{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.10346611484738748, "eval_steps": 9, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010346611484738748, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0010346611484738748, "eval_loss": NaN, "eval_runtime": 81.2644, "eval_samples_per_second": 10.017, "eval_steps_per_second": 1.255, "step": 1 }, { "epoch": 0.0020693222969477496, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0031039834454216243, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.004138644593895499, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.005173305742369374, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.006207966890843249, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.007242628039317123, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.008277289187790998, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.009311950336264873, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.009311950336264873, "eval_loss": NaN, "eval_runtime": 80.7642, "eval_samples_per_second": 10.079, "eval_steps_per_second": 1.263, "step": 9 }, { "epoch": 0.010346611484738748, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.011381272633212623, "grad_norm": NaN, "learning_rate": 9.99695413509548e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.012415933781686497, "grad_norm": NaN, "learning_rate": 9.987820251299122e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.013450594930160372, "grad_norm": NaN, "learning_rate": 9.972609476841367e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.014485256078634247, "grad_norm": NaN, "learning_rate": 9.951340343707852e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.015519917227108122, "grad_norm": NaN, "learning_rate": 9.924038765061042e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.016554578375581996, "grad_norm": NaN, "learning_rate": 9.890738003669029e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.01758923952405587, "grad_norm": NaN, "learning_rate": 9.851478631379982e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.018623900672529746, "grad_norm": NaN, "learning_rate": 9.806308479691595e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.018623900672529746, "eval_loss": NaN, "eval_runtime": 80.7549, "eval_samples_per_second": 10.08, "eval_steps_per_second": 1.263, "step": 18 }, { "epoch": 0.01965856182100362, "grad_norm": NaN, "learning_rate": 9.755282581475769e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.020693222969477496, "grad_norm": NaN, "learning_rate": 9.698463103929542e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.02172788411795137, "grad_norm": NaN, "learning_rate": 9.635919272833938e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.022762545266425245, "grad_norm": NaN, "learning_rate": 9.567727288213005e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.02379720641489912, "grad_norm": NaN, "learning_rate": 9.493970231495835e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.024831867563372995, "grad_norm": NaN, "learning_rate": 9.414737964294636e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.02586652871184687, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.026901189860320744, "grad_norm": NaN, "learning_rate": 9.24024048078213e-05, "loss": 0.0, "step": 26 }, { "epoch": 0.02793585100879462, "grad_norm": NaN, "learning_rate": 9.145187862775209e-05, "loss": 0.0, "step": 27 }, { "epoch": 0.02793585100879462, "eval_loss": NaN, "eval_runtime": 80.7597, "eval_samples_per_second": 10.079, "eval_steps_per_second": 1.263, "step": 27 }, { "epoch": 0.028970512157268494, "grad_norm": NaN, "learning_rate": 9.045084971874738e-05, "loss": 0.0, "step": 28 }, { "epoch": 0.03000517330574237, "grad_norm": NaN, "learning_rate": 8.940053768033609e-05, "loss": 0.0, "step": 29 }, { "epoch": 0.031039834454216243, "grad_norm": NaN, "learning_rate": 8.83022221559489e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.03207449560269012, "grad_norm": NaN, "learning_rate": 8.715724127386972e-05, "loss": 0.0, "step": 31 }, { "epoch": 0.03310915675116399, "grad_norm": NaN, "learning_rate": 8.596699001693255e-05, "loss": 0.0, "step": 32 }, { "epoch": 0.03414381789963787, "grad_norm": NaN, "learning_rate": 8.473291852294987e-05, "loss": 0.0, "step": 33 }, { "epoch": 0.03517847904811174, "grad_norm": NaN, "learning_rate": 8.345653031794292e-05, "loss": 0.0, "step": 34 }, { "epoch": 0.03621314019658562, "grad_norm": NaN, "learning_rate": 8.213938048432697e-05, "loss": 0.0, "step": 35 }, { "epoch": 0.03724780134505949, "grad_norm": NaN, "learning_rate": 8.07830737662829e-05, "loss": 0.0, "step": 36 }, { "epoch": 0.03724780134505949, "eval_loss": NaN, "eval_runtime": 80.7578, "eval_samples_per_second": 10.08, "eval_steps_per_second": 1.263, "step": 36 }, { "epoch": 0.03828246249353337, "grad_norm": NaN, "learning_rate": 7.938926261462366e-05, "loss": 0.0, "step": 37 }, { "epoch": 0.03931712364200724, "grad_norm": NaN, "learning_rate": 7.795964517353735e-05, "loss": 0.0, "step": 38 }, { "epoch": 0.04035178479048112, "grad_norm": NaN, "learning_rate": 7.649596321166024e-05, "loss": 0.0, "step": 39 }, { "epoch": 0.04138644593895499, "grad_norm": NaN, "learning_rate": 7.500000000000001e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.04242110708742887, "grad_norm": NaN, "learning_rate": 7.347357813929454e-05, "loss": 0.0, "step": 41 }, { "epoch": 0.04345576823590274, "grad_norm": NaN, "learning_rate": 7.191855733945387e-05, "loss": 0.0, "step": 42 }, { "epoch": 0.04449042938437662, "grad_norm": NaN, "learning_rate": 7.033683215379002e-05, "loss": 0.0, "step": 43 }, { "epoch": 0.04552509053285049, "grad_norm": NaN, "learning_rate": 6.873032967079561e-05, "loss": 0.0, "step": 44 }, { "epoch": 0.04655975168132437, "grad_norm": NaN, "learning_rate": 6.710100716628344e-05, "loss": 0.0, "step": 45 }, { "epoch": 0.04655975168132437, "eval_loss": NaN, "eval_runtime": 80.7509, "eval_samples_per_second": 10.08, "eval_steps_per_second": 1.263, "step": 45 }, { "epoch": 0.04759441282979824, "grad_norm": NaN, "learning_rate": 6.545084971874738e-05, "loss": 0.0, "step": 46 }, { "epoch": 0.04862907397827212, "grad_norm": NaN, "learning_rate": 6.378186779084995e-05, "loss": 0.0, "step": 47 }, { "epoch": 0.04966373512674599, "grad_norm": NaN, "learning_rate": 6.209609477998338e-05, "loss": 0.0, "step": 48 }, { "epoch": 0.05069839627521987, "grad_norm": NaN, "learning_rate": 6.0395584540887963e-05, "loss": 0.0, "step": 49 }, { "epoch": 0.05173305742369374, "grad_norm": NaN, "learning_rate": 5.868240888334653e-05, "loss": 0.0, "step": 50 }, { "epoch": 0.05276771857216762, "grad_norm": NaN, "learning_rate": 5.695865504800327e-05, "loss": 0.0, "step": 51 }, { "epoch": 0.05380237972064149, "grad_norm": NaN, "learning_rate": 5.522642316338268e-05, "loss": 0.0, "step": 52 }, { "epoch": 0.05483704086911537, "grad_norm": NaN, "learning_rate": 5.348782368720626e-05, "loss": 0.0, "step": 53 }, { "epoch": 0.05587170201758924, "grad_norm": NaN, "learning_rate": 5.174497483512506e-05, "loss": 0.0, "step": 54 }, { "epoch": 0.05587170201758924, "eval_loss": NaN, "eval_runtime": 80.7688, "eval_samples_per_second": 10.078, "eval_steps_per_second": 1.263, "step": 54 }, { "epoch": 0.056906363166063116, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 55 }, { "epoch": 0.05794102431453699, "grad_norm": NaN, "learning_rate": 4.825502516487497e-05, "loss": 0.0, "step": 56 }, { "epoch": 0.058975685463010866, "grad_norm": NaN, "learning_rate": 4.6512176312793736e-05, "loss": 0.0, "step": 57 }, { "epoch": 0.06001034661148474, "grad_norm": NaN, "learning_rate": 4.477357683661734e-05, "loss": 0.0, "step": 58 }, { "epoch": 0.061045007759958615, "grad_norm": NaN, "learning_rate": 4.3041344951996746e-05, "loss": 0.0, "step": 59 }, { "epoch": 0.062079668908432487, "grad_norm": NaN, "learning_rate": 4.131759111665349e-05, "loss": 0.0, "step": 60 }, { "epoch": 0.06311433005690636, "grad_norm": NaN, "learning_rate": 3.960441545911204e-05, "loss": 0.0, "step": 61 }, { "epoch": 0.06414899120538024, "grad_norm": NaN, "learning_rate": 3.790390522001662e-05, "loss": 0.0, "step": 62 }, { "epoch": 0.06518365235385411, "grad_norm": NaN, "learning_rate": 3.6218132209150045e-05, "loss": 0.0, "step": 63 }, { "epoch": 0.06518365235385411, "eval_loss": NaN, "eval_runtime": 80.7509, "eval_samples_per_second": 10.08, "eval_steps_per_second": 1.263, "step": 63 }, { "epoch": 0.06621831350232799, "grad_norm": NaN, "learning_rate": 3.4549150281252636e-05, "loss": 0.0, "step": 64 }, { "epoch": 0.06725297465080186, "grad_norm": NaN, "learning_rate": 3.289899283371657e-05, "loss": 0.0, "step": 65 }, { "epoch": 0.06828763579927574, "grad_norm": NaN, "learning_rate": 3.12696703292044e-05, "loss": 0.0, "step": 66 }, { "epoch": 0.0693222969477496, "grad_norm": NaN, "learning_rate": 2.9663167846209998e-05, "loss": 0.0, "step": 67 }, { "epoch": 0.07035695809622348, "grad_norm": NaN, "learning_rate": 2.8081442660546125e-05, "loss": 0.0, "step": 68 }, { "epoch": 0.07139161924469736, "grad_norm": NaN, "learning_rate": 2.6526421860705473e-05, "loss": 0.0, "step": 69 }, { "epoch": 0.07242628039317124, "grad_norm": NaN, "learning_rate": 2.500000000000001e-05, "loss": 0.0, "step": 70 }, { "epoch": 0.0734609415416451, "grad_norm": NaN, "learning_rate": 2.350403678833976e-05, "loss": 0.0, "step": 71 }, { "epoch": 0.07449560269011898, "grad_norm": NaN, "learning_rate": 2.2040354826462668e-05, "loss": 0.0, "step": 72 }, { "epoch": 0.07449560269011898, "eval_loss": NaN, "eval_runtime": 80.7464, "eval_samples_per_second": 10.081, "eval_steps_per_second": 1.263, "step": 72 }, { "epoch": 0.07553026383859286, "grad_norm": NaN, "learning_rate": 2.061073738537635e-05, "loss": 0.0, "step": 73 }, { "epoch": 0.07656492498706674, "grad_norm": NaN, "learning_rate": 1.9216926233717085e-05, "loss": 0.0, "step": 74 }, { "epoch": 0.0775995861355406, "grad_norm": NaN, "learning_rate": 1.7860619515673033e-05, "loss": 0.0, "step": 75 }, { "epoch": 0.07863424728401448, "grad_norm": NaN, "learning_rate": 1.6543469682057106e-05, "loss": 0.0, "step": 76 }, { "epoch": 0.07966890843248836, "grad_norm": NaN, "learning_rate": 1.526708147705013e-05, "loss": 0.0, "step": 77 }, { "epoch": 0.08070356958096224, "grad_norm": NaN, "learning_rate": 1.4033009983067452e-05, "loss": 0.0, "step": 78 }, { "epoch": 0.0817382307294361, "grad_norm": NaN, "learning_rate": 1.2842758726130283e-05, "loss": 0.0, "step": 79 }, { "epoch": 0.08277289187790998, "grad_norm": NaN, "learning_rate": 1.1697777844051105e-05, "loss": 0.0, "step": 80 }, { "epoch": 0.08380755302638386, "grad_norm": NaN, "learning_rate": 1.0599462319663905e-05, "loss": 0.0, "step": 81 }, { "epoch": 0.08380755302638386, "eval_loss": NaN, "eval_runtime": 80.7484, "eval_samples_per_second": 10.081, "eval_steps_per_second": 1.263, "step": 81 }, { "epoch": 0.08484221417485774, "grad_norm": NaN, "learning_rate": 9.549150281252633e-06, "loss": 0.0, "step": 82 }, { "epoch": 0.0858768753233316, "grad_norm": NaN, "learning_rate": 8.548121372247918e-06, "loss": 0.0, "step": 83 }, { "epoch": 0.08691153647180548, "grad_norm": NaN, "learning_rate": 7.597595192178702e-06, "loss": 0.0, "step": 84 }, { "epoch": 0.08794619762027936, "grad_norm": NaN, "learning_rate": 6.698729810778065e-06, "loss": 0.0, "step": 85 }, { "epoch": 0.08898085876875324, "grad_norm": NaN, "learning_rate": 5.852620357053651e-06, "loss": 0.0, "step": 86 }, { "epoch": 0.0900155199172271, "grad_norm": NaN, "learning_rate": 5.060297685041659e-06, "loss": 0.0, "step": 87 }, { "epoch": 0.09105018106570098, "grad_norm": NaN, "learning_rate": 4.322727117869951e-06, "loss": 0.0, "step": 88 }, { "epoch": 0.09208484221417486, "grad_norm": NaN, "learning_rate": 3.6408072716606346e-06, "loss": 0.0, "step": 89 }, { "epoch": 0.09311950336264874, "grad_norm": NaN, "learning_rate": 3.0153689607045845e-06, "loss": 0.0, "step": 90 }, { "epoch": 0.09311950336264874, "eval_loss": NaN, "eval_runtime": 80.747, "eval_samples_per_second": 10.081, "eval_steps_per_second": 1.263, "step": 90 }, { "epoch": 0.0941541645111226, "grad_norm": NaN, "learning_rate": 2.4471741852423237e-06, "loss": 0.0, "step": 91 }, { "epoch": 0.09518882565959648, "grad_norm": NaN, "learning_rate": 1.9369152030840556e-06, "loss": 0.0, "step": 92 }, { "epoch": 0.09622348680807036, "grad_norm": NaN, "learning_rate": 1.4852136862001764e-06, "loss": 0.0, "step": 93 }, { "epoch": 0.09725814795654424, "grad_norm": NaN, "learning_rate": 1.0926199633097157e-06, "loss": 0.0, "step": 94 }, { "epoch": 0.0982928091050181, "grad_norm": NaN, "learning_rate": 7.596123493895991e-07, "loss": 0.0, "step": 95 }, { "epoch": 0.09932747025349198, "grad_norm": NaN, "learning_rate": 4.865965629214819e-07, "loss": 0.0, "step": 96 }, { "epoch": 0.10036213140196586, "grad_norm": NaN, "learning_rate": 2.7390523158633554e-07, "loss": 0.0, "step": 97 }, { "epoch": 0.10139679255043973, "grad_norm": NaN, "learning_rate": 1.2179748700879012e-07, "loss": 0.0, "step": 98 }, { "epoch": 0.1024314536989136, "grad_norm": NaN, "learning_rate": 3.04586490452119e-08, "loss": 0.0, "step": 99 }, { "epoch": 0.1024314536989136, "eval_loss": NaN, "eval_runtime": 80.7533, "eval_samples_per_second": 10.08, "eval_steps_per_second": 1.263, "step": 99 }, { "epoch": 0.10346611484738748, "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": 6.53464644354048e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }