gemmy-checkpoint-288 / trainer_state.json
kubernetes-bad's picture
Upload folder using huggingface_hub
ef0ced8 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9982668977469671,
"eval_steps": 500,
"global_step": 288,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0034662045060658577,
"grad_norm": 0.322265625,
"learning_rate": 4.000000000000001e-06,
"loss": 1.5121,
"step": 1
},
{
"epoch": 0.006932409012131715,
"grad_norm": 0.66015625,
"learning_rate": 8.000000000000001e-06,
"loss": 1.5791,
"step": 2
},
{
"epoch": 0.010398613518197574,
"grad_norm": 0.330078125,
"learning_rate": 1.2e-05,
"loss": 1.5152,
"step": 3
},
{
"epoch": 0.01386481802426343,
"grad_norm": 0.32421875,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.5108,
"step": 4
},
{
"epoch": 0.01733102253032929,
"grad_norm": 0.326171875,
"learning_rate": 2e-05,
"loss": 1.516,
"step": 5
},
{
"epoch": 0.02079722703639515,
"grad_norm": 0.32421875,
"learning_rate": 2.4e-05,
"loss": 1.536,
"step": 6
},
{
"epoch": 0.024263431542461005,
"grad_norm": 0.34765625,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.6207,
"step": 7
},
{
"epoch": 0.02772963604852686,
"grad_norm": 0.30078125,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.5638,
"step": 8
},
{
"epoch": 0.03119584055459272,
"grad_norm": 0.234375,
"learning_rate": 3.6e-05,
"loss": 1.508,
"step": 9
},
{
"epoch": 0.03466204506065858,
"grad_norm": 0.2578125,
"learning_rate": 4e-05,
"loss": 1.4821,
"step": 10
},
{
"epoch": 0.038128249566724434,
"grad_norm": 0.287109375,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.4769,
"step": 11
},
{
"epoch": 0.0415944540727903,
"grad_norm": 0.3203125,
"learning_rate": 4.8e-05,
"loss": 1.4965,
"step": 12
},
{
"epoch": 0.045060658578856154,
"grad_norm": 0.2734375,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.4346,
"step": 13
},
{
"epoch": 0.04852686308492201,
"grad_norm": 0.2392578125,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.4573,
"step": 14
},
{
"epoch": 0.05199306759098787,
"grad_norm": 0.263671875,
"learning_rate": 6e-05,
"loss": 1.3925,
"step": 15
},
{
"epoch": 0.05545927209705372,
"grad_norm": 0.2392578125,
"learning_rate": 6.400000000000001e-05,
"loss": 1.45,
"step": 16
},
{
"epoch": 0.058925476603119586,
"grad_norm": 0.20703125,
"learning_rate": 6.800000000000001e-05,
"loss": 1.4752,
"step": 17
},
{
"epoch": 0.06239168110918544,
"grad_norm": 0.1630859375,
"learning_rate": 7.2e-05,
"loss": 1.2915,
"step": 18
},
{
"epoch": 0.0658578856152513,
"grad_norm": 0.1640625,
"learning_rate": 7.6e-05,
"loss": 1.4101,
"step": 19
},
{
"epoch": 0.06932409012131716,
"grad_norm": 0.1328125,
"learning_rate": 8e-05,
"loss": 1.3524,
"step": 20
},
{
"epoch": 0.07279029462738301,
"grad_norm": 0.1279296875,
"learning_rate": 8.4e-05,
"loss": 1.3107,
"step": 21
},
{
"epoch": 0.07625649913344887,
"grad_norm": 0.263671875,
"learning_rate": 8.800000000000001e-05,
"loss": 1.4215,
"step": 22
},
{
"epoch": 0.07972270363951472,
"grad_norm": 0.1435546875,
"learning_rate": 9.200000000000001e-05,
"loss": 1.364,
"step": 23
},
{
"epoch": 0.0831889081455806,
"grad_norm": 0.154296875,
"learning_rate": 9.6e-05,
"loss": 1.3493,
"step": 24
},
{
"epoch": 0.08665511265164645,
"grad_norm": 0.12451171875,
"learning_rate": 0.0001,
"loss": 1.3874,
"step": 25
},
{
"epoch": 0.09012131715771231,
"grad_norm": 0.1220703125,
"learning_rate": 0.00010400000000000001,
"loss": 1.4087,
"step": 26
},
{
"epoch": 0.09358752166377816,
"grad_norm": 0.15234375,
"learning_rate": 0.00010800000000000001,
"loss": 1.3556,
"step": 27
},
{
"epoch": 0.09705372616984402,
"grad_norm": 0.12158203125,
"learning_rate": 0.00011200000000000001,
"loss": 1.3657,
"step": 28
},
{
"epoch": 0.10051993067590988,
"grad_norm": 0.12060546875,
"learning_rate": 0.000116,
"loss": 1.3307,
"step": 29
},
{
"epoch": 0.10398613518197573,
"grad_norm": 0.134765625,
"learning_rate": 0.00012,
"loss": 1.389,
"step": 30
},
{
"epoch": 0.10745233968804159,
"grad_norm": 0.11865234375,
"learning_rate": 0.000124,
"loss": 1.3153,
"step": 31
},
{
"epoch": 0.11091854419410745,
"grad_norm": 0.1162109375,
"learning_rate": 0.00012800000000000002,
"loss": 1.2661,
"step": 32
},
{
"epoch": 0.11438474870017332,
"grad_norm": 0.1240234375,
"learning_rate": 0.000132,
"loss": 1.3624,
"step": 33
},
{
"epoch": 0.11785095320623917,
"grad_norm": 0.1640625,
"learning_rate": 0.00013600000000000003,
"loss": 1.3389,
"step": 34
},
{
"epoch": 0.12131715771230503,
"grad_norm": 0.10888671875,
"learning_rate": 0.00014,
"loss": 1.257,
"step": 35
},
{
"epoch": 0.12478336221837089,
"grad_norm": 0.11083984375,
"learning_rate": 0.000144,
"loss": 1.2892,
"step": 36
},
{
"epoch": 0.12824956672443674,
"grad_norm": 0.2890625,
"learning_rate": 0.000148,
"loss": 1.3073,
"step": 37
},
{
"epoch": 0.1317157712305026,
"grad_norm": 0.11962890625,
"learning_rate": 0.000152,
"loss": 1.2713,
"step": 38
},
{
"epoch": 0.13518197573656845,
"grad_norm": 0.142578125,
"learning_rate": 0.00015600000000000002,
"loss": 1.3651,
"step": 39
},
{
"epoch": 0.1386481802426343,
"grad_norm": 0.123046875,
"learning_rate": 0.00016,
"loss": 1.376,
"step": 40
},
{
"epoch": 0.14211438474870017,
"grad_norm": 0.146484375,
"learning_rate": 0.000164,
"loss": 1.4392,
"step": 41
},
{
"epoch": 0.14558058925476602,
"grad_norm": 0.169921875,
"learning_rate": 0.000168,
"loss": 1.3044,
"step": 42
},
{
"epoch": 0.14904679376083188,
"grad_norm": 0.1484375,
"learning_rate": 0.000172,
"loss": 1.3437,
"step": 43
},
{
"epoch": 0.15251299826689774,
"grad_norm": 0.1640625,
"learning_rate": 0.00017600000000000002,
"loss": 1.3892,
"step": 44
},
{
"epoch": 0.1559792027729636,
"grad_norm": 0.12451171875,
"learning_rate": 0.00018,
"loss": 1.3279,
"step": 45
},
{
"epoch": 0.15944540727902945,
"grad_norm": 0.15625,
"learning_rate": 0.00018400000000000003,
"loss": 1.3208,
"step": 46
},
{
"epoch": 0.16291161178509533,
"grad_norm": 0.1416015625,
"learning_rate": 0.000188,
"loss": 1.3207,
"step": 47
},
{
"epoch": 0.1663778162911612,
"grad_norm": 0.1337890625,
"learning_rate": 0.000192,
"loss": 1.325,
"step": 48
},
{
"epoch": 0.16984402079722705,
"grad_norm": 0.162109375,
"learning_rate": 0.000196,
"loss": 1.3512,
"step": 49
},
{
"epoch": 0.1733102253032929,
"grad_norm": 0.12890625,
"learning_rate": 0.0002,
"loss": 1.2986,
"step": 50
},
{
"epoch": 0.17677642980935876,
"grad_norm": 0.40234375,
"learning_rate": 0.00019999821640202586,
"loss": 1.3212,
"step": 51
},
{
"epoch": 0.18024263431542462,
"grad_norm": 0.1376953125,
"learning_rate": 0.00019999286567172776,
"loss": 1.3269,
"step": 52
},
{
"epoch": 0.18370883882149047,
"grad_norm": 0.13671875,
"learning_rate": 0.00019998394799997682,
"loss": 1.2831,
"step": 53
},
{
"epoch": 0.18717504332755633,
"grad_norm": 0.1591796875,
"learning_rate": 0.00019997146370488383,
"loss": 1.2762,
"step": 54
},
{
"epoch": 0.19064124783362218,
"grad_norm": 0.1279296875,
"learning_rate": 0.00019995541323178807,
"loss": 1.2278,
"step": 55
},
{
"epoch": 0.19410745233968804,
"grad_norm": 0.15234375,
"learning_rate": 0.00019993579715324135,
"loss": 1.2913,
"step": 56
},
{
"epoch": 0.1975736568457539,
"grad_norm": 0.1298828125,
"learning_rate": 0.00019991261616898767,
"loss": 1.2971,
"step": 57
},
{
"epoch": 0.20103986135181975,
"grad_norm": 0.162109375,
"learning_rate": 0.00019988587110593808,
"loss": 1.304,
"step": 58
},
{
"epoch": 0.2045060658578856,
"grad_norm": 0.12890625,
"learning_rate": 0.00019985556291814147,
"loss": 1.2796,
"step": 59
},
{
"epoch": 0.20797227036395147,
"grad_norm": 0.1728515625,
"learning_rate": 0.00019982169268675023,
"loss": 1.3182,
"step": 60
},
{
"epoch": 0.21143847487001732,
"grad_norm": 0.3828125,
"learning_rate": 0.00019978426161998194,
"loss": 1.4574,
"step": 61
},
{
"epoch": 0.21490467937608318,
"grad_norm": 0.13671875,
"learning_rate": 0.00019974327105307604,
"loss": 1.284,
"step": 62
},
{
"epoch": 0.21837088388214904,
"grad_norm": 0.138671875,
"learning_rate": 0.00019969872244824638,
"loss": 1.2724,
"step": 63
},
{
"epoch": 0.2218370883882149,
"grad_norm": 0.546875,
"learning_rate": 0.00019965061739462902,
"loss": 1.28,
"step": 64
},
{
"epoch": 0.22530329289428075,
"grad_norm": 0.1220703125,
"learning_rate": 0.00019959895760822546,
"loss": 1.219,
"step": 65
},
{
"epoch": 0.22876949740034663,
"grad_norm": 0.126953125,
"learning_rate": 0.00019954374493184152,
"loss": 1.2601,
"step": 66
},
{
"epoch": 0.2322357019064125,
"grad_norm": 0.134765625,
"learning_rate": 0.00019948498133502153,
"loss": 1.3263,
"step": 67
},
{
"epoch": 0.23570190641247835,
"grad_norm": 0.1435546875,
"learning_rate": 0.00019942266891397815,
"loss": 1.3496,
"step": 68
},
{
"epoch": 0.2391681109185442,
"grad_norm": 0.125,
"learning_rate": 0.00019935680989151757,
"loss": 1.2856,
"step": 69
},
{
"epoch": 0.24263431542461006,
"grad_norm": 0.138671875,
"learning_rate": 0.0001992874066169601,
"loss": 1.2727,
"step": 70
},
{
"epoch": 0.24610051993067592,
"grad_norm": 0.111328125,
"learning_rate": 0.00019921446156605664,
"loss": 1.214,
"step": 71
},
{
"epoch": 0.24956672443674177,
"grad_norm": 0.150390625,
"learning_rate": 0.00019913797734089997,
"loss": 1.2299,
"step": 72
},
{
"epoch": 0.2530329289428076,
"grad_norm": 0.1357421875,
"learning_rate": 0.00019905795666983234,
"loss": 1.2439,
"step": 73
},
{
"epoch": 0.2564991334488735,
"grad_norm": 0.1435546875,
"learning_rate": 0.00019897440240734788,
"loss": 1.2721,
"step": 74
},
{
"epoch": 0.25996533795493937,
"grad_norm": 0.1337890625,
"learning_rate": 0.00019888731753399088,
"loss": 1.2411,
"step": 75
},
{
"epoch": 0.2634315424610052,
"grad_norm": 0.1494140625,
"learning_rate": 0.00019879670515624936,
"loss": 1.2302,
"step": 76
},
{
"epoch": 0.2668977469670711,
"grad_norm": 0.1318359375,
"learning_rate": 0.0001987025685064444,
"loss": 1.2711,
"step": 77
},
{
"epoch": 0.2703639514731369,
"grad_norm": 0.3203125,
"learning_rate": 0.0001986049109426148,
"loss": 1.2415,
"step": 78
},
{
"epoch": 0.2738301559792028,
"grad_norm": 0.1494140625,
"learning_rate": 0.00019850373594839716,
"loss": 1.3111,
"step": 79
},
{
"epoch": 0.2772963604852686,
"grad_norm": 0.142578125,
"learning_rate": 0.00019839904713290184,
"loss": 1.3138,
"step": 80
},
{
"epoch": 0.2807625649913345,
"grad_norm": 0.1318359375,
"learning_rate": 0.000198290848230584,
"loss": 1.2662,
"step": 81
},
{
"epoch": 0.28422876949740034,
"grad_norm": 0.13671875,
"learning_rate": 0.00019817914310111046,
"loss": 1.2258,
"step": 82
},
{
"epoch": 0.2876949740034662,
"grad_norm": 0.1728515625,
"learning_rate": 0.0001980639357292221,
"loss": 1.2435,
"step": 83
},
{
"epoch": 0.29116117850953205,
"grad_norm": 0.5546875,
"learning_rate": 0.00019794523022459166,
"loss": 1.2568,
"step": 84
},
{
"epoch": 0.29462738301559793,
"grad_norm": 0.1455078125,
"learning_rate": 0.00019782303082167704,
"loss": 1.2181,
"step": 85
},
{
"epoch": 0.29809358752166376,
"grad_norm": 0.283203125,
"learning_rate": 0.00019769734187957038,
"loss": 1.2465,
"step": 86
},
{
"epoch": 0.30155979202772965,
"grad_norm": 0.1552734375,
"learning_rate": 0.00019756816788184259,
"loss": 1.2623,
"step": 87
},
{
"epoch": 0.3050259965337955,
"grad_norm": 0.1474609375,
"learning_rate": 0.00019743551343638324,
"loss": 1.193,
"step": 88
},
{
"epoch": 0.30849220103986136,
"grad_norm": 0.1123046875,
"learning_rate": 0.00019729938327523635,
"loss": 1.2262,
"step": 89
},
{
"epoch": 0.3119584055459272,
"grad_norm": 0.1796875,
"learning_rate": 0.00019715978225443148,
"loss": 1.2862,
"step": 90
},
{
"epoch": 0.31542461005199307,
"grad_norm": 0.146484375,
"learning_rate": 0.00019701671535381064,
"loss": 1.2466,
"step": 91
},
{
"epoch": 0.3188908145580589,
"grad_norm": 0.150390625,
"learning_rate": 0.0001968701876768505,
"loss": 1.2048,
"step": 92
},
{
"epoch": 0.3223570190641248,
"grad_norm": 0.1533203125,
"learning_rate": 0.00019672020445048036,
"loss": 1.3168,
"step": 93
},
{
"epoch": 0.32582322357019067,
"grad_norm": 0.1416015625,
"learning_rate": 0.00019656677102489588,
"loss": 1.2833,
"step": 94
},
{
"epoch": 0.3292894280762565,
"grad_norm": 0.1318359375,
"learning_rate": 0.00019640989287336792,
"loss": 1.3131,
"step": 95
},
{
"epoch": 0.3327556325823224,
"grad_norm": 0.1591796875,
"learning_rate": 0.00019624957559204761,
"loss": 1.2941,
"step": 96
},
{
"epoch": 0.3362218370883882,
"grad_norm": 0.150390625,
"learning_rate": 0.00019608582489976647,
"loss": 1.2618,
"step": 97
},
{
"epoch": 0.3396880415944541,
"grad_norm": 0.130859375,
"learning_rate": 0.0001959186466378326,
"loss": 1.2308,
"step": 98
},
{
"epoch": 0.3431542461005199,
"grad_norm": 0.12890625,
"learning_rate": 0.00019574804676982216,
"loss": 1.1744,
"step": 99
},
{
"epoch": 0.3466204506065858,
"grad_norm": 0.14453125,
"learning_rate": 0.00019557403138136672,
"loss": 1.2391,
"step": 100
},
{
"epoch": 0.35008665511265163,
"grad_norm": 0.1337890625,
"learning_rate": 0.0001953966066799362,
"loss": 1.2976,
"step": 101
},
{
"epoch": 0.3535528596187175,
"grad_norm": 0.1318359375,
"learning_rate": 0.00019521577899461731,
"loss": 1.289,
"step": 102
},
{
"epoch": 0.35701906412478335,
"grad_norm": 0.130859375,
"learning_rate": 0.00019503155477588796,
"loss": 1.219,
"step": 103
},
{
"epoch": 0.36048526863084923,
"grad_norm": 0.181640625,
"learning_rate": 0.000194843940595387,
"loss": 1.2099,
"step": 104
},
{
"epoch": 0.36395147313691506,
"grad_norm": 0.146484375,
"learning_rate": 0.00019465294314567987,
"loss": 1.2524,
"step": 105
},
{
"epoch": 0.36741767764298094,
"grad_norm": 0.12451171875,
"learning_rate": 0.0001944585692400199,
"loss": 1.2382,
"step": 106
},
{
"epoch": 0.3708838821490468,
"grad_norm": 0.1328125,
"learning_rate": 0.0001942608258121051,
"loss": 1.259,
"step": 107
},
{
"epoch": 0.37435008665511266,
"grad_norm": 0.32421875,
"learning_rate": 0.00019405971991583108,
"loss": 1.2613,
"step": 108
},
{
"epoch": 0.3778162911611785,
"grad_norm": 0.349609375,
"learning_rate": 0.0001938552587250392,
"loss": 1.3308,
"step": 109
},
{
"epoch": 0.38128249566724437,
"grad_norm": 0.2138671875,
"learning_rate": 0.00019364744953326074,
"loss": 1.3292,
"step": 110
},
{
"epoch": 0.3847487001733102,
"grad_norm": 0.146484375,
"learning_rate": 0.00019343629975345685,
"loss": 1.2605,
"step": 111
},
{
"epoch": 0.3882149046793761,
"grad_norm": 0.142578125,
"learning_rate": 0.00019322181691775386,
"loss": 1.2033,
"step": 112
},
{
"epoch": 0.39168110918544197,
"grad_norm": 0.138671875,
"learning_rate": 0.00019300400867717482,
"loss": 1.2595,
"step": 113
},
{
"epoch": 0.3951473136915078,
"grad_norm": 0.1962890625,
"learning_rate": 0.00019278288280136647,
"loss": 1.245,
"step": 114
},
{
"epoch": 0.3986135181975737,
"grad_norm": 0.1533203125,
"learning_rate": 0.00019255844717832205,
"loss": 1.2452,
"step": 115
},
{
"epoch": 0.4020797227036395,
"grad_norm": 0.1318359375,
"learning_rate": 0.00019233070981410007,
"loss": 1.2467,
"step": 116
},
{
"epoch": 0.4055459272097054,
"grad_norm": 0.1455078125,
"learning_rate": 0.00019209967883253849,
"loss": 1.2339,
"step": 117
},
{
"epoch": 0.4090121317157712,
"grad_norm": 0.1455078125,
"learning_rate": 0.00019186536247496518,
"loss": 1.2301,
"step": 118
},
{
"epoch": 0.4124783362218371,
"grad_norm": 0.2021484375,
"learning_rate": 0.00019162776909990373,
"loss": 1.2376,
"step": 119
},
{
"epoch": 0.41594454072790293,
"grad_norm": 0.134765625,
"learning_rate": 0.00019138690718277542,
"loss": 1.2114,
"step": 120
},
{
"epoch": 0.4194107452339688,
"grad_norm": 0.1494140625,
"learning_rate": 0.00019114278531559675,
"loss": 1.2057,
"step": 121
},
{
"epoch": 0.42287694974003465,
"grad_norm": 0.1328125,
"learning_rate": 0.0001908954122066731,
"loss": 1.2832,
"step": 122
},
{
"epoch": 0.42634315424610053,
"grad_norm": 0.201171875,
"learning_rate": 0.000190644796680288,
"loss": 1.2481,
"step": 123
},
{
"epoch": 0.42980935875216636,
"grad_norm": 0.3046875,
"learning_rate": 0.00019039094767638832,
"loss": 1.212,
"step": 124
},
{
"epoch": 0.43327556325823224,
"grad_norm": 0.1552734375,
"learning_rate": 0.0001901338742502655,
"loss": 1.2385,
"step": 125
},
{
"epoch": 0.43674176776429807,
"grad_norm": 0.1982421875,
"learning_rate": 0.00018987358557223232,
"loss": 1.2925,
"step": 126
},
{
"epoch": 0.44020797227036396,
"grad_norm": 0.1474609375,
"learning_rate": 0.000189610090927296,
"loss": 1.2285,
"step": 127
},
{
"epoch": 0.4436741767764298,
"grad_norm": 0.12158203125,
"learning_rate": 0.00018934339971482674,
"loss": 1.2074,
"step": 128
},
{
"epoch": 0.44714038128249567,
"grad_norm": 0.126953125,
"learning_rate": 0.00018907352144822284,
"loss": 1.1342,
"step": 129
},
{
"epoch": 0.4506065857885615,
"grad_norm": 0.142578125,
"learning_rate": 0.00018880046575457074,
"loss": 1.2651,
"step": 130
},
{
"epoch": 0.4540727902946274,
"grad_norm": 0.1337890625,
"learning_rate": 0.00018852424237430216,
"loss": 1.1864,
"step": 131
},
{
"epoch": 0.45753899480069327,
"grad_norm": 0.1376953125,
"learning_rate": 0.0001882448611608463,
"loss": 1.1171,
"step": 132
},
{
"epoch": 0.4610051993067591,
"grad_norm": 0.1455078125,
"learning_rate": 0.0001879623320802785,
"loss": 1.2275,
"step": 133
},
{
"epoch": 0.464471403812825,
"grad_norm": 0.384765625,
"learning_rate": 0.00018767666521096466,
"loss": 1.2224,
"step": 134
},
{
"epoch": 0.4679376083188908,
"grad_norm": 0.140625,
"learning_rate": 0.00018738787074320179,
"loss": 1.2373,
"step": 135
},
{
"epoch": 0.4714038128249567,
"grad_norm": 0.1435546875,
"learning_rate": 0.00018709595897885439,
"loss": 1.2542,
"step": 136
},
{
"epoch": 0.4748700173310225,
"grad_norm": 0.146484375,
"learning_rate": 0.00018680094033098716,
"loss": 1.2231,
"step": 137
},
{
"epoch": 0.4783362218370884,
"grad_norm": 0.1298828125,
"learning_rate": 0.00018650282532349332,
"loss": 1.1947,
"step": 138
},
{
"epoch": 0.48180242634315423,
"grad_norm": 0.1630859375,
"learning_rate": 0.00018620162459071936,
"loss": 1.2309,
"step": 139
},
{
"epoch": 0.4852686308492201,
"grad_norm": 0.1552734375,
"learning_rate": 0.00018589734887708556,
"loss": 1.2276,
"step": 140
},
{
"epoch": 0.48873483535528595,
"grad_norm": 0.14453125,
"learning_rate": 0.0001855900090367029,
"loss": 1.2637,
"step": 141
},
{
"epoch": 0.49220103986135183,
"grad_norm": 0.1416015625,
"learning_rate": 0.00018527961603298572,
"loss": 1.3006,
"step": 142
},
{
"epoch": 0.49566724436741766,
"grad_norm": 0.1298828125,
"learning_rate": 0.00018496618093826063,
"loss": 1.2016,
"step": 143
},
{
"epoch": 0.49913344887348354,
"grad_norm": 0.1484375,
"learning_rate": 0.00018464971493337167,
"loss": 1.1819,
"step": 144
},
{
"epoch": 0.5025996533795494,
"grad_norm": 0.1552734375,
"learning_rate": 0.00018433022930728133,
"loss": 1.2551,
"step": 145
},
{
"epoch": 0.5060658578856152,
"grad_norm": 0.1337890625,
"learning_rate": 0.00018400773545666787,
"loss": 1.2634,
"step": 146
},
{
"epoch": 0.5095320623916811,
"grad_norm": 0.1416015625,
"learning_rate": 0.00018368224488551896,
"loss": 1.1993,
"step": 147
},
{
"epoch": 0.512998266897747,
"grad_norm": 0.1533203125,
"learning_rate": 0.00018335376920472097,
"loss": 1.2224,
"step": 148
},
{
"epoch": 0.5164644714038128,
"grad_norm": 0.16796875,
"learning_rate": 0.00018302232013164518,
"loss": 1.2288,
"step": 149
},
{
"epoch": 0.5199306759098787,
"grad_norm": 0.1328125,
"learning_rate": 0.0001826879094897294,
"loss": 1.1786,
"step": 150
},
{
"epoch": 0.5233968804159446,
"grad_norm": 0.138671875,
"learning_rate": 0.00018235054920805652,
"loss": 1.2411,
"step": 151
},
{
"epoch": 0.5268630849220104,
"grad_norm": 0.1337890625,
"learning_rate": 0.00018201025132092889,
"loss": 1.1916,
"step": 152
},
{
"epoch": 0.5303292894280762,
"grad_norm": 0.21875,
"learning_rate": 0.00018166702796743888,
"loss": 1.2354,
"step": 153
},
{
"epoch": 0.5337954939341422,
"grad_norm": 0.13671875,
"learning_rate": 0.00018132089139103613,
"loss": 1.24,
"step": 154
},
{
"epoch": 0.537261698440208,
"grad_norm": 0.1552734375,
"learning_rate": 0.00018097185393909049,
"loss": 1.2284,
"step": 155
},
{
"epoch": 0.5407279029462738,
"grad_norm": 0.294921875,
"learning_rate": 0.00018061992806245184,
"loss": 1.2164,
"step": 156
},
{
"epoch": 0.5441941074523396,
"grad_norm": 0.130859375,
"learning_rate": 0.00018026512631500583,
"loss": 1.204,
"step": 157
},
{
"epoch": 0.5476603119584056,
"grad_norm": 0.1357421875,
"learning_rate": 0.00017990746135322592,
"loss": 1.2307,
"step": 158
},
{
"epoch": 0.5511265164644714,
"grad_norm": 0.1630859375,
"learning_rate": 0.00017954694593572227,
"loss": 1.2445,
"step": 159
},
{
"epoch": 0.5545927209705372,
"grad_norm": 0.1904296875,
"learning_rate": 0.00017918359292278611,
"loss": 1.2107,
"step": 160
},
{
"epoch": 0.5580589254766031,
"grad_norm": 0.1484375,
"learning_rate": 0.0001788174152759315,
"loss": 1.1999,
"step": 161
},
{
"epoch": 0.561525129982669,
"grad_norm": 0.1337890625,
"learning_rate": 0.00017844842605743258,
"loss": 1.2639,
"step": 162
},
{
"epoch": 0.5649913344887348,
"grad_norm": 0.115234375,
"learning_rate": 0.00017807663842985777,
"loss": 1.1628,
"step": 163
},
{
"epoch": 0.5684575389948007,
"grad_norm": 0.1513671875,
"learning_rate": 0.00017770206565560033,
"loss": 1.2099,
"step": 164
},
{
"epoch": 0.5719237435008665,
"grad_norm": 0.1318359375,
"learning_rate": 0.00017732472109640503,
"loss": 1.231,
"step": 165
},
{
"epoch": 0.5753899480069324,
"grad_norm": 0.1318359375,
"learning_rate": 0.00017694461821289172,
"loss": 1.1915,
"step": 166
},
{
"epoch": 0.5788561525129983,
"grad_norm": 0.1416015625,
"learning_rate": 0.00017656177056407505,
"loss": 1.2476,
"step": 167
},
{
"epoch": 0.5823223570190641,
"grad_norm": 0.1435546875,
"learning_rate": 0.00017617619180688085,
"loss": 1.2174,
"step": 168
},
{
"epoch": 0.58578856152513,
"grad_norm": 0.1611328125,
"learning_rate": 0.0001757878956956589,
"loss": 1.1836,
"step": 169
},
{
"epoch": 0.5892547660311959,
"grad_norm": 0.1376953125,
"learning_rate": 0.00017539689608169238,
"loss": 1.1782,
"step": 170
},
{
"epoch": 0.5927209705372617,
"grad_norm": 0.16796875,
"learning_rate": 0.00017500320691270365,
"loss": 1.2416,
"step": 171
},
{
"epoch": 0.5961871750433275,
"grad_norm": 0.1328125,
"learning_rate": 0.0001746068422323568,
"loss": 1.1911,
"step": 172
},
{
"epoch": 0.5996533795493935,
"grad_norm": 0.1357421875,
"learning_rate": 0.00017420781617975665,
"loss": 1.2743,
"step": 173
},
{
"epoch": 0.6031195840554593,
"grad_norm": 0.1240234375,
"learning_rate": 0.00017380614298894442,
"loss": 1.2339,
"step": 174
},
{
"epoch": 0.6065857885615251,
"grad_norm": 0.1396484375,
"learning_rate": 0.0001734018369883898,
"loss": 1.2063,
"step": 175
},
{
"epoch": 0.610051993067591,
"grad_norm": 0.138671875,
"learning_rate": 0.0001729949126004802,
"loss": 1.2124,
"step": 176
},
{
"epoch": 0.6135181975736569,
"grad_norm": 0.134765625,
"learning_rate": 0.00017258538434100577,
"loss": 1.1958,
"step": 177
},
{
"epoch": 0.6169844020797227,
"grad_norm": 0.193359375,
"learning_rate": 0.00017217326681864207,
"loss": 1.1745,
"step": 178
},
{
"epoch": 0.6204506065857885,
"grad_norm": 0.16015625,
"learning_rate": 0.00017175857473442863,
"loss": 1.1491,
"step": 179
},
{
"epoch": 0.6239168110918544,
"grad_norm": 0.1181640625,
"learning_rate": 0.00017134132288124465,
"loss": 1.1795,
"step": 180
},
{
"epoch": 0.6273830155979203,
"grad_norm": 0.12451171875,
"learning_rate": 0.00017092152614328135,
"loss": 1.1323,
"step": 181
},
{
"epoch": 0.6308492201039861,
"grad_norm": 0.138671875,
"learning_rate": 0.00017049919949551102,
"loss": 1.2577,
"step": 182
},
{
"epoch": 0.634315424610052,
"grad_norm": 0.14453125,
"learning_rate": 0.00017007435800315263,
"loss": 1.2299,
"step": 183
},
{
"epoch": 0.6377816291161178,
"grad_norm": 0.1640625,
"learning_rate": 0.00016964701682113475,
"loss": 1.2503,
"step": 184
},
{
"epoch": 0.6412478336221837,
"grad_norm": 0.130859375,
"learning_rate": 0.00016921719119355468,
"loss": 1.1444,
"step": 185
},
{
"epoch": 0.6447140381282496,
"grad_norm": 0.134765625,
"learning_rate": 0.0001687848964531348,
"loss": 1.1779,
"step": 186
},
{
"epoch": 0.6481802426343154,
"grad_norm": 0.18359375,
"learning_rate": 0.00016835014802067558,
"loss": 1.1597,
"step": 187
},
{
"epoch": 0.6516464471403813,
"grad_norm": 0.13671875,
"learning_rate": 0.00016791296140450545,
"loss": 1.2693,
"step": 188
},
{
"epoch": 0.6551126516464472,
"grad_norm": 0.1337890625,
"learning_rate": 0.00016747335219992774,
"loss": 1.2418,
"step": 189
},
{
"epoch": 0.658578856152513,
"grad_norm": 0.130859375,
"learning_rate": 0.00016703133608866414,
"loss": 1.2335,
"step": 190
},
{
"epoch": 0.6620450606585788,
"grad_norm": 0.126953125,
"learning_rate": 0.00016658692883829548,
"loss": 1.1994,
"step": 191
},
{
"epoch": 0.6655112651646448,
"grad_norm": 0.1259765625,
"learning_rate": 0.00016614014630169917,
"loss": 1.1553,
"step": 192
},
{
"epoch": 0.6689774696707106,
"grad_norm": 0.1357421875,
"learning_rate": 0.00016569100441648374,
"loss": 1.187,
"step": 193
},
{
"epoch": 0.6724436741767764,
"grad_norm": 0.1259765625,
"learning_rate": 0.00016523951920442034,
"loss": 1.2037,
"step": 194
},
{
"epoch": 0.6759098786828422,
"grad_norm": 0.1318359375,
"learning_rate": 0.00016478570677087116,
"loss": 1.2211,
"step": 195
},
{
"epoch": 0.6793760831889082,
"grad_norm": 0.193359375,
"learning_rate": 0.00016432958330421497,
"loss": 1.2273,
"step": 196
},
{
"epoch": 0.682842287694974,
"grad_norm": 0.1435546875,
"learning_rate": 0.00016387116507526957,
"loss": 1.1865,
"step": 197
},
{
"epoch": 0.6863084922010398,
"grad_norm": 0.12451171875,
"learning_rate": 0.00016341046843671144,
"loss": 1.192,
"step": 198
},
{
"epoch": 0.6897746967071057,
"grad_norm": 0.150390625,
"learning_rate": 0.0001629475098224924,
"loss": 1.255,
"step": 199
},
{
"epoch": 0.6932409012131716,
"grad_norm": 0.1396484375,
"learning_rate": 0.0001624823057472534,
"loss": 1.2314,
"step": 200
},
{
"epoch": 0.6967071057192374,
"grad_norm": 0.13671875,
"learning_rate": 0.00016201487280573536,
"loss": 1.2079,
"step": 201
},
{
"epoch": 0.7001733102253033,
"grad_norm": 0.16015625,
"learning_rate": 0.00016154522767218725,
"loss": 1.2081,
"step": 202
},
{
"epoch": 0.7036395147313691,
"grad_norm": 0.1494140625,
"learning_rate": 0.0001610733870997712,
"loss": 1.2703,
"step": 203
},
{
"epoch": 0.707105719237435,
"grad_norm": 0.146484375,
"learning_rate": 0.000160599367919965,
"loss": 1.2438,
"step": 204
},
{
"epoch": 0.7105719237435009,
"grad_norm": 0.142578125,
"learning_rate": 0.00016012318704196164,
"loss": 1.2292,
"step": 205
},
{
"epoch": 0.7140381282495667,
"grad_norm": 0.1494140625,
"learning_rate": 0.0001596448614520661,
"loss": 1.2269,
"step": 206
},
{
"epoch": 0.7175043327556326,
"grad_norm": 0.263671875,
"learning_rate": 0.0001591644082130895,
"loss": 1.2389,
"step": 207
},
{
"epoch": 0.7209705372616985,
"grad_norm": 0.1474609375,
"learning_rate": 0.0001586818444637402,
"loss": 1.2191,
"step": 208
},
{
"epoch": 0.7244367417677643,
"grad_norm": 0.1630859375,
"learning_rate": 0.00015819718741801283,
"loss": 1.1904,
"step": 209
},
{
"epoch": 0.7279029462738301,
"grad_norm": 0.140625,
"learning_rate": 0.0001577104543645738,
"loss": 1.2045,
"step": 210
},
{
"epoch": 0.7313691507798961,
"grad_norm": 0.13671875,
"learning_rate": 0.00015722166266614494,
"loss": 1.2283,
"step": 211
},
{
"epoch": 0.7348353552859619,
"grad_norm": 0.265625,
"learning_rate": 0.00015673082975888386,
"loss": 1.2956,
"step": 212
},
{
"epoch": 0.7383015597920277,
"grad_norm": 0.138671875,
"learning_rate": 0.00015623797315176218,
"loss": 1.2189,
"step": 213
},
{
"epoch": 0.7417677642980935,
"grad_norm": 0.2099609375,
"learning_rate": 0.0001557431104259408,
"loss": 1.1593,
"step": 214
},
{
"epoch": 0.7452339688041595,
"grad_norm": 0.1376953125,
"learning_rate": 0.00015524625923414283,
"loss": 1.1329,
"step": 215
},
{
"epoch": 0.7487001733102253,
"grad_norm": 0.130859375,
"learning_rate": 0.0001547474373000238,
"loss": 1.1314,
"step": 216
},
{
"epoch": 0.7521663778162911,
"grad_norm": 0.1572265625,
"learning_rate": 0.00015424666241753966,
"loss": 1.2665,
"step": 217
},
{
"epoch": 0.755632582322357,
"grad_norm": 0.15234375,
"learning_rate": 0.0001537439524503116,
"loss": 1.2165,
"step": 218
},
{
"epoch": 0.7590987868284229,
"grad_norm": 0.1318359375,
"learning_rate": 0.00015323932533098925,
"loss": 1.2062,
"step": 219
},
{
"epoch": 0.7625649913344887,
"grad_norm": 0.1298828125,
"learning_rate": 0.00015273279906061082,
"loss": 1.1524,
"step": 220
},
{
"epoch": 0.7660311958405546,
"grad_norm": 0.140625,
"learning_rate": 0.0001522243917079608,
"loss": 1.1551,
"step": 221
},
{
"epoch": 0.7694974003466204,
"grad_norm": 0.1474609375,
"learning_rate": 0.00015171412140892575,
"loss": 1.2309,
"step": 222
},
{
"epoch": 0.7729636048526863,
"grad_norm": 0.150390625,
"learning_rate": 0.0001512020063658471,
"loss": 1.1908,
"step": 223
},
{
"epoch": 0.7764298093587522,
"grad_norm": 0.12158203125,
"learning_rate": 0.0001506880648468719,
"loss": 1.1917,
"step": 224
},
{
"epoch": 0.779896013864818,
"grad_norm": 0.146484375,
"learning_rate": 0.00015017231518530118,
"loss": 1.1562,
"step": 225
},
{
"epoch": 0.7833622183708839,
"grad_norm": 0.1396484375,
"learning_rate": 0.00014965477577893598,
"loss": 1.1602,
"step": 226
},
{
"epoch": 0.7868284228769498,
"grad_norm": 0.1630859375,
"learning_rate": 0.00014913546508942105,
"loss": 1.2065,
"step": 227
},
{
"epoch": 0.7902946273830156,
"grad_norm": 0.1484375,
"learning_rate": 0.0001486144016415862,
"loss": 1.1824,
"step": 228
},
{
"epoch": 0.7937608318890814,
"grad_norm": 0.1513671875,
"learning_rate": 0.00014809160402278572,
"loss": 1.1687,
"step": 229
},
{
"epoch": 0.7972270363951474,
"grad_norm": 0.158203125,
"learning_rate": 0.0001475670908822351,
"loss": 1.2072,
"step": 230
},
{
"epoch": 0.8006932409012132,
"grad_norm": 0.1396484375,
"learning_rate": 0.0001470408809303457,
"loss": 1.2255,
"step": 231
},
{
"epoch": 0.804159445407279,
"grad_norm": 0.1435546875,
"learning_rate": 0.00014651299293805774,
"loss": 1.243,
"step": 232
},
{
"epoch": 0.8076256499133448,
"grad_norm": 0.1337890625,
"learning_rate": 0.00014598344573617022,
"loss": 1.1895,
"step": 233
},
{
"epoch": 0.8110918544194108,
"grad_norm": 0.12890625,
"learning_rate": 0.0001454522582146695,
"loss": 1.1114,
"step": 234
},
{
"epoch": 0.8145580589254766,
"grad_norm": 0.1728515625,
"learning_rate": 0.0001449194493220553,
"loss": 1.1989,
"step": 235
},
{
"epoch": 0.8180242634315424,
"grad_norm": 0.1435546875,
"learning_rate": 0.0001443850380646649,
"loss": 1.2013,
"step": 236
},
{
"epoch": 0.8214904679376083,
"grad_norm": 0.1669921875,
"learning_rate": 0.00014384904350599496,
"loss": 1.1654,
"step": 237
},
{
"epoch": 0.8249566724436742,
"grad_norm": 0.142578125,
"learning_rate": 0.0001433114847660217,
"loss": 1.1622,
"step": 238
},
{
"epoch": 0.82842287694974,
"grad_norm": 0.1376953125,
"learning_rate": 0.0001427723810205187,
"loss": 1.1871,
"step": 239
},
{
"epoch": 0.8318890814558059,
"grad_norm": 0.173828125,
"learning_rate": 0.00014223175150037296,
"loss": 1.2285,
"step": 240
},
{
"epoch": 0.8353552859618717,
"grad_norm": 0.169921875,
"learning_rate": 0.00014168961549089874,
"loss": 1.1787,
"step": 241
},
{
"epoch": 0.8388214904679376,
"grad_norm": 0.1484375,
"learning_rate": 0.00014114599233114986,
"loss": 1.1703,
"step": 242
},
{
"epoch": 0.8422876949740035,
"grad_norm": 0.13671875,
"learning_rate": 0.00014060090141322968,
"loss": 1.1674,
"step": 243
},
{
"epoch": 0.8457538994800693,
"grad_norm": 0.173828125,
"learning_rate": 0.00014005436218159927,
"loss": 1.2099,
"step": 244
},
{
"epoch": 0.8492201039861352,
"grad_norm": 0.169921875,
"learning_rate": 0.00013950639413238394,
"loss": 1.1779,
"step": 245
},
{
"epoch": 0.8526863084922011,
"grad_norm": 0.13671875,
"learning_rate": 0.00013895701681267784,
"loss": 1.2203,
"step": 246
},
{
"epoch": 0.8561525129982669,
"grad_norm": 0.14453125,
"learning_rate": 0.0001384062498198464,
"loss": 1.1241,
"step": 247
},
{
"epoch": 0.8596187175043327,
"grad_norm": 0.140625,
"learning_rate": 0.00013785411280082746,
"loss": 1.2283,
"step": 248
},
{
"epoch": 0.8630849220103987,
"grad_norm": 0.3984375,
"learning_rate": 0.0001373006254514304,
"loss": 1.2642,
"step": 249
},
{
"epoch": 0.8665511265164645,
"grad_norm": 0.1298828125,
"learning_rate": 0.00013674580751563356,
"loss": 1.1703,
"step": 250
},
{
"epoch": 0.8700173310225303,
"grad_norm": 0.146484375,
"learning_rate": 0.00013618967878487983,
"loss": 1.2154,
"step": 251
},
{
"epoch": 0.8734835355285961,
"grad_norm": 0.275390625,
"learning_rate": 0.00013563225909737076,
"loss": 1.1762,
"step": 252
},
{
"epoch": 0.8769497400346621,
"grad_norm": 0.1904296875,
"learning_rate": 0.00013507356833735888,
"loss": 1.2806,
"step": 253
},
{
"epoch": 0.8804159445407279,
"grad_norm": 0.150390625,
"learning_rate": 0.00013451362643443832,
"loss": 1.2032,
"step": 254
},
{
"epoch": 0.8838821490467937,
"grad_norm": 0.15625,
"learning_rate": 0.00013395245336283396,
"loss": 1.2122,
"step": 255
},
{
"epoch": 0.8873483535528596,
"grad_norm": 0.16015625,
"learning_rate": 0.0001333900691406889,
"loss": 1.1839,
"step": 256
},
{
"epoch": 0.8908145580589255,
"grad_norm": 0.1416015625,
"learning_rate": 0.00013282649382935027,
"loss": 1.184,
"step": 257
},
{
"epoch": 0.8942807625649913,
"grad_norm": 0.130859375,
"learning_rate": 0.0001322617475326538,
"loss": 1.1703,
"step": 258
},
{
"epoch": 0.8977469670710572,
"grad_norm": 0.205078125,
"learning_rate": 0.0001316958503962065,
"loss": 1.2546,
"step": 259
},
{
"epoch": 0.901213171577123,
"grad_norm": 0.2177734375,
"learning_rate": 0.00013112882260666805,
"loss": 1.2206,
"step": 260
},
{
"epoch": 0.9046793760831889,
"grad_norm": 0.125,
"learning_rate": 0.00013056068439103085,
"loss": 1.16,
"step": 261
},
{
"epoch": 0.9081455805892548,
"grad_norm": 0.1591796875,
"learning_rate": 0.00012999145601589823,
"loss": 1.2333,
"step": 262
},
{
"epoch": 0.9116117850953206,
"grad_norm": 0.2109375,
"learning_rate": 0.00012942115778676177,
"loss": 1.1691,
"step": 263
},
{
"epoch": 0.9150779896013865,
"grad_norm": 0.19140625,
"learning_rate": 0.00012884981004727676,
"loss": 1.2484,
"step": 264
},
{
"epoch": 0.9185441941074524,
"grad_norm": 0.126953125,
"learning_rate": 0.00012827743317853665,
"loss": 1.1829,
"step": 265
},
{
"epoch": 0.9220103986135182,
"grad_norm": 0.19921875,
"learning_rate": 0.00012770404759834594,
"loss": 1.1925,
"step": 266
},
{
"epoch": 0.925476603119584,
"grad_norm": 0.1455078125,
"learning_rate": 0.00012712967376049176,
"loss": 1.2528,
"step": 267
},
{
"epoch": 0.92894280762565,
"grad_norm": 0.17578125,
"learning_rate": 0.00012655433215401438,
"loss": 1.2717,
"step": 268
},
{
"epoch": 0.9324090121317158,
"grad_norm": 0.154296875,
"learning_rate": 0.0001259780433024763,
"loss": 1.2076,
"step": 269
},
{
"epoch": 0.9358752166377816,
"grad_norm": 0.46484375,
"learning_rate": 0.00012540082776323007,
"loss": 1.2072,
"step": 270
},
{
"epoch": 0.9393414211438474,
"grad_norm": 0.1357421875,
"learning_rate": 0.00012482270612668508,
"loss": 1.1718,
"step": 271
},
{
"epoch": 0.9428076256499134,
"grad_norm": 0.134765625,
"learning_rate": 0.0001242436990155728,
"loss": 1.1794,
"step": 272
},
{
"epoch": 0.9462738301559792,
"grad_norm": 0.1494140625,
"learning_rate": 0.00012366382708421154,
"loss": 1.2162,
"step": 273
},
{
"epoch": 0.949740034662045,
"grad_norm": 0.1806640625,
"learning_rate": 0.00012308311101776932,
"loss": 1.22,
"step": 274
},
{
"epoch": 0.9532062391681109,
"grad_norm": 0.13671875,
"learning_rate": 0.0001225015715315261,
"loss": 1.1998,
"step": 275
},
{
"epoch": 0.9566724436741768,
"grad_norm": 0.6015625,
"learning_rate": 0.00012191922937013489,
"loss": 1.1541,
"step": 276
},
{
"epoch": 0.9601386481802426,
"grad_norm": 0.1650390625,
"learning_rate": 0.00012133610530688168,
"loss": 1.2099,
"step": 277
},
{
"epoch": 0.9636048526863085,
"grad_norm": 0.1474609375,
"learning_rate": 0.00012075222014294447,
"loss": 1.2157,
"step": 278
},
{
"epoch": 0.9670710571923743,
"grad_norm": 0.1298828125,
"learning_rate": 0.00012016759470665112,
"loss": 1.1958,
"step": 279
},
{
"epoch": 0.9705372616984402,
"grad_norm": 0.1767578125,
"learning_rate": 0.00011958224985273648,
"loss": 1.1857,
"step": 280
},
{
"epoch": 0.9740034662045061,
"grad_norm": 0.1376953125,
"learning_rate": 0.00011899620646159855,
"loss": 1.1818,
"step": 281
},
{
"epoch": 0.9774696707105719,
"grad_norm": 0.130859375,
"learning_rate": 0.00011840948543855335,
"loss": 1.1787,
"step": 282
},
{
"epoch": 0.9809358752166378,
"grad_norm": 0.1279296875,
"learning_rate": 0.00011782210771308948,
"loss": 1.1672,
"step": 283
},
{
"epoch": 0.9844020797227037,
"grad_norm": 0.142578125,
"learning_rate": 0.00011723409423812134,
"loss": 1.1523,
"step": 284
},
{
"epoch": 0.9878682842287695,
"grad_norm": 0.1474609375,
"learning_rate": 0.00011664546598924184,
"loss": 1.1124,
"step": 285
},
{
"epoch": 0.9913344887348353,
"grad_norm": 0.1416015625,
"learning_rate": 0.00011605624396397398,
"loss": 1.2084,
"step": 286
},
{
"epoch": 0.9948006932409013,
"grad_norm": 0.1533203125,
"learning_rate": 0.00011546644918102196,
"loss": 1.1845,
"step": 287
},
{
"epoch": 0.9982668977469671,
"grad_norm": 0.13671875,
"learning_rate": 0.00011487610267952142,
"loss": 1.1879,
"step": 288
}
],
"logging_steps": 1,
"max_steps": 576,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 288,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.8196759500528026e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}