model_7883b480 / checkpoint-246 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
ac7fb6b verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.870967741935484,
"eval_steps": 500,
"global_step": 246,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.024193548387096774,
"grad_norm": 33.12635803222656,
"learning_rate": 5.0000000000000004e-08,
"loss": 2.4997,
"step": 1
},
{
"epoch": 0.04838709677419355,
"grad_norm": 32.004058837890625,
"learning_rate": 1.0000000000000001e-07,
"loss": 2.4277,
"step": 2
},
{
"epoch": 0.07258064516129033,
"grad_norm": 34.234554290771484,
"learning_rate": 1.5000000000000002e-07,
"loss": 2.6112,
"step": 3
},
{
"epoch": 0.0967741935483871,
"grad_norm": 32.96908187866211,
"learning_rate": 2.0000000000000002e-07,
"loss": 2.5017,
"step": 4
},
{
"epoch": 0.12096774193548387,
"grad_norm": 35.06013870239258,
"learning_rate": 2.5000000000000004e-07,
"loss": 2.6115,
"step": 5
},
{
"epoch": 0.14516129032258066,
"grad_norm": 33.552955627441406,
"learning_rate": 3.0000000000000004e-07,
"loss": 2.5234,
"step": 6
},
{
"epoch": 0.1693548387096774,
"grad_norm": 32.13972091674805,
"learning_rate": 3.5000000000000004e-07,
"loss": 2.4724,
"step": 7
},
{
"epoch": 0.1935483870967742,
"grad_norm": 32.68510055541992,
"learning_rate": 4.0000000000000003e-07,
"loss": 2.4925,
"step": 8
},
{
"epoch": 0.21774193548387097,
"grad_norm": 32.32320785522461,
"learning_rate": 4.5000000000000003e-07,
"loss": 2.4983,
"step": 9
},
{
"epoch": 0.24193548387096775,
"grad_norm": 32.311553955078125,
"learning_rate": 5.000000000000001e-07,
"loss": 2.4833,
"step": 10
},
{
"epoch": 0.2661290322580645,
"grad_norm": 31.869163513183594,
"learning_rate": 5.5e-07,
"loss": 2.4362,
"step": 11
},
{
"epoch": 0.2903225806451613,
"grad_norm": 31.329313278198242,
"learning_rate": 6.000000000000001e-07,
"loss": 2.4228,
"step": 12
},
{
"epoch": 0.31451612903225806,
"grad_norm": 29.42159652709961,
"learning_rate": 6.5e-07,
"loss": 2.2499,
"step": 13
},
{
"epoch": 0.3387096774193548,
"grad_norm": 31.27863311767578,
"learning_rate": 7.000000000000001e-07,
"loss": 2.3354,
"step": 14
},
{
"epoch": 0.3629032258064516,
"grad_norm": 31.095605850219727,
"learning_rate": 7.5e-07,
"loss": 2.2723,
"step": 15
},
{
"epoch": 0.3870967741935484,
"grad_norm": 30.90537452697754,
"learning_rate": 8.000000000000001e-07,
"loss": 2.2003,
"step": 16
},
{
"epoch": 0.4112903225806452,
"grad_norm": 30.878215789794922,
"learning_rate": 8.500000000000001e-07,
"loss": 2.0797,
"step": 17
},
{
"epoch": 0.43548387096774194,
"grad_norm": 32.37583541870117,
"learning_rate": 9.000000000000001e-07,
"loss": 1.9855,
"step": 18
},
{
"epoch": 0.4596774193548387,
"grad_norm": 32.957889556884766,
"learning_rate": 9.500000000000001e-07,
"loss": 1.8497,
"step": 19
},
{
"epoch": 0.4838709677419355,
"grad_norm": 33.7425537109375,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.7037,
"step": 20
},
{
"epoch": 0.5080645161290323,
"grad_norm": 35.177791595458984,
"learning_rate": 1.0500000000000001e-06,
"loss": 1.645,
"step": 21
},
{
"epoch": 0.532258064516129,
"grad_norm": 34.37784957885742,
"learning_rate": 1.1e-06,
"loss": 1.4705,
"step": 22
},
{
"epoch": 0.5564516129032258,
"grad_norm": 32.561283111572266,
"learning_rate": 1.1500000000000002e-06,
"loss": 1.3819,
"step": 23
},
{
"epoch": 0.5806451612903226,
"grad_norm": 28.166706085205078,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.1496,
"step": 24
},
{
"epoch": 0.6048387096774194,
"grad_norm": 30.428386688232422,
"learning_rate": 1.25e-06,
"loss": 1.0998,
"step": 25
},
{
"epoch": 0.6290322580645161,
"grad_norm": 34.153076171875,
"learning_rate": 1.3e-06,
"loss": 0.9278,
"step": 26
},
{
"epoch": 0.6532258064516129,
"grad_norm": 39.16960906982422,
"learning_rate": 1.3500000000000002e-06,
"loss": 0.7463,
"step": 27
},
{
"epoch": 0.6774193548387096,
"grad_norm": 39.09505081176758,
"learning_rate": 1.4000000000000001e-06,
"loss": 0.5676,
"step": 28
},
{
"epoch": 0.7016129032258065,
"grad_norm": 38.89931869506836,
"learning_rate": 1.45e-06,
"loss": 0.4015,
"step": 29
},
{
"epoch": 0.7258064516129032,
"grad_norm": 23.554725646972656,
"learning_rate": 1.5e-06,
"loss": 0.2364,
"step": 30
},
{
"epoch": 0.75,
"grad_norm": 11.884359359741211,
"learning_rate": 1.5500000000000002e-06,
"loss": 0.1429,
"step": 31
},
{
"epoch": 0.7741935483870968,
"grad_norm": 5.657749176025391,
"learning_rate": 1.6000000000000001e-06,
"loss": 0.136,
"step": 32
},
{
"epoch": 0.7983870967741935,
"grad_norm": 3.42618465423584,
"learning_rate": 1.6500000000000003e-06,
"loss": 0.0964,
"step": 33
},
{
"epoch": 0.8225806451612904,
"grad_norm": 2.808098554611206,
"learning_rate": 1.7000000000000002e-06,
"loss": 0.0826,
"step": 34
},
{
"epoch": 0.8467741935483871,
"grad_norm": 2.475355625152588,
"learning_rate": 1.75e-06,
"loss": 0.0781,
"step": 35
},
{
"epoch": 0.8709677419354839,
"grad_norm": 1.9219006299972534,
"learning_rate": 1.8000000000000001e-06,
"loss": 0.0637,
"step": 36
},
{
"epoch": 0.8951612903225806,
"grad_norm": 1.8285995721817017,
"learning_rate": 1.85e-06,
"loss": 0.0708,
"step": 37
},
{
"epoch": 0.9193548387096774,
"grad_norm": 1.9102882146835327,
"learning_rate": 1.9000000000000002e-06,
"loss": 0.0865,
"step": 38
},
{
"epoch": 0.9435483870967742,
"grad_norm": 2.190868854522705,
"learning_rate": 1.9500000000000004e-06,
"loss": 0.0732,
"step": 39
},
{
"epoch": 0.967741935483871,
"grad_norm": 1.923084020614624,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0767,
"step": 40
},
{
"epoch": 0.9919354838709677,
"grad_norm": 1.8931093215942383,
"learning_rate": 2.05e-06,
"loss": 0.0868,
"step": 41
},
{
"epoch": 1.0,
"grad_norm": 1.8931093215942383,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.138,
"step": 42
},
{
"epoch": 1.0241935483870968,
"grad_norm": 6.719915866851807,
"learning_rate": 2.15e-06,
"loss": 0.0736,
"step": 43
},
{
"epoch": 1.0483870967741935,
"grad_norm": 1.6687527894973755,
"learning_rate": 2.2e-06,
"loss": 0.0675,
"step": 44
},
{
"epoch": 1.0725806451612903,
"grad_norm": 1.6767126321792603,
"learning_rate": 2.25e-06,
"loss": 0.0629,
"step": 45
},
{
"epoch": 1.096774193548387,
"grad_norm": 1.3529062271118164,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.0614,
"step": 46
},
{
"epoch": 1.120967741935484,
"grad_norm": 2.1146080493927,
"learning_rate": 2.35e-06,
"loss": 0.0602,
"step": 47
},
{
"epoch": 1.1451612903225807,
"grad_norm": 1.1904520988464355,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.0639,
"step": 48
},
{
"epoch": 1.1693548387096775,
"grad_norm": 1.1737815141677856,
"learning_rate": 2.4500000000000003e-06,
"loss": 0.0478,
"step": 49
},
{
"epoch": 1.1935483870967742,
"grad_norm": 1.3181250095367432,
"learning_rate": 2.5e-06,
"loss": 0.0564,
"step": 50
},
{
"epoch": 1.217741935483871,
"grad_norm": 2.057123899459839,
"learning_rate": 2.55e-06,
"loss": 0.0432,
"step": 51
},
{
"epoch": 1.2419354838709677,
"grad_norm": 1.1123464107513428,
"learning_rate": 2.6e-06,
"loss": 0.051,
"step": 52
},
{
"epoch": 1.2661290322580645,
"grad_norm": 1.5854344367980957,
"learning_rate": 2.6500000000000005e-06,
"loss": 0.0494,
"step": 53
},
{
"epoch": 1.2903225806451613,
"grad_norm": 1.2793511152267456,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.0464,
"step": 54
},
{
"epoch": 1.314516129032258,
"grad_norm": 1.3535298109054565,
"learning_rate": 2.7500000000000004e-06,
"loss": 0.0477,
"step": 55
},
{
"epoch": 1.3387096774193548,
"grad_norm": 1.186978816986084,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.0375,
"step": 56
},
{
"epoch": 1.3629032258064515,
"grad_norm": 1.4667912721633911,
"learning_rate": 2.85e-06,
"loss": 0.0424,
"step": 57
},
{
"epoch": 1.3870967741935485,
"grad_norm": 1.0930287837982178,
"learning_rate": 2.9e-06,
"loss": 0.0417,
"step": 58
},
{
"epoch": 1.4112903225806452,
"grad_norm": 1.5085082054138184,
"learning_rate": 2.95e-06,
"loss": 0.0479,
"step": 59
},
{
"epoch": 1.435483870967742,
"grad_norm": 1.4030777215957642,
"learning_rate": 3e-06,
"loss": 0.0413,
"step": 60
},
{
"epoch": 1.4596774193548387,
"grad_norm": 1.6423301696777344,
"learning_rate": 3.05e-06,
"loss": 0.0349,
"step": 61
},
{
"epoch": 1.4838709677419355,
"grad_norm": 1.3811825513839722,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.0482,
"step": 62
},
{
"epoch": 1.5080645161290323,
"grad_norm": 1.2499895095825195,
"learning_rate": 3.1500000000000003e-06,
"loss": 0.0308,
"step": 63
},
{
"epoch": 1.532258064516129,
"grad_norm": 1.1597909927368164,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.0293,
"step": 64
},
{
"epoch": 1.5564516129032258,
"grad_norm": 1.1042351722717285,
"learning_rate": 3.2500000000000002e-06,
"loss": 0.035,
"step": 65
},
{
"epoch": 1.5806451612903225,
"grad_norm": 1.13418710231781,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.0254,
"step": 66
},
{
"epoch": 1.6048387096774195,
"grad_norm": 0.934019148349762,
"learning_rate": 3.3500000000000005e-06,
"loss": 0.0283,
"step": 67
},
{
"epoch": 1.629032258064516,
"grad_norm": 1.468568205833435,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.0325,
"step": 68
},
{
"epoch": 1.653225806451613,
"grad_norm": 1.3268495798110962,
"learning_rate": 3.45e-06,
"loss": 0.027,
"step": 69
},
{
"epoch": 1.6774193548387095,
"grad_norm": 0.8941407203674316,
"learning_rate": 3.5e-06,
"loss": 0.0244,
"step": 70
},
{
"epoch": 1.7016129032258065,
"grad_norm": 1.0857181549072266,
"learning_rate": 3.5500000000000003e-06,
"loss": 0.0225,
"step": 71
},
{
"epoch": 1.7258064516129032,
"grad_norm": 1.1653308868408203,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.029,
"step": 72
},
{
"epoch": 1.75,
"grad_norm": 1.0501737594604492,
"learning_rate": 3.65e-06,
"loss": 0.0199,
"step": 73
},
{
"epoch": 1.7741935483870968,
"grad_norm": 0.8470718264579773,
"learning_rate": 3.7e-06,
"loss": 0.0219,
"step": 74
},
{
"epoch": 1.7983870967741935,
"grad_norm": 0.8664724826812744,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0161,
"step": 75
},
{
"epoch": 1.8225806451612905,
"grad_norm": 1.5050084590911865,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.0246,
"step": 76
},
{
"epoch": 1.846774193548387,
"grad_norm": 1.6326985359191895,
"learning_rate": 3.85e-06,
"loss": 0.0253,
"step": 77
},
{
"epoch": 1.870967741935484,
"grad_norm": 1.5506129264831543,
"learning_rate": 3.900000000000001e-06,
"loss": 0.0133,
"step": 78
},
{
"epoch": 1.8951612903225805,
"grad_norm": 0.7956012487411499,
"learning_rate": 3.95e-06,
"loss": 0.0093,
"step": 79
},
{
"epoch": 1.9193548387096775,
"grad_norm": 1.898987054824829,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0142,
"step": 80
},
{
"epoch": 1.9435483870967742,
"grad_norm": 0.832822859287262,
"learning_rate": 4.05e-06,
"loss": 0.0177,
"step": 81
},
{
"epoch": 1.967741935483871,
"grad_norm": 0.9572640657424927,
"learning_rate": 4.1e-06,
"loss": 0.0077,
"step": 82
},
{
"epoch": 1.9919354838709677,
"grad_norm": 0.6162229180335999,
"learning_rate": 4.15e-06,
"loss": 0.0078,
"step": 83
},
{
"epoch": 2.0,
"grad_norm": 0.6162229180335999,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.0152,
"step": 84
},
{
"epoch": 2.024193548387097,
"grad_norm": 2.586178779602051,
"learning_rate": 4.25e-06,
"loss": 0.0048,
"step": 85
},
{
"epoch": 2.0483870967741935,
"grad_norm": 0.6102266907691956,
"learning_rate": 4.3e-06,
"loss": 0.0079,
"step": 86
},
{
"epoch": 2.0725806451612905,
"grad_norm": 0.5254344940185547,
"learning_rate": 4.350000000000001e-06,
"loss": 0.0059,
"step": 87
},
{
"epoch": 2.096774193548387,
"grad_norm": 0.47239282727241516,
"learning_rate": 4.4e-06,
"loss": 0.0039,
"step": 88
},
{
"epoch": 2.120967741935484,
"grad_norm": 0.4822653830051422,
"learning_rate": 4.450000000000001e-06,
"loss": 0.0032,
"step": 89
},
{
"epoch": 2.1451612903225805,
"grad_norm": 0.26892364025115967,
"learning_rate": 4.5e-06,
"loss": 0.0022,
"step": 90
},
{
"epoch": 2.1693548387096775,
"grad_norm": 0.4505153298377991,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.006,
"step": 91
},
{
"epoch": 2.193548387096774,
"grad_norm": 0.4410068094730377,
"learning_rate": 4.600000000000001e-06,
"loss": 0.0037,
"step": 92
},
{
"epoch": 2.217741935483871,
"grad_norm": 0.5575999617576599,
"learning_rate": 4.65e-06,
"loss": 0.0062,
"step": 93
},
{
"epoch": 2.241935483870968,
"grad_norm": 0.8343164324760437,
"learning_rate": 4.7e-06,
"loss": 0.0051,
"step": 94
},
{
"epoch": 2.2661290322580645,
"grad_norm": 0.4667530655860901,
"learning_rate": 4.75e-06,
"loss": 0.0012,
"step": 95
},
{
"epoch": 2.2903225806451615,
"grad_norm": 0.4000648558139801,
"learning_rate": 4.800000000000001e-06,
"loss": 0.0029,
"step": 96
},
{
"epoch": 2.314516129032258,
"grad_norm": 0.37442290782928467,
"learning_rate": 4.85e-06,
"loss": 0.0009,
"step": 97
},
{
"epoch": 2.338709677419355,
"grad_norm": 1.7328227758407593,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.0022,
"step": 98
},
{
"epoch": 2.3629032258064515,
"grad_norm": 0.3352905511856079,
"learning_rate": 4.95e-06,
"loss": 0.0022,
"step": 99
},
{
"epoch": 2.3870967741935485,
"grad_norm": 0.26117730140686035,
"learning_rate": 5e-06,
"loss": 0.0029,
"step": 100
},
{
"epoch": 2.411290322580645,
"grad_norm": 0.7075008153915405,
"learning_rate": 4.999421254949728e-06,
"loss": 0.0011,
"step": 101
},
{
"epoch": 2.435483870967742,
"grad_norm": 0.05702031031250954,
"learning_rate": 4.9976852877555755e-06,
"loss": 0.0015,
"step": 102
},
{
"epoch": 2.4596774193548385,
"grad_norm": 1.964158058166504,
"learning_rate": 4.9947929021634815e-06,
"loss": 0.0019,
"step": 103
},
{
"epoch": 2.4838709677419355,
"grad_norm": 0.7456927299499512,
"learning_rate": 4.99074543733652e-06,
"loss": 0.002,
"step": 104
},
{
"epoch": 2.508064516129032,
"grad_norm": 0.5102735161781311,
"learning_rate": 4.98554476723488e-06,
"loss": 0.0039,
"step": 105
},
{
"epoch": 2.532258064516129,
"grad_norm": 0.7966336011886597,
"learning_rate": 4.979193299748225e-06,
"loss": 0.0009,
"step": 106
},
{
"epoch": 2.556451612903226,
"grad_norm": 0.024575965479016304,
"learning_rate": 4.971693975580851e-06,
"loss": 0.0009,
"step": 107
},
{
"epoch": 2.5806451612903225,
"grad_norm": 0.1903764009475708,
"learning_rate": 4.963050266890152e-06,
"loss": 0.001,
"step": 108
},
{
"epoch": 2.6048387096774195,
"grad_norm": 0.45592474937438965,
"learning_rate": 4.953266175679023e-06,
"loss": 0.0032,
"step": 109
},
{
"epoch": 2.629032258064516,
"grad_norm": 0.2592508792877197,
"learning_rate": 4.942346231942955e-06,
"loss": 0.0017,
"step": 110
},
{
"epoch": 2.653225806451613,
"grad_norm": 1.9442164897918701,
"learning_rate": 4.9302954915726535e-06,
"loss": 0.0004,
"step": 111
},
{
"epoch": 2.6774193548387095,
"grad_norm": 0.07151424884796143,
"learning_rate": 4.917119534013194e-06,
"loss": 0.0006,
"step": 112
},
{
"epoch": 2.7016129032258065,
"grad_norm": 0.08166387677192688,
"learning_rate": 4.9028244596807525e-06,
"loss": 0.0007,
"step": 113
},
{
"epoch": 2.725806451612903,
"grad_norm": 1.0235861539840698,
"learning_rate": 4.887416887138139e-06,
"loss": 0.0021,
"step": 114
},
{
"epoch": 2.75,
"grad_norm": 0.14721287786960602,
"learning_rate": 4.870903950030429e-06,
"loss": 0.0005,
"step": 115
},
{
"epoch": 2.774193548387097,
"grad_norm": 0.03769293054938316,
"learning_rate": 4.853293293782118e-06,
"loss": 0.0017,
"step": 116
},
{
"epoch": 2.7983870967741935,
"grad_norm": 1.2892156839370728,
"learning_rate": 4.834593072057313e-06,
"loss": 0.0005,
"step": 117
},
{
"epoch": 2.8225806451612905,
"grad_norm": 0.1497962474822998,
"learning_rate": 4.814811942984625e-06,
"loss": 0.0009,
"step": 118
},
{
"epoch": 2.846774193548387,
"grad_norm": 0.19922426342964172,
"learning_rate": 4.793959065148484e-06,
"loss": 0.0002,
"step": 119
},
{
"epoch": 2.870967741935484,
"grad_norm": 0.025655284523963928,
"learning_rate": 4.772044093348757e-06,
"loss": 0.0006,
"step": 120
},
{
"epoch": 2.8951612903225805,
"grad_norm": 0.6246688961982727,
"learning_rate": 4.749077174130609e-06,
"loss": 0.0002,
"step": 121
},
{
"epoch": 2.9193548387096775,
"grad_norm": 0.06197616085410118,
"learning_rate": 4.725068941086693e-06,
"loss": 0.0002,
"step": 122
},
{
"epoch": 2.943548387096774,
"grad_norm": 0.09112539142370224,
"learning_rate": 4.70003050993384e-06,
"loss": 0.0002,
"step": 123
},
{
"epoch": 2.967741935483871,
"grad_norm": 0.01392870768904686,
"learning_rate": 4.6739734733665275e-06,
"loss": 0.0001,
"step": 124
},
{
"epoch": 2.991935483870968,
"grad_norm": 0.0538908950984478,
"learning_rate": 4.646909895689508e-06,
"loss": 0.0002,
"step": 125
},
{
"epoch": 3.0,
"grad_norm": 0.011572198010981083,
"learning_rate": 4.618852307232078e-06,
"loss": 0.0,
"step": 126
},
{
"epoch": 3.024193548387097,
"grad_norm": 0.014770111069083214,
"learning_rate": 4.589813698546592e-06,
"loss": 0.0001,
"step": 127
},
{
"epoch": 3.0483870967741935,
"grad_norm": 0.024740448221564293,
"learning_rate": 4.5598075143938855e-06,
"loss": 0.0001,
"step": 128
},
{
"epoch": 3.0725806451612905,
"grad_norm": 0.010587488301098347,
"learning_rate": 4.528847647518403e-06,
"loss": 0.0001,
"step": 129
},
{
"epoch": 3.096774193548387,
"grad_norm": 0.008824610151350498,
"learning_rate": 4.4969484322159125e-06,
"loss": 0.0001,
"step": 130
},
{
"epoch": 3.120967741935484,
"grad_norm": 0.006249427329748869,
"learning_rate": 4.464124637696786e-06,
"loss": 0.0,
"step": 131
},
{
"epoch": 3.1451612903225805,
"grad_norm": 0.006542777642607689,
"learning_rate": 4.430391461247911e-06,
"loss": 0.0,
"step": 132
},
{
"epoch": 3.1693548387096775,
"grad_norm": 0.010512913577258587,
"learning_rate": 4.3957645211964065e-06,
"loss": 0.0,
"step": 133
},
{
"epoch": 3.193548387096774,
"grad_norm": 0.012207292020320892,
"learning_rate": 4.360259849678402e-06,
"loss": 0.0,
"step": 134
},
{
"epoch": 3.217741935483871,
"grad_norm": 0.008094793185591698,
"learning_rate": 4.3238938852162195e-06,
"loss": 0.0,
"step": 135
},
{
"epoch": 3.241935483870968,
"grad_norm": 0.004484089091420174,
"learning_rate": 4.286683465107403e-06,
"loss": 0.0,
"step": 136
},
{
"epoch": 3.2661290322580645,
"grad_norm": 0.005113545805215836,
"learning_rate": 4.2486458176291176e-06,
"loss": 0.0,
"step": 137
},
{
"epoch": 3.2903225806451615,
"grad_norm": 0.039181407541036606,
"learning_rate": 4.209798554061527e-06,
"loss": 0.0001,
"step": 138
},
{
"epoch": 3.314516129032258,
"grad_norm": 0.008053544908761978,
"learning_rate": 4.170159660533834e-06,
"loss": 0.0001,
"step": 139
},
{
"epoch": 3.338709677419355,
"grad_norm": 0.0030653164722025394,
"learning_rate": 4.129747489696781e-06,
"loss": 0.0,
"step": 140
},
{
"epoch": 3.3629032258064515,
"grad_norm": 0.0038352159317582846,
"learning_rate": 4.0885807522254435e-06,
"loss": 0.0,
"step": 141
},
{
"epoch": 3.3870967741935485,
"grad_norm": 0.023383919149637222,
"learning_rate": 4.046678508156259e-06,
"loss": 0.0,
"step": 142
},
{
"epoch": 3.411290322580645,
"grad_norm": 0.026204578578472137,
"learning_rate": 4.004060158062306e-06,
"loss": 0.0001,
"step": 143
},
{
"epoch": 3.435483870967742,
"grad_norm": 0.007208545226603746,
"learning_rate": 3.9607454340709215e-06,
"loss": 0.0,
"step": 144
},
{
"epoch": 3.4596774193548385,
"grad_norm": 0.005157825071364641,
"learning_rate": 3.916754390727795e-06,
"loss": 0.0,
"step": 145
},
{
"epoch": 3.4838709677419355,
"grad_norm": 0.0048579806461930275,
"learning_rate": 3.872107395711799e-06,
"loss": 0.0,
"step": 146
},
{
"epoch": 3.508064516129032,
"grad_norm": 0.003963091876357794,
"learning_rate": 3.8268251204048335e-06,
"loss": 0.0,
"step": 147
},
{
"epoch": 3.532258064516129,
"grad_norm": 0.003541983664035797,
"learning_rate": 3.78092853032106e-06,
"loss": 0.0,
"step": 148
},
{
"epoch": 3.556451612903226,
"grad_norm": 0.00556611642241478,
"learning_rate": 3.7344388753999434e-06,
"loss": 0.0,
"step": 149
},
{
"epoch": 3.5806451612903225,
"grad_norm": 0.005311247892677784,
"learning_rate": 3.6873776801676265e-06,
"loss": 0.0,
"step": 150
},
{
"epoch": 3.6048387096774195,
"grad_norm": 0.005124111659824848,
"learning_rate": 3.6397667337711475e-06,
"loss": 0.0,
"step": 151
},
{
"epoch": 3.629032258064516,
"grad_norm": 0.002724511083215475,
"learning_rate": 3.5916280798901604e-06,
"loss": 0.0,
"step": 152
},
{
"epoch": 3.653225806451613,
"grad_norm": 0.012781741097569466,
"learning_rate": 3.5429840065307924e-06,
"loss": 0.0001,
"step": 153
},
{
"epoch": 3.6774193548387095,
"grad_norm": 0.002880590036511421,
"learning_rate": 3.4938570357063906e-06,
"loss": 0.0,
"step": 154
},
{
"epoch": 3.7016129032258065,
"grad_norm": 0.007057458162307739,
"learning_rate": 3.444269913009912e-06,
"loss": 0.0,
"step": 155
},
{
"epoch": 3.725806451612903,
"grad_norm": 0.0030600889585912228,
"learning_rate": 3.3942455970828146e-06,
"loss": 0.0,
"step": 156
},
{
"epoch": 3.75,
"grad_norm": 0.0037060801405459642,
"learning_rate": 3.3438072489852837e-06,
"loss": 0.0,
"step": 157
},
{
"epoch": 3.774193548387097,
"grad_norm": 0.0037356216926127672,
"learning_rate": 3.2929782214727657e-06,
"loss": 0.0,
"step": 158
},
{
"epoch": 3.7983870967741935,
"grad_norm": 0.0021931882947683334,
"learning_rate": 3.241782048183726e-06,
"loss": 0.0,
"step": 159
},
{
"epoch": 3.8225806451612905,
"grad_norm": 0.0031978520564734936,
"learning_rate": 3.190242432743673e-06,
"loss": 0.0,
"step": 160
},
{
"epoch": 3.846774193548387,
"grad_norm": 0.0027142702601850033,
"learning_rate": 3.1383832377904676e-06,
"loss": 0.0,
"step": 161
},
{
"epoch": 3.870967741935484,
"grad_norm": 0.005236359313130379,
"learning_rate": 3.0862284739260247e-06,
"loss": 0.0,
"step": 162
},
{
"epoch": 3.8951612903225805,
"grad_norm": 0.00442493474110961,
"learning_rate": 3.0338022885994904e-06,
"loss": 0.0,
"step": 163
},
{
"epoch": 3.9193548387096775,
"grad_norm": 0.003939308691769838,
"learning_rate": 2.981128954927075e-06,
"loss": 0.0,
"step": 164
},
{
"epoch": 3.943548387096774,
"grad_norm": 0.0058077434077858925,
"learning_rate": 2.928232860453694e-06,
"loss": 0.0,
"step": 165
},
{
"epoch": 3.967741935483871,
"grad_norm": 0.012285425327718258,
"learning_rate": 2.8751384958616318e-06,
"loss": 0.0,
"step": 166
},
{
"epoch": 3.991935483870968,
"grad_norm": 0.005668473429977894,
"learning_rate": 2.8218704436314525e-06,
"loss": 0.0,
"step": 167
},
{
"epoch": 4.0,
"grad_norm": 0.005668473429977894,
"learning_rate": 2.768453366660408e-06,
"loss": 0.0,
"step": 168
},
{
"epoch": 4.024193548387097,
"grad_norm": 0.0070312549360096455,
"learning_rate": 2.714911996843617e-06,
"loss": 0.0,
"step": 169
},
{
"epoch": 4.048387096774194,
"grad_norm": 0.002901165746152401,
"learning_rate": 2.6612711236232915e-06,
"loss": 0.0,
"step": 170
},
{
"epoch": 4.07258064516129,
"grad_norm": 0.004153820686042309,
"learning_rate": 2.6075555825113265e-06,
"loss": 0.0,
"step": 171
},
{
"epoch": 4.096774193548387,
"grad_norm": 0.002925405977293849,
"learning_rate": 2.553790243590556e-06,
"loss": 0.0,
"step": 172
},
{
"epoch": 4.120967741935484,
"grad_norm": 0.0030930652283132076,
"learning_rate": 2.5e-06,
"loss": 0.0,
"step": 173
},
{
"epoch": 4.145161290322581,
"grad_norm": 0.002492116065695882,
"learning_rate": 2.446209756409445e-06,
"loss": 0.0,
"step": 174
},
{
"epoch": 4.169354838709677,
"grad_norm": 0.012719309888780117,
"learning_rate": 2.3924444174886735e-06,
"loss": 0.0,
"step": 175
},
{
"epoch": 4.193548387096774,
"grad_norm": 0.0035637742839753628,
"learning_rate": 2.3387288763767097e-06,
"loss": 0.0,
"step": 176
},
{
"epoch": 4.217741935483871,
"grad_norm": 0.002116712275892496,
"learning_rate": 2.2850880031563845e-06,
"loss": 0.0,
"step": 177
},
{
"epoch": 4.241935483870968,
"grad_norm": 0.002913803094998002,
"learning_rate": 2.2315466333395927e-06,
"loss": 0.0,
"step": 178
},
{
"epoch": 4.266129032258064,
"grad_norm": 0.002084016101434827,
"learning_rate": 2.178129556368548e-06,
"loss": 0.0,
"step": 179
},
{
"epoch": 4.290322580645161,
"grad_norm": 0.0027423023711889982,
"learning_rate": 2.1248615041383686e-06,
"loss": 0.0,
"step": 180
},
{
"epoch": 4.314516129032258,
"grad_norm": 0.0027472435031086206,
"learning_rate": 2.0717671395463063e-06,
"loss": 0.0,
"step": 181
},
{
"epoch": 4.338709677419355,
"grad_norm": 0.0022199389059096575,
"learning_rate": 2.0188710450729255e-06,
"loss": 0.0,
"step": 182
},
{
"epoch": 4.362903225806452,
"grad_norm": 0.0020855457987636328,
"learning_rate": 1.96619771140051e-06,
"loss": 0.0,
"step": 183
},
{
"epoch": 4.387096774193548,
"grad_norm": 0.001854368718340993,
"learning_rate": 1.913771526073976e-06,
"loss": 0.0,
"step": 184
},
{
"epoch": 4.411290322580645,
"grad_norm": 0.0019964484963566065,
"learning_rate": 1.8616167622095328e-06,
"loss": 0.0,
"step": 185
},
{
"epoch": 4.435483870967742,
"grad_norm": 0.0020302555058151484,
"learning_rate": 1.8097575672563278e-06,
"loss": 0.0,
"step": 186
},
{
"epoch": 4.459677419354839,
"grad_norm": 0.0028748398181051016,
"learning_rate": 1.7582179518162742e-06,
"loss": 0.0,
"step": 187
},
{
"epoch": 4.483870967741936,
"grad_norm": 0.0022295413073152304,
"learning_rate": 1.7070217785272354e-06,
"loss": 0.0,
"step": 188
},
{
"epoch": 4.508064516129032,
"grad_norm": 0.0026783861685544252,
"learning_rate": 1.6561927510147172e-06,
"loss": 0.0,
"step": 189
},
{
"epoch": 4.532258064516129,
"grad_norm": 0.002686347346752882,
"learning_rate": 1.6057544029171863e-06,
"loss": 0.0,
"step": 190
},
{
"epoch": 4.556451612903226,
"grad_norm": 0.002102716825902462,
"learning_rate": 1.5557300869900876e-06,
"loss": 0.0,
"step": 191
},
{
"epoch": 4.580645161290323,
"grad_norm": 0.002360268495976925,
"learning_rate": 1.5061429642936107e-06,
"loss": 0.0,
"step": 192
},
{
"epoch": 4.604838709677419,
"grad_norm": 0.0019272768404334784,
"learning_rate": 1.4570159934692085e-06,
"loss": 0.0,
"step": 193
},
{
"epoch": 4.629032258064516,
"grad_norm": 0.004223938565701246,
"learning_rate": 1.4083719201098404e-06,
"loss": 0.0,
"step": 194
},
{
"epoch": 4.653225806451613,
"grad_norm": 0.0030710650607943535,
"learning_rate": 1.3602332662288536e-06,
"loss": 0.0,
"step": 195
},
{
"epoch": 4.67741935483871,
"grad_norm": 0.0022593277972191572,
"learning_rate": 1.3126223198323752e-06,
"loss": 0.0,
"step": 196
},
{
"epoch": 4.701612903225806,
"grad_norm": 0.003411229234188795,
"learning_rate": 1.265561124600057e-06,
"loss": 0.0,
"step": 197
},
{
"epoch": 4.725806451612903,
"grad_norm": 0.0026067630387842655,
"learning_rate": 1.219071469678941e-06,
"loss": 0.0,
"step": 198
},
{
"epoch": 4.75,
"grad_norm": 0.0027266363613307476,
"learning_rate": 1.173174879595166e-06,
"loss": 0.0,
"step": 199
},
{
"epoch": 4.774193548387097,
"grad_norm": 0.001948651159182191,
"learning_rate": 1.1278926042882026e-06,
"loss": 0.0,
"step": 200
},
{
"epoch": 4.798387096774194,
"grad_norm": 0.0035516598727554083,
"learning_rate": 1.0832456092722063e-06,
"loss": 0.0,
"step": 201
},
{
"epoch": 4.82258064516129,
"grad_norm": 0.002599873812869191,
"learning_rate": 1.0392545659290789e-06,
"loss": 0.0,
"step": 202
},
{
"epoch": 4.846774193548387,
"grad_norm": 0.0024046015460044146,
"learning_rate": 9.95939841937693e-07,
"loss": 0.0,
"step": 203
},
{
"epoch": 4.870967741935484,
"grad_norm": 0.0016676371451467276,
"learning_rate": 9.533214918437422e-07,
"loss": 0.0,
"step": 204
},
{
"epoch": 4.895161290322581,
"grad_norm": 0.005082397721707821,
"learning_rate": 9.114192477745568e-07,
"loss": 0.0,
"step": 205
},
{
"epoch": 4.919354838709677,
"grad_norm": 0.0022361574228852987,
"learning_rate": 8.702525103032186e-07,
"loss": 0.0,
"step": 206
},
{
"epoch": 4.943548387096774,
"grad_norm": 0.00175854389090091,
"learning_rate": 8.298403394661658e-07,
"loss": 0.0,
"step": 207
},
{
"epoch": 4.967741935483871,
"grad_norm": 0.002364831743761897,
"learning_rate": 7.902014459384744e-07,
"loss": 0.0,
"step": 208
},
{
"epoch": 4.991935483870968,
"grad_norm": 0.0020899497903883457,
"learning_rate": 7.513541823708828e-07,
"loss": 0.0,
"step": 209
},
{
"epoch": 5.0,
"grad_norm": 0.0020899497903883457,
"learning_rate": 7.133165348925978e-07,
"loss": 0.0,
"step": 210
},
{
"epoch": 5.024193548387097,
"grad_norm": 0.0033509680069983006,
"learning_rate": 6.761061147837808e-07,
"loss": 0.0,
"step": 211
},
{
"epoch": 5.048387096774194,
"grad_norm": 0.0016700942069292068,
"learning_rate": 6.397401503215992e-07,
"loss": 0.0,
"step": 212
},
{
"epoch": 5.07258064516129,
"grad_norm": 0.0036097129341214895,
"learning_rate": 6.042354788035943e-07,
"loss": 0.0,
"step": 213
},
{
"epoch": 5.096774193548387,
"grad_norm": 0.0019725814927369356,
"learning_rate": 5.696085387520894e-07,
"loss": 0.0,
"step": 214
},
{
"epoch": 5.120967741935484,
"grad_norm": 0.002575285965576768,
"learning_rate": 5.358753623032137e-07,
"loss": 0.0,
"step": 215
},
{
"epoch": 5.145161290322581,
"grad_norm": 0.0023315041325986385,
"learning_rate": 5.030515677840883e-07,
"loss": 0.0,
"step": 216
},
{
"epoch": 5.169354838709677,
"grad_norm": 0.002346003893762827,
"learning_rate": 4.711523524815978e-07,
"loss": 0.0,
"step": 217
},
{
"epoch": 5.193548387096774,
"grad_norm": 0.0021207425743341446,
"learning_rate": 4.401924856061146e-07,
"loss": 0.0,
"step": 218
},
{
"epoch": 5.217741935483871,
"grad_norm": 0.003580324584618211,
"learning_rate": 4.1018630145340744e-07,
"loss": 0.0,
"step": 219
},
{
"epoch": 5.241935483870968,
"grad_norm": 0.0020650820806622505,
"learning_rate": 3.811476927679228e-07,
"loss": 0.0,
"step": 220
},
{
"epoch": 5.266129032258064,
"grad_norm": 0.0015676968032494187,
"learning_rate": 3.5309010431049284e-07,
"loss": 0.0,
"step": 221
},
{
"epoch": 5.290322580645161,
"grad_norm": 0.0023263345938175917,
"learning_rate": 3.260265266334725e-07,
"loss": 0.0,
"step": 222
},
{
"epoch": 5.314516129032258,
"grad_norm": 0.00231003575026989,
"learning_rate": 2.9996949006616096e-07,
"loss": 0.0,
"step": 223
},
{
"epoch": 5.338709677419355,
"grad_norm": 0.0019675635267049074,
"learning_rate": 2.7493105891330837e-07,
"loss": 0.0,
"step": 224
},
{
"epoch": 5.362903225806452,
"grad_norm": 0.002346566179767251,
"learning_rate": 2.5092282586939187e-07,
"loss": 0.0,
"step": 225
},
{
"epoch": 5.387096774193548,
"grad_norm": 0.0021014949306845665,
"learning_rate": 2.2795590665124267e-07,
"loss": 0.0,
"step": 226
},
{
"epoch": 5.411290322580645,
"grad_norm": 0.0017796737374737859,
"learning_rate": 2.0604093485151548e-07,
"loss": 0.0,
"step": 227
},
{
"epoch": 5.435483870967742,
"grad_norm": 0.0015546936774626374,
"learning_rate": 1.851880570153755e-07,
"loss": 0.0,
"step": 228
},
{
"epoch": 5.459677419354839,
"grad_norm": 0.0038863597437739372,
"learning_rate": 1.654069279426873e-07,
"loss": 0.0,
"step": 229
},
{
"epoch": 5.483870967741936,
"grad_norm": 0.0019028914393857121,
"learning_rate": 1.467067062178823e-07,
"loss": 0.0,
"step": 230
},
{
"epoch": 5.508064516129032,
"grad_norm": 0.0014524314319714904,
"learning_rate": 1.2909604996957093e-07,
"loss": 0.0,
"step": 231
},
{
"epoch": 5.532258064516129,
"grad_norm": 0.0026214567478746176,
"learning_rate": 1.1258311286186208e-07,
"loss": 0.0,
"step": 232
},
{
"epoch": 5.556451612903226,
"grad_norm": 0.001435131300240755,
"learning_rate": 9.717554031924842e-08,
"loss": 0.0,
"step": 233
},
{
"epoch": 5.580645161290323,
"grad_norm": 0.0044931466691195965,
"learning_rate": 8.288046598680627e-08,
"loss": 0.0,
"step": 234
},
{
"epoch": 5.604838709677419,
"grad_norm": 0.0016189351445063949,
"learning_rate": 6.97045084273465e-08,
"loss": 0.0,
"step": 235
},
{
"epoch": 5.629032258064516,
"grad_norm": 0.0017611249350011349,
"learning_rate": 5.7653768057045757e-08,
"loss": 0.0,
"step": 236
},
{
"epoch": 5.653225806451613,
"grad_norm": 0.002121084136888385,
"learning_rate": 4.6733824320976674e-08,
"loss": 0.0,
"step": 237
},
{
"epoch": 5.67741935483871,
"grad_norm": 0.0014778735348954797,
"learning_rate": 3.6949733109848395e-08,
"loss": 0.0,
"step": 238
},
{
"epoch": 5.701612903225806,
"grad_norm": 0.026431361213326454,
"learning_rate": 2.8306024419148814e-08,
"loss": 0.0,
"step": 239
},
{
"epoch": 5.725806451612903,
"grad_norm": 0.0016552675515413284,
"learning_rate": 2.0806700251775057e-08,
"loss": 0.0,
"step": 240
},
{
"epoch": 5.75,
"grad_norm": 0.006627636030316353,
"learning_rate": 1.4455232765120397e-08,
"loss": 0.0,
"step": 241
},
{
"epoch": 5.774193548387097,
"grad_norm": 0.0024116451386362314,
"learning_rate": 9.25456266348046e-09,
"loss": 0.0,
"step": 242
},
{
"epoch": 5.798387096774194,
"grad_norm": 0.001904924400150776,
"learning_rate": 5.20709783651957e-09,
"loss": 0.0,
"step": 243
},
{
"epoch": 5.82258064516129,
"grad_norm": 0.0022408179938793182,
"learning_rate": 2.3147122444250327e-09,
"loss": 0.0,
"step": 244
},
{
"epoch": 5.846774193548387,
"grad_norm": 0.0030523776076734066,
"learning_rate": 5.787450502728331e-10,
"loss": 0.0,
"step": 245
},
{
"epoch": 5.870967741935484,
"grad_norm": 0.0039012248162180185,
"learning_rate": 0.0,
"loss": 0.0,
"step": 246
}
],
"logging_steps": 1,
"max_steps": 246,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 41,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.098273592095539e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}