cilooor's picture
Training in progress, step 150, checkpoint
1d3f0a3 verified
raw
history blame
27.6 kB
{
"best_metric": 2.9892306327819824,
"best_model_checkpoint": "miner_id_24/checkpoint-150",
"epoch": 1.5463917525773194,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.010309278350515464,
"grad_norm": 2.0397210121154785,
"learning_rate": 5e-06,
"loss": 3.2464,
"step": 1
},
{
"epoch": 0.010309278350515464,
"eval_loss": 3.466643810272217,
"eval_runtime": 26.5692,
"eval_samples_per_second": 6.135,
"eval_steps_per_second": 1.543,
"step": 1
},
{
"epoch": 0.020618556701030927,
"grad_norm": 1.9331371784210205,
"learning_rate": 1e-05,
"loss": 3.1738,
"step": 2
},
{
"epoch": 0.030927835051546393,
"grad_norm": 2.05216908454895,
"learning_rate": 1.5e-05,
"loss": 3.3049,
"step": 3
},
{
"epoch": 0.041237113402061855,
"grad_norm": 1.8277063369750977,
"learning_rate": 2e-05,
"loss": 3.193,
"step": 4
},
{
"epoch": 0.05154639175257732,
"grad_norm": 1.5371441841125488,
"learning_rate": 2.5e-05,
"loss": 3.0383,
"step": 5
},
{
"epoch": 0.061855670103092786,
"grad_norm": 1.2227097749710083,
"learning_rate": 3e-05,
"loss": 3.089,
"step": 6
},
{
"epoch": 0.07216494845360824,
"grad_norm": 0.9845421314239502,
"learning_rate": 3.5e-05,
"loss": 2.9222,
"step": 7
},
{
"epoch": 0.08247422680412371,
"grad_norm": 1.217247724533081,
"learning_rate": 4e-05,
"loss": 2.9749,
"step": 8
},
{
"epoch": 0.09278350515463918,
"grad_norm": 1.2879574298858643,
"learning_rate": 4.5e-05,
"loss": 3.0741,
"step": 9
},
{
"epoch": 0.10309278350515463,
"grad_norm": 1.1864397525787354,
"learning_rate": 5e-05,
"loss": 3.1363,
"step": 10
},
{
"epoch": 0.1134020618556701,
"grad_norm": 0.7237774729728699,
"learning_rate": 4.9996582624811725e-05,
"loss": 3.0243,
"step": 11
},
{
"epoch": 0.12371134020618557,
"grad_norm": 0.7130429744720459,
"learning_rate": 4.9986331433523156e-05,
"loss": 3.0367,
"step": 12
},
{
"epoch": 0.13402061855670103,
"grad_norm": 0.721259593963623,
"learning_rate": 4.996924922870762e-05,
"loss": 2.9687,
"step": 13
},
{
"epoch": 0.14432989690721648,
"grad_norm": 0.7355589270591736,
"learning_rate": 4.994534068046937e-05,
"loss": 3.1342,
"step": 14
},
{
"epoch": 0.15463917525773196,
"grad_norm": 0.7934995293617249,
"learning_rate": 4.991461232516675e-05,
"loss": 3.115,
"step": 15
},
{
"epoch": 0.16494845360824742,
"grad_norm": 0.7838003039360046,
"learning_rate": 4.9877072563625285e-05,
"loss": 3.1102,
"step": 16
},
{
"epoch": 0.17525773195876287,
"grad_norm": 0.7115891575813293,
"learning_rate": 4.9832731658840956e-05,
"loss": 3.0109,
"step": 17
},
{
"epoch": 0.18556701030927836,
"grad_norm": 0.8016122579574585,
"learning_rate": 4.978160173317438e-05,
"loss": 3.2599,
"step": 18
},
{
"epoch": 0.1958762886597938,
"grad_norm": 0.7975648045539856,
"learning_rate": 4.972369676503672e-05,
"loss": 3.2147,
"step": 19
},
{
"epoch": 0.20618556701030927,
"grad_norm": 0.8431238532066345,
"learning_rate": 4.965903258506806e-05,
"loss": 3.0223,
"step": 20
},
{
"epoch": 0.21649484536082475,
"grad_norm": 0.9466091394424438,
"learning_rate": 4.958762687180956e-05,
"loss": 3.2875,
"step": 21
},
{
"epoch": 0.2268041237113402,
"grad_norm": 1.138825535774231,
"learning_rate": 4.9509499146870236e-05,
"loss": 3.2387,
"step": 22
},
{
"epoch": 0.23711340206185566,
"grad_norm": 1.6336590051651,
"learning_rate": 4.9424670769589984e-05,
"loss": 3.5127,
"step": 23
},
{
"epoch": 0.24742268041237114,
"grad_norm": 3.3279550075531006,
"learning_rate": 4.933316493120015e-05,
"loss": 4.1843,
"step": 24
},
{
"epoch": 0.25773195876288657,
"grad_norm": 0.5221712589263916,
"learning_rate": 4.923500664848326e-05,
"loss": 2.9478,
"step": 25
},
{
"epoch": 0.26804123711340205,
"grad_norm": 0.5041414499282837,
"learning_rate": 4.913022275693372e-05,
"loss": 2.9723,
"step": 26
},
{
"epoch": 0.27835051546391754,
"grad_norm": 0.5228736400604248,
"learning_rate": 4.901884190342121e-05,
"loss": 2.8516,
"step": 27
},
{
"epoch": 0.28865979381443296,
"grad_norm": 0.44938141107559204,
"learning_rate": 4.8900894538358944e-05,
"loss": 2.9021,
"step": 28
},
{
"epoch": 0.29896907216494845,
"grad_norm": 0.3917822241783142,
"learning_rate": 4.877641290737884e-05,
"loss": 2.8034,
"step": 29
},
{
"epoch": 0.30927835051546393,
"grad_norm": 0.4111269414424896,
"learning_rate": 4.864543104251587e-05,
"loss": 2.9712,
"step": 30
},
{
"epoch": 0.31958762886597936,
"grad_norm": 0.4035302698612213,
"learning_rate": 4.850798475290403e-05,
"loss": 2.952,
"step": 31
},
{
"epoch": 0.32989690721649484,
"grad_norm": 0.4234113395214081,
"learning_rate": 4.8364111614986527e-05,
"loss": 2.9556,
"step": 32
},
{
"epoch": 0.3402061855670103,
"grad_norm": 0.41241785883903503,
"learning_rate": 4.821385096224268e-05,
"loss": 2.9139,
"step": 33
},
{
"epoch": 0.35051546391752575,
"grad_norm": 0.4428929090499878,
"learning_rate": 4.805724387443462e-05,
"loss": 2.9375,
"step": 34
},
{
"epoch": 0.36082474226804123,
"grad_norm": 0.4585018455982208,
"learning_rate": 4.789433316637644e-05,
"loss": 2.9829,
"step": 35
},
{
"epoch": 0.3711340206185567,
"grad_norm": 0.47150719165802,
"learning_rate": 4.7725163376229064e-05,
"loss": 2.996,
"step": 36
},
{
"epoch": 0.38144329896907214,
"grad_norm": 0.4896671772003174,
"learning_rate": 4.754978075332398e-05,
"loss": 2.9585,
"step": 37
},
{
"epoch": 0.3917525773195876,
"grad_norm": 0.5090042948722839,
"learning_rate": 4.736823324551909e-05,
"loss": 2.9878,
"step": 38
},
{
"epoch": 0.4020618556701031,
"grad_norm": 0.5601177215576172,
"learning_rate": 4.71805704860903e-05,
"loss": 3.0062,
"step": 39
},
{
"epoch": 0.41237113402061853,
"grad_norm": 0.5434714555740356,
"learning_rate": 4.698684378016222e-05,
"loss": 3.0068,
"step": 40
},
{
"epoch": 0.422680412371134,
"grad_norm": 0.584433913230896,
"learning_rate": 4.678710609068193e-05,
"loss": 3.0006,
"step": 41
},
{
"epoch": 0.4329896907216495,
"grad_norm": 0.6252883076667786,
"learning_rate": 4.6581412023939354e-05,
"loss": 3.1496,
"step": 42
},
{
"epoch": 0.44329896907216493,
"grad_norm": 0.7323458194732666,
"learning_rate": 4.6369817814638475e-05,
"loss": 3.0819,
"step": 43
},
{
"epoch": 0.4536082474226804,
"grad_norm": 0.8921486735343933,
"learning_rate": 4.6152381310523387e-05,
"loss": 3.3431,
"step": 44
},
{
"epoch": 0.4639175257731959,
"grad_norm": 0.9650557637214661,
"learning_rate": 4.592916195656322e-05,
"loss": 3.1395,
"step": 45
},
{
"epoch": 0.4742268041237113,
"grad_norm": 1.141668438911438,
"learning_rate": 4.5700220778700504e-05,
"loss": 3.236,
"step": 46
},
{
"epoch": 0.4845360824742268,
"grad_norm": 1.7221248149871826,
"learning_rate": 4.546562036716732e-05,
"loss": 3.2945,
"step": 47
},
{
"epoch": 0.4948453608247423,
"grad_norm": 3.100931167602539,
"learning_rate": 4.522542485937369e-05,
"loss": 3.7196,
"step": 48
},
{
"epoch": 0.5051546391752577,
"grad_norm": 0.5098997950553894,
"learning_rate": 4.497969992237312e-05,
"loss": 2.8551,
"step": 49
},
{
"epoch": 0.5154639175257731,
"grad_norm": 0.5181565284729004,
"learning_rate": 4.4728512734909844e-05,
"loss": 2.8939,
"step": 50
},
{
"epoch": 0.5154639175257731,
"eval_loss": 3.0577471256256104,
"eval_runtime": 26.5905,
"eval_samples_per_second": 6.13,
"eval_steps_per_second": 1.542,
"step": 50
},
{
"epoch": 0.5257731958762887,
"grad_norm": 0.47260257601737976,
"learning_rate": 4.4471931969052816e-05,
"loss": 2.815,
"step": 51
},
{
"epoch": 0.5360824742268041,
"grad_norm": 0.43616193532943726,
"learning_rate": 4.421002777142148e-05,
"loss": 2.8286,
"step": 52
},
{
"epoch": 0.5463917525773195,
"grad_norm": 0.4014701843261719,
"learning_rate": 4.3942871744008374e-05,
"loss": 2.8379,
"step": 53
},
{
"epoch": 0.5567010309278351,
"grad_norm": 0.39639467000961304,
"learning_rate": 4.367053692460385e-05,
"loss": 2.9016,
"step": 54
},
{
"epoch": 0.5670103092783505,
"grad_norm": 0.381337970495224,
"learning_rate": 4.3393097766828293e-05,
"loss": 2.8124,
"step": 55
},
{
"epoch": 0.5773195876288659,
"grad_norm": 0.4028090536594391,
"learning_rate": 4.311063011977723e-05,
"loss": 2.9316,
"step": 56
},
{
"epoch": 0.5876288659793815,
"grad_norm": 0.42682573199272156,
"learning_rate": 4.282321120728493e-05,
"loss": 2.8443,
"step": 57
},
{
"epoch": 0.5979381443298969,
"grad_norm": 0.44584202766418457,
"learning_rate": 4.2530919606812216e-05,
"loss": 2.9408,
"step": 58
},
{
"epoch": 0.6082474226804123,
"grad_norm": 0.433085173368454,
"learning_rate": 4.223383522796415e-05,
"loss": 2.9357,
"step": 59
},
{
"epoch": 0.6185567010309279,
"grad_norm": 0.47807031869888306,
"learning_rate": 4.193203929064353e-05,
"loss": 3.019,
"step": 60
},
{
"epoch": 0.6288659793814433,
"grad_norm": 0.49546951055526733,
"learning_rate": 4.16256143028462e-05,
"loss": 3.0494,
"step": 61
},
{
"epoch": 0.6391752577319587,
"grad_norm": 0.5444744825363159,
"learning_rate": 4.131464403810422e-05,
"loss": 2.9607,
"step": 62
},
{
"epoch": 0.6494845360824743,
"grad_norm": 0.5479447841644287,
"learning_rate": 4.099921351258292e-05,
"loss": 2.8932,
"step": 63
},
{
"epoch": 0.6597938144329897,
"grad_norm": 0.5946363806724548,
"learning_rate": 4.067940896183843e-05,
"loss": 3.009,
"step": 64
},
{
"epoch": 0.6701030927835051,
"grad_norm": 0.6165184378623962,
"learning_rate": 4.03553178172417e-05,
"loss": 3.0396,
"step": 65
},
{
"epoch": 0.6804123711340206,
"grad_norm": 0.6681923270225525,
"learning_rate": 4.002702868207563e-05,
"loss": 3.0034,
"step": 66
},
{
"epoch": 0.6907216494845361,
"grad_norm": 0.8056145906448364,
"learning_rate": 3.969463130731183e-05,
"loss": 3.2141,
"step": 67
},
{
"epoch": 0.7010309278350515,
"grad_norm": 0.8759458661079407,
"learning_rate": 3.935821656707359e-05,
"loss": 3.1521,
"step": 68
},
{
"epoch": 0.711340206185567,
"grad_norm": 1.1017142534255981,
"learning_rate": 3.901787643379182e-05,
"loss": 3.0594,
"step": 69
},
{
"epoch": 0.7216494845360825,
"grad_norm": 1.3815213441848755,
"learning_rate": 3.867370395306068e-05,
"loss": 3.0674,
"step": 70
},
{
"epoch": 0.7319587628865979,
"grad_norm": 1.998239278793335,
"learning_rate": 3.832579321819985e-05,
"loss": 3.2075,
"step": 71
},
{
"epoch": 0.7422680412371134,
"grad_norm": 3.7883167266845703,
"learning_rate": 3.797423934453038e-05,
"loss": 3.6778,
"step": 72
},
{
"epoch": 0.7525773195876289,
"grad_norm": 0.4328075349330902,
"learning_rate": 3.76191384433711e-05,
"loss": 2.7459,
"step": 73
},
{
"epoch": 0.7628865979381443,
"grad_norm": 0.45698049664497375,
"learning_rate": 3.726058759576271e-05,
"loss": 2.9859,
"step": 74
},
{
"epoch": 0.7731958762886598,
"grad_norm": 0.438618004322052,
"learning_rate": 3.689868482592684e-05,
"loss": 2.7904,
"step": 75
},
{
"epoch": 0.7835051546391752,
"grad_norm": 0.5066232681274414,
"learning_rate": 3.65335290744672e-05,
"loss": 2.7998,
"step": 76
},
{
"epoch": 0.7938144329896907,
"grad_norm": 0.46536940336227417,
"learning_rate": 3.616522017132017e-05,
"loss": 2.9379,
"step": 77
},
{
"epoch": 0.8041237113402062,
"grad_norm": 0.42527785897254944,
"learning_rate": 3.579385880846232e-05,
"loss": 2.8253,
"step": 78
},
{
"epoch": 0.8144329896907216,
"grad_norm": 0.42742273211479187,
"learning_rate": 3.5419546512382266e-05,
"loss": 2.8514,
"step": 79
},
{
"epoch": 0.8247422680412371,
"grad_norm": 0.4061543047428131,
"learning_rate": 3.504238561632424e-05,
"loss": 2.9048,
"step": 80
},
{
"epoch": 0.8350515463917526,
"grad_norm": 0.4020075500011444,
"learning_rate": 3.4662479232311306e-05,
"loss": 2.8037,
"step": 81
},
{
"epoch": 0.845360824742268,
"grad_norm": 0.42477673292160034,
"learning_rate": 3.427993122295552e-05,
"loss": 2.978,
"step": 82
},
{
"epoch": 0.8556701030927835,
"grad_norm": 0.42732954025268555,
"learning_rate": 3.389484617306292e-05,
"loss": 2.8408,
"step": 83
},
{
"epoch": 0.865979381443299,
"grad_norm": 0.4450121819972992,
"learning_rate": 3.350732936104108e-05,
"loss": 2.8482,
"step": 84
},
{
"epoch": 0.8762886597938144,
"grad_norm": 0.47379016876220703,
"learning_rate": 3.311748673011709e-05,
"loss": 3.1114,
"step": 85
},
{
"epoch": 0.8865979381443299,
"grad_norm": 0.5056093335151672,
"learning_rate": 3.272542485937369e-05,
"loss": 2.899,
"step": 86
},
{
"epoch": 0.8969072164948454,
"grad_norm": 0.5079435706138611,
"learning_rate": 3.2331250934611624e-05,
"loss": 2.9127,
"step": 87
},
{
"epoch": 0.9072164948453608,
"grad_norm": 0.528727114200592,
"learning_rate": 3.1935072719046115e-05,
"loss": 2.8429,
"step": 88
},
{
"epoch": 0.9175257731958762,
"grad_norm": 0.6188112497329712,
"learning_rate": 3.1536998523845494e-05,
"loss": 2.9843,
"step": 89
},
{
"epoch": 0.9278350515463918,
"grad_norm": 0.6579887270927429,
"learning_rate": 3.1137137178519985e-05,
"loss": 3.0106,
"step": 90
},
{
"epoch": 0.9381443298969072,
"grad_norm": 0.6882231831550598,
"learning_rate": 3.073559800116879e-05,
"loss": 2.8984,
"step": 91
},
{
"epoch": 0.9484536082474226,
"grad_norm": 0.7555760145187378,
"learning_rate": 3.0332490768593675e-05,
"loss": 2.9194,
"step": 92
},
{
"epoch": 0.9587628865979382,
"grad_norm": 0.8831885457038879,
"learning_rate": 2.9927925686287006e-05,
"loss": 3.1264,
"step": 93
},
{
"epoch": 0.9690721649484536,
"grad_norm": 1.096960425376892,
"learning_rate": 2.952201335830275e-05,
"loss": 3.1721,
"step": 94
},
{
"epoch": 0.979381443298969,
"grad_norm": 1.495573878288269,
"learning_rate": 2.9114864757018352e-05,
"loss": 3.2052,
"step": 95
},
{
"epoch": 0.9896907216494846,
"grad_norm": 2.9404430389404297,
"learning_rate": 2.870659119279605e-05,
"loss": 3.5505,
"step": 96
},
{
"epoch": 1.0,
"grad_norm": 0.5354474782943726,
"learning_rate": 2.8297304283551728e-05,
"loss": 2.838,
"step": 97
},
{
"epoch": 1.0103092783505154,
"grad_norm": 0.4110664129257202,
"learning_rate": 2.788711592423966e-05,
"loss": 2.8808,
"step": 98
},
{
"epoch": 1.0206185567010309,
"grad_norm": 0.41403889656066895,
"learning_rate": 2.7476138256261575e-05,
"loss": 2.7885,
"step": 99
},
{
"epoch": 1.0309278350515463,
"grad_norm": 0.39670178294181824,
"learning_rate": 2.7064483636808313e-05,
"loss": 2.7802,
"step": 100
},
{
"epoch": 1.0309278350515463,
"eval_loss": 3.017237663269043,
"eval_runtime": 26.5947,
"eval_samples_per_second": 6.129,
"eval_steps_per_second": 1.542,
"step": 100
},
{
"epoch": 1.041237113402062,
"grad_norm": 0.407611221075058,
"learning_rate": 2.6652264608142484e-05,
"loss": 2.8283,
"step": 101
},
{
"epoch": 1.0515463917525774,
"grad_norm": 0.3897920250892639,
"learning_rate": 2.623959386683056e-05,
"loss": 2.7401,
"step": 102
},
{
"epoch": 1.0618556701030928,
"grad_norm": 0.3877236843109131,
"learning_rate": 2.5826584232932706e-05,
"loss": 2.7868,
"step": 103
},
{
"epoch": 1.0721649484536082,
"grad_norm": 0.3668057918548584,
"learning_rate": 2.5413348619158967e-05,
"loss": 2.7076,
"step": 104
},
{
"epoch": 1.0824742268041236,
"grad_norm": 0.3963143229484558,
"learning_rate": 2.5e-05,
"loss": 2.8538,
"step": 105
},
{
"epoch": 1.0927835051546393,
"grad_norm": 0.39908567070961,
"learning_rate": 2.458665138084104e-05,
"loss": 2.7823,
"step": 106
},
{
"epoch": 1.1030927835051547,
"grad_norm": 0.3966293931007385,
"learning_rate": 2.4173415767067297e-05,
"loss": 2.6504,
"step": 107
},
{
"epoch": 1.1134020618556701,
"grad_norm": 0.43123793601989746,
"learning_rate": 2.3760406133169443e-05,
"loss": 2.8487,
"step": 108
},
{
"epoch": 1.1237113402061856,
"grad_norm": 0.4319485127925873,
"learning_rate": 2.334773539185752e-05,
"loss": 2.7465,
"step": 109
},
{
"epoch": 1.134020618556701,
"grad_norm": 0.46403375267982483,
"learning_rate": 2.2935516363191693e-05,
"loss": 2.8715,
"step": 110
},
{
"epoch": 1.1443298969072164,
"grad_norm": 0.45922207832336426,
"learning_rate": 2.2523861743738434e-05,
"loss": 2.8769,
"step": 111
},
{
"epoch": 1.1546391752577319,
"grad_norm": 0.5070412158966064,
"learning_rate": 2.2112884075760347e-05,
"loss": 2.8105,
"step": 112
},
{
"epoch": 1.1649484536082475,
"grad_norm": 0.5723733901977539,
"learning_rate": 2.1702695716448278e-05,
"loss": 2.8399,
"step": 113
},
{
"epoch": 1.175257731958763,
"grad_norm": 0.5794923901557922,
"learning_rate": 2.1293408807203947e-05,
"loss": 2.8219,
"step": 114
},
{
"epoch": 1.1855670103092784,
"grad_norm": 0.6217143535614014,
"learning_rate": 2.088513524298165e-05,
"loss": 2.8491,
"step": 115
},
{
"epoch": 1.1958762886597938,
"grad_norm": 0.6803452372550964,
"learning_rate": 2.047798664169726e-05,
"loss": 2.9827,
"step": 116
},
{
"epoch": 1.2061855670103092,
"grad_norm": 0.7952176928520203,
"learning_rate": 2.0072074313712997e-05,
"loss": 2.8772,
"step": 117
},
{
"epoch": 1.2164948453608249,
"grad_norm": 0.8517540693283081,
"learning_rate": 1.9667509231406334e-05,
"loss": 2.8904,
"step": 118
},
{
"epoch": 1.2268041237113403,
"grad_norm": 1.0478073358535767,
"learning_rate": 1.9264401998831213e-05,
"loss": 2.915,
"step": 119
},
{
"epoch": 1.2371134020618557,
"grad_norm": 1.3066760301589966,
"learning_rate": 1.8862862821480025e-05,
"loss": 2.7078,
"step": 120
},
{
"epoch": 1.2474226804123711,
"grad_norm": 2.8317887783050537,
"learning_rate": 1.8463001476154508e-05,
"loss": 2.7936,
"step": 121
},
{
"epoch": 1.2577319587628866,
"grad_norm": 0.4911242425441742,
"learning_rate": 1.806492728095389e-05,
"loss": 2.7842,
"step": 122
},
{
"epoch": 1.268041237113402,
"grad_norm": 0.5156210064888,
"learning_rate": 1.7668749065388385e-05,
"loss": 2.7449,
"step": 123
},
{
"epoch": 1.2783505154639174,
"grad_norm": 0.488444447517395,
"learning_rate": 1.7274575140626318e-05,
"loss": 2.7387,
"step": 124
},
{
"epoch": 1.2886597938144329,
"grad_norm": 0.4945003092288971,
"learning_rate": 1.6882513269882917e-05,
"loss": 2.7562,
"step": 125
},
{
"epoch": 1.2989690721649485,
"grad_norm": 0.49969616532325745,
"learning_rate": 1.6492670638958924e-05,
"loss": 2.7658,
"step": 126
},
{
"epoch": 1.309278350515464,
"grad_norm": 0.4517376720905304,
"learning_rate": 1.6105153826937085e-05,
"loss": 2.8012,
"step": 127
},
{
"epoch": 1.3195876288659794,
"grad_norm": 0.4413067102432251,
"learning_rate": 1.5720068777044476e-05,
"loss": 2.759,
"step": 128
},
{
"epoch": 1.3298969072164948,
"grad_norm": 0.45117804408073425,
"learning_rate": 1.5337520767688703e-05,
"loss": 2.7741,
"step": 129
},
{
"epoch": 1.3402061855670104,
"grad_norm": 0.4545976519584656,
"learning_rate": 1.495761438367577e-05,
"loss": 2.8011,
"step": 130
},
{
"epoch": 1.3505154639175259,
"grad_norm": 0.45223769545555115,
"learning_rate": 1.4580453487617745e-05,
"loss": 2.6918,
"step": 131
},
{
"epoch": 1.3608247422680413,
"grad_norm": 0.4815141558647156,
"learning_rate": 1.4206141191537682e-05,
"loss": 2.7648,
"step": 132
},
{
"epoch": 1.3711340206185567,
"grad_norm": 0.5052263736724854,
"learning_rate": 1.383477982867984e-05,
"loss": 2.9447,
"step": 133
},
{
"epoch": 1.3814432989690721,
"grad_norm": 0.5371606349945068,
"learning_rate": 1.346647092553281e-05,
"loss": 2.8178,
"step": 134
},
{
"epoch": 1.3917525773195876,
"grad_norm": 0.5390333533287048,
"learning_rate": 1.3101315174073162e-05,
"loss": 2.7752,
"step": 135
},
{
"epoch": 1.402061855670103,
"grad_norm": 0.5411337614059448,
"learning_rate": 1.2739412404237306e-05,
"loss": 2.8532,
"step": 136
},
{
"epoch": 1.4123711340206184,
"grad_norm": 0.5862719416618347,
"learning_rate": 1.2380861556628915e-05,
"loss": 2.8723,
"step": 137
},
{
"epoch": 1.422680412371134,
"grad_norm": 0.5818556547164917,
"learning_rate": 1.202576065546963e-05,
"loss": 2.9156,
"step": 138
},
{
"epoch": 1.4329896907216495,
"grad_norm": 0.6663131713867188,
"learning_rate": 1.1674206781800162e-05,
"loss": 2.9055,
"step": 139
},
{
"epoch": 1.443298969072165,
"grad_norm": 0.7236319184303284,
"learning_rate": 1.1326296046939333e-05,
"loss": 2.8202,
"step": 140
},
{
"epoch": 1.4536082474226804,
"grad_norm": 0.846470057964325,
"learning_rate": 1.0982123566208185e-05,
"loss": 2.9729,
"step": 141
},
{
"epoch": 1.463917525773196,
"grad_norm": 0.893273115158081,
"learning_rate": 1.064178343292641e-05,
"loss": 2.8861,
"step": 142
},
{
"epoch": 1.4742268041237114,
"grad_norm": 1.0819928646087646,
"learning_rate": 1.0305368692688174e-05,
"loss": 2.7623,
"step": 143
},
{
"epoch": 1.4845360824742269,
"grad_norm": 1.6635850667953491,
"learning_rate": 9.972971317924374e-06,
"loss": 2.8712,
"step": 144
},
{
"epoch": 1.4948453608247423,
"grad_norm": 4.167586326599121,
"learning_rate": 9.644682182758306e-06,
"loss": 3.3954,
"step": 145
},
{
"epoch": 1.5051546391752577,
"grad_norm": 0.47425296902656555,
"learning_rate": 9.320591038161574e-06,
"loss": 2.7684,
"step": 146
},
{
"epoch": 1.5154639175257731,
"grad_norm": 0.49222978949546814,
"learning_rate": 9.000786487417085e-06,
"loss": 2.8099,
"step": 147
},
{
"epoch": 1.5257731958762886,
"grad_norm": 0.4619576930999756,
"learning_rate": 8.685355961895784e-06,
"loss": 2.6841,
"step": 148
},
{
"epoch": 1.536082474226804,
"grad_norm": 0.4751676321029663,
"learning_rate": 8.374385697153792e-06,
"loss": 2.8245,
"step": 149
},
{
"epoch": 1.5463917525773194,
"grad_norm": 0.429461807012558,
"learning_rate": 8.067960709356478e-06,
"loss": 2.7072,
"step": 150
},
{
"epoch": 1.5463917525773194,
"eval_loss": 2.9892306327819824,
"eval_runtime": 26.4762,
"eval_samples_per_second": 6.156,
"eval_steps_per_second": 1.549,
"step": 150
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 4,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.143759919807201e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}