15k_sft_020525 / trainer_state.json
aadityap's picture
Model save
3a14d6b verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1052,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0019011406844106464,
"grad_norm": 0.03668688377117645,
"learning_rate": 1.886792452830189e-07,
"loss": 0.7196,
"step": 1
},
{
"epoch": 0.0038022813688212928,
"grad_norm": 0.035952567213973156,
"learning_rate": 3.773584905660378e-07,
"loss": 0.6543,
"step": 2
},
{
"epoch": 0.005703422053231939,
"grad_norm": 0.034396901240204815,
"learning_rate": 5.660377358490567e-07,
"loss": 0.6342,
"step": 3
},
{
"epoch": 0.0076045627376425855,
"grad_norm": 0.03101352011559978,
"learning_rate": 7.547169811320755e-07,
"loss": 0.5223,
"step": 4
},
{
"epoch": 0.009505703422053232,
"grad_norm": 0.036575726773312375,
"learning_rate": 9.433962264150944e-07,
"loss": 0.6899,
"step": 5
},
{
"epoch": 0.011406844106463879,
"grad_norm": 0.033897651666239606,
"learning_rate": 1.1320754716981133e-06,
"loss": 0.6142,
"step": 6
},
{
"epoch": 0.013307984790874524,
"grad_norm": 0.033700806599582314,
"learning_rate": 1.3207547169811322e-06,
"loss": 0.5715,
"step": 7
},
{
"epoch": 0.015209125475285171,
"grad_norm": 0.030982637040042928,
"learning_rate": 1.509433962264151e-06,
"loss": 0.5732,
"step": 8
},
{
"epoch": 0.017110266159695818,
"grad_norm": 0.03614218285927396,
"learning_rate": 1.6981132075471698e-06,
"loss": 0.6487,
"step": 9
},
{
"epoch": 0.019011406844106463,
"grad_norm": 0.03291005003403244,
"learning_rate": 1.8867924528301889e-06,
"loss": 0.599,
"step": 10
},
{
"epoch": 0.02091254752851711,
"grad_norm": 0.03524509129630007,
"learning_rate": 2.075471698113208e-06,
"loss": 0.6225,
"step": 11
},
{
"epoch": 0.022813688212927757,
"grad_norm": 0.030669610415498205,
"learning_rate": 2.2641509433962266e-06,
"loss": 0.5753,
"step": 12
},
{
"epoch": 0.024714828897338403,
"grad_norm": 0.03687063960415838,
"learning_rate": 2.4528301886792453e-06,
"loss": 0.6895,
"step": 13
},
{
"epoch": 0.026615969581749048,
"grad_norm": 0.03611941017678787,
"learning_rate": 2.6415094339622644e-06,
"loss": 0.6264,
"step": 14
},
{
"epoch": 0.028517110266159697,
"grad_norm": 0.03401456315750716,
"learning_rate": 2.830188679245283e-06,
"loss": 0.5686,
"step": 15
},
{
"epoch": 0.030418250950570342,
"grad_norm": 0.03419637601617932,
"learning_rate": 3.018867924528302e-06,
"loss": 0.608,
"step": 16
},
{
"epoch": 0.03231939163498099,
"grad_norm": 0.03584287912078038,
"learning_rate": 3.207547169811321e-06,
"loss": 0.5813,
"step": 17
},
{
"epoch": 0.034220532319391636,
"grad_norm": 0.03615992890750685,
"learning_rate": 3.3962264150943395e-06,
"loss": 0.5755,
"step": 18
},
{
"epoch": 0.03612167300380228,
"grad_norm": 0.03110134121928749,
"learning_rate": 3.5849056603773586e-06,
"loss": 0.5446,
"step": 19
},
{
"epoch": 0.03802281368821293,
"grad_norm": 0.03232315708906836,
"learning_rate": 3.7735849056603777e-06,
"loss": 0.5658,
"step": 20
},
{
"epoch": 0.039923954372623575,
"grad_norm": 0.03924214823765209,
"learning_rate": 3.962264150943396e-06,
"loss": 0.708,
"step": 21
},
{
"epoch": 0.04182509505703422,
"grad_norm": 0.03682731607691239,
"learning_rate": 4.150943396226416e-06,
"loss": 0.5808,
"step": 22
},
{
"epoch": 0.043726235741444866,
"grad_norm": 0.030617107823517682,
"learning_rate": 4.339622641509435e-06,
"loss": 0.4551,
"step": 23
},
{
"epoch": 0.045627376425855515,
"grad_norm": 0.033812282631185166,
"learning_rate": 4.528301886792453e-06,
"loss": 0.5435,
"step": 24
},
{
"epoch": 0.04752851711026616,
"grad_norm": 0.034386356534444155,
"learning_rate": 4.716981132075472e-06,
"loss": 0.5295,
"step": 25
},
{
"epoch": 0.049429657794676805,
"grad_norm": 0.0356182441226142,
"learning_rate": 4.905660377358491e-06,
"loss": 0.558,
"step": 26
},
{
"epoch": 0.051330798479087454,
"grad_norm": 0.036577927998350704,
"learning_rate": 5.09433962264151e-06,
"loss": 0.5265,
"step": 27
},
{
"epoch": 0.053231939163498096,
"grad_norm": 0.03304001445051265,
"learning_rate": 5.283018867924529e-06,
"loss": 0.4835,
"step": 28
},
{
"epoch": 0.055133079847908745,
"grad_norm": 0.04201451567231352,
"learning_rate": 5.4716981132075475e-06,
"loss": 0.6623,
"step": 29
},
{
"epoch": 0.057034220532319393,
"grad_norm": 0.04247369627455591,
"learning_rate": 5.660377358490566e-06,
"loss": 0.6387,
"step": 30
},
{
"epoch": 0.058935361216730035,
"grad_norm": 0.038223344796174466,
"learning_rate": 5.849056603773585e-06,
"loss": 0.575,
"step": 31
},
{
"epoch": 0.060836501901140684,
"grad_norm": 0.038744694247938374,
"learning_rate": 6.037735849056604e-06,
"loss": 0.543,
"step": 32
},
{
"epoch": 0.06273764258555133,
"grad_norm": 0.04824408233555485,
"learning_rate": 6.226415094339623e-06,
"loss": 0.7119,
"step": 33
},
{
"epoch": 0.06463878326996197,
"grad_norm": 0.04187197162423142,
"learning_rate": 6.415094339622642e-06,
"loss": 0.6076,
"step": 34
},
{
"epoch": 0.06653992395437262,
"grad_norm": 0.0389443389521866,
"learning_rate": 6.60377358490566e-06,
"loss": 0.5593,
"step": 35
},
{
"epoch": 0.06844106463878327,
"grad_norm": 0.04670007654518919,
"learning_rate": 6.792452830188679e-06,
"loss": 0.6212,
"step": 36
},
{
"epoch": 0.07034220532319392,
"grad_norm": 0.03685730922340025,
"learning_rate": 6.981132075471699e-06,
"loss": 0.5979,
"step": 37
},
{
"epoch": 0.07224334600760456,
"grad_norm": 0.04520087956267333,
"learning_rate": 7.169811320754717e-06,
"loss": 0.6699,
"step": 38
},
{
"epoch": 0.0741444866920152,
"grad_norm": 0.042901948849604715,
"learning_rate": 7.358490566037736e-06,
"loss": 0.6285,
"step": 39
},
{
"epoch": 0.07604562737642585,
"grad_norm": 0.04422418983311354,
"learning_rate": 7.5471698113207555e-06,
"loss": 0.6251,
"step": 40
},
{
"epoch": 0.0779467680608365,
"grad_norm": 0.035707194488757074,
"learning_rate": 7.735849056603775e-06,
"loss": 0.5684,
"step": 41
},
{
"epoch": 0.07984790874524715,
"grad_norm": 0.03523812130796158,
"learning_rate": 7.924528301886793e-06,
"loss": 0.5295,
"step": 42
},
{
"epoch": 0.0817490494296578,
"grad_norm": 0.04005409994339303,
"learning_rate": 8.113207547169812e-06,
"loss": 0.6207,
"step": 43
},
{
"epoch": 0.08365019011406843,
"grad_norm": 0.03875008979754778,
"learning_rate": 8.301886792452832e-06,
"loss": 0.6121,
"step": 44
},
{
"epoch": 0.08555133079847908,
"grad_norm": 0.03192147884997576,
"learning_rate": 8.49056603773585e-06,
"loss": 0.4839,
"step": 45
},
{
"epoch": 0.08745247148288973,
"grad_norm": 0.035931672099034556,
"learning_rate": 8.67924528301887e-06,
"loss": 0.5836,
"step": 46
},
{
"epoch": 0.08935361216730038,
"grad_norm": 0.036619233293086306,
"learning_rate": 8.867924528301887e-06,
"loss": 0.5626,
"step": 47
},
{
"epoch": 0.09125475285171103,
"grad_norm": 0.035039592869265425,
"learning_rate": 9.056603773584907e-06,
"loss": 0.5583,
"step": 48
},
{
"epoch": 0.09315589353612168,
"grad_norm": 0.034224086735969404,
"learning_rate": 9.245283018867926e-06,
"loss": 0.566,
"step": 49
},
{
"epoch": 0.09505703422053231,
"grad_norm": 0.03240395449368507,
"learning_rate": 9.433962264150944e-06,
"loss": 0.5183,
"step": 50
},
{
"epoch": 0.09695817490494296,
"grad_norm": 0.033078153570674076,
"learning_rate": 9.622641509433963e-06,
"loss": 0.4964,
"step": 51
},
{
"epoch": 0.09885931558935361,
"grad_norm": 0.03042799523677292,
"learning_rate": 9.811320754716981e-06,
"loss": 0.5534,
"step": 52
},
{
"epoch": 0.10076045627376426,
"grad_norm": 0.03836324861482314,
"learning_rate": 1e-05,
"loss": 0.6341,
"step": 53
},
{
"epoch": 0.10266159695817491,
"grad_norm": 0.033942069333683274,
"learning_rate": 1.018867924528302e-05,
"loss": 0.6775,
"step": 54
},
{
"epoch": 0.10456273764258556,
"grad_norm": 0.025887503952264527,
"learning_rate": 1.0377358490566038e-05,
"loss": 0.4627,
"step": 55
},
{
"epoch": 0.10646387832699619,
"grad_norm": 0.03394457148243923,
"learning_rate": 1.0566037735849058e-05,
"loss": 0.6204,
"step": 56
},
{
"epoch": 0.10836501901140684,
"grad_norm": 0.028338427146352457,
"learning_rate": 1.0754716981132076e-05,
"loss": 0.4382,
"step": 57
},
{
"epoch": 0.11026615969581749,
"grad_norm": 0.027333559713593924,
"learning_rate": 1.0943396226415095e-05,
"loss": 0.4175,
"step": 58
},
{
"epoch": 0.11216730038022814,
"grad_norm": 0.03359787126455066,
"learning_rate": 1.1132075471698115e-05,
"loss": 0.6217,
"step": 59
},
{
"epoch": 0.11406844106463879,
"grad_norm": 0.03025080325985568,
"learning_rate": 1.1320754716981132e-05,
"loss": 0.4926,
"step": 60
},
{
"epoch": 0.11596958174904944,
"grad_norm": 0.0309218336145624,
"learning_rate": 1.1509433962264152e-05,
"loss": 0.4542,
"step": 61
},
{
"epoch": 0.11787072243346007,
"grad_norm": 0.02984510262256353,
"learning_rate": 1.169811320754717e-05,
"loss": 0.4389,
"step": 62
},
{
"epoch": 0.11977186311787072,
"grad_norm": 0.033556526158935,
"learning_rate": 1.188679245283019e-05,
"loss": 0.5732,
"step": 63
},
{
"epoch": 0.12167300380228137,
"grad_norm": 0.0284281501030829,
"learning_rate": 1.2075471698113209e-05,
"loss": 0.4243,
"step": 64
},
{
"epoch": 0.12357414448669202,
"grad_norm": 0.03174232497744746,
"learning_rate": 1.2264150943396227e-05,
"loss": 0.5259,
"step": 65
},
{
"epoch": 0.12547528517110265,
"grad_norm": 0.02833552096705856,
"learning_rate": 1.2452830188679246e-05,
"loss": 0.5491,
"step": 66
},
{
"epoch": 0.12737642585551331,
"grad_norm": 0.028611836078715383,
"learning_rate": 1.2641509433962264e-05,
"loss": 0.6006,
"step": 67
},
{
"epoch": 0.12927756653992395,
"grad_norm": 0.03132563373904203,
"learning_rate": 1.2830188679245283e-05,
"loss": 0.4095,
"step": 68
},
{
"epoch": 0.1311787072243346,
"grad_norm": 0.02524499759557046,
"learning_rate": 1.3018867924528303e-05,
"loss": 0.483,
"step": 69
},
{
"epoch": 0.13307984790874525,
"grad_norm": 0.027887458074904888,
"learning_rate": 1.320754716981132e-05,
"loss": 0.493,
"step": 70
},
{
"epoch": 0.13498098859315588,
"grad_norm": 0.031232250695461282,
"learning_rate": 1.339622641509434e-05,
"loss": 0.4961,
"step": 71
},
{
"epoch": 0.13688212927756654,
"grad_norm": 0.03387446832617775,
"learning_rate": 1.3584905660377358e-05,
"loss": 0.5181,
"step": 72
},
{
"epoch": 0.13878326996197718,
"grad_norm": 0.03648093707574201,
"learning_rate": 1.3773584905660378e-05,
"loss": 0.6117,
"step": 73
},
{
"epoch": 0.14068441064638784,
"grad_norm": 0.02991484915971992,
"learning_rate": 1.3962264150943397e-05,
"loss": 0.5813,
"step": 74
},
{
"epoch": 0.14258555133079848,
"grad_norm": 0.0242367290202634,
"learning_rate": 1.4150943396226415e-05,
"loss": 0.4708,
"step": 75
},
{
"epoch": 0.1444866920152091,
"grad_norm": 0.022688931847156046,
"learning_rate": 1.4339622641509435e-05,
"loss": 0.4818,
"step": 76
},
{
"epoch": 0.14638783269961977,
"grad_norm": 0.02246018206602372,
"learning_rate": 1.4528301886792452e-05,
"loss": 0.4843,
"step": 77
},
{
"epoch": 0.1482889733840304,
"grad_norm": 0.020144711191450268,
"learning_rate": 1.4716981132075472e-05,
"loss": 0.4567,
"step": 78
},
{
"epoch": 0.15019011406844107,
"grad_norm": 0.024418448428126814,
"learning_rate": 1.4905660377358491e-05,
"loss": 0.5455,
"step": 79
},
{
"epoch": 0.1520912547528517,
"grad_norm": 0.018259798366678376,
"learning_rate": 1.5094339622641511e-05,
"loss": 0.4245,
"step": 80
},
{
"epoch": 0.15399239543726237,
"grad_norm": 0.020571149791388653,
"learning_rate": 1.5283018867924532e-05,
"loss": 0.5728,
"step": 81
},
{
"epoch": 0.155893536121673,
"grad_norm": 0.019419569306863834,
"learning_rate": 1.547169811320755e-05,
"loss": 0.4749,
"step": 82
},
{
"epoch": 0.15779467680608364,
"grad_norm": 0.01873004169719714,
"learning_rate": 1.5660377358490568e-05,
"loss": 0.4674,
"step": 83
},
{
"epoch": 0.1596958174904943,
"grad_norm": 0.01821765696372897,
"learning_rate": 1.5849056603773586e-05,
"loss": 0.4949,
"step": 84
},
{
"epoch": 0.16159695817490494,
"grad_norm": 0.022516771000966596,
"learning_rate": 1.6037735849056607e-05,
"loss": 0.5164,
"step": 85
},
{
"epoch": 0.1634980988593156,
"grad_norm": 0.018221938257895465,
"learning_rate": 1.6226415094339625e-05,
"loss": 0.4871,
"step": 86
},
{
"epoch": 0.16539923954372623,
"grad_norm": 0.01658953731682099,
"learning_rate": 1.6415094339622643e-05,
"loss": 0.5215,
"step": 87
},
{
"epoch": 0.16730038022813687,
"grad_norm": 0.01674622907707825,
"learning_rate": 1.6603773584905664e-05,
"loss": 0.4574,
"step": 88
},
{
"epoch": 0.16920152091254753,
"grad_norm": 0.017762783610176393,
"learning_rate": 1.679245283018868e-05,
"loss": 0.4577,
"step": 89
},
{
"epoch": 0.17110266159695817,
"grad_norm": 0.01762770573990937,
"learning_rate": 1.69811320754717e-05,
"loss": 0.4692,
"step": 90
},
{
"epoch": 0.17300380228136883,
"grad_norm": 0.017322040277817134,
"learning_rate": 1.716981132075472e-05,
"loss": 0.5164,
"step": 91
},
{
"epoch": 0.17490494296577946,
"grad_norm": 0.018718653390551426,
"learning_rate": 1.735849056603774e-05,
"loss": 0.5602,
"step": 92
},
{
"epoch": 0.17680608365019013,
"grad_norm": 0.020062480889097352,
"learning_rate": 1.7547169811320756e-05,
"loss": 0.5318,
"step": 93
},
{
"epoch": 0.17870722433460076,
"grad_norm": 0.016213045403896325,
"learning_rate": 1.7735849056603774e-05,
"loss": 0.4815,
"step": 94
},
{
"epoch": 0.1806083650190114,
"grad_norm": 0.015622055125179094,
"learning_rate": 1.7924528301886795e-05,
"loss": 0.5143,
"step": 95
},
{
"epoch": 0.18250950570342206,
"grad_norm": 0.016442850437595302,
"learning_rate": 1.8113207547169813e-05,
"loss": 0.4147,
"step": 96
},
{
"epoch": 0.1844106463878327,
"grad_norm": 0.01655292657070884,
"learning_rate": 1.830188679245283e-05,
"loss": 0.4282,
"step": 97
},
{
"epoch": 0.18631178707224336,
"grad_norm": 0.019520087480489844,
"learning_rate": 1.8490566037735852e-05,
"loss": 0.458,
"step": 98
},
{
"epoch": 0.188212927756654,
"grad_norm": 0.016399201324681423,
"learning_rate": 1.867924528301887e-05,
"loss": 0.4447,
"step": 99
},
{
"epoch": 0.19011406844106463,
"grad_norm": 0.01716766677575734,
"learning_rate": 1.8867924528301888e-05,
"loss": 0.4929,
"step": 100
},
{
"epoch": 0.1920152091254753,
"grad_norm": 0.01754420516743432,
"learning_rate": 1.905660377358491e-05,
"loss": 0.491,
"step": 101
},
{
"epoch": 0.19391634980988592,
"grad_norm": 0.017159235430977852,
"learning_rate": 1.9245283018867927e-05,
"loss": 0.5279,
"step": 102
},
{
"epoch": 0.1958174904942966,
"grad_norm": 0.016855111063929475,
"learning_rate": 1.9433962264150945e-05,
"loss": 0.5295,
"step": 103
},
{
"epoch": 0.19771863117870722,
"grad_norm": 0.018232977596542764,
"learning_rate": 1.9622641509433963e-05,
"loss": 0.5494,
"step": 104
},
{
"epoch": 0.19961977186311788,
"grad_norm": 0.02013827150488014,
"learning_rate": 1.9811320754716984e-05,
"loss": 0.4967,
"step": 105
},
{
"epoch": 0.20152091254752852,
"grad_norm": 0.01601850564273604,
"learning_rate": 2e-05,
"loss": 0.5408,
"step": 106
},
{
"epoch": 0.20342205323193915,
"grad_norm": 0.015080995013080477,
"learning_rate": 1.9999944857420527e-05,
"loss": 0.4361,
"step": 107
},
{
"epoch": 0.20532319391634982,
"grad_norm": 0.016582553669836204,
"learning_rate": 1.9999779430290247e-05,
"loss": 0.4896,
"step": 108
},
{
"epoch": 0.20722433460076045,
"grad_norm": 0.014960817408208395,
"learning_rate": 1.9999503720433575e-05,
"loss": 0.481,
"step": 109
},
{
"epoch": 0.20912547528517111,
"grad_norm": 0.01520222559031829,
"learning_rate": 1.999911773089118e-05,
"loss": 0.4902,
"step": 110
},
{
"epoch": 0.21102661596958175,
"grad_norm": 0.014460789211133408,
"learning_rate": 1.999862146591996e-05,
"loss": 0.4465,
"step": 111
},
{
"epoch": 0.21292775665399238,
"grad_norm": 0.015975633584946487,
"learning_rate": 1.9998014930992976e-05,
"loss": 0.4625,
"step": 112
},
{
"epoch": 0.21482889733840305,
"grad_norm": 0.017919922669170172,
"learning_rate": 1.9997298132799408e-05,
"loss": 0.4213,
"step": 113
},
{
"epoch": 0.21673003802281368,
"grad_norm": 0.01889452329085544,
"learning_rate": 1.9996471079244477e-05,
"loss": 0.4523,
"step": 114
},
{
"epoch": 0.21863117870722434,
"grad_norm": 0.016761850759718987,
"learning_rate": 1.999553377944936e-05,
"loss": 0.434,
"step": 115
},
{
"epoch": 0.22053231939163498,
"grad_norm": 0.016133783491997265,
"learning_rate": 1.9994486243751076e-05,
"loss": 0.4778,
"step": 116
},
{
"epoch": 0.2224334600760456,
"grad_norm": 0.018531447789392804,
"learning_rate": 1.9993328483702393e-05,
"loss": 0.5375,
"step": 117
},
{
"epoch": 0.22433460076045628,
"grad_norm": 0.01551741242441263,
"learning_rate": 1.999206051207169e-05,
"loss": 0.5587,
"step": 118
},
{
"epoch": 0.2262357414448669,
"grad_norm": 0.015842500025624345,
"learning_rate": 1.9990682342842805e-05,
"loss": 0.5979,
"step": 119
},
{
"epoch": 0.22813688212927757,
"grad_norm": 0.020876630929871697,
"learning_rate": 1.99891939912149e-05,
"loss": 0.6885,
"step": 120
},
{
"epoch": 0.2300380228136882,
"grad_norm": 0.01644422720447315,
"learning_rate": 1.9987595473602292e-05,
"loss": 0.5064,
"step": 121
},
{
"epoch": 0.23193916349809887,
"grad_norm": 0.017044981544664082,
"learning_rate": 1.9985886807634246e-05,
"loss": 0.4923,
"step": 122
},
{
"epoch": 0.2338403041825095,
"grad_norm": 0.016870862107049755,
"learning_rate": 1.9984068012154824e-05,
"loss": 0.423,
"step": 123
},
{
"epoch": 0.23574144486692014,
"grad_norm": 0.015777583476224797,
"learning_rate": 1.9982139107222634e-05,
"loss": 0.4574,
"step": 124
},
{
"epoch": 0.2376425855513308,
"grad_norm": 0.015781286625695973,
"learning_rate": 1.9980100114110637e-05,
"loss": 0.4665,
"step": 125
},
{
"epoch": 0.23954372623574144,
"grad_norm": 0.015679150227417577,
"learning_rate": 1.99779510553059e-05,
"loss": 0.4425,
"step": 126
},
{
"epoch": 0.2414448669201521,
"grad_norm": 0.017376402458769775,
"learning_rate": 1.9975691954509347e-05,
"loss": 0.4736,
"step": 127
},
{
"epoch": 0.24334600760456274,
"grad_norm": 0.01663302538553884,
"learning_rate": 1.9973322836635517e-05,
"loss": 0.427,
"step": 128
},
{
"epoch": 0.24524714828897337,
"grad_norm": 0.01619990675448057,
"learning_rate": 1.997084372781226e-05,
"loss": 0.4789,
"step": 129
},
{
"epoch": 0.24714828897338403,
"grad_norm": 0.014751100997639594,
"learning_rate": 1.9968254655380465e-05,
"loss": 0.4641,
"step": 130
},
{
"epoch": 0.24904942965779467,
"grad_norm": 0.01788111921176585,
"learning_rate": 1.996555564789376e-05,
"loss": 0.6526,
"step": 131
},
{
"epoch": 0.2509505703422053,
"grad_norm": 0.017304585767881957,
"learning_rate": 1.996274673511819e-05,
"loss": 0.5883,
"step": 132
},
{
"epoch": 0.25285171102661597,
"grad_norm": 0.017558281140256256,
"learning_rate": 1.99598279480319e-05,
"loss": 0.5356,
"step": 133
},
{
"epoch": 0.25475285171102663,
"grad_norm": 0.01653596608203917,
"learning_rate": 1.9956799318824776e-05,
"loss": 0.4124,
"step": 134
},
{
"epoch": 0.25665399239543724,
"grad_norm": 0.018759070146296956,
"learning_rate": 1.99536608808981e-05,
"loss": 0.4521,
"step": 135
},
{
"epoch": 0.2585551330798479,
"grad_norm": 0.016451732444213572,
"learning_rate": 1.995041266886419e-05,
"loss": 0.4564,
"step": 136
},
{
"epoch": 0.26045627376425856,
"grad_norm": 0.03972131177385222,
"learning_rate": 1.9947054718545996e-05,
"loss": 0.5367,
"step": 137
},
{
"epoch": 0.2623574144486692,
"grad_norm": 0.017213070936728483,
"learning_rate": 1.994358706697674e-05,
"loss": 0.4412,
"step": 138
},
{
"epoch": 0.26425855513307983,
"grad_norm": 0.01820884630697662,
"learning_rate": 1.9940009752399462e-05,
"loss": 0.4635,
"step": 139
},
{
"epoch": 0.2661596958174905,
"grad_norm": 0.019567114976084547,
"learning_rate": 1.9936322814266634e-05,
"loss": 0.56,
"step": 140
},
{
"epoch": 0.26806083650190116,
"grad_norm": 0.017133833604248784,
"learning_rate": 1.9932526293239713e-05,
"loss": 0.4149,
"step": 141
},
{
"epoch": 0.26996197718631176,
"grad_norm": 0.018600324556852586,
"learning_rate": 1.9928620231188694e-05,
"loss": 0.3961,
"step": 142
},
{
"epoch": 0.2718631178707224,
"grad_norm": 0.018970017200871575,
"learning_rate": 1.992460467119164e-05,
"loss": 0.4488,
"step": 143
},
{
"epoch": 0.2737642585551331,
"grad_norm": 0.018135694037860434,
"learning_rate": 1.992047965753422e-05,
"loss": 0.5313,
"step": 144
},
{
"epoch": 0.27566539923954375,
"grad_norm": 0.04619547629543339,
"learning_rate": 1.991624523570922e-05,
"loss": 0.4452,
"step": 145
},
{
"epoch": 0.27756653992395436,
"grad_norm": 0.019254266322524038,
"learning_rate": 1.9911901452416012e-05,
"loss": 0.4949,
"step": 146
},
{
"epoch": 0.279467680608365,
"grad_norm": 0.020224200919704446,
"learning_rate": 1.9907448355560094e-05,
"loss": 0.5203,
"step": 147
},
{
"epoch": 0.2813688212927757,
"grad_norm": 0.019583737042576384,
"learning_rate": 1.9902885994252506e-05,
"loss": 0.4314,
"step": 148
},
{
"epoch": 0.2832699619771863,
"grad_norm": 0.020322692978619984,
"learning_rate": 1.989821441880933e-05,
"loss": 0.5791,
"step": 149
},
{
"epoch": 0.28517110266159695,
"grad_norm": 0.02330003106029221,
"learning_rate": 1.9893433680751105e-05,
"loss": 0.4411,
"step": 150
},
{
"epoch": 0.2870722433460076,
"grad_norm": 0.02159054999321492,
"learning_rate": 1.9888543832802277e-05,
"loss": 0.499,
"step": 151
},
{
"epoch": 0.2889733840304182,
"grad_norm": 0.01996792223389153,
"learning_rate": 1.9883544928890612e-05,
"loss": 0.4229,
"step": 152
},
{
"epoch": 0.2908745247148289,
"grad_norm": 0.021058283772857712,
"learning_rate": 1.9878437024146603e-05,
"loss": 0.5255,
"step": 153
},
{
"epoch": 0.29277566539923955,
"grad_norm": 0.024196266685836586,
"learning_rate": 1.9873220174902857e-05,
"loss": 0.4656,
"step": 154
},
{
"epoch": 0.2946768060836502,
"grad_norm": 0.02096696363566598,
"learning_rate": 1.986789443869348e-05,
"loss": 0.4385,
"step": 155
},
{
"epoch": 0.2965779467680608,
"grad_norm": 0.020706886476065403,
"learning_rate": 1.9862459874253438e-05,
"loss": 0.4272,
"step": 156
},
{
"epoch": 0.2984790874524715,
"grad_norm": 0.025633809682526005,
"learning_rate": 1.985691654151791e-05,
"loss": 0.4376,
"step": 157
},
{
"epoch": 0.30038022813688214,
"grad_norm": 0.022367447749969346,
"learning_rate": 1.9851264501621635e-05,
"loss": 0.476,
"step": 158
},
{
"epoch": 0.30228136882129275,
"grad_norm": 0.019818236100033224,
"learning_rate": 1.984550381689822e-05,
"loss": 0.4381,
"step": 159
},
{
"epoch": 0.3041825095057034,
"grad_norm": 0.018035025834197898,
"learning_rate": 1.983963455087946e-05,
"loss": 0.4139,
"step": 160
},
{
"epoch": 0.3060836501901141,
"grad_norm": 0.02102741417831402,
"learning_rate": 1.983365676829466e-05,
"loss": 0.4498,
"step": 161
},
{
"epoch": 0.30798479087452474,
"grad_norm": 0.019483110144615897,
"learning_rate": 1.982757053506989e-05,
"loss": 0.4141,
"step": 162
},
{
"epoch": 0.30988593155893535,
"grad_norm": 0.01815612650289187,
"learning_rate": 1.9821375918327268e-05,
"loss": 0.4323,
"step": 163
},
{
"epoch": 0.311787072243346,
"grad_norm": 0.017730579316108816,
"learning_rate": 1.981507298638422e-05,
"loss": 0.5347,
"step": 164
},
{
"epoch": 0.31368821292775667,
"grad_norm": 0.019188868789103374,
"learning_rate": 1.9808661808752735e-05,
"loss": 0.4088,
"step": 165
},
{
"epoch": 0.3155893536121673,
"grad_norm": 0.021357864822283502,
"learning_rate": 1.980214245613858e-05,
"loss": 0.4764,
"step": 166
},
{
"epoch": 0.31749049429657794,
"grad_norm": 0.017524761211716523,
"learning_rate": 1.979551500044055e-05,
"loss": 0.5122,
"step": 167
},
{
"epoch": 0.3193916349809886,
"grad_norm": 0.018425099678369045,
"learning_rate": 1.9788779514749635e-05,
"loss": 0.4602,
"step": 168
},
{
"epoch": 0.32129277566539927,
"grad_norm": 0.018975566503684312,
"learning_rate": 1.978193607334826e-05,
"loss": 0.4846,
"step": 169
},
{
"epoch": 0.3231939163498099,
"grad_norm": 0.018506385123025323,
"learning_rate": 1.977498475170941e-05,
"loss": 0.5318,
"step": 170
},
{
"epoch": 0.32509505703422054,
"grad_norm": 0.017679822429953924,
"learning_rate": 1.9767925626495857e-05,
"loss": 0.438,
"step": 171
},
{
"epoch": 0.3269961977186312,
"grad_norm": 0.01875235194047055,
"learning_rate": 1.9760758775559275e-05,
"loss": 0.4472,
"step": 172
},
{
"epoch": 0.3288973384030418,
"grad_norm": 0.01767922446458576,
"learning_rate": 1.975348427793939e-05,
"loss": 0.5602,
"step": 173
},
{
"epoch": 0.33079847908745247,
"grad_norm": 0.018382173225872267,
"learning_rate": 1.9746102213863113e-05,
"loss": 0.4756,
"step": 174
},
{
"epoch": 0.33269961977186313,
"grad_norm": 0.01662767369884979,
"learning_rate": 1.973861266474366e-05,
"loss": 0.4727,
"step": 175
},
{
"epoch": 0.33460076045627374,
"grad_norm": 0.020123291885424312,
"learning_rate": 1.9731015713179643e-05,
"loss": 0.4743,
"step": 176
},
{
"epoch": 0.3365019011406844,
"grad_norm": 0.016913284449301725,
"learning_rate": 1.9723311442954163e-05,
"loss": 0.4673,
"step": 177
},
{
"epoch": 0.33840304182509506,
"grad_norm": 0.02195956626625843,
"learning_rate": 1.9715499939033883e-05,
"loss": 0.3841,
"step": 178
},
{
"epoch": 0.3403041825095057,
"grad_norm": 0.018554265629519444,
"learning_rate": 1.9707581287568094e-05,
"loss": 0.5465,
"step": 179
},
{
"epoch": 0.34220532319391633,
"grad_norm": 0.016914420157391603,
"learning_rate": 1.969955557588778e-05,
"loss": 0.4325,
"step": 180
},
{
"epoch": 0.344106463878327,
"grad_norm": 0.02019706373919531,
"learning_rate": 1.9691422892504626e-05,
"loss": 0.4832,
"step": 181
},
{
"epoch": 0.34600760456273766,
"grad_norm": 0.02068472935834528,
"learning_rate": 1.968318332711006e-05,
"loss": 0.4557,
"step": 182
},
{
"epoch": 0.34790874524714827,
"grad_norm": 0.01885222047217075,
"learning_rate": 1.9674836970574253e-05,
"loss": 0.4579,
"step": 183
},
{
"epoch": 0.34980988593155893,
"grad_norm": 0.01929841860727856,
"learning_rate": 1.966638391494514e-05,
"loss": 0.4636,
"step": 184
},
{
"epoch": 0.3517110266159696,
"grad_norm": 0.01681745337606996,
"learning_rate": 1.9657824253447378e-05,
"loss": 0.4486,
"step": 185
},
{
"epoch": 0.35361216730038025,
"grad_norm": 0.017711355674748283,
"learning_rate": 1.9649158080481327e-05,
"loss": 0.4196,
"step": 186
},
{
"epoch": 0.35551330798479086,
"grad_norm": 0.021237427364918404,
"learning_rate": 1.964038549162201e-05,
"loss": 0.4849,
"step": 187
},
{
"epoch": 0.3574144486692015,
"grad_norm": 0.020159495183868427,
"learning_rate": 1.963150658361807e-05,
"loss": 0.4576,
"step": 188
},
{
"epoch": 0.3593155893536122,
"grad_norm": 0.018156933355716387,
"learning_rate": 1.962252145439068e-05,
"loss": 0.4448,
"step": 189
},
{
"epoch": 0.3612167300380228,
"grad_norm": 0.016649738646787975,
"learning_rate": 1.9613430203032486e-05,
"loss": 0.3491,
"step": 190
},
{
"epoch": 0.36311787072243346,
"grad_norm": 0.019962082237500515,
"learning_rate": 1.9604232929806493e-05,
"loss": 0.5425,
"step": 191
},
{
"epoch": 0.3650190114068441,
"grad_norm": 0.018374631285756067,
"learning_rate": 1.9594929736144978e-05,
"loss": 0.4724,
"step": 192
},
{
"epoch": 0.3669201520912547,
"grad_norm": 0.02317193691864784,
"learning_rate": 1.9585520724648354e-05,
"loss": 0.4765,
"step": 193
},
{
"epoch": 0.3688212927756654,
"grad_norm": 0.018838805142255447,
"learning_rate": 1.957600599908406e-05,
"loss": 0.5229,
"step": 194
},
{
"epoch": 0.37072243346007605,
"grad_norm": 0.01761088352260932,
"learning_rate": 1.95663856643854e-05,
"loss": 0.464,
"step": 195
},
{
"epoch": 0.3726235741444867,
"grad_norm": 0.016815312376514308,
"learning_rate": 1.955665982665038e-05,
"loss": 0.4853,
"step": 196
},
{
"epoch": 0.3745247148288973,
"grad_norm": 0.018392067679920427,
"learning_rate": 1.9546828593140565e-05,
"loss": 0.4762,
"step": 197
},
{
"epoch": 0.376425855513308,
"grad_norm": 0.02122811232370391,
"learning_rate": 1.9536892072279863e-05,
"loss": 0.3899,
"step": 198
},
{
"epoch": 0.37832699619771865,
"grad_norm": 0.019854868900050456,
"learning_rate": 1.9526850373653356e-05,
"loss": 0.3948,
"step": 199
},
{
"epoch": 0.38022813688212925,
"grad_norm": 0.023763843903790046,
"learning_rate": 1.9516703608006074e-05,
"loss": 0.4453,
"step": 200
},
{
"epoch": 0.3821292775665399,
"grad_norm": 0.01927284079047068,
"learning_rate": 1.9506451887241787e-05,
"loss": 0.5135,
"step": 201
},
{
"epoch": 0.3840304182509506,
"grad_norm": 0.020767632866775965,
"learning_rate": 1.949609532442176e-05,
"loss": 0.5374,
"step": 202
},
{
"epoch": 0.38593155893536124,
"grad_norm": 0.019139363444625492,
"learning_rate": 1.9485634033763507e-05,
"loss": 0.4858,
"step": 203
},
{
"epoch": 0.38783269961977185,
"grad_norm": 0.017436727750232788,
"learning_rate": 1.9475068130639543e-05,
"loss": 0.5505,
"step": 204
},
{
"epoch": 0.3897338403041825,
"grad_norm": 0.01696558264370334,
"learning_rate": 1.9464397731576093e-05,
"loss": 0.4323,
"step": 205
},
{
"epoch": 0.3916349809885932,
"grad_norm": 0.019107284844297346,
"learning_rate": 1.945362295425183e-05,
"loss": 0.4586,
"step": 206
},
{
"epoch": 0.3935361216730038,
"grad_norm": 0.018034308085610313,
"learning_rate": 1.944274391749655e-05,
"loss": 0.4668,
"step": 207
},
{
"epoch": 0.39543726235741444,
"grad_norm": 0.019543142514623062,
"learning_rate": 1.9431760741289886e-05,
"loss": 0.5371,
"step": 208
},
{
"epoch": 0.3973384030418251,
"grad_norm": 0.019931000999436656,
"learning_rate": 1.942067354675997e-05,
"loss": 0.4441,
"step": 209
},
{
"epoch": 0.39923954372623577,
"grad_norm": 0.018331743495642414,
"learning_rate": 1.9409482456182105e-05,
"loss": 0.4379,
"step": 210
},
{
"epoch": 0.4011406844106464,
"grad_norm": 0.02230823654311762,
"learning_rate": 1.939818759297741e-05,
"loss": 0.4806,
"step": 211
},
{
"epoch": 0.40304182509505704,
"grad_norm": 0.019717968785659953,
"learning_rate": 1.9386789081711465e-05,
"loss": 0.547,
"step": 212
},
{
"epoch": 0.4049429657794677,
"grad_norm": 0.01996049638659254,
"learning_rate": 1.9375287048092927e-05,
"loss": 0.4786,
"step": 213
},
{
"epoch": 0.4068441064638783,
"grad_norm": 0.022379601814349274,
"learning_rate": 1.9363681618972166e-05,
"loss": 0.4812,
"step": 214
},
{
"epoch": 0.40874524714828897,
"grad_norm": 0.019091180196167398,
"learning_rate": 1.9351972922339835e-05,
"loss": 0.492,
"step": 215
},
{
"epoch": 0.41064638783269963,
"grad_norm": 0.017533111807113918,
"learning_rate": 1.9340161087325483e-05,
"loss": 0.4814,
"step": 216
},
{
"epoch": 0.41254752851711024,
"grad_norm": 0.021445851431766402,
"learning_rate": 1.9328246244196117e-05,
"loss": 0.5106,
"step": 217
},
{
"epoch": 0.4144486692015209,
"grad_norm": 0.018645780324267735,
"learning_rate": 1.931622852435478e-05,
"loss": 0.4236,
"step": 218
},
{
"epoch": 0.41634980988593157,
"grad_norm": 0.02124080488001633,
"learning_rate": 1.930410806033908e-05,
"loss": 0.4447,
"step": 219
},
{
"epoch": 0.41825095057034223,
"grad_norm": 0.020448657398421086,
"learning_rate": 1.929188498581975e-05,
"loss": 0.4553,
"step": 220
},
{
"epoch": 0.42015209125475284,
"grad_norm": 0.022998272051918525,
"learning_rate": 1.9279559435599164e-05,
"loss": 0.5504,
"step": 221
},
{
"epoch": 0.4220532319391635,
"grad_norm": 0.01751636845626442,
"learning_rate": 1.926713154560984e-05,
"loss": 0.4087,
"step": 222
},
{
"epoch": 0.42395437262357416,
"grad_norm": 0.0183705673199705,
"learning_rate": 1.9254601452912972e-05,
"loss": 0.477,
"step": 223
},
{
"epoch": 0.42585551330798477,
"grad_norm": 0.01700996933235925,
"learning_rate": 1.924196929569688e-05,
"loss": 0.4239,
"step": 224
},
{
"epoch": 0.42775665399239543,
"grad_norm": 0.028348207596178773,
"learning_rate": 1.922923521327551e-05,
"loss": 0.5081,
"step": 225
},
{
"epoch": 0.4296577946768061,
"grad_norm": 0.020351003380647062,
"learning_rate": 1.9216399346086893e-05,
"loss": 0.4489,
"step": 226
},
{
"epoch": 0.43155893536121676,
"grad_norm": 0.025094961377472726,
"learning_rate": 1.9203461835691596e-05,
"loss": 0.4519,
"step": 227
},
{
"epoch": 0.43346007604562736,
"grad_norm": 0.01931118839865135,
"learning_rate": 1.9190422824771158e-05,
"loss": 0.4261,
"step": 228
},
{
"epoch": 0.435361216730038,
"grad_norm": 0.023998044821670804,
"learning_rate": 1.9177282457126515e-05,
"loss": 0.501,
"step": 229
},
{
"epoch": 0.4372623574144487,
"grad_norm": 0.02017772118245582,
"learning_rate": 1.9164040877676425e-05,
"loss": 0.463,
"step": 230
},
{
"epoch": 0.4391634980988593,
"grad_norm": 0.02035855929839421,
"learning_rate": 1.9150698232455853e-05,
"loss": 0.4087,
"step": 231
},
{
"epoch": 0.44106463878326996,
"grad_norm": 0.019391301479384226,
"learning_rate": 1.913725466861438e-05,
"loss": 0.536,
"step": 232
},
{
"epoch": 0.4429657794676806,
"grad_norm": 0.02051219750595343,
"learning_rate": 1.9123710334414552e-05,
"loss": 0.4986,
"step": 233
},
{
"epoch": 0.4448669201520912,
"grad_norm": 0.021123597813669577,
"learning_rate": 1.911006537923029e-05,
"loss": 0.489,
"step": 234
},
{
"epoch": 0.4467680608365019,
"grad_norm": 0.01934532070020403,
"learning_rate": 1.9096319953545186e-05,
"loss": 0.5335,
"step": 235
},
{
"epoch": 0.44866920152091255,
"grad_norm": 0.022232569152747954,
"learning_rate": 1.908247420895089e-05,
"loss": 0.5413,
"step": 236
},
{
"epoch": 0.4505703422053232,
"grad_norm": 0.01918609878743169,
"learning_rate": 1.9068528298145418e-05,
"loss": 0.3835,
"step": 237
},
{
"epoch": 0.4524714828897338,
"grad_norm": 0.022646076049038216,
"learning_rate": 1.905448237493147e-05,
"loss": 0.6124,
"step": 238
},
{
"epoch": 0.4543726235741445,
"grad_norm": 0.0202683182037997,
"learning_rate": 1.9040336594214727e-05,
"loss": 0.5275,
"step": 239
},
{
"epoch": 0.45627376425855515,
"grad_norm": 0.022029101866042167,
"learning_rate": 1.9026091112002163e-05,
"loss": 0.4243,
"step": 240
},
{
"epoch": 0.45817490494296575,
"grad_norm": 0.020459631583791056,
"learning_rate": 1.90117460854003e-05,
"loss": 0.4901,
"step": 241
},
{
"epoch": 0.4600760456273764,
"grad_norm": 0.025114855573878776,
"learning_rate": 1.8997301672613496e-05,
"loss": 0.4977,
"step": 242
},
{
"epoch": 0.4619771863117871,
"grad_norm": 0.021614635116058833,
"learning_rate": 1.8982758032942184e-05,
"loss": 0.4515,
"step": 243
},
{
"epoch": 0.46387832699619774,
"grad_norm": 0.021672300801502467,
"learning_rate": 1.896811532678113e-05,
"loss": 0.4489,
"step": 244
},
{
"epoch": 0.46577946768060835,
"grad_norm": 0.018022961395727993,
"learning_rate": 1.8953373715617646e-05,
"loss": 0.4495,
"step": 245
},
{
"epoch": 0.467680608365019,
"grad_norm": 0.018779771734770696,
"learning_rate": 1.893853336202983e-05,
"loss": 0.4212,
"step": 246
},
{
"epoch": 0.4695817490494297,
"grad_norm": 0.020783339016957118,
"learning_rate": 1.892359442968475e-05,
"loss": 0.5068,
"step": 247
},
{
"epoch": 0.4714828897338403,
"grad_norm": 0.01987320833611613,
"learning_rate": 1.8908557083336668e-05,
"loss": 0.5315,
"step": 248
},
{
"epoch": 0.47338403041825095,
"grad_norm": 0.018697682064789396,
"learning_rate": 1.889342148882519e-05,
"loss": 0.4605,
"step": 249
},
{
"epoch": 0.4752851711026616,
"grad_norm": 0.021499753416302066,
"learning_rate": 1.8878187813073465e-05,
"loss": 0.4466,
"step": 250
},
{
"epoch": 0.47718631178707227,
"grad_norm": 0.018547287933737062,
"learning_rate": 1.886285622408633e-05,
"loss": 0.4693,
"step": 251
},
{
"epoch": 0.4790874524714829,
"grad_norm": 0.023084485584254806,
"learning_rate": 1.8847426890948447e-05,
"loss": 0.4594,
"step": 252
},
{
"epoch": 0.48098859315589354,
"grad_norm": 0.02095991299497145,
"learning_rate": 1.8831899983822475e-05,
"loss": 0.5958,
"step": 253
},
{
"epoch": 0.4828897338403042,
"grad_norm": 0.022676472901591558,
"learning_rate": 1.8816275673947148e-05,
"loss": 0.4794,
"step": 254
},
{
"epoch": 0.4847908745247148,
"grad_norm": 0.022256603233549825,
"learning_rate": 1.8800554133635417e-05,
"loss": 0.4385,
"step": 255
},
{
"epoch": 0.4866920152091255,
"grad_norm": 0.018181221043854088,
"learning_rate": 1.8784735536272543e-05,
"loss": 0.3858,
"step": 256
},
{
"epoch": 0.48859315589353614,
"grad_norm": 0.022066225412088022,
"learning_rate": 1.8768820056314173e-05,
"loss": 0.4495,
"step": 257
},
{
"epoch": 0.49049429657794674,
"grad_norm": 0.02200490107058745,
"learning_rate": 1.875280786928444e-05,
"loss": 0.5011,
"step": 258
},
{
"epoch": 0.4923954372623574,
"grad_norm": 0.021271769486431728,
"learning_rate": 1.873669915177399e-05,
"loss": 0.4346,
"step": 259
},
{
"epoch": 0.49429657794676807,
"grad_norm": 0.02012803137107531,
"learning_rate": 1.872049408143808e-05,
"loss": 0.4196,
"step": 260
},
{
"epoch": 0.49619771863117873,
"grad_norm": 0.021961152700393033,
"learning_rate": 1.8704192836994578e-05,
"loss": 0.3991,
"step": 261
},
{
"epoch": 0.49809885931558934,
"grad_norm": 0.024936197092006625,
"learning_rate": 1.8687795598222024e-05,
"loss": 0.5895,
"step": 262
},
{
"epoch": 0.5,
"grad_norm": 0.021262424107645336,
"learning_rate": 1.8671302545957628e-05,
"loss": 0.4397,
"step": 263
},
{
"epoch": 0.5019011406844106,
"grad_norm": 0.02111275635557399,
"learning_rate": 1.8654713862095272e-05,
"loss": 0.4706,
"step": 264
},
{
"epoch": 0.5038022813688213,
"grad_norm": 0.021959234105395655,
"learning_rate": 1.8638029729583524e-05,
"loss": 0.3666,
"step": 265
},
{
"epoch": 0.5057034220532319,
"grad_norm": 0.02200752182868664,
"learning_rate": 1.8621250332423603e-05,
"loss": 0.4428,
"step": 266
},
{
"epoch": 0.5076045627376425,
"grad_norm": 0.025080248739382673,
"learning_rate": 1.860437585566736e-05,
"loss": 0.6006,
"step": 267
},
{
"epoch": 0.5095057034220533,
"grad_norm": 0.022659597179735286,
"learning_rate": 1.8587406485415226e-05,
"loss": 0.4237,
"step": 268
},
{
"epoch": 0.5114068441064639,
"grad_norm": 0.023798174928936905,
"learning_rate": 1.8570342408814173e-05,
"loss": 0.4126,
"step": 269
},
{
"epoch": 0.5133079847908745,
"grad_norm": 0.022256558231383495,
"learning_rate": 1.855318381405564e-05,
"loss": 0.4742,
"step": 270
},
{
"epoch": 0.5152091254752852,
"grad_norm": 0.02111936212093974,
"learning_rate": 1.8535930890373467e-05,
"loss": 0.3881,
"step": 271
},
{
"epoch": 0.5171102661596958,
"grad_norm": 0.02224791336065645,
"learning_rate": 1.8518583828041787e-05,
"loss": 0.3921,
"step": 272
},
{
"epoch": 0.5190114068441065,
"grad_norm": 0.022880761831731673,
"learning_rate": 1.8501142818372964e-05,
"loss": 0.6346,
"step": 273
},
{
"epoch": 0.5209125475285171,
"grad_norm": 0.024343970646870612,
"learning_rate": 1.848360805371544e-05,
"loss": 0.4756,
"step": 274
},
{
"epoch": 0.5228136882129277,
"grad_norm": 0.024351775075405556,
"learning_rate": 1.8465979727451653e-05,
"loss": 0.4734,
"step": 275
},
{
"epoch": 0.5247148288973384,
"grad_norm": 0.018962907375531707,
"learning_rate": 1.8448258033995877e-05,
"loss": 0.3971,
"step": 276
},
{
"epoch": 0.526615969581749,
"grad_norm": 0.021617768076139313,
"learning_rate": 1.8430443168792087e-05,
"loss": 0.5119,
"step": 277
},
{
"epoch": 0.5285171102661597,
"grad_norm": 0.021857799342184975,
"learning_rate": 1.8412535328311813e-05,
"loss": 0.5116,
"step": 278
},
{
"epoch": 0.5304182509505704,
"grad_norm": 0.02809434456106648,
"learning_rate": 1.8394534710051956e-05,
"loss": 0.4666,
"step": 279
},
{
"epoch": 0.532319391634981,
"grad_norm": 0.02234090014207455,
"learning_rate": 1.8376441512532617e-05,
"loss": 0.4725,
"step": 280
},
{
"epoch": 0.5342205323193916,
"grad_norm": 0.02451211288371571,
"learning_rate": 1.835825593529492e-05,
"loss": 0.4708,
"step": 281
},
{
"epoch": 0.5361216730038023,
"grad_norm": 0.022641545839139392,
"learning_rate": 1.833997817889878e-05,
"loss": 0.4214,
"step": 282
},
{
"epoch": 0.5380228136882129,
"grad_norm": 0.025872109051734524,
"learning_rate": 1.8321608444920738e-05,
"loss": 0.5036,
"step": 283
},
{
"epoch": 0.5399239543726235,
"grad_norm": 0.023529092183304456,
"learning_rate": 1.830314693595169e-05,
"loss": 0.5425,
"step": 284
},
{
"epoch": 0.5418250950570342,
"grad_norm": 0.024348495219394833,
"learning_rate": 1.828459385559468e-05,
"loss": 0.4342,
"step": 285
},
{
"epoch": 0.5437262357414449,
"grad_norm": 0.02239963896857723,
"learning_rate": 1.8265949408462657e-05,
"loss": 0.4776,
"step": 286
},
{
"epoch": 0.5456273764258555,
"grad_norm": 0.02080669784822377,
"learning_rate": 1.8247213800176192e-05,
"loss": 0.3624,
"step": 287
},
{
"epoch": 0.5475285171102662,
"grad_norm": 0.023617380475480572,
"learning_rate": 1.8228387237361245e-05,
"loss": 0.3952,
"step": 288
},
{
"epoch": 0.5494296577946768,
"grad_norm": 0.024814665778031497,
"learning_rate": 1.8209469927646863e-05,
"loss": 0.4507,
"step": 289
},
{
"epoch": 0.5513307984790875,
"grad_norm": 0.021845348519988903,
"learning_rate": 1.8190462079662897e-05,
"loss": 0.4285,
"step": 290
},
{
"epoch": 0.5532319391634981,
"grad_norm": 0.02184467934463939,
"learning_rate": 1.81713639030377e-05,
"loss": 0.4422,
"step": 291
},
{
"epoch": 0.5551330798479087,
"grad_norm": 0.029176904840741643,
"learning_rate": 1.8152175608395814e-05,
"loss": 0.4321,
"step": 292
},
{
"epoch": 0.5570342205323194,
"grad_norm": 0.026819867766165566,
"learning_rate": 1.8132897407355657e-05,
"loss": 0.4717,
"step": 293
},
{
"epoch": 0.55893536121673,
"grad_norm": 0.021172044415504698,
"learning_rate": 1.811352951252717e-05,
"loss": 0.4148,
"step": 294
},
{
"epoch": 0.5608365019011406,
"grad_norm": 0.020343820915447078,
"learning_rate": 1.809407213750949e-05,
"loss": 0.5348,
"step": 295
},
{
"epoch": 0.5627376425855514,
"grad_norm": 0.02421850881920752,
"learning_rate": 1.807452549688859e-05,
"loss": 0.4458,
"step": 296
},
{
"epoch": 0.564638783269962,
"grad_norm": 0.023147892279235603,
"learning_rate": 1.8054889806234906e-05,
"loss": 0.4486,
"step": 297
},
{
"epoch": 0.5665399239543726,
"grad_norm": 0.02395397717021146,
"learning_rate": 1.8035165282100963e-05,
"loss": 0.5499,
"step": 298
},
{
"epoch": 0.5684410646387833,
"grad_norm": 0.02031353995079303,
"learning_rate": 1.8015352142018984e-05,
"loss": 0.5031,
"step": 299
},
{
"epoch": 0.5703422053231939,
"grad_norm": 0.020808578024095383,
"learning_rate": 1.799545060449851e-05,
"loss": 0.467,
"step": 300
},
{
"epoch": 0.5722433460076045,
"grad_norm": 0.019246896542792716,
"learning_rate": 1.797546088902396e-05,
"loss": 0.487,
"step": 301
},
{
"epoch": 0.5741444866920152,
"grad_norm": 0.022104685939284753,
"learning_rate": 1.7955383216052224e-05,
"loss": 0.4903,
"step": 302
},
{
"epoch": 0.5760456273764258,
"grad_norm": 0.02365048405686273,
"learning_rate": 1.7935217807010238e-05,
"loss": 0.4795,
"step": 303
},
{
"epoch": 0.5779467680608364,
"grad_norm": 0.023930921277957873,
"learning_rate": 1.7914964884292543e-05,
"loss": 0.5356,
"step": 304
},
{
"epoch": 0.5798479087452472,
"grad_norm": 0.024823876120292392,
"learning_rate": 1.7894624671258813e-05,
"loss": 0.4837,
"step": 305
},
{
"epoch": 0.5817490494296578,
"grad_norm": 0.019457627346199154,
"learning_rate": 1.7874197392231414e-05,
"loss": 0.3855,
"step": 306
},
{
"epoch": 0.5836501901140685,
"grad_norm": 0.01924926829147994,
"learning_rate": 1.7853683272492913e-05,
"loss": 0.3732,
"step": 307
},
{
"epoch": 0.5855513307984791,
"grad_norm": 0.024460829179782474,
"learning_rate": 1.7833082538283615e-05,
"loss": 0.3846,
"step": 308
},
{
"epoch": 0.5874524714828897,
"grad_norm": 0.020841592567127323,
"learning_rate": 1.7812395416799034e-05,
"loss": 0.6149,
"step": 309
},
{
"epoch": 0.5893536121673004,
"grad_norm": 0.023282119114238924,
"learning_rate": 1.7791622136187422e-05,
"loss": 0.5066,
"step": 310
},
{
"epoch": 0.591254752851711,
"grad_norm": 0.021526927277188218,
"learning_rate": 1.7770762925547235e-05,
"loss": 0.5292,
"step": 311
},
{
"epoch": 0.5931558935361216,
"grad_norm": 0.021188916531237858,
"learning_rate": 1.7749818014924612e-05,
"loss": 0.4636,
"step": 312
},
{
"epoch": 0.5950570342205324,
"grad_norm": 0.0207773105187197,
"learning_rate": 1.7728787635310828e-05,
"loss": 0.4813,
"step": 313
},
{
"epoch": 0.596958174904943,
"grad_norm": 0.01936236572719632,
"learning_rate": 1.770767201863976e-05,
"loss": 0.4322,
"step": 314
},
{
"epoch": 0.5988593155893536,
"grad_norm": 0.02286004336607461,
"learning_rate": 1.7686471397785322e-05,
"loss": 0.4369,
"step": 315
},
{
"epoch": 0.6007604562737643,
"grad_norm": 0.022439241037259583,
"learning_rate": 1.76651860065589e-05,
"loss": 0.4423,
"step": 316
},
{
"epoch": 0.6026615969581749,
"grad_norm": 0.024478715442342234,
"learning_rate": 1.764381607970677e-05,
"loss": 0.5333,
"step": 317
},
{
"epoch": 0.6045627376425855,
"grad_norm": 0.025558126559534863,
"learning_rate": 1.7622361852907506e-05,
"loss": 0.524,
"step": 318
},
{
"epoch": 0.6064638783269962,
"grad_norm": 0.0201537954427199,
"learning_rate": 1.760082356276939e-05,
"loss": 0.3705,
"step": 319
},
{
"epoch": 0.6083650190114068,
"grad_norm": 0.023944335476352968,
"learning_rate": 1.75792014468278e-05,
"loss": 0.5327,
"step": 320
},
{
"epoch": 0.6102661596958175,
"grad_norm": 0.021784871903256658,
"learning_rate": 1.7557495743542586e-05,
"loss": 0.4492,
"step": 321
},
{
"epoch": 0.6121673003802282,
"grad_norm": 0.021130751816902157,
"learning_rate": 1.7535706692295436e-05,
"loss": 0.4425,
"step": 322
},
{
"epoch": 0.6140684410646388,
"grad_norm": 0.01834511623783937,
"learning_rate": 1.7513834533387256e-05,
"loss": 0.3811,
"step": 323
},
{
"epoch": 0.6159695817490495,
"grad_norm": 0.02088833695832576,
"learning_rate": 1.7491879508035488e-05,
"loss": 0.5583,
"step": 324
},
{
"epoch": 0.6178707224334601,
"grad_norm": 0.0245919479523908,
"learning_rate": 1.746984185837149e-05,
"loss": 0.3603,
"step": 325
},
{
"epoch": 0.6197718631178707,
"grad_norm": 0.020568875402404277,
"learning_rate": 1.744772182743782e-05,
"loss": 0.4601,
"step": 326
},
{
"epoch": 0.6216730038022814,
"grad_norm": 0.025449491000498543,
"learning_rate": 1.7425519659185596e-05,
"loss": 0.5307,
"step": 327
},
{
"epoch": 0.623574144486692,
"grad_norm": 0.021055420950145058,
"learning_rate": 1.740323559847179e-05,
"loss": 0.494,
"step": 328
},
{
"epoch": 0.6254752851711026,
"grad_norm": 0.02478574829718437,
"learning_rate": 1.738086989105651e-05,
"loss": 0.3949,
"step": 329
},
{
"epoch": 0.6273764258555133,
"grad_norm": 0.02437888482474706,
"learning_rate": 1.735842278360032e-05,
"loss": 0.451,
"step": 330
},
{
"epoch": 0.629277566539924,
"grad_norm": 0.02216815353892549,
"learning_rate": 1.73358945236615e-05,
"loss": 0.51,
"step": 331
},
{
"epoch": 0.6311787072243346,
"grad_norm": 0.022424223813542376,
"learning_rate": 1.7313285359693322e-05,
"loss": 0.4929,
"step": 332
},
{
"epoch": 0.6330798479087453,
"grad_norm": 0.022029524884207886,
"learning_rate": 1.7290595541041312e-05,
"loss": 0.4765,
"step": 333
},
{
"epoch": 0.6349809885931559,
"grad_norm": 0.021618750137745387,
"learning_rate": 1.7267825317940494e-05,
"loss": 0.536,
"step": 334
},
{
"epoch": 0.6368821292775665,
"grad_norm": 0.022165231076960286,
"learning_rate": 1.724497494151264e-05,
"loss": 0.4764,
"step": 335
},
{
"epoch": 0.6387832699619772,
"grad_norm": 0.024275845667969007,
"learning_rate": 1.7222044663763484e-05,
"loss": 0.4296,
"step": 336
},
{
"epoch": 0.6406844106463878,
"grad_norm": 0.022498217810086048,
"learning_rate": 1.7199034737579962e-05,
"loss": 0.4807,
"step": 337
},
{
"epoch": 0.6425855513307985,
"grad_norm": 0.022762477103989702,
"learning_rate": 1.7175945416727405e-05,
"loss": 0.6568,
"step": 338
},
{
"epoch": 0.6444866920152091,
"grad_norm": 0.01854881996841053,
"learning_rate": 1.7152776955846768e-05,
"loss": 0.3959,
"step": 339
},
{
"epoch": 0.6463878326996197,
"grad_norm": 0.023310529482788885,
"learning_rate": 1.7129529610451775e-05,
"loss": 0.4058,
"step": 340
},
{
"epoch": 0.6482889733840305,
"grad_norm": 0.020208656516758884,
"learning_rate": 1.7106203636926154e-05,
"loss": 0.3985,
"step": 341
},
{
"epoch": 0.6501901140684411,
"grad_norm": 0.022675781235370007,
"learning_rate": 1.7082799292520767e-05,
"loss": 0.4728,
"step": 342
},
{
"epoch": 0.6520912547528517,
"grad_norm": 0.02260039611252313,
"learning_rate": 1.7059316835350806e-05,
"loss": 0.3194,
"step": 343
},
{
"epoch": 0.6539923954372624,
"grad_norm": 0.021816735403941915,
"learning_rate": 1.7035756524392924e-05,
"loss": 0.3993,
"step": 344
},
{
"epoch": 0.655893536121673,
"grad_norm": 0.02352607809906742,
"learning_rate": 1.7012118619482376e-05,
"loss": 0.4171,
"step": 345
},
{
"epoch": 0.6577946768060836,
"grad_norm": 0.018309898170808483,
"learning_rate": 1.6988403381310177e-05,
"loss": 0.4375,
"step": 346
},
{
"epoch": 0.6596958174904943,
"grad_norm": 0.023011889903058493,
"learning_rate": 1.696461107142021e-05,
"loss": 0.5271,
"step": 347
},
{
"epoch": 0.6615969581749049,
"grad_norm": 0.022185873665259752,
"learning_rate": 1.6940741952206342e-05,
"loss": 0.4455,
"step": 348
},
{
"epoch": 0.6634980988593155,
"grad_norm": 0.021145487112860135,
"learning_rate": 1.691679628690953e-05,
"loss": 0.4888,
"step": 349
},
{
"epoch": 0.6653992395437263,
"grad_norm": 0.0197337711656993,
"learning_rate": 1.6892774339614927e-05,
"loss": 0.3221,
"step": 350
},
{
"epoch": 0.6673003802281369,
"grad_norm": 0.021128667885235902,
"learning_rate": 1.686867637524896e-05,
"loss": 0.4796,
"step": 351
},
{
"epoch": 0.6692015209125475,
"grad_norm": 0.021485021868132094,
"learning_rate": 1.6844502659576414e-05,
"loss": 0.3866,
"step": 352
},
{
"epoch": 0.6711026615969582,
"grad_norm": 0.021674363310584633,
"learning_rate": 1.6820253459197493e-05,
"loss": 0.4131,
"step": 353
},
{
"epoch": 0.6730038022813688,
"grad_norm": 0.022317690282530892,
"learning_rate": 1.679592904154489e-05,
"loss": 0.4718,
"step": 354
},
{
"epoch": 0.6749049429657795,
"grad_norm": 0.018420112637605318,
"learning_rate": 1.677152967488084e-05,
"loss": 0.3682,
"step": 355
},
{
"epoch": 0.6768060836501901,
"grad_norm": 0.021728437667337796,
"learning_rate": 1.6747055628294134e-05,
"loss": 0.4865,
"step": 356
},
{
"epoch": 0.6787072243346007,
"grad_norm": 0.021879642157367866,
"learning_rate": 1.6722507171697184e-05,
"loss": 0.418,
"step": 357
},
{
"epoch": 0.6806083650190115,
"grad_norm": 0.02041980559071294,
"learning_rate": 1.669788457582304e-05,
"loss": 0.44,
"step": 358
},
{
"epoch": 0.6825095057034221,
"grad_norm": 0.02525296949818493,
"learning_rate": 1.6673188112222394e-05,
"loss": 0.4058,
"step": 359
},
{
"epoch": 0.6844106463878327,
"grad_norm": 0.027087654040755537,
"learning_rate": 1.6648418053260585e-05,
"loss": 0.4206,
"step": 360
},
{
"epoch": 0.6863117870722434,
"grad_norm": 0.02064549274424258,
"learning_rate": 1.6623574672114596e-05,
"loss": 0.5434,
"step": 361
},
{
"epoch": 0.688212927756654,
"grad_norm": 0.025193009760092363,
"learning_rate": 1.6598658242770054e-05,
"loss": 0.5539,
"step": 362
},
{
"epoch": 0.6901140684410646,
"grad_norm": 0.023006148706161383,
"learning_rate": 1.6573669040018202e-05,
"loss": 0.4982,
"step": 363
},
{
"epoch": 0.6920152091254753,
"grad_norm": 0.02394923199036728,
"learning_rate": 1.6548607339452853e-05,
"loss": 0.4504,
"step": 364
},
{
"epoch": 0.6939163498098859,
"grad_norm": 0.024973727525077836,
"learning_rate": 1.652347341746737e-05,
"loss": 0.4296,
"step": 365
},
{
"epoch": 0.6958174904942965,
"grad_norm": 0.02229406442674028,
"learning_rate": 1.6498267551251618e-05,
"loss": 0.6645,
"step": 366
},
{
"epoch": 0.6977186311787072,
"grad_norm": 0.02196890781900034,
"learning_rate": 1.6472990018788884e-05,
"loss": 0.4139,
"step": 367
},
{
"epoch": 0.6996197718631179,
"grad_norm": 0.01864786240108333,
"learning_rate": 1.644764109885284e-05,
"loss": 0.3669,
"step": 368
},
{
"epoch": 0.7015209125475285,
"grad_norm": 0.023341226120807423,
"learning_rate": 1.642222107100446e-05,
"loss": 0.4633,
"step": 369
},
{
"epoch": 0.7034220532319392,
"grad_norm": 0.01791373151822567,
"learning_rate": 1.6396730215588913e-05,
"loss": 0.432,
"step": 370
},
{
"epoch": 0.7053231939163498,
"grad_norm": 0.023304889020227138,
"learning_rate": 1.6371168813732514e-05,
"loss": 0.4637,
"step": 371
},
{
"epoch": 0.7072243346007605,
"grad_norm": 0.02409824499740041,
"learning_rate": 1.6345537147339578e-05,
"loss": 0.451,
"step": 372
},
{
"epoch": 0.7091254752851711,
"grad_norm": 0.023503094615128773,
"learning_rate": 1.6319835499089358e-05,
"loss": 0.5037,
"step": 373
},
{
"epoch": 0.7110266159695817,
"grad_norm": 0.02100086883115099,
"learning_rate": 1.6294064152432878e-05,
"loss": 0.3789,
"step": 374
},
{
"epoch": 0.7129277566539924,
"grad_norm": 0.02271881779830291,
"learning_rate": 1.626822339158985e-05,
"loss": 0.4531,
"step": 375
},
{
"epoch": 0.714828897338403,
"grad_norm": 0.02500592478382567,
"learning_rate": 1.6242313501545522e-05,
"loss": 0.423,
"step": 376
},
{
"epoch": 0.7167300380228137,
"grad_norm": 0.02235032483913223,
"learning_rate": 1.621633476804752e-05,
"loss": 0.4618,
"step": 377
},
{
"epoch": 0.7186311787072244,
"grad_norm": 0.02151840511807487,
"learning_rate": 1.6190287477602716e-05,
"loss": 0.487,
"step": 378
},
{
"epoch": 0.720532319391635,
"grad_norm": 0.025756572129519126,
"learning_rate": 1.6164171917474078e-05,
"loss": 0.4099,
"step": 379
},
{
"epoch": 0.7224334600760456,
"grad_norm": 0.02018147798619793,
"learning_rate": 1.6137988375677466e-05,
"loss": 0.3906,
"step": 380
},
{
"epoch": 0.7243346007604563,
"grad_norm": 0.020746327994583716,
"learning_rate": 1.6111737140978495e-05,
"loss": 0.5042,
"step": 381
},
{
"epoch": 0.7262357414448669,
"grad_norm": 0.02087825161781339,
"learning_rate": 1.6085418502889315e-05,
"loss": 0.4793,
"step": 382
},
{
"epoch": 0.7281368821292775,
"grad_norm": 0.02597453558637949,
"learning_rate": 1.6059032751665454e-05,
"loss": 0.5275,
"step": 383
},
{
"epoch": 0.7300380228136882,
"grad_norm": 0.023924733808265878,
"learning_rate": 1.6032580178302585e-05,
"loss": 0.4981,
"step": 384
},
{
"epoch": 0.7319391634980988,
"grad_norm": 0.05994054536254508,
"learning_rate": 1.600606107453333e-05,
"loss": 0.5581,
"step": 385
},
{
"epoch": 0.7338403041825095,
"grad_norm": 0.022744320177798528,
"learning_rate": 1.597947573282405e-05,
"loss": 0.5067,
"step": 386
},
{
"epoch": 0.7357414448669202,
"grad_norm": 0.02367987566710115,
"learning_rate": 1.5952824446371608e-05,
"loss": 0.4065,
"step": 387
},
{
"epoch": 0.7376425855513308,
"grad_norm": 0.022780020712552165,
"learning_rate": 1.592610750910014e-05,
"loss": 0.3968,
"step": 388
},
{
"epoch": 0.7395437262357415,
"grad_norm": 0.02119299594456647,
"learning_rate": 1.589932521565781e-05,
"loss": 0.5469,
"step": 389
},
{
"epoch": 0.7414448669201521,
"grad_norm": 0.019341262557617835,
"learning_rate": 1.587247786141358e-05,
"loss": 0.4319,
"step": 390
},
{
"epoch": 0.7433460076045627,
"grad_norm": 0.02055570641111801,
"learning_rate": 1.5845565742453906e-05,
"loss": 0.4241,
"step": 391
},
{
"epoch": 0.7452471482889734,
"grad_norm": 0.024031176474825826,
"learning_rate": 1.581858915557953e-05,
"loss": 0.4805,
"step": 392
},
{
"epoch": 0.747148288973384,
"grad_norm": 0.020151689729205665,
"learning_rate": 1.5791548398302167e-05,
"loss": 0.5204,
"step": 393
},
{
"epoch": 0.7490494296577946,
"grad_norm": 0.022487690028723358,
"learning_rate": 1.5764443768841234e-05,
"loss": 0.4249,
"step": 394
},
{
"epoch": 0.7509505703422054,
"grad_norm": 0.01982347263114696,
"learning_rate": 1.5737275566120577e-05,
"loss": 0.406,
"step": 395
},
{
"epoch": 0.752851711026616,
"grad_norm": 0.02086227032375837,
"learning_rate": 1.5710044089765144e-05,
"loss": 0.4371,
"step": 396
},
{
"epoch": 0.7547528517110266,
"grad_norm": 0.02108925366040013,
"learning_rate": 1.5682749640097708e-05,
"loss": 0.442,
"step": 397
},
{
"epoch": 0.7566539923954373,
"grad_norm": 0.023564638230995968,
"learning_rate": 1.565539251813554e-05,
"loss": 0.5355,
"step": 398
},
{
"epoch": 0.7585551330798479,
"grad_norm": 0.020789849453501902,
"learning_rate": 1.5627973025587093e-05,
"loss": 0.4253,
"step": 399
},
{
"epoch": 0.7604562737642585,
"grad_norm": 0.023234777071662778,
"learning_rate": 1.560049146484868e-05,
"loss": 0.4928,
"step": 400
},
{
"epoch": 0.7623574144486692,
"grad_norm": 0.022799909007585953,
"learning_rate": 1.5572948139001128e-05,
"loss": 0.4247,
"step": 401
},
{
"epoch": 0.7642585551330798,
"grad_norm": 0.021289848782095718,
"learning_rate": 1.5545343351806443e-05,
"loss": 0.508,
"step": 402
},
{
"epoch": 0.7661596958174905,
"grad_norm": 0.021905746023760754,
"learning_rate": 1.551767740770446e-05,
"loss": 0.5947,
"step": 403
},
{
"epoch": 0.7680608365019012,
"grad_norm": 0.02386151968622635,
"learning_rate": 1.5489950611809484e-05,
"loss": 0.4853,
"step": 404
},
{
"epoch": 0.7699619771863118,
"grad_norm": 0.02351691541197354,
"learning_rate": 1.5462163269906928e-05,
"loss": 0.457,
"step": 405
},
{
"epoch": 0.7718631178707225,
"grad_norm": 0.02703946419471593,
"learning_rate": 1.5434315688449924e-05,
"loss": 0.429,
"step": 406
},
{
"epoch": 0.7737642585551331,
"grad_norm": 0.021253357245547846,
"learning_rate": 1.5406408174555978e-05,
"loss": 0.4011,
"step": 407
},
{
"epoch": 0.7756653992395437,
"grad_norm": 0.021592073586737193,
"learning_rate": 1.5378441036003543e-05,
"loss": 0.3939,
"step": 408
},
{
"epoch": 0.7775665399239544,
"grad_norm": 0.023635965388808643,
"learning_rate": 1.535041458122865e-05,
"loss": 0.4447,
"step": 409
},
{
"epoch": 0.779467680608365,
"grad_norm": 0.021614797502256346,
"learning_rate": 1.5322329119321508e-05,
"loss": 0.3896,
"step": 410
},
{
"epoch": 0.7813688212927756,
"grad_norm": 0.029020909400450004,
"learning_rate": 1.529418496002308e-05,
"loss": 0.4969,
"step": 411
},
{
"epoch": 0.7832699619771863,
"grad_norm": 0.025667462527941966,
"learning_rate": 1.5265982413721662e-05,
"loss": 0.4258,
"step": 412
},
{
"epoch": 0.785171102661597,
"grad_norm": 0.0219880878115105,
"learning_rate": 1.5237721791449497e-05,
"loss": 0.4472,
"step": 413
},
{
"epoch": 0.7870722433460076,
"grad_norm": 0.020681701545778697,
"learning_rate": 1.5209403404879305e-05,
"loss": 0.5025,
"step": 414
},
{
"epoch": 0.7889733840304183,
"grad_norm": 0.02569506503249528,
"learning_rate": 1.5181027566320858e-05,
"loss": 0.4951,
"step": 415
},
{
"epoch": 0.7908745247148289,
"grad_norm": 0.02403074940855541,
"learning_rate": 1.5152594588717544e-05,
"loss": 0.4516,
"step": 416
},
{
"epoch": 0.7927756653992395,
"grad_norm": 0.03162539286762685,
"learning_rate": 1.5124104785642909e-05,
"loss": 0.4576,
"step": 417
},
{
"epoch": 0.7946768060836502,
"grad_norm": 0.02780725707898336,
"learning_rate": 1.5095558471297196e-05,
"loss": 0.4441,
"step": 418
},
{
"epoch": 0.7965779467680608,
"grad_norm": 0.021938480615319306,
"learning_rate": 1.5066955960503893e-05,
"loss": 0.4821,
"step": 419
},
{
"epoch": 0.7984790874524715,
"grad_norm": 0.022669187205589948,
"learning_rate": 1.5038297568706244e-05,
"loss": 0.3651,
"step": 420
},
{
"epoch": 0.8003802281368821,
"grad_norm": 0.029651223858315957,
"learning_rate": 1.5009583611963772e-05,
"loss": 0.3709,
"step": 421
},
{
"epoch": 0.8022813688212928,
"grad_norm": 0.020262767284707564,
"learning_rate": 1.4980814406948806e-05,
"loss": 0.3868,
"step": 422
},
{
"epoch": 0.8041825095057035,
"grad_norm": 0.0313851795438847,
"learning_rate": 1.4951990270942991e-05,
"loss": 0.4345,
"step": 423
},
{
"epoch": 0.8060836501901141,
"grad_norm": 0.026505025778599832,
"learning_rate": 1.492311152183376e-05,
"loss": 0.4845,
"step": 424
},
{
"epoch": 0.8079847908745247,
"grad_norm": 0.024933250165890146,
"learning_rate": 1.4894178478110856e-05,
"loss": 0.5436,
"step": 425
},
{
"epoch": 0.8098859315589354,
"grad_norm": 0.02668529314177586,
"learning_rate": 1.4865191458862816e-05,
"loss": 0.4722,
"step": 426
},
{
"epoch": 0.811787072243346,
"grad_norm": 0.023968647430953227,
"learning_rate": 1.4836150783773442e-05,
"loss": 0.4006,
"step": 427
},
{
"epoch": 0.8136882129277566,
"grad_norm": 0.028240700565109782,
"learning_rate": 1.4807056773118276e-05,
"loss": 0.4548,
"step": 428
},
{
"epoch": 0.8155893536121673,
"grad_norm": 0.024113176209241565,
"learning_rate": 1.4777909747761085e-05,
"loss": 0.4394,
"step": 429
},
{
"epoch": 0.8174904942965779,
"grad_norm": 0.023240692257416155,
"learning_rate": 1.4748710029150296e-05,
"loss": 0.5083,
"step": 430
},
{
"epoch": 0.8193916349809885,
"grad_norm": 0.022014547992322716,
"learning_rate": 1.4719457939315468e-05,
"loss": 0.3793,
"step": 431
},
{
"epoch": 0.8212927756653993,
"grad_norm": 0.025056756565885647,
"learning_rate": 1.4690153800863743e-05,
"loss": 0.4505,
"step": 432
},
{
"epoch": 0.8231939163498099,
"grad_norm": 0.024078196797270524,
"learning_rate": 1.4660797936976278e-05,
"loss": 0.5511,
"step": 433
},
{
"epoch": 0.8250950570342205,
"grad_norm": 0.023506365080185394,
"learning_rate": 1.4631390671404682e-05,
"loss": 0.486,
"step": 434
},
{
"epoch": 0.8269961977186312,
"grad_norm": 0.02656548640736279,
"learning_rate": 1.460193232846745e-05,
"loss": 0.4877,
"step": 435
},
{
"epoch": 0.8288973384030418,
"grad_norm": 0.02521957317818189,
"learning_rate": 1.4572423233046386e-05,
"loss": 0.4654,
"step": 436
},
{
"epoch": 0.8307984790874525,
"grad_norm": 0.02696732985436355,
"learning_rate": 1.4542863710583022e-05,
"loss": 0.5085,
"step": 437
},
{
"epoch": 0.8326996197718631,
"grad_norm": 0.024288469099333042,
"learning_rate": 1.4513254087075015e-05,
"loss": 0.5373,
"step": 438
},
{
"epoch": 0.8346007604562737,
"grad_norm": 0.023081137704624097,
"learning_rate": 1.4483594689072571e-05,
"loss": 0.4279,
"step": 439
},
{
"epoch": 0.8365019011406845,
"grad_norm": 0.02353653197134096,
"learning_rate": 1.4453885843674837e-05,
"loss": 0.445,
"step": 440
},
{
"epoch": 0.8384030418250951,
"grad_norm": 0.021931438665748156,
"learning_rate": 1.4424127878526278e-05,
"loss": 0.372,
"step": 441
},
{
"epoch": 0.8403041825095057,
"grad_norm": 0.022816959298283885,
"learning_rate": 1.4394321121813093e-05,
"loss": 0.4521,
"step": 442
},
{
"epoch": 0.8422053231939164,
"grad_norm": 0.022654432569100512,
"learning_rate": 1.436446590225957e-05,
"loss": 0.4813,
"step": 443
},
{
"epoch": 0.844106463878327,
"grad_norm": 0.022714918777658636,
"learning_rate": 1.433456254912447e-05,
"loss": 0.4993,
"step": 444
},
{
"epoch": 0.8460076045627376,
"grad_norm": 0.02442999457743802,
"learning_rate": 1.4304611392197399e-05,
"loss": 0.4246,
"step": 445
},
{
"epoch": 0.8479087452471483,
"grad_norm": 0.021928052281800055,
"learning_rate": 1.427461276179517e-05,
"loss": 0.4304,
"step": 446
},
{
"epoch": 0.8498098859315589,
"grad_norm": 0.02141867354122271,
"learning_rate": 1.4244566988758152e-05,
"loss": 0.3977,
"step": 447
},
{
"epoch": 0.8517110266159695,
"grad_norm": 0.02458743104943235,
"learning_rate": 1.4214474404446633e-05,
"loss": 0.4378,
"step": 448
},
{
"epoch": 0.8536121673003803,
"grad_norm": 0.019632792154314082,
"learning_rate": 1.4184335340737158e-05,
"loss": 0.3955,
"step": 449
},
{
"epoch": 0.8555133079847909,
"grad_norm": 0.02484904211495459,
"learning_rate": 1.4154150130018867e-05,
"loss": 0.419,
"step": 450
},
{
"epoch": 0.8574144486692015,
"grad_norm": 0.02272220324215502,
"learning_rate": 1.4123919105189836e-05,
"loss": 0.4037,
"step": 451
},
{
"epoch": 0.8593155893536122,
"grad_norm": 0.026986410749335596,
"learning_rate": 1.4093642599653406e-05,
"loss": 0.5189,
"step": 452
},
{
"epoch": 0.8612167300380228,
"grad_norm": 0.02094686405878515,
"learning_rate": 1.40633209473145e-05,
"loss": 0.4121,
"step": 453
},
{
"epoch": 0.8631178707224335,
"grad_norm": 0.02805756954495035,
"learning_rate": 1.4032954482575938e-05,
"loss": 0.4802,
"step": 454
},
{
"epoch": 0.8650190114068441,
"grad_norm": 0.024880650473757853,
"learning_rate": 1.4002543540334766e-05,
"loss": 0.4679,
"step": 455
},
{
"epoch": 0.8669201520912547,
"grad_norm": 0.022025534936640348,
"learning_rate": 1.3972088455978537e-05,
"loss": 0.4339,
"step": 456
},
{
"epoch": 0.8688212927756654,
"grad_norm": 0.02271172419542242,
"learning_rate": 1.3941589565381635e-05,
"loss": 0.4472,
"step": 457
},
{
"epoch": 0.870722433460076,
"grad_norm": 0.02456897431856478,
"learning_rate": 1.391104720490156e-05,
"loss": 0.5024,
"step": 458
},
{
"epoch": 0.8726235741444867,
"grad_norm": 0.02458479535995488,
"learning_rate": 1.3880461711375224e-05,
"loss": 0.5078,
"step": 459
},
{
"epoch": 0.8745247148288974,
"grad_norm": 0.02440410211111402,
"learning_rate": 1.3849833422115221e-05,
"loss": 0.4871,
"step": 460
},
{
"epoch": 0.876425855513308,
"grad_norm": 0.021736397843613076,
"learning_rate": 1.3819162674906134e-05,
"loss": 0.4741,
"step": 461
},
{
"epoch": 0.8783269961977186,
"grad_norm": 0.020438052604190595,
"learning_rate": 1.378844980800078e-05,
"loss": 0.3974,
"step": 462
},
{
"epoch": 0.8802281368821293,
"grad_norm": 0.022715925959570137,
"learning_rate": 1.3757695160116502e-05,
"loss": 0.434,
"step": 463
},
{
"epoch": 0.8821292775665399,
"grad_norm": 0.024729238859494334,
"learning_rate": 1.3726899070431423e-05,
"loss": 0.4243,
"step": 464
},
{
"epoch": 0.8840304182509505,
"grad_norm": 0.021886379292725234,
"learning_rate": 1.3696061878580707e-05,
"loss": 0.4074,
"step": 465
},
{
"epoch": 0.8859315589353612,
"grad_norm": 0.022623550123516575,
"learning_rate": 1.3665183924652817e-05,
"loss": 0.4924,
"step": 466
},
{
"epoch": 0.8878326996197718,
"grad_norm": 0.021674597567570526,
"learning_rate": 1.3634265549185755e-05,
"loss": 0.4528,
"step": 467
},
{
"epoch": 0.8897338403041825,
"grad_norm": 0.021414986192180713,
"learning_rate": 1.3603307093163319e-05,
"loss": 0.3658,
"step": 468
},
{
"epoch": 0.8916349809885932,
"grad_norm": 0.021523850295941727,
"learning_rate": 1.3572308898011328e-05,
"loss": 0.4219,
"step": 469
},
{
"epoch": 0.8935361216730038,
"grad_norm": 0.022491621170717423,
"learning_rate": 1.3541271305593878e-05,
"loss": 0.5062,
"step": 470
},
{
"epoch": 0.8954372623574145,
"grad_norm": 0.023578729751256165,
"learning_rate": 1.3510194658209547e-05,
"loss": 0.4714,
"step": 471
},
{
"epoch": 0.8973384030418251,
"grad_norm": 0.02479993313265921,
"learning_rate": 1.3479079298587634e-05,
"loss": 0.4418,
"step": 472
},
{
"epoch": 0.8992395437262357,
"grad_norm": 0.024770693363266767,
"learning_rate": 1.3447925569884374e-05,
"loss": 0.4312,
"step": 473
},
{
"epoch": 0.9011406844106464,
"grad_norm": 0.02503485087771604,
"learning_rate": 1.3416733815679166e-05,
"loss": 0.4861,
"step": 474
},
{
"epoch": 0.903041825095057,
"grad_norm": 0.02307394045917917,
"learning_rate": 1.3385504379970764e-05,
"loss": 0.4166,
"step": 475
},
{
"epoch": 0.9049429657794676,
"grad_norm": 0.025894998951279422,
"learning_rate": 1.3354237607173494e-05,
"loss": 0.5021,
"step": 476
},
{
"epoch": 0.9068441064638784,
"grad_norm": 0.02128176686440997,
"learning_rate": 1.3322933842113457e-05,
"loss": 0.4473,
"step": 477
},
{
"epoch": 0.908745247148289,
"grad_norm": 0.023893280860003332,
"learning_rate": 1.3291593430024727e-05,
"loss": 0.4755,
"step": 478
},
{
"epoch": 0.9106463878326996,
"grad_norm": 0.02449762016338503,
"learning_rate": 1.3260216716545534e-05,
"loss": 0.3953,
"step": 479
},
{
"epoch": 0.9125475285171103,
"grad_norm": 0.021110069746746216,
"learning_rate": 1.3228804047714462e-05,
"loss": 0.3212,
"step": 480
},
{
"epoch": 0.9144486692015209,
"grad_norm": 0.02299821393531202,
"learning_rate": 1.319735576996663e-05,
"loss": 0.4059,
"step": 481
},
{
"epoch": 0.9163498098859315,
"grad_norm": 0.022805233387983515,
"learning_rate": 1.3165872230129869e-05,
"loss": 0.4378,
"step": 482
},
{
"epoch": 0.9182509505703422,
"grad_norm": 0.022483195363811,
"learning_rate": 1.3134353775420895e-05,
"loss": 0.4952,
"step": 483
},
{
"epoch": 0.9201520912547528,
"grad_norm": 0.027980344075661134,
"learning_rate": 1.3102800753441488e-05,
"loss": 0.453,
"step": 484
},
{
"epoch": 0.9220532319391636,
"grad_norm": 0.022320233170224718,
"learning_rate": 1.3071213512174655e-05,
"loss": 0.4042,
"step": 485
},
{
"epoch": 0.9239543726235742,
"grad_norm": 0.027021346941736732,
"learning_rate": 1.3039592399980785e-05,
"loss": 0.4668,
"step": 486
},
{
"epoch": 0.9258555133079848,
"grad_norm": 0.02482265015460327,
"learning_rate": 1.3007937765593818e-05,
"loss": 0.5227,
"step": 487
},
{
"epoch": 0.9277566539923955,
"grad_norm": 0.02357348090540923,
"learning_rate": 1.2976249958117395e-05,
"loss": 0.4767,
"step": 488
},
{
"epoch": 0.9296577946768061,
"grad_norm": 0.023443354906239822,
"learning_rate": 1.2944529327021002e-05,
"loss": 0.405,
"step": 489
},
{
"epoch": 0.9315589353612167,
"grad_norm": 0.02179663602896819,
"learning_rate": 1.291277622213612e-05,
"loss": 0.4287,
"step": 490
},
{
"epoch": 0.9334600760456274,
"grad_norm": 0.023454518004330533,
"learning_rate": 1.2880990993652379e-05,
"loss": 0.3772,
"step": 491
},
{
"epoch": 0.935361216730038,
"grad_norm": 0.02290314421630447,
"learning_rate": 1.2849173992113669e-05,
"loss": 0.4915,
"step": 492
},
{
"epoch": 0.9372623574144486,
"grad_norm": 0.023222346475490627,
"learning_rate": 1.2817325568414299e-05,
"loss": 0.4789,
"step": 493
},
{
"epoch": 0.9391634980988594,
"grad_norm": 0.02409598567792761,
"learning_rate": 1.2785446073795118e-05,
"loss": 0.4782,
"step": 494
},
{
"epoch": 0.94106463878327,
"grad_norm": 0.022615260816886574,
"learning_rate": 1.2753535859839638e-05,
"loss": 0.433,
"step": 495
},
{
"epoch": 0.9429657794676806,
"grad_norm": 0.025611694327824334,
"learning_rate": 1.272159527847016e-05,
"loss": 0.4573,
"step": 496
},
{
"epoch": 0.9448669201520913,
"grad_norm": 0.025768369769655665,
"learning_rate": 1.2689624681943897e-05,
"loss": 0.462,
"step": 497
},
{
"epoch": 0.9467680608365019,
"grad_norm": 0.02301862416038207,
"learning_rate": 1.2657624422849077e-05,
"loss": 0.4171,
"step": 498
},
{
"epoch": 0.9486692015209125,
"grad_norm": 0.022425187287103614,
"learning_rate": 1.2625594854101066e-05,
"loss": 0.4152,
"step": 499
},
{
"epoch": 0.9505703422053232,
"grad_norm": 0.02317505253670741,
"learning_rate": 1.2593536328938471e-05,
"loss": 0.4775,
"step": 500
},
{
"epoch": 0.9524714828897338,
"grad_norm": 0.022725516030892436,
"learning_rate": 1.2561449200919253e-05,
"loss": 0.5123,
"step": 501
},
{
"epoch": 0.9543726235741445,
"grad_norm": 0.02563269287207282,
"learning_rate": 1.2529333823916807e-05,
"loss": 0.4626,
"step": 502
},
{
"epoch": 0.9562737642585551,
"grad_norm": 0.02440201438687382,
"learning_rate": 1.2497190552116082e-05,
"loss": 0.5584,
"step": 503
},
{
"epoch": 0.9581749049429658,
"grad_norm": 0.025258409411193533,
"learning_rate": 1.2465019740009662e-05,
"loss": 0.4721,
"step": 504
},
{
"epoch": 0.9600760456273765,
"grad_norm": 0.02364236622754602,
"learning_rate": 1.2432821742393854e-05,
"loss": 0.4637,
"step": 505
},
{
"epoch": 0.9619771863117871,
"grad_norm": 0.022744877336730626,
"learning_rate": 1.2400596914364792e-05,
"loss": 0.4163,
"step": 506
},
{
"epoch": 0.9638783269961977,
"grad_norm": 0.02512981829788003,
"learning_rate": 1.2368345611314508e-05,
"loss": 0.4209,
"step": 507
},
{
"epoch": 0.9657794676806084,
"grad_norm": 0.02396214976378719,
"learning_rate": 1.2336068188927002e-05,
"loss": 0.4876,
"step": 508
},
{
"epoch": 0.967680608365019,
"grad_norm": 0.024846858848635564,
"learning_rate": 1.2303765003174342e-05,
"loss": 0.4766,
"step": 509
},
{
"epoch": 0.9695817490494296,
"grad_norm": 0.024647771640303358,
"learning_rate": 1.2271436410312727e-05,
"loss": 0.4745,
"step": 510
},
{
"epoch": 0.9714828897338403,
"grad_norm": 0.028460909629351355,
"learning_rate": 1.2239082766878557e-05,
"loss": 0.443,
"step": 511
},
{
"epoch": 0.973384030418251,
"grad_norm": 0.026842716136457133,
"learning_rate": 1.2206704429684504e-05,
"loss": 0.416,
"step": 512
},
{
"epoch": 0.9752851711026616,
"grad_norm": 0.023577587200559337,
"learning_rate": 1.2174301755815572e-05,
"loss": 0.4547,
"step": 513
},
{
"epoch": 0.9771863117870723,
"grad_norm": 0.02434178157072622,
"learning_rate": 1.2141875102625166e-05,
"loss": 0.4154,
"step": 514
},
{
"epoch": 0.9790874524714829,
"grad_norm": 0.022686551363613607,
"learning_rate": 1.2109424827731144e-05,
"loss": 0.4248,
"step": 515
},
{
"epoch": 0.9809885931558935,
"grad_norm": 0.027765889183457126,
"learning_rate": 1.2076951289011884e-05,
"loss": 0.4786,
"step": 516
},
{
"epoch": 0.9828897338403042,
"grad_norm": 0.026014404370096878,
"learning_rate": 1.204445484460232e-05,
"loss": 0.3835,
"step": 517
},
{
"epoch": 0.9847908745247148,
"grad_norm": 0.02536068801523813,
"learning_rate": 1.2011935852890004e-05,
"loss": 0.4766,
"step": 518
},
{
"epoch": 0.9866920152091255,
"grad_norm": 0.025270660975692583,
"learning_rate": 1.1979394672511156e-05,
"loss": 0.4271,
"step": 519
},
{
"epoch": 0.9885931558935361,
"grad_norm": 0.023163661163739562,
"learning_rate": 1.19468316623467e-05,
"loss": 0.4191,
"step": 520
},
{
"epoch": 0.9904942965779467,
"grad_norm": 0.025133903922973964,
"learning_rate": 1.1914247181518312e-05,
"loss": 0.453,
"step": 521
},
{
"epoch": 0.9923954372623575,
"grad_norm": 0.022840078992228126,
"learning_rate": 1.1881641589384456e-05,
"loss": 0.3876,
"step": 522
},
{
"epoch": 0.9942965779467681,
"grad_norm": 0.02952192013190572,
"learning_rate": 1.1849015245536424e-05,
"loss": 0.4796,
"step": 523
},
{
"epoch": 0.9961977186311787,
"grad_norm": 0.0255544735356746,
"learning_rate": 1.1816368509794365e-05,
"loss": 0.4575,
"step": 524
},
{
"epoch": 0.9980988593155894,
"grad_norm": 0.025426553898411263,
"learning_rate": 1.1783701742203326e-05,
"loss": 0.4142,
"step": 525
},
{
"epoch": 1.0,
"grad_norm": 0.02487998894271571,
"learning_rate": 1.1751015303029272e-05,
"loss": 0.4154,
"step": 526
},
{
"epoch": 1.0,
"eval_loss": 0.49419376254081726,
"eval_runtime": 2.0606,
"eval_samples_per_second": 2.912,
"eval_steps_per_second": 0.485,
"step": 526
},
{
"epoch": 1.0019011406844107,
"grad_norm": 0.026839867865076257,
"learning_rate": 1.1718309552755118e-05,
"loss": 0.5472,
"step": 527
},
{
"epoch": 1.0038022813688212,
"grad_norm": 0.02475665144540004,
"learning_rate": 1.1685584852076746e-05,
"loss": 0.4676,
"step": 528
},
{
"epoch": 1.005703422053232,
"grad_norm": 0.02330183147946208,
"learning_rate": 1.1652841561899042e-05,
"loss": 0.3749,
"step": 529
},
{
"epoch": 1.0076045627376427,
"grad_norm": 0.025076421971174816,
"learning_rate": 1.1620080043331901e-05,
"loss": 0.5404,
"step": 530
},
{
"epoch": 1.0095057034220531,
"grad_norm": 0.02418624605710623,
"learning_rate": 1.1587300657686254e-05,
"loss": 0.5074,
"step": 531
},
{
"epoch": 1.0114068441064639,
"grad_norm": 0.02479812200820215,
"learning_rate": 1.1554503766470069e-05,
"loss": 0.4338,
"step": 532
},
{
"epoch": 1.0133079847908746,
"grad_norm": 0.024884250210395493,
"learning_rate": 1.1521689731384391e-05,
"loss": 0.4654,
"step": 533
},
{
"epoch": 1.015209125475285,
"grad_norm": 0.026548403950977323,
"learning_rate": 1.1488858914319321e-05,
"loss": 0.4087,
"step": 534
},
{
"epoch": 1.0171102661596958,
"grad_norm": 0.025613189908928795,
"learning_rate": 1.1456011677350052e-05,
"loss": 0.5427,
"step": 535
},
{
"epoch": 1.0190114068441065,
"grad_norm": 0.023186535836589698,
"learning_rate": 1.1423148382732854e-05,
"loss": 0.4261,
"step": 536
},
{
"epoch": 1.020912547528517,
"grad_norm": 0.025681515076642358,
"learning_rate": 1.1390269392901096e-05,
"loss": 0.4077,
"step": 537
},
{
"epoch": 1.0228136882129277,
"grad_norm": 0.021744852880452904,
"learning_rate": 1.1357375070461241e-05,
"loss": 0.4751,
"step": 538
},
{
"epoch": 1.0247148288973384,
"grad_norm": 0.028443593252172297,
"learning_rate": 1.1324465778188846e-05,
"loss": 0.4456,
"step": 539
},
{
"epoch": 1.026615969581749,
"grad_norm": 0.03000660451469647,
"learning_rate": 1.1291541879024568e-05,
"loss": 0.5253,
"step": 540
},
{
"epoch": 1.0285171102661597,
"grad_norm": 0.02368491275040552,
"learning_rate": 1.1258603736070145e-05,
"loss": 0.4023,
"step": 541
},
{
"epoch": 1.0304182509505704,
"grad_norm": 0.02836407575641823,
"learning_rate": 1.1225651712584413e-05,
"loss": 0.5033,
"step": 542
},
{
"epoch": 1.032319391634981,
"grad_norm": 0.022941031264003417,
"learning_rate": 1.1192686171979288e-05,
"loss": 0.3946,
"step": 543
},
{
"epoch": 1.0342205323193916,
"grad_norm": 0.023139941818018577,
"learning_rate": 1.1159707477815756e-05,
"loss": 0.4706,
"step": 544
},
{
"epoch": 1.0361216730038023,
"grad_norm": 0.023983638303565175,
"learning_rate": 1.1126715993799875e-05,
"loss": 0.5789,
"step": 545
},
{
"epoch": 1.038022813688213,
"grad_norm": 0.026461190964423308,
"learning_rate": 1.1093712083778748e-05,
"loss": 0.3951,
"step": 546
},
{
"epoch": 1.0399239543726235,
"grad_norm": 0.02236185807063053,
"learning_rate": 1.1060696111736515e-05,
"loss": 0.3543,
"step": 547
},
{
"epoch": 1.0418250950570342,
"grad_norm": 0.02192591241120657,
"learning_rate": 1.1027668441790358e-05,
"loss": 0.4706,
"step": 548
},
{
"epoch": 1.043726235741445,
"grad_norm": 0.02426010800732934,
"learning_rate": 1.099462943818646e-05,
"loss": 0.4082,
"step": 549
},
{
"epoch": 1.0456273764258555,
"grad_norm": 0.02508083322632236,
"learning_rate": 1.0961579465295987e-05,
"loss": 0.5272,
"step": 550
},
{
"epoch": 1.0475285171102662,
"grad_norm": 0.03202071310568031,
"learning_rate": 1.0928518887611099e-05,
"loss": 0.4791,
"step": 551
},
{
"epoch": 1.049429657794677,
"grad_norm": 0.02210572731788688,
"learning_rate": 1.0895448069740902e-05,
"loss": 0.4891,
"step": 552
},
{
"epoch": 1.0513307984790874,
"grad_norm": 0.023820693600161792,
"learning_rate": 1.0862367376407433e-05,
"loss": 0.4378,
"step": 553
},
{
"epoch": 1.053231939163498,
"grad_norm": 0.021388417872325642,
"learning_rate": 1.0829277172441648e-05,
"loss": 0.4474,
"step": 554
},
{
"epoch": 1.0551330798479088,
"grad_norm": 0.026332353861382985,
"learning_rate": 1.0796177822779384e-05,
"loss": 0.4167,
"step": 555
},
{
"epoch": 1.0570342205323193,
"grad_norm": 0.028186191098638017,
"learning_rate": 1.0763069692457346e-05,
"loss": 0.3917,
"step": 556
},
{
"epoch": 1.05893536121673,
"grad_norm": 0.026368775979214235,
"learning_rate": 1.0729953146609076e-05,
"loss": 0.4001,
"step": 557
},
{
"epoch": 1.0608365019011408,
"grad_norm": 0.0265502482480294,
"learning_rate": 1.0696828550460928e-05,
"loss": 0.4659,
"step": 558
},
{
"epoch": 1.0627376425855513,
"grad_norm": 0.02622664842688001,
"learning_rate": 1.0663696269328034e-05,
"loss": 0.4399,
"step": 559
},
{
"epoch": 1.064638783269962,
"grad_norm": 0.02349997729830601,
"learning_rate": 1.0630556668610286e-05,
"loss": 0.4721,
"step": 560
},
{
"epoch": 1.0665399239543727,
"grad_norm": 0.02834767943397841,
"learning_rate": 1.059741011378829e-05,
"loss": 0.5075,
"step": 561
},
{
"epoch": 1.0684410646387832,
"grad_norm": 0.02288613867623036,
"learning_rate": 1.0564256970419367e-05,
"loss": 0.4565,
"step": 562
},
{
"epoch": 1.070342205323194,
"grad_norm": 0.023688637706669773,
"learning_rate": 1.0531097604133473e-05,
"loss": 0.4472,
"step": 563
},
{
"epoch": 1.0722433460076046,
"grad_norm": 0.024490569664163846,
"learning_rate": 1.0497932380629207e-05,
"loss": 0.5221,
"step": 564
},
{
"epoch": 1.0741444866920151,
"grad_norm": 0.02782768534592333,
"learning_rate": 1.0464761665669771e-05,
"loss": 0.4004,
"step": 565
},
{
"epoch": 1.0760456273764258,
"grad_norm": 0.02669839048402323,
"learning_rate": 1.0431585825078916e-05,
"loss": 0.3402,
"step": 566
},
{
"epoch": 1.0779467680608366,
"grad_norm": 0.02651283388836949,
"learning_rate": 1.0398405224736927e-05,
"loss": 0.4832,
"step": 567
},
{
"epoch": 1.079847908745247,
"grad_norm": 0.026449286845883088,
"learning_rate": 1.0365220230576592e-05,
"loss": 0.4047,
"step": 568
},
{
"epoch": 1.0817490494296578,
"grad_norm": 0.025418648342092183,
"learning_rate": 1.0332031208579133e-05,
"loss": 0.4801,
"step": 569
},
{
"epoch": 1.0836501901140685,
"grad_norm": 0.025412976006421107,
"learning_rate": 1.0298838524770212e-05,
"loss": 0.4752,
"step": 570
},
{
"epoch": 1.085551330798479,
"grad_norm": 0.025562260205010442,
"learning_rate": 1.0265642545215872e-05,
"loss": 0.457,
"step": 571
},
{
"epoch": 1.0874524714828897,
"grad_norm": 0.02643263881346091,
"learning_rate": 1.0232443636018502e-05,
"loss": 0.4357,
"step": 572
},
{
"epoch": 1.0893536121673004,
"grad_norm": 0.024528515527150255,
"learning_rate": 1.0199242163312794e-05,
"loss": 0.4794,
"step": 573
},
{
"epoch": 1.091254752851711,
"grad_norm": 0.026385215484675005,
"learning_rate": 1.0166038493261723e-05,
"loss": 0.4806,
"step": 574
},
{
"epoch": 1.0931558935361216,
"grad_norm": 0.022033026900315677,
"learning_rate": 1.013283299205249e-05,
"loss": 0.3609,
"step": 575
},
{
"epoch": 1.0950570342205324,
"grad_norm": 0.023678677060218277,
"learning_rate": 1.0099626025892491e-05,
"loss": 0.4579,
"step": 576
},
{
"epoch": 1.0969581749049429,
"grad_norm": 0.02487159791018364,
"learning_rate": 1.0066417961005283e-05,
"loss": 0.4429,
"step": 577
},
{
"epoch": 1.0988593155893536,
"grad_norm": 0.028657863587199493,
"learning_rate": 1.0033209163626539e-05,
"loss": 0.4093,
"step": 578
},
{
"epoch": 1.1007604562737643,
"grad_norm": 0.024174264086675668,
"learning_rate": 1e-05,
"loss": 0.3613,
"step": 579
},
{
"epoch": 1.102661596958175,
"grad_norm": 0.02551921343391446,
"learning_rate": 9.966790836373465e-06,
"loss": 0.5205,
"step": 580
},
{
"epoch": 1.1045627376425855,
"grad_norm": 0.028485515076974856,
"learning_rate": 9.933582038994719e-06,
"loss": 0.4851,
"step": 581
},
{
"epoch": 1.1064638783269962,
"grad_norm": 0.02504285375969555,
"learning_rate": 9.90037397410751e-06,
"loss": 0.4423,
"step": 582
},
{
"epoch": 1.108365019011407,
"grad_norm": 0.03088688093720148,
"learning_rate": 9.867167007947511e-06,
"loss": 0.5082,
"step": 583
},
{
"epoch": 1.1102661596958174,
"grad_norm": 0.026178357076301492,
"learning_rate": 9.833961506738282e-06,
"loss": 0.4638,
"step": 584
},
{
"epoch": 1.1121673003802282,
"grad_norm": 0.027152075516306527,
"learning_rate": 9.80075783668721e-06,
"loss": 0.5317,
"step": 585
},
{
"epoch": 1.1140684410646389,
"grad_norm": 0.026406197929923356,
"learning_rate": 9.767556363981503e-06,
"loss": 0.4423,
"step": 586
},
{
"epoch": 1.1159695817490494,
"grad_norm": 0.029606704129030288,
"learning_rate": 9.734357454784131e-06,
"loss": 0.4607,
"step": 587
},
{
"epoch": 1.11787072243346,
"grad_norm": 0.024228905576484227,
"learning_rate": 9.701161475229791e-06,
"loss": 0.4676,
"step": 588
},
{
"epoch": 1.1197718631178708,
"grad_norm": 0.028240824433468956,
"learning_rate": 9.66796879142087e-06,
"loss": 0.4688,
"step": 589
},
{
"epoch": 1.1216730038022813,
"grad_norm": 0.02619951444252266,
"learning_rate": 9.634779769423412e-06,
"loss": 0.4492,
"step": 590
},
{
"epoch": 1.123574144486692,
"grad_norm": 0.02778733641177876,
"learning_rate": 9.601594775263073e-06,
"loss": 0.4274,
"step": 591
},
{
"epoch": 1.1254752851711027,
"grad_norm": 0.026571662777596382,
"learning_rate": 9.568414174921085e-06,
"loss": 0.4036,
"step": 592
},
{
"epoch": 1.1273764258555132,
"grad_norm": 0.027953815742300783,
"learning_rate": 9.535238334330234e-06,
"loss": 0.48,
"step": 593
},
{
"epoch": 1.129277566539924,
"grad_norm": 0.028979318933333602,
"learning_rate": 9.502067619370794e-06,
"loss": 0.4805,
"step": 594
},
{
"epoch": 1.1311787072243347,
"grad_norm": 0.025679003425845764,
"learning_rate": 9.468902395866532e-06,
"loss": 0.4512,
"step": 595
},
{
"epoch": 1.1330798479087452,
"grad_norm": 0.02987754854820351,
"learning_rate": 9.435743029580638e-06,
"loss": 0.3995,
"step": 596
},
{
"epoch": 1.1349809885931559,
"grad_norm": 0.026169185432569683,
"learning_rate": 9.402589886211711e-06,
"loss": 0.4173,
"step": 597
},
{
"epoch": 1.1368821292775666,
"grad_norm": 0.025436753367301015,
"learning_rate": 9.369443331389718e-06,
"loss": 0.473,
"step": 598
},
{
"epoch": 1.138783269961977,
"grad_norm": 0.03206356955139165,
"learning_rate": 9.336303730671968e-06,
"loss": 0.3991,
"step": 599
},
{
"epoch": 1.1406844106463878,
"grad_norm": 0.02931513421234435,
"learning_rate": 9.303171449539074e-06,
"loss": 0.4343,
"step": 600
},
{
"epoch": 1.1425855513307985,
"grad_norm": 0.02902528636856751,
"learning_rate": 9.270046853390924e-06,
"loss": 0.4996,
"step": 601
},
{
"epoch": 1.144486692015209,
"grad_norm": 0.025005773856039703,
"learning_rate": 9.236930307542654e-06,
"loss": 0.3278,
"step": 602
},
{
"epoch": 1.1463878326996197,
"grad_norm": 0.02426738245019188,
"learning_rate": 9.203822177220621e-06,
"loss": 0.3638,
"step": 603
},
{
"epoch": 1.1482889733840305,
"grad_norm": 0.027177816967694415,
"learning_rate": 9.170722827558357e-06,
"loss": 0.4095,
"step": 604
},
{
"epoch": 1.1501901140684412,
"grad_norm": 0.0243722592720861,
"learning_rate": 9.13763262359257e-06,
"loss": 0.5409,
"step": 605
},
{
"epoch": 1.1520912547528517,
"grad_norm": 0.025710645397755146,
"learning_rate": 9.104551930259101e-06,
"loss": 0.39,
"step": 606
},
{
"epoch": 1.1539923954372624,
"grad_norm": 0.028241783918859797,
"learning_rate": 9.071481112388905e-06,
"loss": 0.4221,
"step": 607
},
{
"epoch": 1.1558935361216731,
"grad_norm": 0.02361782757674789,
"learning_rate": 9.038420534704015e-06,
"loss": 0.5406,
"step": 608
},
{
"epoch": 1.1577946768060836,
"grad_norm": 0.028580064019494145,
"learning_rate": 9.005370561813545e-06,
"loss": 0.4474,
"step": 609
},
{
"epoch": 1.1596958174904943,
"grad_norm": 0.024832970874222413,
"learning_rate": 8.972331558209644e-06,
"loss": 0.4104,
"step": 610
},
{
"epoch": 1.161596958174905,
"grad_norm": 0.02650404583878491,
"learning_rate": 8.939303888263485e-06,
"loss": 0.4492,
"step": 611
},
{
"epoch": 1.1634980988593155,
"grad_norm": 0.028814172792613935,
"learning_rate": 8.906287916221259e-06,
"loss": 0.475,
"step": 612
},
{
"epoch": 1.1653992395437263,
"grad_norm": 0.02414307982273957,
"learning_rate": 8.873284006200129e-06,
"loss": 0.3797,
"step": 613
},
{
"epoch": 1.167300380228137,
"grad_norm": 0.026513183843780715,
"learning_rate": 8.840292522184247e-06,
"loss": 0.4611,
"step": 614
},
{
"epoch": 1.1692015209125475,
"grad_norm": 0.027917195350160733,
"learning_rate": 8.807313828020715e-06,
"loss": 0.453,
"step": 615
},
{
"epoch": 1.1711026615969582,
"grad_norm": 0.027001830723944378,
"learning_rate": 8.774348287415589e-06,
"loss": 0.4705,
"step": 616
},
{
"epoch": 1.173003802281369,
"grad_norm": 0.027024796400000384,
"learning_rate": 8.74139626392986e-06,
"loss": 0.5125,
"step": 617
},
{
"epoch": 1.1749049429657794,
"grad_norm": 0.025733010017667625,
"learning_rate": 8.708458120975436e-06,
"loss": 0.4606,
"step": 618
},
{
"epoch": 1.1768060836501901,
"grad_norm": 0.02537306800520621,
"learning_rate": 8.675534221811156e-06,
"loss": 0.5052,
"step": 619
},
{
"epoch": 1.1787072243346008,
"grad_norm": 0.025502247996832712,
"learning_rate": 8.64262492953876e-06,
"loss": 0.3923,
"step": 620
},
{
"epoch": 1.1806083650190113,
"grad_norm": 0.0283037881188794,
"learning_rate": 8.60973060709891e-06,
"loss": 0.3562,
"step": 621
},
{
"epoch": 1.182509505703422,
"grad_norm": 0.02765397296367,
"learning_rate": 8.576851617267151e-06,
"loss": 0.4207,
"step": 622
},
{
"epoch": 1.1844106463878328,
"grad_norm": 0.030939294178597098,
"learning_rate": 8.543988322649954e-06,
"loss": 0.4353,
"step": 623
},
{
"epoch": 1.1863117870722433,
"grad_norm": 0.025900960501617727,
"learning_rate": 8.511141085680684e-06,
"loss": 0.4533,
"step": 624
},
{
"epoch": 1.188212927756654,
"grad_norm": 0.02336257345992659,
"learning_rate": 8.478310268615612e-06,
"loss": 0.4378,
"step": 625
},
{
"epoch": 1.1901140684410647,
"grad_norm": 0.03104086432751278,
"learning_rate": 8.445496233529934e-06,
"loss": 0.4014,
"step": 626
},
{
"epoch": 1.1920152091254752,
"grad_norm": 0.026279681702473717,
"learning_rate": 8.41269934231375e-06,
"loss": 0.5791,
"step": 627
},
{
"epoch": 1.193916349809886,
"grad_norm": 0.026431098394421208,
"learning_rate": 8.3799199566681e-06,
"loss": 0.4104,
"step": 628
},
{
"epoch": 1.1958174904942966,
"grad_norm": 0.025842256802881006,
"learning_rate": 8.34715843810096e-06,
"loss": 0.3822,
"step": 629
},
{
"epoch": 1.1977186311787071,
"grad_norm": 0.025700224411035477,
"learning_rate": 8.314415147923254e-06,
"loss": 0.4173,
"step": 630
},
{
"epoch": 1.1996197718631179,
"grad_norm": 0.028760898752997432,
"learning_rate": 8.281690447244887e-06,
"loss": 0.5265,
"step": 631
},
{
"epoch": 1.2015209125475286,
"grad_norm": 0.027983533875392992,
"learning_rate": 8.248984696970732e-06,
"loss": 0.4234,
"step": 632
},
{
"epoch": 1.203422053231939,
"grad_norm": 0.02995083103885102,
"learning_rate": 8.216298257796677e-06,
"loss": 0.4052,
"step": 633
},
{
"epoch": 1.2053231939163498,
"grad_norm": 0.02622577127605968,
"learning_rate": 8.183631490205636e-06,
"loss": 0.3944,
"step": 634
},
{
"epoch": 1.2072243346007605,
"grad_norm": 0.027365500007942224,
"learning_rate": 8.150984754463578e-06,
"loss": 0.4624,
"step": 635
},
{
"epoch": 1.209125475285171,
"grad_norm": 0.027106768146702834,
"learning_rate": 8.118358410615545e-06,
"loss": 0.5294,
"step": 636
},
{
"epoch": 1.2110266159695817,
"grad_norm": 0.028174780302516515,
"learning_rate": 8.08575281848169e-06,
"loss": 0.535,
"step": 637
},
{
"epoch": 1.2129277566539924,
"grad_norm": 0.02494806903289972,
"learning_rate": 8.0531683376533e-06,
"loss": 0.4464,
"step": 638
},
{
"epoch": 1.214828897338403,
"grad_norm": 0.026813886692445315,
"learning_rate": 8.020605327488846e-06,
"loss": 0.4196,
"step": 639
},
{
"epoch": 1.2167300380228137,
"grad_norm": 0.030178054600389817,
"learning_rate": 7.988064147110001e-06,
"loss": 0.426,
"step": 640
},
{
"epoch": 1.2186311787072244,
"grad_norm": 0.027322836613505857,
"learning_rate": 7.955545155397684e-06,
"loss": 0.4922,
"step": 641
},
{
"epoch": 1.2205323193916349,
"grad_norm": 0.02851456463701536,
"learning_rate": 7.923048710988119e-06,
"loss": 0.3909,
"step": 642
},
{
"epoch": 1.2224334600760456,
"grad_norm": 0.029679647372534257,
"learning_rate": 7.890575172268858e-06,
"loss": 0.4655,
"step": 643
},
{
"epoch": 1.2243346007604563,
"grad_norm": 0.024011488075073195,
"learning_rate": 7.858124897374837e-06,
"loss": 0.3861,
"step": 644
},
{
"epoch": 1.2262357414448668,
"grad_norm": 0.025094837748294702,
"learning_rate": 7.825698244184432e-06,
"loss": 0.4222,
"step": 645
},
{
"epoch": 1.2281368821292775,
"grad_norm": 0.025610173350570063,
"learning_rate": 7.7932955703155e-06,
"loss": 0.473,
"step": 646
},
{
"epoch": 1.2300380228136882,
"grad_norm": 0.02352347182601007,
"learning_rate": 7.760917233121443e-06,
"loss": 0.3626,
"step": 647
},
{
"epoch": 1.231939163498099,
"grad_norm": 0.029283299091673688,
"learning_rate": 7.728563589687275e-06,
"loss": 0.4963,
"step": 648
},
{
"epoch": 1.2338403041825095,
"grad_norm": 0.030862682323859268,
"learning_rate": 7.696234996825663e-06,
"loss": 0.3789,
"step": 649
},
{
"epoch": 1.2357414448669202,
"grad_norm": 0.03168967860296208,
"learning_rate": 7.663931811073003e-06,
"loss": 0.4766,
"step": 650
},
{
"epoch": 1.2376425855513309,
"grad_norm": 0.02423696133628203,
"learning_rate": 7.631654388685496e-06,
"loss": 0.3808,
"step": 651
},
{
"epoch": 1.2395437262357414,
"grad_norm": 0.03104175426538144,
"learning_rate": 7.599403085635208e-06,
"loss": 0.5122,
"step": 652
},
{
"epoch": 1.241444866920152,
"grad_norm": 0.029467045004493608,
"learning_rate": 7.567178257606147e-06,
"loss": 0.4188,
"step": 653
},
{
"epoch": 1.2433460076045628,
"grad_norm": 0.02627856743434748,
"learning_rate": 7.534980259990341e-06,
"loss": 0.4134,
"step": 654
},
{
"epoch": 1.2452471482889733,
"grad_norm": 0.026443976993739387,
"learning_rate": 7.50280944788392e-06,
"loss": 0.4495,
"step": 655
},
{
"epoch": 1.247148288973384,
"grad_norm": 0.02910290850363252,
"learning_rate": 7.470666176083193e-06,
"loss": 0.4956,
"step": 656
},
{
"epoch": 1.2490494296577948,
"grad_norm": 0.030787111442524107,
"learning_rate": 7.438550799080746e-06,
"loss": 0.4578,
"step": 657
},
{
"epoch": 1.2509505703422052,
"grad_norm": 0.02755054067169159,
"learning_rate": 7.40646367106153e-06,
"loss": 0.4393,
"step": 658
},
{
"epoch": 1.252851711026616,
"grad_norm": 0.028551333737617562,
"learning_rate": 7.3744051458989395e-06,
"loss": 0.4782,
"step": 659
},
{
"epoch": 1.2547528517110267,
"grad_norm": 0.029957333643541806,
"learning_rate": 7.342375577150928e-06,
"loss": 0.4624,
"step": 660
},
{
"epoch": 1.2566539923954372,
"grad_norm": 0.02808482409369459,
"learning_rate": 7.310375318056107e-06,
"loss": 0.4679,
"step": 661
},
{
"epoch": 1.258555133079848,
"grad_norm": 0.02588158997964679,
"learning_rate": 7.278404721529843e-06,
"loss": 0.5797,
"step": 662
},
{
"epoch": 1.2604562737642586,
"grad_norm": 0.023897308281060525,
"learning_rate": 7.246464140160365e-06,
"loss": 0.443,
"step": 663
},
{
"epoch": 1.2623574144486693,
"grad_norm": 0.031053266329604933,
"learning_rate": 7.214553926204884e-06,
"loss": 0.4107,
"step": 664
},
{
"epoch": 1.2642585551330798,
"grad_norm": 0.026719606285468933,
"learning_rate": 7.182674431585703e-06,
"loss": 0.5636,
"step": 665
},
{
"epoch": 1.2661596958174905,
"grad_norm": 0.02306740449177855,
"learning_rate": 7.150826007886334e-06,
"loss": 0.4318,
"step": 666
},
{
"epoch": 1.2680608365019013,
"grad_norm": 0.026119267635482755,
"learning_rate": 7.119009006347625e-06,
"loss": 0.3306,
"step": 667
},
{
"epoch": 1.2699619771863118,
"grad_norm": 0.03419415738994974,
"learning_rate": 7.087223777863883e-06,
"loss": 0.5362,
"step": 668
},
{
"epoch": 1.2718631178707225,
"grad_norm": 0.03072698649650123,
"learning_rate": 7.055470672979003e-06,
"loss": 0.4542,
"step": 669
},
{
"epoch": 1.2737642585551332,
"grad_norm": 0.026887865333932157,
"learning_rate": 7.023750041882609e-06,
"loss": 0.5468,
"step": 670
},
{
"epoch": 1.2756653992395437,
"grad_norm": 0.02859574453492066,
"learning_rate": 6.992062234406185e-06,
"loss": 0.4279,
"step": 671
},
{
"epoch": 1.2775665399239544,
"grad_norm": 0.02866149676116349,
"learning_rate": 6.960407600019217e-06,
"loss": 0.4671,
"step": 672
},
{
"epoch": 1.2794676806083651,
"grad_norm": 0.024968391509913344,
"learning_rate": 6.9287864878253475e-06,
"loss": 0.3833,
"step": 673
},
{
"epoch": 1.2813688212927756,
"grad_norm": 0.03457718232305868,
"learning_rate": 6.897199246558515e-06,
"loss": 0.4175,
"step": 674
},
{
"epoch": 1.2832699619771863,
"grad_norm": 0.02896136132570871,
"learning_rate": 6.865646224579108e-06,
"loss": 0.4343,
"step": 675
},
{
"epoch": 1.285171102661597,
"grad_norm": 0.029212521848368124,
"learning_rate": 6.834127769870134e-06,
"loss": 0.4066,
"step": 676
},
{
"epoch": 1.2870722433460076,
"grad_norm": 0.02799355491203608,
"learning_rate": 6.802644230033373e-06,
"loss": 0.4299,
"step": 677
},
{
"epoch": 1.2889733840304183,
"grad_norm": 0.029789337038738203,
"learning_rate": 6.771195952285541e-06,
"loss": 0.4238,
"step": 678
},
{
"epoch": 1.290874524714829,
"grad_norm": 0.03367895441324516,
"learning_rate": 6.739783283454469e-06,
"loss": 0.4823,
"step": 679
},
{
"epoch": 1.2927756653992395,
"grad_norm": 0.028940087009468582,
"learning_rate": 6.708406569975274e-06,
"loss": 0.4209,
"step": 680
},
{
"epoch": 1.2946768060836502,
"grad_norm": 0.027738242534913166,
"learning_rate": 6.6770661578865444e-06,
"loss": 0.47,
"step": 681
},
{
"epoch": 1.296577946768061,
"grad_norm": 0.026705324113941907,
"learning_rate": 6.645762392826509e-06,
"loss": 0.3689,
"step": 682
},
{
"epoch": 1.2984790874524714,
"grad_norm": 0.028661736682716873,
"learning_rate": 6.614495620029238e-06,
"loss": 0.4969,
"step": 683
},
{
"epoch": 1.3003802281368821,
"grad_norm": 0.026180052367738408,
"learning_rate": 6.583266184320836e-06,
"loss": 0.4422,
"step": 684
},
{
"epoch": 1.3022813688212929,
"grad_norm": 0.029666386897892704,
"learning_rate": 6.552074430115624e-06,
"loss": 0.5087,
"step": 685
},
{
"epoch": 1.3041825095057034,
"grad_norm": 0.026792793282078037,
"learning_rate": 6.520920701412371e-06,
"loss": 0.4812,
"step": 686
},
{
"epoch": 1.306083650190114,
"grad_norm": 0.02551359544734154,
"learning_rate": 6.489805341790456e-06,
"loss": 0.4641,
"step": 687
},
{
"epoch": 1.3079847908745248,
"grad_norm": 0.026500067110995663,
"learning_rate": 6.458728694406124e-06,
"loss": 0.4662,
"step": 688
},
{
"epoch": 1.3098859315589353,
"grad_norm": 0.03395026623518602,
"learning_rate": 6.427691101988673e-06,
"loss": 0.3852,
"step": 689
},
{
"epoch": 1.311787072243346,
"grad_norm": 0.02634387079965298,
"learning_rate": 6.396692906836686e-06,
"loss": 0.3745,
"step": 690
},
{
"epoch": 1.3136882129277567,
"grad_norm": 0.024158130217925743,
"learning_rate": 6.3657344508142495e-06,
"loss": 0.3748,
"step": 691
},
{
"epoch": 1.3155893536121672,
"grad_norm": 0.028848449256611498,
"learning_rate": 6.334816075347185e-06,
"loss": 0.442,
"step": 692
},
{
"epoch": 1.317490494296578,
"grad_norm": 0.03023585725462282,
"learning_rate": 6.303938121419295e-06,
"loss": 0.416,
"step": 693
},
{
"epoch": 1.3193916349809887,
"grad_norm": 0.026370730125347006,
"learning_rate": 6.273100929568579e-06,
"loss": 0.3592,
"step": 694
},
{
"epoch": 1.3212927756653992,
"grad_norm": 0.02727386863891104,
"learning_rate": 6.242304839883502e-06,
"loss": 0.4762,
"step": 695
},
{
"epoch": 1.3231939163498099,
"grad_norm": 0.030668183566592767,
"learning_rate": 6.211550191999223e-06,
"loss": 0.5194,
"step": 696
},
{
"epoch": 1.3250950570342206,
"grad_norm": 0.02972347024127305,
"learning_rate": 6.18083732509387e-06,
"loss": 0.4843,
"step": 697
},
{
"epoch": 1.326996197718631,
"grad_norm": 0.026145838925778292,
"learning_rate": 6.150166577884781e-06,
"loss": 0.386,
"step": 698
},
{
"epoch": 1.3288973384030418,
"grad_norm": 0.032041397582118325,
"learning_rate": 6.119538288624778e-06,
"loss": 0.4001,
"step": 699
},
{
"epoch": 1.3307984790874525,
"grad_norm": 0.029828153624763563,
"learning_rate": 6.088952795098442e-06,
"loss": 0.4283,
"step": 700
},
{
"epoch": 1.332699619771863,
"grad_norm": 0.031995216287676834,
"learning_rate": 6.058410434618367e-06,
"loss": 0.4421,
"step": 701
},
{
"epoch": 1.3346007604562737,
"grad_norm": 0.031637583686470815,
"learning_rate": 6.027911544021465e-06,
"loss": 0.4724,
"step": 702
},
{
"epoch": 1.3365019011406845,
"grad_norm": 0.02779799173287801,
"learning_rate": 5.997456459665237e-06,
"loss": 0.5191,
"step": 703
},
{
"epoch": 1.338403041825095,
"grad_norm": 0.026787215560895514,
"learning_rate": 5.967045517424062e-06,
"loss": 0.3672,
"step": 704
},
{
"epoch": 1.3403041825095057,
"grad_norm": 0.028848537313750235,
"learning_rate": 5.936679052685505e-06,
"loss": 0.4277,
"step": 705
},
{
"epoch": 1.3422053231939164,
"grad_norm": 0.028783359031467698,
"learning_rate": 5.906357400346596e-06,
"loss": 0.4509,
"step": 706
},
{
"epoch": 1.3441064638783269,
"grad_norm": 0.02773116659224034,
"learning_rate": 5.876080894810167e-06,
"loss": 0.5577,
"step": 707
},
{
"epoch": 1.3460076045627376,
"grad_norm": 0.028553697016596574,
"learning_rate": 5.845849869981137e-06,
"loss": 0.3898,
"step": 708
},
{
"epoch": 1.3479087452471483,
"grad_norm": 0.028156392246010412,
"learning_rate": 5.815664659262845e-06,
"loss": 0.3766,
"step": 709
},
{
"epoch": 1.3498098859315588,
"grad_norm": 0.03100657087735765,
"learning_rate": 5.78552559555337e-06,
"loss": 0.5583,
"step": 710
},
{
"epoch": 1.3517110266159695,
"grad_norm": 0.02797485074428679,
"learning_rate": 5.755433011241851e-06,
"loss": 0.4785,
"step": 711
},
{
"epoch": 1.3536121673003803,
"grad_norm": 0.027358375412801707,
"learning_rate": 5.725387238204831e-06,
"loss": 0.4732,
"step": 712
},
{
"epoch": 1.3555133079847907,
"grad_norm": 0.030912775982331196,
"learning_rate": 5.695388607802603e-06,
"loss": 0.5375,
"step": 713
},
{
"epoch": 1.3574144486692015,
"grad_norm": 0.032068076675599765,
"learning_rate": 5.665437450875534e-06,
"loss": 0.4606,
"step": 714
},
{
"epoch": 1.3593155893536122,
"grad_norm": 0.03223317604676853,
"learning_rate": 5.635534097740435e-06,
"loss": 0.4024,
"step": 715
},
{
"epoch": 1.3612167300380227,
"grad_norm": 0.02682575918004717,
"learning_rate": 5.605678878186911e-06,
"loss": 0.3428,
"step": 716
},
{
"epoch": 1.3631178707224334,
"grad_norm": 0.03148540229771045,
"learning_rate": 5.575872121473722e-06,
"loss": 0.3892,
"step": 717
},
{
"epoch": 1.3650190114068441,
"grad_norm": 0.029382666135706115,
"learning_rate": 5.546114156325166e-06,
"loss": 0.5357,
"step": 718
},
{
"epoch": 1.3669201520912546,
"grad_norm": 0.02919874406990327,
"learning_rate": 5.516405310927431e-06,
"loss": 0.464,
"step": 719
},
{
"epoch": 1.3688212927756653,
"grad_norm": 0.02896813714737485,
"learning_rate": 5.4867459129249846e-06,
"loss": 0.5409,
"step": 720
},
{
"epoch": 1.370722433460076,
"grad_norm": 0.034416303220981784,
"learning_rate": 5.4571362894169795e-06,
"loss": 0.4672,
"step": 721
},
{
"epoch": 1.3726235741444868,
"grad_norm": 0.024902435863464658,
"learning_rate": 5.427576766953615e-06,
"loss": 0.4113,
"step": 722
},
{
"epoch": 1.3745247148288973,
"grad_norm": 0.027717131676122143,
"learning_rate": 5.398067671532554e-06,
"loss": 0.4107,
"step": 723
},
{
"epoch": 1.376425855513308,
"grad_norm": 0.02819798108310211,
"learning_rate": 5.368609328595323e-06,
"loss": 0.54,
"step": 724
},
{
"epoch": 1.3783269961977187,
"grad_norm": 0.0318198691073443,
"learning_rate": 5.339202063023727e-06,
"loss": 0.4745,
"step": 725
},
{
"epoch": 1.3802281368821292,
"grad_norm": 0.03160178400979231,
"learning_rate": 5.309846199136258e-06,
"loss": 0.5534,
"step": 726
},
{
"epoch": 1.38212927756654,
"grad_norm": 0.031203987967182555,
"learning_rate": 5.280542060684535e-06,
"loss": 0.4872,
"step": 727
},
{
"epoch": 1.3840304182509506,
"grad_norm": 0.03212939770548475,
"learning_rate": 5.2512899708497086e-06,
"loss": 0.4987,
"step": 728
},
{
"epoch": 1.3859315589353614,
"grad_norm": 0.02667203925098415,
"learning_rate": 5.222090252238916e-06,
"loss": 0.4661,
"step": 729
},
{
"epoch": 1.3878326996197718,
"grad_norm": 0.03050695800339695,
"learning_rate": 5.192943226881724e-06,
"loss": 0.5221,
"step": 730
},
{
"epoch": 1.3897338403041826,
"grad_norm": 0.027805559765800788,
"learning_rate": 5.163849216226562e-06,
"loss": 0.408,
"step": 731
},
{
"epoch": 1.3916349809885933,
"grad_norm": 0.02909423144948114,
"learning_rate": 5.134808541137183e-06,
"loss": 0.4871,
"step": 732
},
{
"epoch": 1.3935361216730038,
"grad_norm": 0.03294086065938786,
"learning_rate": 5.105821521889147e-06,
"loss": 0.5285,
"step": 733
},
{
"epoch": 1.3954372623574145,
"grad_norm": 0.027754896702892988,
"learning_rate": 5.076888478166247e-06,
"loss": 0.4322,
"step": 734
},
{
"epoch": 1.3973384030418252,
"grad_norm": 0.03290516325990418,
"learning_rate": 5.048009729057012e-06,
"loss": 0.4647,
"step": 735
},
{
"epoch": 1.3992395437262357,
"grad_norm": 0.030937260456841767,
"learning_rate": 5.0191855930511946e-06,
"loss": 0.4194,
"step": 736
},
{
"epoch": 1.4011406844106464,
"grad_norm": 0.0277872161185395,
"learning_rate": 4.990416388036233e-06,
"loss": 0.4097,
"step": 737
},
{
"epoch": 1.4030418250950571,
"grad_norm": 0.030180714624574015,
"learning_rate": 4.961702431293759e-06,
"loss": 0.3394,
"step": 738
},
{
"epoch": 1.4049429657794676,
"grad_norm": 0.02913012334006182,
"learning_rate": 4.933044039496107e-06,
"loss": 0.46,
"step": 739
},
{
"epoch": 1.4068441064638784,
"grad_norm": 0.03039527344098277,
"learning_rate": 4.904441528702806e-06,
"loss": 0.4149,
"step": 740
},
{
"epoch": 1.408745247148289,
"grad_norm": 0.02949216153384184,
"learning_rate": 4.875895214357093e-06,
"loss": 0.4067,
"step": 741
},
{
"epoch": 1.4106463878326996,
"grad_norm": 0.029355805600736497,
"learning_rate": 4.847405411282462e-06,
"loss": 0.4412,
"step": 742
},
{
"epoch": 1.4125475285171103,
"grad_norm": 0.029833345308483448,
"learning_rate": 4.818972433679145e-06,
"loss": 0.4834,
"step": 743
},
{
"epoch": 1.414448669201521,
"grad_norm": 0.031040892623573117,
"learning_rate": 4.790596595120699e-06,
"loss": 0.4235,
"step": 744
},
{
"epoch": 1.4163498098859315,
"grad_norm": 0.029418025601028568,
"learning_rate": 4.762278208550505e-06,
"loss": 0.5524,
"step": 745
},
{
"epoch": 1.4182509505703422,
"grad_norm": 0.03234656547481261,
"learning_rate": 4.734017586278337e-06,
"loss": 0.455,
"step": 746
},
{
"epoch": 1.420152091254753,
"grad_norm": 0.030112020587859428,
"learning_rate": 4.7058150399769245e-06,
"loss": 0.5177,
"step": 747
},
{
"epoch": 1.4220532319391634,
"grad_norm": 0.028737634075618794,
"learning_rate": 4.677670880678493e-06,
"loss": 0.5981,
"step": 748
},
{
"epoch": 1.4239543726235742,
"grad_norm": 0.02811256918101417,
"learning_rate": 4.649585418771348e-06,
"loss": 0.4547,
"step": 749
},
{
"epoch": 1.4258555133079849,
"grad_norm": 0.028878580084001036,
"learning_rate": 4.621558963996458e-06,
"loss": 0.428,
"step": 750
},
{
"epoch": 1.4277566539923954,
"grad_norm": 0.03111349099552106,
"learning_rate": 4.593591825444028e-06,
"loss": 0.5579,
"step": 751
},
{
"epoch": 1.429657794676806,
"grad_norm": 0.028704224469254278,
"learning_rate": 4.565684311550077e-06,
"loss": 0.4346,
"step": 752
},
{
"epoch": 1.4315589353612168,
"grad_norm": 0.029538862975289022,
"learning_rate": 4.537836730093077e-06,
"loss": 0.3984,
"step": 753
},
{
"epoch": 1.4334600760456273,
"grad_norm": 0.02920814557830504,
"learning_rate": 4.510049388190518e-06,
"loss": 0.4732,
"step": 754
},
{
"epoch": 1.435361216730038,
"grad_norm": 0.026042563331556207,
"learning_rate": 4.482322592295541e-06,
"loss": 0.4252,
"step": 755
},
{
"epoch": 1.4372623574144487,
"grad_norm": 0.03446984414969546,
"learning_rate": 4.454656648193559e-06,
"loss": 0.5051,
"step": 756
},
{
"epoch": 1.4391634980988592,
"grad_norm": 0.031148293151505677,
"learning_rate": 4.427051860998877e-06,
"loss": 0.4379,
"step": 757
},
{
"epoch": 1.44106463878327,
"grad_norm": 0.03187960963872275,
"learning_rate": 4.399508535151321e-06,
"loss": 0.4388,
"step": 758
},
{
"epoch": 1.4429657794676807,
"grad_norm": 0.029156787441216785,
"learning_rate": 4.372026974412907e-06,
"loss": 0.4099,
"step": 759
},
{
"epoch": 1.4448669201520912,
"grad_norm": 0.027570371450881585,
"learning_rate": 4.344607481864466e-06,
"loss": 0.3871,
"step": 760
},
{
"epoch": 1.446768060836502,
"grad_norm": 0.03001707256533982,
"learning_rate": 4.317250359902295e-06,
"loss": 0.4918,
"step": 761
},
{
"epoch": 1.4486692015209126,
"grad_norm": 0.02815136784810877,
"learning_rate": 4.2899559102348585e-06,
"loss": 0.489,
"step": 762
},
{
"epoch": 1.450570342205323,
"grad_norm": 0.030887177367103905,
"learning_rate": 4.262724433879427e-06,
"loss": 0.4149,
"step": 763
},
{
"epoch": 1.4524714828897338,
"grad_norm": 0.03101054435233135,
"learning_rate": 4.235556231158765e-06,
"loss": 0.382,
"step": 764
},
{
"epoch": 1.4543726235741445,
"grad_norm": 0.03003088571504904,
"learning_rate": 4.208451601697836e-06,
"loss": 0.4431,
"step": 765
},
{
"epoch": 1.456273764258555,
"grad_norm": 0.041707849733573374,
"learning_rate": 4.181410844420473e-06,
"loss": 0.5137,
"step": 766
},
{
"epoch": 1.4581749049429658,
"grad_norm": 0.028879053883781557,
"learning_rate": 4.154434257546095e-06,
"loss": 0.404,
"step": 767
},
{
"epoch": 1.4600760456273765,
"grad_norm": 0.031166888939069805,
"learning_rate": 4.127522138586424e-06,
"loss": 0.4769,
"step": 768
},
{
"epoch": 1.461977186311787,
"grad_norm": 0.030755634558385713,
"learning_rate": 4.10067478434219e-06,
"loss": 0.4582,
"step": 769
},
{
"epoch": 1.4638783269961977,
"grad_norm": 0.02834069018800523,
"learning_rate": 4.073892490899865e-06,
"loss": 0.428,
"step": 770
},
{
"epoch": 1.4657794676806084,
"grad_norm": 0.029920699324498402,
"learning_rate": 4.047175553628397e-06,
"loss": 0.3844,
"step": 771
},
{
"epoch": 1.467680608365019,
"grad_norm": 0.029994581045541858,
"learning_rate": 4.020524267175954e-06,
"loss": 0.4341,
"step": 772
},
{
"epoch": 1.4695817490494296,
"grad_norm": 0.030296431261687077,
"learning_rate": 3.993938925466674e-06,
"loss": 0.4781,
"step": 773
},
{
"epoch": 1.4714828897338403,
"grad_norm": 0.031388201776416984,
"learning_rate": 3.96741982169742e-06,
"loss": 0.403,
"step": 774
},
{
"epoch": 1.4733840304182508,
"grad_norm": 0.034323278285153046,
"learning_rate": 3.9409672483345465e-06,
"loss": 0.4479,
"step": 775
},
{
"epoch": 1.4752851711026616,
"grad_norm": 0.039442138478036716,
"learning_rate": 3.914581497110684e-06,
"loss": 0.4226,
"step": 776
},
{
"epoch": 1.4771863117870723,
"grad_norm": 0.027820650801430504,
"learning_rate": 3.888262859021508e-06,
"loss": 0.4751,
"step": 777
},
{
"epoch": 1.4790874524714828,
"grad_norm": 0.028212566710192757,
"learning_rate": 3.862011624322534e-06,
"loss": 0.3768,
"step": 778
},
{
"epoch": 1.4809885931558935,
"grad_norm": 0.027663868858047506,
"learning_rate": 3.835828082525925e-06,
"loss": 0.3845,
"step": 779
},
{
"epoch": 1.4828897338403042,
"grad_norm": 0.0286387603298508,
"learning_rate": 3.8097125223972864e-06,
"loss": 0.4723,
"step": 780
},
{
"epoch": 1.4847908745247147,
"grad_norm": 0.028742371931207277,
"learning_rate": 3.7836652319524835e-06,
"loss": 0.4091,
"step": 781
},
{
"epoch": 1.4866920152091254,
"grad_norm": 0.028776691349877988,
"learning_rate": 3.7576864984544814e-06,
"loss": 0.4418,
"step": 782
},
{
"epoch": 1.4885931558935361,
"grad_norm": 0.02717344017433737,
"learning_rate": 3.73177660841015e-06,
"loss": 0.375,
"step": 783
},
{
"epoch": 1.4904942965779466,
"grad_norm": 0.04105268953972606,
"learning_rate": 3.7059358475671225e-06,
"loss": 0.434,
"step": 784
},
{
"epoch": 1.4923954372623573,
"grad_norm": 0.03127383121023246,
"learning_rate": 3.680164500910646e-06,
"loss": 0.3745,
"step": 785
},
{
"epoch": 1.494296577946768,
"grad_norm": 0.029885424011204434,
"learning_rate": 3.654462852660423e-06,
"loss": 0.5187,
"step": 786
},
{
"epoch": 1.4961977186311788,
"grad_norm": 0.030127846598248572,
"learning_rate": 3.6288311862674885e-06,
"loss": 0.423,
"step": 787
},
{
"epoch": 1.4980988593155893,
"grad_norm": 0.033965255384920984,
"learning_rate": 3.6032697844110896e-06,
"loss": 0.4487,
"step": 788
},
{
"epoch": 1.5,
"grad_norm": 0.031051910837305945,
"learning_rate": 3.5777789289955454e-06,
"loss": 0.5404,
"step": 789
},
{
"epoch": 1.5019011406844105,
"grad_norm": 0.027096542766531128,
"learning_rate": 3.5523589011471592e-06,
"loss": 0.4042,
"step": 790
},
{
"epoch": 1.5038022813688214,
"grad_norm": 0.03435456762542711,
"learning_rate": 3.527009981211119e-06,
"loss": 0.4893,
"step": 791
},
{
"epoch": 1.505703422053232,
"grad_norm": 0.027520683723539555,
"learning_rate": 3.5017324487483873e-06,
"loss": 0.4118,
"step": 792
},
{
"epoch": 1.5076045627376424,
"grad_norm": 0.029455592603562925,
"learning_rate": 3.47652658253263e-06,
"loss": 0.4488,
"step": 793
},
{
"epoch": 1.5095057034220534,
"grad_norm": 0.03054107669871993,
"learning_rate": 3.4513926605471504e-06,
"loss": 0.5746,
"step": 794
},
{
"epoch": 1.5114068441064639,
"grad_norm": 0.03169123866581408,
"learning_rate": 3.4263309599818017e-06,
"loss": 0.3971,
"step": 795
},
{
"epoch": 1.5133079847908744,
"grad_norm": 0.028699094422273308,
"learning_rate": 3.4013417572299446e-06,
"loss": 0.5152,
"step": 796
},
{
"epoch": 1.5152091254752853,
"grad_norm": 0.027529958113480905,
"learning_rate": 3.37642532788541e-06,
"loss": 0.4457,
"step": 797
},
{
"epoch": 1.5171102661596958,
"grad_norm": 0.03048754581317044,
"learning_rate": 3.3515819467394184e-06,
"loss": 0.4127,
"step": 798
},
{
"epoch": 1.5190114068441065,
"grad_norm": 0.02821106287426813,
"learning_rate": 3.326811887777607e-06,
"loss": 0.3581,
"step": 799
},
{
"epoch": 1.5209125475285172,
"grad_norm": 0.025512659096068077,
"learning_rate": 3.3021154241769606e-06,
"loss": 0.3813,
"step": 800
},
{
"epoch": 1.5228136882129277,
"grad_norm": 0.027111936862849854,
"learning_rate": 3.2774928283028153e-06,
"loss": 0.4563,
"step": 801
},
{
"epoch": 1.5247148288973384,
"grad_norm": 0.029468115910336434,
"learning_rate": 3.2529443717058693e-06,
"loss": 0.4347,
"step": 802
},
{
"epoch": 1.5266159695817492,
"grad_norm": 0.03144089627867526,
"learning_rate": 3.228470325119164e-06,
"loss": 0.5228,
"step": 803
},
{
"epoch": 1.5285171102661597,
"grad_norm": 0.026828502717138106,
"learning_rate": 3.20407095845511e-06,
"loss": 0.3327,
"step": 804
},
{
"epoch": 1.5304182509505704,
"grad_norm": 0.03191218461014265,
"learning_rate": 3.179746540802506e-06,
"loss": 0.4629,
"step": 805
},
{
"epoch": 1.532319391634981,
"grad_norm": 0.029064440550334705,
"learning_rate": 3.155497340423588e-06,
"loss": 0.3646,
"step": 806
},
{
"epoch": 1.5342205323193916,
"grad_norm": 0.03303936902708768,
"learning_rate": 3.1313236247510414e-06,
"loss": 0.4376,
"step": 807
},
{
"epoch": 1.5361216730038023,
"grad_norm": 0.029358567199211188,
"learning_rate": 3.107225660385077e-06,
"loss": 0.4566,
"step": 808
},
{
"epoch": 1.538022813688213,
"grad_norm": 0.029522564844707316,
"learning_rate": 3.0832037130904748e-06,
"loss": 0.465,
"step": 809
},
{
"epoch": 1.5399239543726235,
"grad_norm": 0.030610433655364134,
"learning_rate": 3.0592580477936606e-06,
"loss": 0.4463,
"step": 810
},
{
"epoch": 1.5418250950570342,
"grad_norm": 0.030867638795095506,
"learning_rate": 3.035388928579792e-06,
"loss": 0.4166,
"step": 811
},
{
"epoch": 1.543726235741445,
"grad_norm": 0.031003703162365476,
"learning_rate": 3.011596618689825e-06,
"loss": 0.4822,
"step": 812
},
{
"epoch": 1.5456273764258555,
"grad_norm": 0.025768323397602613,
"learning_rate": 2.9878813805176252e-06,
"loss": 0.3659,
"step": 813
},
{
"epoch": 1.5475285171102662,
"grad_norm": 0.02887988122441581,
"learning_rate": 2.9642434756070793e-06,
"loss": 0.3947,
"step": 814
},
{
"epoch": 1.549429657794677,
"grad_norm": 0.04214948236847536,
"learning_rate": 2.940683164649194e-06,
"loss": 0.4057,
"step": 815
},
{
"epoch": 1.5513307984790874,
"grad_norm": 0.028795233112838173,
"learning_rate": 2.9172007074792342e-06,
"loss": 0.367,
"step": 816
},
{
"epoch": 1.553231939163498,
"grad_norm": 0.04269869786294826,
"learning_rate": 2.8937963630738517e-06,
"loss": 0.4783,
"step": 817
},
{
"epoch": 1.5551330798479088,
"grad_norm": 0.03976255951688538,
"learning_rate": 2.87047038954823e-06,
"loss": 0.4598,
"step": 818
},
{
"epoch": 1.5570342205323193,
"grad_norm": 0.02756738259971169,
"learning_rate": 2.8472230441532365e-06,
"loss": 0.3534,
"step": 819
},
{
"epoch": 1.55893536121673,
"grad_norm": 0.032031044063694496,
"learning_rate": 2.8240545832725963e-06,
"loss": 0.437,
"step": 820
},
{
"epoch": 1.5608365019011408,
"grad_norm": 0.03232689680617355,
"learning_rate": 2.8009652624200436e-06,
"loss": 0.3954,
"step": 821
},
{
"epoch": 1.5627376425855513,
"grad_norm": 0.028779225361362428,
"learning_rate": 2.7779553362365184e-06,
"loss": 0.3788,
"step": 822
},
{
"epoch": 1.564638783269962,
"grad_norm": 0.033053817697612495,
"learning_rate": 2.755025058487364e-06,
"loss": 0.5015,
"step": 823
},
{
"epoch": 1.5665399239543727,
"grad_norm": 0.026957049890508244,
"learning_rate": 2.7321746820595084e-06,
"loss": 0.3915,
"step": 824
},
{
"epoch": 1.5684410646387832,
"grad_norm": 0.029741526560517362,
"learning_rate": 2.709404458958693e-06,
"loss": 0.4319,
"step": 825
},
{
"epoch": 1.570342205323194,
"grad_norm": 0.034766455283583235,
"learning_rate": 2.6867146403066833e-06,
"loss": 0.4974,
"step": 826
},
{
"epoch": 1.5722433460076046,
"grad_norm": 0.02835777392351599,
"learning_rate": 2.6641054763385044e-06,
"loss": 0.3743,
"step": 827
},
{
"epoch": 1.5741444866920151,
"grad_norm": 0.031431886268975404,
"learning_rate": 2.6415772163996845e-06,
"loss": 0.562,
"step": 828
},
{
"epoch": 1.5760456273764258,
"grad_norm": 0.02852970629061991,
"learning_rate": 2.619130108943494e-06,
"loss": 0.507,
"step": 829
},
{
"epoch": 1.5779467680608366,
"grad_norm": 0.03200964545830204,
"learning_rate": 2.5967644015282146e-06,
"loss": 0.4173,
"step": 830
},
{
"epoch": 1.579847908745247,
"grad_norm": 0.030109870902287034,
"learning_rate": 2.5744803408144026e-06,
"loss": 0.4756,
"step": 831
},
{
"epoch": 1.5817490494296578,
"grad_norm": 0.02879971785543682,
"learning_rate": 2.5522781725621814e-06,
"loss": 0.4296,
"step": 832
},
{
"epoch": 1.5836501901140685,
"grad_norm": 0.030572562350088872,
"learning_rate": 2.530158141628515e-06,
"loss": 0.3608,
"step": 833
},
{
"epoch": 1.585551330798479,
"grad_norm": 0.029997871888884576,
"learning_rate": 2.508120491964512e-06,
"loss": 0.4984,
"step": 834
},
{
"epoch": 1.5874524714828897,
"grad_norm": 0.0375523224485888,
"learning_rate": 2.486165466612751e-06,
"loss": 0.5286,
"step": 835
},
{
"epoch": 1.5893536121673004,
"grad_norm": 0.03166794783148593,
"learning_rate": 2.464293307704566e-06,
"loss": 0.3404,
"step": 836
},
{
"epoch": 1.591254752851711,
"grad_norm": 0.029065306165181683,
"learning_rate": 2.4425042564574186e-06,
"loss": 0.3846,
"step": 837
},
{
"epoch": 1.5931558935361216,
"grad_norm": 0.03659011859307511,
"learning_rate": 2.4207985531722034e-06,
"loss": 0.4462,
"step": 838
},
{
"epoch": 1.5950570342205324,
"grad_norm": 0.03237371162013363,
"learning_rate": 2.3991764372306113e-06,
"loss": 0.4106,
"step": 839
},
{
"epoch": 1.5969581749049429,
"grad_norm": 0.03163202922364184,
"learning_rate": 2.377638147092497e-06,
"loss": 0.4557,
"step": 840
},
{
"epoch": 1.5988593155893536,
"grad_norm": 0.029894103192715567,
"learning_rate": 2.3561839202932344e-06,
"loss": 0.5256,
"step": 841
},
{
"epoch": 1.6007604562737643,
"grad_norm": 0.031980223022173494,
"learning_rate": 2.3348139934411008e-06,
"loss": 0.4452,
"step": 842
},
{
"epoch": 1.6026615969581748,
"grad_norm": 0.03143298206428353,
"learning_rate": 2.3135286022146785e-06,
"loss": 0.4315,
"step": 843
},
{
"epoch": 1.6045627376425855,
"grad_norm": 0.030631399015622986,
"learning_rate": 2.292327981360245e-06,
"loss": 0.4798,
"step": 844
},
{
"epoch": 1.6064638783269962,
"grad_norm": 0.030773177319533385,
"learning_rate": 2.271212364689176e-06,
"loss": 0.4573,
"step": 845
},
{
"epoch": 1.6083650190114067,
"grad_norm": 0.02942170999285307,
"learning_rate": 2.2501819850753925e-06,
"loss": 0.4104,
"step": 846
},
{
"epoch": 1.6102661596958177,
"grad_norm": 0.032044391662416384,
"learning_rate": 2.229237074452768e-06,
"loss": 0.3595,
"step": 847
},
{
"epoch": 1.6121673003802282,
"grad_norm": 0.02648000190922172,
"learning_rate": 2.2083778638125796e-06,
"loss": 0.4179,
"step": 848
},
{
"epoch": 1.6140684410646386,
"grad_norm": 0.0323786043598909,
"learning_rate": 2.1876045832009694e-06,
"loss": 0.4312,
"step": 849
},
{
"epoch": 1.6159695817490496,
"grad_norm": 0.031962574305962506,
"learning_rate": 2.16691746171639e-06,
"loss": 0.4414,
"step": 850
},
{
"epoch": 1.61787072243346,
"grad_norm": 0.028988170537215887,
"learning_rate": 2.1463167275070863e-06,
"loss": 0.3482,
"step": 851
},
{
"epoch": 1.6197718631178706,
"grad_norm": 0.03211596814985751,
"learning_rate": 2.125802607768588e-06,
"loss": 0.4426,
"step": 852
},
{
"epoch": 1.6216730038022815,
"grad_norm": 0.028882375149180312,
"learning_rate": 2.1053753287411895e-06,
"loss": 0.4839,
"step": 853
},
{
"epoch": 1.623574144486692,
"grad_norm": 0.0325186577163931,
"learning_rate": 2.08503511570746e-06,
"loss": 0.3888,
"step": 854
},
{
"epoch": 1.6254752851711025,
"grad_norm": 0.0278026193043055,
"learning_rate": 2.064782192989765e-06,
"loss": 0.4297,
"step": 855
},
{
"epoch": 1.6273764258555135,
"grad_norm": 0.02686969817654916,
"learning_rate": 2.0446167839477815e-06,
"loss": 0.3861,
"step": 856
},
{
"epoch": 1.629277566539924,
"grad_norm": 0.030445402524440293,
"learning_rate": 2.0245391109760437e-06,
"loss": 0.4997,
"step": 857
},
{
"epoch": 1.6311787072243344,
"grad_norm": 0.029801769119460805,
"learning_rate": 2.0045493955014915e-06,
"loss": 0.347,
"step": 858
},
{
"epoch": 1.6330798479087454,
"grad_norm": 0.02683243241644894,
"learning_rate": 1.984647857981017e-06,
"loss": 0.4397,
"step": 859
},
{
"epoch": 1.6349809885931559,
"grad_norm": 0.03053157289256201,
"learning_rate": 1.96483471789904e-06,
"loss": 0.5046,
"step": 860
},
{
"epoch": 1.6368821292775664,
"grad_norm": 0.03218333973180804,
"learning_rate": 1.9451101937650963e-06,
"loss": 0.4193,
"step": 861
},
{
"epoch": 1.6387832699619773,
"grad_norm": 0.03187704409089051,
"learning_rate": 1.925474503111412e-06,
"loss": 0.4847,
"step": 862
},
{
"epoch": 1.6406844106463878,
"grad_norm": 0.029870834823852343,
"learning_rate": 1.905927862490512e-06,
"loss": 0.412,
"step": 863
},
{
"epoch": 1.6425855513307985,
"grad_norm": 0.03351141391858019,
"learning_rate": 1.8864704874728346e-06,
"loss": 0.4288,
"step": 864
},
{
"epoch": 1.6444866920152093,
"grad_norm": 0.031248306742379217,
"learning_rate": 1.8671025926443464e-06,
"loss": 0.3744,
"step": 865
},
{
"epoch": 1.6463878326996197,
"grad_norm": 0.027804428306329856,
"learning_rate": 1.8478243916041882e-06,
"loss": 0.49,
"step": 866
},
{
"epoch": 1.6482889733840305,
"grad_norm": 0.03248108305698628,
"learning_rate": 1.828636096962304e-06,
"loss": 0.4218,
"step": 867
},
{
"epoch": 1.6501901140684412,
"grad_norm": 0.030985566129981643,
"learning_rate": 1.8095379203371044e-06,
"loss": 0.3549,
"step": 868
},
{
"epoch": 1.6520912547528517,
"grad_norm": 0.029278682974998815,
"learning_rate": 1.7905300723531393e-06,
"loss": 0.4989,
"step": 869
},
{
"epoch": 1.6539923954372624,
"grad_norm": 0.03294348867295606,
"learning_rate": 1.771612762638758e-06,
"loss": 0.473,
"step": 870
},
{
"epoch": 1.6558935361216731,
"grad_norm": 0.032118173778418836,
"learning_rate": 1.7527861998238094e-06,
"loss": 0.5291,
"step": 871
},
{
"epoch": 1.6577946768060836,
"grad_norm": 0.02952093686854592,
"learning_rate": 1.7340505915373495e-06,
"loss": 0.4796,
"step": 872
},
{
"epoch": 1.6596958174904943,
"grad_norm": 0.029492671747804372,
"learning_rate": 1.7154061444053239e-06,
"loss": 0.3782,
"step": 873
},
{
"epoch": 1.661596958174905,
"grad_norm": 0.030817515608522434,
"learning_rate": 1.6968530640483126e-06,
"loss": 0.4224,
"step": 874
},
{
"epoch": 1.6634980988593155,
"grad_norm": 0.0274807609917878,
"learning_rate": 1.6783915550792652e-06,
"loss": 0.3294,
"step": 875
},
{
"epoch": 1.6653992395437263,
"grad_norm": 0.029413278920099938,
"learning_rate": 1.660021821101222e-06,
"loss": 0.5466,
"step": 876
},
{
"epoch": 1.667300380228137,
"grad_norm": 0.02918447464387044,
"learning_rate": 1.6417440647050853e-06,
"loss": 0.5098,
"step": 877
},
{
"epoch": 1.6692015209125475,
"grad_norm": 0.03082479764728793,
"learning_rate": 1.6235584874673848e-06,
"loss": 0.4297,
"step": 878
},
{
"epoch": 1.6711026615969582,
"grad_norm": 0.032422475501209885,
"learning_rate": 1.6054652899480472e-06,
"loss": 0.4871,
"step": 879
},
{
"epoch": 1.673003802281369,
"grad_norm": 0.03141292425621774,
"learning_rate": 1.587464671688187e-06,
"loss": 0.4569,
"step": 880
},
{
"epoch": 1.6749049429657794,
"grad_norm": 0.0330903525633864,
"learning_rate": 1.5695568312079156e-06,
"loss": 0.4469,
"step": 881
},
{
"epoch": 1.6768060836501901,
"grad_norm": 0.031179229475447295,
"learning_rate": 1.5517419660041277e-06,
"loss": 0.5497,
"step": 882
},
{
"epoch": 1.6787072243346008,
"grad_norm": 0.03228263078110552,
"learning_rate": 1.534020272548349e-06,
"loss": 0.4859,
"step": 883
},
{
"epoch": 1.6806083650190113,
"grad_norm": 0.025923393407134707,
"learning_rate": 1.5163919462845622e-06,
"loss": 0.4196,
"step": 884
},
{
"epoch": 1.682509505703422,
"grad_norm": 0.028661954301765564,
"learning_rate": 1.4988571816270402e-06,
"loss": 0.4335,
"step": 885
},
{
"epoch": 1.6844106463878328,
"grad_norm": 0.027963802864611236,
"learning_rate": 1.4814161719582132e-06,
"loss": 0.3977,
"step": 886
},
{
"epoch": 1.6863117870722433,
"grad_norm": 0.032875478037560815,
"learning_rate": 1.4640691096265358e-06,
"loss": 0.629,
"step": 887
},
{
"epoch": 1.688212927756654,
"grad_norm": 0.0374925249439201,
"learning_rate": 1.4468161859443609e-06,
"loss": 0.3625,
"step": 888
},
{
"epoch": 1.6901140684410647,
"grad_norm": 0.03185769773842431,
"learning_rate": 1.4296575911858268e-06,
"loss": 0.4556,
"step": 889
},
{
"epoch": 1.6920152091254752,
"grad_norm": 0.02897215891587595,
"learning_rate": 1.412593514584777e-06,
"loss": 0.5004,
"step": 890
},
{
"epoch": 1.693916349809886,
"grad_norm": 0.029630191567608207,
"learning_rate": 1.3956241443326423e-06,
"loss": 0.4363,
"step": 891
},
{
"epoch": 1.6958174904942966,
"grad_norm": 0.03190130281641041,
"learning_rate": 1.378749667576399e-06,
"loss": 0.4588,
"step": 892
},
{
"epoch": 1.6977186311787071,
"grad_norm": 0.031127873011931113,
"learning_rate": 1.3619702704164783e-06,
"loss": 0.4142,
"step": 893
},
{
"epoch": 1.6996197718631179,
"grad_norm": 0.032640279775106196,
"learning_rate": 1.3452861379047289e-06,
"loss": 0.4733,
"step": 894
},
{
"epoch": 1.7015209125475286,
"grad_norm": 0.035620076327424,
"learning_rate": 1.3286974540423747e-06,
"loss": 0.4201,
"step": 895
},
{
"epoch": 1.703422053231939,
"grad_norm": 0.028735453072537963,
"learning_rate": 1.3122044017779768e-06,
"loss": 0.457,
"step": 896
},
{
"epoch": 1.7053231939163498,
"grad_norm": 0.034944169046894284,
"learning_rate": 1.2958071630054214e-06,
"loss": 0.5117,
"step": 897
},
{
"epoch": 1.7072243346007605,
"grad_norm": 0.033183863875221604,
"learning_rate": 1.279505918561923e-06,
"loss": 0.4804,
"step": 898
},
{
"epoch": 1.709125475285171,
"grad_norm": 0.030811121531080534,
"learning_rate": 1.2633008482260146e-06,
"loss": 0.4716,
"step": 899
},
{
"epoch": 1.7110266159695817,
"grad_norm": 0.03345376038096608,
"learning_rate": 1.2471921307155655e-06,
"loss": 0.4737,
"step": 900
},
{
"epoch": 1.7129277566539924,
"grad_norm": 0.037879982302966894,
"learning_rate": 1.2311799436858275e-06,
"loss": 0.5145,
"step": 901
},
{
"epoch": 1.714828897338403,
"grad_norm": 0.03125840637334411,
"learning_rate": 1.2152644637274603e-06,
"loss": 0.5485,
"step": 902
},
{
"epoch": 1.7167300380228137,
"grad_norm": 0.02870599348239609,
"learning_rate": 1.1994458663645836e-06,
"loss": 0.444,
"step": 903
},
{
"epoch": 1.7186311787072244,
"grad_norm": 0.028065572422978687,
"learning_rate": 1.1837243260528542e-06,
"loss": 0.5199,
"step": 904
},
{
"epoch": 1.7205323193916349,
"grad_norm": 0.029566805517605176,
"learning_rate": 1.168100016177528e-06,
"loss": 0.4565,
"step": 905
},
{
"epoch": 1.7224334600760456,
"grad_norm": 0.03360875256380791,
"learning_rate": 1.1525731090515536e-06,
"loss": 0.4899,
"step": 906
},
{
"epoch": 1.7243346007604563,
"grad_norm": 0.027981726615800055,
"learning_rate": 1.137143775913675e-06,
"loss": 0.4513,
"step": 907
},
{
"epoch": 1.7262357414448668,
"grad_norm": 0.030425084620758658,
"learning_rate": 1.1218121869265365e-06,
"loss": 0.3923,
"step": 908
},
{
"epoch": 1.7281368821292775,
"grad_norm": 0.03058876706165132,
"learning_rate": 1.1065785111748117e-06,
"loss": 0.4462,
"step": 909
},
{
"epoch": 1.7300380228136882,
"grad_norm": 0.02646253874188642,
"learning_rate": 1.0914429166633355e-06,
"loss": 0.4134,
"step": 910
},
{
"epoch": 1.7319391634980987,
"grad_norm": 0.0324500004362468,
"learning_rate": 1.076405570315252e-06,
"loss": 0.4459,
"step": 911
},
{
"epoch": 1.7338403041825095,
"grad_norm": 0.031065005091304766,
"learning_rate": 1.0614666379701732e-06,
"loss": 0.4725,
"step": 912
},
{
"epoch": 1.7357414448669202,
"grad_norm": 0.03012688741381645,
"learning_rate": 1.046626284382356e-06,
"loss": 0.5102,
"step": 913
},
{
"epoch": 1.7376425855513307,
"grad_norm": 0.03454189690967679,
"learning_rate": 1.0318846732188737e-06,
"loss": 0.4659,
"step": 914
},
{
"epoch": 1.7395437262357416,
"grad_norm": 0.029516089989690384,
"learning_rate": 1.017241967057816e-06,
"loss": 0.4616,
"step": 915
},
{
"epoch": 1.741444866920152,
"grad_norm": 0.0332903672973333,
"learning_rate": 1.0026983273865055e-06,
"loss": 0.401,
"step": 916
},
{
"epoch": 1.7433460076045626,
"grad_norm": 0.027987782732721567,
"learning_rate": 9.882539145997027e-07,
"loss": 0.4547,
"step": 917
},
{
"epoch": 1.7452471482889735,
"grad_norm": 0.030911921172495468,
"learning_rate": 9.739088879978409e-07,
"loss": 0.5301,
"step": 918
},
{
"epoch": 1.747148288973384,
"grad_norm": 0.026292516823905276,
"learning_rate": 9.59663405785277e-07,
"loss": 0.3759,
"step": 919
},
{
"epoch": 1.7490494296577945,
"grad_norm": 0.03205077235432636,
"learning_rate": 9.455176250685338e-07,
"loss": 0.4899,
"step": 920
},
{
"epoch": 1.7509505703422055,
"grad_norm": 0.028832804448268377,
"learning_rate": 9.314717018545838e-07,
"loss": 0.4195,
"step": 921
},
{
"epoch": 1.752851711026616,
"grad_norm": 0.028850241158891822,
"learning_rate": 9.17525791049112e-07,
"loss": 0.5263,
"step": 922
},
{
"epoch": 1.7547528517110265,
"grad_norm": 0.02997489825275393,
"learning_rate": 9.036800464548157e-07,
"loss": 0.5086,
"step": 923
},
{
"epoch": 1.7566539923954374,
"grad_norm": 0.03263348036982503,
"learning_rate": 8.899346207697135e-07,
"loss": 0.4947,
"step": 924
},
{
"epoch": 1.758555133079848,
"grad_norm": 0.030306018578941444,
"learning_rate": 8.762896655854481e-07,
"loss": 0.4048,
"step": 925
},
{
"epoch": 1.7604562737642584,
"grad_norm": 0.030759365752075392,
"learning_rate": 8.627453313856249e-07,
"loss": 0.5442,
"step": 926
},
{
"epoch": 1.7623574144486693,
"grad_norm": 0.031728909675695,
"learning_rate": 8.493017675441495e-07,
"loss": 0.4838,
"step": 927
},
{
"epoch": 1.7642585551330798,
"grad_norm": 0.030547999204859254,
"learning_rate": 8.359591223235785e-07,
"loss": 0.4355,
"step": 928
},
{
"epoch": 1.7661596958174905,
"grad_norm": 0.026057203038169253,
"learning_rate": 8.227175428734868e-07,
"loss": 0.4242,
"step": 929
},
{
"epoch": 1.7680608365019013,
"grad_norm": 0.029784743824152658,
"learning_rate": 8.095771752288451e-07,
"loss": 0.4369,
"step": 930
},
{
"epoch": 1.7699619771863118,
"grad_norm": 0.03225492850134359,
"learning_rate": 7.965381643084069e-07,
"loss": 0.3777,
"step": 931
},
{
"epoch": 1.7718631178707225,
"grad_norm": 0.03269172748299184,
"learning_rate": 7.83600653913108e-07,
"loss": 0.469,
"step": 932
},
{
"epoch": 1.7737642585551332,
"grad_norm": 0.030918866700995487,
"learning_rate": 7.707647867244927e-07,
"loss": 0.4663,
"step": 933
},
{
"epoch": 1.7756653992395437,
"grad_norm": 0.028030328242848276,
"learning_rate": 7.580307043031232e-07,
"loss": 0.5157,
"step": 934
},
{
"epoch": 1.7775665399239544,
"grad_norm": 0.033417474341330244,
"learning_rate": 7.453985470870284e-07,
"loss": 0.5319,
"step": 935
},
{
"epoch": 1.7794676806083651,
"grad_norm": 0.03507760060732998,
"learning_rate": 7.328684543901598e-07,
"loss": 0.4532,
"step": 936
},
{
"epoch": 1.7813688212927756,
"grad_norm": 0.028273930230182195,
"learning_rate": 7.204405644008416e-07,
"loss": 0.4521,
"step": 937
},
{
"epoch": 1.7832699619771863,
"grad_norm": 0.03158701741075583,
"learning_rate": 7.081150141802518e-07,
"loss": 0.448,
"step": 938
},
{
"epoch": 1.785171102661597,
"grad_norm": 0.031314206591594035,
"learning_rate": 6.958919396609231e-07,
"loss": 0.4567,
"step": 939
},
{
"epoch": 1.7870722433460076,
"grad_norm": 0.03157721386615864,
"learning_rate": 6.837714756452241e-07,
"loss": 0.4545,
"step": 940
},
{
"epoch": 1.7889733840304183,
"grad_norm": 0.02892824183275648,
"learning_rate": 6.717537558038845e-07,
"loss": 0.4609,
"step": 941
},
{
"epoch": 1.790874524714829,
"grad_norm": 0.03734105942938574,
"learning_rate": 6.598389126745209e-07,
"loss": 0.4129,
"step": 942
},
{
"epoch": 1.7927756653992395,
"grad_norm": 0.028796100332848178,
"learning_rate": 6.480270776601682e-07,
"loss": 0.4933,
"step": 943
},
{
"epoch": 1.7946768060836502,
"grad_norm": 0.02724205290254438,
"learning_rate": 6.36318381027835e-07,
"loss": 0.3796,
"step": 944
},
{
"epoch": 1.796577946768061,
"grad_norm": 0.029765219535193906,
"learning_rate": 6.247129519070728e-07,
"loss": 0.4206,
"step": 945
},
{
"epoch": 1.7984790874524714,
"grad_norm": 0.031351558482127034,
"learning_rate": 6.132109182885382e-07,
"loss": 0.3921,
"step": 946
},
{
"epoch": 1.8003802281368821,
"grad_norm": 0.03313115821415064,
"learning_rate": 6.018124070225928e-07,
"loss": 0.357,
"step": 947
},
{
"epoch": 1.8022813688212929,
"grad_norm": 0.02923966035182855,
"learning_rate": 5.905175438178979e-07,
"loss": 0.5295,
"step": 948
},
{
"epoch": 1.8041825095057034,
"grad_norm": 0.027446344432688532,
"learning_rate": 5.793264532400311e-07,
"loss": 0.4596,
"step": 949
},
{
"epoch": 1.806083650190114,
"grad_norm": 0.03034572172867263,
"learning_rate": 5.68239258710116e-07,
"loss": 0.4495,
"step": 950
},
{
"epoch": 1.8079847908745248,
"grad_norm": 0.03137500197835899,
"learning_rate": 5.572560825034523e-07,
"loss": 0.4195,
"step": 951
},
{
"epoch": 1.8098859315589353,
"grad_norm": 0.02687436007598942,
"learning_rate": 5.463770457481732e-07,
"loss": 0.4481,
"step": 952
},
{
"epoch": 1.811787072243346,
"grad_norm": 0.033298984336612214,
"learning_rate": 5.35602268423906e-07,
"loss": 0.4481,
"step": 953
},
{
"epoch": 1.8136882129277567,
"grad_norm": 0.03074715608006006,
"learning_rate": 5.249318693604577e-07,
"loss": 0.4081,
"step": 954
},
{
"epoch": 1.8155893536121672,
"grad_norm": 0.032907124189825374,
"learning_rate": 5.143659662364931e-07,
"loss": 0.45,
"step": 955
},
{
"epoch": 1.817490494296578,
"grad_norm": 0.02894943546277151,
"learning_rate": 5.039046755782417e-07,
"loss": 0.5292,
"step": 956
},
{
"epoch": 1.8193916349809887,
"grad_norm": 0.03144122062146257,
"learning_rate": 4.935481127582131e-07,
"loss": 0.4253,
"step": 957
},
{
"epoch": 1.8212927756653992,
"grad_norm": 0.029991897988623707,
"learning_rate": 4.83296391993926e-07,
"loss": 0.4225,
"step": 958
},
{
"epoch": 1.8231939163498099,
"grad_norm": 0.03296037001549121,
"learning_rate": 4.7314962634664616e-07,
"loss": 0.428,
"step": 959
},
{
"epoch": 1.8250950570342206,
"grad_norm": 0.03194095308465852,
"learning_rate": 4.631079277201389e-07,
"loss": 0.5275,
"step": 960
},
{
"epoch": 1.826996197718631,
"grad_norm": 0.030900947330494876,
"learning_rate": 4.5317140685943726e-07,
"loss": 0.4579,
"step": 961
},
{
"epoch": 1.8288973384030418,
"grad_norm": 0.034840033361790874,
"learning_rate": 4.433401733496201e-07,
"loss": 0.4375,
"step": 962
},
{
"epoch": 1.8307984790874525,
"grad_norm": 0.029344448848243988,
"learning_rate": 4.3361433561460274e-07,
"loss": 0.4094,
"step": 963
},
{
"epoch": 1.832699619771863,
"grad_norm": 0.03246508942021766,
"learning_rate": 4.2399400091594154e-07,
"loss": 0.4402,
"step": 964
},
{
"epoch": 1.8346007604562737,
"grad_norm": 0.02628871622217315,
"learning_rate": 4.14479275351648e-07,
"loss": 0.4588,
"step": 965
},
{
"epoch": 1.8365019011406845,
"grad_norm": 0.03170635068076932,
"learning_rate": 4.0507026385502747e-07,
"loss": 0.4594,
"step": 966
},
{
"epoch": 1.838403041825095,
"grad_norm": 0.03101671357271921,
"learning_rate": 3.9576707019350903e-07,
"loss": 0.526,
"step": 967
},
{
"epoch": 1.8403041825095057,
"grad_norm": 0.030729567695037974,
"learning_rate": 3.865697969675164e-07,
"loss": 0.6355,
"step": 968
},
{
"epoch": 1.8422053231939164,
"grad_norm": 0.034474475882619045,
"learning_rate": 3.7747854560931996e-07,
"loss": 0.4457,
"step": 969
},
{
"epoch": 1.8441064638783269,
"grad_norm": 0.03421378885683852,
"learning_rate": 3.684934163819309e-07,
"loss": 0.462,
"step": 970
},
{
"epoch": 1.8460076045627376,
"grad_norm": 0.03363185402579016,
"learning_rate": 3.596145083779912e-07,
"loss": 0.5014,
"step": 971
},
{
"epoch": 1.8479087452471483,
"grad_norm": 0.030306139921095637,
"learning_rate": 3.508419195186774e-07,
"loss": 0.4979,
"step": 972
},
{
"epoch": 1.8498098859315588,
"grad_norm": 0.03157930603234884,
"learning_rate": 3.421757465526243e-07,
"loss": 0.479,
"step": 973
},
{
"epoch": 1.8517110266159695,
"grad_norm": 0.03173802078060801,
"learning_rate": 3.33616085054862e-07,
"loss": 0.3983,
"step": 974
},
{
"epoch": 1.8536121673003803,
"grad_norm": 0.031450770993991316,
"learning_rate": 3.2516302942574794e-07,
"loss": 0.545,
"step": 975
},
{
"epoch": 1.8555133079847907,
"grad_norm": 0.032790034715735716,
"learning_rate": 3.1681667288994353e-07,
"loss": 0.4353,
"step": 976
},
{
"epoch": 1.8574144486692015,
"grad_norm": 0.03199939935220213,
"learning_rate": 3.0857710749537585e-07,
"loss": 0.364,
"step": 977
},
{
"epoch": 1.8593155893536122,
"grad_norm": 0.03373185092711587,
"learning_rate": 3.0044442411222066e-07,
"loss": 0.4758,
"step": 978
},
{
"epoch": 1.8612167300380227,
"grad_norm": 0.030669861295071797,
"learning_rate": 2.9241871243190555e-07,
"loss": 0.3871,
"step": 979
},
{
"epoch": 1.8631178707224336,
"grad_norm": 0.02976642847865338,
"learning_rate": 2.845000609661208e-07,
"loss": 0.4292,
"step": 980
},
{
"epoch": 1.8650190114068441,
"grad_norm": 0.029865230773212417,
"learning_rate": 2.7668855704583997e-07,
"loss": 0.4625,
"step": 981
},
{
"epoch": 1.8669201520912546,
"grad_norm": 0.029861179822064734,
"learning_rate": 2.689842868203563e-07,
"loss": 0.5372,
"step": 982
},
{
"epoch": 1.8688212927756656,
"grad_norm": 0.03191778594102872,
"learning_rate": 2.6138733525633896e-07,
"loss": 0.5021,
"step": 983
},
{
"epoch": 1.870722433460076,
"grad_norm": 0.034314296915894583,
"learning_rate": 2.5389778613688744e-07,
"loss": 0.4439,
"step": 984
},
{
"epoch": 1.8726235741444865,
"grad_norm": 0.03774853955023176,
"learning_rate": 2.46515722060614e-07,
"loss": 0.5214,
"step": 985
},
{
"epoch": 1.8745247148288975,
"grad_norm": 0.03368332286177959,
"learning_rate": 2.392412244407294e-07,
"loss": 0.4704,
"step": 986
},
{
"epoch": 1.876425855513308,
"grad_norm": 0.03186220294437927,
"learning_rate": 2.3207437350414418e-07,
"loss": 0.4223,
"step": 987
},
{
"epoch": 1.8783269961977185,
"grad_norm": 0.03615903282922533,
"learning_rate": 2.2501524829059208e-07,
"loss": 0.3987,
"step": 988
},
{
"epoch": 1.8802281368821294,
"grad_norm": 0.030441277038341368,
"learning_rate": 2.180639266517448e-07,
"loss": 0.4291,
"step": 989
},
{
"epoch": 1.88212927756654,
"grad_norm": 0.031277987851696665,
"learning_rate": 2.1122048525036409e-07,
"loss": 0.4889,
"step": 990
},
{
"epoch": 1.8840304182509504,
"grad_norm": 0.029387610313056912,
"learning_rate": 2.0448499955945223e-07,
"loss": 0.4611,
"step": 991
},
{
"epoch": 1.8859315589353614,
"grad_norm": 0.030591474090613247,
"learning_rate": 1.9785754386142164e-07,
"loss": 0.5012,
"step": 992
},
{
"epoch": 1.8878326996197718,
"grad_norm": 0.028714589339226205,
"learning_rate": 1.9133819124727003e-07,
"loss": 0.4686,
"step": 993
},
{
"epoch": 1.8897338403041823,
"grad_norm": 0.02959569862183423,
"learning_rate": 1.8492701361578326e-07,
"loss": 0.4696,
"step": 994
},
{
"epoch": 1.8916349809885933,
"grad_norm": 0.0328146527760817,
"learning_rate": 1.7862408167273472e-07,
"loss": 0.3678,
"step": 995
},
{
"epoch": 1.8935361216730038,
"grad_norm": 0.029123499221954324,
"learning_rate": 1.724294649301095e-07,
"loss": 0.436,
"step": 996
},
{
"epoch": 1.8954372623574145,
"grad_norm": 0.0293269284819944,
"learning_rate": 1.6634323170533928e-07,
"loss": 0.4569,
"step": 997
},
{
"epoch": 1.8973384030418252,
"grad_norm": 0.027814429410490966,
"learning_rate": 1.6036544912054087e-07,
"loss": 0.3659,
"step": 998
},
{
"epoch": 1.8992395437262357,
"grad_norm": 0.0327477941814678,
"learning_rate": 1.544961831017855e-07,
"loss": 0.476,
"step": 999
},
{
"epoch": 1.9011406844106464,
"grad_norm": 0.03443055528922134,
"learning_rate": 1.487354983783673e-07,
"loss": 0.4419,
"step": 1000
},
{
"epoch": 1.9030418250950571,
"grad_norm": 0.02594462226434814,
"learning_rate": 1.430834584820895e-07,
"loss": 0.4449,
"step": 1001
},
{
"epoch": 1.9049429657794676,
"grad_norm": 0.03471230118951238,
"learning_rate": 1.375401257465625e-07,
"loss": 0.4715,
"step": 1002
},
{
"epoch": 1.9068441064638784,
"grad_norm": 0.030751789179219086,
"learning_rate": 1.3210556130652031e-07,
"loss": 0.3707,
"step": 1003
},
{
"epoch": 1.908745247148289,
"grad_norm": 0.03136393500105467,
"learning_rate": 1.2677982509714415e-07,
"loss": 0.429,
"step": 1004
},
{
"epoch": 1.9106463878326996,
"grad_norm": 0.0324151007308297,
"learning_rate": 1.2156297585339872e-07,
"loss": 0.4923,
"step": 1005
},
{
"epoch": 1.9125475285171103,
"grad_norm": 0.030257241474964322,
"learning_rate": 1.1645507110938925e-07,
"loss": 0.3798,
"step": 1006
},
{
"epoch": 1.914448669201521,
"grad_norm": 0.03529946764667141,
"learning_rate": 1.1145616719772545e-07,
"loss": 0.4688,
"step": 1007
},
{
"epoch": 1.9163498098859315,
"grad_norm": 0.0309723338831087,
"learning_rate": 1.0656631924889749e-07,
"loss": 0.5193,
"step": 1008
},
{
"epoch": 1.9182509505703422,
"grad_norm": 0.031474237973403506,
"learning_rate": 1.0178558119067316e-07,
"loss": 0.3985,
"step": 1009
},
{
"epoch": 1.920152091254753,
"grad_norm": 0.03147376204925686,
"learning_rate": 9.711400574749507e-08,
"loss": 0.4797,
"step": 1010
},
{
"epoch": 1.9220532319391634,
"grad_norm": 0.028614904232453716,
"learning_rate": 9.255164443990994e-08,
"loss": 0.4645,
"step": 1011
},
{
"epoch": 1.9239543726235742,
"grad_norm": 0.030365026569649265,
"learning_rate": 8.809854758399017e-08,
"loss": 0.495,
"step": 1012
},
{
"epoch": 1.9258555133079849,
"grad_norm": 0.02958828619871872,
"learning_rate": 8.375476429078543e-08,
"loss": 0.4736,
"step": 1013
},
{
"epoch": 1.9277566539923954,
"grad_norm": 0.03578924085646632,
"learning_rate": 7.952034246577977e-08,
"loss": 0.4667,
"step": 1014
},
{
"epoch": 1.929657794676806,
"grad_norm": 0.03039288957416989,
"learning_rate": 7.539532880836087e-08,
"loss": 0.3965,
"step": 1015
},
{
"epoch": 1.9315589353612168,
"grad_norm": 0.030213945855540075,
"learning_rate": 7.137976881130826e-08,
"loss": 0.3838,
"step": 1016
},
{
"epoch": 1.9334600760456273,
"grad_norm": 0.02884747685368914,
"learning_rate": 6.747370676028819e-08,
"loss": 0.4683,
"step": 1017
},
{
"epoch": 1.935361216730038,
"grad_norm": 0.03421752604319262,
"learning_rate": 6.367718573336845e-08,
"loss": 0.4621,
"step": 1018
},
{
"epoch": 1.9372623574144487,
"grad_norm": 0.03343470147649224,
"learning_rate": 5.999024760054095e-08,
"loss": 0.466,
"step": 1019
},
{
"epoch": 1.9391634980988592,
"grad_norm": 0.027789701521310304,
"learning_rate": 5.641293302326323e-08,
"loss": 0.4209,
"step": 1020
},
{
"epoch": 1.94106463878327,
"grad_norm": 0.03664919177396004,
"learning_rate": 5.2945281454003236e-08,
"loss": 0.45,
"step": 1021
},
{
"epoch": 1.9429657794676807,
"grad_norm": 0.03512768344119699,
"learning_rate": 4.958733113581415e-08,
"loss": 0.5002,
"step": 1022
},
{
"epoch": 1.9448669201520912,
"grad_norm": 0.032285534675066084,
"learning_rate": 4.6339119101902475e-08,
"loss": 0.4585,
"step": 1023
},
{
"epoch": 1.946768060836502,
"grad_norm": 0.028015055200238535,
"learning_rate": 4.320068117522835e-08,
"loss": 0.462,
"step": 1024
},
{
"epoch": 1.9486692015209126,
"grad_norm": 0.026824398589096972,
"learning_rate": 4.0172051968101474e-08,
"loss": 0.3529,
"step": 1025
},
{
"epoch": 1.950570342205323,
"grad_norm": 0.029707737491614556,
"learning_rate": 3.7253264881809137e-08,
"loss": 0.465,
"step": 1026
},
{
"epoch": 1.9524714828897338,
"grad_norm": 0.03173165055291673,
"learning_rate": 3.4444352106242086e-08,
"loss": 0.4333,
"step": 1027
},
{
"epoch": 1.9543726235741445,
"grad_norm": 0.027659676233207857,
"learning_rate": 3.174534461953593e-08,
"loss": 0.4004,
"step": 1028
},
{
"epoch": 1.956273764258555,
"grad_norm": 0.027404644233989556,
"learning_rate": 2.915627218774142e-08,
"loss": 0.3796,
"step": 1029
},
{
"epoch": 1.9581749049429658,
"grad_norm": 0.026599247935916007,
"learning_rate": 2.667716336448356e-08,
"loss": 0.3555,
"step": 1030
},
{
"epoch": 1.9600760456273765,
"grad_norm": 0.03292570768996639,
"learning_rate": 2.430804549065302e-08,
"loss": 0.4199,
"step": 1031
},
{
"epoch": 1.961977186311787,
"grad_norm": 0.029654656511763144,
"learning_rate": 2.2048944694104123e-08,
"loss": 0.4099,
"step": 1032
},
{
"epoch": 1.9638783269961977,
"grad_norm": 0.029568119617424664,
"learning_rate": 1.989988588936509e-08,
"loss": 0.5667,
"step": 1033
},
{
"epoch": 1.9657794676806084,
"grad_norm": 0.03279552786438916,
"learning_rate": 1.7860892777367133e-08,
"loss": 0.4053,
"step": 1034
},
{
"epoch": 1.967680608365019,
"grad_norm": 0.027159340862676504,
"learning_rate": 1.5931987845176912e-08,
"loss": 0.4461,
"step": 1035
},
{
"epoch": 1.9695817490494296,
"grad_norm": 0.03157329108514617,
"learning_rate": 1.411319236575337e-08,
"loss": 0.388,
"step": 1036
},
{
"epoch": 1.9714828897338403,
"grad_norm": 0.031103650357148457,
"learning_rate": 1.2404526397711281e-08,
"loss": 0.4071,
"step": 1037
},
{
"epoch": 1.9733840304182508,
"grad_norm": 0.030963116179377713,
"learning_rate": 1.0806008785100297e-08,
"loss": 0.3987,
"step": 1038
},
{
"epoch": 1.9752851711026616,
"grad_norm": 0.031098576501293572,
"learning_rate": 9.317657157197347e-09,
"loss": 0.4902,
"step": 1039
},
{
"epoch": 1.9771863117870723,
"grad_norm": 0.03523165445859305,
"learning_rate": 7.93948792831234e-09,
"loss": 0.5261,
"step": 1040
},
{
"epoch": 1.9790874524714828,
"grad_norm": 0.03432032449507075,
"learning_rate": 6.671516297606095e-09,
"loss": 0.5043,
"step": 1041
},
{
"epoch": 1.9809885931558935,
"grad_norm": 0.028102832320697466,
"learning_rate": 5.513756248924917e-09,
"loss": 0.4402,
"step": 1042
},
{
"epoch": 1.9828897338403042,
"grad_norm": 0.029094175427136368,
"learning_rate": 4.466220550641831e-09,
"loss": 0.4499,
"step": 1043
},
{
"epoch": 1.9847908745247147,
"grad_norm": 0.030662117911304455,
"learning_rate": 3.528920755523357e-09,
"loss": 0.492,
"step": 1044
},
{
"epoch": 1.9866920152091256,
"grad_norm": 0.036622107235485084,
"learning_rate": 2.701867200592956e-09,
"loss": 0.417,
"step": 1045
},
{
"epoch": 1.9885931558935361,
"grad_norm": 0.03176507464018935,
"learning_rate": 1.9850690070266633e-09,
"loss": 0.5901,
"step": 1046
},
{
"epoch": 1.9904942965779466,
"grad_norm": 0.028746410795910952,
"learning_rate": 1.378534080042071e-09,
"loss": 0.4125,
"step": 1047
},
{
"epoch": 1.9923954372623576,
"grad_norm": 0.03168022954272395,
"learning_rate": 8.822691088195001e-10,
"loss": 0.4419,
"step": 1048
},
{
"epoch": 1.994296577946768,
"grad_norm": 0.03596484061103507,
"learning_rate": 4.962795664265052e-10,
"loss": 0.4668,
"step": 1049
},
{
"epoch": 1.9961977186311786,
"grad_norm": 0.03278898993455145,
"learning_rate": 2.2056970975459223e-10,
"loss": 0.4626,
"step": 1050
},
{
"epoch": 1.9980988593155895,
"grad_norm": 0.02636590369941191,
"learning_rate": 5.514257947369928e-11,
"loss": 0.3786,
"step": 1051
},
{
"epoch": 2.0,
"grad_norm": 0.03134952245123963,
"learning_rate": 0.0,
"loss": 0.4029,
"step": 1052
},
{
"epoch": 2.0,
"eval_loss": 0.4882815182209015,
"eval_runtime": 2.0788,
"eval_samples_per_second": 2.886,
"eval_steps_per_second": 0.481,
"step": 1052
},
{
"epoch": 2.0,
"step": 1052,
"total_flos": 1.6469503016697856e+16,
"train_loss": 0.46453300517888124,
"train_runtime": 22645.592,
"train_samples_per_second": 1.486,
"train_steps_per_second": 0.046
}
],
"logging_steps": 1,
"max_steps": 1052,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 1.6469503016697856e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}