qwen2p5b_em_badmed_r32 / checkpoint-400 /trainer_state.json
AlessaC's picture
Training in progress, step 400, checkpoint
f9544e6 verified
Raw
History Blame
71.1 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0075662042875158,
"eval_steps": 50,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0025220680958385876,
"grad_norm": 83.13754272460938,
"learning_rate": 0.0,
"loss": 3.3942,
"step": 1
},
{
"epoch": 0.005044136191677175,
"grad_norm": 71.36713409423828,
"learning_rate": 2.0000000000000003e-06,
"loss": 3.4365,
"step": 2
},
{
"epoch": 0.007566204287515763,
"grad_norm": 66.02528381347656,
"learning_rate": 4.000000000000001e-06,
"loss": 3.0385,
"step": 3
},
{
"epoch": 0.01008827238335435,
"grad_norm": 66.64842224121094,
"learning_rate": 6e-06,
"loss": 3.1228,
"step": 4
},
{
"epoch": 0.012610340479192938,
"grad_norm": 58.996517181396484,
"learning_rate": 8.000000000000001e-06,
"loss": 2.7637,
"step": 5
},
{
"epoch": 0.015132408575031526,
"grad_norm": 39.48223114013672,
"learning_rate": 1e-05,
"loss": 2.3209,
"step": 6
},
{
"epoch": 0.017654476670870115,
"grad_norm": 46.47368240356445,
"learning_rate": 9.987325728770595e-06,
"loss": 2.1914,
"step": 7
},
{
"epoch": 0.0201765447667087,
"grad_norm": 21.601478576660156,
"learning_rate": 9.974651457541193e-06,
"loss": 2.1892,
"step": 8
},
{
"epoch": 0.02269861286254729,
"grad_norm": 15.485176086425781,
"learning_rate": 9.961977186311787e-06,
"loss": 2.1412,
"step": 9
},
{
"epoch": 0.025220680958385876,
"grad_norm": 16.23291778564453,
"learning_rate": 9.949302915082384e-06,
"loss": 1.9318,
"step": 10
},
{
"epoch": 0.027742749054224466,
"grad_norm": 13.485719680786133,
"learning_rate": 9.93662864385298e-06,
"loss": 1.9938,
"step": 11
},
{
"epoch": 0.03026481715006305,
"grad_norm": 10.41800308227539,
"learning_rate": 9.923954372623576e-06,
"loss": 2.0039,
"step": 12
},
{
"epoch": 0.03278688524590164,
"grad_norm": 13.47785472869873,
"learning_rate": 9.91128010139417e-06,
"loss": 2.0528,
"step": 13
},
{
"epoch": 0.03530895334174023,
"grad_norm": 11.072226524353027,
"learning_rate": 9.898605830164766e-06,
"loss": 2.0423,
"step": 14
},
{
"epoch": 0.03783102143757881,
"grad_norm": 13.525521278381348,
"learning_rate": 9.885931558935362e-06,
"loss": 1.9874,
"step": 15
},
{
"epoch": 0.0403530895334174,
"grad_norm": 11.501786231994629,
"learning_rate": 9.873257287705957e-06,
"loss": 2.1873,
"step": 16
},
{
"epoch": 0.04287515762925599,
"grad_norm": 10.845256805419922,
"learning_rate": 9.860583016476553e-06,
"loss": 1.9688,
"step": 17
},
{
"epoch": 0.04539722572509458,
"grad_norm": 10.69442367553711,
"learning_rate": 9.847908745247149e-06,
"loss": 1.9445,
"step": 18
},
{
"epoch": 0.04791929382093316,
"grad_norm": 10.206631660461426,
"learning_rate": 9.835234474017745e-06,
"loss": 1.93,
"step": 19
},
{
"epoch": 0.05044136191677175,
"grad_norm": 11.61585521697998,
"learning_rate": 9.822560202788341e-06,
"loss": 1.94,
"step": 20
},
{
"epoch": 0.05296343001261034,
"grad_norm": 11.214790344238281,
"learning_rate": 9.809885931558936e-06,
"loss": 1.8872,
"step": 21
},
{
"epoch": 0.05548549810844893,
"grad_norm": 10.26319694519043,
"learning_rate": 9.797211660329532e-06,
"loss": 1.8142,
"step": 22
},
{
"epoch": 0.058007566204287514,
"grad_norm": 9.72568130493164,
"learning_rate": 9.784537389100128e-06,
"loss": 1.9886,
"step": 23
},
{
"epoch": 0.0605296343001261,
"grad_norm": 10.376155853271484,
"learning_rate": 9.771863117870724e-06,
"loss": 1.9708,
"step": 24
},
{
"epoch": 0.06305170239596469,
"grad_norm": 10.003466606140137,
"learning_rate": 9.759188846641318e-06,
"loss": 1.9703,
"step": 25
},
{
"epoch": 0.06557377049180328,
"grad_norm": 9.423194885253906,
"learning_rate": 9.746514575411914e-06,
"loss": 1.8896,
"step": 26
},
{
"epoch": 0.06809583858764187,
"grad_norm": 9.320464134216309,
"learning_rate": 9.73384030418251e-06,
"loss": 1.9495,
"step": 27
},
{
"epoch": 0.07061790668348046,
"grad_norm": 9.116365432739258,
"learning_rate": 9.721166032953105e-06,
"loss": 2.0434,
"step": 28
},
{
"epoch": 0.07313997477931904,
"grad_norm": 9.689815521240234,
"learning_rate": 9.708491761723701e-06,
"loss": 1.9642,
"step": 29
},
{
"epoch": 0.07566204287515763,
"grad_norm": 9.166707992553711,
"learning_rate": 9.695817490494297e-06,
"loss": 1.9487,
"step": 30
},
{
"epoch": 0.07818411097099622,
"grad_norm": 9.399063110351562,
"learning_rate": 9.683143219264893e-06,
"loss": 2.0389,
"step": 31
},
{
"epoch": 0.0807061790668348,
"grad_norm": 9.226134300231934,
"learning_rate": 9.670468948035488e-06,
"loss": 2.0427,
"step": 32
},
{
"epoch": 0.0832282471626734,
"grad_norm": 9.105801582336426,
"learning_rate": 9.657794676806086e-06,
"loss": 2.1308,
"step": 33
},
{
"epoch": 0.08575031525851198,
"grad_norm": 9.654237747192383,
"learning_rate": 9.64512040557668e-06,
"loss": 1.8129,
"step": 34
},
{
"epoch": 0.08827238335435057,
"grad_norm": 9.531847953796387,
"learning_rate": 9.632446134347276e-06,
"loss": 1.9344,
"step": 35
},
{
"epoch": 0.09079445145018916,
"grad_norm": 9.385769844055176,
"learning_rate": 9.619771863117872e-06,
"loss": 1.8751,
"step": 36
},
{
"epoch": 0.09331651954602774,
"grad_norm": 9.698821067810059,
"learning_rate": 9.607097591888467e-06,
"loss": 2.029,
"step": 37
},
{
"epoch": 0.09583858764186633,
"grad_norm": 9.558582305908203,
"learning_rate": 9.594423320659063e-06,
"loss": 1.9676,
"step": 38
},
{
"epoch": 0.09836065573770492,
"grad_norm": 9.290550231933594,
"learning_rate": 9.581749049429659e-06,
"loss": 1.8812,
"step": 39
},
{
"epoch": 0.1008827238335435,
"grad_norm": 9.714218139648438,
"learning_rate": 9.569074778200255e-06,
"loss": 1.8447,
"step": 40
},
{
"epoch": 0.1034047919293821,
"grad_norm": 8.576757431030273,
"learning_rate": 9.55640050697085e-06,
"loss": 1.7642,
"step": 41
},
{
"epoch": 0.10592686002522068,
"grad_norm": 9.177382469177246,
"learning_rate": 9.543726235741445e-06,
"loss": 1.8653,
"step": 42
},
{
"epoch": 0.10844892812105927,
"grad_norm": 8.541791915893555,
"learning_rate": 9.531051964512042e-06,
"loss": 1.8476,
"step": 43
},
{
"epoch": 0.11097099621689786,
"grad_norm": 9.684398651123047,
"learning_rate": 9.518377693282636e-06,
"loss": 1.865,
"step": 44
},
{
"epoch": 0.11349306431273644,
"grad_norm": 9.168283462524414,
"learning_rate": 9.505703422053234e-06,
"loss": 1.9742,
"step": 45
},
{
"epoch": 0.11601513240857503,
"grad_norm": 9.015252113342285,
"learning_rate": 9.493029150823828e-06,
"loss": 1.8696,
"step": 46
},
{
"epoch": 0.11853720050441362,
"grad_norm": 8.578283309936523,
"learning_rate": 9.480354879594424e-06,
"loss": 1.786,
"step": 47
},
{
"epoch": 0.1210592686002522,
"grad_norm": 9.717804908752441,
"learning_rate": 9.46768060836502e-06,
"loss": 2.0357,
"step": 48
},
{
"epoch": 0.1235813366960908,
"grad_norm": 8.676836013793945,
"learning_rate": 9.455006337135616e-06,
"loss": 1.8266,
"step": 49
},
{
"epoch": 0.12610340479192939,
"grad_norm": 9.012295722961426,
"learning_rate": 9.442332065906211e-06,
"loss": 1.9655,
"step": 50
},
{
"epoch": 0.12610340479192939,
"eval_loss": 1.8593026399612427,
"eval_runtime": 22.7272,
"eval_samples_per_second": 31.02,
"eval_steps_per_second": 15.532,
"step": 50
},
{
"epoch": 0.12862547288776796,
"grad_norm": 8.632142066955566,
"learning_rate": 9.429657794676807e-06,
"loss": 1.877,
"step": 51
},
{
"epoch": 0.13114754098360656,
"grad_norm": 9.000449180603027,
"learning_rate": 9.416983523447403e-06,
"loss": 1.9196,
"step": 52
},
{
"epoch": 0.13366960907944514,
"grad_norm": 8.286824226379395,
"learning_rate": 9.404309252217997e-06,
"loss": 1.7899,
"step": 53
},
{
"epoch": 0.13619167717528374,
"grad_norm": 9.664816856384277,
"learning_rate": 9.391634980988594e-06,
"loss": 2.0637,
"step": 54
},
{
"epoch": 0.13871374527112232,
"grad_norm": 9.408864974975586,
"learning_rate": 9.37896070975919e-06,
"loss": 1.9069,
"step": 55
},
{
"epoch": 0.14123581336696092,
"grad_norm": 8.858333587646484,
"learning_rate": 9.366286438529786e-06,
"loss": 1.8742,
"step": 56
},
{
"epoch": 0.1437578814627995,
"grad_norm": 8.489448547363281,
"learning_rate": 9.35361216730038e-06,
"loss": 1.9704,
"step": 57
},
{
"epoch": 0.14627994955863807,
"grad_norm": 8.65485668182373,
"learning_rate": 9.340937896070976e-06,
"loss": 1.8288,
"step": 58
},
{
"epoch": 0.14880201765447668,
"grad_norm": 9.034996032714844,
"learning_rate": 9.328263624841572e-06,
"loss": 1.8237,
"step": 59
},
{
"epoch": 0.15132408575031525,
"grad_norm": 8.894627571105957,
"learning_rate": 9.315589353612169e-06,
"loss": 1.9284,
"step": 60
},
{
"epoch": 0.15384615384615385,
"grad_norm": 9.375040054321289,
"learning_rate": 9.302915082382765e-06,
"loss": 1.8564,
"step": 61
},
{
"epoch": 0.15636822194199243,
"grad_norm": 10.312094688415527,
"learning_rate": 9.290240811153359e-06,
"loss": 1.7402,
"step": 62
},
{
"epoch": 0.15889029003783103,
"grad_norm": 9.399353981018066,
"learning_rate": 9.277566539923955e-06,
"loss": 1.9146,
"step": 63
},
{
"epoch": 0.1614123581336696,
"grad_norm": 9.056628227233887,
"learning_rate": 9.264892268694551e-06,
"loss": 1.8897,
"step": 64
},
{
"epoch": 0.16393442622950818,
"grad_norm": 9.38147258758545,
"learning_rate": 9.252217997465146e-06,
"loss": 1.8415,
"step": 65
},
{
"epoch": 0.1664564943253468,
"grad_norm": 9.386856079101562,
"learning_rate": 9.239543726235742e-06,
"loss": 1.982,
"step": 66
},
{
"epoch": 0.16897856242118536,
"grad_norm": 9.0509614944458,
"learning_rate": 9.226869455006338e-06,
"loss": 1.8456,
"step": 67
},
{
"epoch": 0.17150063051702397,
"grad_norm": 8.862478256225586,
"learning_rate": 9.214195183776934e-06,
"loss": 1.8085,
"step": 68
},
{
"epoch": 0.17402269861286254,
"grad_norm": 9.258233070373535,
"learning_rate": 9.201520912547528e-06,
"loss": 1.8478,
"step": 69
},
{
"epoch": 0.17654476670870115,
"grad_norm": 9.156318664550781,
"learning_rate": 9.188846641318126e-06,
"loss": 1.748,
"step": 70
},
{
"epoch": 0.17906683480453972,
"grad_norm": 9.234468460083008,
"learning_rate": 9.17617237008872e-06,
"loss": 1.8946,
"step": 71
},
{
"epoch": 0.18158890290037832,
"grad_norm": 9.102885246276855,
"learning_rate": 9.163498098859315e-06,
"loss": 1.8383,
"step": 72
},
{
"epoch": 0.1841109709962169,
"grad_norm": 9.106884002685547,
"learning_rate": 9.150823827629913e-06,
"loss": 1.9243,
"step": 73
},
{
"epoch": 0.18663303909205547,
"grad_norm": 8.918400764465332,
"learning_rate": 9.138149556400507e-06,
"loss": 1.9136,
"step": 74
},
{
"epoch": 0.18915510718789408,
"grad_norm": 9.20316219329834,
"learning_rate": 9.125475285171103e-06,
"loss": 1.9757,
"step": 75
},
{
"epoch": 0.19167717528373265,
"grad_norm": 8.938888549804688,
"learning_rate": 9.1128010139417e-06,
"loss": 1.744,
"step": 76
},
{
"epoch": 0.19419924337957126,
"grad_norm": 8.884087562561035,
"learning_rate": 9.100126742712296e-06,
"loss": 1.741,
"step": 77
},
{
"epoch": 0.19672131147540983,
"grad_norm": 9.786199569702148,
"learning_rate": 9.08745247148289e-06,
"loss": 1.795,
"step": 78
},
{
"epoch": 0.19924337957124844,
"grad_norm": 8.94467830657959,
"learning_rate": 9.074778200253486e-06,
"loss": 1.6029,
"step": 79
},
{
"epoch": 0.201765447667087,
"grad_norm": 8.95161247253418,
"learning_rate": 9.062103929024082e-06,
"loss": 1.9906,
"step": 80
},
{
"epoch": 0.2042875157629256,
"grad_norm": 8.998520851135254,
"learning_rate": 9.049429657794677e-06,
"loss": 1.8235,
"step": 81
},
{
"epoch": 0.2068095838587642,
"grad_norm": 9.164076805114746,
"learning_rate": 9.036755386565273e-06,
"loss": 1.9275,
"step": 82
},
{
"epoch": 0.20933165195460277,
"grad_norm": 9.689983367919922,
"learning_rate": 9.024081115335869e-06,
"loss": 1.8506,
"step": 83
},
{
"epoch": 0.21185372005044137,
"grad_norm": 9.274272918701172,
"learning_rate": 9.011406844106465e-06,
"loss": 1.8702,
"step": 84
},
{
"epoch": 0.21437578814627994,
"grad_norm": 8.776298522949219,
"learning_rate": 8.998732572877061e-06,
"loss": 1.7139,
"step": 85
},
{
"epoch": 0.21689785624211855,
"grad_norm": 8.801532745361328,
"learning_rate": 8.986058301647655e-06,
"loss": 1.8459,
"step": 86
},
{
"epoch": 0.21941992433795712,
"grad_norm": 8.84094524383545,
"learning_rate": 8.973384030418252e-06,
"loss": 1.9022,
"step": 87
},
{
"epoch": 0.22194199243379573,
"grad_norm": 9.14400863647461,
"learning_rate": 8.960709759188848e-06,
"loss": 1.8897,
"step": 88
},
{
"epoch": 0.2244640605296343,
"grad_norm": 9.148355484008789,
"learning_rate": 8.948035487959444e-06,
"loss": 1.8187,
"step": 89
},
{
"epoch": 0.22698612862547288,
"grad_norm": 8.494791984558105,
"learning_rate": 8.935361216730038e-06,
"loss": 1.8459,
"step": 90
},
{
"epoch": 0.22950819672131148,
"grad_norm": 9.062163352966309,
"learning_rate": 8.922686945500634e-06,
"loss": 1.8613,
"step": 91
},
{
"epoch": 0.23203026481715006,
"grad_norm": 9.061888694763184,
"learning_rate": 8.91001267427123e-06,
"loss": 1.9857,
"step": 92
},
{
"epoch": 0.23455233291298866,
"grad_norm": 10.139209747314453,
"learning_rate": 8.897338403041825e-06,
"loss": 1.9318,
"step": 93
},
{
"epoch": 0.23707440100882723,
"grad_norm": 9.2800931930542,
"learning_rate": 8.884664131812421e-06,
"loss": 1.7709,
"step": 94
},
{
"epoch": 0.23959646910466584,
"grad_norm": 8.862195014953613,
"learning_rate": 8.871989860583017e-06,
"loss": 1.7987,
"step": 95
},
{
"epoch": 0.2421185372005044,
"grad_norm": 9.58297348022461,
"learning_rate": 8.859315589353613e-06,
"loss": 2.0442,
"step": 96
},
{
"epoch": 0.244640605296343,
"grad_norm": 9.38765811920166,
"learning_rate": 8.846641318124208e-06,
"loss": 1.8665,
"step": 97
},
{
"epoch": 0.2471626733921816,
"grad_norm": 9.039520263671875,
"learning_rate": 8.833967046894805e-06,
"loss": 1.8397,
"step": 98
},
{
"epoch": 0.24968474148802017,
"grad_norm": 8.83530330657959,
"learning_rate": 8.8212927756654e-06,
"loss": 1.7988,
"step": 99
},
{
"epoch": 0.25220680958385877,
"grad_norm": 8.552284240722656,
"learning_rate": 8.808618504435996e-06,
"loss": 1.7445,
"step": 100
},
{
"epoch": 0.25220680958385877,
"eval_loss": 1.821302890777588,
"eval_runtime": 22.4563,
"eval_samples_per_second": 31.394,
"eval_steps_per_second": 15.719,
"step": 100
},
{
"epoch": 0.2547288776796974,
"grad_norm": 9.627294540405273,
"learning_rate": 8.795944233206592e-06,
"loss": 1.8091,
"step": 101
},
{
"epoch": 0.2572509457755359,
"grad_norm": 8.704631805419922,
"learning_rate": 8.783269961977186e-06,
"loss": 2.0544,
"step": 102
},
{
"epoch": 0.2597730138713745,
"grad_norm": 8.846882820129395,
"learning_rate": 8.770595690747782e-06,
"loss": 1.8539,
"step": 103
},
{
"epoch": 0.26229508196721313,
"grad_norm": 8.313948631286621,
"learning_rate": 8.757921419518379e-06,
"loss": 1.6635,
"step": 104
},
{
"epoch": 0.2648171500630517,
"grad_norm": 8.77181625366211,
"learning_rate": 8.745247148288975e-06,
"loss": 1.8712,
"step": 105
},
{
"epoch": 0.2673392181588903,
"grad_norm": 8.449075698852539,
"learning_rate": 8.732572877059569e-06,
"loss": 1.7943,
"step": 106
},
{
"epoch": 0.2698612862547289,
"grad_norm": 9.596981048583984,
"learning_rate": 8.719898605830165e-06,
"loss": 2.0333,
"step": 107
},
{
"epoch": 0.2723833543505675,
"grad_norm": 8.669624328613281,
"learning_rate": 8.707224334600761e-06,
"loss": 1.7816,
"step": 108
},
{
"epoch": 0.27490542244640603,
"grad_norm": 9.708998680114746,
"learning_rate": 8.694550063371356e-06,
"loss": 1.9616,
"step": 109
},
{
"epoch": 0.27742749054224464,
"grad_norm": 8.8702974319458,
"learning_rate": 8.681875792141954e-06,
"loss": 1.9119,
"step": 110
},
{
"epoch": 0.27994955863808324,
"grad_norm": 9.147343635559082,
"learning_rate": 8.669201520912548e-06,
"loss": 1.8413,
"step": 111
},
{
"epoch": 0.28247162673392184,
"grad_norm": 8.951756477355957,
"learning_rate": 8.656527249683144e-06,
"loss": 1.8813,
"step": 112
},
{
"epoch": 0.2849936948297604,
"grad_norm": 9.136735916137695,
"learning_rate": 8.64385297845374e-06,
"loss": 1.7765,
"step": 113
},
{
"epoch": 0.287515762925599,
"grad_norm": 9.53905963897705,
"learning_rate": 8.631178707224336e-06,
"loss": 1.7704,
"step": 114
},
{
"epoch": 0.2900378310214376,
"grad_norm": 8.893516540527344,
"learning_rate": 8.61850443599493e-06,
"loss": 1.6198,
"step": 115
},
{
"epoch": 0.29255989911727615,
"grad_norm": 8.778462409973145,
"learning_rate": 8.605830164765527e-06,
"loss": 1.7663,
"step": 116
},
{
"epoch": 0.29508196721311475,
"grad_norm": 9.09292984008789,
"learning_rate": 8.593155893536123e-06,
"loss": 1.8273,
"step": 117
},
{
"epoch": 0.29760403530895335,
"grad_norm": 9.203009605407715,
"learning_rate": 8.580481622306717e-06,
"loss": 1.9456,
"step": 118
},
{
"epoch": 0.30012610340479196,
"grad_norm": 9.124825477600098,
"learning_rate": 8.567807351077313e-06,
"loss": 1.844,
"step": 119
},
{
"epoch": 0.3026481715006305,
"grad_norm": 9.237686157226562,
"learning_rate": 8.55513307984791e-06,
"loss": 1.7495,
"step": 120
},
{
"epoch": 0.3051702395964691,
"grad_norm": 9.535928726196289,
"learning_rate": 8.542458808618506e-06,
"loss": 1.828,
"step": 121
},
{
"epoch": 0.3076923076923077,
"grad_norm": 9.44102954864502,
"learning_rate": 8.5297845373891e-06,
"loss": 1.9785,
"step": 122
},
{
"epoch": 0.31021437578814626,
"grad_norm": 9.092142105102539,
"learning_rate": 8.517110266159696e-06,
"loss": 1.7611,
"step": 123
},
{
"epoch": 0.31273644388398486,
"grad_norm": 9.274849891662598,
"learning_rate": 8.504435994930292e-06,
"loss": 1.7283,
"step": 124
},
{
"epoch": 0.31525851197982346,
"grad_norm": 8.317136764526367,
"learning_rate": 8.491761723700888e-06,
"loss": 1.8366,
"step": 125
},
{
"epoch": 0.31778058007566207,
"grad_norm": 8.939324378967285,
"learning_rate": 8.479087452471484e-06,
"loss": 1.878,
"step": 126
},
{
"epoch": 0.3203026481715006,
"grad_norm": 9.072879791259766,
"learning_rate": 8.466413181242079e-06,
"loss": 1.8724,
"step": 127
},
{
"epoch": 0.3228247162673392,
"grad_norm": 8.94404411315918,
"learning_rate": 8.453738910012675e-06,
"loss": 1.7007,
"step": 128
},
{
"epoch": 0.3253467843631778,
"grad_norm": 8.423967361450195,
"learning_rate": 8.441064638783271e-06,
"loss": 1.8021,
"step": 129
},
{
"epoch": 0.32786885245901637,
"grad_norm": 9.372537612915039,
"learning_rate": 8.428390367553865e-06,
"loss": 1.8622,
"step": 130
},
{
"epoch": 0.33039092055485497,
"grad_norm": 8.834014892578125,
"learning_rate": 8.415716096324462e-06,
"loss": 1.7708,
"step": 131
},
{
"epoch": 0.3329129886506936,
"grad_norm": 9.13171100616455,
"learning_rate": 8.403041825095058e-06,
"loss": 2.0644,
"step": 132
},
{
"epoch": 0.3354350567465322,
"grad_norm": 9.38616943359375,
"learning_rate": 8.390367553865654e-06,
"loss": 1.8012,
"step": 133
},
{
"epoch": 0.3379571248423707,
"grad_norm": 9.134305953979492,
"learning_rate": 8.377693282636248e-06,
"loss": 1.8579,
"step": 134
},
{
"epoch": 0.34047919293820933,
"grad_norm": 9.147695541381836,
"learning_rate": 8.365019011406846e-06,
"loss": 1.8561,
"step": 135
},
{
"epoch": 0.34300126103404793,
"grad_norm": 9.097079277038574,
"learning_rate": 8.35234474017744e-06,
"loss": 1.9241,
"step": 136
},
{
"epoch": 0.3455233291298865,
"grad_norm": 8.7761812210083,
"learning_rate": 8.339670468948035e-06,
"loss": 1.8393,
"step": 137
},
{
"epoch": 0.3480453972257251,
"grad_norm": 8.91004467010498,
"learning_rate": 8.326996197718633e-06,
"loss": 1.7533,
"step": 138
},
{
"epoch": 0.3505674653215637,
"grad_norm": 9.649863243103027,
"learning_rate": 8.314321926489227e-06,
"loss": 1.9777,
"step": 139
},
{
"epoch": 0.3530895334174023,
"grad_norm": 9.433012008666992,
"learning_rate": 8.301647655259823e-06,
"loss": 1.959,
"step": 140
},
{
"epoch": 0.35561160151324084,
"grad_norm": 9.400664329528809,
"learning_rate": 8.28897338403042e-06,
"loss": 1.7688,
"step": 141
},
{
"epoch": 0.35813366960907944,
"grad_norm": 8.890508651733398,
"learning_rate": 8.276299112801015e-06,
"loss": 1.7521,
"step": 142
},
{
"epoch": 0.36065573770491804,
"grad_norm": 9.65843391418457,
"learning_rate": 8.26362484157161e-06,
"loss": 1.9993,
"step": 143
},
{
"epoch": 0.36317780580075665,
"grad_norm": 8.980792045593262,
"learning_rate": 8.250950570342206e-06,
"loss": 1.7685,
"step": 144
},
{
"epoch": 0.3656998738965952,
"grad_norm": 8.810537338256836,
"learning_rate": 8.238276299112802e-06,
"loss": 1.8443,
"step": 145
},
{
"epoch": 0.3682219419924338,
"grad_norm": 9.117584228515625,
"learning_rate": 8.225602027883396e-06,
"loss": 1.9269,
"step": 146
},
{
"epoch": 0.3707440100882724,
"grad_norm": 9.197243690490723,
"learning_rate": 8.212927756653993e-06,
"loss": 1.8833,
"step": 147
},
{
"epoch": 0.37326607818411095,
"grad_norm": 9.297012329101562,
"learning_rate": 8.200253485424589e-06,
"loss": 1.8194,
"step": 148
},
{
"epoch": 0.37578814627994955,
"grad_norm": 8.982695579528809,
"learning_rate": 8.187579214195185e-06,
"loss": 1.8801,
"step": 149
},
{
"epoch": 0.37831021437578816,
"grad_norm": 8.55199909210205,
"learning_rate": 8.17490494296578e-06,
"loss": 1.7882,
"step": 150
},
{
"epoch": 0.37831021437578816,
"eval_loss": 1.801971435546875,
"eval_runtime": 22.4853,
"eval_samples_per_second": 31.354,
"eval_steps_per_second": 15.699,
"step": 150
},
{
"epoch": 0.38083228247162676,
"grad_norm": 8.808869361877441,
"learning_rate": 8.162230671736375e-06,
"loss": 1.7401,
"step": 151
},
{
"epoch": 0.3833543505674653,
"grad_norm": 9.283302307128906,
"learning_rate": 8.149556400506971e-06,
"loss": 1.9796,
"step": 152
},
{
"epoch": 0.3858764186633039,
"grad_norm": 9.003050804138184,
"learning_rate": 8.136882129277567e-06,
"loss": 1.6729,
"step": 153
},
{
"epoch": 0.3883984867591425,
"grad_norm": 9.130897521972656,
"learning_rate": 8.124207858048164e-06,
"loss": 1.9085,
"step": 154
},
{
"epoch": 0.39092055485498106,
"grad_norm": 8.871198654174805,
"learning_rate": 8.111533586818758e-06,
"loss": 1.9218,
"step": 155
},
{
"epoch": 0.39344262295081966,
"grad_norm": 8.295755386352539,
"learning_rate": 8.098859315589354e-06,
"loss": 1.7709,
"step": 156
},
{
"epoch": 0.39596469104665827,
"grad_norm": 9.15046501159668,
"learning_rate": 8.08618504435995e-06,
"loss": 1.9304,
"step": 157
},
{
"epoch": 0.39848675914249687,
"grad_norm": 8.887716293334961,
"learning_rate": 8.073510773130546e-06,
"loss": 1.8097,
"step": 158
},
{
"epoch": 0.4010088272383354,
"grad_norm": 8.1146821975708,
"learning_rate": 8.06083650190114e-06,
"loss": 1.7202,
"step": 159
},
{
"epoch": 0.403530895334174,
"grad_norm": 9.62702465057373,
"learning_rate": 8.048162230671737e-06,
"loss": 1.8547,
"step": 160
},
{
"epoch": 0.4060529634300126,
"grad_norm": 8.954533576965332,
"learning_rate": 8.035487959442333e-06,
"loss": 1.9418,
"step": 161
},
{
"epoch": 0.4085750315258512,
"grad_norm": 8.709664344787598,
"learning_rate": 8.022813688212927e-06,
"loss": 1.8355,
"step": 162
},
{
"epoch": 0.4110970996216898,
"grad_norm": 9.2684907913208,
"learning_rate": 8.010139416983525e-06,
"loss": 1.9908,
"step": 163
},
{
"epoch": 0.4136191677175284,
"grad_norm": 9.581305503845215,
"learning_rate": 7.99746514575412e-06,
"loss": 1.8155,
"step": 164
},
{
"epoch": 0.416141235813367,
"grad_norm": 9.040098190307617,
"learning_rate": 7.984790874524716e-06,
"loss": 1.8591,
"step": 165
},
{
"epoch": 0.41866330390920553,
"grad_norm": 9.17188549041748,
"learning_rate": 7.972116603295312e-06,
"loss": 1.8332,
"step": 166
},
{
"epoch": 0.42118537200504413,
"grad_norm": 9.190821647644043,
"learning_rate": 7.959442332065906e-06,
"loss": 1.8488,
"step": 167
},
{
"epoch": 0.42370744010088274,
"grad_norm": 9.045573234558105,
"learning_rate": 7.946768060836502e-06,
"loss": 1.7428,
"step": 168
},
{
"epoch": 0.4262295081967213,
"grad_norm": 8.98148250579834,
"learning_rate": 7.934093789607098e-06,
"loss": 1.965,
"step": 169
},
{
"epoch": 0.4287515762925599,
"grad_norm": 8.625720024108887,
"learning_rate": 7.921419518377694e-06,
"loss": 1.8538,
"step": 170
},
{
"epoch": 0.4312736443883985,
"grad_norm": 8.84864330291748,
"learning_rate": 7.908745247148289e-06,
"loss": 1.7758,
"step": 171
},
{
"epoch": 0.4337957124842371,
"grad_norm": 9.253456115722656,
"learning_rate": 7.896070975918885e-06,
"loss": 1.7754,
"step": 172
},
{
"epoch": 0.43631778058007564,
"grad_norm": 9.059581756591797,
"learning_rate": 7.883396704689481e-06,
"loss": 1.9926,
"step": 173
},
{
"epoch": 0.43883984867591425,
"grad_norm": 8.904810905456543,
"learning_rate": 7.870722433460076e-06,
"loss": 1.7971,
"step": 174
},
{
"epoch": 0.44136191677175285,
"grad_norm": 8.4295654296875,
"learning_rate": 7.858048162230673e-06,
"loss": 1.7947,
"step": 175
},
{
"epoch": 0.44388398486759145,
"grad_norm": 8.664776802062988,
"learning_rate": 7.845373891001268e-06,
"loss": 1.9424,
"step": 176
},
{
"epoch": 0.44640605296343,
"grad_norm": 9.025026321411133,
"learning_rate": 7.832699619771864e-06,
"loss": 1.8143,
"step": 177
},
{
"epoch": 0.4489281210592686,
"grad_norm": 8.458661079406738,
"learning_rate": 7.82002534854246e-06,
"loss": 1.7291,
"step": 178
},
{
"epoch": 0.4514501891551072,
"grad_norm": 8.800137519836426,
"learning_rate": 7.807351077313056e-06,
"loss": 1.759,
"step": 179
},
{
"epoch": 0.45397225725094575,
"grad_norm": 8.654534339904785,
"learning_rate": 7.79467680608365e-06,
"loss": 2.0166,
"step": 180
},
{
"epoch": 0.45649432534678436,
"grad_norm": 9.417305946350098,
"learning_rate": 7.782002534854247e-06,
"loss": 1.9709,
"step": 181
},
{
"epoch": 0.45901639344262296,
"grad_norm": 8.89673137664795,
"learning_rate": 7.769328263624843e-06,
"loss": 1.8067,
"step": 182
},
{
"epoch": 0.46153846153846156,
"grad_norm": 8.633663177490234,
"learning_rate": 7.756653992395437e-06,
"loss": 1.8676,
"step": 183
},
{
"epoch": 0.4640605296343001,
"grad_norm": 9.134156227111816,
"learning_rate": 7.743979721166033e-06,
"loss": 1.857,
"step": 184
},
{
"epoch": 0.4665825977301387,
"grad_norm": 8.542975425720215,
"learning_rate": 7.73130544993663e-06,
"loss": 1.638,
"step": 185
},
{
"epoch": 0.4691046658259773,
"grad_norm": 8.729076385498047,
"learning_rate": 7.718631178707225e-06,
"loss": 1.7845,
"step": 186
},
{
"epoch": 0.47162673392181587,
"grad_norm": 8.95164680480957,
"learning_rate": 7.70595690747782e-06,
"loss": 1.8296,
"step": 187
},
{
"epoch": 0.47414880201765447,
"grad_norm": 9.210955619812012,
"learning_rate": 7.693282636248416e-06,
"loss": 1.7914,
"step": 188
},
{
"epoch": 0.4766708701134931,
"grad_norm": 9.148017883300781,
"learning_rate": 7.680608365019012e-06,
"loss": 1.6624,
"step": 189
},
{
"epoch": 0.4791929382093317,
"grad_norm": 8.401142120361328,
"learning_rate": 7.667934093789608e-06,
"loss": 1.691,
"step": 190
},
{
"epoch": 0.4817150063051702,
"grad_norm": 9.830410957336426,
"learning_rate": 7.655259822560204e-06,
"loss": 1.9906,
"step": 191
},
{
"epoch": 0.4842370744010088,
"grad_norm": 8.865063667297363,
"learning_rate": 7.642585551330799e-06,
"loss": 1.9455,
"step": 192
},
{
"epoch": 0.48675914249684743,
"grad_norm": 10.0823335647583,
"learning_rate": 7.629911280101395e-06,
"loss": 1.6741,
"step": 193
},
{
"epoch": 0.489281210592686,
"grad_norm": 9.399166107177734,
"learning_rate": 7.617237008871991e-06,
"loss": 1.8719,
"step": 194
},
{
"epoch": 0.4918032786885246,
"grad_norm": 9.091114044189453,
"learning_rate": 7.604562737642585e-06,
"loss": 2.0057,
"step": 195
},
{
"epoch": 0.4943253467843632,
"grad_norm": 9.053544044494629,
"learning_rate": 7.591888466413182e-06,
"loss": 2.0169,
"step": 196
},
{
"epoch": 0.4968474148802018,
"grad_norm": 8.5532808303833,
"learning_rate": 7.5792141951837775e-06,
"loss": 1.8269,
"step": 197
},
{
"epoch": 0.49936948297604034,
"grad_norm": 8.772011756896973,
"learning_rate": 7.566539923954374e-06,
"loss": 1.7108,
"step": 198
},
{
"epoch": 0.501891551071879,
"grad_norm": 9.473034858703613,
"learning_rate": 7.553865652724969e-06,
"loss": 1.8995,
"step": 199
},
{
"epoch": 0.5044136191677175,
"grad_norm": 9.129395484924316,
"learning_rate": 7.541191381495565e-06,
"loss": 1.8357,
"step": 200
},
{
"epoch": 0.5044136191677175,
"eval_loss": 1.7911782264709473,
"eval_runtime": 22.4856,
"eval_samples_per_second": 31.353,
"eval_steps_per_second": 15.699,
"step": 200
},
{
"epoch": 0.5069356872635561,
"grad_norm": 9.366947174072266,
"learning_rate": 7.52851711026616e-06,
"loss": 1.7247,
"step": 201
},
{
"epoch": 0.5094577553593947,
"grad_norm": 9.029621124267578,
"learning_rate": 7.5158428390367555e-06,
"loss": 1.9187,
"step": 202
},
{
"epoch": 0.5119798234552333,
"grad_norm": 8.75687026977539,
"learning_rate": 7.503168567807352e-06,
"loss": 1.8674,
"step": 203
},
{
"epoch": 0.5145018915510718,
"grad_norm": 8.900492668151855,
"learning_rate": 7.490494296577947e-06,
"loss": 1.8799,
"step": 204
},
{
"epoch": 0.5170239596469105,
"grad_norm": 9.444570541381836,
"learning_rate": 7.477820025348543e-06,
"loss": 1.8788,
"step": 205
},
{
"epoch": 0.519546027742749,
"grad_norm": 8.889688491821289,
"learning_rate": 7.465145754119138e-06,
"loss": 1.9666,
"step": 206
},
{
"epoch": 0.5220680958385876,
"grad_norm": 8.494430541992188,
"learning_rate": 7.452471482889735e-06,
"loss": 1.7426,
"step": 207
},
{
"epoch": 0.5245901639344263,
"grad_norm": 9.225420951843262,
"learning_rate": 7.4397972116603304e-06,
"loss": 1.7908,
"step": 208
},
{
"epoch": 0.5271122320302648,
"grad_norm": 8.304360389709473,
"learning_rate": 7.427122940430926e-06,
"loss": 1.6749,
"step": 209
},
{
"epoch": 0.5296343001261034,
"grad_norm": 8.81341552734375,
"learning_rate": 7.414448669201522e-06,
"loss": 1.9377,
"step": 210
},
{
"epoch": 0.532156368221942,
"grad_norm": 8.664180755615234,
"learning_rate": 7.401774397972117e-06,
"loss": 1.7779,
"step": 211
},
{
"epoch": 0.5346784363177806,
"grad_norm": 8.888455390930176,
"learning_rate": 7.389100126742713e-06,
"loss": 1.956,
"step": 212
},
{
"epoch": 0.5372005044136192,
"grad_norm": 8.316351890563965,
"learning_rate": 7.376425855513308e-06,
"loss": 1.7736,
"step": 213
},
{
"epoch": 0.5397225725094578,
"grad_norm": 9.542658805847168,
"learning_rate": 7.3637515842839045e-06,
"loss": 1.8532,
"step": 214
},
{
"epoch": 0.5422446406052963,
"grad_norm": 9.170520782470703,
"learning_rate": 7.3510773130545e-06,
"loss": 1.8865,
"step": 215
},
{
"epoch": 0.544766708701135,
"grad_norm": 9.351484298706055,
"learning_rate": 7.338403041825095e-06,
"loss": 1.8796,
"step": 216
},
{
"epoch": 0.5472887767969735,
"grad_norm": 9.406367301940918,
"learning_rate": 7.325728770595691e-06,
"loss": 1.8942,
"step": 217
},
{
"epoch": 0.5498108448928121,
"grad_norm": 8.844432830810547,
"learning_rate": 7.313054499366286e-06,
"loss": 1.8349,
"step": 218
},
{
"epoch": 0.5523329129886507,
"grad_norm": 9.533503532409668,
"learning_rate": 7.300380228136883e-06,
"loss": 1.957,
"step": 219
},
{
"epoch": 0.5548549810844893,
"grad_norm": 8.604388236999512,
"learning_rate": 7.287705956907478e-06,
"loss": 1.7672,
"step": 220
},
{
"epoch": 0.5573770491803278,
"grad_norm": 9.03526496887207,
"learning_rate": 7.275031685678075e-06,
"loss": 1.8653,
"step": 221
},
{
"epoch": 0.5598991172761665,
"grad_norm": 9.044580459594727,
"learning_rate": 7.26235741444867e-06,
"loss": 1.9083,
"step": 222
},
{
"epoch": 0.562421185372005,
"grad_norm": 8.949540138244629,
"learning_rate": 7.249683143219266e-06,
"loss": 1.6617,
"step": 223
},
{
"epoch": 0.5649432534678437,
"grad_norm": 9.074623107910156,
"learning_rate": 7.237008871989861e-06,
"loss": 1.8499,
"step": 224
},
{
"epoch": 0.5674653215636822,
"grad_norm": 8.888490676879883,
"learning_rate": 7.224334600760457e-06,
"loss": 1.6527,
"step": 225
},
{
"epoch": 0.5699873896595208,
"grad_norm": 9.051539421081543,
"learning_rate": 7.211660329531053e-06,
"loss": 1.8038,
"step": 226
},
{
"epoch": 0.5725094577553594,
"grad_norm": 8.369515419006348,
"learning_rate": 7.198986058301648e-06,
"loss": 1.8563,
"step": 227
},
{
"epoch": 0.575031525851198,
"grad_norm": 8.217233657836914,
"learning_rate": 7.186311787072244e-06,
"loss": 1.6532,
"step": 228
},
{
"epoch": 0.5775535939470365,
"grad_norm": 8.884720802307129,
"learning_rate": 7.173637515842839e-06,
"loss": 1.8103,
"step": 229
},
{
"epoch": 0.5800756620428752,
"grad_norm": 9.489113807678223,
"learning_rate": 7.1609632446134354e-06,
"loss": 1.8983,
"step": 230
},
{
"epoch": 0.5825977301387137,
"grad_norm": 10.489038467407227,
"learning_rate": 7.148288973384031e-06,
"loss": 1.8123,
"step": 231
},
{
"epoch": 0.5851197982345523,
"grad_norm": 8.364508628845215,
"learning_rate": 7.135614702154626e-06,
"loss": 1.9231,
"step": 232
},
{
"epoch": 0.587641866330391,
"grad_norm": 10.242339134216309,
"learning_rate": 7.122940430925223e-06,
"loss": 1.8356,
"step": 233
},
{
"epoch": 0.5901639344262295,
"grad_norm": 8.08353042602539,
"learning_rate": 7.110266159695818e-06,
"loss": 1.6703,
"step": 234
},
{
"epoch": 0.592686002522068,
"grad_norm": 9.348738670349121,
"learning_rate": 7.097591888466414e-06,
"loss": 1.7144,
"step": 235
},
{
"epoch": 0.5952080706179067,
"grad_norm": 9.00921630859375,
"learning_rate": 7.0849176172370095e-06,
"loss": 1.6271,
"step": 236
},
{
"epoch": 0.5977301387137453,
"grad_norm": 9.098313331604004,
"learning_rate": 7.072243346007606e-06,
"loss": 1.8377,
"step": 237
},
{
"epoch": 0.6002522068095839,
"grad_norm": 8.487982749938965,
"learning_rate": 7.059569074778201e-06,
"loss": 1.7231,
"step": 238
},
{
"epoch": 0.6027742749054225,
"grad_norm": 8.85170841217041,
"learning_rate": 7.046894803548796e-06,
"loss": 1.7239,
"step": 239
},
{
"epoch": 0.605296343001261,
"grad_norm": 9.242439270019531,
"learning_rate": 7.034220532319392e-06,
"loss": 1.7778,
"step": 240
},
{
"epoch": 0.6078184110970997,
"grad_norm": 10.266282081604004,
"learning_rate": 7.0215462610899875e-06,
"loss": 1.8505,
"step": 241
},
{
"epoch": 0.6103404791929382,
"grad_norm": 10.174772262573242,
"learning_rate": 7.008871989860584e-06,
"loss": 1.822,
"step": 242
},
{
"epoch": 0.6128625472887768,
"grad_norm": 9.37380313873291,
"learning_rate": 6.996197718631179e-06,
"loss": 1.7181,
"step": 243
},
{
"epoch": 0.6153846153846154,
"grad_norm": 9.645342826843262,
"learning_rate": 6.983523447401776e-06,
"loss": 1.8322,
"step": 244
},
{
"epoch": 0.617906683480454,
"grad_norm": 8.987611770629883,
"learning_rate": 6.97084917617237e-06,
"loss": 1.8805,
"step": 245
},
{
"epoch": 0.6204287515762925,
"grad_norm": 9.18445110321045,
"learning_rate": 6.9581749049429655e-06,
"loss": 1.7114,
"step": 246
},
{
"epoch": 0.6229508196721312,
"grad_norm": 8.987384796142578,
"learning_rate": 6.9455006337135625e-06,
"loss": 1.869,
"step": 247
},
{
"epoch": 0.6254728877679697,
"grad_norm": 8.741730690002441,
"learning_rate": 6.932826362484158e-06,
"loss": 1.8521,
"step": 248
},
{
"epoch": 0.6279949558638083,
"grad_norm": 9.442428588867188,
"learning_rate": 6.920152091254754e-06,
"loss": 1.8787,
"step": 249
},
{
"epoch": 0.6305170239596469,
"grad_norm": 9.383081436157227,
"learning_rate": 6.907477820025349e-06,
"loss": 1.7819,
"step": 250
},
{
"epoch": 0.6305170239596469,
"eval_loss": 1.7835694551467896,
"eval_runtime": 22.5026,
"eval_samples_per_second": 31.33,
"eval_steps_per_second": 15.687,
"step": 250
},
{
"epoch": 0.6330390920554855,
"grad_norm": 8.477014541625977,
"learning_rate": 6.894803548795945e-06,
"loss": 1.7756,
"step": 251
},
{
"epoch": 0.6355611601513241,
"grad_norm": 8.9135160446167,
"learning_rate": 6.8821292775665405e-06,
"loss": 1.6981,
"step": 252
},
{
"epoch": 0.6380832282471627,
"grad_norm": 9.343244552612305,
"learning_rate": 6.869455006337136e-06,
"loss": 1.8793,
"step": 253
},
{
"epoch": 0.6406052963430012,
"grad_norm": 9.541474342346191,
"learning_rate": 6.856780735107732e-06,
"loss": 1.9366,
"step": 254
},
{
"epoch": 0.6431273644388399,
"grad_norm": 9.232076644897461,
"learning_rate": 6.844106463878327e-06,
"loss": 1.79,
"step": 255
},
{
"epoch": 0.6456494325346784,
"grad_norm": 9.20903205871582,
"learning_rate": 6.831432192648923e-06,
"loss": 1.7927,
"step": 256
},
{
"epoch": 0.648171500630517,
"grad_norm": 8.93044662475586,
"learning_rate": 6.8187579214195185e-06,
"loss": 1.8095,
"step": 257
},
{
"epoch": 0.6506935687263556,
"grad_norm": 8.670905113220215,
"learning_rate": 6.806083650190115e-06,
"loss": 1.6471,
"step": 258
},
{
"epoch": 0.6532156368221942,
"grad_norm": 8.664294242858887,
"learning_rate": 6.793409378960711e-06,
"loss": 1.9497,
"step": 259
},
{
"epoch": 0.6557377049180327,
"grad_norm": 9.337104797363281,
"learning_rate": 6.780735107731305e-06,
"loss": 1.7811,
"step": 260
},
{
"epoch": 0.6582597730138714,
"grad_norm": 8.13593864440918,
"learning_rate": 6.768060836501902e-06,
"loss": 1.6531,
"step": 261
},
{
"epoch": 0.6607818411097099,
"grad_norm": 9.000870704650879,
"learning_rate": 6.755386565272497e-06,
"loss": 1.7869,
"step": 262
},
{
"epoch": 0.6633039092055486,
"grad_norm": 8.675310134887695,
"learning_rate": 6.742712294043093e-06,
"loss": 1.7682,
"step": 263
},
{
"epoch": 0.6658259773013872,
"grad_norm": 8.915125846862793,
"learning_rate": 6.730038022813689e-06,
"loss": 1.7886,
"step": 264
},
{
"epoch": 0.6683480453972257,
"grad_norm": 8.760987281799316,
"learning_rate": 6.717363751584285e-06,
"loss": 1.6765,
"step": 265
},
{
"epoch": 0.6708701134930644,
"grad_norm": 9.88598918914795,
"learning_rate": 6.70468948035488e-06,
"loss": 1.7479,
"step": 266
},
{
"epoch": 0.6733921815889029,
"grad_norm": 8.675105094909668,
"learning_rate": 6.692015209125475e-06,
"loss": 1.7543,
"step": 267
},
{
"epoch": 0.6759142496847415,
"grad_norm": 9.642090797424316,
"learning_rate": 6.679340937896071e-06,
"loss": 1.9508,
"step": 268
},
{
"epoch": 0.6784363177805801,
"grad_norm": 9.55046272277832,
"learning_rate": 6.666666666666667e-06,
"loss": 1.7196,
"step": 269
},
{
"epoch": 0.6809583858764187,
"grad_norm": 10.080808639526367,
"learning_rate": 6.653992395437263e-06,
"loss": 1.7838,
"step": 270
},
{
"epoch": 0.6834804539722572,
"grad_norm": 9.57958698272705,
"learning_rate": 6.641318124207858e-06,
"loss": 1.849,
"step": 271
},
{
"epoch": 0.6860025220680959,
"grad_norm": 8.220699310302734,
"learning_rate": 6.628643852978455e-06,
"loss": 1.717,
"step": 272
},
{
"epoch": 0.6885245901639344,
"grad_norm": 9.084957122802734,
"learning_rate": 6.61596958174905e-06,
"loss": 1.8759,
"step": 273
},
{
"epoch": 0.691046658259773,
"grad_norm": 9.193656921386719,
"learning_rate": 6.6032953105196455e-06,
"loss": 1.8918,
"step": 274
},
{
"epoch": 0.6935687263556116,
"grad_norm": 9.222799301147461,
"learning_rate": 6.590621039290242e-06,
"loss": 1.899,
"step": 275
},
{
"epoch": 0.6960907944514502,
"grad_norm": 9.636636734008789,
"learning_rate": 6.577946768060837e-06,
"loss": 1.8116,
"step": 276
},
{
"epoch": 0.6986128625472888,
"grad_norm": 9.802331924438477,
"learning_rate": 6.565272496831433e-06,
"loss": 1.9349,
"step": 277
},
{
"epoch": 0.7011349306431274,
"grad_norm": 9.755422592163086,
"learning_rate": 6.552598225602028e-06,
"loss": 1.8527,
"step": 278
},
{
"epoch": 0.7036569987389659,
"grad_norm": 10.284688949584961,
"learning_rate": 6.539923954372624e-06,
"loss": 1.9025,
"step": 279
},
{
"epoch": 0.7061790668348046,
"grad_norm": 9.143197059631348,
"learning_rate": 6.52724968314322e-06,
"loss": 1.7448,
"step": 280
},
{
"epoch": 0.7087011349306431,
"grad_norm": 9.599867820739746,
"learning_rate": 6.514575411913816e-06,
"loss": 1.8387,
"step": 281
},
{
"epoch": 0.7112232030264817,
"grad_norm": 8.4711275100708,
"learning_rate": 6.501901140684411e-06,
"loss": 1.6271,
"step": 282
},
{
"epoch": 0.7137452711223203,
"grad_norm": 8.960174560546875,
"learning_rate": 6.489226869455006e-06,
"loss": 1.9262,
"step": 283
},
{
"epoch": 0.7162673392181589,
"grad_norm": 9.175895690917969,
"learning_rate": 6.476552598225603e-06,
"loss": 1.8258,
"step": 284
},
{
"epoch": 0.7187894073139974,
"grad_norm": 8.494986534118652,
"learning_rate": 6.4638783269961976e-06,
"loss": 1.8624,
"step": 285
},
{
"epoch": 0.7213114754098361,
"grad_norm": 8.861451148986816,
"learning_rate": 6.4512040557667945e-06,
"loss": 1.7639,
"step": 286
},
{
"epoch": 0.7238335435056746,
"grad_norm": 9.249289512634277,
"learning_rate": 6.43852978453739e-06,
"loss": 1.8052,
"step": 287
},
{
"epoch": 0.7263556116015133,
"grad_norm": 9.551322937011719,
"learning_rate": 6.425855513307986e-06,
"loss": 1.888,
"step": 288
},
{
"epoch": 0.7288776796973518,
"grad_norm": 7.97605037689209,
"learning_rate": 6.413181242078581e-06,
"loss": 1.7407,
"step": 289
},
{
"epoch": 0.7313997477931904,
"grad_norm": 8.704668998718262,
"learning_rate": 6.400506970849176e-06,
"loss": 1.6289,
"step": 290
},
{
"epoch": 0.733921815889029,
"grad_norm": 9.57497787475586,
"learning_rate": 6.3878326996197725e-06,
"loss": 1.7025,
"step": 291
},
{
"epoch": 0.7364438839848676,
"grad_norm": 9.079139709472656,
"learning_rate": 6.375158428390368e-06,
"loss": 1.6973,
"step": 292
},
{
"epoch": 0.7389659520807061,
"grad_norm": 8.671896934509277,
"learning_rate": 6.362484157160964e-06,
"loss": 1.691,
"step": 293
},
{
"epoch": 0.7414880201765448,
"grad_norm": 9.564823150634766,
"learning_rate": 6.349809885931559e-06,
"loss": 1.8636,
"step": 294
},
{
"epoch": 0.7440100882723834,
"grad_norm": 8.475247383117676,
"learning_rate": 6.337135614702155e-06,
"loss": 1.8106,
"step": 295
},
{
"epoch": 0.7465321563682219,
"grad_norm": 9.372197151184082,
"learning_rate": 6.3244613434727505e-06,
"loss": 1.8129,
"step": 296
},
{
"epoch": 0.7490542244640606,
"grad_norm": 9.042529106140137,
"learning_rate": 6.311787072243346e-06,
"loss": 1.8301,
"step": 297
},
{
"epoch": 0.7515762925598991,
"grad_norm": 9.25075912475586,
"learning_rate": 6.299112801013943e-06,
"loss": 1.9945,
"step": 298
},
{
"epoch": 0.7540983606557377,
"grad_norm": 9.301259994506836,
"learning_rate": 6.286438529784538e-06,
"loss": 1.8318,
"step": 299
},
{
"epoch": 0.7566204287515763,
"grad_norm": 9.111929893493652,
"learning_rate": 6.273764258555134e-06,
"loss": 1.79,
"step": 300
},
{
"epoch": 0.7566204287515763,
"eval_loss": 1.773391842842102,
"eval_runtime": 22.5092,
"eval_samples_per_second": 31.321,
"eval_steps_per_second": 15.683,
"step": 300
},
{
"epoch": 0.7591424968474149,
"grad_norm": 9.18808364868164,
"learning_rate": 6.261089987325729e-06,
"loss": 1.6887,
"step": 301
},
{
"epoch": 0.7616645649432535,
"grad_norm": 8.52299976348877,
"learning_rate": 6.2484157160963254e-06,
"loss": 1.7068,
"step": 302
},
{
"epoch": 0.7641866330390921,
"grad_norm": 9.556783676147461,
"learning_rate": 6.235741444866921e-06,
"loss": 1.8265,
"step": 303
},
{
"epoch": 0.7667087011349306,
"grad_norm": 8.4852294921875,
"learning_rate": 6.223067173637516e-06,
"loss": 1.7148,
"step": 304
},
{
"epoch": 0.7692307692307693,
"grad_norm": 9.724072456359863,
"learning_rate": 6.210392902408112e-06,
"loss": 1.7973,
"step": 305
},
{
"epoch": 0.7717528373266078,
"grad_norm": 9.087509155273438,
"learning_rate": 6.197718631178707e-06,
"loss": 1.8091,
"step": 306
},
{
"epoch": 0.7742749054224464,
"grad_norm": 8.920263290405273,
"learning_rate": 6.1850443599493034e-06,
"loss": 1.7686,
"step": 307
},
{
"epoch": 0.776796973518285,
"grad_norm": 8.707300186157227,
"learning_rate": 6.172370088719899e-06,
"loss": 1.7653,
"step": 308
},
{
"epoch": 0.7793190416141236,
"grad_norm": 9.387958526611328,
"learning_rate": 6.159695817490496e-06,
"loss": 1.9009,
"step": 309
},
{
"epoch": 0.7818411097099621,
"grad_norm": 9.361507415771484,
"learning_rate": 6.147021546261091e-06,
"loss": 1.8205,
"step": 310
},
{
"epoch": 0.7843631778058008,
"grad_norm": 8.466252326965332,
"learning_rate": 6.134347275031685e-06,
"loss": 1.657,
"step": 311
},
{
"epoch": 0.7868852459016393,
"grad_norm": 8.961893081665039,
"learning_rate": 6.121673003802282e-06,
"loss": 1.6343,
"step": 312
},
{
"epoch": 0.7894073139974779,
"grad_norm": 9.126177787780762,
"learning_rate": 6.1089987325728775e-06,
"loss": 1.8017,
"step": 313
},
{
"epoch": 0.7919293820933165,
"grad_norm": 9.051336288452148,
"learning_rate": 6.096324461343474e-06,
"loss": 1.8121,
"step": 314
},
{
"epoch": 0.7944514501891551,
"grad_norm": 9.269831657409668,
"learning_rate": 6.083650190114069e-06,
"loss": 1.9142,
"step": 315
},
{
"epoch": 0.7969735182849937,
"grad_norm": 9.106327056884766,
"learning_rate": 6.070975918884665e-06,
"loss": 1.8408,
"step": 316
},
{
"epoch": 0.7994955863808323,
"grad_norm": 8.638962745666504,
"learning_rate": 6.05830164765526e-06,
"loss": 1.8278,
"step": 317
},
{
"epoch": 0.8020176544766708,
"grad_norm": 8.961545944213867,
"learning_rate": 6.0456273764258555e-06,
"loss": 1.7788,
"step": 318
},
{
"epoch": 0.8045397225725095,
"grad_norm": 8.860641479492188,
"learning_rate": 6.032953105196452e-06,
"loss": 1.7679,
"step": 319
},
{
"epoch": 0.807061790668348,
"grad_norm": 9.001996040344238,
"learning_rate": 6.020278833967047e-06,
"loss": 1.825,
"step": 320
},
{
"epoch": 0.8095838587641866,
"grad_norm": 8.475961685180664,
"learning_rate": 6.007604562737643e-06,
"loss": 1.8415,
"step": 321
},
{
"epoch": 0.8121059268600253,
"grad_norm": 9.001214027404785,
"learning_rate": 5.994930291508238e-06,
"loss": 1.8361,
"step": 322
},
{
"epoch": 0.8146279949558638,
"grad_norm": 9.263764381408691,
"learning_rate": 5.982256020278835e-06,
"loss": 1.8687,
"step": 323
},
{
"epoch": 0.8171500630517023,
"grad_norm": 8.717523574829102,
"learning_rate": 5.9695817490494305e-06,
"loss": 1.7933,
"step": 324
},
{
"epoch": 0.819672131147541,
"grad_norm": 9.021601676940918,
"learning_rate": 5.956907477820026e-06,
"loss": 1.7985,
"step": 325
},
{
"epoch": 0.8221941992433796,
"grad_norm": 10.068187713623047,
"learning_rate": 5.944233206590622e-06,
"loss": 1.7753,
"step": 326
},
{
"epoch": 0.8247162673392182,
"grad_norm": 8.52224349975586,
"learning_rate": 5.931558935361217e-06,
"loss": 1.8362,
"step": 327
},
{
"epoch": 0.8272383354350568,
"grad_norm": 8.305383682250977,
"learning_rate": 5.918884664131813e-06,
"loss": 1.7546,
"step": 328
},
{
"epoch": 0.8297604035308953,
"grad_norm": 9.338051795959473,
"learning_rate": 5.9062103929024085e-06,
"loss": 1.9501,
"step": 329
},
{
"epoch": 0.832282471626734,
"grad_norm": 8.662667274475098,
"learning_rate": 5.8935361216730046e-06,
"loss": 1.7911,
"step": 330
},
{
"epoch": 0.8348045397225725,
"grad_norm": 9.117914199829102,
"learning_rate": 5.8808618504436e-06,
"loss": 1.9963,
"step": 331
},
{
"epoch": 0.8373266078184111,
"grad_norm": 8.750685691833496,
"learning_rate": 5.868187579214195e-06,
"loss": 1.7431,
"step": 332
},
{
"epoch": 0.8398486759142497,
"grad_norm": 9.731898307800293,
"learning_rate": 5.855513307984791e-06,
"loss": 1.7908,
"step": 333
},
{
"epoch": 0.8423707440100883,
"grad_norm": 8.483211517333984,
"learning_rate": 5.8428390367553864e-06,
"loss": 1.9832,
"step": 334
},
{
"epoch": 0.8448928121059268,
"grad_norm": 8.711883544921875,
"learning_rate": 5.830164765525983e-06,
"loss": 1.7276,
"step": 335
},
{
"epoch": 0.8474148802017655,
"grad_norm": 9.403569221496582,
"learning_rate": 5.817490494296578e-06,
"loss": 1.7779,
"step": 336
},
{
"epoch": 0.849936948297604,
"grad_norm": 9.861798286437988,
"learning_rate": 5.804816223067175e-06,
"loss": 1.8812,
"step": 337
},
{
"epoch": 0.8524590163934426,
"grad_norm": 9.074817657470703,
"learning_rate": 5.79214195183777e-06,
"loss": 1.814,
"step": 338
},
{
"epoch": 0.8549810844892812,
"grad_norm": 9.062159538269043,
"learning_rate": 5.779467680608365e-06,
"loss": 1.6469,
"step": 339
},
{
"epoch": 0.8575031525851198,
"grad_norm": 8.966131210327148,
"learning_rate": 5.766793409378961e-06,
"loss": 1.8023,
"step": 340
},
{
"epoch": 0.8600252206809584,
"grad_norm": 9.410212516784668,
"learning_rate": 5.754119138149557e-06,
"loss": 1.872,
"step": 341
},
{
"epoch": 0.862547288776797,
"grad_norm": 8.417155265808105,
"learning_rate": 5.741444866920153e-06,
"loss": 1.7251,
"step": 342
},
{
"epoch": 0.8650693568726355,
"grad_norm": 9.311077117919922,
"learning_rate": 5.728770595690748e-06,
"loss": 1.7222,
"step": 343
},
{
"epoch": 0.8675914249684742,
"grad_norm": 8.766838073730469,
"learning_rate": 5.716096324461344e-06,
"loss": 1.711,
"step": 344
},
{
"epoch": 0.8701134930643127,
"grad_norm": 9.32026481628418,
"learning_rate": 5.703422053231939e-06,
"loss": 1.9097,
"step": 345
},
{
"epoch": 0.8726355611601513,
"grad_norm": 9.121573448181152,
"learning_rate": 5.6907477820025355e-06,
"loss": 1.7767,
"step": 346
},
{
"epoch": 0.8751576292559899,
"grad_norm": 9.25794792175293,
"learning_rate": 5.678073510773131e-06,
"loss": 1.8932,
"step": 347
},
{
"epoch": 0.8776796973518285,
"grad_norm": 8.6607027053833,
"learning_rate": 5.665399239543726e-06,
"loss": 1.7855,
"step": 348
},
{
"epoch": 0.880201765447667,
"grad_norm": 8.80229377746582,
"learning_rate": 5.652724968314323e-06,
"loss": 1.6629,
"step": 349
},
{
"epoch": 0.8827238335435057,
"grad_norm": 8.451213836669922,
"learning_rate": 5.640050697084918e-06,
"loss": 1.8383,
"step": 350
},
{
"epoch": 0.8827238335435057,
"eval_loss": 1.7666597366333008,
"eval_runtime": 22.5285,
"eval_samples_per_second": 31.294,
"eval_steps_per_second": 15.669,
"step": 350
},
{
"epoch": 0.8852459016393442,
"grad_norm": 8.855935096740723,
"learning_rate": 5.627376425855514e-06,
"loss": 1.8248,
"step": 351
},
{
"epoch": 0.8877679697351829,
"grad_norm": 8.918074607849121,
"learning_rate": 5.61470215462611e-06,
"loss": 1.8095,
"step": 352
},
{
"epoch": 0.8902900378310215,
"grad_norm": 8.412212371826172,
"learning_rate": 5.602027883396706e-06,
"loss": 1.7792,
"step": 353
},
{
"epoch": 0.89281210592686,
"grad_norm": 8.616189002990723,
"learning_rate": 5.589353612167301e-06,
"loss": 1.9303,
"step": 354
},
{
"epoch": 0.8953341740226987,
"grad_norm": 9.573508262634277,
"learning_rate": 5.576679340937896e-06,
"loss": 1.903,
"step": 355
},
{
"epoch": 0.8978562421185372,
"grad_norm": 9.231846809387207,
"learning_rate": 5.564005069708492e-06,
"loss": 1.9207,
"step": 356
},
{
"epoch": 0.9003783102143758,
"grad_norm": 8.668343544006348,
"learning_rate": 5.5513307984790876e-06,
"loss": 1.8209,
"step": 357
},
{
"epoch": 0.9029003783102144,
"grad_norm": 9.020340919494629,
"learning_rate": 5.538656527249684e-06,
"loss": 1.7936,
"step": 358
},
{
"epoch": 0.905422446406053,
"grad_norm": 9.167196273803711,
"learning_rate": 5.525982256020279e-06,
"loss": 1.8981,
"step": 359
},
{
"epoch": 0.9079445145018915,
"grad_norm": 8.988978385925293,
"learning_rate": 5.513307984790876e-06,
"loss": 1.6867,
"step": 360
},
{
"epoch": 0.9104665825977302,
"grad_norm": 9.246484756469727,
"learning_rate": 5.50063371356147e-06,
"loss": 1.9292,
"step": 361
},
{
"epoch": 0.9129886506935687,
"grad_norm": 9.017062187194824,
"learning_rate": 5.4879594423320656e-06,
"loss": 1.9438,
"step": 362
},
{
"epoch": 0.9155107187894073,
"grad_norm": 8.916227340698242,
"learning_rate": 5.4752851711026625e-06,
"loss": 1.6769,
"step": 363
},
{
"epoch": 0.9180327868852459,
"grad_norm": 8.565522193908691,
"learning_rate": 5.462610899873258e-06,
"loss": 1.7735,
"step": 364
},
{
"epoch": 0.9205548549810845,
"grad_norm": 9.010213851928711,
"learning_rate": 5.449936628643854e-06,
"loss": 1.834,
"step": 365
},
{
"epoch": 0.9230769230769231,
"grad_norm": 8.799229621887207,
"learning_rate": 5.437262357414449e-06,
"loss": 1.8073,
"step": 366
},
{
"epoch": 0.9255989911727617,
"grad_norm": 8.609127044677734,
"learning_rate": 5.424588086185045e-06,
"loss": 1.6314,
"step": 367
},
{
"epoch": 0.9281210592686002,
"grad_norm": 9.32305908203125,
"learning_rate": 5.4119138149556405e-06,
"loss": 1.7677,
"step": 368
},
{
"epoch": 0.9306431273644389,
"grad_norm": 8.93819808959961,
"learning_rate": 5.399239543726236e-06,
"loss": 1.8062,
"step": 369
},
{
"epoch": 0.9331651954602774,
"grad_norm": 9.007331848144531,
"learning_rate": 5.386565272496832e-06,
"loss": 1.7967,
"step": 370
},
{
"epoch": 0.935687263556116,
"grad_norm": 9.112802505493164,
"learning_rate": 5.373891001267427e-06,
"loss": 1.827,
"step": 371
},
{
"epoch": 0.9382093316519546,
"grad_norm": 8.801994323730469,
"learning_rate": 5.361216730038023e-06,
"loss": 1.8673,
"step": 372
},
{
"epoch": 0.9407313997477932,
"grad_norm": 9.644193649291992,
"learning_rate": 5.3485424588086185e-06,
"loss": 1.6999,
"step": 373
},
{
"epoch": 0.9432534678436317,
"grad_norm": 9.589875221252441,
"learning_rate": 5.3358681875792155e-06,
"loss": 1.8667,
"step": 374
},
{
"epoch": 0.9457755359394704,
"grad_norm": 9.18924617767334,
"learning_rate": 5.323193916349811e-06,
"loss": 1.9254,
"step": 375
},
{
"epoch": 0.9482976040353089,
"grad_norm": 8.787095069885254,
"learning_rate": 5.310519645120405e-06,
"loss": 1.8468,
"step": 376
},
{
"epoch": 0.9508196721311475,
"grad_norm": 8.947575569152832,
"learning_rate": 5.297845373891002e-06,
"loss": 2.0021,
"step": 377
},
{
"epoch": 0.9533417402269861,
"grad_norm": 9.039846420288086,
"learning_rate": 5.285171102661597e-06,
"loss": 1.5899,
"step": 378
},
{
"epoch": 0.9558638083228247,
"grad_norm": 8.660459518432617,
"learning_rate": 5.2724968314321934e-06,
"loss": 1.8402,
"step": 379
},
{
"epoch": 0.9583858764186634,
"grad_norm": 8.48667049407959,
"learning_rate": 5.259822560202789e-06,
"loss": 1.8095,
"step": 380
},
{
"epoch": 0.9609079445145019,
"grad_norm": 8.915818214416504,
"learning_rate": 5.247148288973385e-06,
"loss": 1.8222,
"step": 381
},
{
"epoch": 0.9634300126103404,
"grad_norm": 9.791091918945312,
"learning_rate": 5.23447401774398e-06,
"loss": 1.8119,
"step": 382
},
{
"epoch": 0.9659520807061791,
"grad_norm": 9.289512634277344,
"learning_rate": 5.221799746514575e-06,
"loss": 1.9832,
"step": 383
},
{
"epoch": 0.9684741488020177,
"grad_norm": 8.83728313446045,
"learning_rate": 5.2091254752851714e-06,
"loss": 1.7095,
"step": 384
},
{
"epoch": 0.9709962168978562,
"grad_norm": 8.655898094177246,
"learning_rate": 5.196451204055767e-06,
"loss": 1.7634,
"step": 385
},
{
"epoch": 0.9735182849936949,
"grad_norm": 9.05538558959961,
"learning_rate": 5.183776932826363e-06,
"loss": 1.9431,
"step": 386
},
{
"epoch": 0.9760403530895334,
"grad_norm": 9.3674898147583,
"learning_rate": 5.171102661596958e-06,
"loss": 1.7756,
"step": 387
},
{
"epoch": 0.978562421185372,
"grad_norm": 8.614623069763184,
"learning_rate": 5.158428390367555e-06,
"loss": 1.741,
"step": 388
},
{
"epoch": 0.9810844892812106,
"grad_norm": 8.469090461730957,
"learning_rate": 5.14575411913815e-06,
"loss": 1.7514,
"step": 389
},
{
"epoch": 0.9836065573770492,
"grad_norm": 8.436793327331543,
"learning_rate": 5.1330798479087455e-06,
"loss": 1.8312,
"step": 390
},
{
"epoch": 0.9861286254728878,
"grad_norm": 9.177275657653809,
"learning_rate": 5.120405576679342e-06,
"loss": 1.7916,
"step": 391
},
{
"epoch": 0.9886506935687264,
"grad_norm": 9.22571849822998,
"learning_rate": 5.107731305449937e-06,
"loss": 1.7274,
"step": 392
},
{
"epoch": 0.9911727616645649,
"grad_norm": 8.921821594238281,
"learning_rate": 5.095057034220533e-06,
"loss": 1.8486,
"step": 393
},
{
"epoch": 0.9936948297604036,
"grad_norm": 9.777151107788086,
"learning_rate": 5.082382762991128e-06,
"loss": 1.7962,
"step": 394
},
{
"epoch": 0.9962168978562421,
"grad_norm": 9.289339065551758,
"learning_rate": 5.069708491761724e-06,
"loss": 1.8634,
"step": 395
},
{
"epoch": 0.9987389659520807,
"grad_norm": 8.674428939819336,
"learning_rate": 5.05703422053232e-06,
"loss": 1.7491,
"step": 396
},
{
"epoch": 1.0,
"grad_norm": 11.861848831176758,
"learning_rate": 5.044359949302915e-06,
"loss": 1.7503,
"step": 397
},
{
"epoch": 1.0025220680958387,
"grad_norm": 8.58899974822998,
"learning_rate": 5.031685678073511e-06,
"loss": 1.732,
"step": 398
},
{
"epoch": 1.005044136191677,
"grad_norm": 8.345893859863281,
"learning_rate": 5.019011406844106e-06,
"loss": 1.5869,
"step": 399
},
{
"epoch": 1.0075662042875158,
"grad_norm": 8.831095695495605,
"learning_rate": 5.006337135614703e-06,
"loss": 1.7195,
"step": 400
},
{
"epoch": 1.0075662042875158,
"eval_loss": 1.7611252069473267,
"eval_runtime": 22.4939,
"eval_samples_per_second": 31.342,
"eval_steps_per_second": 15.693,
"step": 400
}
],
"logging_steps": 1,
"max_steps": 794,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2153917719426048.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}