souging's picture
Training in progress, epoch 0, checkpoint
1e28a0f verified
Raw
History Blame Contribute Delete
86.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.3389830508474576,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006779661016949153,
"grad_norm": 23.002347946166992,
"learning_rate": 2.0000000000000003e-06,
"loss": 9.7716,
"step": 1
},
{
"epoch": 0.0013559322033898306,
"grad_norm": 22.777915954589844,
"learning_rate": 4.000000000000001e-06,
"loss": 9.9392,
"step": 2
},
{
"epoch": 0.002033898305084746,
"grad_norm": 19.260889053344727,
"learning_rate": 6e-06,
"loss": 9.0313,
"step": 3
},
{
"epoch": 0.002711864406779661,
"grad_norm": 19.569047927856445,
"learning_rate": 8.000000000000001e-06,
"loss": 9.5254,
"step": 4
},
{
"epoch": 0.003389830508474576,
"grad_norm": 19.794172286987305,
"learning_rate": 1e-05,
"loss": 9.0274,
"step": 5
},
{
"epoch": 0.004067796610169492,
"grad_norm": 17.149099349975586,
"learning_rate": 1.2e-05,
"loss": 9.0768,
"step": 6
},
{
"epoch": 0.0047457627118644066,
"grad_norm": 14.945192337036133,
"learning_rate": 1.4000000000000001e-05,
"loss": 9.1802,
"step": 7
},
{
"epoch": 0.005423728813559322,
"grad_norm": 18.449960708618164,
"learning_rate": 1.6000000000000003e-05,
"loss": 8.9464,
"step": 8
},
{
"epoch": 0.006101694915254237,
"grad_norm": 24.250812530517578,
"learning_rate": 1.8e-05,
"loss": 8.6232,
"step": 9
},
{
"epoch": 0.006779661016949152,
"grad_norm": 27.281187057495117,
"learning_rate": 2e-05,
"loss": 8.909,
"step": 10
},
{
"epoch": 0.007457627118644068,
"grad_norm": 19.675508499145508,
"learning_rate": 2.2000000000000003e-05,
"loss": 8.5624,
"step": 11
},
{
"epoch": 0.008135593220338983,
"grad_norm": 14.400312423706055,
"learning_rate": 2.4e-05,
"loss": 8.008,
"step": 12
},
{
"epoch": 0.008813559322033898,
"grad_norm": 10.545919418334961,
"learning_rate": 2.6000000000000002e-05,
"loss": 8.0736,
"step": 13
},
{
"epoch": 0.009491525423728813,
"grad_norm": 11.350264549255371,
"learning_rate": 2.8000000000000003e-05,
"loss": 8.0693,
"step": 14
},
{
"epoch": 0.010169491525423728,
"grad_norm": 12.852901458740234,
"learning_rate": 3e-05,
"loss": 7.6522,
"step": 15
},
{
"epoch": 0.010847457627118645,
"grad_norm": 12.827103614807129,
"learning_rate": 3.2000000000000005e-05,
"loss": 7.4653,
"step": 16
},
{
"epoch": 0.01152542372881356,
"grad_norm": 9.765871047973633,
"learning_rate": 3.4000000000000007e-05,
"loss": 7.2956,
"step": 17
},
{
"epoch": 0.012203389830508475,
"grad_norm": 10.082915306091309,
"learning_rate": 3.6e-05,
"loss": 7.2504,
"step": 18
},
{
"epoch": 0.01288135593220339,
"grad_norm": 9.88174819946289,
"learning_rate": 3.8e-05,
"loss": 7.3783,
"step": 19
},
{
"epoch": 0.013559322033898305,
"grad_norm": 8.21225357055664,
"learning_rate": 4e-05,
"loss": 7.0012,
"step": 20
},
{
"epoch": 0.01423728813559322,
"grad_norm": 9.938831329345703,
"learning_rate": 4.2e-05,
"loss": 7.2661,
"step": 21
},
{
"epoch": 0.014915254237288136,
"grad_norm": 7.108133792877197,
"learning_rate": 4.4000000000000006e-05,
"loss": 6.9342,
"step": 22
},
{
"epoch": 0.015593220338983051,
"grad_norm": 9.083900451660156,
"learning_rate": 4.600000000000001e-05,
"loss": 6.741,
"step": 23
},
{
"epoch": 0.016271186440677966,
"grad_norm": 7.797006607055664,
"learning_rate": 4.8e-05,
"loss": 6.616,
"step": 24
},
{
"epoch": 0.01694915254237288,
"grad_norm": 8.14676284790039,
"learning_rate": 5e-05,
"loss": 6.703,
"step": 25
},
{
"epoch": 0.017627118644067796,
"grad_norm": 7.908254623413086,
"learning_rate": 5.2000000000000004e-05,
"loss": 6.9014,
"step": 26
},
{
"epoch": 0.01830508474576271,
"grad_norm": 7.190468788146973,
"learning_rate": 5.4000000000000005e-05,
"loss": 6.7583,
"step": 27
},
{
"epoch": 0.018983050847457626,
"grad_norm": 7.662473201751709,
"learning_rate": 5.6000000000000006e-05,
"loss": 6.8967,
"step": 28
},
{
"epoch": 0.01966101694915254,
"grad_norm": 6.693227291107178,
"learning_rate": 5.8e-05,
"loss": 6.5308,
"step": 29
},
{
"epoch": 0.020338983050847456,
"grad_norm": 8.479073524475098,
"learning_rate": 6e-05,
"loss": 6.6283,
"step": 30
},
{
"epoch": 0.021016949152542375,
"grad_norm": 7.684070587158203,
"learning_rate": 6.2e-05,
"loss": 6.7679,
"step": 31
},
{
"epoch": 0.02169491525423729,
"grad_norm": 6.615173816680908,
"learning_rate": 6.400000000000001e-05,
"loss": 6.6732,
"step": 32
},
{
"epoch": 0.022372881355932205,
"grad_norm": 8.378983497619629,
"learning_rate": 6.6e-05,
"loss": 6.6607,
"step": 33
},
{
"epoch": 0.02305084745762712,
"grad_norm": 6.350676536560059,
"learning_rate": 6.800000000000001e-05,
"loss": 6.6672,
"step": 34
},
{
"epoch": 0.023728813559322035,
"grad_norm": 6.454582214355469,
"learning_rate": 7e-05,
"loss": 6.8824,
"step": 35
},
{
"epoch": 0.02440677966101695,
"grad_norm": 6.217319488525391,
"learning_rate": 7.2e-05,
"loss": 6.5813,
"step": 36
},
{
"epoch": 0.025084745762711864,
"grad_norm": 5.651987075805664,
"learning_rate": 7.4e-05,
"loss": 6.842,
"step": 37
},
{
"epoch": 0.02576271186440678,
"grad_norm": 7.406353950500488,
"learning_rate": 7.6e-05,
"loss": 6.6527,
"step": 38
},
{
"epoch": 0.026440677966101694,
"grad_norm": 5.57485818862915,
"learning_rate": 7.800000000000001e-05,
"loss": 6.771,
"step": 39
},
{
"epoch": 0.02711864406779661,
"grad_norm": 6.6117682456970215,
"learning_rate": 8e-05,
"loss": 6.1066,
"step": 40
},
{
"epoch": 0.027796610169491524,
"grad_norm": 5.126145839691162,
"learning_rate": 8.2e-05,
"loss": 6.5221,
"step": 41
},
{
"epoch": 0.02847457627118644,
"grad_norm": 6.1036224365234375,
"learning_rate": 8.4e-05,
"loss": 6.8725,
"step": 42
},
{
"epoch": 0.029152542372881354,
"grad_norm": 5.15429162979126,
"learning_rate": 8.6e-05,
"loss": 6.716,
"step": 43
},
{
"epoch": 0.029830508474576273,
"grad_norm": 5.755465984344482,
"learning_rate": 8.800000000000001e-05,
"loss": 6.4796,
"step": 44
},
{
"epoch": 0.030508474576271188,
"grad_norm": 5.456299304962158,
"learning_rate": 9e-05,
"loss": 6.5924,
"step": 45
},
{
"epoch": 0.031186440677966103,
"grad_norm": 5.266402721405029,
"learning_rate": 9.200000000000001e-05,
"loss": 6.7563,
"step": 46
},
{
"epoch": 0.031864406779661014,
"grad_norm": 5.692070960998535,
"learning_rate": 9.4e-05,
"loss": 6.6863,
"step": 47
},
{
"epoch": 0.03254237288135593,
"grad_norm": 5.5329437255859375,
"learning_rate": 9.6e-05,
"loss": 6.3942,
"step": 48
},
{
"epoch": 0.033220338983050844,
"grad_norm": 6.364491939544678,
"learning_rate": 9.8e-05,
"loss": 6.6862,
"step": 49
},
{
"epoch": 0.03389830508474576,
"grad_norm": 5.994080543518066,
"learning_rate": 0.0001,
"loss": 6.5349,
"step": 50
},
{
"epoch": 0.03457627118644068,
"grad_norm": 5.3678436279296875,
"learning_rate": 0.00010200000000000001,
"loss": 6.6993,
"step": 51
},
{
"epoch": 0.03525423728813559,
"grad_norm": 6.403738021850586,
"learning_rate": 0.00010400000000000001,
"loss": 6.8351,
"step": 52
},
{
"epoch": 0.03593220338983051,
"grad_norm": 4.906039237976074,
"learning_rate": 0.00010600000000000002,
"loss": 6.2518,
"step": 53
},
{
"epoch": 0.03661016949152542,
"grad_norm": 5.51943302154541,
"learning_rate": 0.00010800000000000001,
"loss": 6.3121,
"step": 54
},
{
"epoch": 0.03728813559322034,
"grad_norm": 5.520563125610352,
"learning_rate": 0.00011000000000000002,
"loss": 6.6873,
"step": 55
},
{
"epoch": 0.03796610169491525,
"grad_norm": 5.560564041137695,
"learning_rate": 0.00011200000000000001,
"loss": 6.3521,
"step": 56
},
{
"epoch": 0.03864406779661017,
"grad_norm": 5.662564277648926,
"learning_rate": 0.00011399999999999999,
"loss": 6.4836,
"step": 57
},
{
"epoch": 0.03932203389830508,
"grad_norm": 5.317500591278076,
"learning_rate": 0.000116,
"loss": 6.6697,
"step": 58
},
{
"epoch": 0.04,
"grad_norm": 5.199156284332275,
"learning_rate": 0.000118,
"loss": 6.5322,
"step": 59
},
{
"epoch": 0.04067796610169491,
"grad_norm": 5.430077075958252,
"learning_rate": 0.00012,
"loss": 6.5479,
"step": 60
},
{
"epoch": 0.04135593220338983,
"grad_norm": 5.413340091705322,
"learning_rate": 0.000122,
"loss": 6.5284,
"step": 61
},
{
"epoch": 0.04203389830508475,
"grad_norm": 5.688055038452148,
"learning_rate": 0.000124,
"loss": 6.3871,
"step": 62
},
{
"epoch": 0.04271186440677966,
"grad_norm": 4.919246196746826,
"learning_rate": 0.000126,
"loss": 6.2397,
"step": 63
},
{
"epoch": 0.04338983050847458,
"grad_norm": 5.281830310821533,
"learning_rate": 0.00012800000000000002,
"loss": 6.5555,
"step": 64
},
{
"epoch": 0.04406779661016949,
"grad_norm": 5.29904317855835,
"learning_rate": 0.00013000000000000002,
"loss": 6.5344,
"step": 65
},
{
"epoch": 0.04474576271186441,
"grad_norm": 4.955327987670898,
"learning_rate": 0.000132,
"loss": 6.3642,
"step": 66
},
{
"epoch": 0.04542372881355932,
"grad_norm": 4.803442478179932,
"learning_rate": 0.000134,
"loss": 6.3102,
"step": 67
},
{
"epoch": 0.04610169491525424,
"grad_norm": 5.19502067565918,
"learning_rate": 0.00013600000000000003,
"loss": 6.6601,
"step": 68
},
{
"epoch": 0.04677966101694915,
"grad_norm": 5.458391189575195,
"learning_rate": 0.000138,
"loss": 6.2998,
"step": 69
},
{
"epoch": 0.04745762711864407,
"grad_norm": 4.660610198974609,
"learning_rate": 0.00014,
"loss": 6.3571,
"step": 70
},
{
"epoch": 0.04813559322033898,
"grad_norm": 5.055753231048584,
"learning_rate": 0.000142,
"loss": 6.4724,
"step": 71
},
{
"epoch": 0.0488135593220339,
"grad_norm": 4.7137041091918945,
"learning_rate": 0.000144,
"loss": 6.2174,
"step": 72
},
{
"epoch": 0.04949152542372881,
"grad_norm": 4.584828853607178,
"learning_rate": 0.000146,
"loss": 6.5231,
"step": 73
},
{
"epoch": 0.05016949152542373,
"grad_norm": 5.140486240386963,
"learning_rate": 0.000148,
"loss": 6.5894,
"step": 74
},
{
"epoch": 0.05084745762711865,
"grad_norm": 4.370701313018799,
"learning_rate": 0.00015000000000000001,
"loss": 6.1671,
"step": 75
},
{
"epoch": 0.05152542372881356,
"grad_norm": 4.74658727645874,
"learning_rate": 0.000152,
"loss": 6.4448,
"step": 76
},
{
"epoch": 0.05220338983050848,
"grad_norm": 4.522503852844238,
"learning_rate": 0.000154,
"loss": 6.1638,
"step": 77
},
{
"epoch": 0.05288135593220339,
"grad_norm": 4.795144557952881,
"learning_rate": 0.00015600000000000002,
"loss": 6.2783,
"step": 78
},
{
"epoch": 0.05355932203389831,
"grad_norm": 5.0294952392578125,
"learning_rate": 0.00015800000000000002,
"loss": 6.6309,
"step": 79
},
{
"epoch": 0.05423728813559322,
"grad_norm": 4.863598346710205,
"learning_rate": 0.00016,
"loss": 6.4011,
"step": 80
},
{
"epoch": 0.05491525423728814,
"grad_norm": 4.773859024047852,
"learning_rate": 0.000162,
"loss": 5.8704,
"step": 81
},
{
"epoch": 0.05559322033898305,
"grad_norm": 4.518772602081299,
"learning_rate": 0.000164,
"loss": 6.3375,
"step": 82
},
{
"epoch": 0.05627118644067797,
"grad_norm": 4.793971061706543,
"learning_rate": 0.000166,
"loss": 6.5121,
"step": 83
},
{
"epoch": 0.05694915254237288,
"grad_norm": 4.927656173706055,
"learning_rate": 0.000168,
"loss": 6.2994,
"step": 84
},
{
"epoch": 0.0576271186440678,
"grad_norm": 4.6142425537109375,
"learning_rate": 0.00017,
"loss": 6.2367,
"step": 85
},
{
"epoch": 0.05830508474576271,
"grad_norm": 5.891679286956787,
"learning_rate": 0.000172,
"loss": 6.5811,
"step": 86
},
{
"epoch": 0.05898305084745763,
"grad_norm": 4.594151496887207,
"learning_rate": 0.000174,
"loss": 6.3963,
"step": 87
},
{
"epoch": 0.059661016949152545,
"grad_norm": 4.939855575561523,
"learning_rate": 0.00017600000000000002,
"loss": 6.1509,
"step": 88
},
{
"epoch": 0.06033898305084746,
"grad_norm": 4.762392520904541,
"learning_rate": 0.00017800000000000002,
"loss": 6.5095,
"step": 89
},
{
"epoch": 0.061016949152542375,
"grad_norm": 4.262040615081787,
"learning_rate": 0.00018,
"loss": 6.477,
"step": 90
},
{
"epoch": 0.06169491525423729,
"grad_norm": 5.843923091888428,
"learning_rate": 0.000182,
"loss": 6.4408,
"step": 91
},
{
"epoch": 0.062372881355932205,
"grad_norm": 4.501123428344727,
"learning_rate": 0.00018400000000000003,
"loss": 6.2459,
"step": 92
},
{
"epoch": 0.06305084745762712,
"grad_norm": 4.2876057624816895,
"learning_rate": 0.00018600000000000002,
"loss": 6.0569,
"step": 93
},
{
"epoch": 0.06372881355932203,
"grad_norm": 4.6542558670043945,
"learning_rate": 0.000188,
"loss": 6.3479,
"step": 94
},
{
"epoch": 0.06440677966101695,
"grad_norm": 6.14705228805542,
"learning_rate": 0.00019,
"loss": 6.3884,
"step": 95
},
{
"epoch": 0.06508474576271187,
"grad_norm": 5.148488998413086,
"learning_rate": 0.000192,
"loss": 6.4866,
"step": 96
},
{
"epoch": 0.06576271186440678,
"grad_norm": 4.671205520629883,
"learning_rate": 0.000194,
"loss": 6.461,
"step": 97
},
{
"epoch": 0.06644067796610169,
"grad_norm": 4.673304080963135,
"learning_rate": 0.000196,
"loss": 6.2204,
"step": 98
},
{
"epoch": 0.0671186440677966,
"grad_norm": 4.501871109008789,
"learning_rate": 0.00019800000000000002,
"loss": 6.2709,
"step": 99
},
{
"epoch": 0.06779661016949153,
"grad_norm": 4.749882698059082,
"learning_rate": 0.0002,
"loss": 6.4241,
"step": 100
},
{
"epoch": 0.06847457627118644,
"grad_norm": 4.940063953399658,
"learning_rate": 0.00019999691576447898,
"loss": 6.3946,
"step": 101
},
{
"epoch": 0.06915254237288136,
"grad_norm": 4.987453460693359,
"learning_rate": 0.00019998766324816607,
"loss": 6.769,
"step": 102
},
{
"epoch": 0.06983050847457627,
"grad_norm": 4.208788871765137,
"learning_rate": 0.00019997224302180006,
"loss": 6.3744,
"step": 103
},
{
"epoch": 0.07050847457627119,
"grad_norm": 4.716567039489746,
"learning_rate": 0.00019995065603657316,
"loss": 5.9775,
"step": 104
},
{
"epoch": 0.0711864406779661,
"grad_norm": 4.53123140335083,
"learning_rate": 0.0001999229036240723,
"loss": 6.2904,
"step": 105
},
{
"epoch": 0.07186440677966102,
"grad_norm": 5.139428615570068,
"learning_rate": 0.00019988898749619702,
"loss": 6.1856,
"step": 106
},
{
"epoch": 0.07254237288135593,
"grad_norm": 4.759083271026611,
"learning_rate": 0.00019984890974505381,
"loss": 6.3847,
"step": 107
},
{
"epoch": 0.07322033898305084,
"grad_norm": 4.986558437347412,
"learning_rate": 0.00019980267284282717,
"loss": 6.2453,
"step": 108
},
{
"epoch": 0.07389830508474576,
"grad_norm": 4.802744388580322,
"learning_rate": 0.00019975027964162702,
"loss": 6.0677,
"step": 109
},
{
"epoch": 0.07457627118644068,
"grad_norm": 4.860638618469238,
"learning_rate": 0.0001996917333733128,
"loss": 6.4106,
"step": 110
},
{
"epoch": 0.07525423728813559,
"grad_norm": 4.956095218658447,
"learning_rate": 0.00019962703764929413,
"loss": 6.34,
"step": 111
},
{
"epoch": 0.0759322033898305,
"grad_norm": 4.707270622253418,
"learning_rate": 0.00019955619646030802,
"loss": 6.0478,
"step": 112
},
{
"epoch": 0.07661016949152542,
"grad_norm": 5.431143283843994,
"learning_rate": 0.00019947921417617267,
"loss": 6.3597,
"step": 113
},
{
"epoch": 0.07728813559322034,
"grad_norm": 4.946473121643066,
"learning_rate": 0.000199396095545518,
"loss": 5.796,
"step": 114
},
{
"epoch": 0.07796610169491526,
"grad_norm": 5.105308532714844,
"learning_rate": 0.00019930684569549264,
"loss": 6.4113,
"step": 115
},
{
"epoch": 0.07864406779661016,
"grad_norm": 5.422460556030273,
"learning_rate": 0.0001992114701314478,
"loss": 6.459,
"step": 116
},
{
"epoch": 0.07932203389830508,
"grad_norm": 4.75588321685791,
"learning_rate": 0.0001991099747365975,
"loss": 5.9358,
"step": 117
},
{
"epoch": 0.08,
"grad_norm": 5.012182712554932,
"learning_rate": 0.00019900236577165576,
"loss": 6.2463,
"step": 118
},
{
"epoch": 0.08067796610169492,
"grad_norm": 5.4908223152160645,
"learning_rate": 0.0001988886498744505,
"loss": 6.6087,
"step": 119
},
{
"epoch": 0.08135593220338982,
"grad_norm": 4.770055294036865,
"learning_rate": 0.00019876883405951377,
"loss": 6.1849,
"step": 120
},
{
"epoch": 0.08203389830508474,
"grad_norm": 5.126617431640625,
"learning_rate": 0.00019864292571764955,
"loss": 5.9254,
"step": 121
},
{
"epoch": 0.08271186440677966,
"grad_norm": 5.1747002601623535,
"learning_rate": 0.0001985109326154774,
"loss": 6.7117,
"step": 122
},
{
"epoch": 0.08338983050847458,
"grad_norm": 4.939129829406738,
"learning_rate": 0.00019837286289495361,
"loss": 6.3142,
"step": 123
},
{
"epoch": 0.0840677966101695,
"grad_norm": 4.76216459274292,
"learning_rate": 0.0001982287250728689,
"loss": 6.5198,
"step": 124
},
{
"epoch": 0.0847457627118644,
"grad_norm": 4.859055519104004,
"learning_rate": 0.00019807852804032305,
"loss": 6.2479,
"step": 125
},
{
"epoch": 0.08542372881355932,
"grad_norm": 4.679764270782471,
"learning_rate": 0.00019792228106217658,
"loss": 6.3733,
"step": 126
},
{
"epoch": 0.08610169491525424,
"grad_norm": 4.5518798828125,
"learning_rate": 0.0001977599937764791,
"loss": 6.2992,
"step": 127
},
{
"epoch": 0.08677966101694916,
"grad_norm": 5.031368255615234,
"learning_rate": 0.00019759167619387476,
"loss": 6.4611,
"step": 128
},
{
"epoch": 0.08745762711864406,
"grad_norm": 4.4103851318359375,
"learning_rate": 0.00019741733869698495,
"loss": 6.2472,
"step": 129
},
{
"epoch": 0.08813559322033898,
"grad_norm": 4.683863639831543,
"learning_rate": 0.00019723699203976766,
"loss": 6.3004,
"step": 130
},
{
"epoch": 0.0888135593220339,
"grad_norm": 5.239562034606934,
"learning_rate": 0.00019705064734685425,
"loss": 6.4668,
"step": 131
},
{
"epoch": 0.08949152542372882,
"grad_norm": 4.492875099182129,
"learning_rate": 0.0001968583161128631,
"loss": 6.1692,
"step": 132
},
{
"epoch": 0.09016949152542372,
"grad_norm": 5.021076679229736,
"learning_rate": 0.00019666001020169073,
"loss": 6.5165,
"step": 133
},
{
"epoch": 0.09084745762711864,
"grad_norm": 4.894111633300781,
"learning_rate": 0.00019645574184577982,
"loss": 6.2766,
"step": 134
},
{
"epoch": 0.09152542372881356,
"grad_norm": 5.421933174133301,
"learning_rate": 0.00019624552364536473,
"loss": 6.3515,
"step": 135
},
{
"epoch": 0.09220338983050848,
"grad_norm": 4.519160747528076,
"learning_rate": 0.0001960293685676943,
"loss": 6.2316,
"step": 136
},
{
"epoch": 0.0928813559322034,
"grad_norm": 5.342835426330566,
"learning_rate": 0.00019580728994623195,
"loss": 6.3037,
"step": 137
},
{
"epoch": 0.0935593220338983,
"grad_norm": 5.112016677856445,
"learning_rate": 0.00019557930147983302,
"loss": 6.6776,
"step": 138
},
{
"epoch": 0.09423728813559322,
"grad_norm": 4.4139885902404785,
"learning_rate": 0.0001953454172319001,
"loss": 5.853,
"step": 139
},
{
"epoch": 0.09491525423728814,
"grad_norm": 4.596457481384277,
"learning_rate": 0.00019510565162951537,
"loss": 5.9871,
"step": 140
},
{
"epoch": 0.09559322033898306,
"grad_norm": 4.741262912750244,
"learning_rate": 0.00019486001946255046,
"loss": 6.1821,
"step": 141
},
{
"epoch": 0.09627118644067796,
"grad_norm": 4.936989784240723,
"learning_rate": 0.00019460853588275454,
"loss": 5.8616,
"step": 142
},
{
"epoch": 0.09694915254237288,
"grad_norm": 5.334706783294678,
"learning_rate": 0.00019435121640281938,
"loss": 6.346,
"step": 143
},
{
"epoch": 0.0976271186440678,
"grad_norm": 5.411738395690918,
"learning_rate": 0.00019408807689542257,
"loss": 6.4823,
"step": 144
},
{
"epoch": 0.09830508474576272,
"grad_norm": 5.372300148010254,
"learning_rate": 0.00019381913359224842,
"loss": 6.4007,
"step": 145
},
{
"epoch": 0.09898305084745762,
"grad_norm": 5.0469231605529785,
"learning_rate": 0.00019354440308298675,
"loss": 6.1397,
"step": 146
},
{
"epoch": 0.09966101694915254,
"grad_norm": 4.648036956787109,
"learning_rate": 0.00019326390231430942,
"loss": 6.0854,
"step": 147
},
{
"epoch": 0.10033898305084746,
"grad_norm": 4.539030075073242,
"learning_rate": 0.00019297764858882514,
"loss": 6.3843,
"step": 148
},
{
"epoch": 0.10101694915254238,
"grad_norm": 4.90519905090332,
"learning_rate": 0.00019268565956401208,
"loss": 6.23,
"step": 149
},
{
"epoch": 0.1016949152542373,
"grad_norm": 4.798630237579346,
"learning_rate": 0.0001923879532511287,
"loss": 6.0267,
"step": 150
},
{
"epoch": 0.1023728813559322,
"grad_norm": 4.804618835449219,
"learning_rate": 0.00019208454801410266,
"loss": 6.0775,
"step": 151
},
{
"epoch": 0.10305084745762712,
"grad_norm": 5.302704334259033,
"learning_rate": 0.00019177546256839812,
"loss": 6.0585,
"step": 152
},
{
"epoch": 0.10372881355932204,
"grad_norm": 5.225855827331543,
"learning_rate": 0.00019146071597986138,
"loss": 5.7564,
"step": 153
},
{
"epoch": 0.10440677966101695,
"grad_norm": 5.5482497215271,
"learning_rate": 0.00019114032766354453,
"loss": 6.3289,
"step": 154
},
{
"epoch": 0.10508474576271186,
"grad_norm": 5.361143112182617,
"learning_rate": 0.00019081431738250814,
"loss": 6.1316,
"step": 155
},
{
"epoch": 0.10576271186440678,
"grad_norm": 5.750701904296875,
"learning_rate": 0.00019048270524660196,
"loss": 6.0047,
"step": 156
},
{
"epoch": 0.1064406779661017,
"grad_norm": 4.948786735534668,
"learning_rate": 0.00019014551171122457,
"loss": 6.3563,
"step": 157
},
{
"epoch": 0.10711864406779661,
"grad_norm": 5.0279951095581055,
"learning_rate": 0.00018980275757606157,
"loss": 6.5178,
"step": 158
},
{
"epoch": 0.10779661016949152,
"grad_norm": 4.7514328956604,
"learning_rate": 0.0001894544639838025,
"loss": 6.324,
"step": 159
},
{
"epoch": 0.10847457627118644,
"grad_norm": 6.772828102111816,
"learning_rate": 0.0001891006524188368,
"loss": 6.2511,
"step": 160
},
{
"epoch": 0.10915254237288136,
"grad_norm": 5.096282958984375,
"learning_rate": 0.00018874134470592835,
"loss": 6.4203,
"step": 161
},
{
"epoch": 0.10983050847457627,
"grad_norm": 5.466090679168701,
"learning_rate": 0.00018837656300886937,
"loss": 6.493,
"step": 162
},
{
"epoch": 0.11050847457627119,
"grad_norm": 4.798202037811279,
"learning_rate": 0.00018800632982911322,
"loss": 6.0481,
"step": 163
},
{
"epoch": 0.1111864406779661,
"grad_norm": 5.258927822113037,
"learning_rate": 0.00018763066800438636,
"loss": 6.321,
"step": 164
},
{
"epoch": 0.11186440677966102,
"grad_norm": 4.769421100616455,
"learning_rate": 0.00018724960070727972,
"loss": 6.0992,
"step": 165
},
{
"epoch": 0.11254237288135593,
"grad_norm": 5.010873317718506,
"learning_rate": 0.00018686315144381913,
"loss": 6.1914,
"step": 166
},
{
"epoch": 0.11322033898305085,
"grad_norm": 4.994409561157227,
"learning_rate": 0.0001864713440520155,
"loss": 6.5174,
"step": 167
},
{
"epoch": 0.11389830508474576,
"grad_norm": 5.172726154327393,
"learning_rate": 0.0001860742027003944,
"loss": 6.3372,
"step": 168
},
{
"epoch": 0.11457627118644068,
"grad_norm": 4.9218926429748535,
"learning_rate": 0.00018567175188650498,
"loss": 5.8695,
"step": 169
},
{
"epoch": 0.1152542372881356,
"grad_norm": 5.080742835998535,
"learning_rate": 0.00018526401643540922,
"loss": 6.3184,
"step": 170
},
{
"epoch": 0.11593220338983051,
"grad_norm": 5.230204105377197,
"learning_rate": 0.00018485102149815038,
"loss": 6.2349,
"step": 171
},
{
"epoch": 0.11661016949152542,
"grad_norm": 6.117705821990967,
"learning_rate": 0.00018443279255020152,
"loss": 6.4514,
"step": 172
},
{
"epoch": 0.11728813559322034,
"grad_norm": 5.159461498260498,
"learning_rate": 0.0001840093553898942,
"loss": 6.1726,
"step": 173
},
{
"epoch": 0.11796610169491525,
"grad_norm": 4.630697250366211,
"learning_rate": 0.00018358073613682706,
"loss": 6.1207,
"step": 174
},
{
"epoch": 0.11864406779661017,
"grad_norm": 5.049693584442139,
"learning_rate": 0.00018314696123025454,
"loss": 6.1229,
"step": 175
},
{
"epoch": 0.11932203389830509,
"grad_norm": 5.2024054527282715,
"learning_rate": 0.00018270805742745617,
"loss": 6.1572,
"step": 176
},
{
"epoch": 0.12,
"grad_norm": 4.8713483810424805,
"learning_rate": 0.000182264051802086,
"loss": 5.6644,
"step": 177
},
{
"epoch": 0.12067796610169491,
"grad_norm": 5.3373026847839355,
"learning_rate": 0.00018181497174250236,
"loss": 5.9139,
"step": 178
},
{
"epoch": 0.12135593220338983,
"grad_norm": 5.174800872802734,
"learning_rate": 0.00018136084495007872,
"loss": 6.0723,
"step": 179
},
{
"epoch": 0.12203389830508475,
"grad_norm": 5.144172668457031,
"learning_rate": 0.00018090169943749476,
"loss": 5.9506,
"step": 180
},
{
"epoch": 0.12271186440677966,
"grad_norm": 5.016770362854004,
"learning_rate": 0.00018043756352700846,
"loss": 6.1359,
"step": 181
},
{
"epoch": 0.12338983050847457,
"grad_norm": 4.965948581695557,
"learning_rate": 0.00017996846584870908,
"loss": 5.9799,
"step": 182
},
{
"epoch": 0.12406779661016949,
"grad_norm": 4.926914215087891,
"learning_rate": 0.000179494435338751,
"loss": 6.0858,
"step": 183
},
{
"epoch": 0.12474576271186441,
"grad_norm": 4.776947498321533,
"learning_rate": 0.00017901550123756906,
"loss": 6.2803,
"step": 184
},
{
"epoch": 0.12542372881355932,
"grad_norm": 5.452550888061523,
"learning_rate": 0.00017853169308807448,
"loss": 6.0974,
"step": 185
},
{
"epoch": 0.12610169491525425,
"grad_norm": 4.798600673675537,
"learning_rate": 0.000178043040733833,
"loss": 6.4779,
"step": 186
},
{
"epoch": 0.12677966101694915,
"grad_norm": 6.300480842590332,
"learning_rate": 0.00017754957431722346,
"loss": 5.9342,
"step": 187
},
{
"epoch": 0.12745762711864406,
"grad_norm": 4.676181316375732,
"learning_rate": 0.00017705132427757895,
"loss": 5.692,
"step": 188
},
{
"epoch": 0.128135593220339,
"grad_norm": 5.04424524307251,
"learning_rate": 0.00017654832134930882,
"loss": 5.994,
"step": 189
},
{
"epoch": 0.1288135593220339,
"grad_norm": 5.5914998054504395,
"learning_rate": 0.0001760405965600031,
"loss": 5.9218,
"step": 190
},
{
"epoch": 0.12949152542372883,
"grad_norm": 5.248879432678223,
"learning_rate": 0.00017552818122851838,
"loss": 5.7513,
"step": 191
},
{
"epoch": 0.13016949152542373,
"grad_norm": 5.793510913848877,
"learning_rate": 0.00017501110696304596,
"loss": 6.1747,
"step": 192
},
{
"epoch": 0.13084745762711864,
"grad_norm": 4.834245681762695,
"learning_rate": 0.00017448940565916222,
"loss": 6.2859,
"step": 193
},
{
"epoch": 0.13152542372881357,
"grad_norm": 5.704695701599121,
"learning_rate": 0.000173963109497861,
"loss": 5.851,
"step": 194
},
{
"epoch": 0.13220338983050847,
"grad_norm": 4.992715835571289,
"learning_rate": 0.00017343225094356855,
"loss": 6.4777,
"step": 195
},
{
"epoch": 0.13288135593220338,
"grad_norm": 5.46926736831665,
"learning_rate": 0.00017289686274214118,
"loss": 6.4349,
"step": 196
},
{
"epoch": 0.1335593220338983,
"grad_norm": 5.428121566772461,
"learning_rate": 0.00017235697791884494,
"loss": 6.6623,
"step": 197
},
{
"epoch": 0.1342372881355932,
"grad_norm": 4.84019660949707,
"learning_rate": 0.00017181262977631888,
"loss": 5.947,
"step": 198
},
{
"epoch": 0.13491525423728815,
"grad_norm": 5.079449653625488,
"learning_rate": 0.00017126385189252053,
"loss": 6.4734,
"step": 199
},
{
"epoch": 0.13559322033898305,
"grad_norm": 4.7480244636535645,
"learning_rate": 0.00017071067811865476,
"loss": 5.6252,
"step": 200
},
{
"epoch": 0.13627118644067795,
"grad_norm": 5.020679950714111,
"learning_rate": 0.0001701531425770856,
"loss": 6.0411,
"step": 201
},
{
"epoch": 0.1369491525423729,
"grad_norm": 5.467161655426025,
"learning_rate": 0.00016959127965923142,
"loss": 6.1694,
"step": 202
},
{
"epoch": 0.1376271186440678,
"grad_norm": 5.133565425872803,
"learning_rate": 0.00016902512402344373,
"loss": 5.7361,
"step": 203
},
{
"epoch": 0.13830508474576272,
"grad_norm": 5.7364068031311035,
"learning_rate": 0.00016845471059286887,
"loss": 6.4208,
"step": 204
},
{
"epoch": 0.13898305084745763,
"grad_norm": 5.106006145477295,
"learning_rate": 0.0001678800745532942,
"loss": 6.07,
"step": 205
},
{
"epoch": 0.13966101694915253,
"grad_norm": 5.257018089294434,
"learning_rate": 0.00016730125135097735,
"loss": 6.0624,
"step": 206
},
{
"epoch": 0.14033898305084747,
"grad_norm": 5.442288875579834,
"learning_rate": 0.00016671827669045998,
"loss": 6.2715,
"step": 207
},
{
"epoch": 0.14101694915254237,
"grad_norm": 5.088027477264404,
"learning_rate": 0.00016613118653236518,
"loss": 5.9313,
"step": 208
},
{
"epoch": 0.14169491525423727,
"grad_norm": 5.052608489990234,
"learning_rate": 0.0001655400170911794,
"loss": 6.0811,
"step": 209
},
{
"epoch": 0.1423728813559322,
"grad_norm": 5.035278797149658,
"learning_rate": 0.00016494480483301836,
"loss": 5.7876,
"step": 210
},
{
"epoch": 0.1430508474576271,
"grad_norm": 5.224352836608887,
"learning_rate": 0.0001643455864733779,
"loss": 5.8463,
"step": 211
},
{
"epoch": 0.14372881355932204,
"grad_norm": 4.919455051422119,
"learning_rate": 0.000163742398974869,
"loss": 5.9865,
"step": 212
},
{
"epoch": 0.14440677966101695,
"grad_norm": 5.542516708374023,
"learning_rate": 0.00016313527954493778,
"loss": 6.006,
"step": 213
},
{
"epoch": 0.14508474576271185,
"grad_norm": 5.1170806884765625,
"learning_rate": 0.00016252426563357055,
"loss": 5.7836,
"step": 214
},
{
"epoch": 0.14576271186440679,
"grad_norm": 4.993136405944824,
"learning_rate": 0.00016190939493098344,
"loss": 5.9138,
"step": 215
},
{
"epoch": 0.1464406779661017,
"grad_norm": 5.0120134353637695,
"learning_rate": 0.00016129070536529766,
"loss": 6.3102,
"step": 216
},
{
"epoch": 0.14711864406779662,
"grad_norm": 5.003673076629639,
"learning_rate": 0.00016066823510019998,
"loss": 6.0372,
"step": 217
},
{
"epoch": 0.14779661016949153,
"grad_norm": 5.501419544219971,
"learning_rate": 0.00016004202253258842,
"loss": 5.955,
"step": 218
},
{
"epoch": 0.14847457627118643,
"grad_norm": 5.139267921447754,
"learning_rate": 0.00015941210629020388,
"loss": 6.2234,
"step": 219
},
{
"epoch": 0.14915254237288136,
"grad_norm": 4.98293399810791,
"learning_rate": 0.00015877852522924732,
"loss": 6.2804,
"step": 220
},
{
"epoch": 0.14983050847457627,
"grad_norm": 5.735854625701904,
"learning_rate": 0.00015814131843198308,
"loss": 6.3997,
"step": 221
},
{
"epoch": 0.15050847457627117,
"grad_norm": 5.05024528503418,
"learning_rate": 0.00015750052520432787,
"loss": 5.8383,
"step": 222
},
{
"epoch": 0.1511864406779661,
"grad_norm": 5.492971897125244,
"learning_rate": 0.0001568561850734264,
"loss": 5.9048,
"step": 223
},
{
"epoch": 0.151864406779661,
"grad_norm": 4.997868537902832,
"learning_rate": 0.00015620833778521307,
"loss": 5.9265,
"step": 224
},
{
"epoch": 0.15254237288135594,
"grad_norm": 5.124069690704346,
"learning_rate": 0.00015555702330196023,
"loss": 5.8762,
"step": 225
},
{
"epoch": 0.15322033898305085,
"grad_norm": 5.169366359710693,
"learning_rate": 0.0001549022817998132,
"loss": 6.089,
"step": 226
},
{
"epoch": 0.15389830508474575,
"grad_norm": 5.053045749664307,
"learning_rate": 0.00015424415366631188,
"loss": 6.1325,
"step": 227
},
{
"epoch": 0.15457627118644068,
"grad_norm": 4.839998722076416,
"learning_rate": 0.00015358267949789966,
"loss": 5.6427,
"step": 228
},
{
"epoch": 0.1552542372881356,
"grad_norm": 5.0462188720703125,
"learning_rate": 0.00015291790009741907,
"loss": 5.9041,
"step": 229
},
{
"epoch": 0.15593220338983052,
"grad_norm": 5.20048189163208,
"learning_rate": 0.0001522498564715949,
"loss": 5.8469,
"step": 230
},
{
"epoch": 0.15661016949152542,
"grad_norm": 4.952335357666016,
"learning_rate": 0.00015157858982850475,
"loss": 5.9452,
"step": 231
},
{
"epoch": 0.15728813559322033,
"grad_norm": 4.864283561706543,
"learning_rate": 0.00015090414157503714,
"loss": 5.5529,
"step": 232
},
{
"epoch": 0.15796610169491526,
"grad_norm": 5.3518805503845215,
"learning_rate": 0.00015022655331433727,
"loss": 6.2074,
"step": 233
},
{
"epoch": 0.15864406779661017,
"grad_norm": 5.023462772369385,
"learning_rate": 0.00014954586684324078,
"loss": 6.1686,
"step": 234
},
{
"epoch": 0.15932203389830507,
"grad_norm": 4.920138359069824,
"learning_rate": 0.00014886212414969553,
"loss": 5.7356,
"step": 235
},
{
"epoch": 0.16,
"grad_norm": 4.807256698608398,
"learning_rate": 0.00014817536741017152,
"loss": 5.9261,
"step": 236
},
{
"epoch": 0.1606779661016949,
"grad_norm": 5.198086738586426,
"learning_rate": 0.00014748563898705946,
"loss": 6.2649,
"step": 237
},
{
"epoch": 0.16135593220338984,
"grad_norm": 5.742856979370117,
"learning_rate": 0.00014679298142605734,
"loss": 6.3636,
"step": 238
},
{
"epoch": 0.16203389830508474,
"grad_norm": 5.001709461212158,
"learning_rate": 0.00014609743745354624,
"loss": 5.8704,
"step": 239
},
{
"epoch": 0.16271186440677965,
"grad_norm": 4.839583873748779,
"learning_rate": 0.00014539904997395468,
"loss": 5.8693,
"step": 240
},
{
"epoch": 0.16338983050847458,
"grad_norm": 5.401934623718262,
"learning_rate": 0.00014469786206711214,
"loss": 5.8424,
"step": 241
},
{
"epoch": 0.1640677966101695,
"grad_norm": 5.6193742752075195,
"learning_rate": 0.00014399391698559152,
"loss": 5.739,
"step": 242
},
{
"epoch": 0.16474576271186442,
"grad_norm": 5.3960113525390625,
"learning_rate": 0.00014328725815204144,
"loss": 5.6365,
"step": 243
},
{
"epoch": 0.16542372881355932,
"grad_norm": 5.593850135803223,
"learning_rate": 0.00014257792915650728,
"loss": 5.9272,
"step": 244
},
{
"epoch": 0.16610169491525423,
"grad_norm": 5.487994194030762,
"learning_rate": 0.0001418659737537428,
"loss": 5.9545,
"step": 245
},
{
"epoch": 0.16677966101694916,
"grad_norm": 5.606075763702393,
"learning_rate": 0.00014115143586051088,
"loss": 5.9499,
"step": 246
},
{
"epoch": 0.16745762711864406,
"grad_norm": 4.903677463531494,
"learning_rate": 0.00014043435955287452,
"loss": 5.8177,
"step": 247
},
{
"epoch": 0.168135593220339,
"grad_norm": 5.0607075691223145,
"learning_rate": 0.00013971478906347806,
"loss": 5.7957,
"step": 248
},
{
"epoch": 0.1688135593220339,
"grad_norm": 5.3411712646484375,
"learning_rate": 0.00013899276877881884,
"loss": 5.7592,
"step": 249
},
{
"epoch": 0.1694915254237288,
"grad_norm": 4.852824687957764,
"learning_rate": 0.000138268343236509,
"loss": 5.9809,
"step": 250
},
{
"epoch": 0.17016949152542374,
"grad_norm": 5.161794662475586,
"learning_rate": 0.00013754155712252832,
"loss": 6.1598,
"step": 251
},
{
"epoch": 0.17084745762711864,
"grad_norm": 5.486487865447998,
"learning_rate": 0.00013681245526846783,
"loss": 6.0534,
"step": 252
},
{
"epoch": 0.17152542372881355,
"grad_norm": 5.071621417999268,
"learning_rate": 0.0001360810826487642,
"loss": 5.7017,
"step": 253
},
{
"epoch": 0.17220338983050848,
"grad_norm": 5.624743461608887,
"learning_rate": 0.00013534748437792573,
"loss": 6.1016,
"step": 254
},
{
"epoch": 0.17288135593220338,
"grad_norm": 5.243331432342529,
"learning_rate": 0.0001346117057077493,
"loss": 6.0871,
"step": 255
},
{
"epoch": 0.17355932203389832,
"grad_norm": 5.0800676345825195,
"learning_rate": 0.00013387379202452917,
"loss": 5.7192,
"step": 256
},
{
"epoch": 0.17423728813559322,
"grad_norm": 5.550308704376221,
"learning_rate": 0.0001331337888462571,
"loss": 6.1076,
"step": 257
},
{
"epoch": 0.17491525423728813,
"grad_norm": 4.588940620422363,
"learning_rate": 0.00013239174181981495,
"loss": 5.7483,
"step": 258
},
{
"epoch": 0.17559322033898306,
"grad_norm": 4.923100471496582,
"learning_rate": 0.00013164769671815862,
"loss": 5.896,
"step": 259
},
{
"epoch": 0.17627118644067796,
"grad_norm": 4.9847869873046875,
"learning_rate": 0.00013090169943749476,
"loss": 5.849,
"step": 260
},
{
"epoch": 0.1769491525423729,
"grad_norm": 5.453402996063232,
"learning_rate": 0.00013015379599444957,
"loss": 6.2982,
"step": 261
},
{
"epoch": 0.1776271186440678,
"grad_norm": 4.822309494018555,
"learning_rate": 0.0001294040325232304,
"loss": 5.8829,
"step": 262
},
{
"epoch": 0.1783050847457627,
"grad_norm": 5.658265590667725,
"learning_rate": 0.00012865245527277986,
"loss": 6.1517,
"step": 263
},
{
"epoch": 0.17898305084745764,
"grad_norm": 5.287138938903809,
"learning_rate": 0.00012789911060392294,
"loss": 5.734,
"step": 264
},
{
"epoch": 0.17966101694915254,
"grad_norm": 5.047686576843262,
"learning_rate": 0.00012714404498650743,
"loss": 6.0721,
"step": 265
},
{
"epoch": 0.18033898305084745,
"grad_norm": 5.461929798126221,
"learning_rate": 0.0001263873049965373,
"loss": 5.9866,
"step": 266
},
{
"epoch": 0.18101694915254238,
"grad_norm": 5.072149276733398,
"learning_rate": 0.00012562893731329967,
"loss": 5.8339,
"step": 267
},
{
"epoch": 0.18169491525423728,
"grad_norm": 5.105294704437256,
"learning_rate": 0.0001248689887164855,
"loss": 6.0138,
"step": 268
},
{
"epoch": 0.18237288135593221,
"grad_norm": 5.0447096824646,
"learning_rate": 0.00012410750608330388,
"loss": 6.1863,
"step": 269
},
{
"epoch": 0.18305084745762712,
"grad_norm": 5.030888557434082,
"learning_rate": 0.00012334453638559057,
"loss": 5.7278,
"step": 270
},
{
"epoch": 0.18372881355932202,
"grad_norm": 5.871072292327881,
"learning_rate": 0.0001225801266869104,
"loss": 5.7478,
"step": 271
},
{
"epoch": 0.18440677966101696,
"grad_norm": 5.490414619445801,
"learning_rate": 0.00012181432413965428,
"loss": 5.9,
"step": 272
},
{
"epoch": 0.18508474576271186,
"grad_norm": 8.317123413085938,
"learning_rate": 0.00012104717598213056,
"loss": 5.8373,
"step": 273
},
{
"epoch": 0.1857627118644068,
"grad_norm": 5.147652626037598,
"learning_rate": 0.00012027872953565125,
"loss": 5.8758,
"step": 274
},
{
"epoch": 0.1864406779661017,
"grad_norm": 5.846799850463867,
"learning_rate": 0.00011950903220161285,
"loss": 5.8581,
"step": 275
},
{
"epoch": 0.1871186440677966,
"grad_norm": 5.395052433013916,
"learning_rate": 0.00011873813145857249,
"loss": 5.9107,
"step": 276
},
{
"epoch": 0.18779661016949153,
"grad_norm": 5.438141345977783,
"learning_rate": 0.00011796607485931928,
"loss": 5.9882,
"step": 277
},
{
"epoch": 0.18847457627118644,
"grad_norm": 5.343430042266846,
"learning_rate": 0.00011719291002794096,
"loss": 5.8695,
"step": 278
},
{
"epoch": 0.18915254237288134,
"grad_norm": 5.369635105133057,
"learning_rate": 0.0001164186846568863,
"loss": 5.6414,
"step": 279
},
{
"epoch": 0.18983050847457628,
"grad_norm": 4.9964375495910645,
"learning_rate": 0.0001156434465040231,
"loss": 5.6538,
"step": 280
},
{
"epoch": 0.19050847457627118,
"grad_norm": 5.169989585876465,
"learning_rate": 0.00011486724338969232,
"loss": 5.8451,
"step": 281
},
{
"epoch": 0.1911864406779661,
"grad_norm": 5.625612258911133,
"learning_rate": 0.00011409012319375827,
"loss": 6.2101,
"step": 282
},
{
"epoch": 0.19186440677966102,
"grad_norm": 5.7747344970703125,
"learning_rate": 0.00011331213385265524,
"loss": 5.9105,
"step": 283
},
{
"epoch": 0.19254237288135592,
"grad_norm": 5.748979091644287,
"learning_rate": 0.00011253332335643043,
"loss": 5.7059,
"step": 284
},
{
"epoch": 0.19322033898305085,
"grad_norm": 5.487430095672607,
"learning_rate": 0.00011175373974578378,
"loss": 5.5471,
"step": 285
},
{
"epoch": 0.19389830508474576,
"grad_norm": 5.194690704345703,
"learning_rate": 0.00011097343110910452,
"loss": 5.8633,
"step": 286
},
{
"epoch": 0.1945762711864407,
"grad_norm": 5.309774398803711,
"learning_rate": 0.000110192445579505,
"loss": 6.1561,
"step": 287
},
{
"epoch": 0.1952542372881356,
"grad_norm": 5.074641704559326,
"learning_rate": 0.00010941083133185146,
"loss": 5.5088,
"step": 288
},
{
"epoch": 0.1959322033898305,
"grad_norm": 5.381385326385498,
"learning_rate": 0.00010862863657979237,
"loss": 5.4756,
"step": 289
},
{
"epoch": 0.19661016949152543,
"grad_norm": 5.016583442687988,
"learning_rate": 0.0001078459095727845,
"loss": 5.6684,
"step": 290
},
{
"epoch": 0.19728813559322034,
"grad_norm": 5.347949981689453,
"learning_rate": 0.00010706269859311669,
"loss": 6.1365,
"step": 291
},
{
"epoch": 0.19796610169491524,
"grad_norm": 4.940281867980957,
"learning_rate": 0.00010627905195293135,
"loss": 5.8259,
"step": 292
},
{
"epoch": 0.19864406779661017,
"grad_norm": 4.891435146331787,
"learning_rate": 0.0001054950179912446,
"loss": 5.8111,
"step": 293
},
{
"epoch": 0.19932203389830508,
"grad_norm": 5.574452877044678,
"learning_rate": 0.00010471064507096426,
"loss": 5.6971,
"step": 294
},
{
"epoch": 0.2,
"grad_norm": 5.2969183921813965,
"learning_rate": 0.00010392598157590688,
"loss": 5.5519,
"step": 295
},
{
"epoch": 0.20067796610169492,
"grad_norm": 5.546970844268799,
"learning_rate": 0.00010314107590781284,
"loss": 5.8701,
"step": 296
},
{
"epoch": 0.20135593220338982,
"grad_norm": 5.5944695472717285,
"learning_rate": 0.00010235597648336104,
"loss": 5.7588,
"step": 297
},
{
"epoch": 0.20203389830508475,
"grad_norm": 5.222428321838379,
"learning_rate": 0.00010157073173118208,
"loss": 6.02,
"step": 298
},
{
"epoch": 0.20271186440677966,
"grad_norm": 5.442862510681152,
"learning_rate": 0.00010078539008887114,
"loss": 5.922,
"step": 299
},
{
"epoch": 0.2033898305084746,
"grad_norm": 5.367995738983154,
"learning_rate": 0.0001,
"loss": 6.0455,
"step": 300
},
{
"epoch": 0.2040677966101695,
"grad_norm": 5.291725158691406,
"learning_rate": 9.921460991112891e-05,
"loss": 5.8758,
"step": 301
},
{
"epoch": 0.2047457627118644,
"grad_norm": 5.123097896575928,
"learning_rate": 9.842926826881796e-05,
"loss": 5.6799,
"step": 302
},
{
"epoch": 0.20542372881355933,
"grad_norm": 4.956916332244873,
"learning_rate": 9.764402351663901e-05,
"loss": 5.5279,
"step": 303
},
{
"epoch": 0.20610169491525424,
"grad_norm": 5.0795392990112305,
"learning_rate": 9.685892409218717e-05,
"loss": 5.5645,
"step": 304
},
{
"epoch": 0.20677966101694914,
"grad_norm": 5.748232841491699,
"learning_rate": 9.607401842409317e-05,
"loss": 6.0103,
"step": 305
},
{
"epoch": 0.20745762711864407,
"grad_norm": 5.127262115478516,
"learning_rate": 9.528935492903575e-05,
"loss": 5.7528,
"step": 306
},
{
"epoch": 0.20813559322033898,
"grad_norm": 5.199704647064209,
"learning_rate": 9.450498200875546e-05,
"loss": 5.7107,
"step": 307
},
{
"epoch": 0.2088135593220339,
"grad_norm": 5.631073474884033,
"learning_rate": 9.372094804706867e-05,
"loss": 5.2502,
"step": 308
},
{
"epoch": 0.2094915254237288,
"grad_norm": 5.47221565246582,
"learning_rate": 9.293730140688336e-05,
"loss": 5.9423,
"step": 309
},
{
"epoch": 0.21016949152542372,
"grad_norm": 5.291194915771484,
"learning_rate": 9.215409042721552e-05,
"loss": 5.4936,
"step": 310
},
{
"epoch": 0.21084745762711865,
"grad_norm": 6.0206193923950195,
"learning_rate": 9.137136342020768e-05,
"loss": 5.8952,
"step": 311
},
{
"epoch": 0.21152542372881356,
"grad_norm": 5.855842113494873,
"learning_rate": 9.058916866814858e-05,
"loss": 6.0302,
"step": 312
},
{
"epoch": 0.2122033898305085,
"grad_norm": 5.3791279792785645,
"learning_rate": 8.980755442049502e-05,
"loss": 5.8662,
"step": 313
},
{
"epoch": 0.2128813559322034,
"grad_norm": 5.692892074584961,
"learning_rate": 8.902656889089548e-05,
"loss": 6.1698,
"step": 314
},
{
"epoch": 0.2135593220338983,
"grad_norm": 5.510669231414795,
"learning_rate": 8.824626025421626e-05,
"loss": 5.7629,
"step": 315
},
{
"epoch": 0.21423728813559323,
"grad_norm": 6.722097873687744,
"learning_rate": 8.746667664356956e-05,
"loss": 5.9961,
"step": 316
},
{
"epoch": 0.21491525423728813,
"grad_norm": 5.199115753173828,
"learning_rate": 8.668786614734478e-05,
"loss": 5.3831,
"step": 317
},
{
"epoch": 0.21559322033898304,
"grad_norm": 5.564209938049316,
"learning_rate": 8.590987680624174e-05,
"loss": 5.7547,
"step": 318
},
{
"epoch": 0.21627118644067797,
"grad_norm": 5.0240068435668945,
"learning_rate": 8.51327566103077e-05,
"loss": 5.6938,
"step": 319
},
{
"epoch": 0.21694915254237288,
"grad_norm": 5.5108137130737305,
"learning_rate": 8.435655349597689e-05,
"loss": 5.6034,
"step": 320
},
{
"epoch": 0.2176271186440678,
"grad_norm": 5.678736686706543,
"learning_rate": 8.358131534311372e-05,
"loss": 5.7397,
"step": 321
},
{
"epoch": 0.2183050847457627,
"grad_norm": 5.272124767303467,
"learning_rate": 8.280708997205904e-05,
"loss": 5.5856,
"step": 322
},
{
"epoch": 0.21898305084745762,
"grad_norm": 5.846488952636719,
"learning_rate": 8.203392514068074e-05,
"loss": 5.7099,
"step": 323
},
{
"epoch": 0.21966101694915255,
"grad_norm": 5.6002631187438965,
"learning_rate": 8.126186854142752e-05,
"loss": 6.0163,
"step": 324
},
{
"epoch": 0.22033898305084745,
"grad_norm": 5.317785739898682,
"learning_rate": 8.049096779838719e-05,
"loss": 5.6488,
"step": 325
},
{
"epoch": 0.22101694915254239,
"grad_norm": 5.817031383514404,
"learning_rate": 7.972127046434878e-05,
"loss": 5.9647,
"step": 326
},
{
"epoch": 0.2216949152542373,
"grad_norm": 5.460287094116211,
"learning_rate": 7.895282401786945e-05,
"loss": 5.5276,
"step": 327
},
{
"epoch": 0.2223728813559322,
"grad_norm": 5.143774509429932,
"learning_rate": 7.818567586034577e-05,
"loss": 5.942,
"step": 328
},
{
"epoch": 0.22305084745762713,
"grad_norm": 5.42582893371582,
"learning_rate": 7.741987331308964e-05,
"loss": 5.8206,
"step": 329
},
{
"epoch": 0.22372881355932203,
"grad_norm": 5.489831447601318,
"learning_rate": 7.66554636144095e-05,
"loss": 5.9051,
"step": 330
},
{
"epoch": 0.22440677966101694,
"grad_norm": 5.278120040893555,
"learning_rate": 7.589249391669616e-05,
"loss": 5.6335,
"step": 331
},
{
"epoch": 0.22508474576271187,
"grad_norm": 5.30599308013916,
"learning_rate": 7.513101128351454e-05,
"loss": 5.828,
"step": 332
},
{
"epoch": 0.22576271186440677,
"grad_norm": 5.318668842315674,
"learning_rate": 7.437106268670034e-05,
"loss": 5.7997,
"step": 333
},
{
"epoch": 0.2264406779661017,
"grad_norm": 5.23081636428833,
"learning_rate": 7.361269500346274e-05,
"loss": 5.3156,
"step": 334
},
{
"epoch": 0.2271186440677966,
"grad_norm": 5.351925849914551,
"learning_rate": 7.285595501349258e-05,
"loss": 6.1906,
"step": 335
},
{
"epoch": 0.22779661016949151,
"grad_norm": 5.411080360412598,
"learning_rate": 7.210088939607708e-05,
"loss": 5.6178,
"step": 336
},
{
"epoch": 0.22847457627118645,
"grad_norm": 4.98875617980957,
"learning_rate": 7.134754472722017e-05,
"loss": 5.5609,
"step": 337
},
{
"epoch": 0.22915254237288135,
"grad_norm": 5.774802207946777,
"learning_rate": 7.059596747676962e-05,
"loss": 5.8021,
"step": 338
},
{
"epoch": 0.22983050847457628,
"grad_norm": 5.243258953094482,
"learning_rate": 6.984620400555044e-05,
"loss": 5.3282,
"step": 339
},
{
"epoch": 0.2305084745762712,
"grad_norm": 4.958450794219971,
"learning_rate": 6.909830056250527e-05,
"loss": 5.3944,
"step": 340
},
{
"epoch": 0.2311864406779661,
"grad_norm": 5.597701549530029,
"learning_rate": 6.835230328184138e-05,
"loss": 5.4275,
"step": 341
},
{
"epoch": 0.23186440677966103,
"grad_norm": 5.59750509262085,
"learning_rate": 6.760825818018508e-05,
"loss": 5.8666,
"step": 342
},
{
"epoch": 0.23254237288135593,
"grad_norm": 6.007476806640625,
"learning_rate": 6.68662111537429e-05,
"loss": 5.6547,
"step": 343
},
{
"epoch": 0.23322033898305083,
"grad_norm": 5.207009315490723,
"learning_rate": 6.612620797547087e-05,
"loss": 5.4279,
"step": 344
},
{
"epoch": 0.23389830508474577,
"grad_norm": 5.5680389404296875,
"learning_rate": 6.538829429225069e-05,
"loss": 5.3114,
"step": 345
},
{
"epoch": 0.23457627118644067,
"grad_norm": 5.515926837921143,
"learning_rate": 6.465251562207431e-05,
"loss": 5.6996,
"step": 346
},
{
"epoch": 0.2352542372881356,
"grad_norm": 5.626382827758789,
"learning_rate": 6.391891735123582e-05,
"loss": 6.0254,
"step": 347
},
{
"epoch": 0.2359322033898305,
"grad_norm": 5.397551536560059,
"learning_rate": 6.318754473153221e-05,
"loss": 5.368,
"step": 348
},
{
"epoch": 0.2366101694915254,
"grad_norm": 5.405299663543701,
"learning_rate": 6.245844287747168e-05,
"loss": 5.1728,
"step": 349
},
{
"epoch": 0.23728813559322035,
"grad_norm": 5.230056285858154,
"learning_rate": 6.173165676349103e-05,
"loss": 5.5227,
"step": 350
},
{
"epoch": 0.23796610169491525,
"grad_norm": 5.585433483123779,
"learning_rate": 6.1007231221181206e-05,
"loss": 5.8477,
"step": 351
},
{
"epoch": 0.23864406779661018,
"grad_norm": 5.70974588394165,
"learning_rate": 6.0285210936521955e-05,
"loss": 5.7222,
"step": 352
},
{
"epoch": 0.2393220338983051,
"grad_norm": 5.623781681060791,
"learning_rate": 5.956564044712551e-05,
"loss": 5.4821,
"step": 353
},
{
"epoch": 0.24,
"grad_norm": 5.539468288421631,
"learning_rate": 5.884856413948913e-05,
"loss": 5.2843,
"step": 354
},
{
"epoch": 0.24067796610169492,
"grad_norm": 5.467306613922119,
"learning_rate": 5.8134026246257225e-05,
"loss": 5.4843,
"step": 355
},
{
"epoch": 0.24135593220338983,
"grad_norm": 5.998471736907959,
"learning_rate": 5.7422070843492734e-05,
"loss": 5.7297,
"step": 356
},
{
"epoch": 0.24203389830508473,
"grad_norm": 5.730869293212891,
"learning_rate": 5.671274184795865e-05,
"loss": 5.4708,
"step": 357
},
{
"epoch": 0.24271186440677966,
"grad_norm": 6.254504203796387,
"learning_rate": 5.6006083014408484e-05,
"loss": 5.5472,
"step": 358
},
{
"epoch": 0.24338983050847457,
"grad_norm": 5.713361740112305,
"learning_rate": 5.53021379328879e-05,
"loss": 5.4419,
"step": 359
},
{
"epoch": 0.2440677966101695,
"grad_norm": 5.973865032196045,
"learning_rate": 5.4600950026045326e-05,
"loss": 5.6945,
"step": 360
},
{
"epoch": 0.2447457627118644,
"grad_norm": 5.073235034942627,
"learning_rate": 5.390256254645378e-05,
"loss": 5.1762,
"step": 361
},
{
"epoch": 0.2454237288135593,
"grad_norm": 5.638620376586914,
"learning_rate": 5.320701857394268e-05,
"loss": 5.9491,
"step": 362
},
{
"epoch": 0.24610169491525424,
"grad_norm": 5.932898998260498,
"learning_rate": 5.251436101294056e-05,
"loss": 5.8446,
"step": 363
},
{
"epoch": 0.24677966101694915,
"grad_norm": 5.434826850891113,
"learning_rate": 5.182463258982846e-05,
"loss": 5.5691,
"step": 364
},
{
"epoch": 0.24745762711864408,
"grad_norm": 5.914247035980225,
"learning_rate": 5.113787585030454e-05,
"loss": 5.5884,
"step": 365
},
{
"epoch": 0.24813559322033898,
"grad_norm": 5.391599178314209,
"learning_rate": 5.045413315675924e-05,
"loss": 5.5539,
"step": 366
},
{
"epoch": 0.2488135593220339,
"grad_norm": 5.657290458679199,
"learning_rate": 4.977344668566275e-05,
"loss": 5.8106,
"step": 367
},
{
"epoch": 0.24949152542372882,
"grad_norm": 5.725247383117676,
"learning_rate": 4.909585842496287e-05,
"loss": 5.7574,
"step": 368
},
{
"epoch": 0.2501694915254237,
"grad_norm": 5.543122291564941,
"learning_rate": 4.842141017149526e-05,
"loss": 5.5064,
"step": 369
},
{
"epoch": 0.25084745762711863,
"grad_norm": 5.4209303855896,
"learning_rate": 4.7750143528405126e-05,
"loss": 5.5809,
"step": 370
},
{
"epoch": 0.25152542372881354,
"grad_norm": 5.547783374786377,
"learning_rate": 4.708209990258095e-05,
"loss": 5.4158,
"step": 371
},
{
"epoch": 0.2522033898305085,
"grad_norm": 5.520477294921875,
"learning_rate": 4.6417320502100316e-05,
"loss": 5.5091,
"step": 372
},
{
"epoch": 0.2528813559322034,
"grad_norm": 5.4549970626831055,
"learning_rate": 4.575584633368815e-05,
"loss": 5.3763,
"step": 373
},
{
"epoch": 0.2535593220338983,
"grad_norm": 6.0628814697265625,
"learning_rate": 4.5097718200186814e-05,
"loss": 5.8492,
"step": 374
},
{
"epoch": 0.2542372881355932,
"grad_norm": 5.97998046875,
"learning_rate": 4.444297669803981e-05,
"loss": 5.608,
"step": 375
},
{
"epoch": 0.2549152542372881,
"grad_norm": 5.170746326446533,
"learning_rate": 4.379166221478697e-05,
"loss": 5.5551,
"step": 376
},
{
"epoch": 0.2555932203389831,
"grad_norm": 5.509799480438232,
"learning_rate": 4.31438149265736e-05,
"loss": 5.6183,
"step": 377
},
{
"epoch": 0.256271186440678,
"grad_norm": 5.532557487487793,
"learning_rate": 4.249947479567218e-05,
"loss": 5.6561,
"step": 378
},
{
"epoch": 0.2569491525423729,
"grad_norm": 5.654819488525391,
"learning_rate": 4.185868156801694e-05,
"loss": 5.9242,
"step": 379
},
{
"epoch": 0.2576271186440678,
"grad_norm": 5.431266784667969,
"learning_rate": 4.12214747707527e-05,
"loss": 5.2671,
"step": 380
},
{
"epoch": 0.2583050847457627,
"grad_norm": 5.76847505569458,
"learning_rate": 4.058789370979615e-05,
"loss": 5.6203,
"step": 381
},
{
"epoch": 0.25898305084745765,
"grad_norm": 5.608331203460693,
"learning_rate": 3.9957977467411615e-05,
"loss": 5.2894,
"step": 382
},
{
"epoch": 0.25966101694915256,
"grad_norm": 5.352730751037598,
"learning_rate": 3.933176489980005e-05,
"loss": 5.7837,
"step": 383
},
{
"epoch": 0.26033898305084746,
"grad_norm": 5.750943183898926,
"learning_rate": 3.8709294634702376e-05,
"loss": 6.0277,
"step": 384
},
{
"epoch": 0.26101694915254237,
"grad_norm": 6.469532489776611,
"learning_rate": 3.8090605069016595e-05,
"loss": 5.6117,
"step": 385
},
{
"epoch": 0.26169491525423727,
"grad_norm": 5.662360668182373,
"learning_rate": 3.747573436642951e-05,
"loss": 5.4094,
"step": 386
},
{
"epoch": 0.26237288135593223,
"grad_norm": 5.911714553833008,
"learning_rate": 3.686472045506223e-05,
"loss": 5.4519,
"step": 387
},
{
"epoch": 0.26305084745762713,
"grad_norm": 5.62433385848999,
"learning_rate": 3.6257601025131026e-05,
"loss": 5.6033,
"step": 388
},
{
"epoch": 0.26372881355932204,
"grad_norm": 5.5420966148376465,
"learning_rate": 3.565441352662211e-05,
"loss": 5.665,
"step": 389
},
{
"epoch": 0.26440677966101694,
"grad_norm": 5.550889015197754,
"learning_rate": 3.5055195166981645e-05,
"loss": 5.7331,
"step": 390
},
{
"epoch": 0.26508474576271185,
"grad_norm": 6.002449989318848,
"learning_rate": 3.445998290882062e-05,
"loss": 5.6414,
"step": 391
},
{
"epoch": 0.26576271186440675,
"grad_norm": 6.255985736846924,
"learning_rate": 3.386881346763483e-05,
"loss": 5.7452,
"step": 392
},
{
"epoch": 0.2664406779661017,
"grad_norm": 5.7584919929504395,
"learning_rate": 3.328172330954001e-05,
"loss": 5.4645,
"step": 393
},
{
"epoch": 0.2671186440677966,
"grad_norm": 5.411556243896484,
"learning_rate": 3.269874864902269e-05,
"loss": 5.5256,
"step": 394
},
{
"epoch": 0.2677966101694915,
"grad_norm": 5.638591289520264,
"learning_rate": 3.211992544670582e-05,
"loss": 5.5345,
"step": 395
},
{
"epoch": 0.2684745762711864,
"grad_norm": 5.49556303024292,
"learning_rate": 3.154528940713113e-05,
"loss": 5.7834,
"step": 396
},
{
"epoch": 0.26915254237288133,
"grad_norm": 5.54540491104126,
"learning_rate": 3.0974875976556284e-05,
"loss": 5.6866,
"step": 397
},
{
"epoch": 0.2698305084745763,
"grad_norm": 5.196211338043213,
"learning_rate": 3.0408720340768572e-05,
"loss": 5.2216,
"step": 398
},
{
"epoch": 0.2705084745762712,
"grad_norm": 5.35925817489624,
"learning_rate": 2.9846857422914433e-05,
"loss": 5.1594,
"step": 399
},
{
"epoch": 0.2711864406779661,
"grad_norm": 5.4410080909729,
"learning_rate": 2.9289321881345254e-05,
"loss": 5.819,
"step": 400
},
{
"epoch": 0.271864406779661,
"grad_norm": 5.762651443481445,
"learning_rate": 2.8736148107479467e-05,
"loss": 5.4804,
"step": 401
},
{
"epoch": 0.2725423728813559,
"grad_norm": 5.4722981452941895,
"learning_rate": 2.8187370223681132e-05,
"loss": 5.5458,
"step": 402
},
{
"epoch": 0.27322033898305087,
"grad_norm": 5.910475730895996,
"learning_rate": 2.764302208115508e-05,
"loss": 5.732,
"step": 403
},
{
"epoch": 0.2738983050847458,
"grad_norm": 5.407331943511963,
"learning_rate": 2.7103137257858868e-05,
"loss": 5.4342,
"step": 404
},
{
"epoch": 0.2745762711864407,
"grad_norm": 5.824403285980225,
"learning_rate": 2.6567749056431467e-05,
"loss": 5.581,
"step": 405
},
{
"epoch": 0.2752542372881356,
"grad_norm": 5.7097086906433105,
"learning_rate": 2.603689050213902e-05,
"loss": 5.6796,
"step": 406
},
{
"epoch": 0.2759322033898305,
"grad_norm": 6.071976661682129,
"learning_rate": 2.5510594340837824e-05,
"loss": 5.1967,
"step": 407
},
{
"epoch": 0.27661016949152545,
"grad_norm": 5.329769611358643,
"learning_rate": 2.4988893036954043e-05,
"loss": 5.5662,
"step": 408
},
{
"epoch": 0.27728813559322035,
"grad_norm": 5.527679443359375,
"learning_rate": 2.4471818771481648e-05,
"loss": 5.362,
"step": 409
},
{
"epoch": 0.27796610169491526,
"grad_norm": 5.589406490325928,
"learning_rate": 2.3959403439996907e-05,
"loss": 5.1217,
"step": 410
},
{
"epoch": 0.27864406779661016,
"grad_norm": 5.69094181060791,
"learning_rate": 2.34516786506912e-05,
"loss": 5.4005,
"step": 411
},
{
"epoch": 0.27932203389830507,
"grad_norm": 5.374352931976318,
"learning_rate": 2.2948675722421086e-05,
"loss": 5.6702,
"step": 412
},
{
"epoch": 0.28,
"grad_norm": 5.293539524078369,
"learning_rate": 2.2450425682776565e-05,
"loss": 5.4775,
"step": 413
},
{
"epoch": 0.28067796610169493,
"grad_norm": 5.905485153198242,
"learning_rate": 2.195695926616702e-05,
"loss": 5.5452,
"step": 414
},
{
"epoch": 0.28135593220338984,
"grad_norm": 5.549497604370117,
"learning_rate": 2.146830691192553e-05,
"loss": 5.3305,
"step": 415
},
{
"epoch": 0.28203389830508474,
"grad_norm": 5.897935390472412,
"learning_rate": 2.098449876243096e-05,
"loss": 5.6255,
"step": 416
},
{
"epoch": 0.28271186440677964,
"grad_norm": 5.720310688018799,
"learning_rate": 2.0505564661249e-05,
"loss": 5.4534,
"step": 417
},
{
"epoch": 0.28338983050847455,
"grad_norm": 5.820013999938965,
"learning_rate": 2.0031534151290943e-05,
"loss": 5.3081,
"step": 418
},
{
"epoch": 0.2840677966101695,
"grad_norm": 6.240899085998535,
"learning_rate": 1.9562436472991552e-05,
"loss": 5.9156,
"step": 419
},
{
"epoch": 0.2847457627118644,
"grad_norm": 5.758796215057373,
"learning_rate": 1.9098300562505266e-05,
"loss": 5.4116,
"step": 420
},
{
"epoch": 0.2854237288135593,
"grad_norm": 6.092564105987549,
"learning_rate": 1.863915504992131e-05,
"loss": 5.7903,
"step": 421
},
{
"epoch": 0.2861016949152542,
"grad_norm": 5.848187446594238,
"learning_rate": 1.818502825749764e-05,
"loss": 5.5823,
"step": 422
},
{
"epoch": 0.28677966101694913,
"grad_norm": 5.051366329193115,
"learning_rate": 1.773594819791403e-05,
"loss": 5.274,
"step": 423
},
{
"epoch": 0.2874576271186441,
"grad_norm": 5.7866129875183105,
"learning_rate": 1.7291942572543807e-05,
"loss": 5.6109,
"step": 424
},
{
"epoch": 0.288135593220339,
"grad_norm": 6.054172515869141,
"learning_rate": 1.6853038769745467e-05,
"loss": 5.5136,
"step": 425
},
{
"epoch": 0.2888135593220339,
"grad_norm": 5.935192108154297,
"learning_rate": 1.6419263863172997e-05,
"loss": 5.6772,
"step": 426
},
{
"epoch": 0.2894915254237288,
"grad_norm": 5.998628616333008,
"learning_rate": 1.599064461010581e-05,
"loss": 5.8913,
"step": 427
},
{
"epoch": 0.2901694915254237,
"grad_norm": 5.500387191772461,
"learning_rate": 1.5567207449798515e-05,
"loss": 5.4011,
"step": 428
},
{
"epoch": 0.29084745762711867,
"grad_norm": 5.5121660232543945,
"learning_rate": 1.5148978501849642e-05,
"loss": 5.4678,
"step": 429
},
{
"epoch": 0.29152542372881357,
"grad_norm": 5.580468654632568,
"learning_rate": 1.4735983564590783e-05,
"loss": 5.3353,
"step": 430
},
{
"epoch": 0.2922033898305085,
"grad_norm": 5.571037292480469,
"learning_rate": 1.4328248113495047e-05,
"loss": 5.3953,
"step": 431
},
{
"epoch": 0.2928813559322034,
"grad_norm": 5.397740364074707,
"learning_rate": 1.3925797299605647e-05,
"loss": 5.223,
"step": 432
},
{
"epoch": 0.2935593220338983,
"grad_norm": 6.440202713012695,
"learning_rate": 1.3528655947984504e-05,
"loss": 5.9279,
"step": 433
},
{
"epoch": 0.29423728813559324,
"grad_norm": 5.653568267822266,
"learning_rate": 1.3136848556180892e-05,
"loss": 5.4896,
"step": 434
},
{
"epoch": 0.29491525423728815,
"grad_norm": 5.772056579589844,
"learning_rate": 1.2750399292720283e-05,
"loss": 5.3452,
"step": 435
},
{
"epoch": 0.29559322033898305,
"grad_norm": 5.690596580505371,
"learning_rate": 1.2369331995613665e-05,
"loss": 5.1033,
"step": 436
},
{
"epoch": 0.29627118644067796,
"grad_norm": 5.667556285858154,
"learning_rate": 1.1993670170886806e-05,
"loss": 5.4504,
"step": 437
},
{
"epoch": 0.29694915254237286,
"grad_norm": 6.178337097167969,
"learning_rate": 1.1623436991130654e-05,
"loss": 5.7523,
"step": 438
},
{
"epoch": 0.2976271186440678,
"grad_norm": 5.961308479309082,
"learning_rate": 1.1258655294071685e-05,
"loss": 5.887,
"step": 439
},
{
"epoch": 0.2983050847457627,
"grad_norm": 6.2464094161987305,
"learning_rate": 1.0899347581163221e-05,
"loss": 5.6344,
"step": 440
},
{
"epoch": 0.29898305084745763,
"grad_norm": 5.896814823150635,
"learning_rate": 1.0545536016197499e-05,
"loss": 5.5173,
"step": 441
},
{
"epoch": 0.29966101694915254,
"grad_norm": 6.12027645111084,
"learning_rate": 1.0197242423938446e-05,
"loss": 5.6183,
"step": 442
},
{
"epoch": 0.30033898305084744,
"grad_norm": 6.067883014678955,
"learning_rate": 9.854488288775422e-06,
"loss": 5.7134,
"step": 443
},
{
"epoch": 0.30101694915254235,
"grad_norm": 5.843398571014404,
"learning_rate": 9.517294753398064e-06,
"loss": 5.153,
"step": 444
},
{
"epoch": 0.3016949152542373,
"grad_norm": 5.859512805938721,
"learning_rate": 9.185682617491863e-06,
"loss": 5.4347,
"step": 445
},
{
"epoch": 0.3023728813559322,
"grad_norm": 5.9133524894714355,
"learning_rate": 8.85967233645547e-06,
"loss": 5.333,
"step": 446
},
{
"epoch": 0.3030508474576271,
"grad_norm": 5.7199602127075195,
"learning_rate": 8.539284020138638e-06,
"loss": 5.5811,
"step": 447
},
{
"epoch": 0.303728813559322,
"grad_norm": 5.764463424682617,
"learning_rate": 8.224537431601886e-06,
"loss": 5.1644,
"step": 448
},
{
"epoch": 0.3044067796610169,
"grad_norm": 6.3609771728515625,
"learning_rate": 7.915451985897382e-06,
"loss": 5.8289,
"step": 449
},
{
"epoch": 0.3050847457627119,
"grad_norm": 6.216641902923584,
"learning_rate": 7.612046748871327e-06,
"loss": 5.6793,
"step": 450
},
{
"epoch": 0.3057627118644068,
"grad_norm": 5.693812847137451,
"learning_rate": 7.314340435987921e-06,
"loss": 5.535,
"step": 451
},
{
"epoch": 0.3064406779661017,
"grad_norm": 5.719924449920654,
"learning_rate": 7.022351411174866e-06,
"loss": 5.4541,
"step": 452
},
{
"epoch": 0.3071186440677966,
"grad_norm": 6.138946056365967,
"learning_rate": 6.736097685690601e-06,
"loss": 5.4689,
"step": 453
},
{
"epoch": 0.3077966101694915,
"grad_norm": 5.265680313110352,
"learning_rate": 6.455596917013273e-06,
"loss": 5.2224,
"step": 454
},
{
"epoch": 0.30847457627118646,
"grad_norm": 5.933971881866455,
"learning_rate": 6.180866407751595e-06,
"loss": 5.5028,
"step": 455
},
{
"epoch": 0.30915254237288137,
"grad_norm": 6.345917224884033,
"learning_rate": 5.911923104577455e-06,
"loss": 5.8293,
"step": 456
},
{
"epoch": 0.30983050847457627,
"grad_norm": 6.0259246826171875,
"learning_rate": 5.6487835971806515e-06,
"loss": 5.7334,
"step": 457
},
{
"epoch": 0.3105084745762712,
"grad_norm": 6.232974052429199,
"learning_rate": 5.39146411724547e-06,
"loss": 5.7355,
"step": 458
},
{
"epoch": 0.3111864406779661,
"grad_norm": 5.333173751831055,
"learning_rate": 5.13998053744954e-06,
"loss": 5.0914,
"step": 459
},
{
"epoch": 0.31186440677966104,
"grad_norm": 5.692471981048584,
"learning_rate": 4.8943483704846475e-06,
"loss": 5.4779,
"step": 460
},
{
"epoch": 0.31254237288135595,
"grad_norm": 5.704821586608887,
"learning_rate": 4.65458276809988e-06,
"loss": 5.1225,
"step": 461
},
{
"epoch": 0.31322033898305085,
"grad_norm": 6.1564178466796875,
"learning_rate": 4.420698520166988e-06,
"loss": 5.3608,
"step": 462
},
{
"epoch": 0.31389830508474575,
"grad_norm": 5.814398288726807,
"learning_rate": 4.19271005376809e-06,
"loss": 5.7354,
"step": 463
},
{
"epoch": 0.31457627118644066,
"grad_norm": 6.079257011413574,
"learning_rate": 3.970631432305694e-06,
"loss": 5.438,
"step": 464
},
{
"epoch": 0.3152542372881356,
"grad_norm": 5.558388710021973,
"learning_rate": 3.7544763546352834e-06,
"loss": 4.9623,
"step": 465
},
{
"epoch": 0.3159322033898305,
"grad_norm": 5.569544792175293,
"learning_rate": 3.5442581542201923e-06,
"loss": 5.506,
"step": 466
},
{
"epoch": 0.31661016949152543,
"grad_norm": 5.387109756469727,
"learning_rate": 3.339989798309273e-06,
"loss": 5.1544,
"step": 467
},
{
"epoch": 0.31728813559322033,
"grad_norm": 6.365401744842529,
"learning_rate": 3.1416838871368924e-06,
"loss": 5.6504,
"step": 468
},
{
"epoch": 0.31796610169491524,
"grad_norm": 5.795852184295654,
"learning_rate": 2.949352653145754e-06,
"loss": 5.7313,
"step": 469
},
{
"epoch": 0.31864406779661014,
"grad_norm": 5.420914173126221,
"learning_rate": 2.7630079602323442e-06,
"loss": 5.2842,
"step": 470
},
{
"epoch": 0.3193220338983051,
"grad_norm": 5.971484184265137,
"learning_rate": 2.582661303015066e-06,
"loss": 5.2509,
"step": 471
},
{
"epoch": 0.32,
"grad_norm": 6.273356914520264,
"learning_rate": 2.4083238061252567e-06,
"loss": 5.5561,
"step": 472
},
{
"epoch": 0.3206779661016949,
"grad_norm": 5.857372283935547,
"learning_rate": 2.240006223520941e-06,
"loss": 5.8628,
"step": 473
},
{
"epoch": 0.3213559322033898,
"grad_norm": 5.4021406173706055,
"learning_rate": 2.0777189378234143e-06,
"loss": 5.2859,
"step": 474
},
{
"epoch": 0.3220338983050847,
"grad_norm": 5.596453666687012,
"learning_rate": 1.921471959676957e-06,
"loss": 5.6427,
"step": 475
},
{
"epoch": 0.3227118644067797,
"grad_norm": 5.894739151000977,
"learning_rate": 1.771274927131139e-06,
"loss": 5.5308,
"step": 476
},
{
"epoch": 0.3233898305084746,
"grad_norm": 5.8096604347229,
"learning_rate": 1.6271371050464056e-06,
"loss": 5.4596,
"step": 477
},
{
"epoch": 0.3240677966101695,
"grad_norm": 5.567196846008301,
"learning_rate": 1.4890673845226133e-06,
"loss": 4.9016,
"step": 478
},
{
"epoch": 0.3247457627118644,
"grad_norm": 5.913093090057373,
"learning_rate": 1.3570742823504567e-06,
"loss": 5.3648,
"step": 479
},
{
"epoch": 0.3254237288135593,
"grad_norm": 7.292970657348633,
"learning_rate": 1.231165940486234e-06,
"loss": 5.3914,
"step": 480
},
{
"epoch": 0.32610169491525426,
"grad_norm": 5.614869594573975,
"learning_rate": 1.1113501255495485e-06,
"loss": 5.6071,
"step": 481
},
{
"epoch": 0.32677966101694916,
"grad_norm": 5.5307793617248535,
"learning_rate": 9.976342283442463e-07,
"loss": 5.3506,
"step": 482
},
{
"epoch": 0.32745762711864407,
"grad_norm": 5.844662189483643,
"learning_rate": 8.900252634025274e-07,
"loss": 5.4613,
"step": 483
},
{
"epoch": 0.328135593220339,
"grad_norm": 5.883512020111084,
"learning_rate": 7.885298685522235e-07,
"loss": 5.384,
"step": 484
},
{
"epoch": 0.3288135593220339,
"grad_norm": 6.151786804199219,
"learning_rate": 6.931543045073708e-07,
"loss": 5.3603,
"step": 485
},
{
"epoch": 0.32949152542372884,
"grad_norm": 6.09454870223999,
"learning_rate": 6.039044544820404e-07,
"loss": 5.7218,
"step": 486
},
{
"epoch": 0.33016949152542374,
"grad_norm": 5.7950029373168945,
"learning_rate": 5.207858238273522e-07,
"loss": 5.5284,
"step": 487
},
{
"epoch": 0.33084745762711865,
"grad_norm": 5.701831817626953,
"learning_rate": 4.438035396920004e-07,
"loss": 5.3463,
"step": 488
},
{
"epoch": 0.33152542372881355,
"grad_norm": 5.579401016235352,
"learning_rate": 3.7296235070587435e-07,
"loss": 5.0637,
"step": 489
},
{
"epoch": 0.33220338983050846,
"grad_norm": 5.498964309692383,
"learning_rate": 3.0826662668720364e-07,
"loss": 5.4843,
"step": 490
},
{
"epoch": 0.3328813559322034,
"grad_norm": 5.720179080963135,
"learning_rate": 2.497203583729957e-07,
"loss": 5.3577,
"step": 491
},
{
"epoch": 0.3335593220338983,
"grad_norm": 5.618310928344727,
"learning_rate": 1.973271571728441e-07,
"loss": 5.3295,
"step": 492
},
{
"epoch": 0.3342372881355932,
"grad_norm": 5.815048694610596,
"learning_rate": 1.5109025494620677e-07,
"loss": 5.5574,
"step": 493
},
{
"epoch": 0.33491525423728813,
"grad_norm": 6.3128557205200195,
"learning_rate": 1.1101250380300965e-07,
"loss": 5.8221,
"step": 494
},
{
"epoch": 0.33559322033898303,
"grad_norm": 5.930164337158203,
"learning_rate": 7.709637592770991e-08,
"loss": 5.2433,
"step": 495
},
{
"epoch": 0.336271186440678,
"grad_norm": 5.927285194396973,
"learning_rate": 4.934396342684e-08,
"loss": 5.4684,
"step": 496
},
{
"epoch": 0.3369491525423729,
"grad_norm": 5.755299091339111,
"learning_rate": 2.7756978199944273e-08,
"loss": 5.3045,
"step": 497
},
{
"epoch": 0.3376271186440678,
"grad_norm": 5.913015365600586,
"learning_rate": 1.2336751833941229e-08,
"loss": 5.4991,
"step": 498
},
{
"epoch": 0.3383050847457627,
"grad_norm": 6.161080837249756,
"learning_rate": 3.0842355210336515e-09,
"loss": 4.9174,
"step": 499
},
{
"epoch": 0.3389830508474576,
"grad_norm": 5.968166828155518,
"learning_rate": 0.0,
"loss": 5.5617,
"step": 500
},
{
"epoch": 0.3389830508474576,
"eval_loss": 1.366518259048462,
"eval_runtime": 158.5178,
"eval_samples_per_second": 47.017,
"eval_steps_per_second": 1.962,
"step": 500
}
],
"logging_steps": 1,
"max_steps": 500,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.313912319681233e+18,
"train_batch_size": 3,
"trial_name": null,
"trial_params": null
}