Testys's picture
Add 11 files
e23d9d4 verified
Raw
History Blame Contribute Delete
108 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 118,
"global_step": 590,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01694915254237288,
"grad_norm": 0.3882841169834137,
"learning_rate": 0.0,
"loss": 1.580078125,
"step": 1
},
{
"epoch": 0.03389830508474576,
"grad_norm": 0.40203434228897095,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.5751953125,
"step": 2
},
{
"epoch": 0.05084745762711865,
"grad_norm": 0.32282793521881104,
"learning_rate": 6.666666666666667e-06,
"loss": 1.412109375,
"step": 3
},
{
"epoch": 0.06779661016949153,
"grad_norm": 0.46856820583343506,
"learning_rate": 1e-05,
"loss": 1.625,
"step": 4
},
{
"epoch": 0.0847457627118644,
"grad_norm": 0.49137574434280396,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.56787109375,
"step": 5
},
{
"epoch": 0.1016949152542373,
"grad_norm": 0.4288746416568756,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.543212890625,
"step": 6
},
{
"epoch": 0.11864406779661017,
"grad_norm": 0.3335217237472534,
"learning_rate": 2e-05,
"loss": 1.4423828125,
"step": 7
},
{
"epoch": 0.13559322033898305,
"grad_norm": 0.22800016403198242,
"learning_rate": 2.3333333333333336e-05,
"loss": 1.3408203125,
"step": 8
},
{
"epoch": 0.15254237288135594,
"grad_norm": 0.2231530249118805,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.3544921875,
"step": 9
},
{
"epoch": 0.1694915254237288,
"grad_norm": 0.16720709204673767,
"learning_rate": 3e-05,
"loss": 1.31494140625,
"step": 10
},
{
"epoch": 0.1864406779661017,
"grad_norm": 0.12689752876758575,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.3134765625,
"step": 11
},
{
"epoch": 0.2033898305084746,
"grad_norm": 0.0942511260509491,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.2275390625,
"step": 12
},
{
"epoch": 0.22033898305084745,
"grad_norm": 0.0895562544465065,
"learning_rate": 4e-05,
"loss": 1.228515625,
"step": 13
},
{
"epoch": 0.23728813559322035,
"grad_norm": 0.09689676761627197,
"learning_rate": 4.3333333333333334e-05,
"loss": 1.21484375,
"step": 14
},
{
"epoch": 0.2542372881355932,
"grad_norm": 0.11385320872068405,
"learning_rate": 4.666666666666667e-05,
"loss": 1.2548828125,
"step": 15
},
{
"epoch": 0.2711864406779661,
"grad_norm": 0.16627047955989838,
"learning_rate": 5e-05,
"loss": 1.2099609375,
"step": 16
},
{
"epoch": 0.288135593220339,
"grad_norm": 0.155990332365036,
"learning_rate": 5.333333333333333e-05,
"loss": 1.24462890625,
"step": 17
},
{
"epoch": 0.3050847457627119,
"grad_norm": 0.11767745018005371,
"learning_rate": 5.666666666666667e-05,
"loss": 1.228515625,
"step": 18
},
{
"epoch": 0.3220338983050847,
"grad_norm": 0.10818684846162796,
"learning_rate": 6e-05,
"loss": 1.2919921875,
"step": 19
},
{
"epoch": 0.3389830508474576,
"grad_norm": 0.0706990584731102,
"learning_rate": 6.333333333333333e-05,
"loss": 1.15283203125,
"step": 20
},
{
"epoch": 0.3559322033898305,
"grad_norm": 0.0639033317565918,
"learning_rate": 6.666666666666667e-05,
"loss": 1.102020263671875,
"step": 21
},
{
"epoch": 0.3728813559322034,
"grad_norm": 0.07082787156105042,
"learning_rate": 7e-05,
"loss": 1.19580078125,
"step": 22
},
{
"epoch": 0.3898305084745763,
"grad_norm": 0.07857843488454819,
"learning_rate": 7.333333333333333e-05,
"loss": 1.1728515625,
"step": 23
},
{
"epoch": 0.4067796610169492,
"grad_norm": 0.07582847774028778,
"learning_rate": 7.666666666666667e-05,
"loss": 1.1123046875,
"step": 24
},
{
"epoch": 0.423728813559322,
"grad_norm": 0.07055588066577911,
"learning_rate": 8e-05,
"loss": 1.15234375,
"step": 25
},
{
"epoch": 0.4406779661016949,
"grad_norm": 0.06727379560470581,
"learning_rate": 8.333333333333334e-05,
"loss": 1.0146484375,
"step": 26
},
{
"epoch": 0.4576271186440678,
"grad_norm": 0.058710888028144836,
"learning_rate": 8.666666666666667e-05,
"loss": 1.02392578125,
"step": 27
},
{
"epoch": 0.4745762711864407,
"grad_norm": 0.05762356519699097,
"learning_rate": 9e-05,
"loss": 1.064453125,
"step": 28
},
{
"epoch": 0.4915254237288136,
"grad_norm": 0.051819637417793274,
"learning_rate": 9.333333333333334e-05,
"loss": 1.2421875,
"step": 29
},
{
"epoch": 0.5084745762711864,
"grad_norm": 0.044223979115486145,
"learning_rate": 9.666666666666667e-05,
"loss": 1.11181640625,
"step": 30
},
{
"epoch": 0.5254237288135594,
"grad_norm": 0.04457638040184975,
"learning_rate": 0.0001,
"loss": 1.10009765625,
"step": 31
},
{
"epoch": 0.5423728813559322,
"grad_norm": 0.055358678102493286,
"learning_rate": 9.999929188291895e-05,
"loss": 1.189453125,
"step": 32
},
{
"epoch": 0.559322033898305,
"grad_norm": 0.04296921193599701,
"learning_rate": 9.999716755396153e-05,
"loss": 1.12939453125,
"step": 33
},
{
"epoch": 0.576271186440678,
"grad_norm": 0.04023062810301781,
"learning_rate": 9.999362707998438e-05,
"loss": 1.07568359375,
"step": 34
},
{
"epoch": 0.5932203389830508,
"grad_norm": 0.04000389948487282,
"learning_rate": 9.99886705724128e-05,
"loss": 1.087890625,
"step": 35
},
{
"epoch": 0.6101694915254238,
"grad_norm": 0.03627844899892807,
"learning_rate": 9.998229818723739e-05,
"loss": 1.041015625,
"step": 36
},
{
"epoch": 0.6271186440677966,
"grad_norm": 0.03456282243132591,
"learning_rate": 9.997451012500901e-05,
"loss": 0.95458984375,
"step": 37
},
{
"epoch": 0.6440677966101694,
"grad_norm": 0.04247819259762764,
"learning_rate": 9.996530663083255e-05,
"loss": 1.02197265625,
"step": 38
},
{
"epoch": 0.6610169491525424,
"grad_norm": 0.041472356766462326,
"learning_rate": 9.995468799435917e-05,
"loss": 1.171875,
"step": 39
},
{
"epoch": 0.6779661016949152,
"grad_norm": 0.028900958597660065,
"learning_rate": 9.994265454977724e-05,
"loss": 1.05419921875,
"step": 40
},
{
"epoch": 0.6949152542372882,
"grad_norm": 0.03293260931968689,
"learning_rate": 9.992920667580176e-05,
"loss": 1.05908203125,
"step": 41
},
{
"epoch": 0.711864406779661,
"grad_norm": 0.036883097141981125,
"learning_rate": 9.991434479566246e-05,
"loss": 0.9921875,
"step": 42
},
{
"epoch": 0.7288135593220338,
"grad_norm": 0.03548790514469147,
"learning_rate": 9.989806937709054e-05,
"loss": 1.09521484375,
"step": 43
},
{
"epoch": 0.7457627118644068,
"grad_norm": 0.03864596411585808,
"learning_rate": 9.988038093230382e-05,
"loss": 1.149658203125,
"step": 44
},
{
"epoch": 0.7627118644067796,
"grad_norm": 0.03816678002476692,
"learning_rate": 9.986128001799077e-05,
"loss": 1.11572265625,
"step": 45
},
{
"epoch": 0.7796610169491526,
"grad_norm": 0.030919115990400314,
"learning_rate": 9.984076723529288e-05,
"loss": 1.119384765625,
"step": 46
},
{
"epoch": 0.7966101694915254,
"grad_norm": 0.03027261048555374,
"learning_rate": 9.981884322978576e-05,
"loss": 1.0732421875,
"step": 47
},
{
"epoch": 0.8135593220338984,
"grad_norm": 0.032278310507535934,
"learning_rate": 9.97955086914589e-05,
"loss": 1.0068359375,
"step": 48
},
{
"epoch": 0.8305084745762712,
"grad_norm": 0.033531028777360916,
"learning_rate": 9.977076435469385e-05,
"loss": 1.060546875,
"step": 49
},
{
"epoch": 0.847457627118644,
"grad_norm": 0.03016388602554798,
"learning_rate": 9.974461099824118e-05,
"loss": 1.0205078125,
"step": 50
},
{
"epoch": 0.864406779661017,
"grad_norm": 0.02948145382106304,
"learning_rate": 9.971704944519594e-05,
"loss": 1.07373046875,
"step": 51
},
{
"epoch": 0.8813559322033898,
"grad_norm": 0.03135800361633301,
"learning_rate": 9.96880805629717e-05,
"loss": 1.05322265625,
"step": 52
},
{
"epoch": 0.8983050847457628,
"grad_norm": 0.02797420136630535,
"learning_rate": 9.96577052632734e-05,
"loss": 1.02099609375,
"step": 53
},
{
"epoch": 0.9152542372881356,
"grad_norm": 0.033295344561338425,
"learning_rate": 9.962592450206852e-05,
"loss": 1.048828125,
"step": 54
},
{
"epoch": 0.9322033898305084,
"grad_norm": 0.03138762712478638,
"learning_rate": 9.959273927955706e-05,
"loss": 1.015625,
"step": 55
},
{
"epoch": 0.9491525423728814,
"grad_norm": 0.03059304878115654,
"learning_rate": 9.955815064014006e-05,
"loss": 1.03369140625,
"step": 56
},
{
"epoch": 0.9661016949152542,
"grad_norm": 0.031984712928533554,
"learning_rate": 9.952215967238665e-05,
"loss": 1.05322265625,
"step": 57
},
{
"epoch": 0.9830508474576272,
"grad_norm": 0.029459724202752113,
"learning_rate": 9.948476750899993e-05,
"loss": 1.04541015625,
"step": 58
},
{
"epoch": 1.0,
"grad_norm": 0.033664435148239136,
"learning_rate": 9.94459753267812e-05,
"loss": 1.095703125,
"step": 59
},
{
"epoch": 1.0169491525423728,
"grad_norm": 0.03020293079316616,
"learning_rate": 9.9405784346593e-05,
"loss": 1.068359375,
"step": 60
},
{
"epoch": 1.0338983050847457,
"grad_norm": 0.06664912402629852,
"learning_rate": 9.936419583332062e-05,
"loss": 1.056640625,
"step": 61
},
{
"epoch": 1.0508474576271187,
"grad_norm": 0.030621351674199104,
"learning_rate": 9.932121109583236e-05,
"loss": 0.9853515625,
"step": 62
},
{
"epoch": 1.0677966101694916,
"grad_norm": 0.07098930329084396,
"learning_rate": 9.927683148693833e-05,
"loss": 1.03076171875,
"step": 63
},
{
"epoch": 1.0847457627118644,
"grad_norm": 0.03257926553487778,
"learning_rate": 9.92310584033478e-05,
"loss": 0.95263671875,
"step": 64
},
{
"epoch": 1.1016949152542372,
"grad_norm": 0.032210949808359146,
"learning_rate": 9.918389328562534e-05,
"loss": 1.0093994140625,
"step": 65
},
{
"epoch": 1.11864406779661,
"grad_norm": 0.03204033896327019,
"learning_rate": 9.913533761814537e-05,
"loss": 1.01806640625,
"step": 66
},
{
"epoch": 1.1355932203389831,
"grad_norm": 0.034301772713661194,
"learning_rate": 9.90853929290456e-05,
"loss": 1.0009765625,
"step": 67
},
{
"epoch": 1.152542372881356,
"grad_norm": 0.03531131148338318,
"learning_rate": 9.90340607901788e-05,
"loss": 1.02685546875,
"step": 68
},
{
"epoch": 1.1694915254237288,
"grad_norm": 0.037073180079460144,
"learning_rate": 9.898134281706337e-05,
"loss": 1.0472412109375,
"step": 69
},
{
"epoch": 1.1864406779661016,
"grad_norm": 0.03440655395388603,
"learning_rate": 9.892724066883253e-05,
"loss": 1.0615234375,
"step": 70
},
{
"epoch": 1.2033898305084745,
"grad_norm": 0.03328265622258186,
"learning_rate": 9.887175604818206e-05,
"loss": 1.0166015625,
"step": 71
},
{
"epoch": 1.2203389830508475,
"grad_norm": 0.033875808119773865,
"learning_rate": 9.881489070131677e-05,
"loss": 1.01904296875,
"step": 72
},
{
"epoch": 1.2372881355932204,
"grad_norm": 0.032830610871315,
"learning_rate": 9.875664641789545e-05,
"loss": 1.02490234375,
"step": 73
},
{
"epoch": 1.2542372881355932,
"grad_norm": 0.038139570504426956,
"learning_rate": 9.869702503097466e-05,
"loss": 1.05126953125,
"step": 74
},
{
"epoch": 1.271186440677966,
"grad_norm": 0.0342501699924469,
"learning_rate": 9.86360284169509e-05,
"loss": 1.0439453125,
"step": 75
},
{
"epoch": 1.288135593220339,
"grad_norm": 0.03696940466761589,
"learning_rate": 9.857365849550177e-05,
"loss": 1.04931640625,
"step": 76
},
{
"epoch": 1.305084745762712,
"grad_norm": 0.7050172686576843,
"learning_rate": 9.85099172295253e-05,
"loss": 1.05029296875,
"step": 77
},
{
"epoch": 1.3220338983050848,
"grad_norm": 0.03767024353146553,
"learning_rate": 9.844480662507833e-05,
"loss": 1.11572265625,
"step": 78
},
{
"epoch": 1.3389830508474576,
"grad_norm": 0.03468320146203041,
"learning_rate": 9.83783287313134e-05,
"loss": 1.0009765625,
"step": 79
},
{
"epoch": 1.3559322033898304,
"grad_norm": 0.03470320999622345,
"learning_rate": 9.831048564041413e-05,
"loss": 0.973419189453125,
"step": 80
},
{
"epoch": 1.3728813559322033,
"grad_norm": 0.037841398268938065,
"learning_rate": 9.82412794875295e-05,
"loss": 1.05322265625,
"step": 81
},
{
"epoch": 1.3898305084745763,
"grad_norm": 0.04404933750629425,
"learning_rate": 9.817071245070652e-05,
"loss": 1.00927734375,
"step": 82
},
{
"epoch": 1.4067796610169492,
"grad_norm": 0.039861708879470825,
"learning_rate": 9.809878675082187e-05,
"loss": 0.96240234375,
"step": 83
},
{
"epoch": 1.423728813559322,
"grad_norm": 0.04901144281029701,
"learning_rate": 9.802550465151183e-05,
"loss": 0.99951171875,
"step": 84
},
{
"epoch": 1.4406779661016949,
"grad_norm": 0.052123475819826126,
"learning_rate": 9.795086845910114e-05,
"loss": 0.91455078125,
"step": 85
},
{
"epoch": 1.457627118644068,
"grad_norm": 0.039361584931612015,
"learning_rate": 9.787488052253033e-05,
"loss": 0.89599609375,
"step": 86
},
{
"epoch": 1.4745762711864407,
"grad_norm": 0.039839670062065125,
"learning_rate": 9.779754323328192e-05,
"loss": 0.94677734375,
"step": 87
},
{
"epoch": 1.4915254237288136,
"grad_norm": 0.04241005331277847,
"learning_rate": 9.7718859025305e-05,
"loss": 1.12451171875,
"step": 88
},
{
"epoch": 1.5084745762711864,
"grad_norm": 0.10701971501111984,
"learning_rate": 9.76388303749388e-05,
"loss": 0.98974609375,
"step": 89
},
{
"epoch": 1.5254237288135593,
"grad_norm": 0.03608202189207077,
"learning_rate": 9.755745980083459e-05,
"loss": 0.97802734375,
"step": 90
},
{
"epoch": 1.542372881355932,
"grad_norm": 0.04702189564704895,
"learning_rate": 9.747474986387654e-05,
"loss": 1.0654296875,
"step": 91
},
{
"epoch": 1.559322033898305,
"grad_norm": 0.034969136118888855,
"learning_rate": 9.739070316710106e-05,
"loss": 1.00927734375,
"step": 92
},
{
"epoch": 1.576271186440678,
"grad_norm": 0.04828678071498871,
"learning_rate": 9.730532235561486e-05,
"loss": 0.9697265625,
"step": 93
},
{
"epoch": 1.5932203389830508,
"grad_norm": 0.03894111514091492,
"learning_rate": 9.72186101165118e-05,
"loss": 0.97509765625,
"step": 94
},
{
"epoch": 1.6101694915254239,
"grad_norm": 0.03653335943818092,
"learning_rate": 9.713056917878818e-05,
"loss": 0.93798828125,
"step": 95
},
{
"epoch": 1.6271186440677967,
"grad_norm": 0.035824310034513474,
"learning_rate": 9.704120231325699e-05,
"loss": 0.8662109375,
"step": 96
},
{
"epoch": 1.6440677966101696,
"grad_norm": 0.04098981246352196,
"learning_rate": 9.695051233246065e-05,
"loss": 0.916015625,
"step": 97
},
{
"epoch": 1.6610169491525424,
"grad_norm": 0.03466007113456726,
"learning_rate": 9.685850209058244e-05,
"loss": 1.06640625,
"step": 98
},
{
"epoch": 1.6779661016949152,
"grad_norm": 0.03877757117152214,
"learning_rate": 9.676517448335676e-05,
"loss": 0.96240234375,
"step": 99
},
{
"epoch": 1.694915254237288,
"grad_norm": 0.03928416594862938,
"learning_rate": 9.667053244797795e-05,
"loss": 0.955078125,
"step": 100
},
{
"epoch": 1.711864406779661,
"grad_norm": 0.034469738602638245,
"learning_rate": 9.657457896300791e-05,
"loss": 0.90087890625,
"step": 101
},
{
"epoch": 1.7288135593220337,
"grad_norm": 0.04140961915254593,
"learning_rate": 9.647731704828223e-05,
"loss": 0.99853515625,
"step": 102
},
{
"epoch": 1.7457627118644068,
"grad_norm": 0.03865489736199379,
"learning_rate": 9.637874976481529e-05,
"loss": 1.0560302734375,
"step": 103
},
{
"epoch": 1.7627118644067796,
"grad_norm": 0.038768500089645386,
"learning_rate": 9.627888021470382e-05,
"loss": 1.01806640625,
"step": 104
},
{
"epoch": 1.7796610169491527,
"grad_norm": 0.041120849549770355,
"learning_rate": 9.61777115410294e-05,
"loss": 1.02099609375,
"step": 105
},
{
"epoch": 1.7966101694915255,
"grad_norm": 0.04037615284323692,
"learning_rate": 9.607524692775936e-05,
"loss": 0.98291015625,
"step": 106
},
{
"epoch": 1.8135593220338984,
"grad_norm": 0.036412399262189865,
"learning_rate": 9.597148959964672e-05,
"loss": 0.91357421875,
"step": 107
},
{
"epoch": 1.8305084745762712,
"grad_norm": 0.03873632475733757,
"learning_rate": 9.586644282212866e-05,
"loss": 0.9697265625,
"step": 108
},
{
"epoch": 1.847457627118644,
"grad_norm": 0.0361936129629612,
"learning_rate": 9.576010990122373e-05,
"loss": 0.9326171875,
"step": 109
},
{
"epoch": 1.8644067796610169,
"grad_norm": 0.03641147539019585,
"learning_rate": 9.565249418342783e-05,
"loss": 0.9892578125,
"step": 110
},
{
"epoch": 1.8813559322033897,
"grad_norm": 0.038736745715141296,
"learning_rate": 9.554359905560886e-05,
"loss": 0.95947265625,
"step": 111
},
{
"epoch": 1.8983050847457628,
"grad_norm": 0.03311393782496452,
"learning_rate": 9.543342794490016e-05,
"loss": 0.9453125,
"step": 112
},
{
"epoch": 1.9152542372881356,
"grad_norm": 0.0367845818400383,
"learning_rate": 9.532198431859263e-05,
"loss": 0.96630859375,
"step": 113
},
{
"epoch": 1.9322033898305084,
"grad_norm": 0.037064328789711,
"learning_rate": 9.520927168402562e-05,
"loss": 0.9384765625,
"step": 114
},
{
"epoch": 1.9491525423728815,
"grad_norm": 0.03784039989113808,
"learning_rate": 9.509529358847655e-05,
"loss": 0.94921875,
"step": 115
},
{
"epoch": 1.9661016949152543,
"grad_norm": 0.039805859327316284,
"learning_rate": 9.498005361904925e-05,
"loss": 0.966796875,
"step": 116
},
{
"epoch": 1.9830508474576272,
"grad_norm": 0.037694260478019714,
"learning_rate": 9.48635554025611e-05,
"loss": 0.97216796875,
"step": 117
},
{
"epoch": 2.0,
"grad_norm": 0.04061329737305641,
"learning_rate": 9.474580260542883e-05,
"loss": 1.01318359375,
"step": 118
},
{
"epoch": 2.0,
"eval_loss": 0.95751953125,
"eval_runtime": 5.508,
"eval_samples_per_second": 0.726,
"eval_steps_per_second": 0.182,
"step": 118
},
{
"epoch": 2.016949152542373,
"grad_norm": 0.040729064494371414,
"learning_rate": 9.462679893355322e-05,
"loss": 0.990234375,
"step": 119
},
{
"epoch": 2.0338983050847457,
"grad_norm": 0.04094654694199562,
"learning_rate": 9.450654813220237e-05,
"loss": 0.98388671875,
"step": 120
},
{
"epoch": 2.0508474576271185,
"grad_norm": 0.038161035627126694,
"learning_rate": 9.438505398589392e-05,
"loss": 0.9130859375,
"step": 121
},
{
"epoch": 2.0677966101694913,
"grad_norm": 0.04925229772925377,
"learning_rate": 9.426232031827588e-05,
"loss": 0.9580078125,
"step": 122
},
{
"epoch": 2.084745762711864,
"grad_norm": 0.044360026717185974,
"learning_rate": 9.413835099200629e-05,
"loss": 0.872802734375,
"step": 123
},
{
"epoch": 2.1016949152542375,
"grad_norm": 0.05311605706810951,
"learning_rate": 9.401314990863174e-05,
"loss": 0.93695068359375,
"step": 124
},
{
"epoch": 2.1186440677966103,
"grad_norm": 0.03927534073591232,
"learning_rate": 9.388672100846447e-05,
"loss": 0.94775390625,
"step": 125
},
{
"epoch": 2.135593220338983,
"grad_norm": 0.046237342059612274,
"learning_rate": 9.375906827045841e-05,
"loss": 0.92529296875,
"step": 126
},
{
"epoch": 2.152542372881356,
"grad_norm": 0.04290531575679779,
"learning_rate": 9.363019571208397e-05,
"loss": 0.95947265625,
"step": 127
},
{
"epoch": 2.169491525423729,
"grad_norm": 0.0438193753361702,
"learning_rate": 9.350010738920161e-05,
"loss": 0.975830078125,
"step": 128
},
{
"epoch": 2.1864406779661016,
"grad_norm": 0.05039003863930702,
"learning_rate": 9.336880739593416e-05,
"loss": 0.99267578125,
"step": 129
},
{
"epoch": 2.2033898305084745,
"grad_norm": 0.040518902242183685,
"learning_rate": 9.323629986453793e-05,
"loss": 0.951171875,
"step": 130
},
{
"epoch": 2.2203389830508473,
"grad_norm": 0.04892604798078537,
"learning_rate": 9.310258896527278e-05,
"loss": 0.95166015625,
"step": 131
},
{
"epoch": 2.23728813559322,
"grad_norm": 0.04225604236125946,
"learning_rate": 9.296767890627082e-05,
"loss": 0.9609375,
"step": 132
},
{
"epoch": 2.2542372881355934,
"grad_norm": 0.04745939001441002,
"learning_rate": 9.283157393340386e-05,
"loss": 0.9765625,
"step": 133
},
{
"epoch": 2.2711864406779663,
"grad_norm": 0.040118880569934845,
"learning_rate": 9.269427833014999e-05,
"loss": 0.9873046875,
"step": 134
},
{
"epoch": 2.288135593220339,
"grad_norm": 0.05377362295985222,
"learning_rate": 9.255579641745862e-05,
"loss": 0.9814453125,
"step": 135
},
{
"epoch": 2.305084745762712,
"grad_norm": 0.04429630562663078,
"learning_rate": 9.241613255361455e-05,
"loss": 0.9951171875,
"step": 136
},
{
"epoch": 2.3220338983050848,
"grad_norm": 0.0494614876806736,
"learning_rate": 9.227529113410073e-05,
"loss": 1.05126953125,
"step": 137
},
{
"epoch": 2.3389830508474576,
"grad_norm": 0.04615238308906555,
"learning_rate": 9.213327659146012e-05,
"loss": 0.93798828125,
"step": 138
},
{
"epoch": 2.3559322033898304,
"grad_norm": 0.0424368791282177,
"learning_rate": 9.199009339515595e-05,
"loss": 0.9136962890625,
"step": 139
},
{
"epoch": 2.3728813559322033,
"grad_norm": 0.04381367564201355,
"learning_rate": 9.184574605143119e-05,
"loss": 0.98828125,
"step": 140
},
{
"epoch": 2.389830508474576,
"grad_norm": 0.04783251881599426,
"learning_rate": 9.17002391031667e-05,
"loss": 0.94580078125,
"step": 141
},
{
"epoch": 2.406779661016949,
"grad_norm": 0.04870608448982239,
"learning_rate": 9.155357712973834e-05,
"loss": 0.90087890625,
"step": 142
},
{
"epoch": 2.423728813559322,
"grad_norm": 0.04964032396674156,
"learning_rate": 9.140576474687264e-05,
"loss": 0.93798828125,
"step": 143
},
{
"epoch": 2.440677966101695,
"grad_norm": 0.03433435782790184,
"learning_rate": 9.125680660650177e-05,
"loss": 0.8603515625,
"step": 144
},
{
"epoch": 2.457627118644068,
"grad_norm": 0.043996892869472504,
"learning_rate": 9.110670739661702e-05,
"loss": 0.84375,
"step": 145
},
{
"epoch": 2.4745762711864407,
"grad_norm": 0.037297796458005905,
"learning_rate": 9.095547184112121e-05,
"loss": 0.89208984375,
"step": 146
},
{
"epoch": 2.4915254237288136,
"grad_norm": 0.07118714600801468,
"learning_rate": 9.080310469968015e-05,
"loss": 1.0693359375,
"step": 147
},
{
"epoch": 2.5084745762711864,
"grad_norm": 0.042396120727062225,
"learning_rate": 9.064961076757274e-05,
"loss": 0.93017578125,
"step": 148
},
{
"epoch": 2.5254237288135593,
"grad_norm": 0.037512559443712234,
"learning_rate": 9.049499487554011e-05,
"loss": 0.919921875,
"step": 149
},
{
"epoch": 2.542372881355932,
"grad_norm": 0.04254623129963875,
"learning_rate": 9.033926188963352e-05,
"loss": 1.0078125,
"step": 150
},
{
"epoch": 2.559322033898305,
"grad_norm": 0.03967670351266861,
"learning_rate": 9.018241671106134e-05,
"loss": 0.95458984375,
"step": 151
},
{
"epoch": 2.576271186440678,
"grad_norm": 0.04079322889447212,
"learning_rate": 9.002446427603467e-05,
"loss": 0.9150390625,
"step": 152
},
{
"epoch": 2.593220338983051,
"grad_norm": 0.039984993636608124,
"learning_rate": 8.986540955561205e-05,
"loss": 0.91796875,
"step": 153
},
{
"epoch": 2.610169491525424,
"grad_norm": 0.0440865121781826,
"learning_rate": 8.9705257555543e-05,
"loss": 0.88720703125,
"step": 154
},
{
"epoch": 2.6271186440677967,
"grad_norm": 0.038405925035476685,
"learning_rate": 8.954401331611051e-05,
"loss": 0.81982421875,
"step": 155
},
{
"epoch": 2.6440677966101696,
"grad_norm": 0.04278844967484474,
"learning_rate": 8.938168191197234e-05,
"loss": 0.86181640625,
"step": 156
},
{
"epoch": 2.6610169491525424,
"grad_norm": 0.044962674379348755,
"learning_rate": 8.921826845200139e-05,
"loss": 1.01025390625,
"step": 157
},
{
"epoch": 2.6779661016949152,
"grad_norm": 0.04641561955213547,
"learning_rate": 8.90537780791249e-05,
"loss": 0.9130859375,
"step": 158
},
{
"epoch": 2.694915254237288,
"grad_norm": 0.04224422946572304,
"learning_rate": 8.88882159701625e-05,
"loss": 0.900390625,
"step": 159
},
{
"epoch": 2.711864406779661,
"grad_norm": 0.04439367353916168,
"learning_rate": 8.872158733566343e-05,
"loss": 0.849609375,
"step": 160
},
{
"epoch": 2.7288135593220337,
"grad_norm": 0.04348195716738701,
"learning_rate": 8.855389741974244e-05,
"loss": 0.94287109375,
"step": 161
},
{
"epoch": 2.7457627118644066,
"grad_norm": 0.043041396886110306,
"learning_rate": 8.838515149991487e-05,
"loss": 1.002197265625,
"step": 162
},
{
"epoch": 2.7627118644067794,
"grad_norm": 0.04511250555515289,
"learning_rate": 8.821535488693033e-05,
"loss": 0.96484375,
"step": 163
},
{
"epoch": 2.7796610169491527,
"grad_norm": 0.04521727189421654,
"learning_rate": 8.804451292460585e-05,
"loss": 0.96502685546875,
"step": 164
},
{
"epoch": 2.7966101694915255,
"grad_norm": 0.04706377536058426,
"learning_rate": 8.787263098965748e-05,
"loss": 0.93115234375,
"step": 165
},
{
"epoch": 2.8135593220338984,
"grad_norm": 0.047738347202539444,
"learning_rate": 8.769971449153122e-05,
"loss": 0.86328125,
"step": 166
},
{
"epoch": 2.830508474576271,
"grad_norm": 0.03867924585938454,
"learning_rate": 8.752576887223263e-05,
"loss": 0.9169921875,
"step": 167
},
{
"epoch": 2.847457627118644,
"grad_norm": 0.04564524441957474,
"learning_rate": 8.735079960615567e-05,
"loss": 0.8857421875,
"step": 168
},
{
"epoch": 2.864406779661017,
"grad_norm": 0.04401874914765358,
"learning_rate": 8.71748121999104e-05,
"loss": 0.939453125,
"step": 169
},
{
"epoch": 2.8813559322033897,
"grad_norm": 0.04350343719124794,
"learning_rate": 8.699781219214963e-05,
"loss": 0.90673828125,
"step": 170
},
{
"epoch": 2.898305084745763,
"grad_norm": 0.04142392426729202,
"learning_rate": 8.681980515339464e-05,
"loss": 0.9013671875,
"step": 171
},
{
"epoch": 2.915254237288136,
"grad_norm": 0.041485656052827835,
"learning_rate": 8.664079668585987e-05,
"loss": 0.91650390625,
"step": 172
},
{
"epoch": 2.9322033898305087,
"grad_norm": 0.040332257747650146,
"learning_rate": 8.646079242327658e-05,
"loss": 0.8916015625,
"step": 173
},
{
"epoch": 2.9491525423728815,
"grad_norm": 0.041349105536937714,
"learning_rate": 8.62797980307156e-05,
"loss": 0.90087890625,
"step": 174
},
{
"epoch": 2.9661016949152543,
"grad_norm": 0.04244816675782204,
"learning_rate": 8.609781920440891e-05,
"loss": 0.916015625,
"step": 175
},
{
"epoch": 2.983050847457627,
"grad_norm": 0.04164769873023033,
"learning_rate": 8.591486167157058e-05,
"loss": 0.92529296875,
"step": 176
},
{
"epoch": 3.0,
"grad_norm": 0.04835357144474983,
"learning_rate": 8.573093119021632e-05,
"loss": 0.9599609375,
"step": 177
},
{
"epoch": 3.016949152542373,
"grad_norm": 0.041954249143600464,
"learning_rate": 8.554603354898238e-05,
"loss": 0.9375,
"step": 178
},
{
"epoch": 3.0338983050847457,
"grad_norm": 0.04553646966814995,
"learning_rate": 8.536017456694336e-05,
"loss": 0.93603515625,
"step": 179
},
{
"epoch": 3.0508474576271185,
"grad_norm": 0.042889662086963654,
"learning_rate": 8.517336009342898e-05,
"loss": 0.869140625,
"step": 180
},
{
"epoch": 3.0677966101694913,
"grad_norm": 0.05051923170685768,
"learning_rate": 8.498559600784018e-05,
"loss": 0.908203125,
"step": 181
},
{
"epoch": 3.084745762711864,
"grad_norm": 0.04766980558633804,
"learning_rate": 8.479688821946386e-05,
"loss": 0.8223876953125,
"step": 182
},
{
"epoch": 3.1016949152542375,
"grad_norm": 0.055603887885808945,
"learning_rate": 8.460724266728707e-05,
"loss": 0.8878173828125,
"step": 183
},
{
"epoch": 3.1186440677966103,
"grad_norm": 0.047310296446084976,
"learning_rate": 8.441666531981003e-05,
"loss": 0.90234375,
"step": 184
},
{
"epoch": 3.135593220338983,
"grad_norm": 0.047502048313617706,
"learning_rate": 8.422516217485826e-05,
"loss": 0.87744140625,
"step": 185
},
{
"epoch": 3.152542372881356,
"grad_norm": 0.04852184280753136,
"learning_rate": 8.403273925939396e-05,
"loss": 0.912109375,
"step": 186
},
{
"epoch": 3.169491525423729,
"grad_norm": 0.048945099115371704,
"learning_rate": 8.383940262932607e-05,
"loss": 0.9256591796875,
"step": 187
},
{
"epoch": 3.1864406779661016,
"grad_norm": 0.058072466403245926,
"learning_rate": 8.364515836932003e-05,
"loss": 0.94580078125,
"step": 188
},
{
"epoch": 3.2033898305084745,
"grad_norm": 0.04884786531329155,
"learning_rate": 8.345001259260594e-05,
"loss": 0.90478515625,
"step": 189
},
{
"epoch": 3.2203389830508473,
"grad_norm": 0.050656598061323166,
"learning_rate": 8.325397144078636e-05,
"loss": 0.90380859375,
"step": 190
},
{
"epoch": 3.23728813559322,
"grad_norm": 0.04706762731075287,
"learning_rate": 8.305704108364301e-05,
"loss": 0.916015625,
"step": 191
},
{
"epoch": 3.2542372881355934,
"grad_norm": 0.04916441813111305,
"learning_rate": 8.285922771894254e-05,
"loss": 0.9296875,
"step": 192
},
{
"epoch": 3.2711864406779663,
"grad_norm": 0.04372318834066391,
"learning_rate": 8.266053757224148e-05,
"loss": 0.94677734375,
"step": 193
},
{
"epoch": 3.288135593220339,
"grad_norm": 0.04999133571982384,
"learning_rate": 8.246097689669037e-05,
"loss": 0.9365234375,
"step": 194
},
{
"epoch": 3.305084745762712,
"grad_norm": 0.05068371817469597,
"learning_rate": 8.226055197283689e-05,
"loss": 0.94970703125,
"step": 195
},
{
"epoch": 3.3220338983050848,
"grad_norm": 0.05253295972943306,
"learning_rate": 8.205926910842826e-05,
"loss": 1.00146484375,
"step": 196
},
{
"epoch": 3.3389830508474576,
"grad_norm": 0.04348459094762802,
"learning_rate": 8.185713463821267e-05,
"loss": 0.8916015625,
"step": 197
},
{
"epoch": 3.3559322033898304,
"grad_norm": 0.04552246257662773,
"learning_rate": 8.165415492373993e-05,
"loss": 0.8685150146484375,
"step": 198
},
{
"epoch": 3.3728813559322033,
"grad_norm": 0.04435073584318161,
"learning_rate": 8.14503363531613e-05,
"loss": 0.943115234375,
"step": 199
},
{
"epoch": 3.389830508474576,
"grad_norm": 0.05203387886285782,
"learning_rate": 8.124568534102837e-05,
"loss": 0.89990234375,
"step": 200
},
{
"epoch": 3.406779661016949,
"grad_norm": 0.054702479392290115,
"learning_rate": 8.104020832809127e-05,
"loss": 0.85693359375,
"step": 201
},
{
"epoch": 3.423728813559322,
"grad_norm": 0.050307512283325195,
"learning_rate": 8.083391178109586e-05,
"loss": 0.893310546875,
"step": 202
},
{
"epoch": 3.440677966101695,
"grad_norm": 0.04558728262782097,
"learning_rate": 8.062680219258034e-05,
"loss": 0.824951171875,
"step": 203
},
{
"epoch": 3.457627118644068,
"grad_norm": 0.046926796436309814,
"learning_rate": 8.041888608067079e-05,
"loss": 0.806640625,
"step": 204
},
{
"epoch": 3.4745762711864407,
"grad_norm": 0.043580397963523865,
"learning_rate": 8.021016998887613e-05,
"loss": 0.8544921875,
"step": 205
},
{
"epoch": 3.4915254237288136,
"grad_norm": 0.04389704763889313,
"learning_rate": 8.000066048588211e-05,
"loss": 1.0244140625,
"step": 206
},
{
"epoch": 3.5084745762711864,
"grad_norm": 0.04382007569074631,
"learning_rate": 7.979036416534463e-05,
"loss": 0.888671875,
"step": 207
},
{
"epoch": 3.5254237288135593,
"grad_norm": 0.04426548257470131,
"learning_rate": 7.95792876456822e-05,
"loss": 0.87841796875,
"step": 208
},
{
"epoch": 3.542372881355932,
"grad_norm": 0.04492391273379326,
"learning_rate": 7.936743756986767e-05,
"loss": 0.962890625,
"step": 209
},
{
"epoch": 3.559322033898305,
"grad_norm": 0.04495970532298088,
"learning_rate": 7.915482060521915e-05,
"loss": 0.91162109375,
"step": 210
},
{
"epoch": 3.576271186440678,
"grad_norm": 0.04441111534833908,
"learning_rate": 7.894144344319014e-05,
"loss": 0.873046875,
"step": 211
},
{
"epoch": 3.593220338983051,
"grad_norm": 0.04317812994122505,
"learning_rate": 7.872731279915905e-05,
"loss": 0.876953125,
"step": 212
},
{
"epoch": 3.610169491525424,
"grad_norm": 0.0498715378344059,
"learning_rate": 7.85124354122177e-05,
"loss": 0.8447265625,
"step": 213
},
{
"epoch": 3.6271186440677967,
"grad_norm": 0.041921183466911316,
"learning_rate": 7.829681804495934e-05,
"loss": 0.7841796875,
"step": 214
},
{
"epoch": 3.6440677966101696,
"grad_norm": 0.04422099143266678,
"learning_rate": 7.808046748326579e-05,
"loss": 0.822265625,
"step": 215
},
{
"epoch": 3.6610169491525424,
"grad_norm": 0.046850237995386124,
"learning_rate": 7.786339053609383e-05,
"loss": 0.96630859375,
"step": 216
},
{
"epoch": 3.6779661016949152,
"grad_norm": 0.047524094581604004,
"learning_rate": 7.764559403526101e-05,
"loss": 0.87255859375,
"step": 217
},
{
"epoch": 3.694915254237288,
"grad_norm": 0.043090976774692535,
"learning_rate": 7.742708483523053e-05,
"loss": 0.8564453125,
"step": 218
},
{
"epoch": 3.711864406779661,
"grad_norm": 0.05316559225320816,
"learning_rate": 7.720786981289561e-05,
"loss": 0.81103515625,
"step": 219
},
{
"epoch": 3.7288135593220337,
"grad_norm": 0.043358005583286285,
"learning_rate": 7.698795586736298e-05,
"loss": 0.8984375,
"step": 220
},
{
"epoch": 3.7457627118644066,
"grad_norm": 0.049701083451509476,
"learning_rate": 7.67673499197358e-05,
"loss": 0.961181640625,
"step": 221
},
{
"epoch": 3.7627118644067794,
"grad_norm": 0.04763001948595047,
"learning_rate": 7.654605891289584e-05,
"loss": 0.921875,
"step": 222
},
{
"epoch": 3.7796610169491527,
"grad_norm": 0.05051397159695625,
"learning_rate": 7.632408981128494e-05,
"loss": 0.9193115234375,
"step": 223
},
{
"epoch": 3.7966101694915255,
"grad_norm": 0.051450058817863464,
"learning_rate": 7.61014496006859e-05,
"loss": 0.89013671875,
"step": 224
},
{
"epoch": 3.8135593220338984,
"grad_norm": 0.04962727427482605,
"learning_rate": 7.587814528800253e-05,
"loss": 0.82568359375,
"step": 225
},
{
"epoch": 3.830508474576271,
"grad_norm": 0.04543929919600487,
"learning_rate": 7.56541839010392e-05,
"loss": 0.87744140625,
"step": 226
},
{
"epoch": 3.847457627118644,
"grad_norm": 0.04727281257510185,
"learning_rate": 7.542957248827961e-05,
"loss": 0.8466796875,
"step": 227
},
{
"epoch": 3.864406779661017,
"grad_norm": 0.04577086493372917,
"learning_rate": 7.5204318118665e-05,
"loss": 0.9033203125,
"step": 228
},
{
"epoch": 3.8813559322033897,
"grad_norm": 0.04693583771586418,
"learning_rate": 7.49784278813717e-05,
"loss": 0.867919921875,
"step": 229
},
{
"epoch": 3.898305084745763,
"grad_norm": 0.05010557174682617,
"learning_rate": 7.475190888558792e-05,
"loss": 0.86767578125,
"step": 230
},
{
"epoch": 3.915254237288136,
"grad_norm": 0.05884314328432083,
"learning_rate": 7.452476826029011e-05,
"loss": 0.8779296875,
"step": 231
},
{
"epoch": 3.9322033898305087,
"grad_norm": 0.04666309058666229,
"learning_rate": 7.42970131540186e-05,
"loss": 0.8544921875,
"step": 232
},
{
"epoch": 3.9491525423728815,
"grad_norm": 0.05074760317802429,
"learning_rate": 7.406865073465249e-05,
"loss": 0.86279296875,
"step": 233
},
{
"epoch": 3.9661016949152543,
"grad_norm": 0.04701051115989685,
"learning_rate": 7.383968818918426e-05,
"loss": 0.8779296875,
"step": 234
},
{
"epoch": 3.983050847457627,
"grad_norm": 0.050385430455207825,
"learning_rate": 7.361013272349343e-05,
"loss": 0.88671875,
"step": 235
},
{
"epoch": 4.0,
"grad_norm": 0.049906566739082336,
"learning_rate": 7.337999156211984e-05,
"loss": 0.91455078125,
"step": 236
},
{
"epoch": 4.0,
"eval_loss": 0.91943359375,
"eval_runtime": 5.4908,
"eval_samples_per_second": 0.728,
"eval_steps_per_second": 0.182,
"step": 236
},
{
"epoch": 4.016949152542373,
"grad_norm": 0.052867308259010315,
"learning_rate": 7.314927194803623e-05,
"loss": 0.89404296875,
"step": 237
},
{
"epoch": 4.033898305084746,
"grad_norm": 0.05265556648373604,
"learning_rate": 7.29179811424204e-05,
"loss": 0.8974609375,
"step": 238
},
{
"epoch": 4.0508474576271185,
"grad_norm": 0.05539415776729584,
"learning_rate": 7.268612642442657e-05,
"loss": 0.8349609375,
"step": 239
},
{
"epoch": 4.067796610169491,
"grad_norm": 0.06492127478122711,
"learning_rate": 7.245371509095634e-05,
"loss": 0.8671875,
"step": 240
},
{
"epoch": 4.084745762711864,
"grad_norm": 0.06641252338886261,
"learning_rate": 7.222075445642904e-05,
"loss": 0.7828369140625,
"step": 241
},
{
"epoch": 4.101694915254237,
"grad_norm": 0.0656130462884903,
"learning_rate": 7.198725185255156e-05,
"loss": 0.84295654296875,
"step": 242
},
{
"epoch": 4.11864406779661,
"grad_norm": 0.0834832638502121,
"learning_rate": 7.175321462808754e-05,
"loss": 0.86328125,
"step": 243
},
{
"epoch": 4.135593220338983,
"grad_norm": 0.060139164328575134,
"learning_rate": 7.151865014862614e-05,
"loss": 0.84033203125,
"step": 244
},
{
"epoch": 4.1525423728813555,
"grad_norm": 0.061582718044519424,
"learning_rate": 7.128356579635024e-05,
"loss": 0.87158203125,
"step": 245
},
{
"epoch": 4.169491525423728,
"grad_norm": 0.05848122760653496,
"learning_rate": 7.104796896980409e-05,
"loss": 0.8809814453125,
"step": 246
},
{
"epoch": 4.186440677966102,
"grad_norm": 0.0693947970867157,
"learning_rate": 7.081186708366043e-05,
"loss": 0.90771484375,
"step": 247
},
{
"epoch": 4.203389830508475,
"grad_norm": 0.056311894208192825,
"learning_rate": 7.057526756848719e-05,
"loss": 0.8662109375,
"step": 248
},
{
"epoch": 4.220338983050848,
"grad_norm": 0.05968115106225014,
"learning_rate": 7.033817787051362e-05,
"loss": 0.86767578125,
"step": 249
},
{
"epoch": 4.237288135593221,
"grad_norm": 0.05823725834488869,
"learning_rate": 7.010060545139595e-05,
"loss": 0.8798828125,
"step": 250
},
{
"epoch": 4.254237288135593,
"grad_norm": 0.05956561490893364,
"learning_rate": 6.986255778798253e-05,
"loss": 0.89013671875,
"step": 251
},
{
"epoch": 4.271186440677966,
"grad_norm": 0.052097056061029434,
"learning_rate": 6.962404237207853e-05,
"loss": 0.91259765625,
"step": 252
},
{
"epoch": 4.288135593220339,
"grad_norm": 0.05958912521600723,
"learning_rate": 6.938506671021018e-05,
"loss": 0.8955078125,
"step": 253
},
{
"epoch": 4.305084745762712,
"grad_norm": 0.06402496248483658,
"learning_rate": 6.91456383233885e-05,
"loss": 0.91259765625,
"step": 254
},
{
"epoch": 4.322033898305085,
"grad_norm": 0.05686519294977188,
"learning_rate": 6.890576474687263e-05,
"loss": 0.960693359375,
"step": 255
},
{
"epoch": 4.338983050847458,
"grad_norm": 0.06652466207742691,
"learning_rate": 6.866545352993267e-05,
"loss": 0.857421875,
"step": 256
},
{
"epoch": 4.3559322033898304,
"grad_norm": 0.05327349156141281,
"learning_rate": 6.842471223561202e-05,
"loss": 0.8302459716796875,
"step": 257
},
{
"epoch": 4.372881355932203,
"grad_norm": 0.05054203048348427,
"learning_rate": 6.818354844048951e-05,
"loss": 0.905517578125,
"step": 258
},
{
"epoch": 4.389830508474576,
"grad_norm": 0.06467215716838837,
"learning_rate": 6.794196973444078e-05,
"loss": 0.8603515625,
"step": 259
},
{
"epoch": 4.406779661016949,
"grad_norm": 0.056637249886989594,
"learning_rate": 6.769998372039954e-05,
"loss": 0.8203125,
"step": 260
},
{
"epoch": 4.423728813559322,
"grad_norm": 0.0528288371860981,
"learning_rate": 6.745759801411822e-05,
"loss": 0.85498046875,
"step": 261
},
{
"epoch": 4.440677966101695,
"grad_norm": 0.04762440174818039,
"learning_rate": 6.721482024392835e-05,
"loss": 0.794189453125,
"step": 262
},
{
"epoch": 4.4576271186440675,
"grad_norm": 0.047663457691669464,
"learning_rate": 6.697165805050038e-05,
"loss": 0.775390625,
"step": 263
},
{
"epoch": 4.47457627118644,
"grad_norm": 0.047147005796432495,
"learning_rate": 6.672811908660335e-05,
"loss": 0.81982421875,
"step": 264
},
{
"epoch": 4.491525423728813,
"grad_norm": 0.05504373088479042,
"learning_rate": 6.648421101686392e-05,
"loss": 0.9873046875,
"step": 265
},
{
"epoch": 4.508474576271187,
"grad_norm": 0.05054924264550209,
"learning_rate": 6.623994151752521e-05,
"loss": 0.8515625,
"step": 266
},
{
"epoch": 4.52542372881356,
"grad_norm": 0.04735773429274559,
"learning_rate": 6.599531827620523e-05,
"loss": 0.841796875,
"step": 267
},
{
"epoch": 4.5423728813559325,
"grad_norm": 0.05020519345998764,
"learning_rate": 6.57503489916549e-05,
"loss": 0.9267578125,
"step": 268
},
{
"epoch": 4.559322033898305,
"grad_norm": 0.05061081051826477,
"learning_rate": 6.550504137351576e-05,
"loss": 0.872314453125,
"step": 269
},
{
"epoch": 4.576271186440678,
"grad_norm": 0.04998607560992241,
"learning_rate": 6.525940314207732e-05,
"loss": 0.83740234375,
"step": 270
},
{
"epoch": 4.593220338983051,
"grad_norm": 0.05324844643473625,
"learning_rate": 6.501344202803414e-05,
"loss": 0.841796875,
"step": 271
},
{
"epoch": 4.610169491525424,
"grad_norm": 0.05520491302013397,
"learning_rate": 6.476716577224253e-05,
"loss": 0.80712890625,
"step": 272
},
{
"epoch": 4.627118644067797,
"grad_norm": 0.0474056638777256,
"learning_rate": 6.452058212547684e-05,
"loss": 0.755859375,
"step": 273
},
{
"epoch": 4.6440677966101696,
"grad_norm": 0.051384087651968,
"learning_rate": 6.427369884818559e-05,
"loss": 0.7900390625,
"step": 274
},
{
"epoch": 4.661016949152542,
"grad_norm": 0.05972765386104584,
"learning_rate": 6.402652371024727e-05,
"loss": 0.92626953125,
"step": 275
},
{
"epoch": 4.677966101694915,
"grad_norm": 0.052976883947849274,
"learning_rate": 6.377906449072578e-05,
"loss": 0.83837890625,
"step": 276
},
{
"epoch": 4.694915254237288,
"grad_norm": 0.05546817556023598,
"learning_rate": 6.353132897762554e-05,
"loss": 0.82177734375,
"step": 277
},
{
"epoch": 4.711864406779661,
"grad_norm": 0.05132537707686424,
"learning_rate": 6.328332496764649e-05,
"loss": 0.7802734375,
"step": 278
},
{
"epoch": 4.728813559322034,
"grad_norm": 0.05302242189645767,
"learning_rate": 6.303506026593865e-05,
"loss": 0.865234375,
"step": 279
},
{
"epoch": 4.745762711864407,
"grad_norm": 0.05628819018602371,
"learning_rate": 6.278654268585652e-05,
"loss": 0.92626953125,
"step": 280
},
{
"epoch": 4.762711864406779,
"grad_norm": 0.05794723704457283,
"learning_rate": 6.253778004871315e-05,
"loss": 0.885498046875,
"step": 281
},
{
"epoch": 4.779661016949152,
"grad_norm": 0.057242877781391144,
"learning_rate": 6.228878018353394e-05,
"loss": 0.87762451171875,
"step": 282
},
{
"epoch": 4.796610169491525,
"grad_norm": 0.05840564891695976,
"learning_rate": 6.203955092681039e-05,
"loss": 0.85400390625,
"step": 283
},
{
"epoch": 4.813559322033898,
"grad_norm": 0.05736774206161499,
"learning_rate": 6.179010012225332e-05,
"loss": 0.79052734375,
"step": 284
},
{
"epoch": 4.830508474576272,
"grad_norm": 0.06159093603491783,
"learning_rate": 6.154043562054607e-05,
"loss": 0.84326171875,
"step": 285
},
{
"epoch": 4.847457627118644,
"grad_norm": 0.05166851356625557,
"learning_rate": 6.129056527909747e-05,
"loss": 0.81103515625,
"step": 286
},
{
"epoch": 4.864406779661017,
"grad_norm": 0.05598374083638191,
"learning_rate": 6.10404969617945e-05,
"loss": 0.86767578125,
"step": 287
},
{
"epoch": 4.88135593220339,
"grad_norm": 0.05652940273284912,
"learning_rate": 6.0790238538754774e-05,
"loss": 0.834716796875,
"step": 288
},
{
"epoch": 4.898305084745763,
"grad_norm": 0.052309319376945496,
"learning_rate": 6.053979788607893e-05,
"loss": 0.8388671875,
"step": 289
},
{
"epoch": 4.915254237288136,
"grad_norm": 0.058902446180582047,
"learning_rate": 6.0289182885602704e-05,
"loss": 0.84130859375,
"step": 290
},
{
"epoch": 4.932203389830509,
"grad_norm": 0.052867427468299866,
"learning_rate": 6.003840142464886e-05,
"loss": 0.822265625,
"step": 291
},
{
"epoch": 4.9491525423728815,
"grad_norm": 0.05653911456465721,
"learning_rate": 5.978746139577901e-05,
"loss": 0.828125,
"step": 292
},
{
"epoch": 4.966101694915254,
"grad_norm": 0.0543186217546463,
"learning_rate": 5.9536370696545204e-05,
"loss": 0.84228515625,
"step": 293
},
{
"epoch": 4.983050847457627,
"grad_norm": 0.059324320405721664,
"learning_rate": 5.928513722924135e-05,
"loss": 0.85107421875,
"step": 294
},
{
"epoch": 5.0,
"grad_norm": 0.06161380186676979,
"learning_rate": 5.903376890065452e-05,
"loss": 0.87255859375,
"step": 295
},
{
"epoch": 5.016949152542373,
"grad_norm": 0.054617948830127716,
"learning_rate": 5.8782273621816144e-05,
"loss": 0.85498046875,
"step": 296
},
{
"epoch": 5.033898305084746,
"grad_norm": 0.06646206974983215,
"learning_rate": 5.8530659307753036e-05,
"loss": 0.86376953125,
"step": 297
},
{
"epoch": 5.0508474576271185,
"grad_norm": 0.05474330112338066,
"learning_rate": 5.8278933877238216e-05,
"loss": 0.80224609375,
"step": 298
},
{
"epoch": 5.067796610169491,
"grad_norm": 0.0639771893620491,
"learning_rate": 5.802710525254179e-05,
"loss": 0.83251953125,
"step": 299
},
{
"epoch": 5.084745762711864,
"grad_norm": 0.06556396186351776,
"learning_rate": 5.7775181359181574e-05,
"loss": 0.7459716796875,
"step": 300
},
{
"epoch": 5.101694915254237,
"grad_norm": 0.07050123065710068,
"learning_rate": 5.752317012567363e-05,
"loss": 0.80133056640625,
"step": 301
},
{
"epoch": 5.11864406779661,
"grad_norm": 0.06670650839805603,
"learning_rate": 5.7271079483282844e-05,
"loss": 0.828125,
"step": 302
},
{
"epoch": 5.135593220338983,
"grad_norm": 0.07030098140239716,
"learning_rate": 5.7018917365773184e-05,
"loss": 0.80712890625,
"step": 303
},
{
"epoch": 5.1525423728813555,
"grad_norm": 0.07091601192951202,
"learning_rate": 5.6766691709158096e-05,
"loss": 0.8369140625,
"step": 304
},
{
"epoch": 5.169491525423728,
"grad_norm": 0.0636327862739563,
"learning_rate": 5.651441045145074e-05,
"loss": 0.8394775390625,
"step": 305
},
{
"epoch": 5.186440677966102,
"grad_norm": 0.06778645515441895,
"learning_rate": 5.626208153241411e-05,
"loss": 0.86865234375,
"step": 306
},
{
"epoch": 5.203389830508475,
"grad_norm": 0.06238247826695442,
"learning_rate": 5.600971289331123e-05,
"loss": 0.830322265625,
"step": 307
},
{
"epoch": 5.220338983050848,
"grad_norm": 0.05869225785136223,
"learning_rate": 5.5757312476655155e-05,
"loss": 0.8291015625,
"step": 308
},
{
"epoch": 5.237288135593221,
"grad_norm": 0.058446209877729416,
"learning_rate": 5.5504888225959074e-05,
"loss": 0.8447265625,
"step": 309
},
{
"epoch": 5.254237288135593,
"grad_norm": 0.06622830778360367,
"learning_rate": 5.525244808548624e-05,
"loss": 0.85498046875,
"step": 310
},
{
"epoch": 5.271186440677966,
"grad_norm": 0.05560489743947983,
"learning_rate": 5.500000000000001e-05,
"loss": 0.8779296875,
"step": 311
},
{
"epoch": 5.288135593220339,
"grad_norm": 0.058889489620923996,
"learning_rate": 5.4747551914513775e-05,
"loss": 0.85888671875,
"step": 312
},
{
"epoch": 5.305084745762712,
"grad_norm": 0.06262335181236267,
"learning_rate": 5.449511177404094e-05,
"loss": 0.87744140625,
"step": 313
},
{
"epoch": 5.322033898305085,
"grad_norm": 0.06117553263902664,
"learning_rate": 5.424268752334486e-05,
"loss": 0.926513671875,
"step": 314
},
{
"epoch": 5.338983050847458,
"grad_norm": 0.06420253217220306,
"learning_rate": 5.399028710668879e-05,
"loss": 0.82421875,
"step": 315
},
{
"epoch": 5.3559322033898304,
"grad_norm": 0.07287586480379105,
"learning_rate": 5.37379184675859e-05,
"loss": 0.79345703125,
"step": 316
},
{
"epoch": 5.372881355932203,
"grad_norm": 0.05852669104933739,
"learning_rate": 5.348558954854929e-05,
"loss": 0.872314453125,
"step": 317
},
{
"epoch": 5.389830508474576,
"grad_norm": 0.06779635697603226,
"learning_rate": 5.3233308290841935e-05,
"loss": 0.82666015625,
"step": 318
},
{
"epoch": 5.406779661016949,
"grad_norm": 0.05366363003849983,
"learning_rate": 5.2981082634226854e-05,
"loss": 0.7861328125,
"step": 319
},
{
"epoch": 5.423728813559322,
"grad_norm": 0.06573096662759781,
"learning_rate": 5.272892051671716e-05,
"loss": 0.8212890625,
"step": 320
},
{
"epoch": 5.440677966101695,
"grad_norm": 0.05315324291586876,
"learning_rate": 5.247682987432637e-05,
"loss": 0.7666015625,
"step": 321
},
{
"epoch": 5.4576271186440675,
"grad_norm": 0.052689943462610245,
"learning_rate": 5.222481864081843e-05,
"loss": 0.7470703125,
"step": 322
},
{
"epoch": 5.47457627118644,
"grad_norm": 0.056479569524526596,
"learning_rate": 5.197289474745822e-05,
"loss": 0.7900390625,
"step": 323
},
{
"epoch": 5.491525423728813,
"grad_norm": 0.05618058890104294,
"learning_rate": 5.1721066122761795e-05,
"loss": 0.95458984375,
"step": 324
},
{
"epoch": 5.508474576271187,
"grad_norm": 0.05618249997496605,
"learning_rate": 5.1469340692246995e-05,
"loss": 0.8203125,
"step": 325
},
{
"epoch": 5.52542372881356,
"grad_norm": 0.061622701585292816,
"learning_rate": 5.1217726378183874e-05,
"loss": 0.812744140625,
"step": 326
},
{
"epoch": 5.5423728813559325,
"grad_norm": 0.05948768928647041,
"learning_rate": 5.09662310993455e-05,
"loss": 0.89208984375,
"step": 327
},
{
"epoch": 5.559322033898305,
"grad_norm": 0.05950707197189331,
"learning_rate": 5.071486277075866e-05,
"loss": 0.839599609375,
"step": 328
},
{
"epoch": 5.576271186440678,
"grad_norm": 0.0604095384478569,
"learning_rate": 5.046362930345481e-05,
"loss": 0.80322265625,
"step": 329
},
{
"epoch": 5.593220338983051,
"grad_norm": 0.056235961616039276,
"learning_rate": 5.0212538604221e-05,
"loss": 0.810546875,
"step": 330
},
{
"epoch": 5.610169491525424,
"grad_norm": 0.06234108656644821,
"learning_rate": 4.9961598575351155e-05,
"loss": 0.7734375,
"step": 331
},
{
"epoch": 5.627118644067797,
"grad_norm": 0.05064829811453819,
"learning_rate": 4.9710817114397314e-05,
"loss": 0.72998046875,
"step": 332
},
{
"epoch": 5.6440677966101696,
"grad_norm": 0.05765705928206444,
"learning_rate": 4.946020211392108e-05,
"loss": 0.76123046875,
"step": 333
},
{
"epoch": 5.661016949152542,
"grad_norm": 0.057751040905714035,
"learning_rate": 4.920976146124523e-05,
"loss": 0.89208984375,
"step": 334
},
{
"epoch": 5.677966101694915,
"grad_norm": 0.05537796765565872,
"learning_rate": 4.895950303820552e-05,
"loss": 0.80712890625,
"step": 335
},
{
"epoch": 5.694915254237288,
"grad_norm": 0.061265718191862106,
"learning_rate": 4.870943472090255e-05,
"loss": 0.7919921875,
"step": 336
},
{
"epoch": 5.711864406779661,
"grad_norm": 0.05338221788406372,
"learning_rate": 4.845956437945395e-05,
"loss": 0.751953125,
"step": 337
},
{
"epoch": 5.728813559322034,
"grad_norm": 0.05514635890722275,
"learning_rate": 4.820989987774669e-05,
"loss": 0.83203125,
"step": 338
},
{
"epoch": 5.745762711864407,
"grad_norm": 0.06839360296726227,
"learning_rate": 4.7960449073189606e-05,
"loss": 0.8973388671875,
"step": 339
},
{
"epoch": 5.762711864406779,
"grad_norm": 0.05694277957081795,
"learning_rate": 4.771121981646606e-05,
"loss": 0.85400390625,
"step": 340
},
{
"epoch": 5.779661016949152,
"grad_norm": 0.06382687389850616,
"learning_rate": 4.7462219951286867e-05,
"loss": 0.8419189453125,
"step": 341
},
{
"epoch": 5.796610169491525,
"grad_norm": 0.06284390389919281,
"learning_rate": 4.721345731414348e-05,
"loss": 0.82421875,
"step": 342
},
{
"epoch": 5.813559322033898,
"grad_norm": 0.060006801038980484,
"learning_rate": 4.696493973406135e-05,
"loss": 0.76025390625,
"step": 343
},
{
"epoch": 5.830508474576272,
"grad_norm": 0.05854342132806778,
"learning_rate": 4.671667503235353e-05,
"loss": 0.81396484375,
"step": 344
},
{
"epoch": 5.847457627118644,
"grad_norm": 0.06410715728998184,
"learning_rate": 4.6468671022374475e-05,
"loss": 0.782470703125,
"step": 345
},
{
"epoch": 5.864406779661017,
"grad_norm": 0.05721480771899223,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.83837890625,
"step": 346
},
{
"epoch": 5.88135593220339,
"grad_norm": 0.05396363139152527,
"learning_rate": 4.597347628975272e-05,
"loss": 0.803466796875,
"step": 347
},
{
"epoch": 5.898305084745763,
"grad_norm": 0.0713089257478714,
"learning_rate": 4.572630115181442e-05,
"loss": 0.814453125,
"step": 348
},
{
"epoch": 5.915254237288136,
"grad_norm": 0.061800457537174225,
"learning_rate": 4.5479417874523175e-05,
"loss": 0.8125,
"step": 349
},
{
"epoch": 5.932203389830509,
"grad_norm": 0.0511246956884861,
"learning_rate": 4.523283422775747e-05,
"loss": 0.7919921875,
"step": 350
},
{
"epoch": 5.9491525423728815,
"grad_norm": 0.05642925575375557,
"learning_rate": 4.498655797196586e-05,
"loss": 0.79638671875,
"step": 351
},
{
"epoch": 5.966101694915254,
"grad_norm": 0.05991942435503006,
"learning_rate": 4.47405968579227e-05,
"loss": 0.8134765625,
"step": 352
},
{
"epoch": 5.983050847457627,
"grad_norm": 0.05501863732933998,
"learning_rate": 4.4494958626484276e-05,
"loss": 0.8212890625,
"step": 353
},
{
"epoch": 6.0,
"grad_norm": 0.06661185622215271,
"learning_rate": 4.4249651008345114e-05,
"loss": 0.8408203125,
"step": 354
},
{
"epoch": 6.0,
"eval_loss": 0.916015625,
"eval_runtime": 5.4877,
"eval_samples_per_second": 0.729,
"eval_steps_per_second": 0.182,
"step": 354
},
{
"epoch": 6.016949152542373,
"grad_norm": 0.06619243323802948,
"learning_rate": 4.400468172379476e-05,
"loss": 0.82177734375,
"step": 355
},
{
"epoch": 6.033898305084746,
"grad_norm": 0.06026299297809601,
"learning_rate": 4.3760058482474784e-05,
"loss": 0.83251953125,
"step": 356
},
{
"epoch": 6.0508474576271185,
"grad_norm": 0.059762123972177505,
"learning_rate": 4.3515788983136087e-05,
"loss": 0.7744140625,
"step": 357
},
{
"epoch": 6.067796610169491,
"grad_norm": 0.056844260543584824,
"learning_rate": 4.327188091339666e-05,
"loss": 0.80322265625,
"step": 358
},
{
"epoch": 6.084745762711864,
"grad_norm": 0.06329522281885147,
"learning_rate": 4.302834194949963e-05,
"loss": 0.714111328125,
"step": 359
},
{
"epoch": 6.101694915254237,
"grad_norm": 0.06707035005092621,
"learning_rate": 4.278517975607167e-05,
"loss": 0.76690673828125,
"step": 360
},
{
"epoch": 6.11864406779661,
"grad_norm": 0.05658774822950363,
"learning_rate": 4.2542401985881784e-05,
"loss": 0.7958984375,
"step": 361
},
{
"epoch": 6.135593220338983,
"grad_norm": 0.0594191700220108,
"learning_rate": 4.2300016279600475e-05,
"loss": 0.7763671875,
"step": 362
},
{
"epoch": 6.1525423728813555,
"grad_norm": 0.058310866355895996,
"learning_rate": 4.2058030265559234e-05,
"loss": 0.80322265625,
"step": 363
},
{
"epoch": 6.169491525423728,
"grad_norm": 0.06971953064203262,
"learning_rate": 4.181645155951051e-05,
"loss": 0.8028564453125,
"step": 364
},
{
"epoch": 6.186440677966102,
"grad_norm": 0.06607019156217575,
"learning_rate": 4.157528776438798e-05,
"loss": 0.8359375,
"step": 365
},
{
"epoch": 6.203389830508475,
"grad_norm": 0.05485209450125694,
"learning_rate": 4.133454647006734e-05,
"loss": 0.79833984375,
"step": 366
},
{
"epoch": 6.220338983050848,
"grad_norm": 0.06354575604200363,
"learning_rate": 4.109423525312738e-05,
"loss": 0.80224609375,
"step": 367
},
{
"epoch": 6.237288135593221,
"grad_norm": 0.06003216281533241,
"learning_rate": 4.085436167661151e-05,
"loss": 0.81640625,
"step": 368
},
{
"epoch": 6.254237288135593,
"grad_norm": 0.06671404093503952,
"learning_rate": 4.0614933289789846e-05,
"loss": 0.8251953125,
"step": 369
},
{
"epoch": 6.271186440677966,
"grad_norm": 0.05927859991788864,
"learning_rate": 4.03759576279215e-05,
"loss": 0.85302734375,
"step": 370
},
{
"epoch": 6.288135593220339,
"grad_norm": 0.0703815370798111,
"learning_rate": 4.01374422120175e-05,
"loss": 0.826904296875,
"step": 371
},
{
"epoch": 6.305084745762712,
"grad_norm": 0.06601284444332123,
"learning_rate": 3.989939454860407e-05,
"loss": 0.849609375,
"step": 372
},
{
"epoch": 6.322033898305085,
"grad_norm": 0.06685192883014679,
"learning_rate": 3.966182212948638e-05,
"loss": 0.898681640625,
"step": 373
},
{
"epoch": 6.338983050847458,
"grad_norm": 0.06317102909088135,
"learning_rate": 3.942473243151281e-05,
"loss": 0.79638671875,
"step": 374
},
{
"epoch": 6.3559322033898304,
"grad_norm": 0.06374463438987732,
"learning_rate": 3.918813291633958e-05,
"loss": 0.76348876953125,
"step": 375
},
{
"epoch": 6.372881355932203,
"grad_norm": 0.07027222961187363,
"learning_rate": 3.8952031030195926e-05,
"loss": 0.84423828125,
"step": 376
},
{
"epoch": 6.389830508474576,
"grad_norm": 0.07056409120559692,
"learning_rate": 3.871643420364977e-05,
"loss": 0.794921875,
"step": 377
},
{
"epoch": 6.406779661016949,
"grad_norm": 0.06513359397649765,
"learning_rate": 3.848134985137387e-05,
"loss": 0.7587890625,
"step": 378
},
{
"epoch": 6.423728813559322,
"grad_norm": 0.06463497877120972,
"learning_rate": 3.8246785371912475e-05,
"loss": 0.7919921875,
"step": 379
},
{
"epoch": 6.440677966101695,
"grad_norm": 0.05574393272399902,
"learning_rate": 3.8012748147448454e-05,
"loss": 0.744140625,
"step": 380
},
{
"epoch": 6.4576271186440675,
"grad_norm": 0.0599752701818943,
"learning_rate": 3.777924554357096e-05,
"loss": 0.72509765625,
"step": 381
},
{
"epoch": 6.47457627118644,
"grad_norm": 0.060120273381471634,
"learning_rate": 3.754628490904367e-05,
"loss": 0.763427734375,
"step": 382
},
{
"epoch": 6.491525423728813,
"grad_norm": 0.06007219851016998,
"learning_rate": 3.7313873575573445e-05,
"loss": 0.9267578125,
"step": 383
},
{
"epoch": 6.508474576271187,
"grad_norm": 0.061045046895742416,
"learning_rate": 3.7082018857579616e-05,
"loss": 0.79345703125,
"step": 384
},
{
"epoch": 6.52542372881356,
"grad_norm": 0.06217094510793686,
"learning_rate": 3.6850728051963777e-05,
"loss": 0.783203125,
"step": 385
},
{
"epoch": 6.5423728813559325,
"grad_norm": 0.056108418852090836,
"learning_rate": 3.662000843788018e-05,
"loss": 0.864013671875,
"step": 386
},
{
"epoch": 6.559322033898305,
"grad_norm": 0.057006124407052994,
"learning_rate": 3.6389867276506586e-05,
"loss": 0.81103515625,
"step": 387
},
{
"epoch": 6.576271186440678,
"grad_norm": 0.06159103661775589,
"learning_rate": 3.616031181081575e-05,
"loss": 0.775390625,
"step": 388
},
{
"epoch": 6.593220338983051,
"grad_norm": 0.07258477807044983,
"learning_rate": 3.593134926534751e-05,
"loss": 0.7841796875,
"step": 389
},
{
"epoch": 6.610169491525424,
"grad_norm": 0.05974142253398895,
"learning_rate": 3.5702986845981415e-05,
"loss": 0.74365234375,
"step": 390
},
{
"epoch": 6.627118644067797,
"grad_norm": 0.050698619335889816,
"learning_rate": 3.547523173970989e-05,
"loss": 0.70751953125,
"step": 391
},
{
"epoch": 6.6440677966101696,
"grad_norm": 0.06323334574699402,
"learning_rate": 3.524809111441208e-05,
"loss": 0.73828125,
"step": 392
},
{
"epoch": 6.661016949152542,
"grad_norm": 0.06629112362861633,
"learning_rate": 3.5021572118628306e-05,
"loss": 0.8623046875,
"step": 393
},
{
"epoch": 6.677966101694915,
"grad_norm": 0.0557687021791935,
"learning_rate": 3.479568188133499e-05,
"loss": 0.78173828125,
"step": 394
},
{
"epoch": 6.694915254237288,
"grad_norm": 0.057529300451278687,
"learning_rate": 3.45704275117204e-05,
"loss": 0.76513671875,
"step": 395
},
{
"epoch": 6.711864406779661,
"grad_norm": 0.05451646447181702,
"learning_rate": 3.43458160989608e-05,
"loss": 0.728515625,
"step": 396
},
{
"epoch": 6.728813559322034,
"grad_norm": 0.059587135910987854,
"learning_rate": 3.412185471199747e-05,
"loss": 0.80615234375,
"step": 397
},
{
"epoch": 6.745762711864407,
"grad_norm": 0.05543247237801552,
"learning_rate": 3.38985503993141e-05,
"loss": 0.8704833984375,
"step": 398
},
{
"epoch": 6.762711864406779,
"grad_norm": 0.0564994141459465,
"learning_rate": 3.3675910188715066e-05,
"loss": 0.8291015625,
"step": 399
},
{
"epoch": 6.779661016949152,
"grad_norm": 0.06309057027101517,
"learning_rate": 3.3453941087104186e-05,
"loss": 0.81402587890625,
"step": 400
},
{
"epoch": 6.796610169491525,
"grad_norm": 0.05882086977362633,
"learning_rate": 3.323265008026421e-05,
"loss": 0.7978515625,
"step": 401
},
{
"epoch": 6.813559322033898,
"grad_norm": 0.05446324497461319,
"learning_rate": 3.301204413263704e-05,
"loss": 0.7353515625,
"step": 402
},
{
"epoch": 6.830508474576272,
"grad_norm": 0.06252769380807877,
"learning_rate": 3.27921301871044e-05,
"loss": 0.79052734375,
"step": 403
},
{
"epoch": 6.847457627118644,
"grad_norm": 0.056348856538534164,
"learning_rate": 3.257291516476948e-05,
"loss": 0.757080078125,
"step": 404
},
{
"epoch": 6.864406779661017,
"grad_norm": 0.06016525253653526,
"learning_rate": 3.2354405964739e-05,
"loss": 0.814453125,
"step": 405
},
{
"epoch": 6.88135593220339,
"grad_norm": 0.05666210874915123,
"learning_rate": 3.213660946390619e-05,
"loss": 0.780029296875,
"step": 406
},
{
"epoch": 6.898305084745763,
"grad_norm": 0.054234426468610764,
"learning_rate": 3.191953251673423e-05,
"loss": 0.79296875,
"step": 407
},
{
"epoch": 6.915254237288136,
"grad_norm": 0.05503981187939644,
"learning_rate": 3.170318195504066e-05,
"loss": 0.787109375,
"step": 408
},
{
"epoch": 6.932203389830509,
"grad_norm": 0.05454358085989952,
"learning_rate": 3.1487564587782306e-05,
"loss": 0.76953125,
"step": 409
},
{
"epoch": 6.9491525423728815,
"grad_norm": 0.05586736649274826,
"learning_rate": 3.1272687200840945e-05,
"loss": 0.7705078125,
"step": 410
},
{
"epoch": 6.966101694915254,
"grad_norm": 0.05556340888142586,
"learning_rate": 3.105855655680986e-05,
"loss": 0.78857421875,
"step": 411
},
{
"epoch": 6.983050847457627,
"grad_norm": 0.05732768028974533,
"learning_rate": 3.0845179394780864e-05,
"loss": 0.79833984375,
"step": 412
},
{
"epoch": 7.0,
"grad_norm": 0.06650807708501816,
"learning_rate": 3.063256243013235e-05,
"loss": 0.81201171875,
"step": 413
},
{
"epoch": 7.016949152542373,
"grad_norm": 0.05540502816438675,
"learning_rate": 3.0420712354317817e-05,
"loss": 0.794189453125,
"step": 414
},
{
"epoch": 7.033898305084746,
"grad_norm": 0.058896925300359726,
"learning_rate": 3.0209635834655392e-05,
"loss": 0.806396484375,
"step": 415
},
{
"epoch": 7.0508474576271185,
"grad_norm": 0.06025364249944687,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.7529296875,
"step": 416
},
{
"epoch": 7.067796610169491,
"grad_norm": 0.05996222421526909,
"learning_rate": 2.9789830011123876e-05,
"loss": 0.77587890625,
"step": 417
},
{
"epoch": 7.084745762711864,
"grad_norm": 0.056852515786886215,
"learning_rate": 2.9581113919329218e-05,
"loss": 0.6873779296875,
"step": 418
},
{
"epoch": 7.101694915254237,
"grad_norm": 0.0645318254828453,
"learning_rate": 2.937319780741966e-05,
"loss": 0.73553466796875,
"step": 419
},
{
"epoch": 7.11864406779661,
"grad_norm": 0.060864537954330444,
"learning_rate": 2.916608821890415e-05,
"loss": 0.771484375,
"step": 420
},
{
"epoch": 7.135593220338983,
"grad_norm": 0.06149506941437721,
"learning_rate": 2.8959791671908742e-05,
"loss": 0.75244140625,
"step": 421
},
{
"epoch": 7.1525423728813555,
"grad_norm": 0.05820548161864281,
"learning_rate": 2.8754314658971648e-05,
"loss": 0.77734375,
"step": 422
},
{
"epoch": 7.169491525423728,
"grad_norm": 0.06877381354570389,
"learning_rate": 2.854966364683872e-05,
"loss": 0.7713623046875,
"step": 423
},
{
"epoch": 7.186440677966102,
"grad_norm": 0.06458062678575516,
"learning_rate": 2.8345845076260086e-05,
"loss": 0.80810546875,
"step": 424
},
{
"epoch": 7.203389830508475,
"grad_norm": 0.0636163204908371,
"learning_rate": 2.814286536178734e-05,
"loss": 0.774658203125,
"step": 425
},
{
"epoch": 7.220338983050848,
"grad_norm": 0.05926480516791344,
"learning_rate": 2.7940730891571732e-05,
"loss": 0.77734375,
"step": 426
},
{
"epoch": 7.237288135593221,
"grad_norm": 0.06068592146039009,
"learning_rate": 2.7739448027163112e-05,
"loss": 0.7939453125,
"step": 427
},
{
"epoch": 7.254237288135593,
"grad_norm": 0.0662083625793457,
"learning_rate": 2.7539023103309632e-05,
"loss": 0.796875,
"step": 428
},
{
"epoch": 7.271186440677966,
"grad_norm": 0.05475621670484543,
"learning_rate": 2.7339462427758534e-05,
"loss": 0.82861328125,
"step": 429
},
{
"epoch": 7.288135593220339,
"grad_norm": 0.06986981630325317,
"learning_rate": 2.7140772281057468e-05,
"loss": 0.799560546875,
"step": 430
},
{
"epoch": 7.305084745762712,
"grad_norm": 0.06073429808020592,
"learning_rate": 2.6942958916356998e-05,
"loss": 0.82666015625,
"step": 431
},
{
"epoch": 7.322033898305085,
"grad_norm": 0.0626358687877655,
"learning_rate": 2.6746028559213633e-05,
"loss": 0.871826171875,
"step": 432
},
{
"epoch": 7.338983050847458,
"grad_norm": 0.06005898490548134,
"learning_rate": 2.654998740739407e-05,
"loss": 0.7734375,
"step": 433
},
{
"epoch": 7.3559322033898304,
"grad_norm": 0.06252667307853699,
"learning_rate": 2.6354841630679983e-05,
"loss": 0.7394561767578125,
"step": 434
},
{
"epoch": 7.372881355932203,
"grad_norm": 0.056601013988256454,
"learning_rate": 2.6160597370673917e-05,
"loss": 0.820068359375,
"step": 435
},
{
"epoch": 7.389830508474576,
"grad_norm": 0.06190204992890358,
"learning_rate": 2.596726074060607e-05,
"loss": 0.76953125,
"step": 436
},
{
"epoch": 7.406779661016949,
"grad_norm": 0.0651886984705925,
"learning_rate": 2.577483782514174e-05,
"loss": 0.73681640625,
"step": 437
},
{
"epoch": 7.423728813559322,
"grad_norm": 0.060412950813770294,
"learning_rate": 2.5583334680189997e-05,
"loss": 0.76953125,
"step": 438
},
{
"epoch": 7.440677966101695,
"grad_norm": 0.05615295469760895,
"learning_rate": 2.5392757332712937e-05,
"loss": 0.723876953125,
"step": 439
},
{
"epoch": 7.4576271186440675,
"grad_norm": 0.06169167533516884,
"learning_rate": 2.5203111780536147e-05,
"loss": 0.70654296875,
"step": 440
},
{
"epoch": 7.47457627118644,
"grad_norm": 0.06415694952011108,
"learning_rate": 2.501440399215983e-05,
"loss": 0.744384765625,
"step": 441
},
{
"epoch": 7.491525423728813,
"grad_norm": 0.05577578395605087,
"learning_rate": 2.4826639906571026e-05,
"loss": 0.90185546875,
"step": 442
},
{
"epoch": 7.508474576271187,
"grad_norm": 0.059933505952358246,
"learning_rate": 2.4639825433056656e-05,
"loss": 0.77197265625,
"step": 443
},
{
"epoch": 7.52542372881356,
"grad_norm": 0.06843601912260056,
"learning_rate": 2.445396645101762e-05,
"loss": 0.76220703125,
"step": 444
},
{
"epoch": 7.5423728813559325,
"grad_norm": 0.06491326540708542,
"learning_rate": 2.4269068809783694e-05,
"loss": 0.843505859375,
"step": 445
},
{
"epoch": 7.559322033898305,
"grad_norm": 0.060577765107154846,
"learning_rate": 2.4085138328429427e-05,
"loss": 0.786865234375,
"step": 446
},
{
"epoch": 7.576271186440678,
"grad_norm": 0.057856082916259766,
"learning_rate": 2.3902180795591093e-05,
"loss": 0.751953125,
"step": 447
},
{
"epoch": 7.593220338983051,
"grad_norm": 0.06037498265504837,
"learning_rate": 2.3720201969284413e-05,
"loss": 0.76123046875,
"step": 448
},
{
"epoch": 7.610169491525424,
"grad_norm": 0.06280730664730072,
"learning_rate": 2.353920757672342e-05,
"loss": 0.71923828125,
"step": 449
},
{
"epoch": 7.627118644067797,
"grad_norm": 0.0567949041724205,
"learning_rate": 2.335920331414013e-05,
"loss": 0.692138671875,
"step": 450
},
{
"epoch": 7.6440677966101696,
"grad_norm": 0.06276892870664597,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.71875,
"step": 451
},
{
"epoch": 7.661016949152542,
"grad_norm": 0.05935443565249443,
"learning_rate": 2.3002187807850388e-05,
"loss": 0.83740234375,
"step": 452
},
{
"epoch": 7.677966101694915,
"grad_norm": 0.054099682718515396,
"learning_rate": 2.2825187800089613e-05,
"loss": 0.76025390625,
"step": 453
},
{
"epoch": 7.694915254237288,
"grad_norm": 0.06018521264195442,
"learning_rate": 2.2649200393844347e-05,
"loss": 0.7451171875,
"step": 454
},
{
"epoch": 7.711864406779661,
"grad_norm": 0.0544227734208107,
"learning_rate": 2.2474231127767385e-05,
"loss": 0.708984375,
"step": 455
},
{
"epoch": 7.728813559322034,
"grad_norm": 0.06054379418492317,
"learning_rate": 2.2300285508468792e-05,
"loss": 0.78466796875,
"step": 456
},
{
"epoch": 7.745762711864407,
"grad_norm": 0.05839062109589577,
"learning_rate": 2.2127369010342512e-05,
"loss": 0.8511962890625,
"step": 457
},
{
"epoch": 7.762711864406779,
"grad_norm": 0.06396183371543884,
"learning_rate": 2.195548707539416e-05,
"loss": 0.806396484375,
"step": 458
},
{
"epoch": 7.779661016949152,
"grad_norm": 0.062391553074121475,
"learning_rate": 2.1784645113069677e-05,
"loss": 0.7901611328125,
"step": 459
},
{
"epoch": 7.796610169491525,
"grad_norm": 0.05939257889986038,
"learning_rate": 2.161484850008514e-05,
"loss": 0.7802734375,
"step": 460
},
{
"epoch": 7.813559322033898,
"grad_norm": 0.05780446529388428,
"learning_rate": 2.144610258025755e-05,
"loss": 0.716552734375,
"step": 461
},
{
"epoch": 7.830508474576272,
"grad_norm": 0.057842545211315155,
"learning_rate": 2.1278412664336572e-05,
"loss": 0.77099609375,
"step": 462
},
{
"epoch": 7.847457627118644,
"grad_norm": 0.055694907903671265,
"learning_rate": 2.111178402983751e-05,
"loss": 0.73828125,
"step": 463
},
{
"epoch": 7.864406779661017,
"grad_norm": 0.057917289435863495,
"learning_rate": 2.0946221920875108e-05,
"loss": 0.79443359375,
"step": 464
},
{
"epoch": 7.88135593220339,
"grad_norm": 0.05785181000828743,
"learning_rate": 2.0781731547998614e-05,
"loss": 0.76123046875,
"step": 465
},
{
"epoch": 7.898305084745763,
"grad_norm": 0.057116687297821045,
"learning_rate": 2.0618318088027667e-05,
"loss": 0.77783203125,
"step": 466
},
{
"epoch": 7.915254237288136,
"grad_norm": 0.05883027985692024,
"learning_rate": 2.04559866838895e-05,
"loss": 0.76708984375,
"step": 467
},
{
"epoch": 7.932203389830509,
"grad_norm": 0.05454402044415474,
"learning_rate": 2.0294742444456997e-05,
"loss": 0.74951171875,
"step": 468
},
{
"epoch": 7.9491525423728815,
"grad_norm": 0.0580403134226799,
"learning_rate": 2.0134590444387963e-05,
"loss": 0.75244140625,
"step": 469
},
{
"epoch": 7.966101694915254,
"grad_norm": 0.057807523757219315,
"learning_rate": 1.9975535723965343e-05,
"loss": 0.7705078125,
"step": 470
},
{
"epoch": 7.983050847457627,
"grad_norm": 0.1497156023979187,
"learning_rate": 1.981758328893866e-05,
"loss": 0.7783203125,
"step": 471
},
{
"epoch": 8.0,
"grad_norm": 0.06572739779949188,
"learning_rate": 1.966073811036649e-05,
"loss": 0.78857421875,
"step": 472
},
{
"epoch": 8.0,
"eval_loss": 0.919189453125,
"eval_runtime": 5.4949,
"eval_samples_per_second": 0.728,
"eval_steps_per_second": 0.182,
"step": 472
},
{
"epoch": 8.016949152542374,
"grad_norm": 0.05719840154051781,
"learning_rate": 1.950500512445991e-05,
"loss": 0.7744140625,
"step": 473
},
{
"epoch": 8.033898305084746,
"grad_norm": 0.058026764541864395,
"learning_rate": 1.9350389232427274e-05,
"loss": 0.78759765625,
"step": 474
},
{
"epoch": 8.05084745762712,
"grad_norm": 0.05825353041291237,
"learning_rate": 1.919689530031986e-05,
"loss": 0.73583984375,
"step": 475
},
{
"epoch": 8.067796610169491,
"grad_norm": 0.06011303886771202,
"learning_rate": 1.9044528158878804e-05,
"loss": 0.7568359375,
"step": 476
},
{
"epoch": 8.084745762711865,
"grad_norm": 0.0637953132390976,
"learning_rate": 1.8893292603382994e-05,
"loss": 0.6666259765625,
"step": 477
},
{
"epoch": 8.101694915254237,
"grad_norm": 0.1593656837940216,
"learning_rate": 1.8743193393498227e-05,
"loss": 0.71478271484375,
"step": 478
},
{
"epoch": 8.11864406779661,
"grad_norm": 0.05885632708668709,
"learning_rate": 1.8594235253127375e-05,
"loss": 0.751953125,
"step": 479
},
{
"epoch": 8.135593220338983,
"grad_norm": 0.06632871180772781,
"learning_rate": 1.8446422870261678e-05,
"loss": 0.73388671875,
"step": 480
},
{
"epoch": 8.152542372881356,
"grad_norm": 0.06081196665763855,
"learning_rate": 1.8299760896833295e-05,
"loss": 0.75927734375,
"step": 481
},
{
"epoch": 8.169491525423728,
"grad_norm": 0.07132388651371002,
"learning_rate": 1.8154253948568818e-05,
"loss": 0.748779296875,
"step": 482
},
{
"epoch": 8.186440677966102,
"grad_norm": 0.06340758502483368,
"learning_rate": 1.800990660484406e-05,
"loss": 0.7880859375,
"step": 483
},
{
"epoch": 8.203389830508474,
"grad_norm": 0.06243523955345154,
"learning_rate": 1.786672340853987e-05,
"loss": 0.75634765625,
"step": 484
},
{
"epoch": 8.220338983050848,
"grad_norm": 0.07900620251893997,
"learning_rate": 1.7724708865899263e-05,
"loss": 0.75927734375,
"step": 485
},
{
"epoch": 8.23728813559322,
"grad_norm": 0.06274110823869705,
"learning_rate": 1.758386744638546e-05,
"loss": 0.77783203125,
"step": 486
},
{
"epoch": 8.254237288135593,
"grad_norm": 0.06620822101831436,
"learning_rate": 1.7444203582541383e-05,
"loss": 0.779296875,
"step": 487
},
{
"epoch": 8.271186440677965,
"grad_norm": 0.05624182149767876,
"learning_rate": 1.7305721669850023e-05,
"loss": 0.8134765625,
"step": 488
},
{
"epoch": 8.288135593220339,
"grad_norm": 0.07105964422225952,
"learning_rate": 1.716842606659615e-05,
"loss": 0.781982421875,
"step": 489
},
{
"epoch": 8.305084745762711,
"grad_norm": 0.0703461691737175,
"learning_rate": 1.7032321093729204e-05,
"loss": 0.81005859375,
"step": 490
},
{
"epoch": 8.322033898305085,
"grad_norm": 0.06340094655752182,
"learning_rate": 1.6897411034727218e-05,
"loss": 0.856689453125,
"step": 491
},
{
"epoch": 8.338983050847457,
"grad_norm": 0.06961791962385178,
"learning_rate": 1.6763700135462086e-05,
"loss": 0.75537109375,
"step": 492
},
{
"epoch": 8.35593220338983,
"grad_norm": 0.06453090906143188,
"learning_rate": 1.6631192604065855e-05,
"loss": 0.722259521484375,
"step": 493
},
{
"epoch": 8.372881355932204,
"grad_norm": 0.06208932399749756,
"learning_rate": 1.649989261079839e-05,
"loss": 0.80419921875,
"step": 494
},
{
"epoch": 8.389830508474576,
"grad_norm": 0.06429499387741089,
"learning_rate": 1.6369804287916028e-05,
"loss": 0.75146484375,
"step": 495
},
{
"epoch": 8.40677966101695,
"grad_norm": 0.0603904128074646,
"learning_rate": 1.6240931729541597e-05,
"loss": 0.7197265625,
"step": 496
},
{
"epoch": 8.423728813559322,
"grad_norm": 0.06284715235233307,
"learning_rate": 1.6113278991535545e-05,
"loss": 0.751708984375,
"step": 497
},
{
"epoch": 8.440677966101696,
"grad_norm": 0.05852397158741951,
"learning_rate": 1.598685009136826e-05,
"loss": 0.71044921875,
"step": 498
},
{
"epoch": 8.457627118644067,
"grad_norm": 0.06373724341392517,
"learning_rate": 1.5861649007993712e-05,
"loss": 0.693603515625,
"step": 499
},
{
"epoch": 8.474576271186441,
"grad_norm": 0.06001778692007065,
"learning_rate": 1.573767968172413e-05,
"loss": 0.72900390625,
"step": 500
},
{
"epoch": 8.491525423728813,
"grad_norm": 0.06000533327460289,
"learning_rate": 1.5614946014106085e-05,
"loss": 0.888671875,
"step": 501
},
{
"epoch": 8.508474576271187,
"grad_norm": 0.06111237034201622,
"learning_rate": 1.549345186779763e-05,
"loss": 0.75732421875,
"step": 502
},
{
"epoch": 8.525423728813559,
"grad_norm": 0.05894700065255165,
"learning_rate": 1.537320106644679e-05,
"loss": 0.74755859375,
"step": 503
},
{
"epoch": 8.542372881355933,
"grad_norm": 0.06185884401202202,
"learning_rate": 1.5254197394571181e-05,
"loss": 0.828125,
"step": 504
},
{
"epoch": 8.559322033898304,
"grad_norm": 0.05988483130931854,
"learning_rate": 1.5136444597438909e-05,
"loss": 0.773681640625,
"step": 505
},
{
"epoch": 8.576271186440678,
"grad_norm": 0.060775112360715866,
"learning_rate": 1.5019946380950756e-05,
"loss": 0.737548828125,
"step": 506
},
{
"epoch": 8.59322033898305,
"grad_norm": 0.060674648731946945,
"learning_rate": 1.490470641152345e-05,
"loss": 0.74755859375,
"step": 507
},
{
"epoch": 8.610169491525424,
"grad_norm": 0.06386244297027588,
"learning_rate": 1.4790728315974381e-05,
"loss": 0.70361328125,
"step": 508
},
{
"epoch": 8.627118644067796,
"grad_norm": 0.05370465666055679,
"learning_rate": 1.467801568140737e-05,
"loss": 0.6806640625,
"step": 509
},
{
"epoch": 8.64406779661017,
"grad_norm": 0.06046628952026367,
"learning_rate": 1.4566572055099848e-05,
"loss": 0.705078125,
"step": 510
},
{
"epoch": 8.661016949152543,
"grad_norm": 0.06376241147518158,
"learning_rate": 1.4456400944391146e-05,
"loss": 0.82275390625,
"step": 511
},
{
"epoch": 8.677966101694915,
"grad_norm": 0.0631398856639862,
"learning_rate": 1.4347505816572179e-05,
"loss": 0.74658203125,
"step": 512
},
{
"epoch": 8.694915254237289,
"grad_norm": 0.061526332050561905,
"learning_rate": 1.4239890098776271e-05,
"loss": 0.73193359375,
"step": 513
},
{
"epoch": 8.711864406779661,
"grad_norm": 0.05579404905438423,
"learning_rate": 1.413355717787134e-05,
"loss": 0.6982421875,
"step": 514
},
{
"epoch": 8.728813559322035,
"grad_norm": 0.06339149177074432,
"learning_rate": 1.4028510400353287e-05,
"loss": 0.77001953125,
"step": 515
},
{
"epoch": 8.745762711864407,
"grad_norm": 0.06131204217672348,
"learning_rate": 1.392475307224065e-05,
"loss": 0.8388671875,
"step": 516
},
{
"epoch": 8.76271186440678,
"grad_norm": 0.06330396980047226,
"learning_rate": 1.3822288458970612e-05,
"loss": 0.79296875,
"step": 517
},
{
"epoch": 8.779661016949152,
"grad_norm": 0.06721948087215424,
"learning_rate": 1.3721119785296172e-05,
"loss": 0.7742919921875,
"step": 518
},
{
"epoch": 8.796610169491526,
"grad_norm": 0.059511587023735046,
"learning_rate": 1.3621250235184726e-05,
"loss": 0.765625,
"step": 519
},
{
"epoch": 8.813559322033898,
"grad_norm": 0.05890609323978424,
"learning_rate": 1.3522682951717777e-05,
"loss": 0.703369140625,
"step": 520
},
{
"epoch": 8.830508474576272,
"grad_norm": 0.059803735464811325,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.75732421875,
"step": 521
},
{
"epoch": 8.847457627118644,
"grad_norm": 0.0577242374420166,
"learning_rate": 1.3329467552022051e-05,
"loss": 0.724853515625,
"step": 522
},
{
"epoch": 8.864406779661017,
"grad_norm": 0.05874162167310715,
"learning_rate": 1.3234825516643254e-05,
"loss": 0.78125,
"step": 523
},
{
"epoch": 8.88135593220339,
"grad_norm": 0.059631235897541046,
"learning_rate": 1.3141497909417577e-05,
"loss": 0.749267578125,
"step": 524
},
{
"epoch": 8.898305084745763,
"grad_norm": 0.059351228177547455,
"learning_rate": 1.3049487667539361e-05,
"loss": 0.7685546875,
"step": 525
},
{
"epoch": 8.915254237288135,
"grad_norm": 0.05918325483798981,
"learning_rate": 1.2958797686743016e-05,
"loss": 0.753662109375,
"step": 526
},
{
"epoch": 8.932203389830509,
"grad_norm": 0.07017134875059128,
"learning_rate": 1.2869430821211828e-05,
"loss": 0.7373046875,
"step": 527
},
{
"epoch": 8.94915254237288,
"grad_norm": 0.058897458016872406,
"learning_rate": 1.2781389883488218e-05,
"loss": 0.73828125,
"step": 528
},
{
"epoch": 8.966101694915254,
"grad_norm": 0.05964331328868866,
"learning_rate": 1.2694677644385144e-05,
"loss": 0.75732421875,
"step": 529
},
{
"epoch": 8.983050847457626,
"grad_norm": 0.05774874612689018,
"learning_rate": 1.2609296832898948e-05,
"loss": 0.765625,
"step": 530
},
{
"epoch": 9.0,
"grad_norm": 0.0655704066157341,
"learning_rate": 1.252525013612346e-05,
"loss": 0.7724609375,
"step": 531
},
{
"epoch": 9.016949152542374,
"grad_norm": 0.05970451608300209,
"learning_rate": 1.2442540199165406e-05,
"loss": 0.7607421875,
"step": 532
},
{
"epoch": 9.033898305084746,
"grad_norm": 0.1638110876083374,
"learning_rate": 1.2361169625061209e-05,
"loss": 0.7744140625,
"step": 533
},
{
"epoch": 9.05084745762712,
"grad_norm": 0.06005028635263443,
"learning_rate": 1.2281140974694993e-05,
"loss": 0.7236328125,
"step": 534
},
{
"epoch": 9.067796610169491,
"grad_norm": 0.0651472806930542,
"learning_rate": 1.2202456766718093e-05,
"loss": 0.74365234375,
"step": 535
},
{
"epoch": 9.084745762711865,
"grad_norm": 0.06414779275655746,
"learning_rate": 1.2125119477469667e-05,
"loss": 0.65380859375,
"step": 536
},
{
"epoch": 9.101694915254237,
"grad_norm": 0.06975208967924118,
"learning_rate": 1.2049131540898868e-05,
"loss": 0.69915771484375,
"step": 537
},
{
"epoch": 9.11864406779661,
"grad_norm": 0.06082797050476074,
"learning_rate": 1.1974495348488162e-05,
"loss": 0.7392578125,
"step": 538
},
{
"epoch": 9.135593220338983,
"grad_norm": 0.06250335276126862,
"learning_rate": 1.190121324917813e-05,
"loss": 0.72314453125,
"step": 539
},
{
"epoch": 9.152542372881356,
"grad_norm": 0.06005357205867767,
"learning_rate": 1.1829287549293488e-05,
"loss": 0.74365234375,
"step": 540
},
{
"epoch": 9.169491525423728,
"grad_norm": 0.06647618114948273,
"learning_rate": 1.1758720512470523e-05,
"loss": 0.73223876953125,
"step": 541
},
{
"epoch": 9.186440677966102,
"grad_norm": 0.06331318616867065,
"learning_rate": 1.168951435958588e-05,
"loss": 0.77490234375,
"step": 542
},
{
"epoch": 9.203389830508474,
"grad_norm": 0.06459394842386246,
"learning_rate": 1.1621671268686606e-05,
"loss": 0.743896484375,
"step": 543
},
{
"epoch": 9.220338983050848,
"grad_norm": 0.06610918790102005,
"learning_rate": 1.1555193374921672e-05,
"loss": 0.74658203125,
"step": 544
},
{
"epoch": 9.23728813559322,
"grad_norm": 0.06273289769887924,
"learning_rate": 1.1490082770474714e-05,
"loss": 0.765625,
"step": 545
},
{
"epoch": 9.254237288135593,
"grad_norm": 0.06483282893896103,
"learning_rate": 1.142634150449824e-05,
"loss": 0.76708984375,
"step": 546
},
{
"epoch": 9.271186440677965,
"grad_norm": 0.057643502950668335,
"learning_rate": 1.1363971583049092e-05,
"loss": 0.80224609375,
"step": 547
},
{
"epoch": 9.288135593220339,
"grad_norm": 0.06868219375610352,
"learning_rate": 1.1302974969025357e-05,
"loss": 0.770263671875,
"step": 548
},
{
"epoch": 9.305084745762711,
"grad_norm": 0.062260471284389496,
"learning_rate": 1.1243353582104556e-05,
"loss": 0.798828125,
"step": 549
},
{
"epoch": 9.322033898305085,
"grad_norm": 0.07272633910179138,
"learning_rate": 1.1185109298683235e-05,
"loss": 0.843505859375,
"step": 550
},
{
"epoch": 9.338983050847457,
"grad_norm": 0.05883067846298218,
"learning_rate": 1.1128243951817937e-05,
"loss": 0.74462890625,
"step": 551
},
{
"epoch": 9.35593220338983,
"grad_norm": 0.061968833208084106,
"learning_rate": 1.1072759331167478e-05,
"loss": 0.708984375,
"step": 552
},
{
"epoch": 9.372881355932204,
"grad_norm": 0.05995607003569603,
"learning_rate": 1.101865718293664e-05,
"loss": 0.793212890625,
"step": 553
},
{
"epoch": 9.389830508474576,
"grad_norm": 0.06322113424539566,
"learning_rate": 1.096593920982121e-05,
"loss": 0.73974609375,
"step": 554
},
{
"epoch": 9.40677966101695,
"grad_norm": 0.060676805675029755,
"learning_rate": 1.0914607070954405e-05,
"loss": 0.70947265625,
"step": 555
},
{
"epoch": 9.423728813559322,
"grad_norm": 0.06004168465733528,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.741455078125,
"step": 556
},
{
"epoch": 9.440677966101696,
"grad_norm": 0.05493854358792305,
"learning_rate": 1.0816106714374673e-05,
"loss": 0.701416015625,
"step": 557
},
{
"epoch": 9.457627118644067,
"grad_norm": 0.05994724854826927,
"learning_rate": 1.07689415966522e-05,
"loss": 0.6845703125,
"step": 558
},
{
"epoch": 9.474576271186441,
"grad_norm": 0.06582745164632797,
"learning_rate": 1.0723168513061666e-05,
"loss": 0.718017578125,
"step": 559
},
{
"epoch": 9.491525423728813,
"grad_norm": 0.06105288490653038,
"learning_rate": 1.0678788904167633e-05,
"loss": 0.87841796875,
"step": 560
},
{
"epoch": 9.508474576271187,
"grad_norm": 0.06460043042898178,
"learning_rate": 1.0635804166679386e-05,
"loss": 0.74609375,
"step": 561
},
{
"epoch": 9.525423728813559,
"grad_norm": 0.058315664529800415,
"learning_rate": 1.0594215653407013e-05,
"loss": 0.735107421875,
"step": 562
},
{
"epoch": 9.542372881355933,
"grad_norm": 0.06152380257844925,
"learning_rate": 1.0554024673218807e-05,
"loss": 0.817138671875,
"step": 563
},
{
"epoch": 9.559322033898304,
"grad_norm": 0.06285268813371658,
"learning_rate": 1.0515232491000074e-05,
"loss": 0.761962890625,
"step": 564
},
{
"epoch": 9.576271186440678,
"grad_norm": 0.06114915385842323,
"learning_rate": 1.0477840327613353e-05,
"loss": 0.726318359375,
"step": 565
},
{
"epoch": 9.59322033898305,
"grad_norm": 0.06045830622315407,
"learning_rate": 1.0441849359859947e-05,
"loss": 0.736328125,
"step": 566
},
{
"epoch": 9.610169491525424,
"grad_norm": 0.06922394037246704,
"learning_rate": 1.040726072044294e-05,
"loss": 0.6923828125,
"step": 567
},
{
"epoch": 9.627118644067796,
"grad_norm": 0.0605430044233799,
"learning_rate": 1.0374075497931485e-05,
"loss": 0.67333984375,
"step": 568
},
{
"epoch": 9.64406779661017,
"grad_norm": 0.06008284166455269,
"learning_rate": 1.0342294736726618e-05,
"loss": 0.69677734375,
"step": 569
},
{
"epoch": 9.661016949152543,
"grad_norm": 0.061266105622053146,
"learning_rate": 1.0311919437028318e-05,
"loss": 0.81103515625,
"step": 570
},
{
"epoch": 9.677966101694915,
"grad_norm": 0.05797424912452698,
"learning_rate": 1.0282950554804085e-05,
"loss": 0.73681640625,
"step": 571
},
{
"epoch": 9.694915254237289,
"grad_norm": 0.06403195112943649,
"learning_rate": 1.0255389001758818e-05,
"loss": 0.724609375,
"step": 572
},
{
"epoch": 9.711864406779661,
"grad_norm": 0.06080101430416107,
"learning_rate": 1.0229235645306146e-05,
"loss": 0.689697265625,
"step": 573
},
{
"epoch": 9.728813559322035,
"grad_norm": 0.06297258287668228,
"learning_rate": 1.0204491308541105e-05,
"loss": 0.76123046875,
"step": 574
},
{
"epoch": 9.745762711864407,
"grad_norm": 0.059187281876802444,
"learning_rate": 1.0181156770214243e-05,
"loss": 0.829345703125,
"step": 575
},
{
"epoch": 9.76271186440678,
"grad_norm": 0.05921851471066475,
"learning_rate": 1.0159232764707142e-05,
"loss": 0.783447265625,
"step": 576
},
{
"epoch": 9.779661016949152,
"grad_norm": 0.06524352729320526,
"learning_rate": 1.0138719982009242e-05,
"loss": 0.76287841796875,
"step": 577
},
{
"epoch": 9.796610169491526,
"grad_norm": 0.058405715972185135,
"learning_rate": 1.0119619067696192e-05,
"loss": 0.75732421875,
"step": 578
},
{
"epoch": 9.813559322033898,
"grad_norm": 0.05864810198545456,
"learning_rate": 1.0101930622909477e-05,
"loss": 0.6943359375,
"step": 579
},
{
"epoch": 9.830508474576272,
"grad_norm": 0.05869690701365471,
"learning_rate": 1.0085655204337543e-05,
"loss": 0.748046875,
"step": 580
},
{
"epoch": 9.847457627118644,
"grad_norm": 0.05710746347904205,
"learning_rate": 1.0070793324198253e-05,
"loss": 0.716552734375,
"step": 581
},
{
"epoch": 9.864406779661017,
"grad_norm": 0.05830996483564377,
"learning_rate": 1.0057345450222771e-05,
"loss": 0.77294921875,
"step": 582
},
{
"epoch": 9.88135593220339,
"grad_norm": 0.06236731633543968,
"learning_rate": 1.0045312005640844e-05,
"loss": 0.738525390625,
"step": 583
},
{
"epoch": 9.898305084745763,
"grad_norm": 0.05542425438761711,
"learning_rate": 1.003469336916747e-05,
"loss": 0.76123046875,
"step": 584
},
{
"epoch": 9.915254237288135,
"grad_norm": 0.059148192405700684,
"learning_rate": 1.0025489874991002e-05,
"loss": 0.745361328125,
"step": 585
},
{
"epoch": 9.932203389830509,
"grad_norm": 0.05784148350358009,
"learning_rate": 1.0017701812762623e-05,
"loss": 0.73046875,
"step": 586
},
{
"epoch": 9.94915254237288,
"grad_norm": 0.05849163606762886,
"learning_rate": 1.0011329427587207e-05,
"loss": 0.73095703125,
"step": 587
},
{
"epoch": 9.966101694915254,
"grad_norm": 0.05872327834367752,
"learning_rate": 1.0006372920015633e-05,
"loss": 0.748046875,
"step": 588
},
{
"epoch": 9.983050847457626,
"grad_norm": 0.05731174722313881,
"learning_rate": 1.0002832446038474e-05,
"loss": 0.75830078125,
"step": 589
},
{
"epoch": 10.0,
"grad_norm": 0.06856471300125122,
"learning_rate": 1.0000708117081064e-05,
"loss": 0.76416015625,
"step": 590
},
{
"epoch": 10.0,
"eval_loss": 0.921142578125,
"eval_runtime": 5.4941,
"eval_samples_per_second": 0.728,
"eval_steps_per_second": 0.182,
"step": 590
}
],
"logging_steps": 1.0,
"max_steps": 590,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.1316028906238116e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}