| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9626955475330926, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019902912621359224, | |
| "loss": 2.6183, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00019805825242718447, | |
| "loss": 2.2731, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001970873786407767, | |
| "loss": 2.4264, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019611650485436895, | |
| "loss": 2.3803, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019514563106796118, | |
| "loss": 2.2789, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001941747572815534, | |
| "loss": 2.5586, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019320388349514564, | |
| "loss": 2.3255, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019223300970873787, | |
| "loss": 2.2983, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001912621359223301, | |
| "loss": 2.1903, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019029126213592236, | |
| "loss": 2.3516, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018932038834951458, | |
| "loss": 2.215, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018834951456310681, | |
| "loss": 2.2354, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018737864077669904, | |
| "loss": 2.2487, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018640776699029127, | |
| "loss": 2.1957, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001854368932038835, | |
| "loss": 2.2036, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00018446601941747576, | |
| "loss": 2.1787, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00018349514563106799, | |
| "loss": 2.1839, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00018252427184466022, | |
| "loss": 2.1533, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018155339805825244, | |
| "loss": 2.2554, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018058252427184467, | |
| "loss": 2.2778, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001796116504854369, | |
| "loss": 2.382, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00017864077669902913, | |
| "loss": 2.0803, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001776699029126214, | |
| "loss": 2.26, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00017669902912621362, | |
| "loss": 2.2557, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00017572815533980585, | |
| "loss": 2.0614, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00017475728155339805, | |
| "loss": 2.1342, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00017378640776699028, | |
| "loss": 2.1781, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00017281553398058253, | |
| "loss": 2.1828, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00017184466019417476, | |
| "loss": 2.0557, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000170873786407767, | |
| "loss": 2.1914, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00016990291262135922, | |
| "loss": 2.3306, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00016893203883495145, | |
| "loss": 2.2901, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00016796116504854368, | |
| "loss": 2.1166, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00016699029126213594, | |
| "loss": 2.2927, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00016601941747572817, | |
| "loss": 2.2732, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001650485436893204, | |
| "loss": 2.1614, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00016407766990291262, | |
| "loss": 2.1986, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00016310679611650485, | |
| "loss": 2.3506, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00016213592233009708, | |
| "loss": 2.2425, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001611650485436893, | |
| "loss": 2.2483, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00016019417475728157, | |
| "loss": 2.031, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001592233009708738, | |
| "loss": 2.1587, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00015825242718446603, | |
| "loss": 2.1529, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00015728155339805825, | |
| "loss": 2.181, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00015631067961165048, | |
| "loss": 2.1168, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001553398058252427, | |
| "loss": 2.2189, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00015436893203883497, | |
| "loss": 2.1362, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001533980582524272, | |
| "loss": 2.0704, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00015242718446601943, | |
| "loss": 2.1273, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00015145631067961166, | |
| "loss": 2.1639, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015048543689320389, | |
| "loss": 2.1639, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00014951456310679611, | |
| "loss": 2.0664, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00014854368932038834, | |
| "loss": 2.0539, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001475728155339806, | |
| "loss": 2.206, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00014660194174757283, | |
| "loss": 2.1366, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00014563106796116506, | |
| "loss": 2.1016, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001446601941747573, | |
| "loss": 2.1042, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00014368932038834952, | |
| "loss": 2.144, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00014271844660194175, | |
| "loss": 2.0834, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.000141747572815534, | |
| "loss": 2.0255, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00014077669902912623, | |
| "loss": 2.131, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00013980582524271846, | |
| "loss": 2.2428, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0001388349514563107, | |
| "loss": 2.0831, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00013786407766990292, | |
| "loss": 2.1633, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00013689320388349515, | |
| "loss": 2.2224, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001359223300970874, | |
| "loss": 2.0999, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00013495145631067963, | |
| "loss": 2.1749, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00013398058252427186, | |
| "loss": 1.9726, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0001330097087378641, | |
| "loss": 2.1678, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00013203883495145632, | |
| "loss": 2.0646, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00013106796116504855, | |
| "loss": 2.0049, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00013009708737864078, | |
| "loss": 2.0944, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00012912621359223304, | |
| "loss": 2.2013, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00012815533980582526, | |
| "loss": 2.311, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001271844660194175, | |
| "loss": 2.0863, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00012621359223300972, | |
| "loss": 2.2028, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00012524271844660195, | |
| "loss": 2.0283, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00012427184466019418, | |
| "loss": 2.2133, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0001233009708737864, | |
| "loss": 2.1084, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00012233009708737864, | |
| "loss": 1.967, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00012135922330097087, | |
| "loss": 2.3109, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001203883495145631, | |
| "loss": 2.2248, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00011941747572815534, | |
| "loss": 2.1178, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00011844660194174757, | |
| "loss": 2.161, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001174757281553398, | |
| "loss": 2.0778, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00011650485436893204, | |
| "loss": 2.2326, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00011553398058252427, | |
| "loss": 2.0262, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0001145631067961165, | |
| "loss": 2.076, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00011359223300970874, | |
| "loss": 2.0044, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00011262135922330097, | |
| "loss": 2.0397, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001116504854368932, | |
| "loss": 2.1135, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00011067961165048544, | |
| "loss": 2.29, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00010970873786407767, | |
| "loss": 1.949, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0001087378640776699, | |
| "loss": 2.1177, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00010776699029126213, | |
| "loss": 2.1405, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00010679611650485437, | |
| "loss": 2.2089, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001058252427184466, | |
| "loss": 2.1267, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00010485436893203883, | |
| "loss": 2.0522, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00010388349514563107, | |
| "loss": 2.0273, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0001029126213592233, | |
| "loss": 2.1042, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 206, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 2.9528801422848e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |