xp185 / checkpoint-220 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
2d83c46 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9984871406959153,
"eval_steps": 500,
"global_step": 220,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0045385779122541605,
"grad_norm": 12.459190368652344,
"learning_rate": 5.0000000000000004e-08,
"loss": 4.6369,
"step": 1
},
{
"epoch": 0.009077155824508321,
"grad_norm": 12.756917953491211,
"learning_rate": 1.0000000000000001e-07,
"loss": 4.6738,
"step": 2
},
{
"epoch": 0.01361573373676248,
"grad_norm": 15.50593090057373,
"learning_rate": 1.5000000000000002e-07,
"loss": 4.6681,
"step": 3
},
{
"epoch": 0.018154311649016642,
"grad_norm": 12.976861000061035,
"learning_rate": 2.0000000000000002e-07,
"loss": 4.246,
"step": 4
},
{
"epoch": 0.0226928895612708,
"grad_norm": 14.594775199890137,
"learning_rate": 2.5000000000000004e-07,
"loss": 4.4452,
"step": 5
},
{
"epoch": 0.02723146747352496,
"grad_norm": 16.087888717651367,
"learning_rate": 3.0000000000000004e-07,
"loss": 4.5528,
"step": 6
},
{
"epoch": 0.03177004538577912,
"grad_norm": 13.62125301361084,
"learning_rate": 3.5000000000000004e-07,
"loss": 4.5628,
"step": 7
},
{
"epoch": 0.036308623298033284,
"grad_norm": 17.010616302490234,
"learning_rate": 4.0000000000000003e-07,
"loss": 4.5768,
"step": 8
},
{
"epoch": 0.04084720121028744,
"grad_norm": 14.567586898803711,
"learning_rate": 4.5000000000000003e-07,
"loss": 4.3937,
"step": 9
},
{
"epoch": 0.0453857791225416,
"grad_norm": 15.238479614257812,
"learning_rate": 5.000000000000001e-07,
"loss": 4.495,
"step": 10
},
{
"epoch": 0.049924357034795766,
"grad_norm": 13.89387321472168,
"learning_rate": 5.5e-07,
"loss": 4.4705,
"step": 11
},
{
"epoch": 0.05446293494704992,
"grad_norm": 13.949710845947266,
"learning_rate": 6.000000000000001e-07,
"loss": 4.328,
"step": 12
},
{
"epoch": 0.059001512859304085,
"grad_norm": 13.15122127532959,
"learning_rate": 6.5e-07,
"loss": 4.4296,
"step": 13
},
{
"epoch": 0.06354009077155824,
"grad_norm": 14.076905250549316,
"learning_rate": 7.000000000000001e-07,
"loss": 4.5285,
"step": 14
},
{
"epoch": 0.0680786686838124,
"grad_norm": 14.299891471862793,
"learning_rate": 7.5e-07,
"loss": 4.5849,
"step": 15
},
{
"epoch": 0.07261724659606657,
"grad_norm": 13.573644638061523,
"learning_rate": 8.000000000000001e-07,
"loss": 4.3638,
"step": 16
},
{
"epoch": 0.07715582450832073,
"grad_norm": 14.140484809875488,
"learning_rate": 8.500000000000001e-07,
"loss": 4.4449,
"step": 17
},
{
"epoch": 0.08169440242057488,
"grad_norm": 11.941351890563965,
"learning_rate": 9.000000000000001e-07,
"loss": 4.3646,
"step": 18
},
{
"epoch": 0.08623298033282904,
"grad_norm": 10.630327224731445,
"learning_rate": 9.500000000000001e-07,
"loss": 4.2902,
"step": 19
},
{
"epoch": 0.0907715582450832,
"grad_norm": 11.662637710571289,
"learning_rate": 1.0000000000000002e-06,
"loss": 4.1961,
"step": 20
},
{
"epoch": 0.09531013615733737,
"grad_norm": 12.008113861083984,
"learning_rate": 1.0500000000000001e-06,
"loss": 4.1941,
"step": 21
},
{
"epoch": 0.09984871406959153,
"grad_norm": 12.686023712158203,
"learning_rate": 1.1e-06,
"loss": 4.1346,
"step": 22
},
{
"epoch": 0.1043872919818457,
"grad_norm": 12.529243469238281,
"learning_rate": 1.1500000000000002e-06,
"loss": 4.1137,
"step": 23
},
{
"epoch": 0.10892586989409984,
"grad_norm": 11.19096565246582,
"learning_rate": 1.2000000000000002e-06,
"loss": 4.0772,
"step": 24
},
{
"epoch": 0.11346444780635401,
"grad_norm": 11.182024955749512,
"learning_rate": 1.25e-06,
"loss": 3.8888,
"step": 25
},
{
"epoch": 0.11800302571860817,
"grad_norm": 9.899381637573242,
"learning_rate": 1.3e-06,
"loss": 4.0117,
"step": 26
},
{
"epoch": 0.12254160363086233,
"grad_norm": 9.448798179626465,
"learning_rate": 1.3500000000000002e-06,
"loss": 3.8384,
"step": 27
},
{
"epoch": 0.12708018154311648,
"grad_norm": 10.632583618164062,
"learning_rate": 1.4000000000000001e-06,
"loss": 3.7857,
"step": 28
},
{
"epoch": 0.13161875945537066,
"grad_norm": 10.56238079071045,
"learning_rate": 1.45e-06,
"loss": 3.4783,
"step": 29
},
{
"epoch": 0.1361573373676248,
"grad_norm": 12.410117149353027,
"learning_rate": 1.5e-06,
"loss": 3.4828,
"step": 30
},
{
"epoch": 0.14069591527987896,
"grad_norm": 10.183599472045898,
"learning_rate": 1.5500000000000002e-06,
"loss": 3.6337,
"step": 31
},
{
"epoch": 0.14523449319213314,
"grad_norm": 9.421585083007812,
"learning_rate": 1.6000000000000001e-06,
"loss": 3.4453,
"step": 32
},
{
"epoch": 0.14977307110438728,
"grad_norm": 9.230025291442871,
"learning_rate": 1.6500000000000003e-06,
"loss": 3.3481,
"step": 33
},
{
"epoch": 0.15431164901664146,
"grad_norm": 8.295567512512207,
"learning_rate": 1.7000000000000002e-06,
"loss": 3.3145,
"step": 34
},
{
"epoch": 0.1588502269288956,
"grad_norm": 9.138203620910645,
"learning_rate": 1.75e-06,
"loss": 3.1872,
"step": 35
},
{
"epoch": 0.16338880484114976,
"grad_norm": 11.864872932434082,
"learning_rate": 1.8000000000000001e-06,
"loss": 2.9837,
"step": 36
},
{
"epoch": 0.16792738275340394,
"grad_norm": 12.373150825500488,
"learning_rate": 1.85e-06,
"loss": 3.0049,
"step": 37
},
{
"epoch": 0.17246596066565809,
"grad_norm": 21.665483474731445,
"learning_rate": 1.9000000000000002e-06,
"loss": 2.7664,
"step": 38
},
{
"epoch": 0.17700453857791226,
"grad_norm": 22.663740158081055,
"learning_rate": 1.9500000000000004e-06,
"loss": 2.7272,
"step": 39
},
{
"epoch": 0.1815431164901664,
"grad_norm": 26.674400329589844,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.8077,
"step": 40
},
{
"epoch": 0.18608169440242056,
"grad_norm": 28.503612518310547,
"learning_rate": 2.05e-06,
"loss": 2.7306,
"step": 41
},
{
"epoch": 0.19062027231467474,
"grad_norm": 29.03409767150879,
"learning_rate": 2.1000000000000002e-06,
"loss": 2.7405,
"step": 42
},
{
"epoch": 0.1951588502269289,
"grad_norm": 17.844894409179688,
"learning_rate": 2.15e-06,
"loss": 2.6464,
"step": 43
},
{
"epoch": 0.19969742813918306,
"grad_norm": 19.220829010009766,
"learning_rate": 2.2e-06,
"loss": 2.4554,
"step": 44
},
{
"epoch": 0.2042360060514372,
"grad_norm": 25.161415100097656,
"learning_rate": 2.25e-06,
"loss": 2.2773,
"step": 45
},
{
"epoch": 0.2087745839636914,
"grad_norm": 17.46828269958496,
"learning_rate": 2.3000000000000004e-06,
"loss": 2.3392,
"step": 46
},
{
"epoch": 0.21331316187594554,
"grad_norm": 13.194672584533691,
"learning_rate": 2.35e-06,
"loss": 2.0409,
"step": 47
},
{
"epoch": 0.2178517397881997,
"grad_norm": 7.290500164031982,
"learning_rate": 2.4000000000000003e-06,
"loss": 2.1879,
"step": 48
},
{
"epoch": 0.22239031770045387,
"grad_norm": 7.56943941116333,
"learning_rate": 2.4500000000000003e-06,
"loss": 2.1656,
"step": 49
},
{
"epoch": 0.22692889561270801,
"grad_norm": 8.335527420043945,
"learning_rate": 2.5e-06,
"loss": 2.1294,
"step": 50
},
{
"epoch": 0.2314674735249622,
"grad_norm": 10.013853073120117,
"learning_rate": 2.55e-06,
"loss": 2.1816,
"step": 51
},
{
"epoch": 0.23600605143721634,
"grad_norm": 8.674482345581055,
"learning_rate": 2.6e-06,
"loss": 2.0078,
"step": 52
},
{
"epoch": 0.2405446293494705,
"grad_norm": 6.09174919128418,
"learning_rate": 2.6500000000000005e-06,
"loss": 2.1328,
"step": 53
},
{
"epoch": 0.24508320726172467,
"grad_norm": 7.3330488204956055,
"learning_rate": 2.7000000000000004e-06,
"loss": 1.8961,
"step": 54
},
{
"epoch": 0.24962178517397882,
"grad_norm": 8.764911651611328,
"learning_rate": 2.7500000000000004e-06,
"loss": 1.7026,
"step": 55
},
{
"epoch": 0.25416036308623297,
"grad_norm": 12.413115501403809,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.8172,
"step": 56
},
{
"epoch": 0.2586989409984871,
"grad_norm": 9.009276390075684,
"learning_rate": 2.85e-06,
"loss": 1.6527,
"step": 57
},
{
"epoch": 0.2632375189107413,
"grad_norm": 9.965579986572266,
"learning_rate": 2.9e-06,
"loss": 1.6348,
"step": 58
},
{
"epoch": 0.26777609682299547,
"grad_norm": 7.091963768005371,
"learning_rate": 2.95e-06,
"loss": 1.7016,
"step": 59
},
{
"epoch": 0.2723146747352496,
"grad_norm": 5.276648998260498,
"learning_rate": 3e-06,
"loss": 1.7088,
"step": 60
},
{
"epoch": 0.27685325264750377,
"grad_norm": 9.634596824645996,
"learning_rate": 3.05e-06,
"loss": 1.4961,
"step": 61
},
{
"epoch": 0.2813918305597579,
"grad_norm": 6.663750648498535,
"learning_rate": 3.1000000000000004e-06,
"loss": 1.522,
"step": 62
},
{
"epoch": 0.2859304084720121,
"grad_norm": 36.79426956176758,
"learning_rate": 3.1500000000000003e-06,
"loss": 1.4855,
"step": 63
},
{
"epoch": 0.29046898638426627,
"grad_norm": 31.88567352294922,
"learning_rate": 3.2000000000000003e-06,
"loss": 1.5058,
"step": 64
},
{
"epoch": 0.2950075642965204,
"grad_norm": 12.319960594177246,
"learning_rate": 3.2500000000000002e-06,
"loss": 1.4547,
"step": 65
},
{
"epoch": 0.29954614220877457,
"grad_norm": 4.246046543121338,
"learning_rate": 3.3000000000000006e-06,
"loss": 1.3153,
"step": 66
},
{
"epoch": 0.3040847201210287,
"grad_norm": 5.3949503898620605,
"learning_rate": 3.3500000000000005e-06,
"loss": 1.4237,
"step": 67
},
{
"epoch": 0.3086232980332829,
"grad_norm": 9.975737571716309,
"learning_rate": 3.4000000000000005e-06,
"loss": 1.327,
"step": 68
},
{
"epoch": 0.31316187594553707,
"grad_norm": 6.356144428253174,
"learning_rate": 3.45e-06,
"loss": 1.2685,
"step": 69
},
{
"epoch": 0.3177004538577912,
"grad_norm": 3.9029836654663086,
"learning_rate": 3.5e-06,
"loss": 1.3856,
"step": 70
},
{
"epoch": 0.32223903177004537,
"grad_norm": 4.215930938720703,
"learning_rate": 3.5500000000000003e-06,
"loss": 1.1844,
"step": 71
},
{
"epoch": 0.3267776096822995,
"grad_norm": 27.889633178710938,
"learning_rate": 3.6000000000000003e-06,
"loss": 1.2535,
"step": 72
},
{
"epoch": 0.3313161875945537,
"grad_norm": 23.77273178100586,
"learning_rate": 3.65e-06,
"loss": 1.3189,
"step": 73
},
{
"epoch": 0.3358547655068079,
"grad_norm": 9.203927040100098,
"learning_rate": 3.7e-06,
"loss": 1.1993,
"step": 74
},
{
"epoch": 0.340393343419062,
"grad_norm": 3.1091806888580322,
"learning_rate": 3.7500000000000005e-06,
"loss": 1.1804,
"step": 75
},
{
"epoch": 0.34493192133131617,
"grad_norm": 9.0440034866333,
"learning_rate": 3.8000000000000005e-06,
"loss": 1.2318,
"step": 76
},
{
"epoch": 0.3494704992435703,
"grad_norm": 7.17051362991333,
"learning_rate": 3.85e-06,
"loss": 1.2018,
"step": 77
},
{
"epoch": 0.3540090771558245,
"grad_norm": 8.164457321166992,
"learning_rate": 3.900000000000001e-06,
"loss": 1.0911,
"step": 78
},
{
"epoch": 0.3585476550680787,
"grad_norm": 3.3671042919158936,
"learning_rate": 3.95e-06,
"loss": 1.1747,
"step": 79
},
{
"epoch": 0.3630862329803328,
"grad_norm": 4.223191261291504,
"learning_rate": 4.000000000000001e-06,
"loss": 1.1141,
"step": 80
},
{
"epoch": 0.367624810892587,
"grad_norm": 10.657241821289062,
"learning_rate": 4.05e-06,
"loss": 1.0506,
"step": 81
},
{
"epoch": 0.3721633888048411,
"grad_norm": 2.664783239364624,
"learning_rate": 4.1e-06,
"loss": 1.1271,
"step": 82
},
{
"epoch": 0.3767019667170953,
"grad_norm": 5.334985733032227,
"learning_rate": 4.15e-06,
"loss": 1.0812,
"step": 83
},
{
"epoch": 0.3812405446293495,
"grad_norm": 7.471070289611816,
"learning_rate": 4.2000000000000004e-06,
"loss": 1.1027,
"step": 84
},
{
"epoch": 0.3857791225416036,
"grad_norm": 3.270421028137207,
"learning_rate": 4.25e-06,
"loss": 1.054,
"step": 85
},
{
"epoch": 0.3903177004538578,
"grad_norm": 1.9382085800170898,
"learning_rate": 4.3e-06,
"loss": 0.975,
"step": 86
},
{
"epoch": 0.394856278366112,
"grad_norm": 24.2485408782959,
"learning_rate": 4.350000000000001e-06,
"loss": 1.0288,
"step": 87
},
{
"epoch": 0.39939485627836613,
"grad_norm": 42.359432220458984,
"learning_rate": 4.4e-06,
"loss": 1.111,
"step": 88
},
{
"epoch": 0.4039334341906203,
"grad_norm": 25.72220230102539,
"learning_rate": 4.450000000000001e-06,
"loss": 1.0472,
"step": 89
},
{
"epoch": 0.4084720121028744,
"grad_norm": 3.1196579933166504,
"learning_rate": 4.5e-06,
"loss": 1.0055,
"step": 90
},
{
"epoch": 0.4130105900151286,
"grad_norm": 4.584676742553711,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.9848,
"step": 91
},
{
"epoch": 0.4175491679273828,
"grad_norm": 6.140016078948975,
"learning_rate": 4.600000000000001e-06,
"loss": 0.948,
"step": 92
},
{
"epoch": 0.42208774583963693,
"grad_norm": 5.266363620758057,
"learning_rate": 4.65e-06,
"loss": 0.9261,
"step": 93
},
{
"epoch": 0.4266263237518911,
"grad_norm": 3.6768720149993896,
"learning_rate": 4.7e-06,
"loss": 0.9772,
"step": 94
},
{
"epoch": 0.43116490166414523,
"grad_norm": 8.903961181640625,
"learning_rate": 4.75e-06,
"loss": 0.9514,
"step": 95
},
{
"epoch": 0.4357034795763994,
"grad_norm": 15.684305191040039,
"learning_rate": 4.800000000000001e-06,
"loss": 0.9629,
"step": 96
},
{
"epoch": 0.4402420574886536,
"grad_norm": 21.329519271850586,
"learning_rate": 4.85e-06,
"loss": 1.0118,
"step": 97
},
{
"epoch": 0.44478063540090773,
"grad_norm": 7.824005603790283,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.9094,
"step": 98
},
{
"epoch": 0.4493192133131619,
"grad_norm": 2.283174514770508,
"learning_rate": 4.95e-06,
"loss": 0.8877,
"step": 99
},
{
"epoch": 0.45385779122541603,
"grad_norm": 5.028634548187256,
"learning_rate": 5e-06,
"loss": 0.8946,
"step": 100
},
{
"epoch": 0.4583963691376702,
"grad_norm": 6.072951793670654,
"learning_rate": 4.9999917112344245e-06,
"loss": 0.9248,
"step": 101
},
{
"epoch": 0.4629349470499244,
"grad_norm": 7.111969470977783,
"learning_rate": 4.999966844992657e-06,
"loss": 0.9172,
"step": 102
},
{
"epoch": 0.46747352496217853,
"grad_norm": 3.792372465133667,
"learning_rate": 4.999925401439588e-06,
"loss": 0.8718,
"step": 103
},
{
"epoch": 0.4720121028744327,
"grad_norm": 4.017702579498291,
"learning_rate": 4.999867380850031e-06,
"loss": 0.9121,
"step": 104
},
{
"epoch": 0.47655068078668683,
"grad_norm": 6.903019905090332,
"learning_rate": 4.99979278360872e-06,
"loss": 0.9359,
"step": 105
},
{
"epoch": 0.481089258698941,
"grad_norm": 3.740607500076294,
"learning_rate": 4.999701610210309e-06,
"loss": 0.8474,
"step": 106
},
{
"epoch": 0.4856278366111952,
"grad_norm": 3.379190683364868,
"learning_rate": 4.999593861259373e-06,
"loss": 0.8641,
"step": 107
},
{
"epoch": 0.49016641452344933,
"grad_norm": 3.0796492099761963,
"learning_rate": 4.999469537470394e-06,
"loss": 0.8255,
"step": 108
},
{
"epoch": 0.4947049924357035,
"grad_norm": 3.3708953857421875,
"learning_rate": 4.999328639667765e-06,
"loss": 0.8823,
"step": 109
},
{
"epoch": 0.49924357034795763,
"grad_norm": 3.2106549739837646,
"learning_rate": 4.999171168785783e-06,
"loss": 0.8584,
"step": 110
},
{
"epoch": 0.5037821482602118,
"grad_norm": 6.520877838134766,
"learning_rate": 4.998997125868638e-06,
"loss": 0.8718,
"step": 111
},
{
"epoch": 0.5083207261724659,
"grad_norm": 1.0179104804992676,
"learning_rate": 4.99880651207041e-06,
"loss": 0.871,
"step": 112
},
{
"epoch": 0.5128593040847201,
"grad_norm": 1.1883283853530884,
"learning_rate": 4.998599328655063e-06,
"loss": 0.8689,
"step": 113
},
{
"epoch": 0.5173978819969742,
"grad_norm": 1.2722241878509521,
"learning_rate": 4.998375576996431e-06,
"loss": 0.8594,
"step": 114
},
{
"epoch": 0.5219364599092284,
"grad_norm": 1.8931000232696533,
"learning_rate": 4.9981352585782154e-06,
"loss": 0.8327,
"step": 115
},
{
"epoch": 0.5264750378214826,
"grad_norm": 3.093480348587036,
"learning_rate": 4.997878374993971e-06,
"loss": 0.8372,
"step": 116
},
{
"epoch": 0.5310136157337367,
"grad_norm": 5.2650957107543945,
"learning_rate": 4.9976049279470955e-06,
"loss": 0.8386,
"step": 117
},
{
"epoch": 0.5355521936459909,
"grad_norm": 4.467101573944092,
"learning_rate": 4.997314919250818e-06,
"loss": 0.7788,
"step": 118
},
{
"epoch": 0.540090771558245,
"grad_norm": 3.614868640899658,
"learning_rate": 4.997008350828192e-06,
"loss": 0.874,
"step": 119
},
{
"epoch": 0.5446293494704992,
"grad_norm": 12.209319114685059,
"learning_rate": 4.996685224712077e-06,
"loss": 0.8223,
"step": 120
},
{
"epoch": 0.5491679273827534,
"grad_norm": 4.1903252601623535,
"learning_rate": 4.9963455430451245e-06,
"loss": 0.8455,
"step": 121
},
{
"epoch": 0.5537065052950075,
"grad_norm": 2.649549722671509,
"learning_rate": 4.9959893080797675e-06,
"loss": 0.7875,
"step": 122
},
{
"epoch": 0.5582450832072617,
"grad_norm": 4.935393810272217,
"learning_rate": 4.995616522178207e-06,
"loss": 0.8691,
"step": 123
},
{
"epoch": 0.5627836611195158,
"grad_norm": 5.565356731414795,
"learning_rate": 4.995227187812389e-06,
"loss": 0.8267,
"step": 124
},
{
"epoch": 0.56732223903177,
"grad_norm": 5.23801851272583,
"learning_rate": 4.994821307563995e-06,
"loss": 0.826,
"step": 125
},
{
"epoch": 0.5718608169440242,
"grad_norm": 4.2979736328125,
"learning_rate": 4.994398884124422e-06,
"loss": 0.8068,
"step": 126
},
{
"epoch": 0.5763993948562783,
"grad_norm": 6.285053730010986,
"learning_rate": 4.993959920294764e-06,
"loss": 0.819,
"step": 127
},
{
"epoch": 0.5809379727685325,
"grad_norm": 10.453060150146484,
"learning_rate": 4.9935044189857975e-06,
"loss": 0.773,
"step": 128
},
{
"epoch": 0.5854765506807866,
"grad_norm": 31.77552604675293,
"learning_rate": 4.993032383217957e-06,
"loss": 0.8738,
"step": 129
},
{
"epoch": 0.5900151285930408,
"grad_norm": 1.1456351280212402,
"learning_rate": 4.992543816121317e-06,
"loss": 0.7518,
"step": 130
},
{
"epoch": 0.594553706505295,
"grad_norm": 1.3343666791915894,
"learning_rate": 4.992038720935572e-06,
"loss": 0.8108,
"step": 131
},
{
"epoch": 0.5990922844175491,
"grad_norm": 0.8912076354026794,
"learning_rate": 4.991517101010015e-06,
"loss": 0.8159,
"step": 132
},
{
"epoch": 0.6036308623298033,
"grad_norm": 2.249366044998169,
"learning_rate": 4.990978959803513e-06,
"loss": 0.8124,
"step": 133
},
{
"epoch": 0.6081694402420574,
"grad_norm": 1.2822734117507935,
"learning_rate": 4.990424300884488e-06,
"loss": 0.8213,
"step": 134
},
{
"epoch": 0.6127080181543116,
"grad_norm": 6.053490161895752,
"learning_rate": 4.98985312793089e-06,
"loss": 0.7829,
"step": 135
},
{
"epoch": 0.6172465960665658,
"grad_norm": 2.2606236934661865,
"learning_rate": 4.989265444730176e-06,
"loss": 0.7729,
"step": 136
},
{
"epoch": 0.6217851739788199,
"grad_norm": 3.8894989490509033,
"learning_rate": 4.988661255179276e-06,
"loss": 0.774,
"step": 137
},
{
"epoch": 0.6263237518910741,
"grad_norm": 5.648194313049316,
"learning_rate": 4.988040563284582e-06,
"loss": 0.7251,
"step": 138
},
{
"epoch": 0.6308623298033282,
"grad_norm": 1.7583339214324951,
"learning_rate": 4.98740337316191e-06,
"loss": 0.7875,
"step": 139
},
{
"epoch": 0.6354009077155824,
"grad_norm": 1.3959944248199463,
"learning_rate": 4.9867496890364734e-06,
"loss": 0.7726,
"step": 140
},
{
"epoch": 0.6399394856278366,
"grad_norm": 1.7879443168640137,
"learning_rate": 4.986079515242861e-06,
"loss": 0.786,
"step": 141
},
{
"epoch": 0.6444780635400907,
"grad_norm": 2.0919816493988037,
"learning_rate": 4.985392856225003e-06,
"loss": 0.7802,
"step": 142
},
{
"epoch": 0.649016641452345,
"grad_norm": 1.272477626800537,
"learning_rate": 4.984689716536145e-06,
"loss": 0.7842,
"step": 143
},
{
"epoch": 0.653555219364599,
"grad_norm": 1.1265331506729126,
"learning_rate": 4.983970100838814e-06,
"loss": 0.736,
"step": 144
},
{
"epoch": 0.6580937972768532,
"grad_norm": 0.8514362573623657,
"learning_rate": 4.983234013904791e-06,
"loss": 0.749,
"step": 145
},
{
"epoch": 0.6626323751891074,
"grad_norm": 3.148453950881958,
"learning_rate": 4.9824814606150774e-06,
"loss": 0.7884,
"step": 146
},
{
"epoch": 0.6671709531013615,
"grad_norm": 1.531554937362671,
"learning_rate": 4.981712445959864e-06,
"loss": 0.767,
"step": 147
},
{
"epoch": 0.6717095310136157,
"grad_norm": 1.7979401350021362,
"learning_rate": 4.980926975038496e-06,
"loss": 0.7575,
"step": 148
},
{
"epoch": 0.6762481089258698,
"grad_norm": 1.1131621599197388,
"learning_rate": 4.9801250530594415e-06,
"loss": 0.76,
"step": 149
},
{
"epoch": 0.680786686838124,
"grad_norm": 1.2112400531768799,
"learning_rate": 4.9793066853402535e-06,
"loss": 0.769,
"step": 150
},
{
"epoch": 0.6853252647503782,
"grad_norm": 1.276172161102295,
"learning_rate": 4.978471877307541e-06,
"loss": 0.7641,
"step": 151
},
{
"epoch": 0.6898638426626323,
"grad_norm": 7.614717960357666,
"learning_rate": 4.977620634496926e-06,
"loss": 0.7614,
"step": 152
},
{
"epoch": 0.6944024205748865,
"grad_norm": 0.9541272521018982,
"learning_rate": 4.976752962553008e-06,
"loss": 0.7406,
"step": 153
},
{
"epoch": 0.6989409984871406,
"grad_norm": 0.9793027639389038,
"learning_rate": 4.975868867229332e-06,
"loss": 0.7538,
"step": 154
},
{
"epoch": 0.7034795763993948,
"grad_norm": 8.540267944335938,
"learning_rate": 4.974968354388346e-06,
"loss": 0.7616,
"step": 155
},
{
"epoch": 0.708018154311649,
"grad_norm": 2.279240608215332,
"learning_rate": 4.97405143000136e-06,
"loss": 0.7157,
"step": 156
},
{
"epoch": 0.7125567322239031,
"grad_norm": 2.947227716445923,
"learning_rate": 4.973118100148513e-06,
"loss": 0.7348,
"step": 157
},
{
"epoch": 0.7170953101361573,
"grad_norm": 2.211785316467285,
"learning_rate": 4.9721683710187255e-06,
"loss": 0.7144,
"step": 158
},
{
"epoch": 0.7216338880484114,
"grad_norm": 1.3755372762680054,
"learning_rate": 4.971202248909662e-06,
"loss": 0.6857,
"step": 159
},
{
"epoch": 0.7261724659606656,
"grad_norm": 2.564708709716797,
"learning_rate": 4.970219740227693e-06,
"loss": 0.7124,
"step": 160
},
{
"epoch": 0.7307110438729199,
"grad_norm": 11.76566219329834,
"learning_rate": 4.9692208514878445e-06,
"loss": 0.7815,
"step": 161
},
{
"epoch": 0.735249621785174,
"grad_norm": 3.7665200233459473,
"learning_rate": 4.9682055893137605e-06,
"loss": 0.7021,
"step": 162
},
{
"epoch": 0.7397881996974282,
"grad_norm": 2.9076344966888428,
"learning_rate": 4.967173960437657e-06,
"loss": 0.7083,
"step": 163
},
{
"epoch": 0.7443267776096822,
"grad_norm": 2.336026191711426,
"learning_rate": 4.966125971700277e-06,
"loss": 0.7455,
"step": 164
},
{
"epoch": 0.7488653555219364,
"grad_norm": 6.48813009262085,
"learning_rate": 4.965061630050848e-06,
"loss": 0.7628,
"step": 165
},
{
"epoch": 0.7534039334341907,
"grad_norm": 1.9123872518539429,
"learning_rate": 4.9639809425470324e-06,
"loss": 0.7212,
"step": 166
},
{
"epoch": 0.7579425113464447,
"grad_norm": 6.638424873352051,
"learning_rate": 4.962883916354882e-06,
"loss": 0.7523,
"step": 167
},
{
"epoch": 0.762481089258699,
"grad_norm": 1.3606716394424438,
"learning_rate": 4.961770558748793e-06,
"loss": 0.7651,
"step": 168
},
{
"epoch": 0.7670196671709532,
"grad_norm": 1.2726523876190186,
"learning_rate": 4.960640877111451e-06,
"loss": 0.7729,
"step": 169
},
{
"epoch": 0.7715582450832073,
"grad_norm": 0.9216910600662231,
"learning_rate": 4.959494878933792e-06,
"loss": 0.7162,
"step": 170
},
{
"epoch": 0.7760968229954615,
"grad_norm": 2.3702430725097656,
"learning_rate": 4.958332571814941e-06,
"loss": 0.7038,
"step": 171
},
{
"epoch": 0.7806354009077155,
"grad_norm": 4.6101555824279785,
"learning_rate": 4.957153963462172e-06,
"loss": 0.7141,
"step": 172
},
{
"epoch": 0.7851739788199698,
"grad_norm": 1.7314170598983765,
"learning_rate": 4.955959061690853e-06,
"loss": 0.7374,
"step": 173
},
{
"epoch": 0.789712556732224,
"grad_norm": 2.91019868850708,
"learning_rate": 4.9547478744243914e-06,
"loss": 0.7048,
"step": 174
},
{
"epoch": 0.794251134644478,
"grad_norm": 2.872775077819824,
"learning_rate": 4.953520409694186e-06,
"loss": 0.6912,
"step": 175
},
{
"epoch": 0.7987897125567323,
"grad_norm": 2.2696948051452637,
"learning_rate": 4.952276675639569e-06,
"loss": 0.7432,
"step": 176
},
{
"epoch": 0.8033282904689864,
"grad_norm": 1.8855810165405273,
"learning_rate": 4.951016680507757e-06,
"loss": 0.7056,
"step": 177
},
{
"epoch": 0.8078668683812406,
"grad_norm": 5.202772617340088,
"learning_rate": 4.9497404326537954e-06,
"loss": 0.7114,
"step": 178
},
{
"epoch": 0.8124054462934948,
"grad_norm": 0.7916449904441833,
"learning_rate": 4.948447940540497e-06,
"loss": 0.7202,
"step": 179
},
{
"epoch": 0.8169440242057489,
"grad_norm": 1.5009609460830688,
"learning_rate": 4.947139212738395e-06,
"loss": 0.7245,
"step": 180
},
{
"epoch": 0.8214826021180031,
"grad_norm": 1.858067512512207,
"learning_rate": 4.945814257925679e-06,
"loss": 0.6962,
"step": 181
},
{
"epoch": 0.8260211800302572,
"grad_norm": 0.7835391163825989,
"learning_rate": 4.94447308488814e-06,
"loss": 0.6875,
"step": 182
},
{
"epoch": 0.8305597579425114,
"grad_norm": 21.755929946899414,
"learning_rate": 4.943115702519115e-06,
"loss": 0.7304,
"step": 183
},
{
"epoch": 0.8350983358547656,
"grad_norm": 6.944667816162109,
"learning_rate": 4.941742119819421e-06,
"loss": 0.7381,
"step": 184
},
{
"epoch": 0.8396369137670197,
"grad_norm": 0.9813210368156433,
"learning_rate": 4.940352345897304e-06,
"loss": 0.682,
"step": 185
},
{
"epoch": 0.8441754916792739,
"grad_norm": 1.8010449409484863,
"learning_rate": 4.938946389968372e-06,
"loss": 0.7639,
"step": 186
},
{
"epoch": 0.848714069591528,
"grad_norm": 2.293980121612549,
"learning_rate": 4.937524261355535e-06,
"loss": 0.7027,
"step": 187
},
{
"epoch": 0.8532526475037822,
"grad_norm": 1.9937771558761597,
"learning_rate": 4.9360859694889475e-06,
"loss": 0.688,
"step": 188
},
{
"epoch": 0.8577912254160364,
"grad_norm": 1.8442484140396118,
"learning_rate": 4.934631523905938e-06,
"loss": 0.6261,
"step": 189
},
{
"epoch": 0.8623298033282905,
"grad_norm": 9.626107215881348,
"learning_rate": 4.933160934250957e-06,
"loss": 0.7605,
"step": 190
},
{
"epoch": 0.8668683812405447,
"grad_norm": 14.051777839660645,
"learning_rate": 4.931674210275499e-06,
"loss": 0.7183,
"step": 191
},
{
"epoch": 0.8714069591527988,
"grad_norm": 2.1191225051879883,
"learning_rate": 4.930171361838052e-06,
"loss": 0.697,
"step": 192
},
{
"epoch": 0.875945537065053,
"grad_norm": 1.4051584005355835,
"learning_rate": 4.928652398904022e-06,
"loss": 0.6985,
"step": 193
},
{
"epoch": 0.8804841149773072,
"grad_norm": 0.7633137106895447,
"learning_rate": 4.92711733154567e-06,
"loss": 0.7018,
"step": 194
},
{
"epoch": 0.8850226928895613,
"grad_norm": 1.5257729291915894,
"learning_rate": 4.925566169942048e-06,
"loss": 0.7108,
"step": 195
},
{
"epoch": 0.8895612708018155,
"grad_norm": 1.7885994911193848,
"learning_rate": 4.9239989243789275e-06,
"loss": 0.7251,
"step": 196
},
{
"epoch": 0.8940998487140696,
"grad_norm": 1.8133364915847778,
"learning_rate": 4.922415605248734e-06,
"loss": 0.691,
"step": 197
},
{
"epoch": 0.8986384266263238,
"grad_norm": 1.3306565284729004,
"learning_rate": 4.920816223050475e-06,
"loss": 0.6496,
"step": 198
},
{
"epoch": 0.903177004538578,
"grad_norm": 2.5053746700286865,
"learning_rate": 4.919200788389675e-06,
"loss": 0.7174,
"step": 199
},
{
"epoch": 0.9077155824508321,
"grad_norm": 2.8250479698181152,
"learning_rate": 4.917569311978301e-06,
"loss": 0.6992,
"step": 200
},
{
"epoch": 0.9122541603630863,
"grad_norm": 0.6993988752365112,
"learning_rate": 4.915921804634693e-06,
"loss": 0.6983,
"step": 201
},
{
"epoch": 0.9167927382753404,
"grad_norm": 2.591536045074463,
"learning_rate": 4.914258277283494e-06,
"loss": 0.6686,
"step": 202
},
{
"epoch": 0.9213313161875946,
"grad_norm": 1.7433080673217773,
"learning_rate": 4.912578740955573e-06,
"loss": 0.686,
"step": 203
},
{
"epoch": 0.9258698940998488,
"grad_norm": 1.5048431158065796,
"learning_rate": 4.910883206787958e-06,
"loss": 0.7043,
"step": 204
},
{
"epoch": 0.9304084720121029,
"grad_norm": 0.7160290479660034,
"learning_rate": 4.9091716860237545e-06,
"loss": 0.6703,
"step": 205
},
{
"epoch": 0.9349470499243571,
"grad_norm": 16.788084030151367,
"learning_rate": 4.907444190012081e-06,
"loss": 0.7465,
"step": 206
},
{
"epoch": 0.9394856278366112,
"grad_norm": 6.705326557159424,
"learning_rate": 4.905700730207983e-06,
"loss": 0.6692,
"step": 207
},
{
"epoch": 0.9440242057488654,
"grad_norm": 1.1539785861968994,
"learning_rate": 4.903941318172365e-06,
"loss": 0.6769,
"step": 208
},
{
"epoch": 0.9485627836611196,
"grad_norm": 0.806441068649292,
"learning_rate": 4.902165965571911e-06,
"loss": 0.6788,
"step": 209
},
{
"epoch": 0.9531013615733737,
"grad_norm": 2.599201202392578,
"learning_rate": 4.900374684179005e-06,
"loss": 0.6845,
"step": 210
},
{
"epoch": 0.9576399394856279,
"grad_norm": 1.9495007991790771,
"learning_rate": 4.898567485871656e-06,
"loss": 0.68,
"step": 211
},
{
"epoch": 0.962178517397882,
"grad_norm": 1.3471159934997559,
"learning_rate": 4.896744382633419e-06,
"loss": 0.6799,
"step": 212
},
{
"epoch": 0.9667170953101362,
"grad_norm": 2.436737537384033,
"learning_rate": 4.894905386553316e-06,
"loss": 0.6688,
"step": 213
},
{
"epoch": 0.9712556732223904,
"grad_norm": 2.486992597579956,
"learning_rate": 4.893050509825749e-06,
"loss": 0.6866,
"step": 214
},
{
"epoch": 0.9757942511346445,
"grad_norm": 2.137023687362671,
"learning_rate": 4.891179764750434e-06,
"loss": 0.6891,
"step": 215
},
{
"epoch": 0.9803328290468987,
"grad_norm": 1.3739172220230103,
"learning_rate": 4.8892931637323e-06,
"loss": 0.6219,
"step": 216
},
{
"epoch": 0.9848714069591528,
"grad_norm": 1.6083399057388306,
"learning_rate": 4.887390719281423e-06,
"loss": 0.6805,
"step": 217
},
{
"epoch": 0.989409984871407,
"grad_norm": 0.7767590284347534,
"learning_rate": 4.885472444012937e-06,
"loss": 0.6857,
"step": 218
},
{
"epoch": 0.9939485627836612,
"grad_norm": 0.8085631728172302,
"learning_rate": 4.883538350646949e-06,
"loss": 0.6594,
"step": 219
},
{
"epoch": 0.9984871406959153,
"grad_norm": 0.7762560844421387,
"learning_rate": 4.881588452008457e-06,
"loss": 0.6972,
"step": 220
}
],
"logging_steps": 1,
"max_steps": 1320,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 220,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.677173827304161e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}