8060233744356633e-06, "loss": 0.0, "step": 66 }, { "epoch": 0.054316984191325496, "grad_norm": NaN, "learning_rate": 3.0153689607045845e-06, "loss": 0.0, "step": 67 }, { "epoch": 0.055127685447912446, "grad_norm": NaN, "learning_rate": 2.314152462588659e-06, "loss": 0.0, "step": 68 }, { "epoch": 0.05593838670449939, "grad_norm": NaN, "learning_rate": 1.70370868554659e-06, "loss": 0.0, "step": 69 }, { "epoch": 0.05674908796108634, "grad_norm": NaN, "learning_rate": 1.1851996440033319e-06, "loss": 0.0, "step": 70 }, { "epoch": 0.05755978921767329, "grad_norm": NaN, "learning_rate": 7.596123493895991e-07, "loss": 0.0, "step": 71 }, { "epoch": 0.05837049047426023, "grad_norm": NaN, "learning_rate": 4.277569313094809e-07, "loss": 0.0, "step": 72 }, { "epoch": 0.05918119173084718, "grad_norm": NaN, "learning_rate": 1.9026509541272275e-07, "loss": 0.0, "step": 73 }, { "epoch": 0.05999189298743413, "grad_norm": NaN, "learning_rate": 4.7588920907110094e-08, "loss": 0.0, "step": 74 }, { "epoch": 0.060802594244021076, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 75 }, { "epoch": 0.060802594244021076, "eval_loss": NaN, "eval_runtime": 114.0325, "eval_samples_per_second": 9.111, "eval_steps_per_second": 4.56, "step": 75 } ], "logging_steps": 1, "max_steps": 75, "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": 1.1208807043773235e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }