prxy5606's picture
Training in progress, step 200, checkpoint
6dc2dff verified
{
"best_metric": 0.7592693567276001,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.20222446916076844,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0010111223458038423,
"grad_norm": 0.22056037187576294,
"learning_rate": 1e-05,
"loss": 0.8618,
"step": 1
},
{
"epoch": 0.0010111223458038423,
"eval_loss": 1.1871098279953003,
"eval_runtime": 50.5169,
"eval_samples_per_second": 32.979,
"eval_steps_per_second": 8.255,
"step": 1
},
{
"epoch": 0.0020222446916076846,
"grad_norm": 0.26395174860954285,
"learning_rate": 2e-05,
"loss": 0.9255,
"step": 2
},
{
"epoch": 0.003033367037411527,
"grad_norm": 0.2852858901023865,
"learning_rate": 3e-05,
"loss": 0.9638,
"step": 3
},
{
"epoch": 0.004044489383215369,
"grad_norm": 0.38504543900489807,
"learning_rate": 4e-05,
"loss": 1.0563,
"step": 4
},
{
"epoch": 0.005055611729019211,
"grad_norm": 0.3234420716762543,
"learning_rate": 5e-05,
"loss": 1.0937,
"step": 5
},
{
"epoch": 0.006066734074823054,
"grad_norm": 0.36337852478027344,
"learning_rate": 6e-05,
"loss": 1.1176,
"step": 6
},
{
"epoch": 0.007077856420626896,
"grad_norm": 0.33592489361763,
"learning_rate": 7e-05,
"loss": 1.1071,
"step": 7
},
{
"epoch": 0.008088978766430738,
"grad_norm": 0.351818710565567,
"learning_rate": 8e-05,
"loss": 1.17,
"step": 8
},
{
"epoch": 0.00910010111223458,
"grad_norm": 0.35823991894721985,
"learning_rate": 9e-05,
"loss": 1.1122,
"step": 9
},
{
"epoch": 0.010111223458038422,
"grad_norm": 0.3145882189273834,
"learning_rate": 0.0001,
"loss": 1.0619,
"step": 10
},
{
"epoch": 0.011122345803842264,
"grad_norm": 0.28102269768714905,
"learning_rate": 9.999316524962345e-05,
"loss": 1.0001,
"step": 11
},
{
"epoch": 0.012133468149646108,
"grad_norm": 0.2787579596042633,
"learning_rate": 9.997266286704631e-05,
"loss": 0.998,
"step": 12
},
{
"epoch": 0.01314459049544995,
"grad_norm": 0.28835824131965637,
"learning_rate": 9.993849845741524e-05,
"loss": 1.0519,
"step": 13
},
{
"epoch": 0.014155712841253791,
"grad_norm": 0.3020806312561035,
"learning_rate": 9.989068136093873e-05,
"loss": 1.0241,
"step": 14
},
{
"epoch": 0.015166835187057633,
"grad_norm": 0.3163841962814331,
"learning_rate": 9.98292246503335e-05,
"loss": 1.0472,
"step": 15
},
{
"epoch": 0.016177957532861477,
"grad_norm": 0.27695924043655396,
"learning_rate": 9.975414512725057e-05,
"loss": 0.9929,
"step": 16
},
{
"epoch": 0.017189079878665317,
"grad_norm": 0.26604747772216797,
"learning_rate": 9.966546331768191e-05,
"loss": 0.9837,
"step": 17
},
{
"epoch": 0.01820020222446916,
"grad_norm": 0.2730451226234436,
"learning_rate": 9.956320346634876e-05,
"loss": 0.9492,
"step": 18
},
{
"epoch": 0.019211324570273004,
"grad_norm": 0.26102086901664734,
"learning_rate": 9.944739353007344e-05,
"loss": 0.9103,
"step": 19
},
{
"epoch": 0.020222446916076844,
"grad_norm": 0.2756553292274475,
"learning_rate": 9.931806517013612e-05,
"loss": 0.9833,
"step": 20
},
{
"epoch": 0.021233569261880688,
"grad_norm": 0.2869265377521515,
"learning_rate": 9.917525374361912e-05,
"loss": 0.9217,
"step": 21
},
{
"epoch": 0.022244691607684528,
"grad_norm": 0.30384790897369385,
"learning_rate": 9.901899829374047e-05,
"loss": 0.9443,
"step": 22
},
{
"epoch": 0.023255813953488372,
"grad_norm": 0.30055946111679077,
"learning_rate": 9.884934153917997e-05,
"loss": 0.8959,
"step": 23
},
{
"epoch": 0.024266936299292215,
"grad_norm": 0.32019102573394775,
"learning_rate": 9.86663298624003e-05,
"loss": 0.9216,
"step": 24
},
{
"epoch": 0.025278058645096056,
"grad_norm": 0.2998518943786621,
"learning_rate": 9.847001329696653e-05,
"loss": 0.9124,
"step": 25
},
{
"epoch": 0.0262891809908999,
"grad_norm": 0.31541433930397034,
"learning_rate": 9.826044551386744e-05,
"loss": 0.8651,
"step": 26
},
{
"epoch": 0.027300303336703743,
"grad_norm": 0.3130960464477539,
"learning_rate": 9.803768380684242e-05,
"loss": 0.9222,
"step": 27
},
{
"epoch": 0.028311425682507583,
"grad_norm": 0.30177041888237,
"learning_rate": 9.780178907671789e-05,
"loss": 0.8886,
"step": 28
},
{
"epoch": 0.029322548028311426,
"grad_norm": 0.30322372913360596,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9092,
"step": 29
},
{
"epoch": 0.030333670374115267,
"grad_norm": 0.29467034339904785,
"learning_rate": 9.729086208503174e-05,
"loss": 0.806,
"step": 30
},
{
"epoch": 0.03134479271991911,
"grad_norm": 0.3044412136077881,
"learning_rate": 9.701596950580806e-05,
"loss": 0.8914,
"step": 31
},
{
"epoch": 0.032355915065722954,
"grad_norm": 0.2893608510494232,
"learning_rate": 9.672822322997305e-05,
"loss": 0.7672,
"step": 32
},
{
"epoch": 0.033367037411526794,
"grad_norm": 0.31984978914260864,
"learning_rate": 9.642770192448536e-05,
"loss": 0.8789,
"step": 33
},
{
"epoch": 0.034378159757330634,
"grad_norm": 0.34007686376571655,
"learning_rate": 9.611448774886924e-05,
"loss": 0.8178,
"step": 34
},
{
"epoch": 0.03538928210313448,
"grad_norm": 0.31928136944770813,
"learning_rate": 9.578866633275288e-05,
"loss": 0.838,
"step": 35
},
{
"epoch": 0.03640040444893832,
"grad_norm": 0.35035672783851624,
"learning_rate": 9.545032675245813e-05,
"loss": 0.9043,
"step": 36
},
{
"epoch": 0.03741152679474216,
"grad_norm": 0.30621546506881714,
"learning_rate": 9.509956150664796e-05,
"loss": 0.7837,
"step": 37
},
{
"epoch": 0.03842264914054601,
"grad_norm": 0.35061219334602356,
"learning_rate": 9.473646649103818e-05,
"loss": 0.8034,
"step": 38
},
{
"epoch": 0.03943377148634985,
"grad_norm": 0.33945730328559875,
"learning_rate": 9.43611409721806e-05,
"loss": 0.8484,
"step": 39
},
{
"epoch": 0.04044489383215369,
"grad_norm": 0.3351072072982788,
"learning_rate": 9.397368756032445e-05,
"loss": 0.8901,
"step": 40
},
{
"epoch": 0.041456016177957536,
"grad_norm": 0.3276209235191345,
"learning_rate": 9.357421218136386e-05,
"loss": 0.8053,
"step": 41
},
{
"epoch": 0.042467138523761376,
"grad_norm": 0.3653741776943207,
"learning_rate": 9.316282404787871e-05,
"loss": 0.8432,
"step": 42
},
{
"epoch": 0.043478260869565216,
"grad_norm": 0.33687329292297363,
"learning_rate": 9.273963562927695e-05,
"loss": 0.7478,
"step": 43
},
{
"epoch": 0.044489383215369056,
"grad_norm": 0.37429699301719666,
"learning_rate": 9.230476262104677e-05,
"loss": 0.8141,
"step": 44
},
{
"epoch": 0.0455005055611729,
"grad_norm": 0.4069656431674957,
"learning_rate": 9.185832391312644e-05,
"loss": 0.9173,
"step": 45
},
{
"epoch": 0.046511627906976744,
"grad_norm": 0.3916890323162079,
"learning_rate": 9.140044155740101e-05,
"loss": 0.8077,
"step": 46
},
{
"epoch": 0.047522750252780584,
"grad_norm": 0.4463062286376953,
"learning_rate": 9.093124073433463e-05,
"loss": 0.8657,
"step": 47
},
{
"epoch": 0.04853387259858443,
"grad_norm": 0.45103251934051514,
"learning_rate": 9.045084971874738e-05,
"loss": 0.8811,
"step": 48
},
{
"epoch": 0.04954499494438827,
"grad_norm": 0.43444567918777466,
"learning_rate": 8.995939984474624e-05,
"loss": 0.8014,
"step": 49
},
{
"epoch": 0.05055611729019211,
"grad_norm": 0.7132362723350525,
"learning_rate": 8.945702546981969e-05,
"loss": 1.0374,
"step": 50
},
{
"epoch": 0.05055611729019211,
"eval_loss": 0.83724445104599,
"eval_runtime": 50.3488,
"eval_samples_per_second": 33.089,
"eval_steps_per_second": 8.282,
"step": 50
},
{
"epoch": 0.05156723963599596,
"grad_norm": 0.27149033546447754,
"learning_rate": 8.894386393810563e-05,
"loss": 0.7589,
"step": 51
},
{
"epoch": 0.0525783619817998,
"grad_norm": 0.2584752142429352,
"learning_rate": 8.842005554284296e-05,
"loss": 0.7392,
"step": 52
},
{
"epoch": 0.05358948432760364,
"grad_norm": 0.23517918586730957,
"learning_rate": 8.788574348801675e-05,
"loss": 0.7946,
"step": 53
},
{
"epoch": 0.054600606673407485,
"grad_norm": 0.22960008680820465,
"learning_rate": 8.73410738492077e-05,
"loss": 0.873,
"step": 54
},
{
"epoch": 0.055611729019211326,
"grad_norm": 0.2705351412296295,
"learning_rate": 8.678619553365659e-05,
"loss": 0.9348,
"step": 55
},
{
"epoch": 0.056622851365015166,
"grad_norm": 0.25804203748703003,
"learning_rate": 8.622126023955446e-05,
"loss": 0.8967,
"step": 56
},
{
"epoch": 0.057633973710819006,
"grad_norm": 0.25729477405548096,
"learning_rate": 8.564642241456986e-05,
"loss": 0.8631,
"step": 57
},
{
"epoch": 0.05864509605662285,
"grad_norm": 0.22325828671455383,
"learning_rate": 8.506183921362443e-05,
"loss": 0.8394,
"step": 58
},
{
"epoch": 0.05965621840242669,
"grad_norm": 0.21898649632930756,
"learning_rate": 8.44676704559283e-05,
"loss": 0.7991,
"step": 59
},
{
"epoch": 0.06066734074823053,
"grad_norm": 0.23847903311252594,
"learning_rate": 8.386407858128706e-05,
"loss": 0.814,
"step": 60
},
{
"epoch": 0.06167846309403438,
"grad_norm": 0.2434123158454895,
"learning_rate": 8.32512286056924e-05,
"loss": 0.8955,
"step": 61
},
{
"epoch": 0.06268958543983821,
"grad_norm": 0.23202411830425262,
"learning_rate": 8.262928807620843e-05,
"loss": 0.7946,
"step": 62
},
{
"epoch": 0.06370070778564206,
"grad_norm": 0.2556302547454834,
"learning_rate": 8.199842702516583e-05,
"loss": 0.8622,
"step": 63
},
{
"epoch": 0.06471183013144591,
"grad_norm": 0.2269536405801773,
"learning_rate": 8.135881792367686e-05,
"loss": 0.788,
"step": 64
},
{
"epoch": 0.06572295247724974,
"grad_norm": 0.27471980452537537,
"learning_rate": 8.07106356344834e-05,
"loss": 0.841,
"step": 65
},
{
"epoch": 0.06673407482305359,
"grad_norm": 0.24587734043598175,
"learning_rate": 8.005405736415126e-05,
"loss": 0.8109,
"step": 66
},
{
"epoch": 0.06774519716885744,
"grad_norm": 0.25273898243904114,
"learning_rate": 7.938926261462366e-05,
"loss": 0.7665,
"step": 67
},
{
"epoch": 0.06875631951466127,
"grad_norm": 0.25824081897735596,
"learning_rate": 7.871643313414718e-05,
"loss": 0.7891,
"step": 68
},
{
"epoch": 0.06976744186046512,
"grad_norm": 0.2536833882331848,
"learning_rate": 7.803575286758364e-05,
"loss": 0.7705,
"step": 69
},
{
"epoch": 0.07077856420626896,
"grad_norm": 0.2475842833518982,
"learning_rate": 7.734740790612136e-05,
"loss": 0.7745,
"step": 70
},
{
"epoch": 0.0717896865520728,
"grad_norm": 0.2575015127658844,
"learning_rate": 7.66515864363997e-05,
"loss": 0.82,
"step": 71
},
{
"epoch": 0.07280080889787664,
"grad_norm": 0.25480371713638306,
"learning_rate": 7.594847868906076e-05,
"loss": 0.7403,
"step": 72
},
{
"epoch": 0.07381193124368049,
"grad_norm": 0.29005947709083557,
"learning_rate": 7.52382768867422e-05,
"loss": 0.8034,
"step": 73
},
{
"epoch": 0.07482305358948432,
"grad_norm": 0.2680274546146393,
"learning_rate": 7.452117519152542e-05,
"loss": 0.7968,
"step": 74
},
{
"epoch": 0.07583417593528817,
"grad_norm": 0.2887076437473297,
"learning_rate": 7.379736965185368e-05,
"loss": 0.8094,
"step": 75
},
{
"epoch": 0.07684529828109202,
"grad_norm": 0.2700800597667694,
"learning_rate": 7.30670581489344e-05,
"loss": 0.7144,
"step": 76
},
{
"epoch": 0.07785642062689585,
"grad_norm": 0.31872811913490295,
"learning_rate": 7.233044034264034e-05,
"loss": 0.7936,
"step": 77
},
{
"epoch": 0.0788675429726997,
"grad_norm": 0.27943184971809387,
"learning_rate": 7.158771761692464e-05,
"loss": 0.7288,
"step": 78
},
{
"epoch": 0.07987866531850354,
"grad_norm": 0.29804956912994385,
"learning_rate": 7.083909302476453e-05,
"loss": 0.8038,
"step": 79
},
{
"epoch": 0.08088978766430738,
"grad_norm": 0.2717079520225525,
"learning_rate": 7.008477123264848e-05,
"loss": 0.7394,
"step": 80
},
{
"epoch": 0.08190091001011122,
"grad_norm": 0.30430394411087036,
"learning_rate": 6.932495846462261e-05,
"loss": 0.8305,
"step": 81
},
{
"epoch": 0.08291203235591507,
"grad_norm": 0.2859097123146057,
"learning_rate": 6.855986244591104e-05,
"loss": 0.7393,
"step": 82
},
{
"epoch": 0.0839231547017189,
"grad_norm": 0.29636242985725403,
"learning_rate": 6.778969234612584e-05,
"loss": 0.7287,
"step": 83
},
{
"epoch": 0.08493427704752275,
"grad_norm": 0.29631203413009644,
"learning_rate": 6.701465872208216e-05,
"loss": 0.7141,
"step": 84
},
{
"epoch": 0.0859453993933266,
"grad_norm": 0.3486229181289673,
"learning_rate": 6.623497346023418e-05,
"loss": 0.8352,
"step": 85
},
{
"epoch": 0.08695652173913043,
"grad_norm": 0.3721120059490204,
"learning_rate": 6.545084971874738e-05,
"loss": 0.775,
"step": 86
},
{
"epoch": 0.08796764408493428,
"grad_norm": 0.3254863917827606,
"learning_rate": 6.466250186922325e-05,
"loss": 0.7289,
"step": 87
},
{
"epoch": 0.08897876643073811,
"grad_norm": 0.3482848107814789,
"learning_rate": 6.387014543809223e-05,
"loss": 0.784,
"step": 88
},
{
"epoch": 0.08998988877654196,
"grad_norm": 0.34765949845314026,
"learning_rate": 6.307399704769099e-05,
"loss": 0.8082,
"step": 89
},
{
"epoch": 0.0910010111223458,
"grad_norm": 0.368838906288147,
"learning_rate": 6.227427435703997e-05,
"loss": 0.8052,
"step": 90
},
{
"epoch": 0.09201213346814964,
"grad_norm": 0.3402019143104553,
"learning_rate": 6.147119600233758e-05,
"loss": 0.7237,
"step": 91
},
{
"epoch": 0.09302325581395349,
"grad_norm": 0.32854801416397095,
"learning_rate": 6.066498153718735e-05,
"loss": 0.6896,
"step": 92
},
{
"epoch": 0.09403437815975733,
"grad_norm": 0.3368465006351471,
"learning_rate": 5.985585137257401e-05,
"loss": 0.7005,
"step": 93
},
{
"epoch": 0.09504550050556117,
"grad_norm": 0.4369761645793915,
"learning_rate": 5.90440267166055e-05,
"loss": 0.8051,
"step": 94
},
{
"epoch": 0.09605662285136501,
"grad_norm": 0.34953391551971436,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.69,
"step": 95
},
{
"epoch": 0.09706774519716886,
"grad_norm": 0.33027565479278564,
"learning_rate": 5.74131823855921e-05,
"loss": 0.5934,
"step": 96
},
{
"epoch": 0.0980788675429727,
"grad_norm": 0.42938849329948425,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.7855,
"step": 97
},
{
"epoch": 0.09908998988877654,
"grad_norm": 0.4796953797340393,
"learning_rate": 5.577423184847932e-05,
"loss": 0.7745,
"step": 98
},
{
"epoch": 0.10010111223458039,
"grad_norm": 0.5845953226089478,
"learning_rate": 5.495227651252315e-05,
"loss": 0.9379,
"step": 99
},
{
"epoch": 0.10111223458038422,
"grad_norm": 0.626441240310669,
"learning_rate": 5.4128967273616625e-05,
"loss": 0.8407,
"step": 100
},
{
"epoch": 0.10111223458038422,
"eval_loss": 0.7853623032569885,
"eval_runtime": 50.3614,
"eval_samples_per_second": 33.081,
"eval_steps_per_second": 8.28,
"step": 100
},
{
"epoch": 0.10212335692618807,
"grad_norm": 0.1445879340171814,
"learning_rate": 5.330452921628497e-05,
"loss": 0.7155,
"step": 101
},
{
"epoch": 0.10313447927199192,
"grad_norm": 0.17979127168655396,
"learning_rate": 5.247918773366112e-05,
"loss": 0.795,
"step": 102
},
{
"epoch": 0.10414560161779575,
"grad_norm": 0.16335216164588928,
"learning_rate": 5.165316846586541e-05,
"loss": 0.7166,
"step": 103
},
{
"epoch": 0.1051567239635996,
"grad_norm": 0.1975068598985672,
"learning_rate": 5.0826697238317935e-05,
"loss": 0.8181,
"step": 104
},
{
"epoch": 0.10616784630940344,
"grad_norm": 0.21564233303070068,
"learning_rate": 5e-05,
"loss": 0.8436,
"step": 105
},
{
"epoch": 0.10717896865520728,
"grad_norm": 0.23721911013126373,
"learning_rate": 4.917330276168208e-05,
"loss": 0.8103,
"step": 106
},
{
"epoch": 0.10819009100101112,
"grad_norm": 0.238744854927063,
"learning_rate": 4.834683153413459e-05,
"loss": 0.8356,
"step": 107
},
{
"epoch": 0.10920121334681497,
"grad_norm": 0.24662300944328308,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.8112,
"step": 108
},
{
"epoch": 0.1102123356926188,
"grad_norm": 0.2687962055206299,
"learning_rate": 4.669547078371504e-05,
"loss": 0.7722,
"step": 109
},
{
"epoch": 0.11122345803842265,
"grad_norm": 0.24536916613578796,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.795,
"step": 110
},
{
"epoch": 0.1122345803842265,
"grad_norm": 0.2373892217874527,
"learning_rate": 4.504772348747687e-05,
"loss": 0.7835,
"step": 111
},
{
"epoch": 0.11324570273003033,
"grad_norm": 0.26101693511009216,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.8022,
"step": 112
},
{
"epoch": 0.11425682507583418,
"grad_norm": 0.24881425499916077,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.792,
"step": 113
},
{
"epoch": 0.11526794742163801,
"grad_norm": 0.28947913646698,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.7737,
"step": 114
},
{
"epoch": 0.11627906976744186,
"grad_norm": 0.23814891278743744,
"learning_rate": 4.17702704859633e-05,
"loss": 0.7348,
"step": 115
},
{
"epoch": 0.1172901921132457,
"grad_norm": 0.2723856568336487,
"learning_rate": 4.095597328339452e-05,
"loss": 0.843,
"step": 116
},
{
"epoch": 0.11830131445904954,
"grad_norm": 0.24490369856357574,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.7405,
"step": 117
},
{
"epoch": 0.11931243680485339,
"grad_norm": 0.2560327351093292,
"learning_rate": 3.933501846281267e-05,
"loss": 0.7397,
"step": 118
},
{
"epoch": 0.12032355915065723,
"grad_norm": 0.3040284216403961,
"learning_rate": 3.852880399766243e-05,
"loss": 0.8526,
"step": 119
},
{
"epoch": 0.12133468149646107,
"grad_norm": 0.25108906626701355,
"learning_rate": 3.772572564296005e-05,
"loss": 0.6855,
"step": 120
},
{
"epoch": 0.12234580384226491,
"grad_norm": 0.28637540340423584,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.8158,
"step": 121
},
{
"epoch": 0.12335692618806876,
"grad_norm": 0.2800399959087372,
"learning_rate": 3.612985456190778e-05,
"loss": 0.7052,
"step": 122
},
{
"epoch": 0.1243680485338726,
"grad_norm": 0.2940939664840698,
"learning_rate": 3.533749813077677e-05,
"loss": 0.7797,
"step": 123
},
{
"epoch": 0.12537917087967643,
"grad_norm": 0.29059016704559326,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.7584,
"step": 124
},
{
"epoch": 0.1263902932254803,
"grad_norm": 0.3029254972934723,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.7925,
"step": 125
},
{
"epoch": 0.12740141557128412,
"grad_norm": 0.3084964156150818,
"learning_rate": 3.298534127791785e-05,
"loss": 0.8653,
"step": 126
},
{
"epoch": 0.12841253791708795,
"grad_norm": 0.2903442084789276,
"learning_rate": 3.221030765387417e-05,
"loss": 0.7248,
"step": 127
},
{
"epoch": 0.12942366026289182,
"grad_norm": 0.2756825387477875,
"learning_rate": 3.144013755408895e-05,
"loss": 0.7159,
"step": 128
},
{
"epoch": 0.13043478260869565,
"grad_norm": 0.29607969522476196,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.7328,
"step": 129
},
{
"epoch": 0.13144590495449948,
"grad_norm": 0.28305575251579285,
"learning_rate": 2.991522876735154e-05,
"loss": 0.7405,
"step": 130
},
{
"epoch": 0.13245702730030334,
"grad_norm": 0.3362610638141632,
"learning_rate": 2.916090697523549e-05,
"loss": 0.8088,
"step": 131
},
{
"epoch": 0.13346814964610718,
"grad_norm": 0.31651681661605835,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.7738,
"step": 132
},
{
"epoch": 0.134479271991911,
"grad_norm": 0.3246115744113922,
"learning_rate": 2.766955965735968e-05,
"loss": 0.7475,
"step": 133
},
{
"epoch": 0.13549039433771487,
"grad_norm": 0.31663426756858826,
"learning_rate": 2.693294185106562e-05,
"loss": 0.734,
"step": 134
},
{
"epoch": 0.1365015166835187,
"grad_norm": 0.3378746509552002,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.7825,
"step": 135
},
{
"epoch": 0.13751263902932254,
"grad_norm": 0.3254399001598358,
"learning_rate": 2.547882480847461e-05,
"loss": 0.7292,
"step": 136
},
{
"epoch": 0.1385237613751264,
"grad_norm": 0.3353380262851715,
"learning_rate": 2.476172311325783e-05,
"loss": 0.7263,
"step": 137
},
{
"epoch": 0.13953488372093023,
"grad_norm": 0.3074869215488434,
"learning_rate": 2.405152131093926e-05,
"loss": 0.6498,
"step": 138
},
{
"epoch": 0.14054600606673406,
"grad_norm": 0.3658754229545593,
"learning_rate": 2.3348413563600325e-05,
"loss": 0.7797,
"step": 139
},
{
"epoch": 0.14155712841253792,
"grad_norm": 0.35673946142196655,
"learning_rate": 2.2652592093878666e-05,
"loss": 0.7939,
"step": 140
},
{
"epoch": 0.14256825075834176,
"grad_norm": 0.3774884343147278,
"learning_rate": 2.196424713241637e-05,
"loss": 0.7314,
"step": 141
},
{
"epoch": 0.1435793731041456,
"grad_norm": 0.3515547811985016,
"learning_rate": 2.128356686585282e-05,
"loss": 0.7358,
"step": 142
},
{
"epoch": 0.14459049544994945,
"grad_norm": 0.3989035487174988,
"learning_rate": 2.061073738537635e-05,
"loss": 0.8463,
"step": 143
},
{
"epoch": 0.14560161779575329,
"grad_norm": 0.39837345480918884,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.7461,
"step": 144
},
{
"epoch": 0.14661274014155712,
"grad_norm": 0.3874199092388153,
"learning_rate": 1.928936436551661e-05,
"loss": 0.7415,
"step": 145
},
{
"epoch": 0.14762386248736098,
"grad_norm": 0.44643062353134155,
"learning_rate": 1.8641182076323148e-05,
"loss": 0.8106,
"step": 146
},
{
"epoch": 0.1486349848331648,
"grad_norm": 0.43793392181396484,
"learning_rate": 1.800157297483417e-05,
"loss": 0.7803,
"step": 147
},
{
"epoch": 0.14964610717896865,
"grad_norm": 0.45935964584350586,
"learning_rate": 1.7370711923791567e-05,
"loss": 0.7487,
"step": 148
},
{
"epoch": 0.1506572295247725,
"grad_norm": 0.5578981637954712,
"learning_rate": 1.6748771394307585e-05,
"loss": 0.9711,
"step": 149
},
{
"epoch": 0.15166835187057634,
"grad_norm": 0.6663854718208313,
"learning_rate": 1.6135921418712956e-05,
"loss": 0.9227,
"step": 150
},
{
"epoch": 0.15166835187057634,
"eval_loss": 0.7633453607559204,
"eval_runtime": 50.4394,
"eval_samples_per_second": 33.03,
"eval_steps_per_second": 8.267,
"step": 150
},
{
"epoch": 0.15267947421638017,
"grad_norm": 0.1272272765636444,
"learning_rate": 1.553232954407171e-05,
"loss": 0.6778,
"step": 151
},
{
"epoch": 0.15369059656218403,
"grad_norm": 0.1399427205324173,
"learning_rate": 1.4938160786375572e-05,
"loss": 0.7174,
"step": 152
},
{
"epoch": 0.15470171890798787,
"grad_norm": 0.16902732849121094,
"learning_rate": 1.435357758543015e-05,
"loss": 0.7299,
"step": 153
},
{
"epoch": 0.1557128412537917,
"grad_norm": 0.1675402969121933,
"learning_rate": 1.3778739760445552e-05,
"loss": 0.7037,
"step": 154
},
{
"epoch": 0.15672396359959556,
"grad_norm": 0.21070344746112823,
"learning_rate": 1.3213804466343421e-05,
"loss": 0.7654,
"step": 155
},
{
"epoch": 0.1577350859453994,
"grad_norm": 0.21207165718078613,
"learning_rate": 1.2658926150792322e-05,
"loss": 0.8009,
"step": 156
},
{
"epoch": 0.15874620829120323,
"grad_norm": 0.2189692109823227,
"learning_rate": 1.2114256511983274e-05,
"loss": 0.7592,
"step": 157
},
{
"epoch": 0.1597573306370071,
"grad_norm": 0.2378927320241928,
"learning_rate": 1.157994445715706e-05,
"loss": 0.7884,
"step": 158
},
{
"epoch": 0.16076845298281092,
"grad_norm": 0.24428603053092957,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.814,
"step": 159
},
{
"epoch": 0.16177957532861476,
"grad_norm": 0.23859427869319916,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.7384,
"step": 160
},
{
"epoch": 0.16279069767441862,
"grad_norm": 0.257879376411438,
"learning_rate": 1.0040600155253765e-05,
"loss": 0.7736,
"step": 161
},
{
"epoch": 0.16380182002022245,
"grad_norm": 0.2455569952726364,
"learning_rate": 9.549150281252633e-06,
"loss": 0.7593,
"step": 162
},
{
"epoch": 0.16481294236602628,
"grad_norm": 0.28459832072257996,
"learning_rate": 9.068759265665384e-06,
"loss": 0.8493,
"step": 163
},
{
"epoch": 0.16582406471183014,
"grad_norm": 0.2694055140018463,
"learning_rate": 8.599558442598998e-06,
"loss": 0.8126,
"step": 164
},
{
"epoch": 0.16683518705763398,
"grad_norm": 0.2462318241596222,
"learning_rate": 8.141676086873572e-06,
"loss": 0.7374,
"step": 165
},
{
"epoch": 0.1678463094034378,
"grad_norm": 0.2713393568992615,
"learning_rate": 7.695237378953223e-06,
"loss": 0.7638,
"step": 166
},
{
"epoch": 0.16885743174924167,
"grad_norm": 0.25184810161590576,
"learning_rate": 7.260364370723044e-06,
"loss": 0.7354,
"step": 167
},
{
"epoch": 0.1698685540950455,
"grad_norm": 0.2712859809398651,
"learning_rate": 6.837175952121306e-06,
"loss": 0.7911,
"step": 168
},
{
"epoch": 0.17087967644084934,
"grad_norm": 0.2823898494243622,
"learning_rate": 6.425787818636131e-06,
"loss": 0.7985,
"step": 169
},
{
"epoch": 0.1718907987866532,
"grad_norm": 0.25658711791038513,
"learning_rate": 6.026312439675552e-06,
"loss": 0.7691,
"step": 170
},
{
"epoch": 0.17290192113245703,
"grad_norm": 0.2877839207649231,
"learning_rate": 5.6388590278194096e-06,
"loss": 0.761,
"step": 171
},
{
"epoch": 0.17391304347826086,
"grad_norm": 0.28454214334487915,
"learning_rate": 5.263533508961827e-06,
"loss": 0.7568,
"step": 172
},
{
"epoch": 0.17492416582406473,
"grad_norm": 0.26517605781555176,
"learning_rate": 4.900438493352055e-06,
"loss": 0.6914,
"step": 173
},
{
"epoch": 0.17593528816986856,
"grad_norm": 0.2830790579319,
"learning_rate": 4.549673247541875e-06,
"loss": 0.7735,
"step": 174
},
{
"epoch": 0.1769464105156724,
"grad_norm": 0.306985467672348,
"learning_rate": 4.2113336672471245e-06,
"loss": 0.7257,
"step": 175
},
{
"epoch": 0.17795753286147623,
"grad_norm": 0.29978933930397034,
"learning_rate": 3.885512251130763e-06,
"loss": 0.7711,
"step": 176
},
{
"epoch": 0.1789686552072801,
"grad_norm": 0.289646178483963,
"learning_rate": 3.5722980755146517e-06,
"loss": 0.8057,
"step": 177
},
{
"epoch": 0.17997977755308392,
"grad_norm": 0.2966819405555725,
"learning_rate": 3.271776770026963e-06,
"loss": 0.7282,
"step": 178
},
{
"epoch": 0.18099089989888775,
"grad_norm": 0.31478750705718994,
"learning_rate": 2.9840304941919415e-06,
"loss": 0.7856,
"step": 179
},
{
"epoch": 0.1820020222446916,
"grad_norm": 0.29623422026634216,
"learning_rate": 2.7091379149682685e-06,
"loss": 0.6985,
"step": 180
},
{
"epoch": 0.18301314459049545,
"grad_norm": 0.32452911138534546,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.7571,
"step": 181
},
{
"epoch": 0.18402426693629928,
"grad_norm": 0.2937887907028198,
"learning_rate": 2.1982109232821178e-06,
"loss": 0.6749,
"step": 182
},
{
"epoch": 0.18503538928210314,
"grad_norm": 0.322902113199234,
"learning_rate": 1.962316193157593e-06,
"loss": 0.756,
"step": 183
},
{
"epoch": 0.18604651162790697,
"grad_norm": 0.3696511685848236,
"learning_rate": 1.7395544861325718e-06,
"loss": 0.849,
"step": 184
},
{
"epoch": 0.1870576339737108,
"grad_norm": 0.33034321665763855,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.7859,
"step": 185
},
{
"epoch": 0.18806875631951467,
"grad_norm": 0.34689730405807495,
"learning_rate": 1.333670137599713e-06,
"loss": 0.8283,
"step": 186
},
{
"epoch": 0.1890798786653185,
"grad_norm": 0.3476114571094513,
"learning_rate": 1.1506584608200367e-06,
"loss": 0.7518,
"step": 187
},
{
"epoch": 0.19009100101112233,
"grad_norm": 0.37273553013801575,
"learning_rate": 9.810017062595322e-07,
"loss": 0.816,
"step": 188
},
{
"epoch": 0.1911021233569262,
"grad_norm": 0.35195815563201904,
"learning_rate": 8.247462563808817e-07,
"loss": 0.7478,
"step": 189
},
{
"epoch": 0.19211324570273003,
"grad_norm": 0.3585607707500458,
"learning_rate": 6.819348298638839e-07,
"loss": 0.7828,
"step": 190
},
{
"epoch": 0.19312436804853386,
"grad_norm": 0.3714843988418579,
"learning_rate": 5.526064699265753e-07,
"loss": 0.7635,
"step": 191
},
{
"epoch": 0.19413549039433772,
"grad_norm": 0.37644708156585693,
"learning_rate": 4.367965336512403e-07,
"loss": 0.8012,
"step": 192
},
{
"epoch": 0.19514661274014156,
"grad_norm": 0.4035707712173462,
"learning_rate": 3.3453668231809286e-07,
"loss": 0.8388,
"step": 193
},
{
"epoch": 0.1961577350859454,
"grad_norm": 0.3666282892227173,
"learning_rate": 2.458548727494292e-07,
"loss": 0.6399,
"step": 194
},
{
"epoch": 0.19716885743174925,
"grad_norm": 0.37958642840385437,
"learning_rate": 1.7077534966650766e-07,
"loss": 0.6872,
"step": 195
},
{
"epoch": 0.19817997977755308,
"grad_norm": 0.4451029300689697,
"learning_rate": 1.0931863906127327e-07,
"loss": 0.8135,
"step": 196
},
{
"epoch": 0.19919110212335692,
"grad_norm": 0.492899090051651,
"learning_rate": 6.150154258476315e-08,
"loss": 0.8836,
"step": 197
},
{
"epoch": 0.20020222446916078,
"grad_norm": 0.47472137212753296,
"learning_rate": 2.7337132953697554e-08,
"loss": 0.72,
"step": 198
},
{
"epoch": 0.2012133468149646,
"grad_norm": 0.46337440609931946,
"learning_rate": 6.834750376549792e-09,
"loss": 0.7419,
"step": 199
},
{
"epoch": 0.20222446916076844,
"grad_norm": 0.6667613387107849,
"learning_rate": 0.0,
"loss": 0.7994,
"step": 200
},
{
"epoch": 0.20222446916076844,
"eval_loss": 0.7592693567276001,
"eval_runtime": 50.4908,
"eval_samples_per_second": 32.996,
"eval_steps_per_second": 8.259,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.70907881268183e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}