| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14619883040935672, | |
| "global_step": 200, | |
| "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": 1.2695, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4688, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2927, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2911, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1655, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3511, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2358, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016, | |
| "loss": 1.287, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1919, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3329, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019999993359236733, | |
| "loss": 1.0765, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019999973436955748, | |
| "loss": 1.2112, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019999940233183508, | |
| "loss": 1.2021, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001999989374796411, | |
| "loss": 1.306, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019999833981359296, | |
| "loss": 1.2094, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019999760933448442, | |
| "loss": 1.3033, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019999674604328566, | |
| "loss": 1.2345, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019999574994114335, | |
| "loss": 1.1763, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019999462102938037, | |
| "loss": 1.2333, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019999335930949612, | |
| "loss": 1.213, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.181932806968689, | |
| "eval_runtime": 76.4827, | |
| "eval_samples_per_second": 0.732, | |
| "eval_steps_per_second": 0.183, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019999196478316637, | |
| "loss": 1.1985, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019999043745224323, | |
| "loss": 1.2438, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019998877731875524, | |
| "loss": 1.0714, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019998698438490736, | |
| "loss": 1.2336, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019998505865308084, | |
| "loss": 1.1357, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019998300012583333, | |
| "loss": 1.1176, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001999808088058989, | |
| "loss": 1.2537, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001999784846961879, | |
| "loss": 1.2098, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001999760277997872, | |
| "loss": 1.3226, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019997343811995984, | |
| "loss": 1.271, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019997071566014535, | |
| "loss": 1.1423, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001999678604239596, | |
| "loss": 1.1422, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019996487241519473, | |
| "loss": 1.2029, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001999617516378193, | |
| "loss": 1.1305, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019995849809597814, | |
| "loss": 1.3264, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001999551117939925, | |
| "loss": 1.2266, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001999515927363599, | |
| "loss": 1.1214, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019994794092775418, | |
| "loss": 1.2081, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019994415637302547, | |
| "loss": 1.2039, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019994023907720027, | |
| "loss": 1.2026, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.152363896369934, | |
| "eval_runtime": 76.6763, | |
| "eval_samples_per_second": 0.73, | |
| "eval_steps_per_second": 0.183, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019993618904548131, | |
| "loss": 1.2681, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001999320062832477, | |
| "loss": 1.0463, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019992769079605477, | |
| "loss": 1.2364, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019992324258963413, | |
| "loss": 1.1188, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019991866166989367, | |
| "loss": 1.2932, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019991394804291758, | |
| "loss": 1.1784, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019990910171496627, | |
| "loss": 1.2541, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001999041226924764, | |
| "loss": 1.1132, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019989901098206082, | |
| "loss": 1.1555, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019989376659050877, | |
| "loss": 1.3394, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001998883895247855, | |
| "loss": 1.2951, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019988287979203265, | |
| "loss": 1.2399, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001998772373995679, | |
| "loss": 1.1664, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001998714623548853, | |
| "loss": 1.117, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019986555466565493, | |
| "loss": 1.1931, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019985951433972314, | |
| "loss": 1.2058, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019985334138511237, | |
| "loss": 1.1864, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001998470358100213, | |
| "loss": 1.2206, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019984059762282467, | |
| "loss": 1.0549, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019983402683207332, | |
| "loss": 1.0102, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.1410892009735107, | |
| "eval_runtime": 76.6475, | |
| "eval_samples_per_second": 0.731, | |
| "eval_steps_per_second": 0.183, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019982732344649433, | |
| "loss": 1.0848, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019982048747499081, | |
| "loss": 1.3566, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019981351892664194, | |
| "loss": 1.2252, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019980641781070307, | |
| "loss": 1.2283, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019979918413660553, | |
| "loss": 1.1728, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019979181791395672, | |
| "loss": 1.0926, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019978431915254017, | |
| "loss": 1.1868, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019977668786231534, | |
| "loss": 1.0868, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019976892405341773, | |
| "loss": 1.1116, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019976102773615892, | |
| "loss": 1.1881, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019975299892102636, | |
| "loss": 1.1795, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019974483761868358, | |
| "loss": 1.1028, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019973654383997007, | |
| "loss": 0.9675, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019972811759590118, | |
| "loss": 1.2491, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019971955889766825, | |
| "loss": 1.1393, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019971086775663857, | |
| "loss": 1.1288, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019970204418435526, | |
| "loss": 1.1794, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001996930881925374, | |
| "loss": 0.9819, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001996839997930799, | |
| "loss": 1.1291, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001996747789980536, | |
| "loss": 1.2502, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.1336756944656372, | |
| "eval_runtime": 76.5931, | |
| "eval_samples_per_second": 0.731, | |
| "eval_steps_per_second": 0.183, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000199665425819705, | |
| "loss": 1.0629, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019965594027045665, | |
| "loss": 1.0234, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019964632236290681, | |
| "loss": 1.1065, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019963657210982948, | |
| "loss": 1.1702, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001996266895241745, | |
| "loss": 1.2096, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019961667461906743, | |
| "loss": 1.232, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019960652740780966, | |
| "loss": 1.0296, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001995962479038782, | |
| "loss": 1.1686, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019958583612092576, | |
| "loss": 1.1196, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019957529207278082, | |
| "loss": 1.3479, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001995646157734475, | |
| "loss": 1.1783, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001995538072371055, | |
| "loss": 1.2225, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019954286647811027, | |
| "loss": 1.0859, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019953179351099275, | |
| "loss": 1.0763, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019952058835045957, | |
| "loss": 1.2688, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001995092510113929, | |
| "loss": 1.1738, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019949778150885042, | |
| "loss": 1.1326, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001994861798580654, | |
| "loss": 1.1722, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001994744460744466, | |
| "loss": 1.2148, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019946258017357828, | |
| "loss": 1.2499, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.1291786432266235, | |
| "eval_runtime": 76.5934, | |
| "eval_samples_per_second": 0.731, | |
| "eval_steps_per_second": 0.183, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019945058217122016, | |
| "loss": 1.1765, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019943845208330742, | |
| "loss": 1.2101, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001994261899259507, | |
| "loss": 1.1028, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019941379571543596, | |
| "loss": 1.2198, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019940126946822465, | |
| "loss": 1.2474, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019938861120095353, | |
| "loss": 1.1917, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001993758209304347, | |
| "loss": 1.2239, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019936289867365556, | |
| "loss": 1.2406, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001993498444477789, | |
| "loss": 1.2051, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019933665827014273, | |
| "loss": 1.146, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019932334015826023, | |
| "loss": 1.0871, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019930989012981992, | |
| "loss": 1.1184, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019929630820268552, | |
| "loss": 1.0224, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019928259439489589, | |
| "loss": 1.0958, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001992687487246651, | |
| "loss": 1.1811, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019925477121038218, | |
| "loss": 1.3126, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019924066187061156, | |
| "loss": 1.0572, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001992264207240925, | |
| "loss": 1.0597, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019921204778973944, | |
| "loss": 1.1559, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019919754308664187, | |
| "loss": 1.2146, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.1247767210006714, | |
| "eval_runtime": 80.1123, | |
| "eval_samples_per_second": 0.699, | |
| "eval_steps_per_second": 0.175, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001991829066340642, | |
| "loss": 1.2127, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019916813845144587, | |
| "loss": 1.1637, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019915323855840131, | |
| "loss": 1.2383, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019913820697471985, | |
| "loss": 1.0641, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019912304372036573, | |
| "loss": 1.115, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.000199107748815478, | |
| "loss": 1.0733, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019909232228037076, | |
| "loss": 1.2392, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019907676413553267, | |
| "loss": 1.3308, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019906107440162743, | |
| "loss": 1.1723, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019904525309949334, | |
| "loss": 1.1327, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019902930025014347, | |
| "loss": 1.1309, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019901321587476574, | |
| "loss": 1.1563, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019899699999472258, | |
| "loss": 1.1824, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001989806526315512, | |
| "loss": 1.2014, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019896417380696333, | |
| "loss": 1.182, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001989475635428454, | |
| "loss": 1.1519, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001989308218612584, | |
| "loss": 1.2197, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019891394878443784, | |
| "loss": 1.01, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001988969443347937, | |
| "loss": 1.2011, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001988798085349105, | |
| "loss": 1.1338, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.120542287826538, | |
| "eval_runtime": 79.9836, | |
| "eval_samples_per_second": 0.7, | |
| "eval_steps_per_second": 0.175, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019886254140754722, | |
| "loss": 1.0325, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001988451429756372, | |
| "loss": 1.2331, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019882761326228825, | |
| "loss": 1.1751, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001988099522907825, | |
| "loss": 1.2066, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019879216008457642, | |
| "loss": 1.1406, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019877423666730075, | |
| "loss": 1.2226, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019875618206276053, | |
| "loss": 1.1612, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019873799629493508, | |
| "loss": 1.203, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001987196793879778, | |
| "loss": 1.1134, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019870123136621638, | |
| "loss": 1.164, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019868265225415265, | |
| "loss": 0.9973, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001986639420764624, | |
| "loss": 1.0642, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019864510085799568, | |
| "loss": 1.1626, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019862612862377648, | |
| "loss": 1.1529, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019860702539900287, | |
| "loss": 1.2552, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019858779120904678, | |
| "loss": 1.1867, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019856842607945418, | |
| "loss": 1.2168, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019854893003594493, | |
| "loss": 1.1797, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019852930310441274, | |
| "loss": 1.2606, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019850954531092517, | |
| "loss": 1.2599, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.1176784038543701, | |
| "eval_runtime": 79.9641, | |
| "eval_samples_per_second": 0.7, | |
| "eval_steps_per_second": 0.175, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019848965668172356, | |
| "loss": 0.9995, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001984696372432231, | |
| "loss": 1.2258, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019844948702201265, | |
| "loss": 1.085, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019842920604485473, | |
| "loss": 1.125, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001984087943386856, | |
| "loss": 1.1549, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019838825193061518, | |
| "loss": 1.1749, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019836757884792683, | |
| "loss": 1.1702, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001983467751180776, | |
| "loss": 1.2037, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019832584076869805, | |
| "loss": 1.0019, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019830477582759212, | |
| "loss": 1.1183, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019828358032273735, | |
| "loss": 1.0197, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019826225428228457, | |
| "loss": 1.107, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000198240797734558, | |
| "loss": 1.1855, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001982192107080552, | |
| "loss": 1.2044, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019819749323144709, | |
| "loss": 1.1586, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019817564533357773, | |
| "loss": 1.1092, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019815366704346453, | |
| "loss": 1.2592, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019813155839029797, | |
| "loss": 1.1808, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019810931940344176, | |
| "loss": 1.1179, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001980869501124326, | |
| "loss": 1.1333, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.1160587072372437, | |
| "eval_runtime": 79.8665, | |
| "eval_samples_per_second": 0.701, | |
| "eval_steps_per_second": 0.175, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019806445054698039, | |
| "loss": 1.0633, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019804182073696793, | |
| "loss": 1.1252, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019801906071245111, | |
| "loss": 1.1522, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001979961705036587, | |
| "loss": 1.1706, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019797315014099238, | |
| "loss": 1.1142, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019794999965502672, | |
| "loss": 1.0345, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001979267190765091, | |
| "loss": 1.1029, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019790330843635966, | |
| "loss": 1.1628, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019787976776567133, | |
| "loss": 1.1569, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019785609709570973, | |
| "loss": 1.2024, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019783229645791307, | |
| "loss": 1.1602, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019780836588389225, | |
| "loss": 1.1588, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019778430540543077, | |
| "loss": 1.1104, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019776011505448455, | |
| "loss": 1.1437, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019773579486318213, | |
| "loss": 1.2098, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019771134486382436, | |
| "loss": 1.125, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019768676508888467, | |
| "loss": 1.0576, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019766205557100868, | |
| "loss": 1.1982, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019763721634301443, | |
| "loss": 1.1395, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001976122474378922, | |
| "loss": 1.2491, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.1136831045150757, | |
| "eval_runtime": 79.9646, | |
| "eval_samples_per_second": 0.7, | |
| "eval_steps_per_second": 0.175, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 2736, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.588426799910912e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |