| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9977728285077951, | |
| "eval_steps": 20, | |
| "global_step": 224, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 1.9335, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.9972, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 1.8186, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.9861, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 7.5e-05, | |
| "loss": 1.8548, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.8485, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 1.8735, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.849, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000135, | |
| "loss": 1.8286, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00015, | |
| "loss": 1.8831, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001499980707836663, | |
| "loss": 1.8715, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00014999228323391527, | |
| "loss": 1.9058, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00014998263764849182, | |
| "loss": 1.8479, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001499691345236205, | |
| "loss": 1.8237, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00014995177455397998, | |
| "loss": 1.8827, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00014993055863266725, | |
| "loss": 1.8112, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00014990548785115166, | |
| "loss": 1.7889, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00014987656349921887, | |
| "loss": 1.7984, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00014984378706490442, | |
| "loss": 1.7704, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00014980716023441714, | |
| "loss": 1.8482, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.8568648099899292, | |
| "eval_runtime": 38.6845, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.31, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00014976668489205246, | |
| "loss": 1.8263, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00014972236312009557, | |
| "loss": 1.7868, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00014967419719871407, | |
| "loss": 1.7943, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001496221896058408, | |
| "loss": 1.7331, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00014956634301704636, | |
| "loss": 1.7753, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00014950666030540152, | |
| "loss": 1.8235, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001494431445413292, | |
| "loss": 1.7779, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00014937579899244673, | |
| "loss": 1.7464, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00014930462712339768, | |
| "loss": 1.8215, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00014922963259567356, | |
| "loss": 1.8046, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00014915081926742551, | |
| "loss": 1.7785, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00014906819119326584, | |
| "loss": 1.7834, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00014898175262405928, | |
| "loss": 1.7547, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00014889150800670453, | |
| "loss": 1.7734, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00014879746198390533, | |
| "loss": 1.6926, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00014869961939393165, | |
| "loss": 1.8298, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00014859798527037068, | |
| "loss": 1.8283, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00014849256484186814, | |
| "loss": 1.8148, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000148383363531859, | |
| "loss": 1.7145, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00014827038695828862, | |
| "loss": 1.6823, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.8399871587753296, | |
| "eval_runtime": 38.6779, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.31, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00014815364093332368, | |
| "loss": 1.7295, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00014803313146305322, | |
| "loss": 1.8108, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00014790886474717958, | |
| "loss": 1.8416, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00014778084717869953, | |
| "loss": 1.742, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001476490853435753, | |
| "loss": 1.8345, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00014751358602039578, | |
| "loss": 1.769, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001473743561800279, | |
| "loss": 1.8211, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00014723140298525782, | |
| "loss": 1.7149, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00014708473379042254, | |
| "loss": 1.7783, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00014693435614103158, | |
| "loss": 1.769, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00014678027777337876, | |
| "loss": 1.7785, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00014662250661414414, | |
| "loss": 1.8007, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00014646105077998633, | |
| "loss": 1.7204, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00014629591857712485, | |
| "loss": 1.7557, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00014612711850091285, | |
| "loss": 1.752, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00014595465923540005, | |
| "loss": 1.798, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.000145778549652886, | |
| "loss": 1.7952, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00014559879881346352, | |
| "loss": 1.6717, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001454154159645528, | |
| "loss": 1.7873, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00014522841054042545, | |
| "loss": 1.779, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.8328531980514526, | |
| "eval_runtime": 38.6671, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.31, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00014503779216171937, | |
| "loss": 1.7467, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001448435706349436, | |
| "loss": 1.6856, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001446457559519739, | |
| "loss": 1.8307, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00014444435828953872, | |
| "loss": 1.8962, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00014423938800869573, | |
| "loss": 1.7645, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00014403085565429852, | |
| "loss": 1.6491, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00014381877195445453, | |
| "loss": 1.6784, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00014360314781997267, | |
| "loss": 1.7785, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00014338399434380236, | |
| "loss": 1.7061, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0001431613228004627, | |
| "loss": 1.7057, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00014293514464546245, | |
| "loss": 1.8556, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001427054715147107, | |
| "loss": 1.6799, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00014247231522391824, | |
| "loss": 1.8307, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00014223568776798975, | |
| "loss": 1.7393, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001419956013204066, | |
| "loss": 1.8024, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00014175206823260076, | |
| "loss": 1.7319, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001415051010333191, | |
| "loss": 1.817, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00014125471242797913, | |
| "loss": 1.8538, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00014100091529801515, | |
| "loss": 1.7633, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001407437227002157, | |
| "loss": 1.7776, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.8287429809570312, | |
| "eval_runtime": 38.6957, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.31, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00014048314786605168, | |
| "loss": 1.6936, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00014021920420099581, | |
| "loss": 1.8594, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001399519052838329, | |
| "loss": 1.7749, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00013968126486596123, | |
| "loss": 1.7107, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001394072968706852, | |
| "loss": 1.8344, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00013913001539249902, | |
| "loss": 1.7395, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001388494346963615, | |
| "loss": 1.7746, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00013856556921696233, | |
| "loss": 1.7982, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00013827843355797932, | |
| "loss": 1.7042, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001379880424913272, | |
| "loss": 1.7393, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013769441095639774, | |
| "loss": 1.7614, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013739755405929103, | |
| "loss": 1.816, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013709748707203833, | |
| "loss": 1.7349, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00013679422543181656, | |
| "loss": 1.8416, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00013648778474015399, | |
| "loss": 1.729, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00013617818076212755, | |
| "loss": 1.7117, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00013586542942555207, | |
| "loss": 1.7232, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001355495468201604, | |
| "loss": 1.803, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001352305491967762, | |
| "loss": 1.7586, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00013490845296647736, | |
| "loss": 1.7773, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.8279894590377808, | |
| "eval_runtime": 38.6872, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.31, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00013458327469975214, | |
| "loss": 1.7503, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00013425503112564653, | |
| "loss": 1.7034, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00013392373913090358, | |
| "loss": 1.7173, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00013358941575909464, | |
| "loss": 1.7683, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001332520782097427, | |
| "loss": 1.7292, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001329117438374373, | |
| "loss": 1.8124, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00013256843015094197, | |
| "loss": 1.6621, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00013222215481229326, | |
| "loss": 1.7721, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00013187293563589217, | |
| "loss": 1.8054, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00013152079058758781, | |
| "loss": 1.7337, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00013116573778375296, | |
| "loss": 1.7686, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00013080779549035204, | |
| "loss": 1.6409, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001304469821220016, | |
| "loss": 1.7644, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00013008331624102284, | |
| "loss": 1.6537, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00012971681655648656, | |
| "loss": 1.702, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00012934750192325088, | |
| "loss": 1.7618, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00012897539134099103, | |
| "loss": 1.7597, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00012860050395322207, | |
| "loss": 1.7688, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001282228590463139, | |
| "loss": 1.787, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001278424760484991, | |
| "loss": 1.7328, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.827257752418518, | |
| "eval_runtime": 38.6877, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.31, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001274593745288735, | |
| "loss": 1.7133, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00012707357419638936, | |
| "loss": 1.713, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00012668509489884141, | |
| "loss": 1.713, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001262939566218458, | |
| "loss": 1.7917, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001259001794878119, | |
| "loss": 1.8045, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00012550378375490723, | |
| "loss": 1.6312, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.000125104789816015, | |
| "loss": 1.8702, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001247032181976852, | |
| "loss": 1.7282, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001242990895590785, | |
| "loss": 1.6761, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00012389242469090342, | |
| "loss": 1.8468, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00012348324451434684, | |
| "loss": 1.7638, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00012307157007999755, | |
| "loss": 1.7799, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001226574225667633, | |
| "loss": 1.7186, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001222408232807814, | |
| "loss": 1.8299, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00012182179365432245, | |
| "loss": 1.722, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00012140035524468775, | |
| "loss": 1.8144, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00012097652973310031, | |
| "loss": 1.7382, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00012055033892358951, | |
| "loss": 1.743, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00012012180474186917, | |
| "loss": 1.8136, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00011969094923420983, | |
| "loss": 1.7349, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.8242559432983398, | |
| "eval_runtime": 38.7105, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.31, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011925779456630433, | |
| "loss": 1.7115, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011882236302212763, | |
| "loss": 1.8439, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00011838467700279029, | |
| "loss": 1.7552, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00011794475902538616, | |
| "loss": 1.6786, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00011750263172183381, | |
| "loss": 1.7692, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00011705831783771233, | |
| "loss": 1.7684, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00011661184023109111, | |
| "loss": 1.8193, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00011616322187135392, | |
| "loss": 1.7443, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00011571248583801724, | |
| "loss": 1.7018, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00011525965531954288, | |
| "loss": 1.7432, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00011480475361214499, | |
| "loss": 1.7917, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00011434780411859174, | |
| "loss": 1.865, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00011388883034700114, | |
| "loss": 1.7842, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00011342785590963177, | |
| "loss": 1.7774, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.000112964904521668, | |
| "loss": 1.7166, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0001125, | |
| "loss": 1.7503, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00011203316626199829, | |
| "loss": 1.7856, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001115644273242835, | |
| "loss": 1.7357, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00011109380730149069, | |
| "loss": 1.7742, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00011062133040502877, | |
| "loss": 1.7789, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.8227835893630981, | |
| "eval_runtime": 38.6711, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.31, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00011014702094183498, | |
| "loss": 1.7917, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00010967090331312437, | |
| "loss": 1.7337, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0001091930020131344, | |
| "loss": 1.7775, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00010871334162786493, | |
| "loss": 1.751, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00010823194683381329, | |
| "loss": 1.783, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00010774884239670479, | |
| "loss": 1.6785, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00010726405317021866, | |
| "loss": 1.8272, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001067776040947094, | |
| "loss": 1.8814, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00010628952019592376, | |
| "loss": 1.8227, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00010579982658371316, | |
| "loss": 1.6738, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00010530854845074204, | |
| "loss": 1.7693, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00010481571107119169, | |
| "loss": 1.7958, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00010432133979946002, | |
| "loss": 1.7993, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00010382546006885724, | |
| "loss": 1.614, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00010332809739029735, | |
| "loss": 1.7895, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001028292773509858, | |
| "loss": 1.7137, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00010232902561310306, | |
| "loss": 1.7761, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00010182736791248443, | |
| "loss": 1.6959, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00010132433005729598, | |
| "loss": 1.8765, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.000100819937926707, | |
| "loss": 1.8113, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.8215252161026, | |
| "eval_runtime": 38.7001, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.31, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00010031421746955849, | |
| "loss": 1.7886, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.98071947030282e-05, | |
| "loss": 1.8111, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.929889571129219e-05, | |
| "loss": 1.7057, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.878934664418295e-05, | |
| "loss": 1.8354, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.8278573715844e-05, | |
| "loss": 1.8233, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.776660320338138e-05, | |
| "loss": 1.7187, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.725346144551176e-05, | |
| "loss": 1.6516, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.673917484120744e-05, | |
| "loss": 1.692, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.622376984833817e-05, | |
| "loss": 1.8001, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.570727298231017e-05, | |
| "loss": 1.7514, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.518971081470178e-05, | |
| "loss": 1.7001, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.46711099718967e-05, | |
| "loss": 1.7984, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.415149713371401e-05, | |
| "loss": 1.7321, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.363089903203576e-05, | |
| "loss": 1.8009, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.31093424494315e-05, | |
| "loss": 1.7863, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.258685421778072e-05, | |
| "loss": 1.7774, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.206346121689221e-05, | |
| "loss": 1.694, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.153919037312131e-05, | |
| "loss": 1.7851, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.10140686579847e-05, | |
| "loss": 1.6827, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.04881230867728e-05, | |
| "loss": 1.7, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.8203125, | |
| "eval_runtime": 38.7354, | |
| "eval_samples_per_second": 0.594, | |
| "eval_steps_per_second": 0.31, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.99613807171599e-05, | |
| "loss": 1.8005, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.943386864781223e-05, | |
| "loss": 1.7954, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.890561401699381e-05, | |
| "loss": 1.7705, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.837664400117028e-05, | |
| "loss": 1.7928, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.784698581361081e-05, | |
| "loss": 1.8298, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.731666670298816e-05, | |
| "loss": 1.7958, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.678571395197668e-05, | |
| "loss": 1.8233, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 8.625415487584894e-05, | |
| "loss": 1.717, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 8.572201682107032e-05, | |
| "loss": 1.8032, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 8.518932716389221e-05, | |
| "loss": 1.8317, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 8.465611330894356e-05, | |
| "loss": 1.7089, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 8.412240268782118e-05, | |
| "loss": 1.8331, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.358822275767832e-05, | |
| "loss": 1.7454, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.305360099981222e-05, | |
| "loss": 1.7651, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 8.251856491825029e-05, | |
| "loss": 1.6152, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 8.198314203833513e-05, | |
| "loss": 1.7234, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.144735990530849e-05, | |
| "loss": 1.811, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.091124608289415e-05, | |
| "loss": 1.8182, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.03748281518799e-05, | |
| "loss": 1.7904, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.983813370869873e-05, | |
| "loss": 1.7279, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.820069670677185, | |
| "eval_runtime": 38.6648, | |
| "eval_samples_per_second": 0.595, | |
| "eval_steps_per_second": 0.31, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.930119036400885e-05, | |
| "loss": 1.7795, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.876402574127354e-05, | |
| "loss": 1.718, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.822666747533978e-05, | |
| "loss": 1.8449, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.76891432110168e-05, | |
| "loss": 1.7184, | |
| "step": 224 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 448, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 2.6131840010928783e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |