Devy1's picture
Upload checkpoint Qwen2.5-Coder-CONTROL-checkpoints_multi_language_2k-1.5B-Base-2 at epoch 2
111fbb8 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 268,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007511737089201878,
"grad_norm": 1.5546875,
"learning_rate": 5e-05,
"loss": 0.7059,
"step": 1
},
{
"epoch": 0.015023474178403756,
"grad_norm": 2.046875,
"learning_rate": 4.996268656716418e-05,
"loss": 0.8614,
"step": 2
},
{
"epoch": 0.022535211267605635,
"grad_norm": 14.375,
"learning_rate": 4.992537313432836e-05,
"loss": 0.799,
"step": 3
},
{
"epoch": 0.03004694835680751,
"grad_norm": 2.421875,
"learning_rate": 4.988805970149254e-05,
"loss": 0.7599,
"step": 4
},
{
"epoch": 0.03755868544600939,
"grad_norm": 1.7890625,
"learning_rate": 4.985074626865672e-05,
"loss": 0.7254,
"step": 5
},
{
"epoch": 0.04507042253521127,
"grad_norm": 1.4375,
"learning_rate": 4.98134328358209e-05,
"loss": 0.7982,
"step": 6
},
{
"epoch": 0.05258215962441314,
"grad_norm": 1.546875,
"learning_rate": 4.977611940298508e-05,
"loss": 0.7192,
"step": 7
},
{
"epoch": 0.06009389671361502,
"grad_norm": 2.71875,
"learning_rate": 4.973880597014925e-05,
"loss": 0.8359,
"step": 8
},
{
"epoch": 0.0676056338028169,
"grad_norm": 1.4140625,
"learning_rate": 4.9701492537313436e-05,
"loss": 0.6135,
"step": 9
},
{
"epoch": 0.07511737089201878,
"grad_norm": 3.96875,
"learning_rate": 4.966417910447762e-05,
"loss": 1.0456,
"step": 10
},
{
"epoch": 0.08262910798122065,
"grad_norm": 1.6171875,
"learning_rate": 4.9626865671641794e-05,
"loss": 0.6937,
"step": 11
},
{
"epoch": 0.09014084507042254,
"grad_norm": 1.3828125,
"learning_rate": 4.9589552238805977e-05,
"loss": 0.6935,
"step": 12
},
{
"epoch": 0.09765258215962441,
"grad_norm": 1.7265625,
"learning_rate": 4.955223880597015e-05,
"loss": 0.9582,
"step": 13
},
{
"epoch": 0.10516431924882629,
"grad_norm": 1.6015625,
"learning_rate": 4.951492537313433e-05,
"loss": 0.6369,
"step": 14
},
{
"epoch": 0.11267605633802817,
"grad_norm": 1.4453125,
"learning_rate": 4.9477611940298504e-05,
"loss": 0.8523,
"step": 15
},
{
"epoch": 0.12018779342723004,
"grad_norm": 1.234375,
"learning_rate": 4.944029850746269e-05,
"loss": 0.7572,
"step": 16
},
{
"epoch": 0.12769953051643193,
"grad_norm": 1.6171875,
"learning_rate": 4.940298507462687e-05,
"loss": 0.8729,
"step": 17
},
{
"epoch": 0.1352112676056338,
"grad_norm": 1.4296875,
"learning_rate": 4.9365671641791045e-05,
"loss": 0.7657,
"step": 18
},
{
"epoch": 0.14272300469483568,
"grad_norm": 1.5546875,
"learning_rate": 4.932835820895523e-05,
"loss": 0.7701,
"step": 19
},
{
"epoch": 0.15023474178403756,
"grad_norm": 1.421875,
"learning_rate": 4.92910447761194e-05,
"loss": 0.8063,
"step": 20
},
{
"epoch": 0.15774647887323945,
"grad_norm": 1.203125,
"learning_rate": 4.9253731343283586e-05,
"loss": 0.6274,
"step": 21
},
{
"epoch": 0.1652582159624413,
"grad_norm": 1.0234375,
"learning_rate": 4.921641791044777e-05,
"loss": 0.6862,
"step": 22
},
{
"epoch": 0.1727699530516432,
"grad_norm": 1.3203125,
"learning_rate": 4.9179104477611944e-05,
"loss": 0.8265,
"step": 23
},
{
"epoch": 0.18028169014084508,
"grad_norm": 1.3671875,
"learning_rate": 4.914179104477612e-05,
"loss": 0.6659,
"step": 24
},
{
"epoch": 0.18779342723004694,
"grad_norm": 1.34375,
"learning_rate": 4.91044776119403e-05,
"loss": 0.6795,
"step": 25
},
{
"epoch": 0.19530516431924883,
"grad_norm": 3.734375,
"learning_rate": 4.906716417910448e-05,
"loss": 0.7914,
"step": 26
},
{
"epoch": 0.2028169014084507,
"grad_norm": 1.578125,
"learning_rate": 4.902985074626866e-05,
"loss": 0.7915,
"step": 27
},
{
"epoch": 0.21032863849765257,
"grad_norm": 1.078125,
"learning_rate": 4.899253731343284e-05,
"loss": 0.6433,
"step": 28
},
{
"epoch": 0.21784037558685446,
"grad_norm": 1.2265625,
"learning_rate": 4.895522388059702e-05,
"loss": 0.8444,
"step": 29
},
{
"epoch": 0.22535211267605634,
"grad_norm": 1.328125,
"learning_rate": 4.8917910447761195e-05,
"loss": 0.7353,
"step": 30
},
{
"epoch": 0.23286384976525823,
"grad_norm": 1.0859375,
"learning_rate": 4.888059701492538e-05,
"loss": 0.6133,
"step": 31
},
{
"epoch": 0.2403755868544601,
"grad_norm": 1.4375,
"learning_rate": 4.884328358208955e-05,
"loss": 0.671,
"step": 32
},
{
"epoch": 0.24788732394366197,
"grad_norm": 1.1484375,
"learning_rate": 4.8805970149253735e-05,
"loss": 0.7712,
"step": 33
},
{
"epoch": 0.25539906103286386,
"grad_norm": 1.4765625,
"learning_rate": 4.876865671641792e-05,
"loss": 0.8207,
"step": 34
},
{
"epoch": 0.26291079812206575,
"grad_norm": 1.28125,
"learning_rate": 4.8731343283582094e-05,
"loss": 0.7435,
"step": 35
},
{
"epoch": 0.2704225352112676,
"grad_norm": 1.171875,
"learning_rate": 4.869402985074627e-05,
"loss": 0.7014,
"step": 36
},
{
"epoch": 0.27793427230046946,
"grad_norm": 1.1875,
"learning_rate": 4.8656716417910445e-05,
"loss": 0.7946,
"step": 37
},
{
"epoch": 0.28544600938967135,
"grad_norm": 1.6328125,
"learning_rate": 4.861940298507463e-05,
"loss": 0.5345,
"step": 38
},
{
"epoch": 0.29295774647887324,
"grad_norm": 2.859375,
"learning_rate": 4.858208955223881e-05,
"loss": 0.8832,
"step": 39
},
{
"epoch": 0.3004694835680751,
"grad_norm": 2.09375,
"learning_rate": 4.8544776119402986e-05,
"loss": 0.8591,
"step": 40
},
{
"epoch": 0.307981220657277,
"grad_norm": 1.21875,
"learning_rate": 4.850746268656717e-05,
"loss": 0.6557,
"step": 41
},
{
"epoch": 0.3154929577464789,
"grad_norm": 0.984375,
"learning_rate": 4.8470149253731344e-05,
"loss": 0.715,
"step": 42
},
{
"epoch": 0.32300469483568073,
"grad_norm": 0.9453125,
"learning_rate": 4.843283582089552e-05,
"loss": 0.6608,
"step": 43
},
{
"epoch": 0.3305164319248826,
"grad_norm": 1.5703125,
"learning_rate": 4.83955223880597e-05,
"loss": 0.5904,
"step": 44
},
{
"epoch": 0.3380281690140845,
"grad_norm": 2.703125,
"learning_rate": 4.8358208955223885e-05,
"loss": 0.8645,
"step": 45
},
{
"epoch": 0.3455399061032864,
"grad_norm": 5.84375,
"learning_rate": 4.832089552238806e-05,
"loss": 0.9412,
"step": 46
},
{
"epoch": 0.3530516431924883,
"grad_norm": 1.2734375,
"learning_rate": 4.8283582089552244e-05,
"loss": 0.8767,
"step": 47
},
{
"epoch": 0.36056338028169016,
"grad_norm": 1.296875,
"learning_rate": 4.824626865671642e-05,
"loss": 0.8197,
"step": 48
},
{
"epoch": 0.36807511737089205,
"grad_norm": 1.0625,
"learning_rate": 4.8208955223880595e-05,
"loss": 0.6598,
"step": 49
},
{
"epoch": 0.3755868544600939,
"grad_norm": 4.0,
"learning_rate": 4.817164179104478e-05,
"loss": 1.1535,
"step": 50
},
{
"epoch": 0.38309859154929576,
"grad_norm": 1.09375,
"learning_rate": 4.813432835820896e-05,
"loss": 0.6635,
"step": 51
},
{
"epoch": 0.39061032863849765,
"grad_norm": 1.3125,
"learning_rate": 4.8097014925373136e-05,
"loss": 0.6979,
"step": 52
},
{
"epoch": 0.39812206572769954,
"grad_norm": 1.2734375,
"learning_rate": 4.805970149253732e-05,
"loss": 0.7167,
"step": 53
},
{
"epoch": 0.4056338028169014,
"grad_norm": 1.1640625,
"learning_rate": 4.8022388059701494e-05,
"loss": 0.8033,
"step": 54
},
{
"epoch": 0.4131455399061033,
"grad_norm": 1.421875,
"learning_rate": 4.798507462686567e-05,
"loss": 0.8736,
"step": 55
},
{
"epoch": 0.42065727699530514,
"grad_norm": 1.2890625,
"learning_rate": 4.794776119402985e-05,
"loss": 0.8361,
"step": 56
},
{
"epoch": 0.428169014084507,
"grad_norm": 1.1328125,
"learning_rate": 4.7910447761194035e-05,
"loss": 0.6386,
"step": 57
},
{
"epoch": 0.4356807511737089,
"grad_norm": 1.2421875,
"learning_rate": 4.787313432835821e-05,
"loss": 0.7318,
"step": 58
},
{
"epoch": 0.4431924882629108,
"grad_norm": 1.4375,
"learning_rate": 4.7835820895522394e-05,
"loss": 0.7141,
"step": 59
},
{
"epoch": 0.4507042253521127,
"grad_norm": 1.0859375,
"learning_rate": 4.779850746268657e-05,
"loss": 0.6612,
"step": 60
},
{
"epoch": 0.4582159624413146,
"grad_norm": 1.109375,
"learning_rate": 4.7761194029850745e-05,
"loss": 0.8155,
"step": 61
},
{
"epoch": 0.46572769953051646,
"grad_norm": 1.0546875,
"learning_rate": 4.772388059701493e-05,
"loss": 0.8123,
"step": 62
},
{
"epoch": 0.4732394366197183,
"grad_norm": 1.1640625,
"learning_rate": 4.768656716417911e-05,
"loss": 0.6706,
"step": 63
},
{
"epoch": 0.4807511737089202,
"grad_norm": 1.25,
"learning_rate": 4.7649253731343286e-05,
"loss": 0.8376,
"step": 64
},
{
"epoch": 0.48826291079812206,
"grad_norm": 0.98828125,
"learning_rate": 4.761194029850746e-05,
"loss": 0.7736,
"step": 65
},
{
"epoch": 0.49577464788732395,
"grad_norm": 1.296875,
"learning_rate": 4.7574626865671644e-05,
"loss": 0.777,
"step": 66
},
{
"epoch": 0.5032863849765258,
"grad_norm": 1.1328125,
"learning_rate": 4.753731343283582e-05,
"loss": 0.7517,
"step": 67
},
{
"epoch": 0.5107981220657277,
"grad_norm": 1.2578125,
"learning_rate": 4.75e-05,
"loss": 0.8422,
"step": 68
},
{
"epoch": 0.5183098591549296,
"grad_norm": 1.2109375,
"learning_rate": 4.7462686567164185e-05,
"loss": 0.6369,
"step": 69
},
{
"epoch": 0.5258215962441315,
"grad_norm": 1.0,
"learning_rate": 4.742537313432836e-05,
"loss": 0.6823,
"step": 70
},
{
"epoch": 0.5333333333333333,
"grad_norm": 1.1953125,
"learning_rate": 4.738805970149254e-05,
"loss": 0.6799,
"step": 71
},
{
"epoch": 0.5408450704225352,
"grad_norm": 1.1640625,
"learning_rate": 4.735074626865672e-05,
"loss": 0.6477,
"step": 72
},
{
"epoch": 0.5483568075117371,
"grad_norm": 1.125,
"learning_rate": 4.7313432835820895e-05,
"loss": 0.7116,
"step": 73
},
{
"epoch": 0.5558685446009389,
"grad_norm": 1.0390625,
"learning_rate": 4.727611940298508e-05,
"loss": 0.6501,
"step": 74
},
{
"epoch": 0.5633802816901409,
"grad_norm": 1.203125,
"learning_rate": 4.723880597014926e-05,
"loss": 0.8061,
"step": 75
},
{
"epoch": 0.5708920187793427,
"grad_norm": 1.203125,
"learning_rate": 4.7201492537313436e-05,
"loss": 0.7363,
"step": 76
},
{
"epoch": 0.5784037558685446,
"grad_norm": 1.15625,
"learning_rate": 4.716417910447761e-05,
"loss": 0.7949,
"step": 77
},
{
"epoch": 0.5859154929577465,
"grad_norm": 1.25,
"learning_rate": 4.7126865671641794e-05,
"loss": 0.7815,
"step": 78
},
{
"epoch": 0.5934272300469483,
"grad_norm": 1.40625,
"learning_rate": 4.708955223880597e-05,
"loss": 0.7815,
"step": 79
},
{
"epoch": 0.6009389671361502,
"grad_norm": 1.1796875,
"learning_rate": 4.705223880597015e-05,
"loss": 0.7299,
"step": 80
},
{
"epoch": 0.6084507042253521,
"grad_norm": 1.25,
"learning_rate": 4.7014925373134335e-05,
"loss": 0.5975,
"step": 81
},
{
"epoch": 0.615962441314554,
"grad_norm": 1.8984375,
"learning_rate": 4.697761194029851e-05,
"loss": 0.8056,
"step": 82
},
{
"epoch": 0.6234741784037559,
"grad_norm": 1.3671875,
"learning_rate": 4.6940298507462687e-05,
"loss": 0.8034,
"step": 83
},
{
"epoch": 0.6309859154929578,
"grad_norm": 1.078125,
"learning_rate": 4.690298507462687e-05,
"loss": 0.6472,
"step": 84
},
{
"epoch": 0.6384976525821596,
"grad_norm": 1.328125,
"learning_rate": 4.6865671641791045e-05,
"loss": 0.8561,
"step": 85
},
{
"epoch": 0.6460093896713615,
"grad_norm": 2.90625,
"learning_rate": 4.682835820895523e-05,
"loss": 0.8774,
"step": 86
},
{
"epoch": 0.6535211267605634,
"grad_norm": 1.1484375,
"learning_rate": 4.67910447761194e-05,
"loss": 0.6865,
"step": 87
},
{
"epoch": 0.6610328638497652,
"grad_norm": 1.53125,
"learning_rate": 4.6753731343283586e-05,
"loss": 0.798,
"step": 88
},
{
"epoch": 0.6685446009389672,
"grad_norm": 1.1875,
"learning_rate": 4.671641791044776e-05,
"loss": 0.7587,
"step": 89
},
{
"epoch": 0.676056338028169,
"grad_norm": 1.25,
"learning_rate": 4.667910447761194e-05,
"loss": 0.6989,
"step": 90
},
{
"epoch": 0.6835680751173709,
"grad_norm": 1.0546875,
"learning_rate": 4.664179104477612e-05,
"loss": 0.639,
"step": 91
},
{
"epoch": 0.6910798122065728,
"grad_norm": 1.453125,
"learning_rate": 4.66044776119403e-05,
"loss": 0.6844,
"step": 92
},
{
"epoch": 0.6985915492957746,
"grad_norm": 1.03125,
"learning_rate": 4.656716417910448e-05,
"loss": 0.7513,
"step": 93
},
{
"epoch": 0.7061032863849765,
"grad_norm": 1.015625,
"learning_rate": 4.652985074626866e-05,
"loss": 0.6264,
"step": 94
},
{
"epoch": 0.7136150234741784,
"grad_norm": 1.21875,
"learning_rate": 4.6492537313432837e-05,
"loss": 0.7228,
"step": 95
},
{
"epoch": 0.7211267605633803,
"grad_norm": 1.0078125,
"learning_rate": 4.645522388059701e-05,
"loss": 0.5355,
"step": 96
},
{
"epoch": 0.7286384976525822,
"grad_norm": 1.359375,
"learning_rate": 4.6417910447761195e-05,
"loss": 0.7717,
"step": 97
},
{
"epoch": 0.7361502347417841,
"grad_norm": 1.1328125,
"learning_rate": 4.638059701492538e-05,
"loss": 0.7365,
"step": 98
},
{
"epoch": 0.7436619718309859,
"grad_norm": 3.375,
"learning_rate": 4.634328358208955e-05,
"loss": 0.8382,
"step": 99
},
{
"epoch": 0.7511737089201878,
"grad_norm": 1.421875,
"learning_rate": 4.6305970149253736e-05,
"loss": 0.7674,
"step": 100
},
{
"epoch": 0.7586854460093897,
"grad_norm": 1.7265625,
"learning_rate": 4.626865671641791e-05,
"loss": 0.554,
"step": 101
},
{
"epoch": 0.7661971830985915,
"grad_norm": 1.25,
"learning_rate": 4.623134328358209e-05,
"loss": 0.7921,
"step": 102
},
{
"epoch": 0.7737089201877935,
"grad_norm": 1.2734375,
"learning_rate": 4.6194029850746277e-05,
"loss": 0.6282,
"step": 103
},
{
"epoch": 0.7812206572769953,
"grad_norm": 1.171875,
"learning_rate": 4.615671641791045e-05,
"loss": 0.7992,
"step": 104
},
{
"epoch": 0.7887323943661971,
"grad_norm": 1.0859375,
"learning_rate": 4.611940298507463e-05,
"loss": 0.7313,
"step": 105
},
{
"epoch": 0.7962441314553991,
"grad_norm": 0.9921875,
"learning_rate": 4.608208955223881e-05,
"loss": 0.7154,
"step": 106
},
{
"epoch": 0.8037558685446009,
"grad_norm": 1.0859375,
"learning_rate": 4.6044776119402986e-05,
"loss": 0.6904,
"step": 107
},
{
"epoch": 0.8112676056338028,
"grad_norm": 1.125,
"learning_rate": 4.600746268656716e-05,
"loss": 0.7075,
"step": 108
},
{
"epoch": 0.8187793427230047,
"grad_norm": 2.609375,
"learning_rate": 4.5970149253731345e-05,
"loss": 0.7362,
"step": 109
},
{
"epoch": 0.8262910798122066,
"grad_norm": 1.125,
"learning_rate": 4.593283582089553e-05,
"loss": 0.6568,
"step": 110
},
{
"epoch": 0.8338028169014085,
"grad_norm": 1.3984375,
"learning_rate": 4.58955223880597e-05,
"loss": 0.7508,
"step": 111
},
{
"epoch": 0.8413145539906103,
"grad_norm": 1.078125,
"learning_rate": 4.585820895522388e-05,
"loss": 0.8402,
"step": 112
},
{
"epoch": 0.8488262910798122,
"grad_norm": 1.2734375,
"learning_rate": 4.582089552238806e-05,
"loss": 0.6946,
"step": 113
},
{
"epoch": 0.856338028169014,
"grad_norm": 1.03125,
"learning_rate": 4.578358208955224e-05,
"loss": 0.6877,
"step": 114
},
{
"epoch": 0.863849765258216,
"grad_norm": 1.2890625,
"learning_rate": 4.574626865671642e-05,
"loss": 0.6703,
"step": 115
},
{
"epoch": 0.8713615023474178,
"grad_norm": 1.2578125,
"learning_rate": 4.57089552238806e-05,
"loss": 0.6673,
"step": 116
},
{
"epoch": 0.8788732394366198,
"grad_norm": 1.078125,
"learning_rate": 4.567164179104478e-05,
"loss": 0.8,
"step": 117
},
{
"epoch": 0.8863849765258216,
"grad_norm": 1.7734375,
"learning_rate": 4.5634328358208954e-05,
"loss": 0.7146,
"step": 118
},
{
"epoch": 0.8938967136150234,
"grad_norm": 1.1953125,
"learning_rate": 4.5597014925373136e-05,
"loss": 0.7342,
"step": 119
},
{
"epoch": 0.9014084507042254,
"grad_norm": 1.390625,
"learning_rate": 4.555970149253732e-05,
"loss": 0.865,
"step": 120
},
{
"epoch": 0.9089201877934272,
"grad_norm": 1.171875,
"learning_rate": 4.5522388059701495e-05,
"loss": 0.8743,
"step": 121
},
{
"epoch": 0.9164319248826291,
"grad_norm": 1.0625,
"learning_rate": 4.548507462686568e-05,
"loss": 0.8124,
"step": 122
},
{
"epoch": 0.923943661971831,
"grad_norm": 1.0703125,
"learning_rate": 4.544776119402985e-05,
"loss": 0.739,
"step": 123
},
{
"epoch": 0.9314553990610329,
"grad_norm": 1.109375,
"learning_rate": 4.541044776119403e-05,
"loss": 0.9343,
"step": 124
},
{
"epoch": 0.9389671361502347,
"grad_norm": 1.21875,
"learning_rate": 4.537313432835821e-05,
"loss": 0.8239,
"step": 125
},
{
"epoch": 0.9464788732394366,
"grad_norm": 1.125,
"learning_rate": 4.5335820895522394e-05,
"loss": 0.5928,
"step": 126
},
{
"epoch": 0.9539906103286385,
"grad_norm": 1.140625,
"learning_rate": 4.529850746268657e-05,
"loss": 0.6705,
"step": 127
},
{
"epoch": 0.9615023474178404,
"grad_norm": 1.5390625,
"learning_rate": 4.526119402985075e-05,
"loss": 0.7937,
"step": 128
},
{
"epoch": 0.9690140845070423,
"grad_norm": 1.0703125,
"learning_rate": 4.522388059701493e-05,
"loss": 0.7819,
"step": 129
},
{
"epoch": 0.9765258215962441,
"grad_norm": 1.2265625,
"learning_rate": 4.5186567164179104e-05,
"loss": 0.7217,
"step": 130
},
{
"epoch": 0.984037558685446,
"grad_norm": 0.97265625,
"learning_rate": 4.5149253731343286e-05,
"loss": 0.5954,
"step": 131
},
{
"epoch": 0.9915492957746479,
"grad_norm": 1.171875,
"learning_rate": 4.511194029850747e-05,
"loss": 0.6472,
"step": 132
},
{
"epoch": 0.9990610328638497,
"grad_norm": 1.078125,
"learning_rate": 4.5074626865671645e-05,
"loss": 0.6715,
"step": 133
},
{
"epoch": 1.0,
"grad_norm": 2.765625,
"learning_rate": 4.503731343283582e-05,
"loss": 0.7686,
"step": 134
},
{
"epoch": 1.007511737089202,
"grad_norm": 1.625,
"learning_rate": 4.5e-05,
"loss": 0.6494,
"step": 135
},
{
"epoch": 1.0150234741784037,
"grad_norm": 1.46875,
"learning_rate": 4.496268656716418e-05,
"loss": 0.5652,
"step": 136
},
{
"epoch": 1.0225352112676056,
"grad_norm": 0.9296875,
"learning_rate": 4.492537313432836e-05,
"loss": 0.5451,
"step": 137
},
{
"epoch": 1.0300469483568075,
"grad_norm": 1.1171875,
"learning_rate": 4.4888059701492544e-05,
"loss": 0.7535,
"step": 138
},
{
"epoch": 1.0375586854460095,
"grad_norm": 1.328125,
"learning_rate": 4.485074626865672e-05,
"loss": 0.6217,
"step": 139
},
{
"epoch": 1.0450704225352112,
"grad_norm": 1.1953125,
"learning_rate": 4.4813432835820895e-05,
"loss": 0.6696,
"step": 140
},
{
"epoch": 1.0525821596244131,
"grad_norm": 1.59375,
"learning_rate": 4.477611940298508e-05,
"loss": 0.5071,
"step": 141
},
{
"epoch": 1.060093896713615,
"grad_norm": 1.4921875,
"learning_rate": 4.4738805970149254e-05,
"loss": 0.5824,
"step": 142
},
{
"epoch": 1.0676056338028168,
"grad_norm": 1.1796875,
"learning_rate": 4.4701492537313436e-05,
"loss": 0.4513,
"step": 143
},
{
"epoch": 1.0751173708920188,
"grad_norm": 1.3671875,
"learning_rate": 4.466417910447762e-05,
"loss": 0.6003,
"step": 144
},
{
"epoch": 1.0826291079812207,
"grad_norm": 1.3515625,
"learning_rate": 4.4626865671641794e-05,
"loss": 0.6236,
"step": 145
},
{
"epoch": 1.0901408450704226,
"grad_norm": 1.0859375,
"learning_rate": 4.458955223880597e-05,
"loss": 0.5397,
"step": 146
},
{
"epoch": 1.0976525821596244,
"grad_norm": 2.0625,
"learning_rate": 4.455223880597015e-05,
"loss": 0.8009,
"step": 147
},
{
"epoch": 1.1051643192488263,
"grad_norm": 1.3125,
"learning_rate": 4.451492537313433e-05,
"loss": 0.7748,
"step": 148
},
{
"epoch": 1.1126760563380282,
"grad_norm": 3.421875,
"learning_rate": 4.447761194029851e-05,
"loss": 0.7256,
"step": 149
},
{
"epoch": 1.12018779342723,
"grad_norm": 1.296875,
"learning_rate": 4.4440298507462694e-05,
"loss": 0.6101,
"step": 150
},
{
"epoch": 1.127699530516432,
"grad_norm": 1.109375,
"learning_rate": 4.440298507462687e-05,
"loss": 0.4897,
"step": 151
},
{
"epoch": 1.1352112676056338,
"grad_norm": 1.0703125,
"learning_rate": 4.4365671641791045e-05,
"loss": 0.7608,
"step": 152
},
{
"epoch": 1.1427230046948358,
"grad_norm": 1.1171875,
"learning_rate": 4.432835820895523e-05,
"loss": 0.6389,
"step": 153
},
{
"epoch": 1.1502347417840375,
"grad_norm": 0.98828125,
"learning_rate": 4.4291044776119403e-05,
"loss": 0.4912,
"step": 154
},
{
"epoch": 1.1577464788732394,
"grad_norm": 1.1171875,
"learning_rate": 4.4253731343283586e-05,
"loss": 0.6865,
"step": 155
},
{
"epoch": 1.1652582159624414,
"grad_norm": 1.0078125,
"learning_rate": 4.421641791044777e-05,
"loss": 0.4687,
"step": 156
},
{
"epoch": 1.172769953051643,
"grad_norm": 1.6484375,
"learning_rate": 4.4179104477611944e-05,
"loss": 0.6835,
"step": 157
},
{
"epoch": 1.180281690140845,
"grad_norm": 1.015625,
"learning_rate": 4.414179104477612e-05,
"loss": 0.4748,
"step": 158
},
{
"epoch": 1.187793427230047,
"grad_norm": 1.1015625,
"learning_rate": 4.4104477611940296e-05,
"loss": 0.556,
"step": 159
},
{
"epoch": 1.1953051643192487,
"grad_norm": 1.0390625,
"learning_rate": 4.406716417910448e-05,
"loss": 0.4781,
"step": 160
},
{
"epoch": 1.2028169014084507,
"grad_norm": 0.87890625,
"learning_rate": 4.402985074626866e-05,
"loss": 0.4693,
"step": 161
},
{
"epoch": 1.2103286384976526,
"grad_norm": 1.1171875,
"learning_rate": 4.399253731343284e-05,
"loss": 0.5578,
"step": 162
},
{
"epoch": 1.2178403755868545,
"grad_norm": 1.2890625,
"learning_rate": 4.395522388059702e-05,
"loss": 0.6094,
"step": 163
},
{
"epoch": 1.2253521126760563,
"grad_norm": 1.671875,
"learning_rate": 4.3917910447761195e-05,
"loss": 0.6457,
"step": 164
},
{
"epoch": 1.2328638497652582,
"grad_norm": 0.96875,
"learning_rate": 4.388059701492537e-05,
"loss": 0.5279,
"step": 165
},
{
"epoch": 1.2403755868544601,
"grad_norm": 1.0234375,
"learning_rate": 4.384328358208955e-05,
"loss": 0.5519,
"step": 166
},
{
"epoch": 1.247887323943662,
"grad_norm": 0.97265625,
"learning_rate": 4.3805970149253736e-05,
"loss": 0.4328,
"step": 167
},
{
"epoch": 1.2553990610328638,
"grad_norm": 1.6484375,
"learning_rate": 4.376865671641791e-05,
"loss": 0.6765,
"step": 168
},
{
"epoch": 1.2629107981220657,
"grad_norm": 0.953125,
"learning_rate": 4.3731343283582094e-05,
"loss": 0.4776,
"step": 169
},
{
"epoch": 1.2704225352112677,
"grad_norm": 1.125,
"learning_rate": 4.369402985074627e-05,
"loss": 0.4864,
"step": 170
},
{
"epoch": 1.2779342723004694,
"grad_norm": 1.2421875,
"learning_rate": 4.3656716417910446e-05,
"loss": 0.5458,
"step": 171
},
{
"epoch": 1.2854460093896714,
"grad_norm": 1.046875,
"learning_rate": 4.361940298507463e-05,
"loss": 0.5282,
"step": 172
},
{
"epoch": 1.2929577464788733,
"grad_norm": 1.0703125,
"learning_rate": 4.358208955223881e-05,
"loss": 0.5868,
"step": 173
},
{
"epoch": 1.300469483568075,
"grad_norm": 0.94921875,
"learning_rate": 4.354477611940299e-05,
"loss": 0.5913,
"step": 174
},
{
"epoch": 1.307981220657277,
"grad_norm": 1.1953125,
"learning_rate": 4.350746268656717e-05,
"loss": 0.6012,
"step": 175
},
{
"epoch": 1.315492957746479,
"grad_norm": 1.578125,
"learning_rate": 4.3470149253731345e-05,
"loss": 0.7648,
"step": 176
},
{
"epoch": 1.3230046948356806,
"grad_norm": 1.09375,
"learning_rate": 4.343283582089552e-05,
"loss": 0.5035,
"step": 177
},
{
"epoch": 1.3305164319248826,
"grad_norm": 0.98046875,
"learning_rate": 4.33955223880597e-05,
"loss": 0.6096,
"step": 178
},
{
"epoch": 1.3380281690140845,
"grad_norm": 1.1875,
"learning_rate": 4.3358208955223886e-05,
"loss": 0.6028,
"step": 179
},
{
"epoch": 1.3455399061032864,
"grad_norm": 1.046875,
"learning_rate": 4.332089552238806e-05,
"loss": 0.4301,
"step": 180
},
{
"epoch": 1.3530516431924884,
"grad_norm": 0.875,
"learning_rate": 4.328358208955224e-05,
"loss": 0.4578,
"step": 181
},
{
"epoch": 1.36056338028169,
"grad_norm": 1.2734375,
"learning_rate": 4.324626865671642e-05,
"loss": 0.6293,
"step": 182
},
{
"epoch": 1.368075117370892,
"grad_norm": 1.09375,
"learning_rate": 4.3208955223880596e-05,
"loss": 0.6577,
"step": 183
},
{
"epoch": 1.375586854460094,
"grad_norm": 1.0,
"learning_rate": 4.317164179104478e-05,
"loss": 0.5545,
"step": 184
},
{
"epoch": 1.3830985915492957,
"grad_norm": 1.28125,
"learning_rate": 4.313432835820896e-05,
"loss": 0.6445,
"step": 185
},
{
"epoch": 1.3906103286384977,
"grad_norm": 0.9609375,
"learning_rate": 4.3097014925373137e-05,
"loss": 0.3414,
"step": 186
},
{
"epoch": 1.3981220657276996,
"grad_norm": 1.1328125,
"learning_rate": 4.305970149253731e-05,
"loss": 0.6948,
"step": 187
},
{
"epoch": 1.4056338028169013,
"grad_norm": 1.15625,
"learning_rate": 4.3022388059701495e-05,
"loss": 0.4784,
"step": 188
},
{
"epoch": 1.4131455399061033,
"grad_norm": 1.140625,
"learning_rate": 4.298507462686567e-05,
"loss": 0.665,
"step": 189
},
{
"epoch": 1.4206572769953052,
"grad_norm": 1.0703125,
"learning_rate": 4.294776119402985e-05,
"loss": 0.5881,
"step": 190
},
{
"epoch": 1.428169014084507,
"grad_norm": 0.98046875,
"learning_rate": 4.2910447761194036e-05,
"loss": 0.4298,
"step": 191
},
{
"epoch": 1.4356807511737089,
"grad_norm": 1.2578125,
"learning_rate": 4.287313432835821e-05,
"loss": 0.6543,
"step": 192
},
{
"epoch": 1.4431924882629108,
"grad_norm": 1.09375,
"learning_rate": 4.283582089552239e-05,
"loss": 0.4931,
"step": 193
},
{
"epoch": 1.4507042253521127,
"grad_norm": 1.2265625,
"learning_rate": 4.279850746268657e-05,
"loss": 0.5279,
"step": 194
},
{
"epoch": 1.4582159624413147,
"grad_norm": 1.015625,
"learning_rate": 4.2761194029850746e-05,
"loss": 0.5347,
"step": 195
},
{
"epoch": 1.4657276995305164,
"grad_norm": 1.15625,
"learning_rate": 4.272388059701493e-05,
"loss": 0.48,
"step": 196
},
{
"epoch": 1.4732394366197183,
"grad_norm": 1.25,
"learning_rate": 4.268656716417911e-05,
"loss": 0.6988,
"step": 197
},
{
"epoch": 1.4807511737089203,
"grad_norm": 1.421875,
"learning_rate": 4.2649253731343286e-05,
"loss": 0.5859,
"step": 198
},
{
"epoch": 1.488262910798122,
"grad_norm": 1.1796875,
"learning_rate": 4.261194029850746e-05,
"loss": 0.5283,
"step": 199
},
{
"epoch": 1.495774647887324,
"grad_norm": 1.0703125,
"learning_rate": 4.2574626865671645e-05,
"loss": 0.4631,
"step": 200
},
{
"epoch": 1.503286384976526,
"grad_norm": 0.9921875,
"learning_rate": 4.253731343283582e-05,
"loss": 0.5231,
"step": 201
},
{
"epoch": 1.5107981220657276,
"grad_norm": 1.0625,
"learning_rate": 4.25e-05,
"loss": 0.5583,
"step": 202
},
{
"epoch": 1.5183098591549296,
"grad_norm": 0.9453125,
"learning_rate": 4.2462686567164186e-05,
"loss": 0.4876,
"step": 203
},
{
"epoch": 1.5258215962441315,
"grad_norm": 1.2265625,
"learning_rate": 4.242537313432836e-05,
"loss": 0.4504,
"step": 204
},
{
"epoch": 1.5333333333333332,
"grad_norm": 0.93359375,
"learning_rate": 4.238805970149254e-05,
"loss": 0.4757,
"step": 205
},
{
"epoch": 1.5408450704225352,
"grad_norm": 1.0703125,
"learning_rate": 4.235074626865671e-05,
"loss": 0.5933,
"step": 206
},
{
"epoch": 1.548356807511737,
"grad_norm": 1.0078125,
"learning_rate": 4.2313432835820895e-05,
"loss": 0.5415,
"step": 207
},
{
"epoch": 1.5558685446009388,
"grad_norm": 1.1953125,
"learning_rate": 4.227611940298508e-05,
"loss": 0.7041,
"step": 208
},
{
"epoch": 1.563380281690141,
"grad_norm": 1.109375,
"learning_rate": 4.2238805970149254e-05,
"loss": 0.5753,
"step": 209
},
{
"epoch": 1.5708920187793427,
"grad_norm": 1.1640625,
"learning_rate": 4.2201492537313436e-05,
"loss": 0.552,
"step": 210
},
{
"epoch": 1.5784037558685446,
"grad_norm": 1.0,
"learning_rate": 4.216417910447761e-05,
"loss": 0.5549,
"step": 211
},
{
"epoch": 1.5859154929577466,
"grad_norm": 1.1328125,
"learning_rate": 4.212686567164179e-05,
"loss": 0.6679,
"step": 212
},
{
"epoch": 1.5934272300469483,
"grad_norm": 2.015625,
"learning_rate": 4.208955223880597e-05,
"loss": 0.796,
"step": 213
},
{
"epoch": 1.6009389671361502,
"grad_norm": 2.953125,
"learning_rate": 4.205223880597015e-05,
"loss": 0.6427,
"step": 214
},
{
"epoch": 1.6084507042253522,
"grad_norm": 0.90625,
"learning_rate": 4.201492537313433e-05,
"loss": 0.466,
"step": 215
},
{
"epoch": 1.615962441314554,
"grad_norm": 0.94140625,
"learning_rate": 4.197761194029851e-05,
"loss": 0.4242,
"step": 216
},
{
"epoch": 1.6234741784037559,
"grad_norm": 3.0,
"learning_rate": 4.194029850746269e-05,
"loss": 0.6968,
"step": 217
},
{
"epoch": 1.6309859154929578,
"grad_norm": 0.9765625,
"learning_rate": 4.190298507462686e-05,
"loss": 0.5988,
"step": 218
},
{
"epoch": 1.6384976525821595,
"grad_norm": 1.203125,
"learning_rate": 4.186567164179105e-05,
"loss": 0.4979,
"step": 219
},
{
"epoch": 1.6460093896713615,
"grad_norm": 0.83203125,
"learning_rate": 4.182835820895523e-05,
"loss": 0.3527,
"step": 220
},
{
"epoch": 1.6535211267605634,
"grad_norm": 1.09375,
"learning_rate": 4.1791044776119404e-05,
"loss": 0.5743,
"step": 221
},
{
"epoch": 1.6610328638497651,
"grad_norm": 1.3203125,
"learning_rate": 4.1753731343283586e-05,
"loss": 0.6427,
"step": 222
},
{
"epoch": 1.6685446009389673,
"grad_norm": 1.2109375,
"learning_rate": 4.171641791044776e-05,
"loss": 0.6496,
"step": 223
},
{
"epoch": 1.676056338028169,
"grad_norm": 0.8515625,
"learning_rate": 4.167910447761194e-05,
"loss": 0.3463,
"step": 224
},
{
"epoch": 1.683568075117371,
"grad_norm": 1.34375,
"learning_rate": 4.164179104477613e-05,
"loss": 0.6243,
"step": 225
},
{
"epoch": 1.6910798122065729,
"grad_norm": 0.98828125,
"learning_rate": 4.16044776119403e-05,
"loss": 0.5389,
"step": 226
},
{
"epoch": 1.6985915492957746,
"grad_norm": 1.0,
"learning_rate": 4.156716417910448e-05,
"loss": 0.5515,
"step": 227
},
{
"epoch": 1.7061032863849765,
"grad_norm": 1.2890625,
"learning_rate": 4.152985074626866e-05,
"loss": 0.6783,
"step": 228
},
{
"epoch": 1.7136150234741785,
"grad_norm": 1.0390625,
"learning_rate": 4.149253731343284e-05,
"loss": 0.5099,
"step": 229
},
{
"epoch": 1.7211267605633802,
"grad_norm": 1.078125,
"learning_rate": 4.145522388059702e-05,
"loss": 0.461,
"step": 230
},
{
"epoch": 1.7286384976525822,
"grad_norm": 1.0703125,
"learning_rate": 4.1417910447761195e-05,
"loss": 0.4953,
"step": 231
},
{
"epoch": 1.736150234741784,
"grad_norm": 1.1484375,
"learning_rate": 4.138059701492538e-05,
"loss": 0.5662,
"step": 232
},
{
"epoch": 1.7436619718309858,
"grad_norm": 1.1171875,
"learning_rate": 4.1343283582089554e-05,
"loss": 0.524,
"step": 233
},
{
"epoch": 1.7511737089201878,
"grad_norm": 1.1328125,
"learning_rate": 4.130597014925373e-05,
"loss": 0.424,
"step": 234
},
{
"epoch": 1.7586854460093897,
"grad_norm": 1.5625,
"learning_rate": 4.126865671641791e-05,
"loss": 0.5042,
"step": 235
},
{
"epoch": 1.7661971830985914,
"grad_norm": 0.9765625,
"learning_rate": 4.1231343283582094e-05,
"loss": 0.5515,
"step": 236
},
{
"epoch": 1.7737089201877936,
"grad_norm": 1.0703125,
"learning_rate": 4.119402985074627e-05,
"loss": 0.6026,
"step": 237
},
{
"epoch": 1.7812206572769953,
"grad_norm": 1.171875,
"learning_rate": 4.115671641791045e-05,
"loss": 0.6206,
"step": 238
},
{
"epoch": 1.788732394366197,
"grad_norm": 1.96875,
"learning_rate": 4.111940298507463e-05,
"loss": 0.6904,
"step": 239
},
{
"epoch": 1.7962441314553992,
"grad_norm": 1.0703125,
"learning_rate": 4.1082089552238804e-05,
"loss": 0.4693,
"step": 240
},
{
"epoch": 1.803755868544601,
"grad_norm": 0.8984375,
"learning_rate": 4.104477611940299e-05,
"loss": 0.3648,
"step": 241
},
{
"epoch": 1.8112676056338028,
"grad_norm": 1.2734375,
"learning_rate": 4.100746268656717e-05,
"loss": 0.6071,
"step": 242
},
{
"epoch": 1.8187793427230048,
"grad_norm": 1.1015625,
"learning_rate": 4.0970149253731345e-05,
"loss": 0.4936,
"step": 243
},
{
"epoch": 1.8262910798122065,
"grad_norm": 1.0625,
"learning_rate": 4.093283582089553e-05,
"loss": 0.6627,
"step": 244
},
{
"epoch": 1.8338028169014085,
"grad_norm": 1.0625,
"learning_rate": 4.0895522388059703e-05,
"loss": 0.4625,
"step": 245
},
{
"epoch": 1.8413145539906104,
"grad_norm": 1.2890625,
"learning_rate": 4.085820895522388e-05,
"loss": 0.5132,
"step": 246
},
{
"epoch": 1.8488262910798121,
"grad_norm": 0.91796875,
"learning_rate": 4.082089552238806e-05,
"loss": 0.5464,
"step": 247
},
{
"epoch": 1.856338028169014,
"grad_norm": 1.5390625,
"learning_rate": 4.0783582089552244e-05,
"loss": 0.6268,
"step": 248
},
{
"epoch": 1.863849765258216,
"grad_norm": 1.1015625,
"learning_rate": 4.074626865671642e-05,
"loss": 0.4702,
"step": 249
},
{
"epoch": 1.8713615023474177,
"grad_norm": 1.21875,
"learning_rate": 4.07089552238806e-05,
"loss": 0.6875,
"step": 250
},
{
"epoch": 1.8788732394366199,
"grad_norm": 1.828125,
"learning_rate": 4.067164179104478e-05,
"loss": 0.5994,
"step": 251
},
{
"epoch": 1.8863849765258216,
"grad_norm": 1.1015625,
"learning_rate": 4.0634328358208954e-05,
"loss": 0.513,
"step": 252
},
{
"epoch": 1.8938967136150233,
"grad_norm": 0.99609375,
"learning_rate": 4.059701492537314e-05,
"loss": 0.5234,
"step": 253
},
{
"epoch": 1.9014084507042255,
"grad_norm": 1.03125,
"learning_rate": 4.055970149253732e-05,
"loss": 0.3845,
"step": 254
},
{
"epoch": 1.9089201877934272,
"grad_norm": 0.8515625,
"learning_rate": 4.0522388059701495e-05,
"loss": 0.5088,
"step": 255
},
{
"epoch": 1.9164319248826291,
"grad_norm": 1.3359375,
"learning_rate": 4.048507462686567e-05,
"loss": 0.5853,
"step": 256
},
{
"epoch": 1.923943661971831,
"grad_norm": 1.0859375,
"learning_rate": 4.044776119402985e-05,
"loss": 0.5691,
"step": 257
},
{
"epoch": 1.9314553990610328,
"grad_norm": 1.2890625,
"learning_rate": 4.041044776119403e-05,
"loss": 0.5251,
"step": 258
},
{
"epoch": 1.9389671361502347,
"grad_norm": 1.0390625,
"learning_rate": 4.037313432835821e-05,
"loss": 0.5245,
"step": 259
},
{
"epoch": 1.9464788732394367,
"grad_norm": 1.078125,
"learning_rate": 4.0335820895522394e-05,
"loss": 0.5217,
"step": 260
},
{
"epoch": 1.9539906103286384,
"grad_norm": 1.078125,
"learning_rate": 4.029850746268657e-05,
"loss": 0.4795,
"step": 261
},
{
"epoch": 1.9615023474178404,
"grad_norm": 1.109375,
"learning_rate": 4.0261194029850746e-05,
"loss": 0.5037,
"step": 262
},
{
"epoch": 1.9690140845070423,
"grad_norm": 1.0,
"learning_rate": 4.022388059701493e-05,
"loss": 0.5489,
"step": 263
},
{
"epoch": 1.976525821596244,
"grad_norm": 1.078125,
"learning_rate": 4.0186567164179104e-05,
"loss": 0.6005,
"step": 264
},
{
"epoch": 1.984037558685446,
"grad_norm": 0.96875,
"learning_rate": 4.014925373134329e-05,
"loss": 0.4849,
"step": 265
},
{
"epoch": 1.991549295774648,
"grad_norm": 1.1171875,
"learning_rate": 4.011194029850747e-05,
"loss": 0.541,
"step": 266
},
{
"epoch": 1.9990610328638496,
"grad_norm": 1.109375,
"learning_rate": 4.0074626865671645e-05,
"loss": 0.5955,
"step": 267
},
{
"epoch": 2.0,
"grad_norm": 3.390625,
"learning_rate": 4.003731343283582e-05,
"loss": 0.4322,
"step": 268
}
],
"logging_steps": 1,
"max_steps": 1340,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.3712007927064166e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}