| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006853853007699162, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.138470676932215e-05, | |
| "grad_norm": 14.466765403747559, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 6.6839, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.138470676932215e-05, | |
| "eval_loss": 6.981680870056152, | |
| "eval_runtime": 1042.4912, | |
| "eval_samples_per_second": 8.839, | |
| "eval_steps_per_second": 4.42, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001827694135386443, | |
| "grad_norm": 15.177668571472168, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 7.6193, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002741541203079665, | |
| "grad_norm": 15.911011695861816, | |
| "learning_rate": 0.0001, | |
| "loss": 6.6159, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003655388270772886, | |
| "grad_norm": 13.123141288757324, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 5.8581, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004569235338466108, | |
| "grad_norm": 13.573848724365234, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 5.3065, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000548308240615933, | |
| "grad_norm": 11.101449966430664, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.1295, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006396929473852551, | |
| "grad_norm": 8.28058910369873, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 3.1179, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007310776541545772, | |
| "grad_norm": 9.096076965332031, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 3.0133, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008224623609238994, | |
| "grad_norm": 8.431253433227539, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.8908, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009138470676932215, | |
| "grad_norm": 7.56347131729126, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 2.4816, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010052317744625437, | |
| "grad_norm": 9.71700668334961, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.5144, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001096616481231866, | |
| "grad_norm": 8.16706371307373, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1208, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001188001188001188, | |
| "grad_norm": 6.899288654327393, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.9213, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0012793858947705101, | |
| "grad_norm": 7.026676654815674, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 1.8953, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0013707706015398324, | |
| "grad_norm": 6.5173563957214355, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0217, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014621553083091544, | |
| "grad_norm": 6.742232799530029, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 1.8169, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0015535400150784766, | |
| "grad_norm": 5.812262535095215, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.9582, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0016449247218477988, | |
| "grad_norm": 6.068929672241211, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.9146, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0017363094286171209, | |
| "grad_norm": 5.802151203155518, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.1055, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.001827694135386443, | |
| "grad_norm": 6.522188663482666, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 1.6778, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019190788421557653, | |
| "grad_norm": 5.945748805999756, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.891, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0020104635489250873, | |
| "grad_norm": 4.804516315460205, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 1.6599, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0021018482556944096, | |
| "grad_norm": 5.1375732421875, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.6169, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002193232962463732, | |
| "grad_norm": 4.924495220184326, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4938, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002284617669233054, | |
| "grad_norm": 4.743460655212402, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 1.2229, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002284617669233054, | |
| "eval_loss": 1.457080364227295, | |
| "eval_runtime": 1043.5292, | |
| "eval_samples_per_second": 8.831, | |
| "eval_steps_per_second": 4.416, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002376002376002376, | |
| "grad_norm": 5.3718156814575195, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 1.4273, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.002467387082771698, | |
| "grad_norm": 4.234831809997559, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1389, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0025587717895410203, | |
| "grad_norm": 5.56032133102417, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 1.53, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0026501564963103425, | |
| "grad_norm": 5.804846286773682, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 1.2418, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0027415412030796647, | |
| "grad_norm": 4.4405317306518555, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1612, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002832925909848987, | |
| "grad_norm": 5.623289585113525, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.4001, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0029243106166183088, | |
| "grad_norm": 5.767253875732422, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 1.5194, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.003015695323387631, | |
| "grad_norm": 5.8981852531433105, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3634, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0031070800301569532, | |
| "grad_norm": 6.315387725830078, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 1.2824, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0031984647369262755, | |
| "grad_norm": 5.918696403503418, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.2946, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0032898494436955977, | |
| "grad_norm": 5.576779842376709, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.227, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0033812341504649195, | |
| "grad_norm": 5.354219913482666, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 1.2608, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0034726188572342417, | |
| "grad_norm": 5.7497029304504395, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 1.5261, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.003564003564003564, | |
| "grad_norm": 4.693356990814209, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2093, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003655388270772886, | |
| "grad_norm": 5.870346546173096, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 1.5143, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0037467729775422084, | |
| "grad_norm": 5.203154563903809, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 1.0487, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0038381576843115306, | |
| "grad_norm": 5.0768585205078125, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3043, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003929542391080853, | |
| "grad_norm": 4.440788269042969, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.9258, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.004020927097850175, | |
| "grad_norm": 5.428691387176514, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 1.3457, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.004112311804619497, | |
| "grad_norm": 4.545478343963623, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9944, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004203696511388819, | |
| "grad_norm": 6.674732208251953, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 1.2533, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.004295081218158141, | |
| "grad_norm": 5.448188304901123, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 1.247, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.004386465924927464, | |
| "grad_norm": 5.576430797576904, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2764, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004477850631696785, | |
| "grad_norm": 5.393462657928467, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.9273, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.004569235338466108, | |
| "grad_norm": 5.323672771453857, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 1.0806, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004569235338466108, | |
| "eval_loss": 1.1224627494812012, | |
| "eval_runtime": 1043.091, | |
| "eval_samples_per_second": 8.834, | |
| "eval_steps_per_second": 4.418, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00466062004523543, | |
| "grad_norm": 5.613043308258057, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1746, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.004752004752004752, | |
| "grad_norm": 6.032951831817627, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 1.348, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.004843389458774074, | |
| "grad_norm": 4.618442058563232, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.808, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.004934774165543396, | |
| "grad_norm": 4.89528226852417, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1702, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.005026158872312719, | |
| "grad_norm": 5.89093017578125, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.1912, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.005117543579082041, | |
| "grad_norm": 4.801693439483643, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 1.0937, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.005208928285851362, | |
| "grad_norm": 6.408935070037842, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3091, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.005300312992620685, | |
| "grad_norm": 5.189580917358398, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.8866, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.005391697699390007, | |
| "grad_norm": 5.219249248504639, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.0799, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0054830824061593295, | |
| "grad_norm": 5.454803466796875, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.0661, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.005574467112928651, | |
| "grad_norm": 4.765921592712402, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.7579, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.005665851819697974, | |
| "grad_norm": 5.725944519042969, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 1.0852, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.005757236526467296, | |
| "grad_norm": 4.559783935546875, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9034, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0058486212332366175, | |
| "grad_norm": 5.786202430725098, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 1.0369, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.00594000594000594, | |
| "grad_norm": 4.688554286956787, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 1.0344, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.006031390646775262, | |
| "grad_norm": 5.780782699584961, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9494, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.006122775353544585, | |
| "grad_norm": 5.427234649658203, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.9841, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0062141600603139065, | |
| "grad_norm": 5.6869215965271, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 1.0319, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.006305544767083228, | |
| "grad_norm": 5.268839359283447, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0643, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.006396929473852551, | |
| "grad_norm": 5.248642921447754, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 1.174, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006488314180621873, | |
| "grad_norm": 6.898940086364746, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.2062, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.006579698887391195, | |
| "grad_norm": 5.899970531463623, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.9557, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.006671083594160517, | |
| "grad_norm": 5.415920734405518, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 1.3895, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.006762468300929839, | |
| "grad_norm": 5.120940685272217, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.8528, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.006853853007699162, | |
| "grad_norm": 5.29119873046875, | |
| "learning_rate": 0.0, | |
| "loss": 1.0819, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.006853853007699162, | |
| "eval_loss": 1.0691897869110107, | |
| "eval_runtime": 1043.1267, | |
| "eval_samples_per_second": 8.834, | |
| "eval_steps_per_second": 4.417, | |
| "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": 3.01589487157248e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |