ErrorAI's picture
Training in progress, step 236, checkpoint
cf08e3b verified
Raw History Blame Contribute Delete
42.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 59,
"global_step": 236,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00423728813559322,
"grad_norm": 0.93435138463974,
"learning_rate": 2e-05,
"loss": 6.022,
"step": 1
},
{
"epoch": 0.00423728813559322,
"eval_loss": 1.5282647609710693,
"eval_runtime": 7.1175,
"eval_samples_per_second": 14.05,
"eval_steps_per_second": 7.025,
"step": 1
},
{
"epoch": 0.00847457627118644,
"grad_norm": 1.3107619285583496,
"learning_rate": 4e-05,
"loss": 5.9185,
"step": 2
},
{
"epoch": 0.012711864406779662,
"grad_norm": 0.6630541086196899,
"learning_rate": 6e-05,
"loss": 6.0478,
"step": 3
},
{
"epoch": 0.01694915254237288,
"grad_norm": 1.1335469484329224,
"learning_rate": 8e-05,
"loss": 5.2389,
"step": 4
},
{
"epoch": 0.0211864406779661,
"grad_norm": 1.1335643529891968,
"learning_rate": 0.0001,
"loss": 7.1338,
"step": 5
},
{
"epoch": 0.025423728813559324,
"grad_norm": 1.5306239128112793,
"learning_rate": 0.00012,
"loss": 6.0755,
"step": 6
},
{
"epoch": 0.029661016949152543,
"grad_norm": 1.0867124795913696,
"learning_rate": 0.00014,
"loss": 6.8117,
"step": 7
},
{
"epoch": 0.03389830508474576,
"grad_norm": 0.9578568935394287,
"learning_rate": 0.00016,
"loss": 6.8011,
"step": 8
},
{
"epoch": 0.038135593220338986,
"grad_norm": 1.0799486637115479,
"learning_rate": 0.00018,
"loss": 6.7039,
"step": 9
},
{
"epoch": 0.0423728813559322,
"grad_norm": 1.5282158851623535,
"learning_rate": 0.0002,
"loss": 5.6313,
"step": 10
},
{
"epoch": 0.046610169491525424,
"grad_norm": 1.9403914213180542,
"learning_rate": 0.00019999033847063811,
"loss": 7.0799,
"step": 11
},
{
"epoch": 0.05084745762711865,
"grad_norm": 3.048349618911743,
"learning_rate": 0.00019996135574945544,
"loss": 6.5488,
"step": 12
},
{
"epoch": 0.05508474576271186,
"grad_norm": 2.31885027885437,
"learning_rate": 0.00019991305743680013,
"loss": 7.2261,
"step": 13
},
{
"epoch": 0.059322033898305086,
"grad_norm": 1.8449187278747559,
"learning_rate": 0.0001998454528653836,
"loss": 5.4851,
"step": 14
},
{
"epoch": 0.0635593220338983,
"grad_norm": 4.439443588256836,
"learning_rate": 0.00019975855509847686,
"loss": 6.414,
"step": 15
},
{
"epoch": 0.06779661016949153,
"grad_norm": 2.1660385131835938,
"learning_rate": 0.00019965238092738643,
"loss": 7.2336,
"step": 16
},
{
"epoch": 0.07203389830508475,
"grad_norm": 1.5337001085281372,
"learning_rate": 0.00019952695086820975,
"loss": 6.2012,
"step": 17
},
{
"epoch": 0.07627118644067797,
"grad_norm": 1.4069186449050903,
"learning_rate": 0.0001993822891578708,
"loss": 5.561,
"step": 18
},
{
"epoch": 0.08050847457627118,
"grad_norm": 2.1463675498962402,
"learning_rate": 0.0001992184237494368,
"loss": 5.7428,
"step": 19
},
{
"epoch": 0.0847457627118644,
"grad_norm": 2.5662553310394287,
"learning_rate": 0.0001990353863067169,
"loss": 4.293,
"step": 20
},
{
"epoch": 0.08898305084745763,
"grad_norm": 1.8066450357437134,
"learning_rate": 0.0001988332121981436,
"loss": 4.2494,
"step": 21
},
{
"epoch": 0.09322033898305085,
"grad_norm": 1.886709213256836,
"learning_rate": 0.00019861194048993863,
"loss": 6.4416,
"step": 22
},
{
"epoch": 0.09745762711864407,
"grad_norm": 1.9437390565872192,
"learning_rate": 0.0001983716139385641,
"loss": 5.7425,
"step": 23
},
{
"epoch": 0.1016949152542373,
"grad_norm": 2.127446413040161,
"learning_rate": 0.0001981122789824607,
"loss": 6.2049,
"step": 24
},
{
"epoch": 0.1059322033898305,
"grad_norm": 2.5859451293945312,
"learning_rate": 0.00019783398573307428,
"loss": 6.1108,
"step": 25
},
{
"epoch": 0.11016949152542373,
"grad_norm": 1.9746959209442139,
"learning_rate": 0.00019753678796517282,
"loss": 4.653,
"step": 26
},
{
"epoch": 0.11440677966101695,
"grad_norm": 1.5029537677764893,
"learning_rate": 0.00019722074310645553,
"loss": 6.2839,
"step": 27
},
{
"epoch": 0.11864406779661017,
"grad_norm": 2.269805908203125,
"learning_rate": 0.00019688591222645607,
"loss": 5.628,
"step": 28
},
{
"epoch": 0.1228813559322034,
"grad_norm": 2.1564295291900635,
"learning_rate": 0.000196532360024742,
"loss": 6.4123,
"step": 29
},
{
"epoch": 0.1271186440677966,
"grad_norm": 2.3761954307556152,
"learning_rate": 0.0001961601548184129,
"loss": 5.5128,
"step": 30
},
{
"epoch": 0.13135593220338984,
"grad_norm": 1.9238841533660889,
"learning_rate": 0.00019576936852889936,
"loss": 5.836,
"step": 31
},
{
"epoch": 0.13559322033898305,
"grad_norm": 1.7540390491485596,
"learning_rate": 0.00019536007666806556,
"loss": 6.7537,
"step": 32
},
{
"epoch": 0.13983050847457626,
"grad_norm": 2.3828277587890625,
"learning_rate": 0.0001949323583236181,
"loss": 6.257,
"step": 33
},
{
"epoch": 0.1440677966101695,
"grad_norm": 1.759395718574524,
"learning_rate": 0.0001944862961438239,
"loss": 3.6914,
"step": 34
},
{
"epoch": 0.1483050847457627,
"grad_norm": 2.694974899291992,
"learning_rate": 0.00019402197632153992,
"loss": 6.2578,
"step": 35
},
{
"epoch": 0.15254237288135594,
"grad_norm": 3.1266930103302,
"learning_rate": 0.00019353948857755803,
"loss": 6.6762,
"step": 36
},
{
"epoch": 0.15677966101694915,
"grad_norm": 2.4520297050476074,
"learning_rate": 0.00019303892614326836,
"loss": 6.9808,
"step": 37
},
{
"epoch": 0.16101694915254236,
"grad_norm": 1.475329875946045,
"learning_rate": 0.00019252038574264405,
"loss": 5.6409,
"step": 38
},
{
"epoch": 0.1652542372881356,
"grad_norm": 2.588773012161255,
"learning_rate": 0.00019198396757355118,
"loss": 6.3522,
"step": 39
},
{
"epoch": 0.1694915254237288,
"grad_norm": 1.8694051504135132,
"learning_rate": 0.00019142977528838762,
"loss": 6.1291,
"step": 40
},
{
"epoch": 0.17372881355932204,
"grad_norm": 2.373533010482788,
"learning_rate": 0.00019085791597405404,
"loss": 5.9928,
"step": 41
},
{
"epoch": 0.17796610169491525,
"grad_norm": 3.6754894256591797,
"learning_rate": 0.00019026850013126157,
"loss": 6.3815,
"step": 42
},
{
"epoch": 0.18220338983050846,
"grad_norm": 1.7676002979278564,
"learning_rate": 0.00018966164165317966,
"loss": 6.453,
"step": 43
},
{
"epoch": 0.1864406779661017,
"grad_norm": 1.3256787061691284,
"learning_rate": 0.00018903745780342839,
"loss": 6.3553,
"step": 44
},
{
"epoch": 0.1906779661016949,
"grad_norm": 1.6511330604553223,
"learning_rate": 0.0001883960691934196,
"loss": 4.8997,
"step": 45
},
{
"epoch": 0.19491525423728814,
"grad_norm": 1.721350073814392,
"learning_rate": 0.00018773759975905098,
"loss": 5.0406,
"step": 46
},
{
"epoch": 0.19915254237288135,
"grad_norm": 1.7820731401443481,
"learning_rate": 0.00018706217673675811,
"loss": 5.7118,
"step": 47
},
{
"epoch": 0.2033898305084746,
"grad_norm": 1.6048412322998047,
"learning_rate": 0.0001863699306389282,
"loss": 6.0263,
"step": 48
},
{
"epoch": 0.2076271186440678,
"grad_norm": 1.4817653894424438,
"learning_rate": 0.00018566099522868119,
"loss": 5.9415,
"step": 49
},
{
"epoch": 0.211864406779661,
"grad_norm": 2.7853312492370605,
"learning_rate": 0.00018493550749402278,
"loss": 5.5053,
"step": 50
},
{
"epoch": 0.21610169491525424,
"grad_norm": 1.8527765274047852,
"learning_rate": 0.00018419360762137395,
"loss": 4.5492,
"step": 51
},
{
"epoch": 0.22033898305084745,
"grad_norm": 2.2048535346984863,
"learning_rate": 0.00018343543896848273,
"loss": 8.1486,
"step": 52
},
{
"epoch": 0.2245762711864407,
"grad_norm": 1.7079168558120728,
"learning_rate": 0.00018266114803672318,
"loss": 5.3628,
"step": 53
},
{
"epoch": 0.2288135593220339,
"grad_norm": 2.1374549865722656,
"learning_rate": 0.00018187088444278674,
"loss": 5.8904,
"step": 54
},
{
"epoch": 0.2330508474576271,
"grad_norm": 2.382983684539795,
"learning_rate": 0.00018106480088977172,
"loss": 4.538,
"step": 55
},
{
"epoch": 0.23728813559322035,
"grad_norm": 2.197672128677368,
"learning_rate": 0.00018024305313767646,
"loss": 4.4606,
"step": 56
},
{
"epoch": 0.24152542372881355,
"grad_norm": 1.6247694492340088,
"learning_rate": 0.00017940579997330165,
"loss": 4.0559,
"step": 57
},
{
"epoch": 0.2457627118644068,
"grad_norm": 1.5712074041366577,
"learning_rate": 0.00017855320317956784,
"loss": 5.8273,
"step": 58
},
{
"epoch": 0.25,
"grad_norm": 1.6524977684020996,
"learning_rate": 0.00017768542750425426,
"loss": 6.2318,
"step": 59
},
{
"epoch": 0.25,
"eval_loss": 1.3850336074829102,
"eval_runtime": 7.0902,
"eval_samples_per_second": 14.104,
"eval_steps_per_second": 7.052,
"step": 59
},
{
"epoch": 0.2542372881355932,
"grad_norm": 1.5502198934555054,
"learning_rate": 0.0001768026406281642,
"loss": 5.2109,
"step": 60
},
{
"epoch": 0.2584745762711864,
"grad_norm": 1.8017003536224365,
"learning_rate": 0.00017590501313272415,
"loss": 6.0785,
"step": 61
},
{
"epoch": 0.2627118644067797,
"grad_norm": 1.7847765684127808,
"learning_rate": 0.00017499271846702213,
"loss": 4.9068,
"step": 62
},
{
"epoch": 0.2669491525423729,
"grad_norm": 1.5741537809371948,
"learning_rate": 0.00017406593291429217,
"loss": 5.4379,
"step": 63
},
{
"epoch": 0.2711864406779661,
"grad_norm": 1.365412950515747,
"learning_rate": 0.00017312483555785086,
"loss": 3.6425,
"step": 64
},
{
"epoch": 0.2754237288135593,
"grad_norm": 1.7937501668930054,
"learning_rate": 0.00017216960824649303,
"loss": 6.818,
"step": 65
},
{
"epoch": 0.2796610169491525,
"grad_norm": 1.7252205610275269,
"learning_rate": 0.00017120043555935298,
"loss": 5.2337,
"step": 66
},
{
"epoch": 0.2838983050847458,
"grad_norm": 1.6318126916885376,
"learning_rate": 0.0001702175047702382,
"loss": 4.8196,
"step": 67
},
{
"epoch": 0.288135593220339,
"grad_norm": 2.2506821155548096,
"learning_rate": 0.00016922100581144228,
"loss": 4.5169,
"step": 68
},
{
"epoch": 0.2923728813559322,
"grad_norm": 1.5296686887741089,
"learning_rate": 0.00016821113123704424,
"loss": 4.6808,
"step": 69
},
{
"epoch": 0.2966101694915254,
"grad_norm": 1.6065572500228882,
"learning_rate": 0.00016718807618570106,
"loss": 5.6518,
"step": 70
},
{
"epoch": 0.3008474576271186,
"grad_norm": 1.5301107168197632,
"learning_rate": 0.00016615203834294119,
"loss": 4.3934,
"step": 71
},
{
"epoch": 0.3050847457627119,
"grad_norm": 1.1689343452453613,
"learning_rate": 0.00016510321790296525,
"loss": 4.6425,
"step": 72
},
{
"epoch": 0.3093220338983051,
"grad_norm": 1.2540870904922485,
"learning_rate": 0.00016404181752996289,
"loss": 6.5413,
"step": 73
},
{
"epoch": 0.3135593220338983,
"grad_norm": 2.988340377807617,
"learning_rate": 0.00016296804231895142,
"loss": 2.8704,
"step": 74
},
{
"epoch": 0.3177966101694915,
"grad_norm": 2.624145269393921,
"learning_rate": 0.00016188209975614542,
"loss": 8.0201,
"step": 75
},
{
"epoch": 0.3220338983050847,
"grad_norm": 2.1858763694763184,
"learning_rate": 0.00016078419967886402,
"loss": 6.0421,
"step": 76
},
{
"epoch": 0.326271186440678,
"grad_norm": 1.665157675743103,
"learning_rate": 0.00015967455423498387,
"loss": 6.4215,
"step": 77
},
{
"epoch": 0.3305084745762712,
"grad_norm": 1.1391340494155884,
"learning_rate": 0.00015855337784194577,
"loss": 5.7596,
"step": 78
},
{
"epoch": 0.3347457627118644,
"grad_norm": 1.3100152015686035,
"learning_rate": 0.00015742088714532247,
"loss": 5.2074,
"step": 79
},
{
"epoch": 0.3389830508474576,
"grad_norm": 1.9967092275619507,
"learning_rate": 0.00015627730097695638,
"loss": 5.3709,
"step": 80
},
{
"epoch": 0.3432203389830508,
"grad_norm": 1.5776952505111694,
"learning_rate": 0.00015512284031267437,
"loss": 5.9981,
"step": 81
},
{
"epoch": 0.3474576271186441,
"grad_norm": 1.0257835388183594,
"learning_rate": 0.00015395772822958845,
"loss": 5.9825,
"step": 82
},
{
"epoch": 0.3516949152542373,
"grad_norm": 1.5740242004394531,
"learning_rate": 0.00015278218986299074,
"loss": 4.8249,
"step": 83
},
{
"epoch": 0.3559322033898305,
"grad_norm": 1.6861892938613892,
"learning_rate": 0.0001515964523628501,
"loss": 4.3845,
"step": 84
},
{
"epoch": 0.3601694915254237,
"grad_norm": 1.4004765748977661,
"learning_rate": 0.00015040074484992,
"loss": 4.4196,
"step": 85
},
{
"epoch": 0.3644067796610169,
"grad_norm": 1.792279839515686,
"learning_rate": 0.00014919529837146528,
"loss": 5.1566,
"step": 86
},
{
"epoch": 0.3686440677966102,
"grad_norm": 1.9727193117141724,
"learning_rate": 0.00014798034585661695,
"loss": 6.2365,
"step": 87
},
{
"epoch": 0.3728813559322034,
"grad_norm": 1.918335199356079,
"learning_rate": 0.0001467561220713628,
"loss": 4.8331,
"step": 88
},
{
"epoch": 0.3771186440677966,
"grad_norm": 1.2826801538467407,
"learning_rate": 0.0001455228635731839,
"loss": 6.5472,
"step": 89
},
{
"epoch": 0.3813559322033898,
"grad_norm": 0.9126927852630615,
"learning_rate": 0.00014428080866534396,
"loss": 5.3882,
"step": 90
},
{
"epoch": 0.3855932203389831,
"grad_norm": 1.3578442335128784,
"learning_rate": 0.00014303019735084226,
"loss": 5.4403,
"step": 91
},
{
"epoch": 0.3898305084745763,
"grad_norm": 1.3523539304733276,
"learning_rate": 0.00014177127128603745,
"loss": 6.2458,
"step": 92
},
{
"epoch": 0.3940677966101695,
"grad_norm": 2.189840316772461,
"learning_rate": 0.0001405042737339524,
"loss": 5.3938,
"step": 93
},
{
"epoch": 0.3983050847457627,
"grad_norm": 2.7657406330108643,
"learning_rate": 0.0001392294495172681,
"loss": 6.3785,
"step": 94
},
{
"epoch": 0.4025423728813559,
"grad_norm": 1.462851881980896,
"learning_rate": 0.00013794704497101655,
"loss": 5.4128,
"step": 95
},
{
"epoch": 0.4067796610169492,
"grad_norm": 1.3086453676223755,
"learning_rate": 0.0001366573078949813,
"loss": 5.7441,
"step": 96
},
{
"epoch": 0.4110169491525424,
"grad_norm": 2.55996036529541,
"learning_rate": 0.00013536048750581494,
"loss": 5.4807,
"step": 97
},
{
"epoch": 0.4152542372881356,
"grad_norm": 1.7401981353759766,
"learning_rate": 0.00013405683438888282,
"loss": 5.0087,
"step": 98
},
{
"epoch": 0.4194915254237288,
"grad_norm": 1.833206057548523,
"learning_rate": 0.00013274660044984224,
"loss": 5.401,
"step": 99
},
{
"epoch": 0.423728813559322,
"grad_norm": 1.1227648258209229,
"learning_rate": 0.00013143003886596669,
"loss": 5.8596,
"step": 100
},
{
"epoch": 0.4279661016949153,
"grad_norm": 1.4440932273864746,
"learning_rate": 0.0001301074040372242,
"loss": 4.299,
"step": 101
},
{
"epoch": 0.4322033898305085,
"grad_norm": 1.3902015686035156,
"learning_rate": 0.00012877895153711935,
"loss": 5.2348,
"step": 102
},
{
"epoch": 0.4364406779661017,
"grad_norm": 2.3583362102508545,
"learning_rate": 0.0001274449380633089,
"loss": 6.7036,
"step": 103
},
{
"epoch": 0.4406779661016949,
"grad_norm": 1.4885296821594238,
"learning_rate": 0.00012610562138799978,
"loss": 6.339,
"step": 104
},
{
"epoch": 0.4449152542372881,
"grad_norm": 1.6107800006866455,
"learning_rate": 0.00012476126030813963,
"loss": 5.5737,
"step": 105
},
{
"epoch": 0.4491525423728814,
"grad_norm": 1.6457529067993164,
"learning_rate": 0.0001234121145954094,
"loss": 4.68,
"step": 106
},
{
"epoch": 0.4533898305084746,
"grad_norm": 2.6190664768218994,
"learning_rate": 0.0001220584449460274,
"loss": 5.6051,
"step": 107
},
{
"epoch": 0.4576271186440678,
"grad_norm": 1.8676761388778687,
"learning_rate": 0.00012070051293037492,
"loss": 5.4647,
"step": 108
},
{
"epoch": 0.461864406779661,
"grad_norm": 2.39504337310791,
"learning_rate": 0.00011933858094245281,
"loss": 4.0834,
"step": 109
},
{
"epoch": 0.4661016949152542,
"grad_norm": 2.288006067276001,
"learning_rate": 0.00011797291214917881,
"loss": 5.9169,
"step": 110
},
{
"epoch": 0.4703389830508475,
"grad_norm": 1.2063994407653809,
"learning_rate": 0.00011660377043953588,
"loss": 5.8516,
"step": 111
},
{
"epoch": 0.4745762711864407,
"grad_norm": 2.7913434505462646,
"learning_rate": 0.0001152314203735805,
"loss": 5.452,
"step": 112
},
{
"epoch": 0.4788135593220339,
"grad_norm": 1.5486477613449097,
"learning_rate": 0.0001138561271313219,
"loss": 5.6845,
"step": 113
},
{
"epoch": 0.4830508474576271,
"grad_norm": 1.3842769861221313,
"learning_rate": 0.00011247815646148087,
"loss": 3.9482,
"step": 114
},
{
"epoch": 0.4872881355932203,
"grad_norm": 1.8453153371810913,
"learning_rate": 0.00011109777463013915,
"loss": 6.0286,
"step": 115
},
{
"epoch": 0.4915254237288136,
"grad_norm": 1.570230484008789,
"learning_rate": 0.0001097152483692886,
"loss": 4.6404,
"step": 116
},
{
"epoch": 0.4957627118644068,
"grad_norm": 1.6343928575515747,
"learning_rate": 0.00010833084482529048,
"loss": 6.4812,
"step": 117
},
{
"epoch": 0.5,
"grad_norm": 1.450670838356018,
"learning_rate": 0.00010694483150725458,
"loss": 5.0213,
"step": 118
},
{
"epoch": 0.5,
"eval_loss": 1.3630183935165405,
"eval_runtime": 7.0743,
"eval_samples_per_second": 14.136,
"eval_steps_per_second": 7.068,
"step": 118
},
{
"epoch": 0.5042372881355932,
"grad_norm": 1.6642025709152222,
"learning_rate": 0.00010555747623534831,
"loss": 5.1026,
"step": 119
},
{
"epoch": 0.5084745762711864,
"grad_norm": 2.017059087753296,
"learning_rate": 0.00010416904708904548,
"loss": 4.8477,
"step": 120
},
{
"epoch": 0.5127118644067796,
"grad_norm": 2.029778003692627,
"learning_rate": 0.00010277981235532541,
"loss": 5.9989,
"step": 121
},
{
"epoch": 0.5169491525423728,
"grad_norm": 1.565796136856079,
"learning_rate": 0.00010139004047683151,
"loss": 4.0977,
"step": 122
},
{
"epoch": 0.5211864406779662,
"grad_norm": 1.284759283065796,
"learning_rate": 0.0001,
"loss": 6.3971,
"step": 123
},
{
"epoch": 0.5254237288135594,
"grad_norm": 1.5899869203567505,
"learning_rate": 9.860995952316851e-05,
"loss": 5.342,
"step": 124
},
{
"epoch": 0.5296610169491526,
"grad_norm": 1.2444443702697754,
"learning_rate": 9.722018764467461e-05,
"loss": 5.5082,
"step": 125
},
{
"epoch": 0.5338983050847458,
"grad_norm": 1.5828735828399658,
"learning_rate": 9.583095291095453e-05,
"loss": 5.8702,
"step": 126
},
{
"epoch": 0.538135593220339,
"grad_norm": 3.7572929859161377,
"learning_rate": 9.444252376465171e-05,
"loss": 4.3785,
"step": 127
},
{
"epoch": 0.5423728813559322,
"grad_norm": 2.7158265113830566,
"learning_rate": 9.305516849274541e-05,
"loss": 5.0584,
"step": 128
},
{
"epoch": 0.5466101694915254,
"grad_norm": 1.598179817199707,
"learning_rate": 9.166915517470953e-05,
"loss": 4.3117,
"step": 129
},
{
"epoch": 0.5508474576271186,
"grad_norm": 1.5766159296035767,
"learning_rate": 9.028475163071141e-05,
"loss": 5.6085,
"step": 130
},
{
"epoch": 0.5550847457627118,
"grad_norm": 1.7020022869110107,
"learning_rate": 8.890222536986085e-05,
"loss": 5.3097,
"step": 131
},
{
"epoch": 0.559322033898305,
"grad_norm": 1.423659324645996,
"learning_rate": 8.752184353851916e-05,
"loss": 6.0762,
"step": 132
},
{
"epoch": 0.5635593220338984,
"grad_norm": 2.035299062728882,
"learning_rate": 8.614387286867814e-05,
"loss": 5.5225,
"step": 133
},
{
"epoch": 0.5677966101694916,
"grad_norm": 2.2816035747528076,
"learning_rate": 8.47685796264195e-05,
"loss": 5.565,
"step": 134
},
{
"epoch": 0.5720338983050848,
"grad_norm": 1.8796865940093994,
"learning_rate": 8.339622956046417e-05,
"loss": 5.4363,
"step": 135
},
{
"epoch": 0.576271186440678,
"grad_norm": 1.6780980825424194,
"learning_rate": 8.202708785082121e-05,
"loss": 4.9135,
"step": 136
},
{
"epoch": 0.5805084745762712,
"grad_norm": 2.6253199577331543,
"learning_rate": 8.066141905754723e-05,
"loss": 5.8014,
"step": 137
},
{
"epoch": 0.5847457627118644,
"grad_norm": 1.7806695699691772,
"learning_rate": 7.929948706962508e-05,
"loss": 5.6643,
"step": 138
},
{
"epoch": 0.5889830508474576,
"grad_norm": 1.6690291166305542,
"learning_rate": 7.794155505397261e-05,
"loss": 4.788,
"step": 139
},
{
"epoch": 0.5932203389830508,
"grad_norm": 1.2224397659301758,
"learning_rate": 7.658788540459062e-05,
"loss": 5.7951,
"step": 140
},
{
"epoch": 0.597457627118644,
"grad_norm": 1.7819712162017822,
"learning_rate": 7.523873969186039e-05,
"loss": 5.5056,
"step": 141
},
{
"epoch": 0.6016949152542372,
"grad_norm": 2.8600285053253174,
"learning_rate": 7.389437861200024e-05,
"loss": 4.424,
"step": 142
},
{
"epoch": 0.6059322033898306,
"grad_norm": 2.1180453300476074,
"learning_rate": 7.25550619366911e-05,
"loss": 4.7318,
"step": 143
},
{
"epoch": 0.6101694915254238,
"grad_norm": 1.7061822414398193,
"learning_rate": 7.122104846288064e-05,
"loss": 6.6938,
"step": 144
},
{
"epoch": 0.614406779661017,
"grad_norm": 1.474294900894165,
"learning_rate": 6.989259596277582e-05,
"loss": 5.7241,
"step": 145
},
{
"epoch": 0.6186440677966102,
"grad_norm": 1.4275479316711426,
"learning_rate": 6.85699611340333e-05,
"loss": 4.0837,
"step": 146
},
{
"epoch": 0.6228813559322034,
"grad_norm": 2.809462785720825,
"learning_rate": 6.725339955015777e-05,
"loss": 7.3159,
"step": 147
},
{
"epoch": 0.6271186440677966,
"grad_norm": 2.748603343963623,
"learning_rate": 6.594316561111724e-05,
"loss": 6.2878,
"step": 148
},
{
"epoch": 0.6313559322033898,
"grad_norm": 1.9641263484954834,
"learning_rate": 6.46395124941851e-05,
"loss": 4.7853,
"step": 149
},
{
"epoch": 0.635593220338983,
"grad_norm": 3.6411221027374268,
"learning_rate": 6.334269210501875e-05,
"loss": 5.5019,
"step": 150
},
{
"epoch": 0.6398305084745762,
"grad_norm": 1.7731056213378906,
"learning_rate": 6.205295502898348e-05,
"loss": 4.3701,
"step": 151
},
{
"epoch": 0.6440677966101694,
"grad_norm": 1.3389068841934204,
"learning_rate": 6.0770550482731924e-05,
"loss": 6.5773,
"step": 152
},
{
"epoch": 0.6483050847457628,
"grad_norm": 1.3923825025558472,
"learning_rate": 5.9495726266047605e-05,
"loss": 5.4175,
"step": 153
},
{
"epoch": 0.652542372881356,
"grad_norm": 2.2159035205841064,
"learning_rate": 5.8228728713962543e-05,
"loss": 3.6546,
"step": 154
},
{
"epoch": 0.6567796610169492,
"grad_norm": 1.6734590530395508,
"learning_rate": 5.696980264915777e-05,
"loss": 4.4299,
"step": 155
},
{
"epoch": 0.6610169491525424,
"grad_norm": 1.7563037872314453,
"learning_rate": 5.571919133465605e-05,
"loss": 5.0263,
"step": 156
},
{
"epoch": 0.6652542372881356,
"grad_norm": 1.501452088356018,
"learning_rate": 5.447713642681612e-05,
"loss": 6.2963,
"step": 157
},
{
"epoch": 0.6694915254237288,
"grad_norm": 1.4349921941757202,
"learning_rate": 5.324387792863719e-05,
"loss": 6.4959,
"step": 158
},
{
"epoch": 0.673728813559322,
"grad_norm": 1.7934768199920654,
"learning_rate": 5.201965414338308e-05,
"loss": 5.6093,
"step": 159
},
{
"epoch": 0.6779661016949152,
"grad_norm": 1.5769773721694946,
"learning_rate": 5.080470162853472e-05,
"loss": 6.9835,
"step": 160
},
{
"epoch": 0.6822033898305084,
"grad_norm": 2.40470290184021,
"learning_rate": 4.959925515008002e-05,
"loss": 4.8795,
"step": 161
},
{
"epoch": 0.6864406779661016,
"grad_norm": 1.6426795721054077,
"learning_rate": 4.840354763714991e-05,
"loss": 4.7669,
"step": 162
},
{
"epoch": 0.690677966101695,
"grad_norm": 1.5152642726898193,
"learning_rate": 4.7217810137009274e-05,
"loss": 4.3649,
"step": 163
},
{
"epoch": 0.6949152542372882,
"grad_norm": 0.9684991836547852,
"learning_rate": 4.604227177041156e-05,
"loss": 5.1498,
"step": 164
},
{
"epoch": 0.6991525423728814,
"grad_norm": 1.9173654317855835,
"learning_rate": 4.487715968732568e-05,
"loss": 5.7244,
"step": 165
},
{
"epoch": 0.7033898305084746,
"grad_norm": 1.960520625114441,
"learning_rate": 4.372269902304363e-05,
"loss": 4.9004,
"step": 166
},
{
"epoch": 0.7076271186440678,
"grad_norm": 1.0363643169403076,
"learning_rate": 4.257911285467754e-05,
"loss": 5.8545,
"step": 167
},
{
"epoch": 0.711864406779661,
"grad_norm": 1.3583155870437622,
"learning_rate": 4.144662215805426e-05,
"loss": 6.3824,
"step": 168
},
{
"epoch": 0.7161016949152542,
"grad_norm": 4.059554100036621,
"learning_rate": 4.0325445765016145e-05,
"loss": 4.7046,
"step": 169
},
{
"epoch": 0.7203389830508474,
"grad_norm": 1.8046865463256836,
"learning_rate": 3.921580032113602e-05,
"loss": 3.955,
"step": 170
},
{
"epoch": 0.7245762711864406,
"grad_norm": 1.36460280418396,
"learning_rate": 3.8117900243854595e-05,
"loss": 5.9647,
"step": 171
},
{
"epoch": 0.7288135593220338,
"grad_norm": 1.7739871740341187,
"learning_rate": 3.7031957681048604e-05,
"loss": 6.397,
"step": 172
},
{
"epoch": 0.7330508474576272,
"grad_norm": 2.6238420009613037,
"learning_rate": 3.595818247003713e-05,
"loss": 5.9568,
"step": 173
},
{
"epoch": 0.7372881355932204,
"grad_norm": 1.4640283584594727,
"learning_rate": 3.489678209703475e-05,
"loss": 5.3649,
"step": 174
},
{
"epoch": 0.7415254237288136,
"grad_norm": 1.3590552806854248,
"learning_rate": 3.3847961657058845e-05,
"loss": 6.5281,
"step": 175
},
{
"epoch": 0.7457627118644068,
"grad_norm": 2.4690585136413574,
"learning_rate": 3.281192381429894e-05,
"loss": 5.6778,
"step": 176
},
{
"epoch": 0.75,
"grad_norm": 1.4456470012664795,
"learning_rate": 3.178886876295578e-05,
"loss": 6.7767,
"step": 177
},
{
"epoch": 0.75,
"eval_loss": 1.3556182384490967,
"eval_runtime": 7.0946,
"eval_samples_per_second": 14.095,
"eval_steps_per_second": 7.048,
"step": 177
},
{
"epoch": 0.7542372881355932,
"grad_norm": 1.659873366355896,
"learning_rate": 3.077899418855772e-05,
"loss": 5.2241,
"step": 178
},
{
"epoch": 0.7584745762711864,
"grad_norm": 1.6144360303878784,
"learning_rate": 2.9782495229761808e-05,
"loss": 6.47,
"step": 179
},
{
"epoch": 0.7627118644067796,
"grad_norm": 2.68172287940979,
"learning_rate": 2.879956444064703e-05,
"loss": 5.6168,
"step": 180
},
{
"epoch": 0.7669491525423728,
"grad_norm": 1.148950219154358,
"learning_rate": 2.783039175350699e-05,
"loss": 4.7857,
"step": 181
},
{
"epoch": 0.7711864406779662,
"grad_norm": 2.0405430793762207,
"learning_rate": 2.6875164442149147e-05,
"loss": 4.1435,
"step": 182
},
{
"epoch": 0.7754237288135594,
"grad_norm": 1.8292560577392578,
"learning_rate": 2.5934067085707834e-05,
"loss": 4.8491,
"step": 183
},
{
"epoch": 0.7796610169491526,
"grad_norm": 1.592108964920044,
"learning_rate": 2.500728153297788e-05,
"loss": 5.9074,
"step": 184
},
{
"epoch": 0.7838983050847458,
"grad_norm": 1.3204245567321777,
"learning_rate": 2.409498686727587e-05,
"loss": 5.3229,
"step": 185
},
{
"epoch": 0.788135593220339,
"grad_norm": 1.6157606840133667,
"learning_rate": 2.3197359371835802e-05,
"loss": 5.0719,
"step": 186
},
{
"epoch": 0.7923728813559322,
"grad_norm": 1.5353844165802002,
"learning_rate": 2.2314572495745746e-05,
"loss": 5.2844,
"step": 187
},
{
"epoch": 0.7966101694915254,
"grad_norm": 1.859458327293396,
"learning_rate": 2.1446796820432167e-05,
"loss": 5.0241,
"step": 188
},
{
"epoch": 0.8008474576271186,
"grad_norm": 2.213860273361206,
"learning_rate": 2.0594200026698363e-05,
"loss": 4.9303,
"step": 189
},
{
"epoch": 0.8050847457627118,
"grad_norm": 1.3739302158355713,
"learning_rate": 1.9756946862323535e-05,
"loss": 6.1114,
"step": 190
},
{
"epoch": 0.809322033898305,
"grad_norm": 1.5952653884887695,
"learning_rate": 1.8935199110228275e-05,
"loss": 5.3459,
"step": 191
},
{
"epoch": 0.8135593220338984,
"grad_norm": 1.7411179542541504,
"learning_rate": 1.8129115557213262e-05,
"loss": 6.0951,
"step": 192
},
{
"epoch": 0.8177966101694916,
"grad_norm": 1.467255711555481,
"learning_rate": 1.7338851963276825e-05,
"loss": 3.5396,
"step": 193
},
{
"epoch": 0.8220338983050848,
"grad_norm": 1.6787402629852295,
"learning_rate": 1.656456103151728e-05,
"loss": 4.9857,
"step": 194
},
{
"epoch": 0.826271186440678,
"grad_norm": 1.718984842300415,
"learning_rate": 1.580639237862608e-05,
"loss": 7.6591,
"step": 195
},
{
"epoch": 0.8305084745762712,
"grad_norm": 1.2019591331481934,
"learning_rate": 1.5064492505977234e-05,
"loss": 5.4475,
"step": 196
},
{
"epoch": 0.8347457627118644,
"grad_norm": 1.509769320487976,
"learning_rate": 1.433900477131882e-05,
"loss": 5.373,
"step": 197
},
{
"epoch": 0.8389830508474576,
"grad_norm": 1.1810944080352783,
"learning_rate": 1.363006936107183e-05,
"loss": 6.8259,
"step": 198
},
{
"epoch": 0.8432203389830508,
"grad_norm": 1.7051451206207275,
"learning_rate": 1.29378232632419e-05,
"loss": 5.3893,
"step": 199
},
{
"epoch": 0.847457627118644,
"grad_norm": 1.605209469795227,
"learning_rate": 1.2262400240949023e-05,
"loss": 3.6749,
"step": 200
},
{
"epoch": 0.8516949152542372,
"grad_norm": 1.559640884399414,
"learning_rate": 1.1603930806580444e-05,
"loss": 6.7777,
"step": 201
},
{
"epoch": 0.8559322033898306,
"grad_norm": 1.8430358171463013,
"learning_rate": 1.0962542196571634e-05,
"loss": 5.6894,
"step": 202
},
{
"epoch": 0.8601694915254238,
"grad_norm": 1.3345764875411987,
"learning_rate": 1.0338358346820353e-05,
"loss": 4.8869,
"step": 203
},
{
"epoch": 0.864406779661017,
"grad_norm": 1.2212978601455688,
"learning_rate": 9.731499868738447e-06,
"loss": 5.3213,
"step": 204
},
{
"epoch": 0.8686440677966102,
"grad_norm": 1.6549381017684937,
"learning_rate": 9.142084025945984e-06,
"loss": 6.597,
"step": 205
},
{
"epoch": 0.8728813559322034,
"grad_norm": 1.4284532070159912,
"learning_rate": 8.570224711612385e-06,
"loss": 3.9897,
"step": 206
},
{
"epoch": 0.8771186440677966,
"grad_norm": 1.5879578590393066,
"learning_rate": 8.016032426448817e-06,
"loss": 5.833,
"step": 207
},
{
"epoch": 0.8813559322033898,
"grad_norm": 1.9117746353149414,
"learning_rate": 7.479614257355971e-06,
"loss": 6.5309,
"step": 208
},
{
"epoch": 0.885593220338983,
"grad_norm": 1.4658851623535156,
"learning_rate": 6.961073856731648e-06,
"loss": 5.767,
"step": 209
},
{
"epoch": 0.8898305084745762,
"grad_norm": 1.2028073072433472,
"learning_rate": 6.460511422441984e-06,
"loss": 6.1011,
"step": 210
},
{
"epoch": 0.8940677966101694,
"grad_norm": 1.6110073328018188,
"learning_rate": 5.978023678460099e-06,
"loss": 4.3484,
"step": 211
},
{
"epoch": 0.8983050847457628,
"grad_norm": 3.445389986038208,
"learning_rate": 5.5137038561761115e-06,
"loss": 6.5291,
"step": 212
},
{
"epoch": 0.902542372881356,
"grad_norm": 2.289745330810547,
"learning_rate": 5.067641676381918e-06,
"loss": 6.0326,
"step": 213
},
{
"epoch": 0.9067796610169492,
"grad_norm": 1.7480942010879517,
"learning_rate": 4.639923331934471e-06,
"loss": 4.8869,
"step": 214
},
{
"epoch": 0.9110169491525424,
"grad_norm": 2.0448532104492188,
"learning_rate": 4.230631471100655e-06,
"loss": 6.7924,
"step": 215
},
{
"epoch": 0.9152542372881356,
"grad_norm": 1.7284777164459229,
"learning_rate": 3.839845181587098e-06,
"loss": 5.6074,
"step": 216
},
{
"epoch": 0.9194915254237288,
"grad_norm": 1.3124265670776367,
"learning_rate": 3.467639975257997e-06,
"loss": 5.1132,
"step": 217
},
{
"epoch": 0.923728813559322,
"grad_norm": 2.4826791286468506,
"learning_rate": 3.1140877735439387e-06,
"loss": 7.7159,
"step": 218
},
{
"epoch": 0.9279661016949152,
"grad_norm": 2.097788095474243,
"learning_rate": 2.7792568935444796e-06,
"loss": 3.8859,
"step": 219
},
{
"epoch": 0.9322033898305084,
"grad_norm": 1.7564079761505127,
"learning_rate": 2.4632120348272003e-06,
"loss": 4.8586,
"step": 220
},
{
"epoch": 0.9364406779661016,
"grad_norm": 1.6387519836425781,
"learning_rate": 2.166014266925731e-06,
"loss": 6.3061,
"step": 221
},
{
"epoch": 0.940677966101695,
"grad_norm": 1.330946445465088,
"learning_rate": 1.88772101753929e-06,
"loss": 5.0511,
"step": 222
},
{
"epoch": 0.9449152542372882,
"grad_norm": 1.418730616569519,
"learning_rate": 1.6283860614358936e-06,
"loss": 4.5408,
"step": 223
},
{
"epoch": 0.9491525423728814,
"grad_norm": 1.767754316329956,
"learning_rate": 1.3880595100613792e-06,
"loss": 5.6123,
"step": 224
},
{
"epoch": 0.9533898305084746,
"grad_norm": 1.25843346118927,
"learning_rate": 1.1667878018564171e-06,
"loss": 4.6931,
"step": 225
},
{
"epoch": 0.9576271186440678,
"grad_norm": 1.2846879959106445,
"learning_rate": 9.64613693283123e-07,
"loss": 5.2122,
"step": 226
},
{
"epoch": 0.961864406779661,
"grad_norm": 1.5150436162948608,
"learning_rate": 7.815762505632096e-07,
"loss": 6.3263,
"step": 227
},
{
"epoch": 0.9661016949152542,
"grad_norm": 1.6773252487182617,
"learning_rate": 6.177108421292266e-07,
"loss": 5.8491,
"step": 228
},
{
"epoch": 0.9703389830508474,
"grad_norm": 1.4844250679016113,
"learning_rate": 4.7304913179025965e-07,
"loss": 5.981,
"step": 229
},
{
"epoch": 0.9745762711864406,
"grad_norm": 2.42675518989563,
"learning_rate": 3.4761907261356976e-07,
"loss": 5.1298,
"step": 230
},
{
"epoch": 0.9788135593220338,
"grad_norm": 1.7614575624465942,
"learning_rate": 2.414449015231357e-07,
"loss": 5.1633,
"step": 231
},
{
"epoch": 0.9830508474576272,
"grad_norm": 1.1330649852752686,
"learning_rate": 1.545471346164007e-07,
"loss": 6.7273,
"step": 232
},
{
"epoch": 0.9872881355932204,
"grad_norm": 1.9067260026931763,
"learning_rate": 8.694256319987659e-08,
"loss": 6.0546,
"step": 233
},
{
"epoch": 0.9915254237288136,
"grad_norm": 1.432326078414917,
"learning_rate": 3.8644250544594975e-08,
"loss": 6.6485,
"step": 234
},
{
"epoch": 0.9957627118644068,
"grad_norm": 1.3281971216201782,
"learning_rate": 9.661529361892907e-09,
"loss": 5.262,
"step": 235
},
{
"epoch": 1.0,
"grad_norm": 1.966170072555542,
"learning_rate": 0.0,
"loss": 5.7779,
"step": 236
},
{
"epoch": 1.0,
"eval_loss": 1.3537216186523438,
"eval_runtime": 7.0949,
"eval_samples_per_second": 14.095,
"eval_steps_per_second": 7.047,
"step": 236
}
],
"logging_steps": 1,
"max_steps": 236,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 59,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.0721558879797248e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}