ece5861e6d
Model: fpadovani/isl-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.29655990510083036,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.151007413864136,
|
|
"epoch": 0.0004942665085013839,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.279,
|
|
"mean_token_accuracy": 0.08845784291625022,
|
|
"num_tokens": 11289.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.142992544174194,
|
|
"epoch": 0.0009885330170027679,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.2577,
|
|
"mean_token_accuracy": 0.08933138325810433,
|
|
"num_tokens": 21541.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.182202959060669,
|
|
"epoch": 0.0014827995255041518,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.2317,
|
|
"mean_token_accuracy": 0.0934896469116211,
|
|
"num_tokens": 32257.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.244844675064087,
|
|
"epoch": 0.0019770660340055358,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.2492,
|
|
"mean_token_accuracy": 0.09298909306526185,
|
|
"num_tokens": 44176.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.262534332275391,
|
|
"epoch": 0.0024713325425069197,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.1678,
|
|
"mean_token_accuracy": 0.09061622098088265,
|
|
"num_tokens": 56115.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.378157377243042,
|
|
"epoch": 0.0029655990510083037,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.2162,
|
|
"mean_token_accuracy": 0.09287815466523171,
|
|
"num_tokens": 68828.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.399503707885742,
|
|
"epoch": 0.0034598655595096876,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.2093,
|
|
"mean_token_accuracy": 0.09124612733721733,
|
|
"num_tokens": 80097.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.373995113372803,
|
|
"epoch": 0.0039541320680110716,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.1903,
|
|
"mean_token_accuracy": 0.09260638207197189,
|
|
"num_tokens": 91510.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.330695772171021,
|
|
"epoch": 0.004448398576512456,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.234,
|
|
"mean_token_accuracy": 0.09660193100571632,
|
|
"num_tokens": 103443.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.33756799697876,
|
|
"epoch": 0.0049426650850138395,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.2565,
|
|
"mean_token_accuracy": 0.09188243448734283,
|
|
"num_tokens": 114629.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.324716234207154,
|
|
"epoch": 0.005436931593515224,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.2396,
|
|
"mean_token_accuracy": 0.09266308695077896,
|
|
"num_tokens": 125012.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.393645143508911,
|
|
"epoch": 0.005931198102016607,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.1731,
|
|
"mean_token_accuracy": 0.09935653060674668,
|
|
"num_tokens": 135834.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.348312473297119,
|
|
"epoch": 0.006425464610517992,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.0755,
|
|
"mean_token_accuracy": 0.10009140819311142,
|
|
"num_tokens": 147413.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.368169450759888,
|
|
"epoch": 0.006919731119019375,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.2672,
|
|
"mean_token_accuracy": 0.09652369320392609,
|
|
"num_tokens": 158046.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.3670432567596436,
|
|
"epoch": 0.00741399762752076,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.1792,
|
|
"mean_token_accuracy": 0.09774387776851653,
|
|
"num_tokens": 168564.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.313370609283448,
|
|
"epoch": 0.007908264136022143,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.1885,
|
|
"mean_token_accuracy": 0.09465310201048852,
|
|
"num_tokens": 181168.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.35333480834961,
|
|
"epoch": 0.008402530644523527,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.1552,
|
|
"mean_token_accuracy": 0.09859942272305489,
|
|
"num_tokens": 192666.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.388514804840088,
|
|
"epoch": 0.008896797153024912,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.2204,
|
|
"mean_token_accuracy": 0.09482975378632545,
|
|
"num_tokens": 203688.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.303425407409668,
|
|
"epoch": 0.009391063661526295,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.0729,
|
|
"mean_token_accuracy": 0.10156495124101639,
|
|
"num_tokens": 214399.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.27442512512207,
|
|
"epoch": 0.009885330170027679,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.1681,
|
|
"mean_token_accuracy": 0.09274221584200859,
|
|
"num_tokens": 227549.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.317437267303466,
|
|
"epoch": 0.010379596678529062,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.0679,
|
|
"mean_token_accuracy": 0.11123422309756278,
|
|
"num_tokens": 239612.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.363053894042968,
|
|
"epoch": 0.010873863187030448,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.1978,
|
|
"mean_token_accuracy": 0.09392422363162041,
|
|
"num_tokens": 251163.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.261190605163574,
|
|
"epoch": 0.011368129695531831,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.0645,
|
|
"mean_token_accuracy": 0.10441159456968307,
|
|
"num_tokens": 263995.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.40733699798584,
|
|
"epoch": 0.011862396204033215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.2354,
|
|
"mean_token_accuracy": 0.08496984019875527,
|
|
"num_tokens": 275103.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.273692512512207,
|
|
"epoch": 0.012356662712534598,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.1369,
|
|
"mean_token_accuracy": 0.0968512661755085,
|
|
"num_tokens": 286838.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.423242712020874,
|
|
"epoch": 0.012850929221035983,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.1665,
|
|
"mean_token_accuracy": 0.09364857673645019,
|
|
"num_tokens": 298750.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.250139808654785,
|
|
"epoch": 0.013345195729537367,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.0329,
|
|
"mean_token_accuracy": 0.10625170543789864,
|
|
"num_tokens": 310451.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.348578405380249,
|
|
"epoch": 0.01383946223803875,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.1935,
|
|
"mean_token_accuracy": 0.09695170894265175,
|
|
"num_tokens": 321232.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.488092279434204,
|
|
"epoch": 0.014333728746540134,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.106,
|
|
"mean_token_accuracy": 0.09741687774658203,
|
|
"num_tokens": 332531.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.19592809677124,
|
|
"epoch": 0.01482799525504152,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.1008,
|
|
"mean_token_accuracy": 0.09623056724667549,
|
|
"num_tokens": 346002.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.401388263702392,
|
|
"epoch": 0.015322261763542903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.0874,
|
|
"mean_token_accuracy": 0.09739502891898155,
|
|
"num_tokens": 356691.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.243306970596313,
|
|
"epoch": 0.015816528272044286,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.0938,
|
|
"mean_token_accuracy": 0.1009882666170597,
|
|
"num_tokens": 368749.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.3369566917419435,
|
|
"epoch": 0.01631079478054567,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.0241,
|
|
"mean_token_accuracy": 0.10501249730587006,
|
|
"num_tokens": 379484.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.281102800369263,
|
|
"epoch": 0.016805061289047053,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.0703,
|
|
"mean_token_accuracy": 0.09354055374860763,
|
|
"num_tokens": 389751.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.325433778762817,
|
|
"epoch": 0.017299327797548437,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.0892,
|
|
"mean_token_accuracy": 0.09684126302599907,
|
|
"num_tokens": 400771.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.323175096511841,
|
|
"epoch": 0.017793594306049824,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.1061,
|
|
"mean_token_accuracy": 0.09781083017587662,
|
|
"num_tokens": 413575.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.328048992156982,
|
|
"epoch": 0.018287860814551207,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.0467,
|
|
"mean_token_accuracy": 0.09532680064439773,
|
|
"num_tokens": 424825.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.333641099929809,
|
|
"epoch": 0.01878212732305259,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.1064,
|
|
"mean_token_accuracy": 0.10553916320204734,
|
|
"num_tokens": 435610.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.328917694091797,
|
|
"epoch": 0.019276393831553974,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.1187,
|
|
"mean_token_accuracy": 0.0999750517308712,
|
|
"num_tokens": 445855.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.2166337966918945,
|
|
"epoch": 0.019770660340055358,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.0063,
|
|
"mean_token_accuracy": 0.10225539430975913,
|
|
"num_tokens": 456895.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.476543855667114,
|
|
"epoch": 0.02026492684855674,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.1414,
|
|
"mean_token_accuracy": 0.09506701603531838,
|
|
"num_tokens": 467446.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.272785186767578,
|
|
"epoch": 0.020759193357058125,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.0607,
|
|
"mean_token_accuracy": 0.09756421521306038,
|
|
"num_tokens": 478988.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.290947103500367,
|
|
"epoch": 0.02125345986555951,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.0557,
|
|
"mean_token_accuracy": 0.10137153342366219,
|
|
"num_tokens": 491053.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.357240819931031,
|
|
"epoch": 0.021747726374060895,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.1334,
|
|
"mean_token_accuracy": 0.09304505437612534,
|
|
"num_tokens": 502279.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.198823118209839,
|
|
"epoch": 0.02224199288256228,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.0177,
|
|
"mean_token_accuracy": 0.10008044987916946,
|
|
"num_tokens": 513470.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.373158121109009,
|
|
"epoch": 0.022736259391063662,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.0871,
|
|
"mean_token_accuracy": 0.096877521276474,
|
|
"num_tokens": 524380.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.324968671798706,
|
|
"epoch": 0.023230525899565046,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.0885,
|
|
"mean_token_accuracy": 0.10163207277655602,
|
|
"num_tokens": 535798.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.273069143295288,
|
|
"epoch": 0.02372479240806643,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.0313,
|
|
"mean_token_accuracy": 0.10062324851751328,
|
|
"num_tokens": 545720.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.329104614257813,
|
|
"epoch": 0.024219058916567813,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.0595,
|
|
"mean_token_accuracy": 0.09972514137625695,
|
|
"num_tokens": 557110.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.1850278854370115,
|
|
"epoch": 0.024713325425069196,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.016,
|
|
"mean_token_accuracy": 0.10394479855895042,
|
|
"num_tokens": 568966.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.360903692245484,
|
|
"epoch": 0.02520759193357058,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.0469,
|
|
"mean_token_accuracy": 0.10300094187259674,
|
|
"num_tokens": 580441.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.301402139663696,
|
|
"epoch": 0.025701858442071967,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.0452,
|
|
"mean_token_accuracy": 0.09699605703353882,
|
|
"num_tokens": 592698.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.190503692626953,
|
|
"epoch": 0.02619612495057335,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.0198,
|
|
"mean_token_accuracy": 0.10279446840286255,
|
|
"num_tokens": 604787.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.302949237823486,
|
|
"epoch": 0.026690391459074734,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.013,
|
|
"mean_token_accuracy": 0.09963318407535553,
|
|
"num_tokens": 616445.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.2669110774993895,
|
|
"epoch": 0.027184657967576117,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.0808,
|
|
"mean_token_accuracy": 0.1002419799566269,
|
|
"num_tokens": 627723.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.345779991149902,
|
|
"epoch": 0.0276789244760775,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1067,
|
|
"mean_token_accuracy": 0.10031414031982422,
|
|
"num_tokens": 638987.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.279949617385864,
|
|
"epoch": 0.028173190984578884,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.9384,
|
|
"mean_token_accuracy": 0.10166889876127243,
|
|
"num_tokens": 650626.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.149828386306763,
|
|
"epoch": 0.028667457493080268,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.9604,
|
|
"mean_token_accuracy": 0.10975496619939804,
|
|
"num_tokens": 661911.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.256064605712891,
|
|
"epoch": 0.02916172400158165,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0137,
|
|
"mean_token_accuracy": 0.10477377250790595,
|
|
"num_tokens": 674298.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.236632680892944,
|
|
"epoch": 0.02965599051008304,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.9431,
|
|
"mean_token_accuracy": 0.10994272455573081,
|
|
"num_tokens": 686000.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.216502523422241,
|
|
"epoch": 0.030150257018584422,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.9926,
|
|
"mean_token_accuracy": 0.10297218561172486,
|
|
"num_tokens": 698464.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.215946102142334,
|
|
"epoch": 0.030644523527085805,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.9883,
|
|
"mean_token_accuracy": 0.09871925041079521,
|
|
"num_tokens": 709702.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.40031623840332,
|
|
"epoch": 0.03113879003558719,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.1009,
|
|
"mean_token_accuracy": 0.09918646588921547,
|
|
"num_tokens": 722234.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.222815370559692,
|
|
"epoch": 0.03163305654408857,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.0443,
|
|
"mean_token_accuracy": 0.10143259838223458,
|
|
"num_tokens": 733001.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.251048564910889,
|
|
"epoch": 0.03212732305258996,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.0047,
|
|
"mean_token_accuracy": 0.09862519353628159,
|
|
"num_tokens": 743315.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.253071928024292,
|
|
"epoch": 0.03262158956109134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.9549,
|
|
"mean_token_accuracy": 0.09725747108459473,
|
|
"num_tokens": 754386.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.24435601234436,
|
|
"epoch": 0.033115856069592726,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.0694,
|
|
"mean_token_accuracy": 0.10413578823208809,
|
|
"num_tokens": 766504.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.090495014190674,
|
|
"epoch": 0.033610122578094107,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.9017,
|
|
"mean_token_accuracy": 0.10729243233799934,
|
|
"num_tokens": 777039.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.284985685348511,
|
|
"epoch": 0.034104389086595494,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.0025,
|
|
"mean_token_accuracy": 0.10153071135282517,
|
|
"num_tokens": 787890.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.234701490402221,
|
|
"epoch": 0.034598655595096874,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9532,
|
|
"mean_token_accuracy": 0.10262288972735405,
|
|
"num_tokens": 800129.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.139390373229981,
|
|
"epoch": 0.03509292210359826,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.0596,
|
|
"mean_token_accuracy": 0.0944197230041027,
|
|
"num_tokens": 812517.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.259590196609497,
|
|
"epoch": 0.03558718861209965,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.9787,
|
|
"mean_token_accuracy": 0.10446251705288886,
|
|
"num_tokens": 824570.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.1810768127441404,
|
|
"epoch": 0.03608145512060103,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.9823,
|
|
"mean_token_accuracy": 0.1032750204205513,
|
|
"num_tokens": 836506.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.251035213470459,
|
|
"epoch": 0.036575721629102415,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.9702,
|
|
"mean_token_accuracy": 0.10457680597901345,
|
|
"num_tokens": 846841.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.27037239074707,
|
|
"epoch": 0.037069988137603795,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.0054,
|
|
"mean_token_accuracy": 0.106174336373806,
|
|
"num_tokens": 858770.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.1212574481964115,
|
|
"epoch": 0.03756425464610518,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8786,
|
|
"mean_token_accuracy": 0.10385922640562058,
|
|
"num_tokens": 870184.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.172485733032227,
|
|
"epoch": 0.03805852115460656,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.9197,
|
|
"mean_token_accuracy": 0.10581747069954872,
|
|
"num_tokens": 881843.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.2427778244018555,
|
|
"epoch": 0.03855278766310795,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9489,
|
|
"mean_token_accuracy": 0.10129198804497719,
|
|
"num_tokens": 893453.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.205210494995117,
|
|
"epoch": 0.03904705417160933,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.0049,
|
|
"mean_token_accuracy": 0.09680559858679771,
|
|
"num_tokens": 904417.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.202549695968628,
|
|
"epoch": 0.039541320680110716,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.9462,
|
|
"mean_token_accuracy": 0.0999035358428955,
|
|
"num_tokens": 915134.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.133806133270264,
|
|
"epoch": 0.0400355871886121,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.9589,
|
|
"mean_token_accuracy": 0.1034577377140522,
|
|
"num_tokens": 926361.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.144542980194092,
|
|
"epoch": 0.04052985369711348,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.8841,
|
|
"mean_token_accuracy": 0.10176018252968788,
|
|
"num_tokens": 937474.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.3199704647064205,
|
|
"epoch": 0.04102412020561487,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.947,
|
|
"mean_token_accuracy": 0.10589171275496483,
|
|
"num_tokens": 948897.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.157266998291016,
|
|
"epoch": 0.04151838671411625,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9643,
|
|
"mean_token_accuracy": 0.1008329525589943,
|
|
"num_tokens": 960669.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.024852180480957,
|
|
"epoch": 0.04201265322261764,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8152,
|
|
"mean_token_accuracy": 0.10260056778788566,
|
|
"num_tokens": 973001.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.119008874893188,
|
|
"epoch": 0.04250691973111902,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8859,
|
|
"mean_token_accuracy": 0.10822405442595481,
|
|
"num_tokens": 986214.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.105495595932007,
|
|
"epoch": 0.043001186239620404,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8937,
|
|
"mean_token_accuracy": 0.10061700344085693,
|
|
"num_tokens": 997363.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.120448970794678,
|
|
"epoch": 0.04349545274812179,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.8093,
|
|
"mean_token_accuracy": 0.11288737356662751,
|
|
"num_tokens": 1009543.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.0541246891021725,
|
|
"epoch": 0.04398971925662317,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.9215,
|
|
"mean_token_accuracy": 0.10269275158643723,
|
|
"num_tokens": 1020561.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.185726308822632,
|
|
"epoch": 0.04448398576512456,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8725,
|
|
"mean_token_accuracy": 0.10224331989884376,
|
|
"num_tokens": 1032587.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.159319496154785,
|
|
"epoch": 0.04497825227362594,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8784,
|
|
"mean_token_accuracy": 0.1019284375011921,
|
|
"num_tokens": 1044249.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.076584959030152,
|
|
"epoch": 0.045472518782127325,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.9215,
|
|
"mean_token_accuracy": 0.10558762773871422,
|
|
"num_tokens": 1055415.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.1408079147338865,
|
|
"epoch": 0.045966785290628705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8942,
|
|
"mean_token_accuracy": 0.10558660700917244,
|
|
"num_tokens": 1066593.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.15621657371521,
|
|
"epoch": 0.04646105179913009,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8924,
|
|
"mean_token_accuracy": 0.10691260844469071,
|
|
"num_tokens": 1076966.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.067881631851196,
|
|
"epoch": 0.04695531830763147,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.9491,
|
|
"mean_token_accuracy": 0.09959092512726783,
|
|
"num_tokens": 1089927.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.091880464553833,
|
|
"epoch": 0.04744958481613286,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.8869,
|
|
"mean_token_accuracy": 0.10327862426638604,
|
|
"num_tokens": 1101920.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.182226657867432,
|
|
"epoch": 0.047943851324634246,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.9376,
|
|
"mean_token_accuracy": 0.10818986669182777,
|
|
"num_tokens": 1115078.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.180230808258057,
|
|
"epoch": 0.048438117833135626,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.0315,
|
|
"mean_token_accuracy": 0.0969414807856083,
|
|
"num_tokens": 1127138.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.088583707809448,
|
|
"epoch": 0.04893238434163701,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.815,
|
|
"mean_token_accuracy": 0.10144753381609917,
|
|
"num_tokens": 1138390.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.003582715988159,
|
|
"epoch": 0.04942665085013839,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.78,
|
|
"mean_token_accuracy": 0.11048796996474267,
|
|
"num_tokens": 1149124.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.101625585556031,
|
|
"epoch": 0.04992091735863978,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.8585,
|
|
"mean_token_accuracy": 0.10951191484928131,
|
|
"num_tokens": 1161091.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.118922424316406,
|
|
"epoch": 0.05041518386714116,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.8355,
|
|
"mean_token_accuracy": 0.10461836084723472,
|
|
"num_tokens": 1171919.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.051087188720703,
|
|
"epoch": 0.05090945037564255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.8633,
|
|
"mean_token_accuracy": 0.10401171222329139,
|
|
"num_tokens": 1183688.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.0168451309204105,
|
|
"epoch": 0.051403716884143934,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.7819,
|
|
"mean_token_accuracy": 0.10449134409427643,
|
|
"num_tokens": 1195323.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.09809103012085,
|
|
"epoch": 0.051897983392645314,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.8999,
|
|
"mean_token_accuracy": 0.10218222662806511,
|
|
"num_tokens": 1206782.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.965949535369873,
|
|
"epoch": 0.0523922499011467,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.8013,
|
|
"mean_token_accuracy": 0.10973932594060898,
|
|
"num_tokens": 1218102.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.017365598678589,
|
|
"epoch": 0.05288651640964808,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.7659,
|
|
"mean_token_accuracy": 0.10771052315831184,
|
|
"num_tokens": 1230199.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.0721368312835695,
|
|
"epoch": 0.05338078291814947,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.8896,
|
|
"mean_token_accuracy": 0.10399755015969277,
|
|
"num_tokens": 1242127.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.027034282684326,
|
|
"epoch": 0.05387504942665085,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.7655,
|
|
"mean_token_accuracy": 0.10667505711317063,
|
|
"num_tokens": 1252329.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.865018033981324,
|
|
"epoch": 0.054369315935152235,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7666,
|
|
"mean_token_accuracy": 0.11077538877725601,
|
|
"num_tokens": 1264832.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.053894948959351,
|
|
"epoch": 0.054863582443653615,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.8414,
|
|
"mean_token_accuracy": 0.10259129181504249,
|
|
"num_tokens": 1276708.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.017140913009643,
|
|
"epoch": 0.055357848952155,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.7446,
|
|
"mean_token_accuracy": 0.11817902401089668,
|
|
"num_tokens": 1288089.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.102619647979736,
|
|
"epoch": 0.05585211546065639,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.9011,
|
|
"mean_token_accuracy": 0.10063079670071602,
|
|
"num_tokens": 1299411.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.038193321228027,
|
|
"epoch": 0.05634638196915777,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.8678,
|
|
"mean_token_accuracy": 0.10497712716460228,
|
|
"num_tokens": 1311368.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.996581506729126,
|
|
"epoch": 0.056840648477659156,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.7798,
|
|
"mean_token_accuracy": 0.1104745551943779,
|
|
"num_tokens": 1321962.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.984814691543579,
|
|
"epoch": 0.057334914986160536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.7845,
|
|
"mean_token_accuracy": 0.10723584592342376,
|
|
"num_tokens": 1335150.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.0060882568359375,
|
|
"epoch": 0.05782918149466192,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.8106,
|
|
"mean_token_accuracy": 0.10954170823097228,
|
|
"num_tokens": 1346986.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.04237003326416,
|
|
"epoch": 0.0583234480031633,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.7456,
|
|
"mean_token_accuracy": 0.11029022559523582,
|
|
"num_tokens": 1357820.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.898483562469482,
|
|
"epoch": 0.05881771451166469,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.7381,
|
|
"mean_token_accuracy": 0.1155846431851387,
|
|
"num_tokens": 1368269.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.914667129516602,
|
|
"epoch": 0.05931198102016608,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.7699,
|
|
"mean_token_accuracy": 0.10781971290707588,
|
|
"num_tokens": 1380364.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.9423737049102785,
|
|
"epoch": 0.05980624752866746,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.7359,
|
|
"mean_token_accuracy": 0.11458505317568779,
|
|
"num_tokens": 1390667.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.890728282928467,
|
|
"epoch": 0.060300514037168844,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6885,
|
|
"mean_token_accuracy": 0.10985699743032455,
|
|
"num_tokens": 1401452.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.968847942352295,
|
|
"epoch": 0.060794780545670224,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6936,
|
|
"mean_token_accuracy": 0.11100370958447456,
|
|
"num_tokens": 1412947.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.867507553100586,
|
|
"epoch": 0.06128904705417161,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.7476,
|
|
"mean_token_accuracy": 0.10398394390940666,
|
|
"num_tokens": 1425123.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.928701877593994,
|
|
"epoch": 0.06178331356267299,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.7218,
|
|
"mean_token_accuracy": 0.10982921719551086,
|
|
"num_tokens": 1436538.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.933251285552979,
|
|
"epoch": 0.06227758007117438,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.77,
|
|
"mean_token_accuracy": 0.10577303692698478,
|
|
"num_tokens": 1448269.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.900527620315552,
|
|
"epoch": 0.06277184657967576,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.7432,
|
|
"mean_token_accuracy": 0.11349172964692116,
|
|
"num_tokens": 1459729.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.960564184188843,
|
|
"epoch": 0.06326611308817714,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.7581,
|
|
"mean_token_accuracy": 0.10724205747246743,
|
|
"num_tokens": 1470684.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.889400863647461,
|
|
"epoch": 0.06376037959667853,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.7232,
|
|
"mean_token_accuracy": 0.10671663433313369,
|
|
"num_tokens": 1483571.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.8848834991455075,
|
|
"epoch": 0.06425464610517992,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6891,
|
|
"mean_token_accuracy": 0.11692152470350266,
|
|
"num_tokens": 1494671.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.905150508880615,
|
|
"epoch": 0.06474891261368129,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.7095,
|
|
"mean_token_accuracy": 0.1126905307173729,
|
|
"num_tokens": 1505435.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.948776197433472,
|
|
"epoch": 0.06524317912218268,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.803,
|
|
"mean_token_accuracy": 0.10531418174505233,
|
|
"num_tokens": 1518510.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.9253791809082035,
|
|
"epoch": 0.06573744563068407,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.7145,
|
|
"mean_token_accuracy": 0.11463218927383423,
|
|
"num_tokens": 1530218.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.91641206741333,
|
|
"epoch": 0.06623171213918545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.7582,
|
|
"mean_token_accuracy": 0.11466718763113022,
|
|
"num_tokens": 1542486.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.8444969177246096,
|
|
"epoch": 0.06672597864768683,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.7533,
|
|
"mean_token_accuracy": 0.10930409133434296,
|
|
"num_tokens": 1553873.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.942787122726441,
|
|
"epoch": 0.06722024515618821,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.7047,
|
|
"mean_token_accuracy": 0.1153480589389801,
|
|
"num_tokens": 1565343.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.903558826446533,
|
|
"epoch": 0.0677145116646896,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.7608,
|
|
"mean_token_accuracy": 0.10652155056595802,
|
|
"num_tokens": 1577061.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.872377204895019,
|
|
"epoch": 0.06820877817319099,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.7529,
|
|
"mean_token_accuracy": 0.11244799494743347,
|
|
"num_tokens": 1588083.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.879619789123535,
|
|
"epoch": 0.06870304468169237,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.7159,
|
|
"mean_token_accuracy": 0.10822473615407943,
|
|
"num_tokens": 1599796.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.90326623916626,
|
|
"epoch": 0.06919731119019375,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.7681,
|
|
"mean_token_accuracy": 0.10771963074803352,
|
|
"num_tokens": 1611994.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.872850322723389,
|
|
"epoch": 0.06969157769869513,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.7022,
|
|
"mean_token_accuracy": 0.10573551878333091,
|
|
"num_tokens": 1623280.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.8690471172332765,
|
|
"epoch": 0.07018584420719652,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.7681,
|
|
"mean_token_accuracy": 0.10785022675991059,
|
|
"num_tokens": 1634989.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.947969198226929,
|
|
"epoch": 0.07068011071569791,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.7925,
|
|
"mean_token_accuracy": 0.10478616431355477,
|
|
"num_tokens": 1647042.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.809376001358032,
|
|
"epoch": 0.0711743772241993,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.6855,
|
|
"mean_token_accuracy": 0.1154635414481163,
|
|
"num_tokens": 1659245.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.81630311012268,
|
|
"epoch": 0.07166864373270067,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.6819,
|
|
"mean_token_accuracy": 0.10983811244368553,
|
|
"num_tokens": 1670271.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.873712110519409,
|
|
"epoch": 0.07216291024120206,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.735,
|
|
"mean_token_accuracy": 0.11080555841326714,
|
|
"num_tokens": 1682648.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.822260570526123,
|
|
"epoch": 0.07265717674970344,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.7573,
|
|
"mean_token_accuracy": 0.1052017480134964,
|
|
"num_tokens": 1694542.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.849833726882935,
|
|
"epoch": 0.07315144325820483,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.6493,
|
|
"mean_token_accuracy": 0.10704348310828209,
|
|
"num_tokens": 1705737.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.862112379074096,
|
|
"epoch": 0.0736457097667062,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.71,
|
|
"mean_token_accuracy": 0.10965840369462967,
|
|
"num_tokens": 1718474.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.826199579238891,
|
|
"epoch": 0.07413997627520759,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.6873,
|
|
"mean_token_accuracy": 0.1082968644797802,
|
|
"num_tokens": 1729360.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.8160795211792,
|
|
"epoch": 0.07463424278370898,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.6964,
|
|
"mean_token_accuracy": 0.1107470378279686,
|
|
"num_tokens": 1739654.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.836647272109985,
|
|
"epoch": 0.07512850929221036,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.6939,
|
|
"mean_token_accuracy": 0.11239867880940438,
|
|
"num_tokens": 1752158.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.834174489974975,
|
|
"epoch": 0.07562277580071175,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.6923,
|
|
"mean_token_accuracy": 0.11612112373113632,
|
|
"num_tokens": 1764545.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.821158313751221,
|
|
"epoch": 0.07611704230921312,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.6814,
|
|
"mean_token_accuracy": 0.1128039114177227,
|
|
"num_tokens": 1775422.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.840568494796753,
|
|
"epoch": 0.07661130881771451,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.7088,
|
|
"mean_token_accuracy": 0.10114984959363937,
|
|
"num_tokens": 1787833.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.74714674949646,
|
|
"epoch": 0.0771055753262159,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5723,
|
|
"mean_token_accuracy": 0.1219009131193161,
|
|
"num_tokens": 1798508.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.753849983215332,
|
|
"epoch": 0.07759984183471728,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.6209,
|
|
"mean_token_accuracy": 0.11469837054610252,
|
|
"num_tokens": 1809873.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.821059226989746,
|
|
"epoch": 0.07809410834321866,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.7014,
|
|
"mean_token_accuracy": 0.11237634271383286,
|
|
"num_tokens": 1820876.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.7968470573425295,
|
|
"epoch": 0.07858837485172004,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.663,
|
|
"mean_token_accuracy": 0.10904834121465683,
|
|
"num_tokens": 1833233.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.812273120880127,
|
|
"epoch": 0.07908264136022143,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.7481,
|
|
"mean_token_accuracy": 0.10785818174481392,
|
|
"num_tokens": 1844520.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.765308666229248,
|
|
"epoch": 0.07957690786872282,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.6292,
|
|
"mean_token_accuracy": 0.1142186164855957,
|
|
"num_tokens": 1856814.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.732009649276733,
|
|
"epoch": 0.0800711743772242,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.6196,
|
|
"mean_token_accuracy": 0.11811698004603385,
|
|
"num_tokens": 1867581.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.84562578201294,
|
|
"epoch": 0.08056544088572558,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.6907,
|
|
"mean_token_accuracy": 0.10590304806828499,
|
|
"num_tokens": 1879302.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.756962633132934,
|
|
"epoch": 0.08105970739422697,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.6571,
|
|
"mean_token_accuracy": 0.10640354081988335,
|
|
"num_tokens": 1891697.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.759096002578735,
|
|
"epoch": 0.08155397390272835,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5979,
|
|
"mean_token_accuracy": 0.11474953293800354,
|
|
"num_tokens": 1903544.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.774603033065796,
|
|
"epoch": 0.08204824041122974,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.6545,
|
|
"mean_token_accuracy": 0.11101827323436737,
|
|
"num_tokens": 1915286.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.688508129119873,
|
|
"epoch": 0.08254250691973111,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.11861704438924789,
|
|
"num_tokens": 1926361.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.751745128631592,
|
|
"epoch": 0.0830367734282325,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.11083293855190277,
|
|
"num_tokens": 1938540.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.763704109191894,
|
|
"epoch": 0.08353103993673389,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.10724062249064445,
|
|
"num_tokens": 1950532.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.8038843154907225,
|
|
"epoch": 0.08402530644523527,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.6778,
|
|
"mean_token_accuracy": 0.10919453650712967,
|
|
"num_tokens": 1960899.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.68118052482605,
|
|
"epoch": 0.08451957295373666,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6496,
|
|
"mean_token_accuracy": 0.11730073392391205,
|
|
"num_tokens": 1972278.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.725075197219849,
|
|
"epoch": 0.08501383946223803,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.6692,
|
|
"mean_token_accuracy": 0.1092053584754467,
|
|
"num_tokens": 1985079.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.635829877853394,
|
|
"epoch": 0.08550810597073942,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.7065,
|
|
"mean_token_accuracy": 0.10706321522593498,
|
|
"num_tokens": 1996467.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.8284436702728275,
|
|
"epoch": 0.08600237247924081,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.5832,
|
|
"mean_token_accuracy": 0.11370615139603615,
|
|
"num_tokens": 2007339.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.677596378326416,
|
|
"epoch": 0.0864966389877422,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5879,
|
|
"mean_token_accuracy": 0.1196245089173317,
|
|
"num_tokens": 2019962.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.747453260421753,
|
|
"epoch": 0.08699090549624358,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.5866,
|
|
"mean_token_accuracy": 0.11758355721831322,
|
|
"num_tokens": 2031251.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.661469602584839,
|
|
"epoch": 0.08748517200474495,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.6013,
|
|
"mean_token_accuracy": 0.11161932870745658,
|
|
"num_tokens": 2042412.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.6397772312164305,
|
|
"epoch": 0.08797943851324634,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6221,
|
|
"mean_token_accuracy": 0.11210491955280304,
|
|
"num_tokens": 2054423.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.686139965057373,
|
|
"epoch": 0.08847370502174773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.595,
|
|
"mean_token_accuracy": 0.10692231729626656,
|
|
"num_tokens": 2065657.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.717379331588745,
|
|
"epoch": 0.08896797153024912,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.5827,
|
|
"mean_token_accuracy": 0.11325386464595795,
|
|
"num_tokens": 2076305.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.697859430313111,
|
|
"epoch": 0.08946223803875049,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.5783,
|
|
"mean_token_accuracy": 0.11316154897212982,
|
|
"num_tokens": 2087734.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.595232200622559,
|
|
"epoch": 0.08995650454725188,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4953,
|
|
"mean_token_accuracy": 0.12035880610346794,
|
|
"num_tokens": 2098016.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.665337467193604,
|
|
"epoch": 0.09045077105575326,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.6678,
|
|
"mean_token_accuracy": 0.10886707603931427,
|
|
"num_tokens": 2110293.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.673768377304077,
|
|
"epoch": 0.09094503756425465,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4485,
|
|
"mean_token_accuracy": 0.11682527139782906,
|
|
"num_tokens": 2120441.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.539246511459351,
|
|
"epoch": 0.09143930407275604,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.5683,
|
|
"mean_token_accuracy": 0.11887063086032867,
|
|
"num_tokens": 2131520.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.664091300964356,
|
|
"epoch": 0.09193357058125741,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.5796,
|
|
"mean_token_accuracy": 0.11637971252202987,
|
|
"num_tokens": 2145005.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.605041790008545,
|
|
"epoch": 0.0924278370897588,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.5338,
|
|
"mean_token_accuracy": 0.1211809828877449,
|
|
"num_tokens": 2156608.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.601588439941406,
|
|
"epoch": 0.09292210359826018,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5318,
|
|
"mean_token_accuracy": 0.11969754993915557,
|
|
"num_tokens": 2168341.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.625442409515381,
|
|
"epoch": 0.09341637010676157,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.5258,
|
|
"mean_token_accuracy": 0.11236160099506379,
|
|
"num_tokens": 2178704.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.704224395751953,
|
|
"epoch": 0.09391063661526294,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.6906,
|
|
"mean_token_accuracy": 0.10928287953138352,
|
|
"num_tokens": 2190884.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.682482194900513,
|
|
"epoch": 0.09440490312376433,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.598,
|
|
"mean_token_accuracy": 0.1167626291513443,
|
|
"num_tokens": 2201822.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.629432439804077,
|
|
"epoch": 0.09489916963226572,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.5926,
|
|
"mean_token_accuracy": 0.11254436299204826,
|
|
"num_tokens": 2213362.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.692664337158203,
|
|
"epoch": 0.0953934361407671,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.602,
|
|
"mean_token_accuracy": 0.11311232969164849,
|
|
"num_tokens": 2224366.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.46690821647644,
|
|
"epoch": 0.09588770264926849,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4535,
|
|
"mean_token_accuracy": 0.1190331868827343,
|
|
"num_tokens": 2234645.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.678108978271484,
|
|
"epoch": 0.09638196915776986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.5498,
|
|
"mean_token_accuracy": 0.12018159404397011,
|
|
"num_tokens": 2245904.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.4710277080535885,
|
|
"epoch": 0.09687623566627125,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.49,
|
|
"mean_token_accuracy": 0.11942838132381439,
|
|
"num_tokens": 2257753.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.551316976547241,
|
|
"epoch": 0.09737050217477264,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4953,
|
|
"mean_token_accuracy": 0.1244705080986023,
|
|
"num_tokens": 2269009.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.693281459808349,
|
|
"epoch": 0.09786476868327403,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.5493,
|
|
"mean_token_accuracy": 0.11529032737016678,
|
|
"num_tokens": 2279840.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.533772134780884,
|
|
"epoch": 0.0983590351917754,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5154,
|
|
"mean_token_accuracy": 0.11877169013023377,
|
|
"num_tokens": 2290577.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.553924179077148,
|
|
"epoch": 0.09885330170027679,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5274,
|
|
"mean_token_accuracy": 0.12048136815428734,
|
|
"num_tokens": 2301341.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.566124486923218,
|
|
"epoch": 0.09934756820877817,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999982287888,
|
|
"loss": 6.5896,
|
|
"mean_token_accuracy": 0.11639286801218987,
|
|
"num_tokens": 2312505.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.718512153625488,
|
|
"epoch": 0.09984183471727956,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999910332434,
|
|
"loss": 6.5236,
|
|
"mean_token_accuracy": 0.11419004276394844,
|
|
"num_tokens": 2323443.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.4791271686553955,
|
|
"epoch": 0.10033610122578095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999783026635,
|
|
"loss": 6.5439,
|
|
"mean_token_accuracy": 0.11673406213521957,
|
|
"num_tokens": 2335686.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.514018297195435,
|
|
"epoch": 0.10083036773428232,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999600370491,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.11814445331692695,
|
|
"num_tokens": 2347273.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.552177906036377,
|
|
"epoch": 0.1013246342427837,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999362364008,
|
|
"loss": 6.4427,
|
|
"mean_token_accuracy": 0.12624893859028816,
|
|
"num_tokens": 2358011.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.5004723072052,
|
|
"epoch": 0.1018189007512851,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999069007191,
|
|
"loss": 6.5815,
|
|
"mean_token_accuracy": 0.11536967605352402,
|
|
"num_tokens": 2371390.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.596110677719116,
|
|
"epoch": 0.10231316725978648,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999998720300048,
|
|
"loss": 6.5271,
|
|
"mean_token_accuracy": 0.12005563005805016,
|
|
"num_tokens": 2381887.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.551437664031982,
|
|
"epoch": 0.10280743376828787,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999998316242589,
|
|
"loss": 6.4663,
|
|
"mean_token_accuracy": 0.11999196782708169,
|
|
"num_tokens": 2393632.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.530908870697021,
|
|
"epoch": 0.10330170027678924,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999997856834821,
|
|
"loss": 6.4778,
|
|
"mean_token_accuracy": 0.12028345614671707,
|
|
"num_tokens": 2405686.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.457987642288208,
|
|
"epoch": 0.10379596678529063,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999997342076757,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.11674800738692284,
|
|
"num_tokens": 2417459.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.636799621582031,
|
|
"epoch": 0.10429023329379201,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999996771968408,
|
|
"loss": 6.4995,
|
|
"mean_token_accuracy": 0.11853041127324104,
|
|
"num_tokens": 2428689.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.509030675888061,
|
|
"epoch": 0.1047844998022934,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999996146509791,
|
|
"loss": 6.5295,
|
|
"mean_token_accuracy": 0.11135807186365128,
|
|
"num_tokens": 2439437.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.580507850646972,
|
|
"epoch": 0.10527876631079477,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999995465700919,
|
|
"loss": 6.5104,
|
|
"mean_token_accuracy": 0.11756298467516899,
|
|
"num_tokens": 2450576.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.587932443618774,
|
|
"epoch": 0.10577303281929616,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999994729541809,
|
|
"loss": 6.6509,
|
|
"mean_token_accuracy": 0.11502083018422127,
|
|
"num_tokens": 2462684.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.633237361907959,
|
|
"epoch": 0.10626729932779755,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999993938032481,
|
|
"loss": 6.5244,
|
|
"mean_token_accuracy": 0.12519583106040955,
|
|
"num_tokens": 2474193.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.394119358062744,
|
|
"epoch": 0.10676156583629894,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999993091172952,
|
|
"loss": 6.4655,
|
|
"mean_token_accuracy": 0.11539505198597907,
|
|
"num_tokens": 2486264.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.555998420715332,
|
|
"epoch": 0.10725583234480032,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999992188963245,
|
|
"loss": 6.4541,
|
|
"mean_token_accuracy": 0.12652762085199357,
|
|
"num_tokens": 2497668.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.488944244384766,
|
|
"epoch": 0.1077500988533017,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499999123140338,
|
|
"loss": 6.5113,
|
|
"mean_token_accuracy": 0.11666428670287132,
|
|
"num_tokens": 2509635.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.545294523239136,
|
|
"epoch": 0.10824436536180308,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999990218493382,
|
|
"loss": 6.5051,
|
|
"mean_token_accuracy": 0.12337316423654557,
|
|
"num_tokens": 2521980.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.497365427017212,
|
|
"epoch": 0.10873863187030447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999989150233276,
|
|
"loss": 6.4639,
|
|
"mean_token_accuracy": 0.11867155879735947,
|
|
"num_tokens": 2533750.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.565949201583862,
|
|
"epoch": 0.10923289837880586,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999988026623088,
|
|
"loss": 6.5618,
|
|
"mean_token_accuracy": 0.11584960371255874,
|
|
"num_tokens": 2545620.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.454707479476928,
|
|
"epoch": 0.10972716488730723,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999986847662843,
|
|
"loss": 6.3302,
|
|
"mean_token_accuracy": 0.13472548872232437,
|
|
"num_tokens": 2556463.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.503189325332642,
|
|
"epoch": 0.11022143139580862,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999985613352576,
|
|
"loss": 6.5358,
|
|
"mean_token_accuracy": 0.12201443389058113,
|
|
"num_tokens": 2567396.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.544538831710815,
|
|
"epoch": 0.11071569790431,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999984323692311,
|
|
"loss": 6.48,
|
|
"mean_token_accuracy": 0.123195381462574,
|
|
"num_tokens": 2579208.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.412357044219971,
|
|
"epoch": 0.11120996441281139,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999982978682085,
|
|
"loss": 6.4248,
|
|
"mean_token_accuracy": 0.12385009601712227,
|
|
"num_tokens": 2590940.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.558205413818359,
|
|
"epoch": 0.11170423092131278,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999981578321927,
|
|
"loss": 6.51,
|
|
"mean_token_accuracy": 0.1274452067911625,
|
|
"num_tokens": 2602491.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.439068698883057,
|
|
"epoch": 0.11219849742981415,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999980122611874,
|
|
"loss": 6.3438,
|
|
"mean_token_accuracy": 0.12809207662940025,
|
|
"num_tokens": 2612139.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.445886325836182,
|
|
"epoch": 0.11269276393831554,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499997861155196,
|
|
"loss": 6.5104,
|
|
"mean_token_accuracy": 0.12374393939971924,
|
|
"num_tokens": 2624906.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.474299335479737,
|
|
"epoch": 0.11318703044681692,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999977045142223,
|
|
"loss": 6.4204,
|
|
"mean_token_accuracy": 0.12185963913798332,
|
|
"num_tokens": 2636046.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.521690130233765,
|
|
"epoch": 0.11368129695531831,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999975423382703,
|
|
"loss": 6.4288,
|
|
"mean_token_accuracy": 0.13111222088336943,
|
|
"num_tokens": 2645617.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.534403610229492,
|
|
"epoch": 0.11417556346381968,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999973746273438,
|
|
"loss": 6.4529,
|
|
"mean_token_accuracy": 0.12487476840615272,
|
|
"num_tokens": 2656780.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.454224348068237,
|
|
"epoch": 0.11466982997232107,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499997201381447,
|
|
"loss": 6.438,
|
|
"mean_token_accuracy": 0.1251967266201973,
|
|
"num_tokens": 2668078.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.491998386383057,
|
|
"epoch": 0.11516409648082246,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999970226005841,
|
|
"loss": 6.5242,
|
|
"mean_token_accuracy": 0.11767346188426017,
|
|
"num_tokens": 2679049.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.53035717010498,
|
|
"epoch": 0.11565836298932385,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999968382847595,
|
|
"loss": 6.4624,
|
|
"mean_token_accuracy": 0.12308069095015525,
|
|
"num_tokens": 2690165.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.536982250213623,
|
|
"epoch": 0.11615262949782523,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999966484339778,
|
|
"loss": 6.5002,
|
|
"mean_token_accuracy": 0.116629458963871,
|
|
"num_tokens": 2701965.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.402723407745361,
|
|
"epoch": 0.1166468960063266,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999964530482437,
|
|
"loss": 6.421,
|
|
"mean_token_accuracy": 0.12439692988991738,
|
|
"num_tokens": 2713479.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.465710687637329,
|
|
"epoch": 0.11714116251482799,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999962521275619,
|
|
"loss": 6.436,
|
|
"mean_token_accuracy": 0.12075797766447068,
|
|
"num_tokens": 2725629.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.268183088302612,
|
|
"epoch": 0.11763542902332938,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999960456719374,
|
|
"loss": 6.3492,
|
|
"mean_token_accuracy": 0.12263342142105102,
|
|
"num_tokens": 2736620.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.464852428436279,
|
|
"epoch": 0.11812969553183077,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999958336813753,
|
|
"loss": 6.3325,
|
|
"mean_token_accuracy": 0.1303306147456169,
|
|
"num_tokens": 2747118.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.372828674316406,
|
|
"epoch": 0.11862396204033215,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999956161558807,
|
|
"loss": 6.3799,
|
|
"mean_token_accuracy": 0.1274876520037651,
|
|
"num_tokens": 2758371.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.391465854644776,
|
|
"epoch": 0.11911822854883353,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999953930954591,
|
|
"loss": 6.3852,
|
|
"mean_token_accuracy": 0.12252886295318603,
|
|
"num_tokens": 2770575.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.448058319091797,
|
|
"epoch": 0.11961249505733491,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999951645001159,
|
|
"loss": 6.3455,
|
|
"mean_token_accuracy": 0.1301012769341469,
|
|
"num_tokens": 2783103.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.436516189575196,
|
|
"epoch": 0.1201067615658363,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999949303698568,
|
|
"loss": 6.4665,
|
|
"mean_token_accuracy": 0.12414569854736328,
|
|
"num_tokens": 2796636.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.406609773635864,
|
|
"epoch": 0.12060102807433769,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999946907046875,
|
|
"loss": 6.322,
|
|
"mean_token_accuracy": 0.13122917115688323,
|
|
"num_tokens": 2807798.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.362497234344483,
|
|
"epoch": 0.12109529458283906,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999944455046139,
|
|
"loss": 6.439,
|
|
"mean_token_accuracy": 0.12562692314386367,
|
|
"num_tokens": 2819255.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.454278612136841,
|
|
"epoch": 0.12158956109134045,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499994194769642,
|
|
"loss": 6.4012,
|
|
"mean_token_accuracy": 0.1260200709104538,
|
|
"num_tokens": 2829952.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.518359088897705,
|
|
"epoch": 0.12208382759984183,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499993938499778,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.1282096892595291,
|
|
"num_tokens": 2841056.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.377371597290039,
|
|
"epoch": 0.12257809410834322,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999936766950283,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.13203255608677864,
|
|
"num_tokens": 2852045.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.4568657875061035,
|
|
"epoch": 0.12307236061684461,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999934093553992,
|
|
"loss": 6.434,
|
|
"mean_token_accuracy": 0.12442487627267837,
|
|
"num_tokens": 2863440.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.430741882324218,
|
|
"epoch": 0.12356662712534598,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999931364808972,
|
|
"loss": 6.4369,
|
|
"mean_token_accuracy": 0.1217712052166462,
|
|
"num_tokens": 2874017.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.364642333984375,
|
|
"epoch": 0.12406089363384737,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999928580715293,
|
|
"loss": 6.3657,
|
|
"mean_token_accuracy": 0.1264870472252369,
|
|
"num_tokens": 2885677.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.433004665374756,
|
|
"epoch": 0.12455516014234876,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499992574127302,
|
|
"loss": 6.4812,
|
|
"mean_token_accuracy": 0.1225816085934639,
|
|
"num_tokens": 2897825.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.524859094619751,
|
|
"epoch": 0.12504942665085014,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999922846482226,
|
|
"loss": 6.5257,
|
|
"mean_token_accuracy": 0.1220851257443428,
|
|
"num_tokens": 2909304.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.429646253585815,
|
|
"epoch": 0.12554369315935152,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999919896342981,
|
|
"loss": 6.4588,
|
|
"mean_token_accuracy": 0.12074072510004044,
|
|
"num_tokens": 2920918.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.501003408432007,
|
|
"epoch": 0.12603795966785292,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999916890855358,
|
|
"loss": 6.4073,
|
|
"mean_token_accuracy": 0.12426696866750717,
|
|
"num_tokens": 2932294.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.363391876220703,
|
|
"epoch": 0.1265322261763543,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999913830019431,
|
|
"loss": 6.3237,
|
|
"mean_token_accuracy": 0.13384533002972604,
|
|
"num_tokens": 2943372.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.311191463470459,
|
|
"epoch": 0.12702649268485566,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999910713835272,
|
|
"loss": 6.3047,
|
|
"mean_token_accuracy": 0.13015900626778604,
|
|
"num_tokens": 2953807.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.342788410186768,
|
|
"epoch": 0.12752075919335706,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999907542302962,
|
|
"loss": 6.2438,
|
|
"mean_token_accuracy": 0.13418981581926345,
|
|
"num_tokens": 2964372.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.376524639129639,
|
|
"epoch": 0.12801502570185844,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999904315422577,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.1274750992655754,
|
|
"num_tokens": 2975537.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.296396970748901,
|
|
"epoch": 0.12850929221035984,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999901033194198,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.12614937424659728,
|
|
"num_tokens": 2986094.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.412167549133301,
|
|
"epoch": 0.1290035587188612,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999897695617904,
|
|
"loss": 6.4284,
|
|
"mean_token_accuracy": 0.12951384037733077,
|
|
"num_tokens": 2996023.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.477496385574341,
|
|
"epoch": 0.12949782522736258,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999894302693778,
|
|
"loss": 6.4201,
|
|
"mean_token_accuracy": 0.12168471738696099,
|
|
"num_tokens": 3007584.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.470839118957519,
|
|
"epoch": 0.12999209173586398,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999890854421902,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.11812516897916794,
|
|
"num_tokens": 3018995.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.263270092010498,
|
|
"epoch": 0.13048635824436536,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999887350802362,
|
|
"loss": 6.2577,
|
|
"mean_token_accuracy": 0.13282620459794997,
|
|
"num_tokens": 3030576.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.371448612213134,
|
|
"epoch": 0.13098062475286676,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999883791835246,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.12991052865982056,
|
|
"num_tokens": 3040765.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.39703049659729,
|
|
"epoch": 0.13147489126136813,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999880177520637,
|
|
"loss": 6.3713,
|
|
"mean_token_accuracy": 0.12290074527263642,
|
|
"num_tokens": 3053912.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.269509172439575,
|
|
"epoch": 0.1319691577698695,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999876507858628,
|
|
"loss": 6.358,
|
|
"mean_token_accuracy": 0.12943168208003045,
|
|
"num_tokens": 3065921.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.491255092620849,
|
|
"epoch": 0.1324634242783709,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999872782849308,
|
|
"loss": 6.4118,
|
|
"mean_token_accuracy": 0.1217479057610035,
|
|
"num_tokens": 3078643.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.297278165817261,
|
|
"epoch": 0.13295769078687228,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999869002492768,
|
|
"loss": 6.3262,
|
|
"mean_token_accuracy": 0.12477339208126068,
|
|
"num_tokens": 3090300.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.313536787033081,
|
|
"epoch": 0.13345195729537365,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999865166789102,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.13334870636463164,
|
|
"num_tokens": 3102307.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.430685234069824,
|
|
"epoch": 0.13394622380387505,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999861275738404,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.12200917750597,
|
|
"num_tokens": 3113817.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.360499048233033,
|
|
"epoch": 0.13444049031237643,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999857329340769,
|
|
"loss": 6.2516,
|
|
"mean_token_accuracy": 0.12839845269918443,
|
|
"num_tokens": 3124719.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.246741867065429,
|
|
"epoch": 0.13493475682087783,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999853327596295,
|
|
"loss": 6.2873,
|
|
"mean_token_accuracy": 0.1282256707549095,
|
|
"num_tokens": 3136136.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.370300054550171,
|
|
"epoch": 0.1354290233293792,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499984927050508,
|
|
"loss": 6.3012,
|
|
"mean_token_accuracy": 0.1290183626115322,
|
|
"num_tokens": 3148977.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.377018070220947,
|
|
"epoch": 0.13592328983788057,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999845158067223,
|
|
"loss": 6.3579,
|
|
"mean_token_accuracy": 0.1252500332891941,
|
|
"num_tokens": 3160520.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.366725778579712,
|
|
"epoch": 0.13641755634638197,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999840990282828,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.12962477132678032,
|
|
"num_tokens": 3172895.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.324902153015136,
|
|
"epoch": 0.13691182285488335,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999836767151994,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.13052070513367653,
|
|
"num_tokens": 3183960.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.330108976364135,
|
|
"epoch": 0.13740608936338475,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999832488674827,
|
|
"loss": 6.3886,
|
|
"mean_token_accuracy": 0.1273997098207474,
|
|
"num_tokens": 3194276.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.366259002685547,
|
|
"epoch": 0.13790035587188612,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999828154851432,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.13061744794249536,
|
|
"num_tokens": 3206084.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.301025104522705,
|
|
"epoch": 0.1383946223803875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999823765681915,
|
|
"loss": 6.2972,
|
|
"mean_token_accuracy": 0.13314774185419082,
|
|
"num_tokens": 3217941.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.338549423217773,
|
|
"epoch": 0.1388888888888889,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999819321166385,
|
|
"loss": 6.2742,
|
|
"mean_token_accuracy": 0.13190385103225707,
|
|
"num_tokens": 3229088.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.25566258430481,
|
|
"epoch": 0.13938315539739027,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499981482130495,
|
|
"loss": 6.2205,
|
|
"mean_token_accuracy": 0.13236010000109671,
|
|
"num_tokens": 3240708.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.294620752334595,
|
|
"epoch": 0.13987742190589167,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999810266097721,
|
|
"loss": 6.3444,
|
|
"mean_token_accuracy": 0.1264272078871727,
|
|
"num_tokens": 3251040.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.291800880432129,
|
|
"epoch": 0.14037168841439304,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999805655544811,
|
|
"loss": 6.2912,
|
|
"mean_token_accuracy": 0.13168664127588273,
|
|
"num_tokens": 3262655.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.291258907318115,
|
|
"epoch": 0.14086595492289442,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999800989646333,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.13803994432091712,
|
|
"num_tokens": 3273160.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.300457239151001,
|
|
"epoch": 0.14136022143139582,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999796268402401,
|
|
"loss": 6.2783,
|
|
"mean_token_accuracy": 0.1296892285346985,
|
|
"num_tokens": 3285932.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.249773216247559,
|
|
"epoch": 0.1418544879398972,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999791491813132,
|
|
"loss": 6.2971,
|
|
"mean_token_accuracy": 0.12768914625048639,
|
|
"num_tokens": 3298834.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.409033393859863,
|
|
"epoch": 0.1423487544483986,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999786659878643,
|
|
"loss": 6.2799,
|
|
"mean_token_accuracy": 0.12664505764842032,
|
|
"num_tokens": 3310473.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.182092523574829,
|
|
"epoch": 0.14284302095689996,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999781772599055,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.13217792585492133,
|
|
"num_tokens": 3322662.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.391679096221924,
|
|
"epoch": 0.14333728746540134,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999776829974484,
|
|
"loss": 6.3475,
|
|
"mean_token_accuracy": 0.132525734603405,
|
|
"num_tokens": 3334321.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.246479558944702,
|
|
"epoch": 0.14383155397390274,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999771832005055,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.13095758333802224,
|
|
"num_tokens": 3345130.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.2692060470581055,
|
|
"epoch": 0.1443258204824041,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499976677869089,
|
|
"loss": 6.2271,
|
|
"mean_token_accuracy": 0.13088599741458892,
|
|
"num_tokens": 3355601.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.194102716445923,
|
|
"epoch": 0.14482008699090548,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999761670032115,
|
|
"loss": 6.2295,
|
|
"mean_token_accuracy": 0.13360995799303055,
|
|
"num_tokens": 3367075.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.32319974899292,
|
|
"epoch": 0.14531435349940688,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999756506028851,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.13329043239355087,
|
|
"num_tokens": 3378888.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.248707866668701,
|
|
"epoch": 0.14580862000790826,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999751286681229,
|
|
"loss": 6.2325,
|
|
"mean_token_accuracy": 0.1328907147049904,
|
|
"num_tokens": 3390705.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.288841915130615,
|
|
"epoch": 0.14630288651640966,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999746011989376,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.1373384565114975,
|
|
"num_tokens": 3401710.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.346017694473266,
|
|
"epoch": 0.14679715302491103,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999740681953422,
|
|
"loss": 6.3789,
|
|
"mean_token_accuracy": 0.1264251612126827,
|
|
"num_tokens": 3413467.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.331368350982666,
|
|
"epoch": 0.1472914195334124,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999735296573499,
|
|
"loss": 6.3007,
|
|
"mean_token_accuracy": 0.13292821869254112,
|
|
"num_tokens": 3425885.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.329574871063232,
|
|
"epoch": 0.1477856860419138,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999729855849738,
|
|
"loss": 6.3151,
|
|
"mean_token_accuracy": 0.12490678578615189,
|
|
"num_tokens": 3437952.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.267677640914917,
|
|
"epoch": 0.14827995255041518,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999724359782274,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.1455492317676544,
|
|
"num_tokens": 3449680.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.317681789398193,
|
|
"epoch": 0.14877421905891658,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999718808371241,
|
|
"loss": 6.3432,
|
|
"mean_token_accuracy": 0.12537492960691451,
|
|
"num_tokens": 3460699.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.338581228256226,
|
|
"epoch": 0.14926848556741795,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999713201616776,
|
|
"loss": 6.2238,
|
|
"mean_token_accuracy": 0.13232341259717942,
|
|
"num_tokens": 3471919.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.166346454620362,
|
|
"epoch": 0.14976275207591933,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499970753951902,
|
|
"loss": 6.3229,
|
|
"mean_token_accuracy": 0.12744686827063562,
|
|
"num_tokens": 3484110.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.412110614776611,
|
|
"epoch": 0.15025701858442073,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999701822078107,
|
|
"loss": 6.2352,
|
|
"mean_token_accuracy": 0.12983164712786674,
|
|
"num_tokens": 3496103.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.272561883926391,
|
|
"epoch": 0.1507512850929221,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499969604929418,
|
|
"loss": 6.3098,
|
|
"mean_token_accuracy": 0.13165246173739434,
|
|
"num_tokens": 3507291.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.302027225494385,
|
|
"epoch": 0.1512455516014235,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999690221167382,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.12720877900719643,
|
|
"num_tokens": 3519564.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.204291439056396,
|
|
"epoch": 0.15173981810992487,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999684337697855,
|
|
"loss": 6.1724,
|
|
"mean_token_accuracy": 0.13716719225049018,
|
|
"num_tokens": 3530679.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.2982782363891605,
|
|
"epoch": 0.15223408461842625,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999678398885746,
|
|
"loss": 6.2473,
|
|
"mean_token_accuracy": 0.1318476304411888,
|
|
"num_tokens": 3542662.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.265805768966675,
|
|
"epoch": 0.15272835112692765,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999672404731197,
|
|
"loss": 6.3499,
|
|
"mean_token_accuracy": 0.12811536714434624,
|
|
"num_tokens": 3554760.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.249004793167114,
|
|
"epoch": 0.15322261763542902,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499966635523436,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.13934924975037574,
|
|
"num_tokens": 3565604.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.277536392211914,
|
|
"epoch": 0.1537168841439304,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999660250395381,
|
|
"loss": 6.3141,
|
|
"mean_token_accuracy": 0.12867220491170883,
|
|
"num_tokens": 3577535.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.295968151092529,
|
|
"epoch": 0.1542111506524318,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499965409021441,
|
|
"loss": 6.3235,
|
|
"mean_token_accuracy": 0.12822821363806725,
|
|
"num_tokens": 3590458.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.375429725646972,
|
|
"epoch": 0.15470541716093317,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049996478746916,
|
|
"loss": 6.2851,
|
|
"mean_token_accuracy": 0.13392977118492128,
|
|
"num_tokens": 3600916.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.222699928283691,
|
|
"epoch": 0.15519968366943457,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999641603827104,
|
|
"loss": 6.3037,
|
|
"mean_token_accuracy": 0.12990911155939103,
|
|
"num_tokens": 3612794.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.27130880355835,
|
|
"epoch": 0.15569395017793594,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999635277621073,
|
|
"loss": 6.2037,
|
|
"mean_token_accuracy": 0.1420078307390213,
|
|
"num_tokens": 3624186.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.199323654174805,
|
|
"epoch": 0.15618821668643731,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999628896073668,
|
|
"loss": 6.2448,
|
|
"mean_token_accuracy": 0.12877988070249557,
|
|
"num_tokens": 3636041.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.304298067092896,
|
|
"epoch": 0.15668248319493872,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999622459185042,
|
|
"loss": 6.3071,
|
|
"mean_token_accuracy": 0.12442853599786759,
|
|
"num_tokens": 3646859.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.2107603549957275,
|
|
"epoch": 0.1571767497034401,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999615966955354,
|
|
"loss": 6.119,
|
|
"mean_token_accuracy": 0.14032085835933686,
|
|
"num_tokens": 3657853.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.324536895751953,
|
|
"epoch": 0.1576710162119415,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999609419384764,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.134918150305748,
|
|
"num_tokens": 3668341.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.249271965026855,
|
|
"epoch": 0.15816528272044286,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999602816473434,
|
|
"loss": 6.2563,
|
|
"mean_token_accuracy": 0.13581479713320732,
|
|
"num_tokens": 3679020.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.1892296314239506,
|
|
"epoch": 0.15865954922894424,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999596158221526,
|
|
"loss": 6.1613,
|
|
"mean_token_accuracy": 0.13848758935928346,
|
|
"num_tokens": 3691121.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.234239339828491,
|
|
"epoch": 0.15915381573744564,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999589444629203,
|
|
"loss": 6.2286,
|
|
"mean_token_accuracy": 0.13591036275029184,
|
|
"num_tokens": 3702584.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.20807032585144,
|
|
"epoch": 0.159648082245947,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999582675696631,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.1353621505200863,
|
|
"num_tokens": 3713085.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.320692300796509,
|
|
"epoch": 0.1601423487544484,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999575851423976,
|
|
"loss": 6.2929,
|
|
"mean_token_accuracy": 0.12485695034265518,
|
|
"num_tokens": 3724318.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.2754554271698,
|
|
"epoch": 0.16063661526294978,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999568971811407,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.14148797765374183,
|
|
"num_tokens": 3734288.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.201929521560669,
|
|
"epoch": 0.16113088177145116,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499956203685909,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.13511522933840753,
|
|
"num_tokens": 3744645.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.282017421722412,
|
|
"epoch": 0.16162514827995256,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049995550465672,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.13890446051955224,
|
|
"num_tokens": 3755660.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.125180339813232,
|
|
"epoch": 0.16211941478845393,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999548000935906,
|
|
"loss": 6.1599,
|
|
"mean_token_accuracy": 0.14167107045650482,
|
|
"num_tokens": 3767614.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.254905891418457,
|
|
"epoch": 0.16261368129695533,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999540899965383,
|
|
"loss": 6.308,
|
|
"mean_token_accuracy": 0.1335205040872097,
|
|
"num_tokens": 3780750.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.242093515396118,
|
|
"epoch": 0.1631079478054567,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999533743655803,
|
|
"loss": 6.2965,
|
|
"mean_token_accuracy": 0.1281206913292408,
|
|
"num_tokens": 3793195.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.24614839553833,
|
|
"epoch": 0.16360221431395808,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999526532007346,
|
|
"loss": 6.2606,
|
|
"mean_token_accuracy": 0.13350182473659516,
|
|
"num_tokens": 3804256.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.289435911178589,
|
|
"epoch": 0.16409648082245948,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999519265020187,
|
|
"loss": 6.2237,
|
|
"mean_token_accuracy": 0.12859297171235085,
|
|
"num_tokens": 3815403.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.08995943069458,
|
|
"epoch": 0.16459074733096085,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999511942694504,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.14284673556685448,
|
|
"num_tokens": 3826682.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.215432214736938,
|
|
"epoch": 0.16508501383946222,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999504565030479,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.13716638311743737,
|
|
"num_tokens": 3837780.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.164974164962769,
|
|
"epoch": 0.16557928034796363,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999497132028293,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.1344188041985035,
|
|
"num_tokens": 3848782.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.244879055023193,
|
|
"epoch": 0.166073546856465,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999489643688127,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.13939150497317315,
|
|
"num_tokens": 3859220.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.102788019180298,
|
|
"epoch": 0.1665678133649664,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999482100010169,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.1425606593489647,
|
|
"num_tokens": 3869794.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.161266660690307,
|
|
"epoch": 0.16706207987346777,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999474500994601,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.1334006331861019,
|
|
"num_tokens": 3881133.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.2152763366699215,
|
|
"epoch": 0.16755634638196915,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999466846641611,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.1364052601158619,
|
|
"num_tokens": 3891600.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.224546241760254,
|
|
"epoch": 0.16805061289047055,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999459136951389,
|
|
"loss": 6.2529,
|
|
"mean_token_accuracy": 0.13441457897424697,
|
|
"num_tokens": 3903287.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.245505905151367,
|
|
"epoch": 0.16854487939897192,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999451371924123,
|
|
"loss": 6.1635,
|
|
"mean_token_accuracy": 0.14323566406965255,
|
|
"num_tokens": 3914497.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.2008990287780765,
|
|
"epoch": 0.16903914590747332,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999443551560003,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.13277414664626122,
|
|
"num_tokens": 3925536.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.179309701919555,
|
|
"epoch": 0.1695334124159747,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999435675859224,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.1426541492342949,
|
|
"num_tokens": 3936705.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.117032384872436,
|
|
"epoch": 0.17002767892447607,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999427744821977,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.1389991022646427,
|
|
"num_tokens": 3948422.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.144522857666016,
|
|
"epoch": 0.17052194543297747,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499941975844846,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.14725376516580582,
|
|
"num_tokens": 3958697.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.112959909439087,
|
|
"epoch": 0.17101621194147884,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999411716738866,
|
|
"loss": 6.1208,
|
|
"mean_token_accuracy": 0.13783455789089202,
|
|
"num_tokens": 3970255.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.206806802749634,
|
|
"epoch": 0.17151047844998024,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999403619693397,
|
|
"loss": 6.2172,
|
|
"mean_token_accuracy": 0.13266652897000314,
|
|
"num_tokens": 3980892.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.101211071014404,
|
|
"epoch": 0.17200474495848161,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999395467312249,
|
|
"loss": 6.1532,
|
|
"mean_token_accuracy": 0.13273056447505951,
|
|
"num_tokens": 3991375.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.304367208480835,
|
|
"epoch": 0.172499011466983,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999387259595623,
|
|
"loss": 6.3042,
|
|
"mean_token_accuracy": 0.12940156012773513,
|
|
"num_tokens": 4003352.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.152772092819214,
|
|
"epoch": 0.1729932779754844,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999378996543723,
|
|
"loss": 6.1745,
|
|
"mean_token_accuracy": 0.13783681988716126,
|
|
"num_tokens": 4014429.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.22617883682251,
|
|
"epoch": 0.17348754448398576,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999370678156749,
|
|
"loss": 6.1056,
|
|
"mean_token_accuracy": 0.14252740070223807,
|
|
"num_tokens": 4025213.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.1182598114013675,
|
|
"epoch": 0.17398181099248716,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999362304434909,
|
|
"loss": 6.0983,
|
|
"mean_token_accuracy": 0.1411632165312767,
|
|
"num_tokens": 4036244.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.218455600738525,
|
|
"epoch": 0.17447607750098854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999353875378406,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.13833620101213456,
|
|
"num_tokens": 4047944.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.125010585784912,
|
|
"epoch": 0.1749703440094899,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499934539098745,
|
|
"loss": 6.1127,
|
|
"mean_token_accuracy": 0.13938926681876182,
|
|
"num_tokens": 4058865.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.112168598175049,
|
|
"epoch": 0.1754646105179913,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999336851262247,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.13652415424585343,
|
|
"num_tokens": 4070627.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.221715450286865,
|
|
"epoch": 0.17595887702649268,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999328256203009,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.13283938243985177,
|
|
"num_tokens": 4081406.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.202430009841919,
|
|
"epoch": 0.17645314353499406,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999319605809947,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.1280331313610077,
|
|
"num_tokens": 4092957.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.209701681137085,
|
|
"epoch": 0.17694741004349546,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999310900083274,
|
|
"loss": 6.232,
|
|
"mean_token_accuracy": 0.13681847751140594,
|
|
"num_tokens": 4104381.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.180554962158203,
|
|
"epoch": 0.17744167655199683,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999302139023204,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.13721615672111512,
|
|
"num_tokens": 4117190.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.11452693939209,
|
|
"epoch": 0.17793594306049823,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999293322629951,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.14162272289395333,
|
|
"num_tokens": 4127870.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.098488092422485,
|
|
"epoch": 0.1784302095689996,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999284450903736,
|
|
"loss": 6.1272,
|
|
"mean_token_accuracy": 0.14127160534262656,
|
|
"num_tokens": 4139240.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.223893737792968,
|
|
"epoch": 0.17892447607750098,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999275523844772,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.14117365032434465,
|
|
"num_tokens": 4149885.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.183619403839112,
|
|
"epoch": 0.17941874258600238,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999266541453283,
|
|
"loss": 6.2727,
|
|
"mean_token_accuracy": 0.1341182231903076,
|
|
"num_tokens": 4161824.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.192480278015137,
|
|
"epoch": 0.17991300909450375,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999257503729487,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.13566601723432542,
|
|
"num_tokens": 4173581.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.188820171356201,
|
|
"epoch": 0.18040727560300515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999248410673607,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.14354413226246834,
|
|
"num_tokens": 4184843.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.199634456634522,
|
|
"epoch": 0.18090154211150652,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999239262285869,
|
|
"loss": 6.196,
|
|
"mean_token_accuracy": 0.12894793301820756,
|
|
"num_tokens": 4195016.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.183595895767212,
|
|
"epoch": 0.1813958086200079,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999230058566495,
|
|
"loss": 6.149,
|
|
"mean_token_accuracy": 0.13868849724531174,
|
|
"num_tokens": 4206798.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.20193657875061,
|
|
"epoch": 0.1818900751285093,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999220799515713,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.13616999015212058,
|
|
"num_tokens": 4218784.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.098097658157348,
|
|
"epoch": 0.18238434163701067,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499921148513375,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.13528309762477875,
|
|
"num_tokens": 4229875.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.120871686935425,
|
|
"epoch": 0.18287860814551207,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999202115420836,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.13959604278206825,
|
|
"num_tokens": 4241801.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.136850357055664,
|
|
"epoch": 0.18337287465401345,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999192690377201,
|
|
"loss": 6.112,
|
|
"mean_token_accuracy": 0.13544971346855164,
|
|
"num_tokens": 4253168.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.151134204864502,
|
|
"epoch": 0.18386714116251482,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999183210003076,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.13654277250170707,
|
|
"num_tokens": 4264791.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.127550983428955,
|
|
"epoch": 0.18436140767101622,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999173674298696,
|
|
"loss": 6.0802,
|
|
"mean_token_accuracy": 0.1429269403219223,
|
|
"num_tokens": 4275816.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.2200188636779785,
|
|
"epoch": 0.1848556741795176,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999164083264294,
|
|
"loss": 6.1638,
|
|
"mean_token_accuracy": 0.13557607755064965,
|
|
"num_tokens": 4287806.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.1365429878234865,
|
|
"epoch": 0.185349940688019,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999154436900108,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.13776358291506768,
|
|
"num_tokens": 4300319.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.261188077926636,
|
|
"epoch": 0.18584420719652037,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999144735206373,
|
|
"loss": 6.2191,
|
|
"mean_token_accuracy": 0.13050539270043374,
|
|
"num_tokens": 4310987.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.134886789321899,
|
|
"epoch": 0.18633847370502174,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999134978183328,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.14048967361450196,
|
|
"num_tokens": 4322438.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.216308641433716,
|
|
"epoch": 0.18683274021352314,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999125165831215,
|
|
"loss": 6.194,
|
|
"mean_token_accuracy": 0.13951309472322465,
|
|
"num_tokens": 4333242.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.1126538753509525,
|
|
"epoch": 0.1873270067220245,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999115298150273,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.14102249965071678,
|
|
"num_tokens": 4343660.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.163443613052368,
|
|
"epoch": 0.1878212732305259,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999105375140746,
|
|
"loss": 6.1246,
|
|
"mean_token_accuracy": 0.1411570593714714,
|
|
"num_tokens": 4353382.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.103315830230713,
|
|
"epoch": 0.1883155397390273,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999095396802878,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.13109617531299592,
|
|
"num_tokens": 4364614.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.2517712116241455,
|
|
"epoch": 0.18880980624752866,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999085363136913,
|
|
"loss": 6.1812,
|
|
"mean_token_accuracy": 0.1353604979813099,
|
|
"num_tokens": 4376001.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.128733491897583,
|
|
"epoch": 0.18930407275603006,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049990752741431,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.13217584118247033,
|
|
"num_tokens": 4387083.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.139519214630127,
|
|
"epoch": 0.18979833926453143,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999065129821687,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.13750590831041337,
|
|
"num_tokens": 4399977.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.0825254917144775,
|
|
"epoch": 0.1902926057730328,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999054930172923,
|
|
"loss": 6.0592,
|
|
"mean_token_accuracy": 0.14218987300992011,
|
|
"num_tokens": 4411609.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.175016450881958,
|
|
"epoch": 0.1907868722815342,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999044675197058,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.13701564595103263,
|
|
"num_tokens": 4423567.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.147806310653687,
|
|
"epoch": 0.19128113879003558,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999034364894345,
|
|
"loss": 6.1472,
|
|
"mean_token_accuracy": 0.13876281678676605,
|
|
"num_tokens": 4435410.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.18219690322876,
|
|
"epoch": 0.19177540529853698,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999023999265039,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.1378607526421547,
|
|
"num_tokens": 4445279.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.077285814285278,
|
|
"epoch": 0.19226967180703836,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999013578309392,
|
|
"loss": 6.0385,
|
|
"mean_token_accuracy": 0.14334971085190773,
|
|
"num_tokens": 4456017.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.126475811004639,
|
|
"epoch": 0.19276393831553973,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999003102027663,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.14338691681623458,
|
|
"num_tokens": 4466759.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.117775201797485,
|
|
"epoch": 0.19325820482404113,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499899257042011,
|
|
"loss": 6.1139,
|
|
"mean_token_accuracy": 0.1352181151509285,
|
|
"num_tokens": 4478316.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.208990001678467,
|
|
"epoch": 0.1937524713325425,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998981983486988,
|
|
"loss": 6.1751,
|
|
"mean_token_accuracy": 0.1322692520916462,
|
|
"num_tokens": 4490775.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.064915752410888,
|
|
"epoch": 0.1942467378410439,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998971341228563,
|
|
"loss": 6.039,
|
|
"mean_token_accuracy": 0.1443925455212593,
|
|
"num_tokens": 4501622.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.149889087677002,
|
|
"epoch": 0.19474100434954528,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998960643645093,
|
|
"loss": 6.1338,
|
|
"mean_token_accuracy": 0.13769015669822693,
|
|
"num_tokens": 4512279.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.167524814605713,
|
|
"epoch": 0.19523527085804665,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998949890736841,
|
|
"loss": 6.1239,
|
|
"mean_token_accuracy": 0.14070178642868997,
|
|
"num_tokens": 4524087.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.139242649078369,
|
|
"epoch": 0.19572953736654805,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998939082504075,
|
|
"loss": 6.1075,
|
|
"mean_token_accuracy": 0.13732974529266356,
|
|
"num_tokens": 4534816.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.103002882003784,
|
|
"epoch": 0.19622380387504942,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998928218947057,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.13870148733258247,
|
|
"num_tokens": 4545725.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.218700933456421,
|
|
"epoch": 0.1967180703835508,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998917300066056,
|
|
"loss": 6.1897,
|
|
"mean_token_accuracy": 0.13517609983682632,
|
|
"num_tokens": 4557003.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.099284267425537,
|
|
"epoch": 0.1972123368920522,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998906325861342,
|
|
"loss": 6.1023,
|
|
"mean_token_accuracy": 0.13518477007746696,
|
|
"num_tokens": 4568768.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.103130531311035,
|
|
"epoch": 0.19770660340055357,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998895296333183,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.14329598397016524,
|
|
"num_tokens": 4581116.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.170775890350342,
|
|
"epoch": 0.19820086990905497,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499888421148185,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.13928177580237389,
|
|
"num_tokens": 4592660.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.074905729293823,
|
|
"epoch": 0.19869513641755635,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998873071307617,
|
|
"loss": 6.1321,
|
|
"mean_token_accuracy": 0.13926766365766524,
|
|
"num_tokens": 4603057.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.111081838607788,
|
|
"epoch": 0.19918940292605772,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998861875810758,
|
|
"loss": 6.0145,
|
|
"mean_token_accuracy": 0.14594943076372147,
|
|
"num_tokens": 4613546.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.130213642120362,
|
|
"epoch": 0.19968366943455912,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998850624991548,
|
|
"loss": 6.0932,
|
|
"mean_token_accuracy": 0.13966753333806992,
|
|
"num_tokens": 4624613.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.070725202560425,
|
|
"epoch": 0.2001779359430605,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998839318850263,
|
|
"loss": 6.0581,
|
|
"mean_token_accuracy": 0.14254929646849632,
|
|
"num_tokens": 4636004.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.094811868667603,
|
|
"epoch": 0.2006722024515619,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998827957387182,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.1468837432563305,
|
|
"num_tokens": 4646450.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.105382490158081,
|
|
"epoch": 0.20116646896006327,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998816540602584,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.14319370239973067,
|
|
"num_tokens": 4658928.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.133113861083984,
|
|
"epoch": 0.20166073546856464,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998805068496752,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.13475392609834672,
|
|
"num_tokens": 4670392.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.141398954391479,
|
|
"epoch": 0.20215500197706604,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998793541069964,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.13688452690839767,
|
|
"num_tokens": 4680605.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.069099378585816,
|
|
"epoch": 0.2026492684855674,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998781958322507,
|
|
"loss": 6.0134,
|
|
"mean_token_accuracy": 0.14460673555731773,
|
|
"num_tokens": 4694250.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.110835599899292,
|
|
"epoch": 0.20314353499406881,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998770320254666,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.13903781324625014,
|
|
"num_tokens": 4705754.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.213265514373779,
|
|
"epoch": 0.2036378015025702,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998758626866725,
|
|
"loss": 6.0439,
|
|
"mean_token_accuracy": 0.14397211521863937,
|
|
"num_tokens": 4716393.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.992143011093139,
|
|
"epoch": 0.20413206801107156,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998746878158973,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.14380352646112443,
|
|
"num_tokens": 4726894.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.137889289855957,
|
|
"epoch": 0.20462633451957296,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998735074131699,
|
|
"loss": 6.082,
|
|
"mean_token_accuracy": 0.13775463551282882,
|
|
"num_tokens": 4737488.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.157661390304566,
|
|
"epoch": 0.20512060102807433,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998723214785194,
|
|
"loss": 6.1528,
|
|
"mean_token_accuracy": 0.1327391304075718,
|
|
"num_tokens": 4749131.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.090861511230469,
|
|
"epoch": 0.20561486753657574,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998711300119749,
|
|
"loss": 6.0322,
|
|
"mean_token_accuracy": 0.1410945810377598,
|
|
"num_tokens": 4760503.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.128068828582764,
|
|
"epoch": 0.2061091340450771,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998699330135656,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.1358460932970047,
|
|
"num_tokens": 4771965.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.096466827392578,
|
|
"epoch": 0.20660340055357848,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998687304833212,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.13651231974363326,
|
|
"num_tokens": 4784215.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.102608966827392,
|
|
"epoch": 0.20709766706207988,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499867522421271,
|
|
"loss": 6.0457,
|
|
"mean_token_accuracy": 0.1427777349948883,
|
|
"num_tokens": 4796410.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.065385389328003,
|
|
"epoch": 0.20759193357058126,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499866308827445,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.1456620767712593,
|
|
"num_tokens": 4806990.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.113207626342773,
|
|
"epoch": 0.20808620007908263,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998650897018729,
|
|
"loss": 6.0949,
|
|
"mean_token_accuracy": 0.14114938974380492,
|
|
"num_tokens": 4818903.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.091670751571655,
|
|
"epoch": 0.20858046658758403,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998638650445847,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.14184736907482148,
|
|
"num_tokens": 4829130.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.0775425910949705,
|
|
"epoch": 0.2090747330960854,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998626348556105,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.1536749005317688,
|
|
"num_tokens": 4840424.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.098685884475708,
|
|
"epoch": 0.2095689996045868,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998613991349807,
|
|
"loss": 6.0283,
|
|
"mean_token_accuracy": 0.143294495344162,
|
|
"num_tokens": 4851674.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.9475749969482425,
|
|
"epoch": 0.21006326611308818,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998601578827255,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.1536559596657753,
|
|
"num_tokens": 4863884.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.033754873275757,
|
|
"epoch": 0.21055753262158955,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998589110988755,
|
|
"loss": 6.0494,
|
|
"mean_token_accuracy": 0.14718157574534416,
|
|
"num_tokens": 4875582.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.114961338043213,
|
|
"epoch": 0.21105179913009095,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998576587834614,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.14199472591280937,
|
|
"num_tokens": 4888325.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.098699426651001,
|
|
"epoch": 0.21154606563859232,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499856400936514,
|
|
"loss": 6.072,
|
|
"mean_token_accuracy": 0.14264639914035798,
|
|
"num_tokens": 4899631.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.029827070236206,
|
|
"epoch": 0.21204033214709372,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998551375580643,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.13763367459177972,
|
|
"num_tokens": 4910954.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.051994514465332,
|
|
"epoch": 0.2125345986555951,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998538686481435,
|
|
"loss": 6.0714,
|
|
"mean_token_accuracy": 0.14147689938545227,
|
|
"num_tokens": 4921952.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.0656555652618405,
|
|
"epoch": 0.21302886516409647,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998525942067824,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.14360493123531343,
|
|
"num_tokens": 4933984.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.164171361923218,
|
|
"epoch": 0.21352313167259787,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998513142340128,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.14157587438821792,
|
|
"num_tokens": 4945926.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.026093053817749,
|
|
"epoch": 0.21401739818109924,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998500287298657,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.14866259396076204,
|
|
"num_tokens": 4958123.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.158975839614868,
|
|
"epoch": 0.21451166468960065,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998487376943733,
|
|
"loss": 6.1491,
|
|
"mean_token_accuracy": 0.13338658437132836,
|
|
"num_tokens": 4970409.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.122834396362305,
|
|
"epoch": 0.21500593119810202,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499847441127567,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.13795322477817534,
|
|
"num_tokens": 4980429.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.053185510635376,
|
|
"epoch": 0.2155001977066034,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998461390294787,
|
|
"loss": 6.0711,
|
|
"mean_token_accuracy": 0.14336730688810348,
|
|
"num_tokens": 4991790.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.095970296859742,
|
|
"epoch": 0.2159944642151048,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998448314001405,
|
|
"loss": 6.0869,
|
|
"mean_token_accuracy": 0.14493904113769532,
|
|
"num_tokens": 5003611.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.176206493377686,
|
|
"epoch": 0.21648873072360617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998435182395845,
|
|
"loss": 6.1385,
|
|
"mean_token_accuracy": 0.1309673383831978,
|
|
"num_tokens": 5014824.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.142057228088379,
|
|
"epoch": 0.21698299723210757,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998421995478432,
|
|
"loss": 6.0831,
|
|
"mean_token_accuracy": 0.143635593354702,
|
|
"num_tokens": 5026937.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.116099071502686,
|
|
"epoch": 0.21747726374060894,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998408753249489,
|
|
"loss": 6.1134,
|
|
"mean_token_accuracy": 0.1369356207549572,
|
|
"num_tokens": 5037996.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.096542501449585,
|
|
"epoch": 0.2179715302491103,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998395455709342,
|
|
"loss": 6.0605,
|
|
"mean_token_accuracy": 0.14553544148802758,
|
|
"num_tokens": 5050944.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.150865888595581,
|
|
"epoch": 0.2184657967576117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998382102858317,
|
|
"loss": 6.1,
|
|
"mean_token_accuracy": 0.1378478489816189,
|
|
"num_tokens": 5062129.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.0926353454589846,
|
|
"epoch": 0.2189600632661131,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998368694696743,
|
|
"loss": 6.0959,
|
|
"mean_token_accuracy": 0.14366044774651526,
|
|
"num_tokens": 5073318.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.064820623397827,
|
|
"epoch": 0.21945432977461446,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998355231224952,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.13671059682965278,
|
|
"num_tokens": 5084607.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.1097174167633055,
|
|
"epoch": 0.21994859628311586,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998341712443273,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.14424162060022355,
|
|
"num_tokens": 5096004.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.0761024951934814,
|
|
"epoch": 0.22044286279161723,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499832813835204,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.14155133366584777,
|
|
"num_tokens": 5107171.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.977806282043457,
|
|
"epoch": 0.22093712930011863,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998314508951584,
|
|
"loss": 5.9782,
|
|
"mean_token_accuracy": 0.15077303797006608,
|
|
"num_tokens": 5119249.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.04344334602356,
|
|
"epoch": 0.22143139580862,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998300824242244,
|
|
"loss": 5.9945,
|
|
"mean_token_accuracy": 0.13899804279208183,
|
|
"num_tokens": 5130798.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.146693372726441,
|
|
"epoch": 0.22192566231712138,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998287084224353,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.12782063856720924,
|
|
"num_tokens": 5141376.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.979104852676391,
|
|
"epoch": 0.22241992882562278,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998273288898252,
|
|
"loss": 5.9599,
|
|
"mean_token_accuracy": 0.1464287005364895,
|
|
"num_tokens": 5152888.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.031632804870606,
|
|
"epoch": 0.22291419533412415,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499825943826428,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.14004838690161706,
|
|
"num_tokens": 5165720.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.069583225250244,
|
|
"epoch": 0.22340846184262556,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998245532322776,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.14667778834700584,
|
|
"num_tokens": 5177345.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.060588693618774,
|
|
"epoch": 0.22390272835112693,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998231571074083,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.14570290222764015,
|
|
"num_tokens": 5187385.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.04728593826294,
|
|
"epoch": 0.2243969948596283,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998217554518545,
|
|
"loss": 6.0683,
|
|
"mean_token_accuracy": 0.13824618086218834,
|
|
"num_tokens": 5199552.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.039723873138428,
|
|
"epoch": 0.2248912613681297,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998203482656507,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.14244999885559081,
|
|
"num_tokens": 5210316.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.0842948913574215,
|
|
"epoch": 0.22538552787663108,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998189355488314,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.1472305215895176,
|
|
"num_tokens": 5221595.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.140758895874024,
|
|
"epoch": 0.22587979438513248,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998175173014313,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.13632547855377197,
|
|
"num_tokens": 5232882.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.0675756454467775,
|
|
"epoch": 0.22637406089363385,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998160935234857,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.13839787468314171,
|
|
"num_tokens": 5244841.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.096714353561401,
|
|
"epoch": 0.22686832740213522,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499814664215029,
|
|
"loss": 5.9748,
|
|
"mean_token_accuracy": 0.1458760157227516,
|
|
"num_tokens": 5256162.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.00123872756958,
|
|
"epoch": 0.22736259391063662,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998132293760968,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.15427679419517518,
|
|
"num_tokens": 5267130.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.969837474822998,
|
|
"epoch": 0.227856860419138,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998117890067243,
|
|
"loss": 6.0244,
|
|
"mean_token_accuracy": 0.14411933422088624,
|
|
"num_tokens": 5279394.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.981906747817993,
|
|
"epoch": 0.22835112692763937,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998103431069469,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.1491586372256279,
|
|
"num_tokens": 5291068.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.060888195037842,
|
|
"epoch": 0.22884539343614077,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998088916768002,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.14889078661799432,
|
|
"num_tokens": 5300924.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.016797971725464,
|
|
"epoch": 0.22933965994464214,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998074347163199,
|
|
"loss": 5.9542,
|
|
"mean_token_accuracy": 0.1480551391839981,
|
|
"num_tokens": 5311998.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.06162691116333,
|
|
"epoch": 0.22983392645314354,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998059722255418,
|
|
"loss": 5.9899,
|
|
"mean_token_accuracy": 0.14691204354166984,
|
|
"num_tokens": 5322163.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.0275694847106935,
|
|
"epoch": 0.23032819296164492,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998045042045019,
|
|
"loss": 5.996,
|
|
"mean_token_accuracy": 0.1497631698846817,
|
|
"num_tokens": 5331638.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.048976612091065,
|
|
"epoch": 0.2308224594701463,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998030306532363,
|
|
"loss": 5.9939,
|
|
"mean_token_accuracy": 0.14958565384149553,
|
|
"num_tokens": 5342399.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.055438804626465,
|
|
"epoch": 0.2313167259786477,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998015515717813,
|
|
"loss": 6.0695,
|
|
"mean_token_accuracy": 0.14016990289092063,
|
|
"num_tokens": 5353481.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.052402687072754,
|
|
"epoch": 0.23181099248714906,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998000669601733,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.1473512254655361,
|
|
"num_tokens": 5365167.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.002137184143066,
|
|
"epoch": 0.23230525899565047,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997985768184488,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.1431095339357853,
|
|
"num_tokens": 5375809.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.962526512145996,
|
|
"epoch": 0.23279952550415184,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997970811466443,
|
|
"loss": 5.9133,
|
|
"mean_token_accuracy": 0.1538688361644745,
|
|
"num_tokens": 5387372.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.187628889083863,
|
|
"epoch": 0.2332937920126532,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997955799447969,
|
|
"loss": 6.0898,
|
|
"mean_token_accuracy": 0.13684846088290215,
|
|
"num_tokens": 5399210.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.985762119293213,
|
|
"epoch": 0.2337880585211546,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997940732129432,
|
|
"loss": 6.017,
|
|
"mean_token_accuracy": 0.14093376472592353,
|
|
"num_tokens": 5410969.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.984814739227295,
|
|
"epoch": 0.23428232502965599,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997925609511205,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.14780228435993195,
|
|
"num_tokens": 5422569.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.031500720977784,
|
|
"epoch": 0.2347765915381574,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997910431593659,
|
|
"loss": 5.9606,
|
|
"mean_token_accuracy": 0.15011014714837073,
|
|
"num_tokens": 5434592.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.0243175506591795,
|
|
"epoch": 0.23527085804665876,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997895198377168,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.14284207075834274,
|
|
"num_tokens": 5446525.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.08224196434021,
|
|
"epoch": 0.23576512455516013,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997879909862105,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.14782738387584687,
|
|
"num_tokens": 5457327.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.105248498916626,
|
|
"epoch": 0.23625939106366153,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499786456604885,
|
|
"loss": 6.0642,
|
|
"mean_token_accuracy": 0.1362588956952095,
|
|
"num_tokens": 5468533.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.998384857177735,
|
|
"epoch": 0.2367536575721629,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997849166937776,
|
|
"loss": 5.9451,
|
|
"mean_token_accuracy": 0.14417133554816247,
|
|
"num_tokens": 5480652.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.012068605422973,
|
|
"epoch": 0.2372479240806643,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997833712529265,
|
|
"loss": 5.9707,
|
|
"mean_token_accuracy": 0.14451036602258682,
|
|
"num_tokens": 5491446.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.021755743026733,
|
|
"epoch": 0.23774219058916568,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997818202823695,
|
|
"loss": 5.9945,
|
|
"mean_token_accuracy": 0.14959129244089125,
|
|
"num_tokens": 5502886.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.0749561309814455,
|
|
"epoch": 0.23823645709766705,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997802637821449,
|
|
"loss": 6.023,
|
|
"mean_token_accuracy": 0.14053252562880517,
|
|
"num_tokens": 5514305.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.98513970375061,
|
|
"epoch": 0.23873072360616845,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997787017522909,
|
|
"loss": 5.9437,
|
|
"mean_token_accuracy": 0.15076548904180526,
|
|
"num_tokens": 5525913.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.90565128326416,
|
|
"epoch": 0.23922499011466983,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997771341928459,
|
|
"loss": 5.9446,
|
|
"mean_token_accuracy": 0.1544351950287819,
|
|
"num_tokens": 5537069.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.022730112075806,
|
|
"epoch": 0.2397192566231712,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997755611038487,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.1400386117398739,
|
|
"num_tokens": 5547988.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.105308675765992,
|
|
"epoch": 0.2402135231316726,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997739824853378,
|
|
"loss": 6.1088,
|
|
"mean_token_accuracy": 0.1395256355404854,
|
|
"num_tokens": 5560400.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.987665414810181,
|
|
"epoch": 0.24070778964017397,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997723983373519,
|
|
"loss": 5.9696,
|
|
"mean_token_accuracy": 0.15029642432928086,
|
|
"num_tokens": 5572291.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.100761747360229,
|
|
"epoch": 0.24120205614867538,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997708086599303,
|
|
"loss": 5.9938,
|
|
"mean_token_accuracy": 0.14239495247602463,
|
|
"num_tokens": 5583583.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.093548583984375,
|
|
"epoch": 0.24169632265717675,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997692134531119,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.14349138885736465,
|
|
"num_tokens": 5595499.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.937535381317138,
|
|
"epoch": 0.24219058916567812,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499767612716936,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.1555730566382408,
|
|
"num_tokens": 5606745.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.977556610107422,
|
|
"epoch": 0.24268485567417952,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997660064514419,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.1459631770849228,
|
|
"num_tokens": 5618226.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.103812122344971,
|
|
"epoch": 0.2431791221826809,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997643946566691,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.14382674545049667,
|
|
"num_tokens": 5628941.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.948967981338501,
|
|
"epoch": 0.2436733886911823,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997627773326574,
|
|
"loss": 5.8499,
|
|
"mean_token_accuracy": 0.15501064658164979,
|
|
"num_tokens": 5641077.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.018094301223755,
|
|
"epoch": 0.24416765519968367,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997611544794465,
|
|
"loss": 6.1555,
|
|
"mean_token_accuracy": 0.1338454492390156,
|
|
"num_tokens": 5652156.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.151158618927002,
|
|
"epoch": 0.24466192170818504,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997595260970764,
|
|
"loss": 6.0822,
|
|
"mean_token_accuracy": 0.14347486943006516,
|
|
"num_tokens": 5663988.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.977680206298828,
|
|
"epoch": 0.24515618821668644,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499757892185587,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.14267092123627662,
|
|
"num_tokens": 5676302.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.070641231536865,
|
|
"epoch": 0.24565045472518782,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997562527450187,
|
|
"loss": 6.046,
|
|
"mean_token_accuracy": 0.14550234749913216,
|
|
"num_tokens": 5686686.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.021747350692749,
|
|
"epoch": 0.24614472123368922,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997546077754116,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.15929894894361496,
|
|
"num_tokens": 5698379.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.958306932449341,
|
|
"epoch": 0.2466389877421906,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997529572768063,
|
|
"loss": 5.9432,
|
|
"mean_token_accuracy": 0.1498410865664482,
|
|
"num_tokens": 5708891.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.981058549880982,
|
|
"epoch": 0.24713325425069196,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997513012492434,
|
|
"loss": 5.9923,
|
|
"mean_token_accuracy": 0.14332532063126563,
|
|
"num_tokens": 5720326.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.052645683288574,
|
|
"epoch": 0.24762752075919336,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997496396927636,
|
|
"loss": 5.9112,
|
|
"mean_token_accuracy": 0.15235294178128242,
|
|
"num_tokens": 5731121.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.023140573501587,
|
|
"epoch": 0.24812178726769474,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997479726074077,
|
|
"loss": 5.9597,
|
|
"mean_token_accuracy": 0.15026197880506514,
|
|
"num_tokens": 5741637.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.048560428619385,
|
|
"epoch": 0.24861605377619614,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499746299993217,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.14581428989768028,
|
|
"num_tokens": 5752659.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.998668670654297,
|
|
"epoch": 0.2491103202846975,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997446218502324,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.14580842703580857,
|
|
"num_tokens": 5763829.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.0419858455657955,
|
|
"epoch": 0.24960458679319888,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997429381784952,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.1448736622929573,
|
|
"num_tokens": 5775848.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.984309673309326,
|
|
"epoch": 0.2500988533017003,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997412489780469,
|
|
"loss": 6.0037,
|
|
"mean_token_accuracy": 0.1499286875128746,
|
|
"num_tokens": 5786595.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.964243793487549,
|
|
"epoch": 0.25059311981020166,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499739554248929,
|
|
"loss": 5.8929,
|
|
"mean_token_accuracy": 0.15398191586136817,
|
|
"num_tokens": 5797841.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.912666082382202,
|
|
"epoch": 0.25108738631870303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997378539911832,
|
|
"loss": 5.9089,
|
|
"mean_token_accuracy": 0.15088940635323525,
|
|
"num_tokens": 5809106.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.973687314987183,
|
|
"epoch": 0.2515816528272044,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997361482048513,
|
|
"loss": 5.9215,
|
|
"mean_token_accuracy": 0.1497866354882717,
|
|
"num_tokens": 5820316.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.026650857925415,
|
|
"epoch": 0.25207591933570583,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997344368899753,
|
|
"loss": 6.0408,
|
|
"mean_token_accuracy": 0.139362945407629,
|
|
"num_tokens": 5833137.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.037950611114502,
|
|
"epoch": 0.2525701858442072,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997327200465972,
|
|
"loss": 5.9694,
|
|
"mean_token_accuracy": 0.14529137313365936,
|
|
"num_tokens": 5844088.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.077861881256103,
|
|
"epoch": 0.2530644523527086,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997309976747594,
|
|
"loss": 5.9736,
|
|
"mean_token_accuracy": 0.14326793625950812,
|
|
"num_tokens": 5854546.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.011197853088379,
|
|
"epoch": 0.25355871886120995,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997292697745042,
|
|
"loss": 5.9723,
|
|
"mean_token_accuracy": 0.1466481104493141,
|
|
"num_tokens": 5865326.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.999698734283447,
|
|
"epoch": 0.2540529853697113,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997275363458741,
|
|
"loss": 5.8594,
|
|
"mean_token_accuracy": 0.1503140576183796,
|
|
"num_tokens": 5876487.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.875597381591797,
|
|
"epoch": 0.25454725187821275,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997257973889118,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.14843393564224244,
|
|
"num_tokens": 5887846.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.101366996765137,
|
|
"epoch": 0.25504151838671413,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997240529036599,
|
|
"loss": 5.9412,
|
|
"mean_token_accuracy": 0.15172709226608277,
|
|
"num_tokens": 5898572.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.881202983856201,
|
|
"epoch": 0.2555357848952155,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997223028901615,
|
|
"loss": 6.0037,
|
|
"mean_token_accuracy": 0.1475423127412796,
|
|
"num_tokens": 5908927.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.037431478500366,
|
|
"epoch": 0.2560300514037169,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997205473484596,
|
|
"loss": 5.9495,
|
|
"mean_token_accuracy": 0.1498175874352455,
|
|
"num_tokens": 5919807.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.920142316818238,
|
|
"epoch": 0.25652431791221825,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997187862785974,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.14424620494246482,
|
|
"num_tokens": 5931160.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.088014888763428,
|
|
"epoch": 0.2570185844207197,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997170196806181,
|
|
"loss": 6.0412,
|
|
"mean_token_accuracy": 0.1426064506173134,
|
|
"num_tokens": 5943694.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.981357526779175,
|
|
"epoch": 0.25751285092922105,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997152475545652,
|
|
"loss": 5.9319,
|
|
"mean_token_accuracy": 0.14945385083556176,
|
|
"num_tokens": 5954543.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.9636317729949955,
|
|
"epoch": 0.2580071174377224,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997134699004825,
|
|
"loss": 5.973,
|
|
"mean_token_accuracy": 0.1513287492096424,
|
|
"num_tokens": 5965080.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.036751079559326,
|
|
"epoch": 0.2585013839462238,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997116867184136,
|
|
"loss": 5.9566,
|
|
"mean_token_accuracy": 0.14630378186702728,
|
|
"num_tokens": 5975314.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.02877459526062,
|
|
"epoch": 0.25899565045472517,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997098980084022,
|
|
"loss": 5.9735,
|
|
"mean_token_accuracy": 0.14686284810304642,
|
|
"num_tokens": 5985927.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.9730428695678714,
|
|
"epoch": 0.2594899169632266,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997081037704926,
|
|
"loss": 5.9986,
|
|
"mean_token_accuracy": 0.145076747238636,
|
|
"num_tokens": 5997311.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.986532354354859,
|
|
"epoch": 0.25998418347172797,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997063040047288,
|
|
"loss": 6.0236,
|
|
"mean_token_accuracy": 0.13863110765814782,
|
|
"num_tokens": 6008595.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.084332275390625,
|
|
"epoch": 0.26047844998022934,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997044987111548,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.1485560044646263,
|
|
"num_tokens": 6019055.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.984119462966919,
|
|
"epoch": 0.2609727164887307,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997026878898155,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.13726168423891066,
|
|
"num_tokens": 6030029.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.064934492111206,
|
|
"epoch": 0.2614669829972321,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997008715407552,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.14624494388699533,
|
|
"num_tokens": 6041495.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.0098552227020265,
|
|
"epoch": 0.2619612495057335,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996990496640185,
|
|
"loss": 5.9223,
|
|
"mean_token_accuracy": 0.14212577491998674,
|
|
"num_tokens": 6052307.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.9654816627502445,
|
|
"epoch": 0.2624555160142349,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996972222596505,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.14910161644220352,
|
|
"num_tokens": 6062550.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.945908880233764,
|
|
"epoch": 0.26294978252273626,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996953893276958,
|
|
"loss": 5.9301,
|
|
"mean_token_accuracy": 0.14317954927682877,
|
|
"num_tokens": 6074450.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.945242881774902,
|
|
"epoch": 0.26344404903123764,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996935508681997,
|
|
"loss": 5.9609,
|
|
"mean_token_accuracy": 0.1495286300778389,
|
|
"num_tokens": 6085749.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.005150699615479,
|
|
"epoch": 0.263938315539739,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996917068812075,
|
|
"loss": 5.8905,
|
|
"mean_token_accuracy": 0.1543781578540802,
|
|
"num_tokens": 6096438.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.924571704864502,
|
|
"epoch": 0.26443258204824044,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996898573667643,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.1454748436808586,
|
|
"num_tokens": 6108386.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.008694839477539,
|
|
"epoch": 0.2649268485567418,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996880023249158,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.15368301123380662,
|
|
"num_tokens": 6118771.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.974543571472168,
|
|
"epoch": 0.2654211150652432,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996861417557076,
|
|
"loss": 5.9496,
|
|
"mean_token_accuracy": 0.14521803110837936,
|
|
"num_tokens": 6130718.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.922163200378418,
|
|
"epoch": 0.26591538157374456,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996842756591855,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.14341218546032905,
|
|
"num_tokens": 6142086.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.976787948608399,
|
|
"epoch": 0.26640964808224593,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996824040353953,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.1457512103021145,
|
|
"num_tokens": 6153857.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.125744962692261,
|
|
"epoch": 0.2669039145907473,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996805268843832,
|
|
"loss": 6.0951,
|
|
"mean_token_accuracy": 0.1432183265686035,
|
|
"num_tokens": 6166796.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.963466644287109,
|
|
"epoch": 0.26739818109924873,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996786442061952,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.15192901045084,
|
|
"num_tokens": 6178046.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.9657057762146,
|
|
"epoch": 0.2678924476077501,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996767560008777,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.14713699072599412,
|
|
"num_tokens": 6190455.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.899187612533569,
|
|
"epoch": 0.2683867141162515,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996748622684771,
|
|
"loss": 5.8462,
|
|
"mean_token_accuracy": 0.15217214077711105,
|
|
"num_tokens": 6201659.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.924319171905518,
|
|
"epoch": 0.26888098062475285,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996729630090401,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.1431477539241314,
|
|
"num_tokens": 6213870.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.0065733909606935,
|
|
"epoch": 0.2693752471332542,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996710582226133,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.1548033893108368,
|
|
"num_tokens": 6224237.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.960059928894043,
|
|
"epoch": 0.26986951364175565,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996691479092437,
|
|
"loss": 5.9433,
|
|
"mean_token_accuracy": 0.14833316206932068,
|
|
"num_tokens": 6235868.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.0247667789459225,
|
|
"epoch": 0.270363780150257,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996672320689782,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.14516259282827376,
|
|
"num_tokens": 6247994.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.855693197250366,
|
|
"epoch": 0.2708580466587584,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996653107018638,
|
|
"loss": 5.8469,
|
|
"mean_token_accuracy": 0.15463558286428453,
|
|
"num_tokens": 6259654.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.977344179153443,
|
|
"epoch": 0.2713523131672598,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499663383807948,
|
|
"loss": 5.9049,
|
|
"mean_token_accuracy": 0.1500097319483757,
|
|
"num_tokens": 6270582.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.968403148651123,
|
|
"epoch": 0.27184657967576115,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996614513872781,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.15006383657455444,
|
|
"num_tokens": 6281088.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.981626415252686,
|
|
"epoch": 0.2723408461842626,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996595134399017,
|
|
"loss": 6.0555,
|
|
"mean_token_accuracy": 0.140472724288702,
|
|
"num_tokens": 6292920.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.020872259140015,
|
|
"epoch": 0.27283511269276395,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996575699658664,
|
|
"loss": 5.9111,
|
|
"mean_token_accuracy": 0.15108120441436768,
|
|
"num_tokens": 6304980.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.918898677825927,
|
|
"epoch": 0.2733293792012653,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996556209652199,
|
|
"loss": 5.8999,
|
|
"mean_token_accuracy": 0.15111031085252763,
|
|
"num_tokens": 6316175.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.976380968093872,
|
|
"epoch": 0.2738236457097667,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996536664380104,
|
|
"loss": 5.9517,
|
|
"mean_token_accuracy": 0.15452203899621964,
|
|
"num_tokens": 6327590.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.924459648132324,
|
|
"epoch": 0.27431791221826807,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996517063842859,
|
|
"loss": 5.9716,
|
|
"mean_token_accuracy": 0.1498926803469658,
|
|
"num_tokens": 6339066.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.0026692867279055,
|
|
"epoch": 0.2748121787267695,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996497408040944,
|
|
"loss": 5.9024,
|
|
"mean_token_accuracy": 0.15032327100634574,
|
|
"num_tokens": 6349485.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.844460916519165,
|
|
"epoch": 0.27530644523527087,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996477696974845,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.15661628544330597,
|
|
"num_tokens": 6360775.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.9499735832214355,
|
|
"epoch": 0.27580071174377224,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996457930645046,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.148551806807518,
|
|
"num_tokens": 6371645.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.961523580551147,
|
|
"epoch": 0.2762949782522736,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996438109052034,
|
|
"loss": 5.9074,
|
|
"mean_token_accuracy": 0.15085601136088372,
|
|
"num_tokens": 6383877.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.9515691757202145,
|
|
"epoch": 0.276789244760775,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996418232196296,
|
|
"loss": 5.9828,
|
|
"mean_token_accuracy": 0.14350538998842238,
|
|
"num_tokens": 6394488.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.979497003555298,
|
|
"epoch": 0.2772835112692764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996398300078321,
|
|
"loss": 5.9065,
|
|
"mean_token_accuracy": 0.15064874663949013,
|
|
"num_tokens": 6404948.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.974899482727051,
|
|
"epoch": 0.2777777777777778,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996378312698598,
|
|
"loss": 5.9471,
|
|
"mean_token_accuracy": 0.1533238559961319,
|
|
"num_tokens": 6416273.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.013521671295166,
|
|
"epoch": 0.27827204428627916,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996358270057622,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.1466079130768776,
|
|
"num_tokens": 6427091.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.9516332149505615,
|
|
"epoch": 0.27876631079478054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996338172155883,
|
|
"loss": 5.9126,
|
|
"mean_token_accuracy": 0.14914426058530808,
|
|
"num_tokens": 6438254.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.89876914024353,
|
|
"epoch": 0.2792605773032819,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996318018993876,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.1530715063214302,
|
|
"num_tokens": 6450618.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.980556011199951,
|
|
"epoch": 0.27975484381178334,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996297810572098,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.1491038627922535,
|
|
"num_tokens": 6462467.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.9045891761779785,
|
|
"epoch": 0.2802491103202847,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996277546891045,
|
|
"loss": 5.864,
|
|
"mean_token_accuracy": 0.15746333003044127,
|
|
"num_tokens": 6474206.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.942203712463379,
|
|
"epoch": 0.2807433768287861,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996257227951216,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.1443627193570137,
|
|
"num_tokens": 6486405.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.967880725860596,
|
|
"epoch": 0.28123764333728746,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499623685375311,
|
|
"loss": 5.9336,
|
|
"mean_token_accuracy": 0.14780732095241547,
|
|
"num_tokens": 6496949.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.923089170455933,
|
|
"epoch": 0.28173190984578883,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499621642429723,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.1550042062997818,
|
|
"num_tokens": 6508913.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.956121826171875,
|
|
"epoch": 0.28222617635429026,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996195939584078,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.14797470420598985,
|
|
"num_tokens": 6519837.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.941003894805908,
|
|
"epoch": 0.28272044286279163,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996175399614156,
|
|
"loss": 5.872,
|
|
"mean_token_accuracy": 0.14837601631879807,
|
|
"num_tokens": 6531409.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.937231063842773,
|
|
"epoch": 0.283214709371293,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996154804387972,
|
|
"loss": 5.9121,
|
|
"mean_token_accuracy": 0.15122439116239547,
|
|
"num_tokens": 6543433.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.91095666885376,
|
|
"epoch": 0.2837089758797944,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499613415390603,
|
|
"loss": 5.9883,
|
|
"mean_token_accuracy": 0.14575250148773194,
|
|
"num_tokens": 6554511.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.029332876205444,
|
|
"epoch": 0.28420324238829575,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499611344816884,
|
|
"loss": 5.9113,
|
|
"mean_token_accuracy": 0.1500216841697693,
|
|
"num_tokens": 6564591.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.943623399734497,
|
|
"epoch": 0.2846975088967972,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499609268717691,
|
|
"loss": 5.8826,
|
|
"mean_token_accuracy": 0.15444658771157266,
|
|
"num_tokens": 6575684.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.002884864807129,
|
|
"epoch": 0.28519177540529855,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996071870930753,
|
|
"loss": 6.0142,
|
|
"mean_token_accuracy": 0.1460142984986305,
|
|
"num_tokens": 6588504.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.843828010559082,
|
|
"epoch": 0.2856860419137999,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996050999430878,
|
|
"loss": 5.8341,
|
|
"mean_token_accuracy": 0.1514135092496872,
|
|
"num_tokens": 6599969.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.977163600921631,
|
|
"epoch": 0.2861803084223013,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996030072677802,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.15263523682951927,
|
|
"num_tokens": 6611430.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.925257349014283,
|
|
"epoch": 0.2866745749308027,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996009090672037,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.14462630748748778,
|
|
"num_tokens": 6623247.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.96600112915039,
|
|
"epoch": 0.28716884143930405,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995988053414098,
|
|
"loss": 6.0225,
|
|
"mean_token_accuracy": 0.14478808343410493,
|
|
"num_tokens": 6635508.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.954598236083984,
|
|
"epoch": 0.2876631079478055,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995966960904506,
|
|
"loss": 5.9278,
|
|
"mean_token_accuracy": 0.14939955547451972,
|
|
"num_tokens": 6646020.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.978266286849975,
|
|
"epoch": 0.28815737445630685,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995945813143778,
|
|
"loss": 5.9568,
|
|
"mean_token_accuracy": 0.14021606743335724,
|
|
"num_tokens": 6658194.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.96915636062622,
|
|
"epoch": 0.2886516409648082,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995924610132435,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.1475129932165146,
|
|
"num_tokens": 6670582.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.928704261779785,
|
|
"epoch": 0.2891459074733096,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995903351870998,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.14914150834083556,
|
|
"num_tokens": 6680836.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.073338317871094,
|
|
"epoch": 0.28964017398181097,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499588203835999,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.14328644201159477,
|
|
"num_tokens": 6693045.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.933247041702271,
|
|
"epoch": 0.2901344404903124,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995860669599935,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.14393445253372192,
|
|
"num_tokens": 6704006.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.837153053283691,
|
|
"epoch": 0.29062870699881377,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499583924559136,
|
|
"loss": 5.8793,
|
|
"mean_token_accuracy": 0.14840964674949647,
|
|
"num_tokens": 6717027.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.981049108505249,
|
|
"epoch": 0.29112297350731514,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499581776633479,
|
|
"loss": 5.8749,
|
|
"mean_token_accuracy": 0.15013007670640946,
|
|
"num_tokens": 6728107.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.88144817352295,
|
|
"epoch": 0.2916172400158165,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995796231830756,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.15416626930236815,
|
|
"num_tokens": 6738628.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.934478712081909,
|
|
"epoch": 0.2921115065243179,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995774642079786,
|
|
"loss": 5.8421,
|
|
"mean_token_accuracy": 0.1537696972489357,
|
|
"num_tokens": 6749416.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.905332374572754,
|
|
"epoch": 0.2926057730328193,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499575299708241,
|
|
"loss": 5.947,
|
|
"mean_token_accuracy": 0.14088274016976357,
|
|
"num_tokens": 6761663.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.020952272415161,
|
|
"epoch": 0.2931000395413207,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995731296839163,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.1538805305957794,
|
|
"num_tokens": 6773557.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.81088809967041,
|
|
"epoch": 0.29359430604982206,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995709541350578,
|
|
"loss": 5.8199,
|
|
"mean_token_accuracy": 0.1593501538038254,
|
|
"num_tokens": 6782832.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.9672423839569095,
|
|
"epoch": 0.29408857255832344,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499568773061719,
|
|
"loss": 5.9335,
|
|
"mean_token_accuracy": 0.14496245384216308,
|
|
"num_tokens": 6795165.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.023906803131103,
|
|
"epoch": 0.2945828390668248,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995665864639534,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.1483907014131546,
|
|
"num_tokens": 6807054.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.876065492630005,
|
|
"epoch": 0.29507710557532624,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995643943418149,
|
|
"loss": 5.7332,
|
|
"mean_token_accuracy": 0.15653893128037452,
|
|
"num_tokens": 6817681.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.863463449478149,
|
|
"epoch": 0.2955713720838276,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995621966953576,
|
|
"loss": 5.9026,
|
|
"mean_token_accuracy": 0.1518360435962677,
|
|
"num_tokens": 6829387.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.936010360717773,
|
|
"epoch": 0.296065638592329,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995599935246355,
|
|
"loss": 5.9071,
|
|
"mean_token_accuracy": 0.1520347461104393,
|
|
"num_tokens": 6842023.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.92348346710205,
|
|
"epoch": 0.29655990510083036,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995577848297026,
|
|
"loss": 5.8992,
|
|
"mean_token_accuracy": 0.1477331593632698,
|
|
"num_tokens": 6853189.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.29655990510083036,
|
|
"eval_entropy": 5.794283665472878,
|
|
"eval_loss": 5.955329895019531,
|
|
"eval_mean_token_accuracy": 0.15471349589865732,
|
|
"eval_num_tokens": 6853189.0,
|
|
"eval_runtime": 26.573,
|
|
"eval_samples_per_second": 1223.537,
|
|
"eval_steps_per_second": 152.975,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 101150,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.07246089728e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|