eeve-2.8B_A / trainer_state.json
c10's picture
Model save
bf338d6 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 387,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002583979328165375,
"grad_norm": 6.678133964538574,
"learning_rate": 2.564102564102564e-07,
"loss": 2.2997,
"step": 1
},
{
"epoch": 0.00516795865633075,
"grad_norm": 6.834577560424805,
"learning_rate": 5.128205128205128e-07,
"loss": 2.3158,
"step": 2
},
{
"epoch": 0.007751937984496124,
"grad_norm": 7.110385417938232,
"learning_rate": 7.692307692307694e-07,
"loss": 2.3468,
"step": 3
},
{
"epoch": 0.0103359173126615,
"grad_norm": 6.803109169006348,
"learning_rate": 1.0256410256410257e-06,
"loss": 2.2928,
"step": 4
},
{
"epoch": 0.012919896640826873,
"grad_norm": 6.826089382171631,
"learning_rate": 1.282051282051282e-06,
"loss": 2.3315,
"step": 5
},
{
"epoch": 0.015503875968992248,
"grad_norm": 6.920953750610352,
"learning_rate": 1.5384615384615387e-06,
"loss": 2.3069,
"step": 6
},
{
"epoch": 0.01808785529715762,
"grad_norm": 6.446414947509766,
"learning_rate": 1.794871794871795e-06,
"loss": 2.2685,
"step": 7
},
{
"epoch": 0.020671834625323,
"grad_norm": 6.7022786140441895,
"learning_rate": 2.0512820512820513e-06,
"loss": 2.2895,
"step": 8
},
{
"epoch": 0.023255813953488372,
"grad_norm": 6.589105606079102,
"learning_rate": 2.307692307692308e-06,
"loss": 2.2653,
"step": 9
},
{
"epoch": 0.025839793281653745,
"grad_norm": 5.955119609832764,
"learning_rate": 2.564102564102564e-06,
"loss": 2.1308,
"step": 10
},
{
"epoch": 0.028423772609819122,
"grad_norm": 5.912731647491455,
"learning_rate": 2.8205128205128207e-06,
"loss": 2.1179,
"step": 11
},
{
"epoch": 0.031007751937984496,
"grad_norm": 5.7995123863220215,
"learning_rate": 3.0769230769230774e-06,
"loss": 2.0886,
"step": 12
},
{
"epoch": 0.03359173126614987,
"grad_norm": 4.567681312561035,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.7614,
"step": 13
},
{
"epoch": 0.03617571059431524,
"grad_norm": 4.454052925109863,
"learning_rate": 3.58974358974359e-06,
"loss": 1.7257,
"step": 14
},
{
"epoch": 0.03875968992248062,
"grad_norm": 4.280542850494385,
"learning_rate": 3.846153846153847e-06,
"loss": 1.6546,
"step": 15
},
{
"epoch": 0.041343669250646,
"grad_norm": 4.197136878967285,
"learning_rate": 4.102564102564103e-06,
"loss": 1.5889,
"step": 16
},
{
"epoch": 0.04392764857881137,
"grad_norm": 3.324878692626953,
"learning_rate": 4.358974358974359e-06,
"loss": 1.1931,
"step": 17
},
{
"epoch": 0.046511627906976744,
"grad_norm": 3.594575881958008,
"learning_rate": 4.615384615384616e-06,
"loss": 1.0317,
"step": 18
},
{
"epoch": 0.04909560723514212,
"grad_norm": 3.397719144821167,
"learning_rate": 4.871794871794872e-06,
"loss": 0.9836,
"step": 19
},
{
"epoch": 0.05167958656330749,
"grad_norm": 3.1062400341033936,
"learning_rate": 5.128205128205128e-06,
"loss": 0.9742,
"step": 20
},
{
"epoch": 0.05426356589147287,
"grad_norm": 2.650336742401123,
"learning_rate": 5.384615384615385e-06,
"loss": 0.8934,
"step": 21
},
{
"epoch": 0.056847545219638244,
"grad_norm": 2.466906785964966,
"learning_rate": 5.641025641025641e-06,
"loss": 0.8145,
"step": 22
},
{
"epoch": 0.059431524547803614,
"grad_norm": 1.7531450986862183,
"learning_rate": 5.897435897435898e-06,
"loss": 0.606,
"step": 23
},
{
"epoch": 0.06201550387596899,
"grad_norm": 1.4234894514083862,
"learning_rate": 6.153846153846155e-06,
"loss": 0.4778,
"step": 24
},
{
"epoch": 0.06459948320413436,
"grad_norm": 1.0901433229446411,
"learning_rate": 6.410256410256412e-06,
"loss": 0.4324,
"step": 25
},
{
"epoch": 0.06718346253229975,
"grad_norm": 0.9714887142181396,
"learning_rate": 6.666666666666667e-06,
"loss": 0.4577,
"step": 26
},
{
"epoch": 0.06976744186046512,
"grad_norm": 0.801122784614563,
"learning_rate": 6.923076923076923e-06,
"loss": 0.4528,
"step": 27
},
{
"epoch": 0.07235142118863049,
"grad_norm": 0.7464026808738708,
"learning_rate": 7.17948717948718e-06,
"loss": 0.4109,
"step": 28
},
{
"epoch": 0.07493540051679587,
"grad_norm": 0.7229853272438049,
"learning_rate": 7.435897435897437e-06,
"loss": 0.4129,
"step": 29
},
{
"epoch": 0.07751937984496124,
"grad_norm": 0.6986636519432068,
"learning_rate": 7.692307692307694e-06,
"loss": 0.4276,
"step": 30
},
{
"epoch": 0.08010335917312661,
"grad_norm": 0.7045499086380005,
"learning_rate": 7.948717948717949e-06,
"loss": 0.4173,
"step": 31
},
{
"epoch": 0.082687338501292,
"grad_norm": 0.6709201335906982,
"learning_rate": 8.205128205128205e-06,
"loss": 0.4033,
"step": 32
},
{
"epoch": 0.08527131782945736,
"grad_norm": 0.5888183116912842,
"learning_rate": 8.461538461538462e-06,
"loss": 0.3339,
"step": 33
},
{
"epoch": 0.08785529715762273,
"grad_norm": 0.621361255645752,
"learning_rate": 8.717948717948719e-06,
"loss": 0.3976,
"step": 34
},
{
"epoch": 0.09043927648578812,
"grad_norm": 0.5428451299667358,
"learning_rate": 8.974358974358976e-06,
"loss": 0.3621,
"step": 35
},
{
"epoch": 0.09302325581395349,
"grad_norm": 0.5530751347541809,
"learning_rate": 9.230769230769232e-06,
"loss": 0.3263,
"step": 36
},
{
"epoch": 0.09560723514211886,
"grad_norm": 0.6014180779457092,
"learning_rate": 9.487179487179487e-06,
"loss": 0.3204,
"step": 37
},
{
"epoch": 0.09819121447028424,
"grad_norm": 0.617842435836792,
"learning_rate": 9.743589743589744e-06,
"loss": 0.3432,
"step": 38
},
{
"epoch": 0.10077519379844961,
"grad_norm": 0.5932274460792542,
"learning_rate": 1e-05,
"loss": 0.3807,
"step": 39
},
{
"epoch": 0.10335917312661498,
"grad_norm": 0.531089723110199,
"learning_rate": 9.999796259054765e-06,
"loss": 0.3466,
"step": 40
},
{
"epoch": 0.10594315245478036,
"grad_norm": 0.5526779890060425,
"learning_rate": 9.999185052823207e-06,
"loss": 0.3495,
"step": 41
},
{
"epoch": 0.10852713178294573,
"grad_norm": 0.48364171385765076,
"learning_rate": 9.998166431116421e-06,
"loss": 0.3392,
"step": 42
},
{
"epoch": 0.1111111111111111,
"grad_norm": 0.5286124348640442,
"learning_rate": 9.996740476948386e-06,
"loss": 0.3237,
"step": 43
},
{
"epoch": 0.11369509043927649,
"grad_norm": 0.5805378556251526,
"learning_rate": 9.994907306529203e-06,
"loss": 0.3871,
"step": 44
},
{
"epoch": 0.11627906976744186,
"grad_norm": 0.48061248660087585,
"learning_rate": 9.99266706925562e-06,
"loss": 0.3396,
"step": 45
},
{
"epoch": 0.11886304909560723,
"grad_norm": 0.7416213750839233,
"learning_rate": 9.990019947698864e-06,
"loss": 0.3259,
"step": 46
},
{
"epoch": 0.12144702842377261,
"grad_norm": 0.47168344259262085,
"learning_rate": 9.986966157589751e-06,
"loss": 0.3197,
"step": 47
},
{
"epoch": 0.12403100775193798,
"grad_norm": 0.4842292070388794,
"learning_rate": 9.983505947801115e-06,
"loss": 0.3641,
"step": 48
},
{
"epoch": 0.12661498708010335,
"grad_norm": 0.5371739268302917,
"learning_rate": 9.979639600327522e-06,
"loss": 0.3614,
"step": 49
},
{
"epoch": 0.12919896640826872,
"grad_norm": 0.5148357152938843,
"learning_rate": 9.975367430262289e-06,
"loss": 0.3728,
"step": 50
},
{
"epoch": 0.13178294573643412,
"grad_norm": 0.4844192564487457,
"learning_rate": 9.970689785771798e-06,
"loss": 0.3208,
"step": 51
},
{
"epoch": 0.1343669250645995,
"grad_norm": 0.6069826483726501,
"learning_rate": 9.965607048067138e-06,
"loss": 0.3513,
"step": 52
},
{
"epoch": 0.13695090439276486,
"grad_norm": 0.47529327869415283,
"learning_rate": 9.960119631373023e-06,
"loss": 0.3379,
"step": 53
},
{
"epoch": 0.13953488372093023,
"grad_norm": 0.49472829699516296,
"learning_rate": 9.954227982894034e-06,
"loss": 0.3013,
"step": 54
},
{
"epoch": 0.1421188630490956,
"grad_norm": 0.6334584355354309,
"learning_rate": 9.947932582778188e-06,
"loss": 0.3138,
"step": 55
},
{
"epoch": 0.14470284237726097,
"grad_norm": 0.4577198624610901,
"learning_rate": 9.941233944077789e-06,
"loss": 0.3153,
"step": 56
},
{
"epoch": 0.14728682170542637,
"grad_norm": 0.47782599925994873,
"learning_rate": 9.934132612707631e-06,
"loss": 0.329,
"step": 57
},
{
"epoch": 0.14987080103359174,
"grad_norm": 0.514714777469635,
"learning_rate": 9.9266291674005e-06,
"loss": 0.359,
"step": 58
},
{
"epoch": 0.1524547803617571,
"grad_norm": 0.4538106322288513,
"learning_rate": 9.918724219660013e-06,
"loss": 0.2988,
"step": 59
},
{
"epoch": 0.15503875968992248,
"grad_norm": 0.46882936358451843,
"learning_rate": 9.91041841371078e-06,
"loss": 0.3246,
"step": 60
},
{
"epoch": 0.15762273901808785,
"grad_norm": 0.429165244102478,
"learning_rate": 9.901712426445901e-06,
"loss": 0.2959,
"step": 61
},
{
"epoch": 0.16020671834625322,
"grad_norm": 0.4619984030723572,
"learning_rate": 9.892606967371808e-06,
"loss": 0.3291,
"step": 62
},
{
"epoch": 0.16279069767441862,
"grad_norm": 0.43021416664123535,
"learning_rate": 9.883102778550434e-06,
"loss": 0.3331,
"step": 63
},
{
"epoch": 0.165374677002584,
"grad_norm": 0.5037028193473816,
"learning_rate": 9.873200634538746e-06,
"loss": 0.3265,
"step": 64
},
{
"epoch": 0.16795865633074936,
"grad_norm": 0.4535587728023529,
"learning_rate": 9.862901342325617e-06,
"loss": 0.3312,
"step": 65
},
{
"epoch": 0.17054263565891473,
"grad_norm": 0.42938175797462463,
"learning_rate": 9.852205741266058e-06,
"loss": 0.2971,
"step": 66
},
{
"epoch": 0.1731266149870801,
"grad_norm": 0.4964745342731476,
"learning_rate": 9.841114703012817e-06,
"loss": 0.3306,
"step": 67
},
{
"epoch": 0.17571059431524547,
"grad_norm": 0.4658762216567993,
"learning_rate": 9.829629131445342e-06,
"loss": 0.3055,
"step": 68
},
{
"epoch": 0.17829457364341086,
"grad_norm": 0.4396679699420929,
"learning_rate": 9.817749962596115e-06,
"loss": 0.3204,
"step": 69
},
{
"epoch": 0.18087855297157623,
"grad_norm": 0.44120684266090393,
"learning_rate": 9.805478164574374e-06,
"loss": 0.3204,
"step": 70
},
{
"epoch": 0.1834625322997416,
"grad_norm": 0.4362391531467438,
"learning_rate": 9.792814737487207e-06,
"loss": 0.3001,
"step": 71
},
{
"epoch": 0.18604651162790697,
"grad_norm": 0.45392006635665894,
"learning_rate": 9.77976071335806e-06,
"loss": 0.3204,
"step": 72
},
{
"epoch": 0.18863049095607234,
"grad_norm": 0.4473075270652771,
"learning_rate": 9.766317156042615e-06,
"loss": 0.3342,
"step": 73
},
{
"epoch": 0.19121447028423771,
"grad_norm": 0.45184287428855896,
"learning_rate": 9.752485161142103e-06,
"loss": 0.3168,
"step": 74
},
{
"epoch": 0.1937984496124031,
"grad_norm": 0.4665965735912323,
"learning_rate": 9.738265855914014e-06,
"loss": 0.3347,
"step": 75
},
{
"epoch": 0.19638242894056848,
"grad_norm": 0.44520583748817444,
"learning_rate": 9.723660399180216e-06,
"loss": 0.3012,
"step": 76
},
{
"epoch": 0.19896640826873385,
"grad_norm": 0.4683307111263275,
"learning_rate": 9.708669981232542e-06,
"loss": 0.2947,
"step": 77
},
{
"epoch": 0.20155038759689922,
"grad_norm": 0.5088106989860535,
"learning_rate": 9.693295823735754e-06,
"loss": 0.3519,
"step": 78
},
{
"epoch": 0.2041343669250646,
"grad_norm": 0.4688245952129364,
"learning_rate": 9.677539179628005e-06,
"loss": 0.3178,
"step": 79
},
{
"epoch": 0.20671834625322996,
"grad_norm": 0.4424334168434143,
"learning_rate": 9.661401333018725e-06,
"loss": 0.3098,
"step": 80
},
{
"epoch": 0.20930232558139536,
"grad_norm": 0.4164547324180603,
"learning_rate": 9.644883599083959e-06,
"loss": 0.2869,
"step": 81
},
{
"epoch": 0.21188630490956073,
"grad_norm": 0.500719428062439,
"learning_rate": 9.627987323959195e-06,
"loss": 0.3038,
"step": 82
},
{
"epoch": 0.2144702842377261,
"grad_norm": 0.42712247371673584,
"learning_rate": 9.610713884629667e-06,
"loss": 0.2932,
"step": 83
},
{
"epoch": 0.21705426356589147,
"grad_norm": 0.4611964821815491,
"learning_rate": 9.59306468881811e-06,
"loss": 0.3099,
"step": 84
},
{
"epoch": 0.21963824289405684,
"grad_norm": 0.4781152307987213,
"learning_rate": 9.575041174870062e-06,
"loss": 0.3124,
"step": 85
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.4377368986606598,
"learning_rate": 9.556644811636628e-06,
"loss": 0.3002,
"step": 86
},
{
"epoch": 0.2248062015503876,
"grad_norm": 0.49812576174736023,
"learning_rate": 9.537877098354787e-06,
"loss": 0.348,
"step": 87
},
{
"epoch": 0.22739018087855298,
"grad_norm": 0.47140446305274963,
"learning_rate": 9.51873956452519e-06,
"loss": 0.3233,
"step": 88
},
{
"epoch": 0.22997416020671835,
"grad_norm": 0.45923298597335815,
"learning_rate": 9.499233769787534e-06,
"loss": 0.3187,
"step": 89
},
{
"epoch": 0.23255813953488372,
"grad_norm": 0.45452624559402466,
"learning_rate": 9.479361303793441e-06,
"loss": 0.2953,
"step": 90
},
{
"epoch": 0.2351421188630491,
"grad_norm": 0.5140699744224548,
"learning_rate": 9.459123786076911e-06,
"loss": 0.3142,
"step": 91
},
{
"epoch": 0.23772609819121446,
"grad_norm": 0.4350361227989197,
"learning_rate": 9.438522865922344e-06,
"loss": 0.3193,
"step": 92
},
{
"epoch": 0.24031007751937986,
"grad_norm": 0.4551020860671997,
"learning_rate": 9.417560222230115e-06,
"loss": 0.3084,
"step": 93
},
{
"epoch": 0.24289405684754523,
"grad_norm": 0.42140695452690125,
"learning_rate": 9.396237563379761e-06,
"loss": 0.2798,
"step": 94
},
{
"epoch": 0.2454780361757106,
"grad_norm": 0.4576823115348816,
"learning_rate": 9.374556627090749e-06,
"loss": 0.2936,
"step": 95
},
{
"epoch": 0.24806201550387597,
"grad_norm": 0.4687109887599945,
"learning_rate": 9.352519180280862e-06,
"loss": 0.3223,
"step": 96
},
{
"epoch": 0.25064599483204136,
"grad_norm": 0.42448845505714417,
"learning_rate": 9.330127018922195e-06,
"loss": 0.3152,
"step": 97
},
{
"epoch": 0.2532299741602067,
"grad_norm": 0.46770456433296204,
"learning_rate": 9.307381967894798e-06,
"loss": 0.3358,
"step": 98
},
{
"epoch": 0.2558139534883721,
"grad_norm": 0.4652756154537201,
"learning_rate": 9.284285880837947e-06,
"loss": 0.2824,
"step": 99
},
{
"epoch": 0.25839793281653745,
"grad_norm": 0.4634130597114563,
"learning_rate": 9.26084063999909e-06,
"loss": 0.3005,
"step": 100
},
{
"epoch": 0.26098191214470284,
"grad_norm": 0.4184122681617737,
"learning_rate": 9.237048156080433e-06,
"loss": 0.2782,
"step": 101
},
{
"epoch": 0.26356589147286824,
"grad_norm": 0.4704434275627136,
"learning_rate": 9.212910368083246e-06,
"loss": 0.2759,
"step": 102
},
{
"epoch": 0.2661498708010336,
"grad_norm": 0.4219190776348114,
"learning_rate": 9.188429243149824e-06,
"loss": 0.2694,
"step": 103
},
{
"epoch": 0.268733850129199,
"grad_norm": 0.4400491416454315,
"learning_rate": 9.163606776403182e-06,
"loss": 0.313,
"step": 104
},
{
"epoch": 0.2713178294573643,
"grad_norm": 0.46378496289253235,
"learning_rate": 9.138444990784455e-06,
"loss": 0.3117,
"step": 105
},
{
"epoch": 0.2739018087855297,
"grad_norm": 0.42383599281311035,
"learning_rate": 9.112945936888034e-06,
"loss": 0.2952,
"step": 106
},
{
"epoch": 0.27648578811369506,
"grad_norm": 0.4268609881401062,
"learning_rate": 9.08711169279446e-06,
"loss": 0.2607,
"step": 107
},
{
"epoch": 0.27906976744186046,
"grad_norm": 0.43639639019966125,
"learning_rate": 9.060944363901057e-06,
"loss": 0.2745,
"step": 108
},
{
"epoch": 0.28165374677002586,
"grad_norm": 0.4547524154186249,
"learning_rate": 9.034446082750352e-06,
"loss": 0.3008,
"step": 109
},
{
"epoch": 0.2842377260981912,
"grad_norm": 0.4684068560600281,
"learning_rate": 9.007619008856287e-06,
"loss": 0.2787,
"step": 110
},
{
"epoch": 0.2868217054263566,
"grad_norm": 0.44395485520362854,
"learning_rate": 8.98046532852822e-06,
"loss": 0.2683,
"step": 111
},
{
"epoch": 0.28940568475452194,
"grad_norm": 0.446803480386734,
"learning_rate": 8.952987254692746e-06,
"loss": 0.3084,
"step": 112
},
{
"epoch": 0.29198966408268734,
"grad_norm": 0.4414445161819458,
"learning_rate": 8.925187026713363e-06,
"loss": 0.2841,
"step": 113
},
{
"epoch": 0.29457364341085274,
"grad_norm": 0.43872445821762085,
"learning_rate": 8.897066910207958e-06,
"loss": 0.2739,
"step": 114
},
{
"epoch": 0.2971576227390181,
"grad_norm": 0.4418787956237793,
"learning_rate": 8.868629196864182e-06,
"loss": 0.2842,
"step": 115
},
{
"epoch": 0.2997416020671835,
"grad_norm": 0.4769684374332428,
"learning_rate": 8.83987620425267e-06,
"loss": 0.3137,
"step": 116
},
{
"epoch": 0.3023255813953488,
"grad_norm": 0.43923094868659973,
"learning_rate": 8.810810275638183e-06,
"loss": 0.3191,
"step": 117
},
{
"epoch": 0.3049095607235142,
"grad_norm": 0.4351806044578552,
"learning_rate": 8.781433779788627e-06,
"loss": 0.2799,
"step": 118
},
{
"epoch": 0.30749354005167956,
"grad_norm": 0.4320261478424072,
"learning_rate": 8.751749110782013e-06,
"loss": 0.2849,
"step": 119
},
{
"epoch": 0.31007751937984496,
"grad_norm": 0.4509352147579193,
"learning_rate": 8.721758687811353e-06,
"loss": 0.3009,
"step": 120
},
{
"epoch": 0.31266149870801035,
"grad_norm": 0.4201003313064575,
"learning_rate": 8.691464954987494e-06,
"loss": 0.2675,
"step": 121
},
{
"epoch": 0.3152454780361757,
"grad_norm": 0.42218485474586487,
"learning_rate": 8.660870381139944e-06,
"loss": 0.2872,
"step": 122
},
{
"epoch": 0.3178294573643411,
"grad_norm": 0.41878223419189453,
"learning_rate": 8.629977459615655e-06,
"loss": 0.2667,
"step": 123
},
{
"epoch": 0.32041343669250644,
"grad_norm": 0.4328330159187317,
"learning_rate": 8.598788708075844e-06,
"loss": 0.2916,
"step": 124
},
{
"epoch": 0.32299741602067183,
"grad_norm": 0.4555003046989441,
"learning_rate": 8.567306668290801e-06,
"loss": 0.289,
"step": 125
},
{
"epoch": 0.32558139534883723,
"grad_norm": 0.4696672558784485,
"learning_rate": 8.535533905932739e-06,
"loss": 0.2982,
"step": 126
},
{
"epoch": 0.3281653746770026,
"grad_norm": 0.4428997337818146,
"learning_rate": 8.503473010366713e-06,
"loss": 0.2989,
"step": 127
},
{
"epoch": 0.330749354005168,
"grad_norm": 0.40596020221710205,
"learning_rate": 8.471126594439591e-06,
"loss": 0.2931,
"step": 128
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.4140114486217499,
"learning_rate": 8.438497294267117e-06,
"loss": 0.2715,
"step": 129
},
{
"epoch": 0.3359173126614987,
"grad_norm": 0.47890666127204895,
"learning_rate": 8.405587769019072e-06,
"loss": 0.3099,
"step": 130
},
{
"epoch": 0.3385012919896641,
"grad_norm": 0.6070849299430847,
"learning_rate": 8.372400700702569e-06,
"loss": 0.3061,
"step": 131
},
{
"epoch": 0.34108527131782945,
"grad_norm": 0.39838454127311707,
"learning_rate": 8.338938793943478e-06,
"loss": 0.2751,
"step": 132
},
{
"epoch": 0.34366925064599485,
"grad_norm": 0.3867545425891876,
"learning_rate": 8.305204775766003e-06,
"loss": 0.2835,
"step": 133
},
{
"epoch": 0.3462532299741602,
"grad_norm": 0.41791021823883057,
"learning_rate": 8.27120139537044e-06,
"loss": 0.3058,
"step": 134
},
{
"epoch": 0.3488372093023256,
"grad_norm": 0.45444855093955994,
"learning_rate": 8.23693142390914e-06,
"loss": 0.2913,
"step": 135
},
{
"epoch": 0.35142118863049093,
"grad_norm": 0.44107621908187866,
"learning_rate": 8.202397654260649e-06,
"loss": 0.2696,
"step": 136
},
{
"epoch": 0.35400516795865633,
"grad_norm": 0.4542611539363861,
"learning_rate": 8.167602900802121e-06,
"loss": 0.299,
"step": 137
},
{
"epoch": 0.35658914728682173,
"grad_norm": 0.4426042139530182,
"learning_rate": 8.132549999179934e-06,
"loss": 0.2841,
"step": 138
},
{
"epoch": 0.35917312661498707,
"grad_norm": 0.44145461916923523,
"learning_rate": 8.097241806078616e-06,
"loss": 0.2936,
"step": 139
},
{
"epoch": 0.36175710594315247,
"grad_norm": 0.42730993032455444,
"learning_rate": 8.06168119898802e-06,
"loss": 0.3022,
"step": 140
},
{
"epoch": 0.3643410852713178,
"grad_norm": 0.4857991635799408,
"learning_rate": 8.025871075968828e-06,
"loss": 0.2884,
"step": 141
},
{
"epoch": 0.3669250645994832,
"grad_norm": 0.5083222985267639,
"learning_rate": 7.989814355416362e-06,
"loss": 0.2998,
"step": 142
},
{
"epoch": 0.3695090439276486,
"grad_norm": 0.4802829325199127,
"learning_rate": 7.953513975822755e-06,
"loss": 0.2652,
"step": 143
},
{
"epoch": 0.37209302325581395,
"grad_norm": 0.5173447132110596,
"learning_rate": 7.916972895537471e-06,
"loss": 0.3088,
"step": 144
},
{
"epoch": 0.37467700258397935,
"grad_norm": 0.4066041111946106,
"learning_rate": 7.8801940925262e-06,
"loss": 0.2892,
"step": 145
},
{
"epoch": 0.3772609819121447,
"grad_norm": 0.43255695700645447,
"learning_rate": 7.843180564128178e-06,
"loss": 0.2852,
"step": 146
},
{
"epoch": 0.3798449612403101,
"grad_norm": 0.5515561103820801,
"learning_rate": 7.805935326811913e-06,
"loss": 0.2967,
"step": 147
},
{
"epoch": 0.38242894056847543,
"grad_norm": 0.5547642707824707,
"learning_rate": 7.768461415929344e-06,
"loss": 0.3027,
"step": 148
},
{
"epoch": 0.3850129198966408,
"grad_norm": 0.4299023449420929,
"learning_rate": 7.730761885468486e-06,
"loss": 0.273,
"step": 149
},
{
"epoch": 0.3875968992248062,
"grad_norm": 0.45513665676116943,
"learning_rate": 7.692839807804522e-06,
"loss": 0.2964,
"step": 150
},
{
"epoch": 0.39018087855297157,
"grad_norm": 0.40135088562965393,
"learning_rate": 7.654698273449435e-06,
"loss": 0.2625,
"step": 151
},
{
"epoch": 0.39276485788113696,
"grad_norm": 0.4702034592628479,
"learning_rate": 7.616340390800127e-06,
"loss": 0.2956,
"step": 152
},
{
"epoch": 0.3953488372093023,
"grad_norm": 0.42673245072364807,
"learning_rate": 7.57776928588511e-06,
"loss": 0.2632,
"step": 153
},
{
"epoch": 0.3979328165374677,
"grad_norm": 0.4496805965900421,
"learning_rate": 7.538988102109728e-06,
"loss": 0.2834,
"step": 154
},
{
"epoch": 0.4005167958656331,
"grad_norm": 0.4896727204322815,
"learning_rate": 7.500000000000001e-06,
"loss": 0.3104,
"step": 155
},
{
"epoch": 0.40310077519379844,
"grad_norm": 0.44338440895080566,
"learning_rate": 7.4608081569450365e-06,
"loss": 0.301,
"step": 156
},
{
"epoch": 0.40568475452196384,
"grad_norm": 0.47325599193573,
"learning_rate": 7.421415766938098e-06,
"loss": 0.2898,
"step": 157
},
{
"epoch": 0.4082687338501292,
"grad_norm": 0.45277851819992065,
"learning_rate": 7.381826040316294e-06,
"loss": 0.2618,
"step": 158
},
{
"epoch": 0.4108527131782946,
"grad_norm": 0.47705507278442383,
"learning_rate": 7.342042203498952e-06,
"loss": 0.3078,
"step": 159
},
{
"epoch": 0.4134366925064599,
"grad_norm": 0.4861289858818054,
"learning_rate": 7.302067498724681e-06,
"loss": 0.2826,
"step": 160
},
{
"epoch": 0.4160206718346253,
"grad_norm": 0.48274198174476624,
"learning_rate": 7.261905183787136e-06,
"loss": 0.255,
"step": 161
},
{
"epoch": 0.4186046511627907,
"grad_norm": 0.48785096406936646,
"learning_rate": 7.221558531769519e-06,
"loss": 0.312,
"step": 162
},
{
"epoch": 0.42118863049095606,
"grad_norm": 0.4825511872768402,
"learning_rate": 7.181030830777838e-06,
"loss": 0.2869,
"step": 163
},
{
"epoch": 0.42377260981912146,
"grad_norm": 0.4649406969547272,
"learning_rate": 7.140325383672938e-06,
"loss": 0.2925,
"step": 164
},
{
"epoch": 0.4263565891472868,
"grad_norm": 0.3625810146331787,
"learning_rate": 7.099445507801324e-06,
"loss": 0.2364,
"step": 165
},
{
"epoch": 0.4289405684754522,
"grad_norm": 0.5031020641326904,
"learning_rate": 7.058394534724819e-06,
"loss": 0.2971,
"step": 166
},
{
"epoch": 0.4315245478036176,
"grad_norm": 0.4177357256412506,
"learning_rate": 7.017175809949044e-06,
"loss": 0.2574,
"step": 167
},
{
"epoch": 0.43410852713178294,
"grad_norm": 0.5013376474380493,
"learning_rate": 6.975792692650778e-06,
"loss": 0.3145,
"step": 168
},
{
"epoch": 0.43669250645994834,
"grad_norm": 0.45426902174949646,
"learning_rate": 6.934248555404197e-06,
"loss": 0.2921,
"step": 169
},
{
"epoch": 0.4392764857881137,
"grad_norm": 0.43907979130744934,
"learning_rate": 6.892546783906016e-06,
"loss": 0.2883,
"step": 170
},
{
"epoch": 0.4418604651162791,
"grad_norm": 0.42910337448120117,
"learning_rate": 6.850690776699574e-06,
"loss": 0.3015,
"step": 171
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.4053723216056824,
"learning_rate": 6.808683944897856e-06,
"loss": 0.2627,
"step": 172
},
{
"epoch": 0.4470284237726098,
"grad_norm": 0.4231443703174591,
"learning_rate": 6.766529711905513e-06,
"loss": 0.2475,
"step": 173
},
{
"epoch": 0.4496124031007752,
"grad_norm": 0.40346193313598633,
"learning_rate": 6.724231513139853e-06,
"loss": 0.2872,
"step": 174
},
{
"epoch": 0.45219638242894056,
"grad_norm": 0.4439121186733246,
"learning_rate": 6.681792795750876e-06,
"loss": 0.3125,
"step": 175
},
{
"epoch": 0.45478036175710596,
"grad_norm": 0.4078086316585541,
"learning_rate": 6.639217018340342e-06,
"loss": 0.2685,
"step": 176
},
{
"epoch": 0.4573643410852713,
"grad_norm": 0.4373514652252197,
"learning_rate": 6.5965076506799e-06,
"loss": 0.2877,
"step": 177
},
{
"epoch": 0.4599483204134367,
"grad_norm": 0.40580716729164124,
"learning_rate": 6.553668173428329e-06,
"loss": 0.2677,
"step": 178
},
{
"epoch": 0.4625322997416021,
"grad_norm": 0.4066397547721863,
"learning_rate": 6.510702077847864e-06,
"loss": 0.2735,
"step": 179
},
{
"epoch": 0.46511627906976744,
"grad_norm": 0.44113850593566895,
"learning_rate": 6.467612865519674e-06,
"loss": 0.2666,
"step": 180
},
{
"epoch": 0.46770025839793283,
"grad_norm": 0.38186588883399963,
"learning_rate": 6.424404048058501e-06,
"loss": 0.2588,
"step": 181
},
{
"epoch": 0.4702842377260982,
"grad_norm": 0.4320223033428192,
"learning_rate": 6.3810791468264654e-06,
"loss": 0.2829,
"step": 182
},
{
"epoch": 0.4728682170542636,
"grad_norm": 0.4612186551094055,
"learning_rate": 6.337641692646106e-06,
"loss": 0.2942,
"step": 183
},
{
"epoch": 0.4754521963824289,
"grad_norm": 0.45380473136901855,
"learning_rate": 6.294095225512604e-06,
"loss": 0.2863,
"step": 184
},
{
"epoch": 0.4780361757105943,
"grad_norm": 0.4170936346054077,
"learning_rate": 6.250443294305315e-06,
"loss": 0.2685,
"step": 185
},
{
"epoch": 0.4806201550387597,
"grad_norm": 0.4243358373641968,
"learning_rate": 6.206689456498529e-06,
"loss": 0.275,
"step": 186
},
{
"epoch": 0.48320413436692505,
"grad_norm": 0.40185001492500305,
"learning_rate": 6.162837277871553e-06,
"loss": 0.2707,
"step": 187
},
{
"epoch": 0.48578811369509045,
"grad_norm": 0.43646830320358276,
"learning_rate": 6.118890332218117e-06,
"loss": 0.3082,
"step": 188
},
{
"epoch": 0.4883720930232558,
"grad_norm": 0.4524317681789398,
"learning_rate": 6.074852201055121e-06,
"loss": 0.2862,
"step": 189
},
{
"epoch": 0.4909560723514212,
"grad_norm": 0.42992088198661804,
"learning_rate": 6.0307264733307515e-06,
"loss": 0.2772,
"step": 190
},
{
"epoch": 0.4935400516795866,
"grad_norm": 0.3978720009326935,
"learning_rate": 5.986516745132e-06,
"loss": 0.2825,
"step": 191
},
{
"epoch": 0.49612403100775193,
"grad_norm": 0.399278849363327,
"learning_rate": 5.942226619391592e-06,
"loss": 0.266,
"step": 192
},
{
"epoch": 0.49870801033591733,
"grad_norm": 0.41332167387008667,
"learning_rate": 5.8978597055943585e-06,
"loss": 0.2676,
"step": 193
},
{
"epoch": 0.5012919896640827,
"grad_norm": 0.41946110129356384,
"learning_rate": 5.853419619483083e-06,
"loss": 0.2972,
"step": 194
},
{
"epoch": 0.5038759689922481,
"grad_norm": 0.3924684524536133,
"learning_rate": 5.808909982763825e-06,
"loss": 0.2779,
"step": 195
},
{
"epoch": 0.5064599483204134,
"grad_norm": 0.4718524217605591,
"learning_rate": 5.764334422810767e-06,
"loss": 0.3037,
"step": 196
},
{
"epoch": 0.5090439276485789,
"grad_norm": 0.4339485168457031,
"learning_rate": 5.719696572370596e-06,
"loss": 0.32,
"step": 197
},
{
"epoch": 0.5116279069767442,
"grad_norm": 0.40892696380615234,
"learning_rate": 5.675000069266451e-06,
"loss": 0.297,
"step": 198
},
{
"epoch": 0.5142118863049095,
"grad_norm": 0.4312550723552704,
"learning_rate": 5.630248556101448e-06,
"loss": 0.3062,
"step": 199
},
{
"epoch": 0.5167958656330749,
"grad_norm": 0.42749255895614624,
"learning_rate": 5.585445679961823e-06,
"loss": 0.2777,
"step": 200
},
{
"epoch": 0.5193798449612403,
"grad_norm": 0.428129106760025,
"learning_rate": 5.540595092119709e-06,
"loss": 0.2914,
"step": 201
},
{
"epoch": 0.5219638242894057,
"grad_norm": 0.4062337279319763,
"learning_rate": 5.495700447735572e-06,
"loss": 0.2821,
"step": 202
},
{
"epoch": 0.524547803617571,
"grad_norm": 0.421667218208313,
"learning_rate": 5.450765405560328e-06,
"loss": 0.2984,
"step": 203
},
{
"epoch": 0.5271317829457365,
"grad_norm": 0.3966899514198303,
"learning_rate": 5.405793627637157e-06,
"loss": 0.259,
"step": 204
},
{
"epoch": 0.5297157622739018,
"grad_norm": 0.4205838441848755,
"learning_rate": 5.360788779003082e-06,
"loss": 0.2888,
"step": 205
},
{
"epoch": 0.5322997416020672,
"grad_norm": 0.4325535297393799,
"learning_rate": 5.3157545273902585e-06,
"loss": 0.302,
"step": 206
},
{
"epoch": 0.5348837209302325,
"grad_norm": 0.4171897768974304,
"learning_rate": 5.270694542927089e-06,
"loss": 0.2685,
"step": 207
},
{
"epoch": 0.537467700258398,
"grad_norm": 0.4270216226577759,
"learning_rate": 5.225612497839099e-06,
"loss": 0.2785,
"step": 208
},
{
"epoch": 0.5400516795865633,
"grad_norm": 0.439961314201355,
"learning_rate": 5.180512066149682e-06,
"loss": 0.2916,
"step": 209
},
{
"epoch": 0.5426356589147286,
"grad_norm": 0.42138805985450745,
"learning_rate": 5.1353969233806735e-06,
"loss": 0.2906,
"step": 210
},
{
"epoch": 0.5452196382428941,
"grad_norm": 0.39296743273735046,
"learning_rate": 5.090270746252803e-06,
"loss": 0.2638,
"step": 211
},
{
"epoch": 0.5478036175710594,
"grad_norm": 0.43339210748672485,
"learning_rate": 5.045137212386065e-06,
"loss": 0.2845,
"step": 212
},
{
"epoch": 0.5503875968992248,
"grad_norm": 0.41793346405029297,
"learning_rate": 5e-06,
"loss": 0.2794,
"step": 213
},
{
"epoch": 0.5529715762273901,
"grad_norm": 0.4067362844944,
"learning_rate": 4.954862787613937e-06,
"loss": 0.2834,
"step": 214
},
{
"epoch": 0.5555555555555556,
"grad_norm": 0.4313544034957886,
"learning_rate": 4.909729253747197e-06,
"loss": 0.2786,
"step": 215
},
{
"epoch": 0.5581395348837209,
"grad_norm": 0.422354131937027,
"learning_rate": 4.864603076619329e-06,
"loss": 0.284,
"step": 216
},
{
"epoch": 0.5607235142118863,
"grad_norm": 0.4361294209957123,
"learning_rate": 4.819487933850319e-06,
"loss": 0.3265,
"step": 217
},
{
"epoch": 0.5633074935400517,
"grad_norm": 0.43613091111183167,
"learning_rate": 4.774387502160902e-06,
"loss": 0.2969,
"step": 218
},
{
"epoch": 0.5658914728682171,
"grad_norm": 0.446242094039917,
"learning_rate": 4.729305457072913e-06,
"loss": 0.3051,
"step": 219
},
{
"epoch": 0.5684754521963824,
"grad_norm": 0.42839357256889343,
"learning_rate": 4.684245472609743e-06,
"loss": 0.2851,
"step": 220
},
{
"epoch": 0.5710594315245479,
"grad_norm": 0.41208556294441223,
"learning_rate": 4.6392112209969205e-06,
"loss": 0.2823,
"step": 221
},
{
"epoch": 0.5736434108527132,
"grad_norm": 0.41363725066185,
"learning_rate": 4.594206372362845e-06,
"loss": 0.2668,
"step": 222
},
{
"epoch": 0.5762273901808785,
"grad_norm": 0.40598398447036743,
"learning_rate": 4.549234594439674e-06,
"loss": 0.2757,
"step": 223
},
{
"epoch": 0.5788113695090439,
"grad_norm": 0.39398393034935,
"learning_rate": 4.504299552264428e-06,
"loss": 0.2401,
"step": 224
},
{
"epoch": 0.5813953488372093,
"grad_norm": 0.4146032929420471,
"learning_rate": 4.459404907880293e-06,
"loss": 0.2904,
"step": 225
},
{
"epoch": 0.5839793281653747,
"grad_norm": 0.42441511154174805,
"learning_rate": 4.414554320038179e-06,
"loss": 0.2836,
"step": 226
},
{
"epoch": 0.58656330749354,
"grad_norm": 0.3873770833015442,
"learning_rate": 4.369751443898554e-06,
"loss": 0.2625,
"step": 227
},
{
"epoch": 0.5891472868217055,
"grad_norm": 0.3869360387325287,
"learning_rate": 4.32499993073355e-06,
"loss": 0.2325,
"step": 228
},
{
"epoch": 0.5917312661498708,
"grad_norm": 0.4107780456542969,
"learning_rate": 4.280303427629404e-06,
"loss": 0.2747,
"step": 229
},
{
"epoch": 0.5943152454780362,
"grad_norm": 0.5055181384086609,
"learning_rate": 4.2356655771892355e-06,
"loss": 0.2893,
"step": 230
},
{
"epoch": 0.5968992248062015,
"grad_norm": 0.4263874590396881,
"learning_rate": 4.191090017236177e-06,
"loss": 0.2839,
"step": 231
},
{
"epoch": 0.599483204134367,
"grad_norm": 0.42507773637771606,
"learning_rate": 4.146580380516918e-06,
"loss": 0.2793,
"step": 232
},
{
"epoch": 0.6020671834625323,
"grad_norm": 0.3988296091556549,
"learning_rate": 4.1021402944056415e-06,
"loss": 0.2674,
"step": 233
},
{
"epoch": 0.6046511627906976,
"grad_norm": 0.407911092042923,
"learning_rate": 4.057773380608411e-06,
"loss": 0.2509,
"step": 234
},
{
"epoch": 0.6072351421188631,
"grad_norm": 0.41657814383506775,
"learning_rate": 4.013483254868001e-06,
"loss": 0.2782,
"step": 235
},
{
"epoch": 0.6098191214470284,
"grad_norm": 0.405274897813797,
"learning_rate": 3.969273526669249e-06,
"loss": 0.2565,
"step": 236
},
{
"epoch": 0.6124031007751938,
"grad_norm": 0.4784335196018219,
"learning_rate": 3.92514779894488e-06,
"loss": 0.2989,
"step": 237
},
{
"epoch": 0.6149870801033591,
"grad_norm": 0.3939613997936249,
"learning_rate": 3.881109667781884e-06,
"loss": 0.2695,
"step": 238
},
{
"epoch": 0.6175710594315246,
"grad_norm": 0.4349983036518097,
"learning_rate": 3.8371627221284495e-06,
"loss": 0.2846,
"step": 239
},
{
"epoch": 0.6201550387596899,
"grad_norm": 0.3985432982444763,
"learning_rate": 3.7933105435014727e-06,
"loss": 0.2551,
"step": 240
},
{
"epoch": 0.6227390180878553,
"grad_norm": 0.40800800919532776,
"learning_rate": 3.7495567056946856e-06,
"loss": 0.2758,
"step": 241
},
{
"epoch": 0.6253229974160207,
"grad_norm": 0.4621322453022003,
"learning_rate": 3.705904774487396e-06,
"loss": 0.2921,
"step": 242
},
{
"epoch": 0.627906976744186,
"grad_norm": 0.4144759476184845,
"learning_rate": 3.662358307353897e-06,
"loss": 0.3026,
"step": 243
},
{
"epoch": 0.6304909560723514,
"grad_norm": 0.41925767064094543,
"learning_rate": 3.6189208531735354e-06,
"loss": 0.2799,
"step": 244
},
{
"epoch": 0.6330749354005168,
"grad_norm": 0.4139888882637024,
"learning_rate": 3.5755959519415008e-06,
"loss": 0.2614,
"step": 245
},
{
"epoch": 0.6356589147286822,
"grad_norm": 0.4141432046890259,
"learning_rate": 3.532387134480327e-06,
"loss": 0.2688,
"step": 246
},
{
"epoch": 0.6382428940568475,
"grad_norm": 0.4194762110710144,
"learning_rate": 3.489297922152136e-06,
"loss": 0.2691,
"step": 247
},
{
"epoch": 0.6408268733850129,
"grad_norm": 0.40425029397010803,
"learning_rate": 3.446331826571672e-06,
"loss": 0.2789,
"step": 248
},
{
"epoch": 0.6434108527131783,
"grad_norm": 0.4381207227706909,
"learning_rate": 3.403492349320101e-06,
"loss": 0.3129,
"step": 249
},
{
"epoch": 0.6459948320413437,
"grad_norm": 0.43057993054389954,
"learning_rate": 3.360782981659659e-06,
"loss": 0.2628,
"step": 250
},
{
"epoch": 0.648578811369509,
"grad_norm": 0.4394291043281555,
"learning_rate": 3.3182072042491244e-06,
"loss": 0.3008,
"step": 251
},
{
"epoch": 0.6511627906976745,
"grad_norm": 0.4196249544620514,
"learning_rate": 3.275768486860149e-06,
"loss": 0.2747,
"step": 252
},
{
"epoch": 0.6537467700258398,
"grad_norm": 0.4204075336456299,
"learning_rate": 3.233470288094489e-06,
"loss": 0.2829,
"step": 253
},
{
"epoch": 0.6563307493540051,
"grad_norm": 0.42610615491867065,
"learning_rate": 3.191316055102146e-06,
"loss": 0.2727,
"step": 254
},
{
"epoch": 0.6589147286821705,
"grad_norm": 0.3784283697605133,
"learning_rate": 3.149309223300428e-06,
"loss": 0.2468,
"step": 255
},
{
"epoch": 0.661498708010336,
"grad_norm": 0.4189954698085785,
"learning_rate": 3.107453216093985e-06,
"loss": 0.2679,
"step": 256
},
{
"epoch": 0.6640826873385013,
"grad_norm": 0.41831427812576294,
"learning_rate": 3.0657514445958055e-06,
"loss": 0.2754,
"step": 257
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.4036039113998413,
"learning_rate": 3.0242073073492238e-06,
"loss": 0.2767,
"step": 258
},
{
"epoch": 0.6692506459948321,
"grad_norm": 0.4252059757709503,
"learning_rate": 2.982824190050958e-06,
"loss": 0.292,
"step": 259
},
{
"epoch": 0.6718346253229974,
"grad_norm": 0.3725378215312958,
"learning_rate": 2.9416054652751834e-06,
"loss": 0.2427,
"step": 260
},
{
"epoch": 0.6744186046511628,
"grad_norm": 0.38230738043785095,
"learning_rate": 2.9005544921986774e-06,
"loss": 0.2686,
"step": 261
},
{
"epoch": 0.6770025839793282,
"grad_norm": 0.42745351791381836,
"learning_rate": 2.8596746163270646e-06,
"loss": 0.2448,
"step": 262
},
{
"epoch": 0.6795865633074936,
"grad_norm": 0.46798622608184814,
"learning_rate": 2.8189691692221627e-06,
"loss": 0.2981,
"step": 263
},
{
"epoch": 0.6821705426356589,
"grad_norm": 0.4152715504169464,
"learning_rate": 2.778441468230483e-06,
"loss": 0.2807,
"step": 264
},
{
"epoch": 0.6847545219638242,
"grad_norm": 0.4589405953884125,
"learning_rate": 2.738094816212866e-06,
"loss": 0.2782,
"step": 265
},
{
"epoch": 0.6873385012919897,
"grad_norm": 0.42450419068336487,
"learning_rate": 2.6979325012753214e-06,
"loss": 0.2996,
"step": 266
},
{
"epoch": 0.689922480620155,
"grad_norm": 0.40908730030059814,
"learning_rate": 2.65795779650105e-06,
"loss": 0.261,
"step": 267
},
{
"epoch": 0.6925064599483204,
"grad_norm": 0.4043743908405304,
"learning_rate": 2.6181739596837075e-06,
"loss": 0.2554,
"step": 268
},
{
"epoch": 0.6950904392764858,
"grad_norm": 0.43334946036338806,
"learning_rate": 2.5785842330619038e-06,
"loss": 0.2795,
"step": 269
},
{
"epoch": 0.6976744186046512,
"grad_norm": 0.4369620382785797,
"learning_rate": 2.5391918430549635e-06,
"loss": 0.2758,
"step": 270
},
{
"epoch": 0.7002583979328165,
"grad_norm": 0.35578539967536926,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.2338,
"step": 271
},
{
"epoch": 0.7028423772609819,
"grad_norm": 0.42097681760787964,
"learning_rate": 2.4610118978902732e-06,
"loss": 0.269,
"step": 272
},
{
"epoch": 0.7054263565891473,
"grad_norm": 0.42444154620170593,
"learning_rate": 2.422230714114891e-06,
"loss": 0.2574,
"step": 273
},
{
"epoch": 0.7080103359173127,
"grad_norm": 0.38183045387268066,
"learning_rate": 2.383659609199873e-06,
"loss": 0.2469,
"step": 274
},
{
"epoch": 0.710594315245478,
"grad_norm": 0.4213600754737854,
"learning_rate": 2.345301726550567e-06,
"loss": 0.2707,
"step": 275
},
{
"epoch": 0.7131782945736435,
"grad_norm": 0.3678889870643616,
"learning_rate": 2.3071601921954797e-06,
"loss": 0.2418,
"step": 276
},
{
"epoch": 0.7157622739018088,
"grad_norm": 0.42480871081352234,
"learning_rate": 2.269238114531515e-06,
"loss": 0.2828,
"step": 277
},
{
"epoch": 0.7183462532299741,
"grad_norm": 0.4046178162097931,
"learning_rate": 2.2315385840706548e-06,
"loss": 0.2779,
"step": 278
},
{
"epoch": 0.7209302325581395,
"grad_norm": 0.3712913393974304,
"learning_rate": 2.1940646731880887e-06,
"loss": 0.2454,
"step": 279
},
{
"epoch": 0.7235142118863049,
"grad_norm": 0.40826621651649475,
"learning_rate": 2.156819435871824e-06,
"loss": 0.2714,
"step": 280
},
{
"epoch": 0.7260981912144703,
"grad_norm": 0.40158697962760925,
"learning_rate": 2.1198059074738027e-06,
"loss": 0.2769,
"step": 281
},
{
"epoch": 0.7286821705426356,
"grad_norm": 0.41186589002609253,
"learning_rate": 2.08302710446253e-06,
"loss": 0.2681,
"step": 282
},
{
"epoch": 0.7312661498708011,
"grad_norm": 0.39115414023399353,
"learning_rate": 2.0464860241772454e-06,
"loss": 0.264,
"step": 283
},
{
"epoch": 0.7338501291989664,
"grad_norm": 0.410695880651474,
"learning_rate": 2.010185644583641e-06,
"loss": 0.2725,
"step": 284
},
{
"epoch": 0.7364341085271318,
"grad_norm": 0.43781405687332153,
"learning_rate": 1.9741289240311757e-06,
"loss": 0.2886,
"step": 285
},
{
"epoch": 0.7390180878552972,
"grad_norm": 0.4308369755744934,
"learning_rate": 1.9383188010119818e-06,
"loss": 0.3076,
"step": 286
},
{
"epoch": 0.7416020671834626,
"grad_norm": 0.45121103525161743,
"learning_rate": 1.9027581939213852e-06,
"loss": 0.307,
"step": 287
},
{
"epoch": 0.7441860465116279,
"grad_norm": 0.41774290800094604,
"learning_rate": 1.8674500008200675e-06,
"loss": 0.2747,
"step": 288
},
{
"epoch": 0.7467700258397932,
"grad_norm": 0.41470867395401,
"learning_rate": 1.8323970991978823e-06,
"loss": 0.2719,
"step": 289
},
{
"epoch": 0.7493540051679587,
"grad_norm": 0.40178781747817993,
"learning_rate": 1.797602345739352e-06,
"loss": 0.2608,
"step": 290
},
{
"epoch": 0.751937984496124,
"grad_norm": 0.39378994703292847,
"learning_rate": 1.7630685760908623e-06,
"loss": 0.2766,
"step": 291
},
{
"epoch": 0.7545219638242894,
"grad_norm": 0.41441816091537476,
"learning_rate": 1.7287986046295597e-06,
"loss": 0.2732,
"step": 292
},
{
"epoch": 0.7571059431524548,
"grad_norm": 0.3627479672431946,
"learning_rate": 1.6947952242339993e-06,
"loss": 0.2413,
"step": 293
},
{
"epoch": 0.7596899224806202,
"grad_norm": 0.4463461935520172,
"learning_rate": 1.6610612060565235e-06,
"loss": 0.3035,
"step": 294
},
{
"epoch": 0.7622739018087855,
"grad_norm": 0.440087229013443,
"learning_rate": 1.627599299297431e-06,
"loss": 0.2831,
"step": 295
},
{
"epoch": 0.7648578811369509,
"grad_norm": 0.4249372184276581,
"learning_rate": 1.594412230980928e-06,
"loss": 0.2747,
"step": 296
},
{
"epoch": 0.7674418604651163,
"grad_norm": 0.391125351190567,
"learning_rate": 1.561502705732883e-06,
"loss": 0.2726,
"step": 297
},
{
"epoch": 0.7700258397932817,
"grad_norm": 0.4350535571575165,
"learning_rate": 1.5288734055604087e-06,
"loss": 0.2881,
"step": 298
},
{
"epoch": 0.772609819121447,
"grad_norm": 0.43538013100624084,
"learning_rate": 1.4965269896332884e-06,
"loss": 0.2733,
"step": 299
},
{
"epoch": 0.7751937984496124,
"grad_norm": 0.4050742983818054,
"learning_rate": 1.4644660940672628e-06,
"loss": 0.2633,
"step": 300
},
{
"epoch": 0.7777777777777778,
"grad_norm": 0.40997040271759033,
"learning_rate": 1.4326933317092e-06,
"loss": 0.2671,
"step": 301
},
{
"epoch": 0.7803617571059431,
"grad_norm": 0.3840159475803375,
"learning_rate": 1.4012112919241562e-06,
"loss": 0.2583,
"step": 302
},
{
"epoch": 0.7829457364341085,
"grad_norm": 0.3878195285797119,
"learning_rate": 1.370022540384347e-06,
"loss": 0.26,
"step": 303
},
{
"epoch": 0.7855297157622739,
"grad_norm": 0.4388813376426697,
"learning_rate": 1.3391296188600594e-06,
"loss": 0.2583,
"step": 304
},
{
"epoch": 0.7881136950904393,
"grad_norm": 0.37653830647468567,
"learning_rate": 1.3085350450125073e-06,
"loss": 0.2679,
"step": 305
},
{
"epoch": 0.7906976744186046,
"grad_norm": 0.3878933787345886,
"learning_rate": 1.2782413121886483e-06,
"loss": 0.2369,
"step": 306
},
{
"epoch": 0.7932816537467701,
"grad_norm": 0.38015350699424744,
"learning_rate": 1.2482508892179884e-06,
"loss": 0.2476,
"step": 307
},
{
"epoch": 0.7958656330749354,
"grad_norm": 0.4102688133716583,
"learning_rate": 1.2185662202113764e-06,
"loss": 0.259,
"step": 308
},
{
"epoch": 0.7984496124031008,
"grad_norm": 0.3736209273338318,
"learning_rate": 1.1891897243618184e-06,
"loss": 0.244,
"step": 309
},
{
"epoch": 0.8010335917312662,
"grad_norm": 0.4116411805152893,
"learning_rate": 1.16012379574733e-06,
"loss": 0.2687,
"step": 310
},
{
"epoch": 0.8036175710594315,
"grad_norm": 0.47300201654434204,
"learning_rate": 1.1313708031358183e-06,
"loss": 0.2728,
"step": 311
},
{
"epoch": 0.8062015503875969,
"grad_norm": 0.4103212058544159,
"learning_rate": 1.102933089792042e-06,
"loss": 0.2764,
"step": 312
},
{
"epoch": 0.8087855297157622,
"grad_norm": 0.37040975689888,
"learning_rate": 1.0748129732866391e-06,
"loss": 0.2318,
"step": 313
},
{
"epoch": 0.8113695090439277,
"grad_norm": 0.3986849784851074,
"learning_rate": 1.047012745307255e-06,
"loss": 0.2741,
"step": 314
},
{
"epoch": 0.813953488372093,
"grad_norm": 0.3630805015563965,
"learning_rate": 1.0195346714717813e-06,
"loss": 0.2413,
"step": 315
},
{
"epoch": 0.8165374677002584,
"grad_norm": 0.38989007472991943,
"learning_rate": 9.92380991143712e-07,
"loss": 0.2628,
"step": 316
},
{
"epoch": 0.8191214470284238,
"grad_norm": 0.4112791121006012,
"learning_rate": 9.65553917249648e-07,
"loss": 0.2768,
"step": 317
},
{
"epoch": 0.8217054263565892,
"grad_norm": 0.40445297956466675,
"learning_rate": 9.39055636098945e-07,
"loss": 0.2775,
"step": 318
},
{
"epoch": 0.8242894056847545,
"grad_norm": 0.3824197053909302,
"learning_rate": 9.128883072055411e-07,
"loss": 0.2357,
"step": 319
},
{
"epoch": 0.8268733850129198,
"grad_norm": 0.4150390028953552,
"learning_rate": 8.870540631119667e-07,
"loss": 0.2779,
"step": 320
},
{
"epoch": 0.8294573643410853,
"grad_norm": 0.38705989718437195,
"learning_rate": 8.615550092155478e-07,
"loss": 0.2584,
"step": 321
},
{
"epoch": 0.8320413436692506,
"grad_norm": 0.41040337085723877,
"learning_rate": 8.363932235968198e-07,
"loss": 0.29,
"step": 322
},
{
"epoch": 0.834625322997416,
"grad_norm": 0.4016845226287842,
"learning_rate": 8.115707568501768e-07,
"loss": 0.2502,
"step": 323
},
{
"epoch": 0.8372093023255814,
"grad_norm": 0.3633503317832947,
"learning_rate": 7.870896319167548e-07,
"loss": 0.2431,
"step": 324
},
{
"epoch": 0.8397932816537468,
"grad_norm": 0.43767327070236206,
"learning_rate": 7.629518439195671e-07,
"loss": 0.3077,
"step": 325
},
{
"epoch": 0.8423772609819121,
"grad_norm": 0.4164217412471771,
"learning_rate": 7.391593600009123e-07,
"loss": 0.2841,
"step": 326
},
{
"epoch": 0.8449612403100775,
"grad_norm": 0.381540983915329,
"learning_rate": 7.157141191620548e-07,
"loss": 0.2473,
"step": 327
},
{
"epoch": 0.8475452196382429,
"grad_norm": 0.45407700538635254,
"learning_rate": 6.926180321052045e-07,
"loss": 0.2833,
"step": 328
},
{
"epoch": 0.8501291989664083,
"grad_norm": 0.38916081190109253,
"learning_rate": 6.698729810778065e-07,
"loss": 0.2719,
"step": 329
},
{
"epoch": 0.8527131782945736,
"grad_norm": 0.43010246753692627,
"learning_rate": 6.474808197191401e-07,
"loss": 0.2714,
"step": 330
},
{
"epoch": 0.8552971576227391,
"grad_norm": 0.38088157773017883,
"learning_rate": 6.254433729092518e-07,
"loss": 0.242,
"step": 331
},
{
"epoch": 0.8578811369509044,
"grad_norm": 0.42933011054992676,
"learning_rate": 6.037624366202405e-07,
"loss": 0.2735,
"step": 332
},
{
"epoch": 0.8604651162790697,
"grad_norm": 0.42603251338005066,
"learning_rate": 5.824397777698859e-07,
"loss": 0.2743,
"step": 333
},
{
"epoch": 0.8630490956072352,
"grad_norm": 0.39108431339263916,
"learning_rate": 5.614771340776559e-07,
"loss": 0.2728,
"step": 334
},
{
"epoch": 0.8656330749354005,
"grad_norm": 0.3757094442844391,
"learning_rate": 5.408762139230889e-07,
"loss": 0.2446,
"step": 335
},
{
"epoch": 0.8682170542635659,
"grad_norm": 0.4124755561351776,
"learning_rate": 5.206386962065601e-07,
"loss": 0.2682,
"step": 336
},
{
"epoch": 0.8708010335917312,
"grad_norm": 0.42066821455955505,
"learning_rate": 5.007662302124671e-07,
"loss": 0.2878,
"step": 337
},
{
"epoch": 0.8733850129198967,
"grad_norm": 0.4132254421710968,
"learning_rate": 4.812604354748107e-07,
"loss": 0.2693,
"step": 338
},
{
"epoch": 0.875968992248062,
"grad_norm": 0.4205566346645355,
"learning_rate": 4.6212290164521554e-07,
"loss": 0.2695,
"step": 339
},
{
"epoch": 0.8785529715762274,
"grad_norm": 0.4251742660999298,
"learning_rate": 4.433551883633719e-07,
"loss": 0.2784,
"step": 340
},
{
"epoch": 0.8811369509043928,
"grad_norm": 0.4145876169204712,
"learning_rate": 4.2495882512993913e-07,
"loss": 0.2778,
"step": 341
},
{
"epoch": 0.8837209302325582,
"grad_norm": 0.3994285762310028,
"learning_rate": 4.069353111818913e-07,
"loss": 0.2647,
"step": 342
},
{
"epoch": 0.8863049095607235,
"grad_norm": 0.42055121064186096,
"learning_rate": 3.8928611537033424e-07,
"loss": 0.256,
"step": 343
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.4389072358608246,
"learning_rate": 3.7201267604080436e-07,
"loss": 0.2858,
"step": 344
},
{
"epoch": 0.8914728682170543,
"grad_norm": 0.4421055018901825,
"learning_rate": 3.5511640091604293e-07,
"loss": 0.2671,
"step": 345
},
{
"epoch": 0.8940568475452196,
"grad_norm": 0.42173531651496887,
"learning_rate": 3.385986669812769e-07,
"loss": 0.2771,
"step": 346
},
{
"epoch": 0.896640826873385,
"grad_norm": 0.4103642702102661,
"learning_rate": 3.224608203719953e-07,
"loss": 0.2517,
"step": 347
},
{
"epoch": 0.8992248062015504,
"grad_norm": 0.39951303601264954,
"learning_rate": 3.067041762642475e-07,
"loss": 0.2616,
"step": 348
},
{
"epoch": 0.9018087855297158,
"grad_norm": 0.39229103922843933,
"learning_rate": 2.9133001876746004e-07,
"loss": 0.2629,
"step": 349
},
{
"epoch": 0.9043927648578811,
"grad_norm": 0.41716843843460083,
"learning_rate": 2.763396008197833e-07,
"loss": 0.2856,
"step": 350
},
{
"epoch": 0.9069767441860465,
"grad_norm": 0.38193899393081665,
"learning_rate": 2.617341440859883e-07,
"loss": 0.2436,
"step": 351
},
{
"epoch": 0.9095607235142119,
"grad_norm": 0.3895181715488434,
"learning_rate": 2.475148388578974e-07,
"loss": 0.2363,
"step": 352
},
{
"epoch": 0.9121447028423773,
"grad_norm": 0.3759653866291046,
"learning_rate": 2.3368284395738684e-07,
"loss": 0.2544,
"step": 353
},
{
"epoch": 0.9147286821705426,
"grad_norm": 0.40008825063705444,
"learning_rate": 2.2023928664194229e-07,
"loss": 0.2724,
"step": 354
},
{
"epoch": 0.917312661498708,
"grad_norm": 0.39400628209114075,
"learning_rate": 2.0718526251279346e-07,
"loss": 0.2397,
"step": 355
},
{
"epoch": 0.9198966408268734,
"grad_norm": 0.3940667510032654,
"learning_rate": 1.9452183542562785e-07,
"loss": 0.2546,
"step": 356
},
{
"epoch": 0.9224806201550387,
"grad_norm": 0.393248587846756,
"learning_rate": 1.8225003740388546e-07,
"loss": 0.2657,
"step": 357
},
{
"epoch": 0.9250645994832042,
"grad_norm": 0.3825235962867737,
"learning_rate": 1.7037086855465902e-07,
"loss": 0.2429,
"step": 358
},
{
"epoch": 0.9276485788113695,
"grad_norm": 0.38378632068634033,
"learning_rate": 1.5888529698718347e-07,
"loss": 0.2416,
"step": 359
},
{
"epoch": 0.9302325581395349,
"grad_norm": 0.3894941806793213,
"learning_rate": 1.477942587339426e-07,
"loss": 0.2568,
"step": 360
},
{
"epoch": 0.9328165374677002,
"grad_norm": 0.44816529750823975,
"learning_rate": 1.3709865767438434e-07,
"loss": 0.2892,
"step": 361
},
{
"epoch": 0.9354005167958657,
"grad_norm": 0.3683631718158722,
"learning_rate": 1.2679936546125483e-07,
"loss": 0.2477,
"step": 362
},
{
"epoch": 0.937984496124031,
"grad_norm": 0.4054432809352875,
"learning_rate": 1.1689722144956672e-07,
"loss": 0.263,
"step": 363
},
{
"epoch": 0.9405684754521964,
"grad_norm": 0.45787227153778076,
"learning_rate": 1.0739303262819301e-07,
"loss": 0.2685,
"step": 364
},
{
"epoch": 0.9431524547803618,
"grad_norm": 0.4092801809310913,
"learning_rate": 9.82875735540989e-08,
"loss": 0.2616,
"step": 365
},
{
"epoch": 0.9457364341085271,
"grad_norm": 0.3954561948776245,
"learning_rate": 8.95815862892202e-08,
"loss": 0.2778,
"step": 366
},
{
"epoch": 0.9483204134366925,
"grad_norm": 0.4244314134120941,
"learning_rate": 8.127578033998663e-08,
"loss": 0.2873,
"step": 367
},
{
"epoch": 0.9509043927648578,
"grad_norm": 0.40788134932518005,
"learning_rate": 7.337083259949918e-08,
"loss": 0.2767,
"step": 368
},
{
"epoch": 0.9534883720930233,
"grad_norm": 0.40445661544799805,
"learning_rate": 6.58673872923693e-08,
"loss": 0.2561,
"step": 369
},
{
"epoch": 0.9560723514211886,
"grad_norm": 0.38080865144729614,
"learning_rate": 5.8766055922211965e-08,
"loss": 0.2562,
"step": 370
},
{
"epoch": 0.958656330749354,
"grad_norm": 0.40840834379196167,
"learning_rate": 5.206741722181385e-08,
"loss": 0.2576,
"step": 371
},
{
"epoch": 0.9612403100775194,
"grad_norm": 0.426565945148468,
"learning_rate": 4.577201710596613e-08,
"loss": 0.2936,
"step": 372
},
{
"epoch": 0.9638242894056848,
"grad_norm": 0.39672496914863586,
"learning_rate": 3.98803686269783e-08,
"loss": 0.2397,
"step": 373
},
{
"epoch": 0.9664082687338501,
"grad_norm": 0.4055837094783783,
"learning_rate": 3.439295193286174e-08,
"loss": 0.2532,
"step": 374
},
{
"epoch": 0.9689922480620154,
"grad_norm": 0.40761086344718933,
"learning_rate": 2.9310214228202016e-08,
"loss": 0.2708,
"step": 375
},
{
"epoch": 0.9715762273901809,
"grad_norm": 0.446036696434021,
"learning_rate": 2.463256973771311e-08,
"loss": 0.277,
"step": 376
},
{
"epoch": 0.9741602067183462,
"grad_norm": 0.40387487411499023,
"learning_rate": 2.0360399672478826e-08,
"loss": 0.2539,
"step": 377
},
{
"epoch": 0.9767441860465116,
"grad_norm": 0.4223725497722626,
"learning_rate": 1.6494052198886557e-08,
"loss": 0.2714,
"step": 378
},
{
"epoch": 0.979328165374677,
"grad_norm": 0.373526006937027,
"learning_rate": 1.3033842410251074e-08,
"loss": 0.2407,
"step": 379
},
{
"epoch": 0.9819121447028424,
"grad_norm": 0.3940108120441437,
"learning_rate": 9.980052301137854e-09,
"loss": 0.2554,
"step": 380
},
{
"epoch": 0.9844961240310077,
"grad_norm": 0.3823840320110321,
"learning_rate": 7.332930744380906e-09,
"loss": 0.2605,
"step": 381
},
{
"epoch": 0.9870801033591732,
"grad_norm": 0.41570064425468445,
"learning_rate": 5.092693470798438e-09,
"loss": 0.2538,
"step": 382
},
{
"epoch": 0.9896640826873385,
"grad_norm": 0.4328196346759796,
"learning_rate": 3.2595230516152543e-09,
"loss": 0.258,
"step": 383
},
{
"epoch": 0.9922480620155039,
"grad_norm": 0.3797440826892853,
"learning_rate": 1.8335688835802169e-09,
"loss": 0.2528,
"step": 384
},
{
"epoch": 0.9948320413436692,
"grad_norm": 0.3894307315349579,
"learning_rate": 8.149471767937567e-10,
"loss": 0.2572,
"step": 385
},
{
"epoch": 0.9974160206718347,
"grad_norm": 0.40216878056526184,
"learning_rate": 2.0374094523600841e-10,
"loss": 0.2686,
"step": 386
},
{
"epoch": 1.0,
"grad_norm": 0.3972252607345581,
"learning_rate": 0.0,
"loss": 0.2752,
"step": 387
},
{
"epoch": 1.0,
"eval_loss": 0.39300352334976196,
"eval_runtime": 1.5284,
"eval_samples_per_second": 150.481,
"eval_steps_per_second": 6.543,
"step": 387
},
{
"epoch": 1.0,
"step": 387,
"total_flos": 3.228374416542925e+16,
"train_loss": 0.37563710938898476,
"train_runtime": 503.7567,
"train_samples_per_second": 36.859,
"train_steps_per_second": 0.768
}
],
"logging_steps": 1,
"max_steps": 387,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 800,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.228374416542925e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}