| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9966024915062288, | |
| "eval_steps": 55, | |
| "global_step": 220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004530011325028313, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004530011325028313, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.5744, | |
| "eval_samples_per_second": 21.167, | |
| "eval_steps_per_second": 5.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009060022650056626, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013590033975084938, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01812004530011325, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022650056625141562, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027180067950169876, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.031710079275198186, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0362400906002265, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04077010192525481, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.045300113250283124, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04983012457531144, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05436013590033975, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05889014722536806, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06342015855039637, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06795016987542468, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.072480181200453, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07701019252548132, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08154020385050963, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08607021517553794, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09060022650056625, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09513023782559456, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09966024915062288, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10419026047565119, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1087202718006795, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11325028312570781, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11778029445073612, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12231030577576443, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12684031710079274, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13137032842582105, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13590033975084936, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1404303510758777, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.2e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.144960362400906, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14949037372593432, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15402038505096263, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15855039637599094, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16308040770101925, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16761041902604756, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17214043035107587, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17667044167610418, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1812004530011325, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1857304643261608, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.2e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19026047565118911, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19479048697621745, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19932049830124576, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.20385050962627407, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20838052095130238, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2129105322763307, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.217440543601359, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22197055492638731, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22650056625141562, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23103057757644394, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999146252290264e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.23556058890147225, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.24009060022650056, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99231801983717e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.24462061155152887, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986345866928941e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2491506228765572, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2491506228765572, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.9373, | |
| "eval_samples_per_second": 21.963, | |
| "eval_steps_per_second": 5.491, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2536806342015855, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2582106455266138, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.958223477553714e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2627406568516421, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.94545804185573e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.26727066817667045, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.931003736767013e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2718006795016987, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.27633069082672707, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.89704883800683e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2808607021517554, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.877559839902184e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2853907134767837, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.85640515958057e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.289920724801812, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2944507361268403, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.809128215864097e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.29898074745186864, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.783022097502204e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3035107587768969, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.30804077010192527, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.31257078142695355, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.694941803075283e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3171007927519819, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.662361147021779e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32163080407701017, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.628188298907782e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3261608154020385, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.33069082672706684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.555113246230442e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3352208380520951, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.516235996730645e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.33975084937712347, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.475816456775313e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.34428086070215175, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3488108720271801, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.39040624041849e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.35334088335220837, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.345444731527642e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3578708946772367, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.298999257241863e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.362400906002265, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3669309173272933, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.201720358189464e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3714609286523216, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.150920154077754e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.37599093997734995, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.098702414536107e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.38052095130237823, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.38505096262740657, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.9900861364012e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3895809739524349, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.933724690167417e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.3941109852774632, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.876019880555649e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.3986409966024915, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.816991413705516e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.4031710079275198, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.756659447784368e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.40770101925254815, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.695044586103296e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.41223103057757643, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.632167870081121e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.41676104190260477, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.568050772058762e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.42129105322763305, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.502715187966455e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4258210645526614, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.436183429846313e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.43035107587768967, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.368478218232787e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.434881087202718, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.299622674393614e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.43941109852774635, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.229640312433937e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.44394110985277463, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.158555031266254e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.44847112117780297, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.086391106448965e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.45300113250283125, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.013173181896283e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4575311438278596, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.46206115515288787, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.863675700402526e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.4665911664779162, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.787447196714427e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.4711211778029445, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.710266782362247e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.47565118912797283, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.63216081438678e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4801812004530011, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.553155965904535e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.48471121177802945, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.473279216998895e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.48924122310305773, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.392557845506432e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.49377123442808607, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.311019417701566e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.4983012457531144, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.228691778882693e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4983012457531144, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.8907, | |
| "eval_samples_per_second": 22.024, | |
| "eval_steps_per_second": 5.506, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5028312570781427, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.145603043863045e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.507361268403171, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.061781587369519e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.5118912797281994, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.977256034352712e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.5164212910532276, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.892055250211552e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.5209513023782559, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.806208330935766e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5254813137032842, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.719744593169641e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5300113250283126, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.632693564200416e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.5345413363533409, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5390713476783692, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.456948734446624e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.5436013590033975, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.368314950360415e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5481313703284258, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.279213887972179e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.5526613816534541, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.189675975213094e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5571913929784824, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.099731789198344e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5617214043035108, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.009412045785051e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5662514156285391, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.918747589082853e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5707814269535674, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.82776938092065e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5753114382785957, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.736508490273188e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.579841449603624, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.644996082651017e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5843714609286523, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.553263409457504e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5889014722536806, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4613417973165106e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5934314835787089, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3692626373743706e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.5979614949037373, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.27705737457985e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.6024915062287656, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.184757496945726e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.6070215175537939, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.092394524795649e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.6115515288788222, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6160815402038505, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.907605475204352e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.6206115515288788, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8152425030542766e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.6251415628539071, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.72294262542015e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6296715741789355, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6307373626256306e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.6342015855039638, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5386582026834906e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.638731596828992, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.446736590542497e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.6432616081540203, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3550039173489845e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.6477916194790487, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2634915097268115e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.652321630804077, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1722306190793495e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6568516421291053, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0812524109171476e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6613816534541337, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.99058795421495e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.665911664779162, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9002682108016585e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6704416761041903, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8103240247869075e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.6749716874292185, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.720786112027822e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.6795016987542469, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.631685049639586e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6840317100792752, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.543051265553377e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.6885617214043035, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.6930917327293318, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.367306435799584e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6976217440543602, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2802554068303596e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.7021517553793885, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1937916690642356e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7066817667044167, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.107944749788449e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.711211778029445, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0227439656472877e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.7157417893544734, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9382184126304834e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.7202718006795017, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8543969561369556e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.72480181200453, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.771308221117309e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7293318233295584, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.688980582298435e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.7338618346545867, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.607442154493568e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.7383918459796149, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5267207830011068e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.7429218573046432, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.446844034095466e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.7474518686296716, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3678391856132204e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7474518686296716, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.7388, | |
| "eval_samples_per_second": 22.224, | |
| "eval_steps_per_second": 5.556, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7519818799546999, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2897332176377528e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.7565118912797282, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2125528032855724e-05, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.7610419026047565, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.136324299597474e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.7655719139297849, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.7701019252548131, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9868268181037185e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7746319365798414, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9136088935510362e-05, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.7791619479048698, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8414449687337464e-05, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.7836919592298981, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7703596875660645e-05, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.7882219705549264, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.700377325606388e-05, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.7927519818799547, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.631521781767214e-05, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.797281993204983, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5638165701536868e-05, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.8018120045300113, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4972848120335453e-05, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.8063420158550396, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4319492279412388e-05, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.8108720271800679, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3678321299188801e-05, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.8154020385050963, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3049554138967051e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8199320498301246, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2433405522156332e-05, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.8244620611551529, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.183008586294485e-05, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.8289920724801813, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1239801194443506e-05, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.8335220838052095, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.066275309832584e-05, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.8380520951302378, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0099138635988026e-05, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8425821064552661, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.8471121177802945, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.012975854638949e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.8516421291053228, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.490798459222476e-06, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.8561721404303511, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.982796418105371e-06, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.8607021517553793, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.489143213519301e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8652321630804077, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.010007427581378e-06, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.869762174405436, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.5455526847235825e-06, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.8742921857304643, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0959375958151045e-06, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.8788221970554927, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6613157039969055e-06, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.883352208380521, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.241835432246889e-06, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8878822197055493, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.837640032693558e-06, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.8924122310305775, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.448867537695578e-06, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.8969422423556059, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.075650712703849e-06, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.9014722536806342, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.71811701092219e-06, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.9060022650056625, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.376388529782215e-06, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9105322763306908, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0505819692471792e-06, | |
| "loss": 0.0, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.9150622876557192, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7408085919590264e-06, | |
| "loss": 0.0, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.9195922989807475, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.9241223103057757, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1697790249779636e-06, | |
| "loss": 0.0, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.928652321630804, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.908717841359048e-06, | |
| "loss": 0.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.9331823329558324, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6640797865406288e-06, | |
| "loss": 0.0, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.9377123442808607, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4359484041943038e-06, | |
| "loss": 0.0, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.942242355605889, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2244016009781701e-06, | |
| "loss": 0.0, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.9467723669309174, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0295116199317057e-06, | |
| "loss": 0.0, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.9513023782559457, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.513450158049108e-07, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9558323895809739, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.899626323298713e-07, | |
| "loss": 0.0, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.9603624009060022, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.454195814427021e-07, | |
| "loss": 0.0, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.9648924122310306, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.177652244628627e-07, | |
| "loss": 0.0, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.9694224235560589, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0704315523631953e-07, | |
| "loss": 0.0, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.9739524348810872, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1329118524827662e-07, | |
| "loss": 0.0, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.9784824462061155, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3654133071059893e-07, | |
| "loss": 0.0, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.9830124575311439, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.681980162830282e-08, | |
| "loss": 0.0, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.9875424688561721, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4146992848854695e-08, | |
| "loss": 0.0, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.9920724801812004, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.537477097364522e-09, | |
| "loss": 0.0, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.9966024915062288, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9966024915062288, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.7651, | |
| "eval_samples_per_second": 22.189, | |
| "eval_steps_per_second": 5.547, | |
| "step": 220 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 220, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 55, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.17219892363264e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |