| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.998639455782313, | |
| "eval_steps": 20, | |
| "global_step": 367, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 1.264, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9796, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9343, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8e-05, | |
| "loss": 1.165, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1233, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012, | |
| "loss": 0.9889, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00014, | |
| "loss": 0.9492, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1725, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9987, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0273, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001999961280430958, | |
| "loss": 0.9883, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019998451247222416, | |
| "loss": 0.8587, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001999651541868849, | |
| "loss": 0.9096, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019993805468616693, | |
| "loss": 1.0186, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019990321606863225, | |
| "loss": 0.9402, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019986064103215339, | |
| "loss": 0.927, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019981033287370443, | |
| "loss": 0.935, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019975229548910582, | |
| "loss": 0.9498, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019968653337272261, | |
| "loss": 1.0335, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001996130516171164, | |
| "loss": 0.8899, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.3891513347625732, | |
| "eval_runtime": 119.0073, | |
| "eval_samples_per_second": 3.706, | |
| "eval_steps_per_second": 1.857, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019953185591265103, | |
| "loss": 0.8179, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019944295254705185, | |
| "loss": 1.1169, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019934634840491886, | |
| "loss": 0.9125, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001992420509671936, | |
| "loss": 0.9177, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019913006831057969, | |
| "loss": 0.8608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001990104091069176, | |
| "loss": 0.7755, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019888308262251285, | |
| "loss": 1.0967, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019874809871741876, | |
| "loss": 0.9759, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019860546784467248, | |
| "loss": 0.9605, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019845520104948592, | |
| "loss": 1.0065, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001982973099683902, | |
| "loss": 0.9643, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019813180682833447, | |
| "loss": 0.9065, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019795870444573935, | |
| "loss": 1.1212, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019777801622550408, | |
| "loss": 0.8759, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019758975615996873, | |
| "loss": 0.8474, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019739393882783047, | |
| "loss": 0.9243, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019719057939301477, | |
| "loss": 0.9369, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019697969360350098, | |
| "loss": 1.0376, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019676129779010282, | |
| "loss": 0.8972, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019653540886520386, | |
| "loss": 0.8402, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.3678525686264038, | |
| "eval_runtime": 119.0464, | |
| "eval_samples_per_second": 3.704, | |
| "eval_steps_per_second": 1.856, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001963020443214478, | |
| "loss": 0.8425, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019606122223038376, | |
| "loss": 0.9518, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001958129612410668, | |
| "loss": 1.0741, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001955572805786141, | |
| "loss": 0.9275, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019529420004271567, | |
| "loss": 1.049, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019502374000610151, | |
| "loss": 0.974, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019474592141296372, | |
| "loss": 0.856, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019446076577733475, | |
| "loss": 1.1511, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019416829518142118, | |
| "loss": 0.8645, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001938685322738939, | |
| "loss": 0.9042, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019356150026813405, | |
| "loss": 0.914, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019324722294043558, | |
| "loss": 1.1324, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019292572462816388, | |
| "loss": 0.8499, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001925970302278711, | |
| "loss": 1.0545, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001922611651933683, | |
| "loss": 0.8526, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019191815553375427, | |
| "loss": 0.909, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001915680278114014, | |
| "loss": 1.0598, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001912108091398988, | |
| "loss": 0.8763, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019084652718195238, | |
| "loss": 0.905, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019047521014724304, | |
| "loss": 0.9795, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.3594976663589478, | |
| "eval_runtime": 119.047, | |
| "eval_samples_per_second": 3.704, | |
| "eval_steps_per_second": 1.856, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.8955, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018971158640798368, | |
| "loss": 0.9148, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018931933883779785, | |
| "loss": 1.0147, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001889201744549981, | |
| "loss": 0.9123, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001885141241705303, | |
| "loss": 0.7681, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018810121942857845, | |
| "loss": 0.8203, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001876814922041299, | |
| "loss": 0.9618, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018725497500049907, | |
| "loss": 0.9399, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018682170084681065, | |
| "loss": 1.0265, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018638170329544164, | |
| "loss": 1.0596, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018593501641942317, | |
| "loss": 1.2212, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018548167480980193, | |
| "loss": 1.0959, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018502171357296144, | |
| "loss": 0.7914, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018455516832790338, | |
| "loss": 0.9506, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018408207520348942, | |
| "loss": 0.8409, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00018360247083564342, | |
| "loss": 0.9833, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00018311639236451416, | |
| "loss": 1.0708, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001826238774315995, | |
| "loss": 0.9121, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00018212496417683137, | |
| "loss": 0.9433, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001816196912356222, | |
| "loss": 0.8529, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.3516823053359985, | |
| "eval_runtime": 119.0215, | |
| "eval_samples_per_second": 3.705, | |
| "eval_steps_per_second": 1.857, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000181108097735873, | |
| "loss": 0.9438, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001805902232949435, | |
| "loss": 0.9375, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000180066108016584, | |
| "loss": 0.9696, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017953579248782995, | |
| "loss": 0.8329, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017899931777585882, | |
| "loss": 0.9701, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017845672542480984, | |
| "loss": 0.9774, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00017790805745256704, | |
| "loss": 0.8261, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00017735335634750532, | |
| "loss": 1.021, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00017679266506520012, | |
| "loss": 1.0482, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00017622602702510105, | |
| "loss": 1.0097, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001756534861071696, | |
| "loss": 0.9386, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00017507508664848094, | |
| "loss": 0.7935, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001744908734397906, | |
| "loss": 0.9367, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00017390089172206592, | |
| "loss": 0.7777, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00017330518718298264, | |
| "loss": 0.8662, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001727038059533868, | |
| "loss": 0.805, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001720967946037225, | |
| "loss": 1.0421, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001714842001404254, | |
| "loss": 1.0119, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00017086607000228282, | |
| "loss": 0.9288, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00017024245205675986, | |
| "loss": 1.0169, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.344921588897705, | |
| "eval_runtime": 119.0551, | |
| "eval_samples_per_second": 3.704, | |
| "eval_steps_per_second": 1.856, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001696133945962927, | |
| "loss": 0.9399, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00016897894633454886, | |
| "loss": 0.9817, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00016833915640265484, | |
| "loss": 0.9042, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00016769407434539168, | |
| "loss": 0.8495, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0001670437501173578, | |
| "loss": 0.8376, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00016638823407910084, | |
| "loss": 0.9603, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00016572757699321791, | |
| "loss": 0.924, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0001650618300204242, | |
| "loss": 0.7669, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00016439104471559156, | |
| "loss": 0.8822, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001637152730237558, | |
| "loss": 0.9815, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001630345672760943, | |
| "loss": 1.0067, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.9053, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00016165856484436645, | |
| "loss": 0.8396, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00016096337471674241, | |
| "loss": 0.9769, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00016026346363792567, | |
| "loss": 0.8927, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001595588858084268, | |
| "loss": 0.9105, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00015884969579014566, | |
| "loss": 0.8848, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.000158135948502146, | |
| "loss": 0.8636, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001574176992164026, | |
| "loss": 0.8177, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00015669500355352116, | |
| "loss": 0.8777, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.3403385877609253, | |
| "eval_runtime": 118.9836, | |
| "eval_samples_per_second": 3.706, | |
| "eval_steps_per_second": 1.857, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001559679174784308, | |
| "loss": 1.0621, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001552364972960506, | |
| "loss": 0.9647, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00015450079964692896, | |
| "loss": 0.9974, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00015376088150285773, | |
| "loss": 0.942, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00015301680016246028, | |
| "loss": 0.927, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001522686132467543, | |
| "loss": 0.9022, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001515163786946896, | |
| "loss": 0.9001, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001507601547586616, | |
| "loss": 0.9224, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.9607, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00014923597328443422, | |
| "loss": 0.8044, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00014846813377753456, | |
| "loss": 0.7944, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00014769654094013058, | |
| "loss": 1.0154, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00014692125452370663, | |
| "loss": 0.9003, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00014614233456577454, | |
| "loss": 0.9419, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00014535984138522442, | |
| "loss": 0.8798, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00014457383557765386, | |
| "loss": 1.0318, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.000143784378010675, | |
| "loss": 0.9086, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00014299152981920145, | |
| "loss": 0.9947, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00014219535240071377, | |
| "loss": 0.9156, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00014139590741050502, | |
| "loss": 0.8692, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.3370156288146973, | |
| "eval_runtime": 119.006, | |
| "eval_samples_per_second": 3.706, | |
| "eval_steps_per_second": 1.857, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001405932567569062, | |
| "loss": 0.9393, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00013978746259649209, | |
| "loss": 0.8703, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00013897858732926793, | |
| "loss": 0.9319, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00013816669359383726, | |
| "loss": 1.0655, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00013735184426255117, | |
| "loss": 0.9344, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00013653410243663952, | |
| "loss": 1.0119, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001357135314413245, | |
| "loss": 0.9353, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001348901948209167, | |
| "loss": 0.9807, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013406415633389438, | |
| "loss": 0.9972, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013323547994796597, | |
| "loss": 0.8184, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001324042298351166, | |
| "loss": 0.9096, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00013157047036663853, | |
| "loss": 0.7666, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0001307342661081463, | |
| "loss": 0.9412, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00012989568181457704, | |
| "loss": 0.7595, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00012905478242517562, | |
| "loss": 0.8968, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00012821163305846596, | |
| "loss": 0.8976, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001273662990072083, | |
| "loss": 0.8512, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00012651884573334297, | |
| "loss": 0.9215, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00012566933886292106, | |
| "loss": 0.828, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00012481784418102242, | |
| "loss": 0.8962, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.3367716073989868, | |
| "eval_runtime": 118.9758, | |
| "eval_samples_per_second": 3.707, | |
| "eval_steps_per_second": 1.858, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00012396442762666128, | |
| "loss": 0.8564, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00012310915528768, | |
| "loss": 0.8648, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.9122, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00012139330832064974, | |
| "loss": 0.8912, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00012053286656631093, | |
| "loss": 0.8872, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00011967083476448282, | |
| "loss": 0.8292, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00011880727967016514, | |
| "loss": 0.858, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00011794226815632012, | |
| "loss": 0.8548, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00011707586720869374, | |
| "loss": 0.8587, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00011620814392062873, | |
| "loss": 1.0234, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011533916548786857, | |
| "loss": 0.9115, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011446899920335405, | |
| "loss": 1.0819, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011359771245201232, | |
| "loss": 0.8818, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011272537270553836, | |
| "loss": 0.8352, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00011185204751717029, | |
| "loss": 0.8977, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00011097780451645792, | |
| "loss": 0.855, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00011010271140402579, | |
| "loss": 0.7944, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00010922683594633021, | |
| "loss": 0.9017, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001083502459704117, | |
| "loss": 0.7825, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00010747300935864243, | |
| "loss": 0.7996, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.3361833095550537, | |
| "eval_runtime": 119.0783, | |
| "eval_samples_per_second": 3.703, | |
| "eval_steps_per_second": 1.856, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00010659519404346954, | |
| "loss": 0.9062, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010571686800215444, | |
| "loss": 0.7366, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010483809925150869, | |
| "loss": 0.7322, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010395895584262696, | |
| "loss": 0.7953, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010307950585561706, | |
| "loss": 0.848, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00010219981739432795, | |
| "loss": 1.0637, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00010131995858107591, | |
| "loss": 0.8968, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00010043999755136904, | |
| "loss": 1.0545, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.9560002448631e-05, | |
| "loss": 0.9912, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.868004141892411e-05, | |
| "loss": 0.8248, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.780018260567207e-05, | |
| "loss": 0.9459, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.692049414438299e-05, | |
| "loss": 0.8605, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.604104415737308e-05, | |
| "loss": 0.8436, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.516190074849134e-05, | |
| "loss": 0.9136, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.428313199784556e-05, | |
| "loss": 1.0565, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.340480595653047e-05, | |
| "loss": 0.9397, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.252699064135758e-05, | |
| "loss": 0.9039, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.164975402958834e-05, | |
| "loss": 0.9025, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.077316405366981e-05, | |
| "loss": 1.0392, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 8.989728859597424e-05, | |
| "loss": 0.8475, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.3337310552597046, | |
| "eval_runtime": 119.0825, | |
| "eval_samples_per_second": 3.703, | |
| "eval_steps_per_second": 1.856, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.902219548354209e-05, | |
| "loss": 1.0189, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.814795248282974e-05, | |
| "loss": 0.9149, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.727462729446167e-05, | |
| "loss": 0.8856, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.640228754798773e-05, | |
| "loss": 0.8605, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.553100079664598e-05, | |
| "loss": 0.9093, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.466083451213144e-05, | |
| "loss": 0.8779, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.379185607937126e-05, | |
| "loss": 0.9265, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.292413279130624e-05, | |
| "loss": 1.049, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.205773184367991e-05, | |
| "loss": 0.8172, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.119272032983487e-05, | |
| "loss": 0.927, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.03291652355172e-05, | |
| "loss": 1.0608, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.94671334336891e-05, | |
| "loss": 0.8668, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.860669167935028e-05, | |
| "loss": 0.9103, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 0.8594, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.689084471232001e-05, | |
| "loss": 0.8572, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.603557237333877e-05, | |
| "loss": 0.956, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.518215581897763e-05, | |
| "loss": 0.8796, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.433066113707896e-05, | |
| "loss": 1.0585, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.348115426665705e-05, | |
| "loss": 0.7626, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.263370099279172e-05, | |
| "loss": 0.8566, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.3307039737701416, | |
| "eval_runtime": 119.0797, | |
| "eval_samples_per_second": 3.703, | |
| "eval_steps_per_second": 1.856, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.178836694153405e-05, | |
| "loss": 0.8049, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.09452175748244e-05, | |
| "loss": 1.0561, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.010431818542297e-05, | |
| "loss": 0.7266, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.926573389185371e-05, | |
| "loss": 0.8773, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.842952963336153e-05, | |
| "loss": 0.9103, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.759577016488343e-05, | |
| "loss": 0.6977, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.676452005203406e-05, | |
| "loss": 0.8085, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.593584366610566e-05, | |
| "loss": 0.8944, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.510980517908334e-05, | |
| "loss": 0.7846, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.428646855867553e-05, | |
| "loss": 0.9049, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.34658975633605e-05, | |
| "loss": 1.0148, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.264815573744884e-05, | |
| "loss": 0.8781, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.183330640616273e-05, | |
| "loss": 0.9242, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.102141267073207e-05, | |
| "loss": 0.8635, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.021253740350793e-05, | |
| "loss": 1.0117, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.9406743243093807e-05, | |
| "loss": 0.9206, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.8604092589494994e-05, | |
| "loss": 1.0006, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.780464759928623e-05, | |
| "loss": 0.8629, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.700847018079856e-05, | |
| "loss": 0.9166, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.6215621989325e-05, | |
| "loss": 0.8463, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.3288977146148682, | |
| "eval_runtime": 118.9998, | |
| "eval_samples_per_second": 3.706, | |
| "eval_steps_per_second": 1.857, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.542616442234618e-05, | |
| "loss": 1.0178, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.464015861477557e-05, | |
| "loss": 0.8584, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.385766543422551e-05, | |
| "loss": 0.8194, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.307874547629339e-05, | |
| "loss": 0.8743, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.230345905986944e-05, | |
| "loss": 0.9445, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.1531866222465466e-05, | |
| "loss": 1.0006, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.0764026715565785e-05, | |
| "loss": 0.7993, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.9364, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.9239845241338435e-05, | |
| "loss": 0.8884, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.848362130531039e-05, | |
| "loss": 0.9054, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.7731386753245675e-05, | |
| "loss": 1.0429, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.6983199837539705e-05, | |
| "loss": 0.8428, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.6239118497142256e-05, | |
| "loss": 0.7732, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.549920035307107e-05, | |
| "loss": 1.0696, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.476350270394942e-05, | |
| "loss": 0.8644, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.403208252156921e-05, | |
| "loss": 0.8967, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.3304996446478854e-05, | |
| "loss": 0.7205, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.2582300783597404e-05, | |
| "loss": 1.0014, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.186405149785403e-05, | |
| "loss": 0.7683, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.115030420985437e-05, | |
| "loss": 0.8781, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.3258484601974487, | |
| "eval_runtime": 119.0026, | |
| "eval_samples_per_second": 3.706, | |
| "eval_steps_per_second": 1.857, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.044111419157326e-05, | |
| "loss": 0.962, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.973653636207437e-05, | |
| "loss": 0.8061, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.903662528325759e-05, | |
| "loss": 0.9114, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.834143515563358e-05, | |
| "loss": 0.9192, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 0.9397, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.6965432723905735e-05, | |
| "loss": 0.9167, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.628472697624422e-05, | |
| "loss": 0.9877, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.5608955284408443e-05, | |
| "loss": 1.1038, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.493816997957582e-05, | |
| "loss": 0.868, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.427242300678213e-05, | |
| "loss": 0.7829, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.361176592089919e-05, | |
| "loss": 0.8135, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.295624988264224e-05, | |
| "loss": 0.8382, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.2305925654608326e-05, | |
| "loss": 1.0243, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.1660843597345135e-05, | |
| "loss": 0.7312, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.1021053665451206e-05, | |
| "loss": 0.9365, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.0386605403707346e-05, | |
| "loss": 0.7903, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.975754794324015e-05, | |
| "loss": 0.8536, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.913392999771718e-05, | |
| "loss": 0.993, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.8515799859574588e-05, | |
| "loss": 0.7764, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.7903205396277542e-05, | |
| "loss": 0.9057, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.3229844570159912, | |
| "eval_runtime": 119.0121, | |
| "eval_samples_per_second": 3.706, | |
| "eval_steps_per_second": 1.857, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.729619404661321e-05, | |
| "loss": 0.8637, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.669481281701739e-05, | |
| "loss": 0.8564, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.6099108277934103e-05, | |
| "loss": 0.9834, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.5509126560209428e-05, | |
| "loss": 0.8363, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.4924913351519084e-05, | |
| "loss": 0.8882, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.4346513892830423e-05, | |
| "loss": 0.8547, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.377397297489895e-05, | |
| "loss": 0.9304, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.320733493479992e-05, | |
| "loss": 0.9409, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.2646643652494692e-05, | |
| "loss": 0.9414, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.2091942547432955e-05, | |
| "loss": 0.8788, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.1543274575190188e-05, | |
| "loss": 0.8338, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.100068222414121e-05, | |
| "loss": 0.7986, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.0464207512170065e-05, | |
| "loss": 1.0324, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.993389198341601e-05, | |
| "loss": 0.8743, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.9409776705056516e-05, | |
| "loss": 0.8304, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.8891902264127004e-05, | |
| "loss": 0.8021, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.8380308764377842e-05, | |
| "loss": 0.9101, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.787503582316864e-05, | |
| "loss": 0.8156, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.7376122568400532e-05, | |
| "loss": 0.7932, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.6883607635485877e-05, | |
| "loss": 0.9364, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.3215992450714111, | |
| "eval_runtime": 118.9898, | |
| "eval_samples_per_second": 3.706, | |
| "eval_steps_per_second": 1.857, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.6397529164356606e-05, | |
| "loss": 0.9039, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.5917924796510587e-05, | |
| "loss": 0.9557, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.544483167209664e-05, | |
| "loss": 0.8927, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.4978286427038601e-05, | |
| "loss": 0.9724, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.4518325190198078e-05, | |
| "loss": 0.9405, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.406498358057683e-05, | |
| "loss": 0.9551, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.3618296704558364e-05, | |
| "loss": 0.8297, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.3178299153189366e-05, | |
| "loss": 0.8766, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.2745024999500943e-05, | |
| "loss": 0.8472, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.2318507795870138e-05, | |
| "loss": 0.7698, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.1898780571421552e-05, | |
| "loss": 0.933, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.1485875829469705e-05, | |
| "loss": 0.9372, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.1079825545001888e-05, | |
| "loss": 0.6934, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.0680661162202177e-05, | |
| "loss": 0.9019, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.0288413592016343e-05, | |
| "loss": 1.0839, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 0.9194, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.524789852756954e-06, | |
| "loss": 0.8442, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.153472818047625e-06, | |
| "loss": 0.8134, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.789190860101225e-06, | |
| "loss": 0.8297, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.43197218859858e-06, | |
| "loss": 0.9635, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 1.3210258483886719, | |
| "eval_runtime": 119.0221, | |
| "eval_samples_per_second": 3.705, | |
| "eval_steps_per_second": 1.857, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.081844466245737e-06, | |
| "loss": 0.7029, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.738834806631711e-06, | |
| "loss": 0.898, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.402969772128931e-06, | |
| "loss": 0.8886, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.074275371836148e-06, | |
| "loss": 0.7764, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.75277705956443e-06, | |
| "loss": 0.8431, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.438499731865966e-06, | |
| "loss": 0.8315, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.131467726106144e-06, | |
| "loss": 0.8022, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.831704818578843e-06, | |
| "loss": 1.0034, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.539234222665279e-06, | |
| "loss": 0.9289, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.2540785870362815e-06, | |
| "loss": 1.1203, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.976259993898502e-06, | |
| "loss": 0.8166, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.705799957284351e-06, | |
| "loss": 0.872, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.442719421385922e-06, | |
| "loss": 0.914, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.187038758933204e-06, | |
| "loss": 0.9243, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.938777769616275e-06, | |
| "loss": 0.7485, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.6979556785522116e-06, | |
| "loss": 0.835, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.4645911347961357e-06, | |
| "loss": 0.8814, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.2387022098972153e-06, | |
| "loss": 0.7235, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.0203063964990617e-06, | |
| "loss": 0.9117, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.809420606985236e-06, | |
| "loss": 1.0049, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.3204991817474365, | |
| "eval_runtime": 119.0009, | |
| "eval_samples_per_second": 3.706, | |
| "eval_steps_per_second": 1.857, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.606061172169527e-06, | |
| "loss": 0.8719, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.410243840031279e-06, | |
| "loss": 0.9375, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.2219837744959283e-06, | |
| "loss": 0.8642, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.0412955542606473e-06, | |
| "loss": 0.9535, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.8681931716655221e-06, | |
| "loss": 0.8538, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.7026900316098215e-06, | |
| "loss": 0.736, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.5447989505140925e-06, | |
| "loss": 0.8917, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.3945321553275326e-06, | |
| "loss": 0.7953, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.2519012825812804e-06, | |
| "loss": 0.9073, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.1169173774871478e-06, | |
| "loss": 0.8242, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.89590893082426e-07, | |
| "loss": 1.0244, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 8.699316894203224e-07, | |
| "loss": 0.8013, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.579490328064265e-07, | |
| "loss": 0.8989, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 6.536515950811395e-07, | |
| "loss": 1.013, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.570474529481562e-07, | |
| "loss": 0.8283, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.681440873489762e-07, | |
| "loss": 0.819, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.869483828836007e-07, | |
| "loss": 1.0522, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.134666272774034e-07, | |
| "loss": 1.0221, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.477045108941978e-07, | |
| "loss": 0.93, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.8966712629558957e-07, | |
| "loss": 0.901, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.3202154636383057, | |
| "eval_runtime": 118.9855, | |
| "eval_samples_per_second": 3.706, | |
| "eval_steps_per_second": 1.857, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.393589678466367e-07, | |
| "loss": 1.0046, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.678393136776098e-08, | |
| "loss": 0.9131, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6.194531383307833e-08, | |
| "loss": 1.0747, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.484581311511414e-08, | |
| "loss": 0.994, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.5487527775848164e-08, | |
| "loss": 0.8788, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.87195690421116e-09, | |
| "loss": 0.8329, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.963, | |
| "step": 367 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 367, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 1.0382469155751199e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |