618f2170d1
Model: fpadovani/jpn-jpan-10mb-after-ppt-Dp-100mb-ckpt500_seed455 Source: Original Platform
18068 lines
496 KiB
JSON
18068 lines
496 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.03866128101558,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 8.164552354812622,
|
|
"epoch": 0.0005770340450086555,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.7235,
|
|
"mean_token_accuracy": 0.13572018668055535,
|
|
"num_tokens": 13337.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 8.246073150634766,
|
|
"epoch": 0.001154068090017311,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.8919,
|
|
"mean_token_accuracy": 0.1187807373702526,
|
|
"num_tokens": 26339.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 8.20343017578125,
|
|
"epoch": 0.0017311021350259665,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.8009,
|
|
"mean_token_accuracy": 0.12226058542728424,
|
|
"num_tokens": 39118.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 8.200080871582031,
|
|
"epoch": 0.002308136180034622,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.9304,
|
|
"mean_token_accuracy": 0.11691192910075188,
|
|
"num_tokens": 51367.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 8.19017915725708,
|
|
"epoch": 0.0028851702250432777,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.8692,
|
|
"mean_token_accuracy": 0.12374739944934846,
|
|
"num_tokens": 64639.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 8.127242851257325,
|
|
"epoch": 0.003462204270051933,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.8742,
|
|
"mean_token_accuracy": 0.12418468594551087,
|
|
"num_tokens": 76244.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 8.187537956237794,
|
|
"epoch": 0.004039238315060588,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.912,
|
|
"mean_token_accuracy": 0.11309220269322395,
|
|
"num_tokens": 88490.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 8.093108320236206,
|
|
"epoch": 0.004616272360069244,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.8296,
|
|
"mean_token_accuracy": 0.12792499735951424,
|
|
"num_tokens": 102022.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 8.102341556549073,
|
|
"epoch": 0.0051933064050779,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.8503,
|
|
"mean_token_accuracy": 0.1249616153538227,
|
|
"num_tokens": 114442.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 8.1214994430542,
|
|
"epoch": 0.005770340450086555,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.9016,
|
|
"mean_token_accuracy": 0.11642022728919983,
|
|
"num_tokens": 128044.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 8.168946361541748,
|
|
"epoch": 0.006347374495095211,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.9196,
|
|
"mean_token_accuracy": 0.11260023415088653,
|
|
"num_tokens": 141818.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 8.143735218048096,
|
|
"epoch": 0.006924408540103866,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.8821,
|
|
"mean_token_accuracy": 0.12241782322525978,
|
|
"num_tokens": 155109.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 8.149381828308105,
|
|
"epoch": 0.0075014425851125215,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.8244,
|
|
"mean_token_accuracy": 0.12313178777694703,
|
|
"num_tokens": 167036.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 8.136874580383301,
|
|
"epoch": 0.008078476630121177,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.9797,
|
|
"mean_token_accuracy": 0.1158173181116581,
|
|
"num_tokens": 181398.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 8.139523601531982,
|
|
"epoch": 0.008655510675129832,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.8314,
|
|
"mean_token_accuracy": 0.12376198023557664,
|
|
"num_tokens": 193242.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 8.148941707611083,
|
|
"epoch": 0.009232544720138488,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.8335,
|
|
"mean_token_accuracy": 0.11901628077030182,
|
|
"num_tokens": 206744.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 8.112703990936279,
|
|
"epoch": 0.009809578765147143,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.7994,
|
|
"mean_token_accuracy": 0.1257437027990818,
|
|
"num_tokens": 219120.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 8.163854217529297,
|
|
"epoch": 0.0103866128101558,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.874,
|
|
"mean_token_accuracy": 0.12007838636636733,
|
|
"num_tokens": 231942.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 8.188548183441162,
|
|
"epoch": 0.010963646855164455,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.8636,
|
|
"mean_token_accuracy": 0.11973497197031975,
|
|
"num_tokens": 244786.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 8.129443168640137,
|
|
"epoch": 0.01154068090017311,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.7706,
|
|
"mean_token_accuracy": 0.13497541323304177,
|
|
"num_tokens": 257503.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 8.024968385696411,
|
|
"epoch": 0.012117714945181766,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.7253,
|
|
"mean_token_accuracy": 0.12938223108649255,
|
|
"num_tokens": 270330.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 8.047209739685059,
|
|
"epoch": 0.012694748990190421,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.8195,
|
|
"mean_token_accuracy": 0.13103519529104232,
|
|
"num_tokens": 283866.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 8.176537418365479,
|
|
"epoch": 0.013271783035199077,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.7892,
|
|
"mean_token_accuracy": 0.11941086724400521,
|
|
"num_tokens": 296715.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 8.116231632232665,
|
|
"epoch": 0.013848817080207732,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.8106,
|
|
"mean_token_accuracy": 0.12553205117583274,
|
|
"num_tokens": 309268.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 8.064244985580444,
|
|
"epoch": 0.014425851125216388,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.7923,
|
|
"mean_token_accuracy": 0.13402299582958221,
|
|
"num_tokens": 322471.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 8.130724334716797,
|
|
"epoch": 0.015002885170225043,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.8188,
|
|
"mean_token_accuracy": 0.12116066142916679,
|
|
"num_tokens": 335728.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 8.112252330780029,
|
|
"epoch": 0.015579919215233698,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.7868,
|
|
"mean_token_accuracy": 0.12612647488713263,
|
|
"num_tokens": 347861.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 8.101672506332397,
|
|
"epoch": 0.016156953260242354,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.8175,
|
|
"mean_token_accuracy": 0.12923522740602494,
|
|
"num_tokens": 360275.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.119850635528564,
|
|
"epoch": 0.01673398730525101,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.7957,
|
|
"mean_token_accuracy": 0.12403815910220146,
|
|
"num_tokens": 373948.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.126962089538575,
|
|
"epoch": 0.017311021350259664,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.7728,
|
|
"mean_token_accuracy": 0.12742806524038314,
|
|
"num_tokens": 386267.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.088498830795288,
|
|
"epoch": 0.01788805539526832,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.7321,
|
|
"mean_token_accuracy": 0.12699732854962348,
|
|
"num_tokens": 398595.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.019657421112061,
|
|
"epoch": 0.018465089440276975,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.7922,
|
|
"mean_token_accuracy": 0.12140516936779022,
|
|
"num_tokens": 410626.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.144418334960937,
|
|
"epoch": 0.019042123485285632,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8247,
|
|
"mean_token_accuracy": 0.12391015514731407,
|
|
"num_tokens": 423176.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.170842695236207,
|
|
"epoch": 0.019619157530294286,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7815,
|
|
"mean_token_accuracy": 0.12869809195399284,
|
|
"num_tokens": 435997.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.032562351226806,
|
|
"epoch": 0.020196191575302943,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.7859,
|
|
"mean_token_accuracy": 0.1265020787715912,
|
|
"num_tokens": 449295.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.155485820770263,
|
|
"epoch": 0.0207732256203116,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.805,
|
|
"mean_token_accuracy": 0.12606418877840042,
|
|
"num_tokens": 463983.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.100854730606079,
|
|
"epoch": 0.021350259665320254,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.814,
|
|
"mean_token_accuracy": 0.12124907821416855,
|
|
"num_tokens": 476849.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.118375110626221,
|
|
"epoch": 0.02192729371032891,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.8255,
|
|
"mean_token_accuracy": 0.12398237809538841,
|
|
"num_tokens": 489120.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.123465538024902,
|
|
"epoch": 0.022504327755337564,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.7552,
|
|
"mean_token_accuracy": 0.1278926372528076,
|
|
"num_tokens": 501085.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.084616231918336,
|
|
"epoch": 0.02308136180034622,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.8169,
|
|
"mean_token_accuracy": 0.1159471996128559,
|
|
"num_tokens": 513207.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.162526893615723,
|
|
"epoch": 0.023658395845354875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.7468,
|
|
"mean_token_accuracy": 0.11916335672140121,
|
|
"num_tokens": 524809.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.082560157775879,
|
|
"epoch": 0.024235429890363532,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.8136,
|
|
"mean_token_accuracy": 0.12392313480377197,
|
|
"num_tokens": 538950.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.15697078704834,
|
|
"epoch": 0.024812463935372186,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.793,
|
|
"mean_token_accuracy": 0.13155161514878272,
|
|
"num_tokens": 551199.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.045954370498658,
|
|
"epoch": 0.025389497980380843,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.731,
|
|
"mean_token_accuracy": 0.12966038063168525,
|
|
"num_tokens": 563202.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.128791332244873,
|
|
"epoch": 0.025966532025389497,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.7501,
|
|
"mean_token_accuracy": 0.12665933594107628,
|
|
"num_tokens": 576716.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.056756114959716,
|
|
"epoch": 0.026543566070398154,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.7642,
|
|
"mean_token_accuracy": 0.12589010149240493,
|
|
"num_tokens": 588413.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.159916019439697,
|
|
"epoch": 0.027120600115406807,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.8143,
|
|
"mean_token_accuracy": 0.12119406759738922,
|
|
"num_tokens": 602052.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.061726570129395,
|
|
"epoch": 0.027697634160415464,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.7646,
|
|
"mean_token_accuracy": 0.12605880349874496,
|
|
"num_tokens": 614508.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.145089435577393,
|
|
"epoch": 0.02827466820542412,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.8077,
|
|
"mean_token_accuracy": 0.12516265287995337,
|
|
"num_tokens": 628758.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.007381439208984,
|
|
"epoch": 0.028851702250432775,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.7227,
|
|
"mean_token_accuracy": 0.1311620891094208,
|
|
"num_tokens": 641046.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.058531141281128,
|
|
"epoch": 0.029428736295441432,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.7143,
|
|
"mean_token_accuracy": 0.12785313203930854,
|
|
"num_tokens": 653910.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.076497840881348,
|
|
"epoch": 0.030005770340450086,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.7051,
|
|
"mean_token_accuracy": 0.13272143229842187,
|
|
"num_tokens": 665862.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.979534912109375,
|
|
"epoch": 0.030582804385458743,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.7153,
|
|
"mean_token_accuracy": 0.1262400984764099,
|
|
"num_tokens": 678854.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.1496657371521,
|
|
"epoch": 0.031159838430467397,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.734,
|
|
"mean_token_accuracy": 0.12493550479412079,
|
|
"num_tokens": 690188.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.9987037658691404,
|
|
"epoch": 0.031736872475476054,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.7109,
|
|
"mean_token_accuracy": 0.13045160546898843,
|
|
"num_tokens": 702041.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.06501841545105,
|
|
"epoch": 0.03231390652048471,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.7275,
|
|
"mean_token_accuracy": 0.1316023886203766,
|
|
"num_tokens": 714109.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.041949319839478,
|
|
"epoch": 0.03289094056549336,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.7499,
|
|
"mean_token_accuracy": 0.12448728755116463,
|
|
"num_tokens": 726120.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.055285263061524,
|
|
"epoch": 0.03346797461050202,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.6926,
|
|
"mean_token_accuracy": 0.12664653435349466,
|
|
"num_tokens": 737868.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.153725147247314,
|
|
"epoch": 0.034045008655510675,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.769,
|
|
"mean_token_accuracy": 0.12764903903007507,
|
|
"num_tokens": 751829.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.056012821197509,
|
|
"epoch": 0.03462204270051933,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.7237,
|
|
"mean_token_accuracy": 0.12691396623849868,
|
|
"num_tokens": 764457.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.08794288635254,
|
|
"epoch": 0.03519907674552799,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.7548,
|
|
"mean_token_accuracy": 0.12576484456658363,
|
|
"num_tokens": 776887.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.057601928710938,
|
|
"epoch": 0.03577611079053664,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.7485,
|
|
"mean_token_accuracy": 0.12234131619334221,
|
|
"num_tokens": 789001.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.092532968521118,
|
|
"epoch": 0.0363531448355453,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.7387,
|
|
"mean_token_accuracy": 0.1253275267779827,
|
|
"num_tokens": 802719.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.023380422592163,
|
|
"epoch": 0.03693017888055395,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.6701,
|
|
"mean_token_accuracy": 0.13013212531805038,
|
|
"num_tokens": 815064.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.050508165359497,
|
|
"epoch": 0.03750721292556261,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.7264,
|
|
"mean_token_accuracy": 0.12830724567174911,
|
|
"num_tokens": 827778.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.036063766479492,
|
|
"epoch": 0.038084246970571264,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.6907,
|
|
"mean_token_accuracy": 0.12928537279367447,
|
|
"num_tokens": 840691.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.05320930480957,
|
|
"epoch": 0.03866128101557992,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.7446,
|
|
"mean_token_accuracy": 0.11841234192252159,
|
|
"num_tokens": 852818.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.989465665817261,
|
|
"epoch": 0.03923831506058857,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.7555,
|
|
"mean_token_accuracy": 0.13145181983709336,
|
|
"num_tokens": 866854.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.109742450714112,
|
|
"epoch": 0.03981534910559723,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.7113,
|
|
"mean_token_accuracy": 0.12292054072022437,
|
|
"num_tokens": 879234.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.068915796279907,
|
|
"epoch": 0.040392383150605886,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.6449,
|
|
"mean_token_accuracy": 0.12445924580097198,
|
|
"num_tokens": 890927.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.012982606887817,
|
|
"epoch": 0.04096941719561454,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.6946,
|
|
"mean_token_accuracy": 0.12666598856449127,
|
|
"num_tokens": 902965.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.02733473777771,
|
|
"epoch": 0.0415464512406232,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.6597,
|
|
"mean_token_accuracy": 0.1288968488574028,
|
|
"num_tokens": 916384.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.065688943862915,
|
|
"epoch": 0.042123485285631854,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.5615,
|
|
"mean_token_accuracy": 0.13689733892679215,
|
|
"num_tokens": 928618.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.963602304458618,
|
|
"epoch": 0.04270051933064051,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.6959,
|
|
"mean_token_accuracy": 0.12423681542277336,
|
|
"num_tokens": 940087.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.927715587615967,
|
|
"epoch": 0.04327755337564916,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.6993,
|
|
"mean_token_accuracy": 0.13103626742959024,
|
|
"num_tokens": 953322.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.1933123588562,
|
|
"epoch": 0.04385458742065782,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.7438,
|
|
"mean_token_accuracy": 0.12380573004484177,
|
|
"num_tokens": 965815.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.940394258499145,
|
|
"epoch": 0.044431621465666475,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.6752,
|
|
"mean_token_accuracy": 0.12669538110494613,
|
|
"num_tokens": 978731.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.027307653427124,
|
|
"epoch": 0.04500865551067513,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.5735,
|
|
"mean_token_accuracy": 0.13436778634786606,
|
|
"num_tokens": 989505.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.926584243774414,
|
|
"epoch": 0.04558568955568378,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.7088,
|
|
"mean_token_accuracy": 0.12935978397727013,
|
|
"num_tokens": 1001888.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.996991300582886,
|
|
"epoch": 0.04616272360069244,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.6416,
|
|
"mean_token_accuracy": 0.13667909130454065,
|
|
"num_tokens": 1015362.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.05469207763672,
|
|
"epoch": 0.0467397576457011,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.7052,
|
|
"mean_token_accuracy": 0.12611190229654312,
|
|
"num_tokens": 1028700.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.959253025054932,
|
|
"epoch": 0.04731679169070975,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.7608,
|
|
"mean_token_accuracy": 0.123697529733181,
|
|
"num_tokens": 1040766.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.0970055103302,
|
|
"epoch": 0.04789382573571841,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.5937,
|
|
"mean_token_accuracy": 0.12767987027764321,
|
|
"num_tokens": 1054321.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.88906192779541,
|
|
"epoch": 0.048470859780727064,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.6707,
|
|
"mean_token_accuracy": 0.13818718865513802,
|
|
"num_tokens": 1065410.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.037972116470337,
|
|
"epoch": 0.04904789382573572,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.695,
|
|
"mean_token_accuracy": 0.11944770142436027,
|
|
"num_tokens": 1077369.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.041876745223998,
|
|
"epoch": 0.04962492787074437,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.6535,
|
|
"mean_token_accuracy": 0.1305831678211689,
|
|
"num_tokens": 1089065.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.918288230895996,
|
|
"epoch": 0.05020196191575303,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.5798,
|
|
"mean_token_accuracy": 0.13306143879890442,
|
|
"num_tokens": 1101285.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.921914911270141,
|
|
"epoch": 0.050778995960761686,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.5956,
|
|
"mean_token_accuracy": 0.1294034317135811,
|
|
"num_tokens": 1114001.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.043266582489014,
|
|
"epoch": 0.05135603000577034,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.6698,
|
|
"mean_token_accuracy": 0.12662654593586922,
|
|
"num_tokens": 1126751.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.9704231262207035,
|
|
"epoch": 0.05193306405077899,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.6779,
|
|
"mean_token_accuracy": 0.125260828435421,
|
|
"num_tokens": 1140737.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.907954835891724,
|
|
"epoch": 0.052510098095787654,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.5845,
|
|
"mean_token_accuracy": 0.12618799656629562,
|
|
"num_tokens": 1152569.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.992079973220825,
|
|
"epoch": 0.05308713214079631,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.6289,
|
|
"mean_token_accuracy": 0.12820862010121345,
|
|
"num_tokens": 1166163.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.962404775619507,
|
|
"epoch": 0.05366416618580496,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.606,
|
|
"mean_token_accuracy": 0.12718955501914025,
|
|
"num_tokens": 1177647.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.939283180236816,
|
|
"epoch": 0.054241200230813615,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.6284,
|
|
"mean_token_accuracy": 0.12961039319634438,
|
|
"num_tokens": 1190884.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.944163656234741,
|
|
"epoch": 0.054818234275822275,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.6643,
|
|
"mean_token_accuracy": 0.12723161578178405,
|
|
"num_tokens": 1203276.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.883432531356812,
|
|
"epoch": 0.05539526832083093,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.543,
|
|
"mean_token_accuracy": 0.14349528700113295,
|
|
"num_tokens": 1216001.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.038554286956787,
|
|
"epoch": 0.05597230236583958,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.6852,
|
|
"mean_token_accuracy": 0.12811896130442618,
|
|
"num_tokens": 1228724.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.979045391082764,
|
|
"epoch": 0.05654933641084824,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.6783,
|
|
"mean_token_accuracy": 0.13219430297613144,
|
|
"num_tokens": 1242731.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.960198593139649,
|
|
"epoch": 0.0571263704558569,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.6384,
|
|
"mean_token_accuracy": 0.13144275397062302,
|
|
"num_tokens": 1255275.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.924617958068848,
|
|
"epoch": 0.05770340450086555,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.6371,
|
|
"mean_token_accuracy": 0.13291670829057695,
|
|
"num_tokens": 1267719.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.997011137008667,
|
|
"epoch": 0.058280438545874204,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.6101,
|
|
"mean_token_accuracy": 0.12541425302624704,
|
|
"num_tokens": 1279960.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.934813690185547,
|
|
"epoch": 0.058857472590882864,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.6068,
|
|
"mean_token_accuracy": 0.1224808193743229,
|
|
"num_tokens": 1292570.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.883869075775147,
|
|
"epoch": 0.05943450663589152,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.6065,
|
|
"mean_token_accuracy": 0.1239744633436203,
|
|
"num_tokens": 1305548.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.938631439208985,
|
|
"epoch": 0.06001154068090017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.5338,
|
|
"mean_token_accuracy": 0.13228121995925904,
|
|
"num_tokens": 1318904.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.933946323394776,
|
|
"epoch": 0.060588574725908825,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.626,
|
|
"mean_token_accuracy": 0.12482062131166458,
|
|
"num_tokens": 1332841.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.883927583694458,
|
|
"epoch": 0.061165608770917486,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.6283,
|
|
"mean_token_accuracy": 0.12460393533110618,
|
|
"num_tokens": 1345708.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.9526472091674805,
|
|
"epoch": 0.06174264281592614,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.5758,
|
|
"mean_token_accuracy": 0.1290095902979374,
|
|
"num_tokens": 1358611.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.871510028839111,
|
|
"epoch": 0.06231967686093479,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.6509,
|
|
"mean_token_accuracy": 0.1282058410346508,
|
|
"num_tokens": 1372753.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.92236442565918,
|
|
"epoch": 0.06289671090594345,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.5316,
|
|
"mean_token_accuracy": 0.13794104903936386,
|
|
"num_tokens": 1383811.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.879396390914917,
|
|
"epoch": 0.06347374495095211,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.5916,
|
|
"mean_token_accuracy": 0.12931896969676018,
|
|
"num_tokens": 1395228.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.91993293762207,
|
|
"epoch": 0.06405077899596076,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.6362,
|
|
"mean_token_accuracy": 0.12369817793369293,
|
|
"num_tokens": 1408869.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.821833944320678,
|
|
"epoch": 0.06462781304096941,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.5481,
|
|
"mean_token_accuracy": 0.13478931561112403,
|
|
"num_tokens": 1420926.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.885378456115722,
|
|
"epoch": 0.06520484708597807,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.5576,
|
|
"mean_token_accuracy": 0.13291405290365219,
|
|
"num_tokens": 1432435.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.920798873901367,
|
|
"epoch": 0.06578188113098672,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.6686,
|
|
"mean_token_accuracy": 0.12425242960453034,
|
|
"num_tokens": 1444716.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.834726428985595,
|
|
"epoch": 0.06635891517599539,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.5579,
|
|
"mean_token_accuracy": 0.13059103563427926,
|
|
"num_tokens": 1458129.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.880359935760498,
|
|
"epoch": 0.06693594922100404,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.5193,
|
|
"mean_token_accuracy": 0.13621216639876366,
|
|
"num_tokens": 1472076.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.737836599349976,
|
|
"epoch": 0.0675129832660127,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.5129,
|
|
"mean_token_accuracy": 0.1413876920938492,
|
|
"num_tokens": 1486026.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.900694990158081,
|
|
"epoch": 0.06809001731102135,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.5203,
|
|
"mean_token_accuracy": 0.14100683629512786,
|
|
"num_tokens": 1498735.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.771698427200318,
|
|
"epoch": 0.06866705135603,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.5156,
|
|
"mean_token_accuracy": 0.13441314548254013,
|
|
"num_tokens": 1510755.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.878929662704468,
|
|
"epoch": 0.06924408540103866,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.5271,
|
|
"mean_token_accuracy": 0.13422106131911277,
|
|
"num_tokens": 1522386.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.86671781539917,
|
|
"epoch": 0.06982111944604731,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.5695,
|
|
"mean_token_accuracy": 0.13297740891575813,
|
|
"num_tokens": 1534757.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.748486709594727,
|
|
"epoch": 0.07039815349105598,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.5497,
|
|
"mean_token_accuracy": 0.1324236772954464,
|
|
"num_tokens": 1547684.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.883321237564087,
|
|
"epoch": 0.07097518753606463,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.5574,
|
|
"mean_token_accuracy": 0.12341172322630882,
|
|
"num_tokens": 1560583.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.867546463012696,
|
|
"epoch": 0.07155222158107329,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.5735,
|
|
"mean_token_accuracy": 0.12901610583066941,
|
|
"num_tokens": 1573174.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.840350246429443,
|
|
"epoch": 0.07212925562608194,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.5389,
|
|
"mean_token_accuracy": 0.1297079123556614,
|
|
"num_tokens": 1585746.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.879965114593506,
|
|
"epoch": 0.0727062896710906,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.5187,
|
|
"mean_token_accuracy": 0.12504662796854973,
|
|
"num_tokens": 1598538.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.854893636703491,
|
|
"epoch": 0.07328332371609925,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.5054,
|
|
"mean_token_accuracy": 0.13247747644782065,
|
|
"num_tokens": 1612598.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.714817237854004,
|
|
"epoch": 0.0738603577611079,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.4557,
|
|
"mean_token_accuracy": 0.136217100918293,
|
|
"num_tokens": 1624418.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.805634260177612,
|
|
"epoch": 0.07443739180611655,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.5434,
|
|
"mean_token_accuracy": 0.1354817859828472,
|
|
"num_tokens": 1637512.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.727578449249267,
|
|
"epoch": 0.07501442585112522,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.4692,
|
|
"mean_token_accuracy": 0.13448835983872415,
|
|
"num_tokens": 1650413.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.775011730194092,
|
|
"epoch": 0.07559145989613388,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.4587,
|
|
"mean_token_accuracy": 0.13572532832622528,
|
|
"num_tokens": 1662225.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.828440713882446,
|
|
"epoch": 0.07616849394114253,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.5138,
|
|
"mean_token_accuracy": 0.13002411052584648,
|
|
"num_tokens": 1674458.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.777482557296753,
|
|
"epoch": 0.07674552798615118,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.5272,
|
|
"mean_token_accuracy": 0.12747668400406836,
|
|
"num_tokens": 1686366.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.848160314559936,
|
|
"epoch": 0.07732256203115984,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.5094,
|
|
"mean_token_accuracy": 0.13185340240597726,
|
|
"num_tokens": 1699654.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.789048290252685,
|
|
"epoch": 0.07789959607616849,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.4846,
|
|
"mean_token_accuracy": 0.13520109057426452,
|
|
"num_tokens": 1711923.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.776696729660034,
|
|
"epoch": 0.07847663012117714,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.4714,
|
|
"mean_token_accuracy": 0.13042250275611877,
|
|
"num_tokens": 1723413.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.701392698287964,
|
|
"epoch": 0.07905366416618581,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.4525,
|
|
"mean_token_accuracy": 0.13371195793151855,
|
|
"num_tokens": 1735975.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.6978672504425045,
|
|
"epoch": 0.07963069821119446,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.4664,
|
|
"mean_token_accuracy": 0.1311781272292137,
|
|
"num_tokens": 1748563.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.824566507339478,
|
|
"epoch": 0.08020773225620312,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.4771,
|
|
"mean_token_accuracy": 0.1280561789870262,
|
|
"num_tokens": 1762914.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.78171935081482,
|
|
"epoch": 0.08078476630121177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.4409,
|
|
"mean_token_accuracy": 0.13339700549840927,
|
|
"num_tokens": 1776084.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.676154851913452,
|
|
"epoch": 0.08136180034622043,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.3918,
|
|
"mean_token_accuracy": 0.1427437275648117,
|
|
"num_tokens": 1789316.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.7570672035217285,
|
|
"epoch": 0.08193883439122908,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.4787,
|
|
"mean_token_accuracy": 0.13278622627258302,
|
|
"num_tokens": 1801576.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.686878871917725,
|
|
"epoch": 0.08251586843623773,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.4405,
|
|
"mean_token_accuracy": 0.13206920996308327,
|
|
"num_tokens": 1814039.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.712433910369873,
|
|
"epoch": 0.0830929024812464,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.3683,
|
|
"mean_token_accuracy": 0.13764831200242042,
|
|
"num_tokens": 1825193.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.6329395294189455,
|
|
"epoch": 0.08366993652625505,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.4537,
|
|
"mean_token_accuracy": 0.13079532310366632,
|
|
"num_tokens": 1837983.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.7968615055084225,
|
|
"epoch": 0.08424697057126371,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.3549,
|
|
"mean_token_accuracy": 0.14052335917949677,
|
|
"num_tokens": 1849830.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.692524814605713,
|
|
"epoch": 0.08482400461627236,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.448,
|
|
"mean_token_accuracy": 0.12845715060830115,
|
|
"num_tokens": 1862577.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.684691143035889,
|
|
"epoch": 0.08540103866128101,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.4389,
|
|
"mean_token_accuracy": 0.1409561887383461,
|
|
"num_tokens": 1874888.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.630507850646973,
|
|
"epoch": 0.08597807270628967,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.38,
|
|
"mean_token_accuracy": 0.13916135132312774,
|
|
"num_tokens": 1888400.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.7386709690094,
|
|
"epoch": 0.08655510675129832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.4495,
|
|
"mean_token_accuracy": 0.1248070776462555,
|
|
"num_tokens": 1900961.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.621120452880859,
|
|
"epoch": 0.08713214079630698,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.3786,
|
|
"mean_token_accuracy": 0.1386454552412033,
|
|
"num_tokens": 1913410.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.710708427429199,
|
|
"epoch": 0.08770917484131564,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.4316,
|
|
"mean_token_accuracy": 0.12876348271965982,
|
|
"num_tokens": 1926602.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.669585132598877,
|
|
"epoch": 0.0882862088863243,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.3984,
|
|
"mean_token_accuracy": 0.12868618741631507,
|
|
"num_tokens": 1938904.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.6731616973876955,
|
|
"epoch": 0.08886324293133295,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.4165,
|
|
"mean_token_accuracy": 0.12934457659721374,
|
|
"num_tokens": 1952827.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.672389221191406,
|
|
"epoch": 0.0894402769763416,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.4066,
|
|
"mean_token_accuracy": 0.13497869223356246,
|
|
"num_tokens": 1965182.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.608702707290649,
|
|
"epoch": 0.09001731102135026,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.3787,
|
|
"mean_token_accuracy": 0.13133419081568717,
|
|
"num_tokens": 1976953.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.742263889312744,
|
|
"epoch": 0.09059434506635891,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.4563,
|
|
"mean_token_accuracy": 0.12778021022677422,
|
|
"num_tokens": 1990019.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.656824254989624,
|
|
"epoch": 0.09117137911136756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.4006,
|
|
"mean_token_accuracy": 0.12971119731664657,
|
|
"num_tokens": 2002976.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.721537303924561,
|
|
"epoch": 0.09174841315637623,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.4165,
|
|
"mean_token_accuracy": 0.13233844116330146,
|
|
"num_tokens": 2017368.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.608252668380738,
|
|
"epoch": 0.09232544720138489,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.2751,
|
|
"mean_token_accuracy": 0.14428590834140778,
|
|
"num_tokens": 2029838.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.679257488250732,
|
|
"epoch": 0.09290248124639354,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.3901,
|
|
"mean_token_accuracy": 0.12942394018173217,
|
|
"num_tokens": 2042085.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.609614467620849,
|
|
"epoch": 0.0934795152914022,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.429,
|
|
"mean_token_accuracy": 0.12986384257674216,
|
|
"num_tokens": 2053268.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.730389881134033,
|
|
"epoch": 0.09405654933641085,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.3995,
|
|
"mean_token_accuracy": 0.1275894299149513,
|
|
"num_tokens": 2066621.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.573925876617432,
|
|
"epoch": 0.0946335833814195,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.2761,
|
|
"mean_token_accuracy": 0.13354206904768945,
|
|
"num_tokens": 2079590.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.547151565551758,
|
|
"epoch": 0.09521061742642815,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.3921,
|
|
"mean_token_accuracy": 0.1272098556160927,
|
|
"num_tokens": 2091729.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.617713403701782,
|
|
"epoch": 0.09578765147143682,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.3473,
|
|
"mean_token_accuracy": 0.14121743738651277,
|
|
"num_tokens": 2104254.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.655541276931762,
|
|
"epoch": 0.09636468551644548,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.4288,
|
|
"mean_token_accuracy": 0.12773946151137353,
|
|
"num_tokens": 2116327.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.666590738296509,
|
|
"epoch": 0.09694171956145413,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.4027,
|
|
"mean_token_accuracy": 0.1262945294380188,
|
|
"num_tokens": 2129153.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.557644271850586,
|
|
"epoch": 0.09751875360646278,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.3806,
|
|
"mean_token_accuracy": 0.13962640687823297,
|
|
"num_tokens": 2141705.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.566726779937744,
|
|
"epoch": 0.09809578765147144,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.2944,
|
|
"mean_token_accuracy": 0.14180327355861663,
|
|
"num_tokens": 2153760.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.562725973129273,
|
|
"epoch": 0.09867282169648009,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.3744,
|
|
"mean_token_accuracy": 0.1379995971918106,
|
|
"num_tokens": 2168206.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.643193006515503,
|
|
"epoch": 0.09924985574148874,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.3256,
|
|
"mean_token_accuracy": 0.13964372426271437,
|
|
"num_tokens": 2180779.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.448547601699829,
|
|
"epoch": 0.0998268897864974,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.2866,
|
|
"mean_token_accuracy": 0.13754021003842354,
|
|
"num_tokens": 2194075.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.622214460372925,
|
|
"epoch": 0.10040392383150606,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.2761,
|
|
"mean_token_accuracy": 0.13813476786017417,
|
|
"num_tokens": 2206424.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.570018768310547,
|
|
"epoch": 0.10098095787651472,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.3298,
|
|
"mean_token_accuracy": 0.13034077361226082,
|
|
"num_tokens": 2218550.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.488341760635376,
|
|
"epoch": 0.10155799192152337,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.3548,
|
|
"mean_token_accuracy": 0.13045953586697578,
|
|
"num_tokens": 2231857.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.663240146636963,
|
|
"epoch": 0.10213502596653203,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.3455,
|
|
"mean_token_accuracy": 0.1357438363134861,
|
|
"num_tokens": 2244057.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.607003974914551,
|
|
"epoch": 0.10271206001154068,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.3748,
|
|
"mean_token_accuracy": 0.12887232899665832,
|
|
"num_tokens": 2257361.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.620429849624633,
|
|
"epoch": 0.10328909405654933,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.3642,
|
|
"mean_token_accuracy": 0.12847339510917663,
|
|
"num_tokens": 2269599.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.570056581497193,
|
|
"epoch": 0.10386612810155799,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.3901,
|
|
"mean_token_accuracy": 0.1326812021434307,
|
|
"num_tokens": 2282791.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.571472215652466,
|
|
"epoch": 0.10444316214656665,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.3424,
|
|
"mean_token_accuracy": 0.13455241098999976,
|
|
"num_tokens": 2295336.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.547875213623047,
|
|
"epoch": 0.10502019619157531,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.3645,
|
|
"mean_token_accuracy": 0.12806227579712867,
|
|
"num_tokens": 2308813.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.587298440933227,
|
|
"epoch": 0.10559723023658396,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.3429,
|
|
"mean_token_accuracy": 0.1311824142932892,
|
|
"num_tokens": 2321374.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.545827627182007,
|
|
"epoch": 0.10617426428159261,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.338,
|
|
"mean_token_accuracy": 0.1307897984981537,
|
|
"num_tokens": 2333698.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.575364637374878,
|
|
"epoch": 0.10675129832660127,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.3168,
|
|
"mean_token_accuracy": 0.13864337727427484,
|
|
"num_tokens": 2346557.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.4012375831604,
|
|
"epoch": 0.10732833237160992,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.1836,
|
|
"mean_token_accuracy": 0.14260239005088807,
|
|
"num_tokens": 2360003.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.531010293960572,
|
|
"epoch": 0.10790536641661858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.2266,
|
|
"mean_token_accuracy": 0.13916042149066926,
|
|
"num_tokens": 2372765.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.4169941425323485,
|
|
"epoch": 0.10848240046162723,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.2525,
|
|
"mean_token_accuracy": 0.14179157763719558,
|
|
"num_tokens": 2385154.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.489320898056031,
|
|
"epoch": 0.1090594345066359,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.2705,
|
|
"mean_token_accuracy": 0.13921171203255653,
|
|
"num_tokens": 2397264.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.529940891265869,
|
|
"epoch": 0.10963646855164455,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.3586,
|
|
"mean_token_accuracy": 0.1348928801715374,
|
|
"num_tokens": 2408652.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.531420660018921,
|
|
"epoch": 0.1102135025966532,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.331,
|
|
"mean_token_accuracy": 0.1281139448285103,
|
|
"num_tokens": 2421683.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.433173418045044,
|
|
"epoch": 0.11079053664166186,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.2361,
|
|
"mean_token_accuracy": 0.13509340435266495,
|
|
"num_tokens": 2434622.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.488950967788696,
|
|
"epoch": 0.11136757068667051,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.2495,
|
|
"mean_token_accuracy": 0.14383002668619155,
|
|
"num_tokens": 2448157.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.640981388092041,
|
|
"epoch": 0.11194460473167916,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.2964,
|
|
"mean_token_accuracy": 0.13189825639128686,
|
|
"num_tokens": 2460284.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.387933540344238,
|
|
"epoch": 0.11252163877668782,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.309,
|
|
"mean_token_accuracy": 0.13392101153731345,
|
|
"num_tokens": 2473031.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.540426445007324,
|
|
"epoch": 0.11309867282169649,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.3065,
|
|
"mean_token_accuracy": 0.13692763224244117,
|
|
"num_tokens": 2486870.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.408073234558105,
|
|
"epoch": 0.11367570686670514,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.2302,
|
|
"mean_token_accuracy": 0.1348964937031269,
|
|
"num_tokens": 2498921.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.482239198684693,
|
|
"epoch": 0.1142527409117138,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.2894,
|
|
"mean_token_accuracy": 0.13312276005744933,
|
|
"num_tokens": 2511122.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.542117166519165,
|
|
"epoch": 0.11482977495672245,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.3043,
|
|
"mean_token_accuracy": 0.1307055488228798,
|
|
"num_tokens": 2523726.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.41837511062622,
|
|
"epoch": 0.1154068090017311,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.1923,
|
|
"mean_token_accuracy": 0.1403934270143509,
|
|
"num_tokens": 2536192.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.390990495681763,
|
|
"epoch": 0.11598384304673975,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999999975783157,
|
|
"loss": 7.2816,
|
|
"mean_token_accuracy": 0.1320057801902294,
|
|
"num_tokens": 2550200.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.49788727760315,
|
|
"epoch": 0.11656087709174841,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999877402236,
|
|
"loss": 7.2259,
|
|
"mean_token_accuracy": 0.13413601964712143,
|
|
"num_tokens": 2564045.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.4572518825531,
|
|
"epoch": 0.11713791113675708,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999703343686,
|
|
"loss": 7.238,
|
|
"mean_token_accuracy": 0.13197707533836364,
|
|
"num_tokens": 2576210.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.300177717208863,
|
|
"epoch": 0.11771494518176573,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999999453607515,
|
|
"loss": 7.2207,
|
|
"mean_token_accuracy": 0.13198934867978096,
|
|
"num_tokens": 2589325.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.501029205322266,
|
|
"epoch": 0.11829197922677438,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999128193729,
|
|
"loss": 7.3114,
|
|
"mean_token_accuracy": 0.13109516799449922,
|
|
"num_tokens": 2601522.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.46219277381897,
|
|
"epoch": 0.11886901327178304,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499999872710234,
|
|
"loss": 7.2959,
|
|
"mean_token_accuracy": 0.12850206419825555,
|
|
"num_tokens": 2615364.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.4426497459411625,
|
|
"epoch": 0.11944604731679169,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999998250333361,
|
|
"loss": 7.2097,
|
|
"mean_token_accuracy": 0.13902488797903062,
|
|
"num_tokens": 2628528.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.394994068145752,
|
|
"epoch": 0.12002308136180034,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499999769788681,
|
|
"loss": 7.2178,
|
|
"mean_token_accuracy": 0.13481198623776436,
|
|
"num_tokens": 2641877.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.42519211769104,
|
|
"epoch": 0.120600115406809,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999997069762703,
|
|
"loss": 7.2311,
|
|
"mean_token_accuracy": 0.13621581196784974,
|
|
"num_tokens": 2655419.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.355701065063476,
|
|
"epoch": 0.12117714945181765,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999996365961062,
|
|
"loss": 7.1697,
|
|
"mean_token_accuracy": 0.13674544021487237,
|
|
"num_tokens": 2667551.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.418414783477783,
|
|
"epoch": 0.12175418349682632,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999995586481912,
|
|
"loss": 7.1974,
|
|
"mean_token_accuracy": 0.14013378769159318,
|
|
"num_tokens": 2679948.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.3376726627349855,
|
|
"epoch": 0.12233121754183497,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999994731325276,
|
|
"loss": 7.2412,
|
|
"mean_token_accuracy": 0.13359286561608313,
|
|
"num_tokens": 2691501.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.368611145019531,
|
|
"epoch": 0.12290825158684363,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999993800491187,
|
|
"loss": 7.176,
|
|
"mean_token_accuracy": 0.14094864577054977,
|
|
"num_tokens": 2702689.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.382964181900024,
|
|
"epoch": 0.12348528563185228,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999992793979672,
|
|
"loss": 7.1841,
|
|
"mean_token_accuracy": 0.13821902945637704,
|
|
"num_tokens": 2715023.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.3155985355377195,
|
|
"epoch": 0.12406231967686093,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999991711790769,
|
|
"loss": 7.1123,
|
|
"mean_token_accuracy": 0.13841997236013412,
|
|
"num_tokens": 2729517.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.430340957641602,
|
|
"epoch": 0.12463935372186959,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999990553924511,
|
|
"loss": 7.2008,
|
|
"mean_token_accuracy": 0.13296948969364167,
|
|
"num_tokens": 2740984.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.35272068977356,
|
|
"epoch": 0.12521638776687824,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999989320380939,
|
|
"loss": 7.1488,
|
|
"mean_token_accuracy": 0.1401528961956501,
|
|
"num_tokens": 2752943.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.400033378601075,
|
|
"epoch": 0.1257934218118869,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999988011160094,
|
|
"loss": 7.2192,
|
|
"mean_token_accuracy": 0.1346215933561325,
|
|
"num_tokens": 2765613.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.316109132766724,
|
|
"epoch": 0.12637045585689555,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499998662626202,
|
|
"loss": 7.1648,
|
|
"mean_token_accuracy": 0.1355959139764309,
|
|
"num_tokens": 2776820.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.295491933822632,
|
|
"epoch": 0.12694748990190421,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999985165686764,
|
|
"loss": 7.2006,
|
|
"mean_token_accuracy": 0.13195707648992538,
|
|
"num_tokens": 2788981.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.3825420379638675,
|
|
"epoch": 0.12752452394691285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999983629434373,
|
|
"loss": 7.0555,
|
|
"mean_token_accuracy": 0.14337626621127128,
|
|
"num_tokens": 2801975.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.324372148513794,
|
|
"epoch": 0.12810155799192152,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999982017504901,
|
|
"loss": 7.1557,
|
|
"mean_token_accuracy": 0.13406250923871993,
|
|
"num_tokens": 2814708.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.2684407234191895,
|
|
"epoch": 0.1286785920369302,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999980329898401,
|
|
"loss": 7.174,
|
|
"mean_token_accuracy": 0.13960450887680054,
|
|
"num_tokens": 2827903.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.3982825756073,
|
|
"epoch": 0.12925562608193883,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499997856661493,
|
|
"loss": 7.1933,
|
|
"mean_token_accuracy": 0.13698331117630005,
|
|
"num_tokens": 2841077.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.370109128952026,
|
|
"epoch": 0.1298326601269475,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499997672765455,
|
|
"loss": 7.1852,
|
|
"mean_token_accuracy": 0.13384110406041144,
|
|
"num_tokens": 2853235.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.2596477508544925,
|
|
"epoch": 0.13040969417195614,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999974813017318,
|
|
"loss": 7.1604,
|
|
"mean_token_accuracy": 0.13414481207728385,
|
|
"num_tokens": 2864937.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.35138201713562,
|
|
"epoch": 0.1309867282169648,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999972822703301,
|
|
"loss": 7.1043,
|
|
"mean_token_accuracy": 0.14946642518043518,
|
|
"num_tokens": 2877791.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.182547760009766,
|
|
"epoch": 0.13156376226197344,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999970756712567,
|
|
"loss": 7.1067,
|
|
"mean_token_accuracy": 0.13508472070097924,
|
|
"num_tokens": 2889897.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.388927268981933,
|
|
"epoch": 0.1321407963069821,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999968615045183,
|
|
"loss": 7.1212,
|
|
"mean_token_accuracy": 0.13854536414146423,
|
|
"num_tokens": 2902806.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.248739910125733,
|
|
"epoch": 0.13271783035199078,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999966397701222,
|
|
"loss": 7.0086,
|
|
"mean_token_accuracy": 0.14631882458925247,
|
|
"num_tokens": 2915703.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.229858493804931,
|
|
"epoch": 0.13329486439699942,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999964104680759,
|
|
"loss": 7.2181,
|
|
"mean_token_accuracy": 0.12988507375121117,
|
|
"num_tokens": 2928171.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.360022401809692,
|
|
"epoch": 0.13387189844200809,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999961735983871,
|
|
"loss": 7.0487,
|
|
"mean_token_accuracy": 0.1509324714541435,
|
|
"num_tokens": 2939909.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.3091637134552006,
|
|
"epoch": 0.13444893248701673,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999959291610639,
|
|
"loss": 7.1827,
|
|
"mean_token_accuracy": 0.13319118991494178,
|
|
"num_tokens": 2951510.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.270810317993164,
|
|
"epoch": 0.1350259665320254,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999956771561143,
|
|
"loss": 7.1046,
|
|
"mean_token_accuracy": 0.1315624199807644,
|
|
"num_tokens": 2963326.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.282600927352905,
|
|
"epoch": 0.13560300057703403,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999954175835469,
|
|
"loss": 7.1236,
|
|
"mean_token_accuracy": 0.14552151560783386,
|
|
"num_tokens": 2976226.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.304236793518067,
|
|
"epoch": 0.1361800346220427,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999951504433703,
|
|
"loss": 7.1306,
|
|
"mean_token_accuracy": 0.1356511816382408,
|
|
"num_tokens": 2988180.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.281073331832886,
|
|
"epoch": 0.13675706866705137,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999948757355935,
|
|
"loss": 7.1185,
|
|
"mean_token_accuracy": 0.13962753042578696,
|
|
"num_tokens": 3000215.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.306526613235474,
|
|
"epoch": 0.13733410271206,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499994593460226,
|
|
"loss": 7.1111,
|
|
"mean_token_accuracy": 0.13763693794608117,
|
|
"num_tokens": 3012516.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.259176111221313,
|
|
"epoch": 0.13791113675706868,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999943036172771,
|
|
"loss": 7.1082,
|
|
"mean_token_accuracy": 0.13961452320218087,
|
|
"num_tokens": 3024786.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.322293615341186,
|
|
"epoch": 0.13848817080207732,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999940062067565,
|
|
"loss": 7.04,
|
|
"mean_token_accuracy": 0.1440444752573967,
|
|
"num_tokens": 3037179.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.134593200683594,
|
|
"epoch": 0.13906520484708598,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999937012286742,
|
|
"loss": 7.1333,
|
|
"mean_token_accuracy": 0.14015561193227768,
|
|
"num_tokens": 3049443.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.305765962600708,
|
|
"epoch": 0.13964223889209462,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999933886830405,
|
|
"loss": 7.0521,
|
|
"mean_token_accuracy": 0.133638371527195,
|
|
"num_tokens": 3061857.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.215990972518921,
|
|
"epoch": 0.1402192729371033,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499993068569866,
|
|
"loss": 7.0849,
|
|
"mean_token_accuracy": 0.1435427337884903,
|
|
"num_tokens": 3075185.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.301103687286377,
|
|
"epoch": 0.14079630698211196,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999927408891614,
|
|
"loss": 7.0919,
|
|
"mean_token_accuracy": 0.14063736498355867,
|
|
"num_tokens": 3087645.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.285601663589477,
|
|
"epoch": 0.1413733410271206,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999924056409378,
|
|
"loss": 7.0908,
|
|
"mean_token_accuracy": 0.14075700491666793,
|
|
"num_tokens": 3101185.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.270492601394653,
|
|
"epoch": 0.14195037507212926,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999920628252063,
|
|
"loss": 7.0766,
|
|
"mean_token_accuracy": 0.13953982219099997,
|
|
"num_tokens": 3113694.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.237199211120606,
|
|
"epoch": 0.1425274091171379,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999917124419785,
|
|
"loss": 7.1188,
|
|
"mean_token_accuracy": 0.13823226392269133,
|
|
"num_tokens": 3128225.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.233181381225586,
|
|
"epoch": 0.14310444316214657,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999913544912664,
|
|
"loss": 7.0533,
|
|
"mean_token_accuracy": 0.1442795380949974,
|
|
"num_tokens": 3140118.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.241433238983154,
|
|
"epoch": 0.1436814772071552,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999909889730817,
|
|
"loss": 7.1085,
|
|
"mean_token_accuracy": 0.13870764151215553,
|
|
"num_tokens": 3153479.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.260871505737304,
|
|
"epoch": 0.14425851125216388,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999906158874368,
|
|
"loss": 7.1168,
|
|
"mean_token_accuracy": 0.14061163738369942,
|
|
"num_tokens": 3167062.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.2724611282348635,
|
|
"epoch": 0.14483554529717255,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999902352343444,
|
|
"loss": 7.0729,
|
|
"mean_token_accuracy": 0.1381714127957821,
|
|
"num_tokens": 3179061.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.174509811401367,
|
|
"epoch": 0.1454125793421812,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999898470138171,
|
|
"loss": 7.0213,
|
|
"mean_token_accuracy": 0.13980793803930283,
|
|
"num_tokens": 3191333.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.224514389038086,
|
|
"epoch": 0.14598961338718985,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999894512258681,
|
|
"loss": 7.1164,
|
|
"mean_token_accuracy": 0.13482679277658463,
|
|
"num_tokens": 3204487.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.220690965652466,
|
|
"epoch": 0.1465666474321985,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999890478705107,
|
|
"loss": 7.0728,
|
|
"mean_token_accuracy": 0.1409827023744583,
|
|
"num_tokens": 3216733.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.218664693832397,
|
|
"epoch": 0.14714368147720716,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999886369477585,
|
|
"loss": 7.0233,
|
|
"mean_token_accuracy": 0.14548835158348083,
|
|
"num_tokens": 3229605.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.249156379699707,
|
|
"epoch": 0.1477207155222158,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999882184576251,
|
|
"loss": 7.0641,
|
|
"mean_token_accuracy": 0.14037289768457412,
|
|
"num_tokens": 3241023.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.183506107330322,
|
|
"epoch": 0.14829774956722447,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999877924001248,
|
|
"loss": 7.0454,
|
|
"mean_token_accuracy": 0.1420667700469494,
|
|
"num_tokens": 3252435.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.202338171005249,
|
|
"epoch": 0.1488747836122331,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999873587752718,
|
|
"loss": 7.0315,
|
|
"mean_token_accuracy": 0.14606617093086244,
|
|
"num_tokens": 3265663.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.2627809047698975,
|
|
"epoch": 0.14945181765724178,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999869175830808,
|
|
"loss": 7.0998,
|
|
"mean_token_accuracy": 0.13558180630207062,
|
|
"num_tokens": 3278309.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.196434354782104,
|
|
"epoch": 0.15002885170225044,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999864688235666,
|
|
"loss": 7.0881,
|
|
"mean_token_accuracy": 0.13663394004106522,
|
|
"num_tokens": 3290899.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.256631898880005,
|
|
"epoch": 0.15060588574725908,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999860124967442,
|
|
"loss": 7.0591,
|
|
"mean_token_accuracy": 0.1400838539004326,
|
|
"num_tokens": 3304383.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.142842245101929,
|
|
"epoch": 0.15118291979226775,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999855486026291,
|
|
"loss": 7.0381,
|
|
"mean_token_accuracy": 0.14005750343203544,
|
|
"num_tokens": 3316310.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.253703260421753,
|
|
"epoch": 0.1517599538372764,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999850771412369,
|
|
"loss": 7.1357,
|
|
"mean_token_accuracy": 0.13773472383618354,
|
|
"num_tokens": 3330018.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.299247360229492,
|
|
"epoch": 0.15233698788228506,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999845981125832,
|
|
"loss": 7.1805,
|
|
"mean_token_accuracy": 0.13796070963144302,
|
|
"num_tokens": 3343134.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.159939193725586,
|
|
"epoch": 0.1529140219272937,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999841115166844,
|
|
"loss": 6.9761,
|
|
"mean_token_accuracy": 0.14545321986079215,
|
|
"num_tokens": 3356262.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.279706287384033,
|
|
"epoch": 0.15349105597230236,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999836173535568,
|
|
"loss": 7.1249,
|
|
"mean_token_accuracy": 0.13199433758854867,
|
|
"num_tokens": 3369672.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.183068513870239,
|
|
"epoch": 0.15406809001731103,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999831156232169,
|
|
"loss": 7.0391,
|
|
"mean_token_accuracy": 0.14253250360488892,
|
|
"num_tokens": 3381677.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.151807451248169,
|
|
"epoch": 0.15464512406231967,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999826063256818,
|
|
"loss": 6.9944,
|
|
"mean_token_accuracy": 0.14133523479104043,
|
|
"num_tokens": 3394662.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.135809326171875,
|
|
"epoch": 0.15522215810732834,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999820894609683,
|
|
"loss": 7.0019,
|
|
"mean_token_accuracy": 0.14013058245182036,
|
|
"num_tokens": 3407286.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.337306499481201,
|
|
"epoch": 0.15579919215233698,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999815650290941,
|
|
"loss": 7.0935,
|
|
"mean_token_accuracy": 0.13155431523919106,
|
|
"num_tokens": 3419478.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.090397119522095,
|
|
"epoch": 0.15637622619734565,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999810330300766,
|
|
"loss": 7.0581,
|
|
"mean_token_accuracy": 0.1393677696585655,
|
|
"num_tokens": 3433188.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.227596616744995,
|
|
"epoch": 0.1569532602423543,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499980493463934,
|
|
"loss": 6.9917,
|
|
"mean_token_accuracy": 0.13574201092123986,
|
|
"num_tokens": 3445806.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.163070344924927,
|
|
"epoch": 0.15753029428736295,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999799463306841,
|
|
"loss": 7.0483,
|
|
"mean_token_accuracy": 0.1425718478858471,
|
|
"num_tokens": 3458931.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.1892472267150875,
|
|
"epoch": 0.15810732833237162,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999793916303455,
|
|
"loss": 7.0889,
|
|
"mean_token_accuracy": 0.1362600401043892,
|
|
"num_tokens": 3471338.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.238631296157837,
|
|
"epoch": 0.15868436237738026,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999788293629368,
|
|
"loss": 7.1303,
|
|
"mean_token_accuracy": 0.1389173984527588,
|
|
"num_tokens": 3484865.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.231470727920533,
|
|
"epoch": 0.15926139642238893,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499978259528477,
|
|
"loss": 6.9649,
|
|
"mean_token_accuracy": 0.14690266847610473,
|
|
"num_tokens": 3496676.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.058669900894165,
|
|
"epoch": 0.15983843046739757,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999776821269852,
|
|
"loss": 6.9509,
|
|
"mean_token_accuracy": 0.14693509563803672,
|
|
"num_tokens": 3508748.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.182062768936158,
|
|
"epoch": 0.16041546451240624,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999770971584807,
|
|
"loss": 7.0749,
|
|
"mean_token_accuracy": 0.1334662154316902,
|
|
"num_tokens": 3521490.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.199066686630249,
|
|
"epoch": 0.16099249855741488,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999765046229834,
|
|
"loss": 7.0484,
|
|
"mean_token_accuracy": 0.1401499927043915,
|
|
"num_tokens": 3534092.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.191224384307861,
|
|
"epoch": 0.16156953260242354,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499975904520513,
|
|
"loss": 7.0213,
|
|
"mean_token_accuracy": 0.1379491239786148,
|
|
"num_tokens": 3546583.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.084802722930908,
|
|
"epoch": 0.1621465666474322,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00049997529685109,
|
|
"loss": 7.002,
|
|
"mean_token_accuracy": 0.13953247293829918,
|
|
"num_tokens": 3559409.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.161634111404419,
|
|
"epoch": 0.16272360069244085,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999746816147344,
|
|
"loss": 7.0043,
|
|
"mean_token_accuracy": 0.14320720732212067,
|
|
"num_tokens": 3572362.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.124744558334351,
|
|
"epoch": 0.16330063473744952,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999740588114673,
|
|
"loss": 6.9779,
|
|
"mean_token_accuracy": 0.14698471277952194,
|
|
"num_tokens": 3585505.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.198022842407227,
|
|
"epoch": 0.16387766878245816,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999734284413095,
|
|
"loss": 7.0287,
|
|
"mean_token_accuracy": 0.14301127195358276,
|
|
"num_tokens": 3597322.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.142577838897705,
|
|
"epoch": 0.16445470282746683,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499972790504282,
|
|
"loss": 7.0051,
|
|
"mean_token_accuracy": 0.1411785215139389,
|
|
"num_tokens": 3609941.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.169891500473023,
|
|
"epoch": 0.16503173687247547,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999721450004067,
|
|
"loss": 7.0594,
|
|
"mean_token_accuracy": 0.1376806043088436,
|
|
"num_tokens": 3621751.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.1877641677856445,
|
|
"epoch": 0.16560877091748413,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999714919297049,
|
|
"loss": 6.9994,
|
|
"mean_token_accuracy": 0.1362007051706314,
|
|
"num_tokens": 3633070.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.156223154067993,
|
|
"epoch": 0.1661858049624928,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999708312921987,
|
|
"loss": 6.991,
|
|
"mean_token_accuracy": 0.14234942495822905,
|
|
"num_tokens": 3646730.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.137038898468018,
|
|
"epoch": 0.16676283900750144,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999701630879103,
|
|
"loss": 7.024,
|
|
"mean_token_accuracy": 0.13512019515037538,
|
|
"num_tokens": 3659976.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.2560724258422855,
|
|
"epoch": 0.1673398730525101,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999694873168623,
|
|
"loss": 6.9583,
|
|
"mean_token_accuracy": 0.13890018165111542,
|
|
"num_tokens": 3672607.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.892187547683716,
|
|
"epoch": 0.16791690709751875,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999688039790773,
|
|
"loss": 6.9249,
|
|
"mean_token_accuracy": 0.14720971807837485,
|
|
"num_tokens": 3686338.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.185595369338989,
|
|
"epoch": 0.16849394114252741,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999681130745784,
|
|
"loss": 6.919,
|
|
"mean_token_accuracy": 0.14689514487981797,
|
|
"num_tokens": 3698986.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.067193078994751,
|
|
"epoch": 0.16907097518753605,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999674146033888,
|
|
"loss": 6.9691,
|
|
"mean_token_accuracy": 0.1407572127878666,
|
|
"num_tokens": 3712453.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.098576354980469,
|
|
"epoch": 0.16964800923254472,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999667085655318,
|
|
"loss": 6.9661,
|
|
"mean_token_accuracy": 0.14339267313480378,
|
|
"num_tokens": 3724769.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.177932548522949,
|
|
"epoch": 0.1702250432775534,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999659949610313,
|
|
"loss": 7.0199,
|
|
"mean_token_accuracy": 0.13096101582050323,
|
|
"num_tokens": 3738052.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.143703556060791,
|
|
"epoch": 0.17080207732256203,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999652737899114,
|
|
"loss": 6.9883,
|
|
"mean_token_accuracy": 0.1414633348584175,
|
|
"num_tokens": 3751279.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.204730272293091,
|
|
"epoch": 0.1713791113675707,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999645450521963,
|
|
"loss": 7.0358,
|
|
"mean_token_accuracy": 0.13535647615790367,
|
|
"num_tokens": 3764688.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.067404890060425,
|
|
"epoch": 0.17195614541257934,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999638087479104,
|
|
"loss": 7.0258,
|
|
"mean_token_accuracy": 0.13848631605505943,
|
|
"num_tokens": 3776892.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.166511583328247,
|
|
"epoch": 0.172533179457588,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999630648770786,
|
|
"loss": 6.9324,
|
|
"mean_token_accuracy": 0.14192868992686272,
|
|
"num_tokens": 3789287.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.094117498397827,
|
|
"epoch": 0.17311021350259664,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999623134397257,
|
|
"loss": 6.9241,
|
|
"mean_token_accuracy": 0.13871007338166236,
|
|
"num_tokens": 3801467.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.110012578964233,
|
|
"epoch": 0.1736872475476053,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999615544358774,
|
|
"loss": 6.9988,
|
|
"mean_token_accuracy": 0.14102682918310167,
|
|
"num_tokens": 3814641.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.171355581283569,
|
|
"epoch": 0.17426428159261395,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999607878655587,
|
|
"loss": 7.058,
|
|
"mean_token_accuracy": 0.1313117817044258,
|
|
"num_tokens": 3827187.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.093271684646607,
|
|
"epoch": 0.17484131563762262,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999600137287958,
|
|
"loss": 6.8747,
|
|
"mean_token_accuracy": 0.15039864480495452,
|
|
"num_tokens": 3839832.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.007730913162232,
|
|
"epoch": 0.17541834968263129,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999592320256146,
|
|
"loss": 6.882,
|
|
"mean_token_accuracy": 0.14504249542951583,
|
|
"num_tokens": 3852026.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.090141820907593,
|
|
"epoch": 0.17599538372763993,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999584427560412,
|
|
"loss": 6.9337,
|
|
"mean_token_accuracy": 0.14259505569934844,
|
|
"num_tokens": 3864481.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.11194920539856,
|
|
"epoch": 0.1765724177726486,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999576459201024,
|
|
"loss": 6.926,
|
|
"mean_token_accuracy": 0.14007529392838478,
|
|
"num_tokens": 3876896.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.059630441665649,
|
|
"epoch": 0.17714945181765723,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499956841517825,
|
|
"loss": 6.8702,
|
|
"mean_token_accuracy": 0.14155263453722,
|
|
"num_tokens": 3890230.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.151209115982056,
|
|
"epoch": 0.1777264858626659,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499956029549236,
|
|
"loss": 6.9884,
|
|
"mean_token_accuracy": 0.1379861555993557,
|
|
"num_tokens": 3903138.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.033334732055664,
|
|
"epoch": 0.17830351990767454,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999552100143625,
|
|
"loss": 6.9137,
|
|
"mean_token_accuracy": 0.14293416365981101,
|
|
"num_tokens": 3915709.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.103172302246094,
|
|
"epoch": 0.1788805539526832,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999543829132324,
|
|
"loss": 6.9886,
|
|
"mean_token_accuracy": 0.14267231971025468,
|
|
"num_tokens": 3929265.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.093789052963257,
|
|
"epoch": 0.17945758799769188,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999535482458734,
|
|
"loss": 6.9683,
|
|
"mean_token_accuracy": 0.14312490001320838,
|
|
"num_tokens": 3940416.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.07169542312622,
|
|
"epoch": 0.18003462204270052,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999527060123135,
|
|
"loss": 6.9805,
|
|
"mean_token_accuracy": 0.1391856700181961,
|
|
"num_tokens": 3952999.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.027859497070312,
|
|
"epoch": 0.18061165608770918,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999518562125811,
|
|
"loss": 7.0033,
|
|
"mean_token_accuracy": 0.14257199838757514,
|
|
"num_tokens": 3966852.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.128302907943725,
|
|
"epoch": 0.18118869013271782,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999509988467047,
|
|
"loss": 6.8997,
|
|
"mean_token_accuracy": 0.14498577862977982,
|
|
"num_tokens": 3978242.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.117135620117187,
|
|
"epoch": 0.1817657241777265,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999501339147132,
|
|
"loss": 6.9929,
|
|
"mean_token_accuracy": 0.13448395878076552,
|
|
"num_tokens": 3993122.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.120546340942383,
|
|
"epoch": 0.18234275822273513,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999492614166357,
|
|
"loss": 6.9519,
|
|
"mean_token_accuracy": 0.13845855444669725,
|
|
"num_tokens": 4005230.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.002993774414063,
|
|
"epoch": 0.1829197922677438,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999483813525014,
|
|
"loss": 6.8912,
|
|
"mean_token_accuracy": 0.1465035580098629,
|
|
"num_tokens": 4017413.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.117990589141845,
|
|
"epoch": 0.18349682631275246,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999474937223403,
|
|
"loss": 6.913,
|
|
"mean_token_accuracy": 0.13722215369343757,
|
|
"num_tokens": 4029679.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.0321924686431885,
|
|
"epoch": 0.1840738603577611,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999465985261818,
|
|
"loss": 6.8641,
|
|
"mean_token_accuracy": 0.14145687371492385,
|
|
"num_tokens": 4041857.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.059554100036621,
|
|
"epoch": 0.18465089440276977,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999456957640562,
|
|
"loss": 6.9627,
|
|
"mean_token_accuracy": 0.1417013004422188,
|
|
"num_tokens": 4054743.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.978120374679565,
|
|
"epoch": 0.1852279284477784,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999447854359939,
|
|
"loss": 6.8829,
|
|
"mean_token_accuracy": 0.1442536674439907,
|
|
"num_tokens": 4067554.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.109914064407349,
|
|
"epoch": 0.18580496249278708,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999438675420255,
|
|
"loss": 6.8864,
|
|
"mean_token_accuracy": 0.14278573244810105,
|
|
"num_tokens": 4079912.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.044018888473511,
|
|
"epoch": 0.18638199653779572,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999429420821818,
|
|
"loss": 6.9875,
|
|
"mean_token_accuracy": 0.13912659734487534,
|
|
"num_tokens": 4093217.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.054386758804322,
|
|
"epoch": 0.1869590305828044,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499942009056494,
|
|
"loss": 6.9365,
|
|
"mean_token_accuracy": 0.13861448243260382,
|
|
"num_tokens": 4104328.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.088769435882568,
|
|
"epoch": 0.18753606462781305,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999410684649935,
|
|
"loss": 6.903,
|
|
"mean_token_accuracy": 0.13839107751846313,
|
|
"num_tokens": 4116711.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.108532571792603,
|
|
"epoch": 0.1881130986728217,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999401203077119,
|
|
"loss": 6.916,
|
|
"mean_token_accuracy": 0.14068023785948752,
|
|
"num_tokens": 4129066.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.976222705841065,
|
|
"epoch": 0.18869013271783036,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499939164584681,
|
|
"loss": 6.8407,
|
|
"mean_token_accuracy": 0.14638919979333878,
|
|
"num_tokens": 4141312.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.951454305648804,
|
|
"epoch": 0.189267166762839,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999382012959331,
|
|
"loss": 6.891,
|
|
"mean_token_accuracy": 0.14239912778139113,
|
|
"num_tokens": 4154687.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.107205200195312,
|
|
"epoch": 0.18984420080784767,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999372304415005,
|
|
"loss": 6.9926,
|
|
"mean_token_accuracy": 0.1338139146566391,
|
|
"num_tokens": 4168401.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.093311500549317,
|
|
"epoch": 0.1904212348528563,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999362520214159,
|
|
"loss": 6.9056,
|
|
"mean_token_accuracy": 0.1434105969965458,
|
|
"num_tokens": 4180707.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.006139135360717,
|
|
"epoch": 0.19099826889786498,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999352660357122,
|
|
"loss": 6.8472,
|
|
"mean_token_accuracy": 0.14567850530147552,
|
|
"num_tokens": 4192939.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.006642055511475,
|
|
"epoch": 0.19157530294287364,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999342724844226,
|
|
"loss": 6.8907,
|
|
"mean_token_accuracy": 0.1400732360780239,
|
|
"num_tokens": 4206277.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.036981534957886,
|
|
"epoch": 0.19215233698788228,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999332713675804,
|
|
"loss": 6.9061,
|
|
"mean_token_accuracy": 0.14375606924295425,
|
|
"num_tokens": 4218672.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.058644390106201,
|
|
"epoch": 0.19272937103289095,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999322626852193,
|
|
"loss": 6.8487,
|
|
"mean_token_accuracy": 0.15019180476665497,
|
|
"num_tokens": 4229002.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.931442832946777,
|
|
"epoch": 0.1933064050778996,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999312464373734,
|
|
"loss": 6.7568,
|
|
"mean_token_accuracy": 0.15428706631064415,
|
|
"num_tokens": 4241986.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.937554502487183,
|
|
"epoch": 0.19388343912290826,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999302226240767,
|
|
"loss": 6.8767,
|
|
"mean_token_accuracy": 0.14542328268289567,
|
|
"num_tokens": 4254670.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.057171106338501,
|
|
"epoch": 0.1944604731679169,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999291912453637,
|
|
"loss": 6.9243,
|
|
"mean_token_accuracy": 0.14324737936258317,
|
|
"num_tokens": 4267561.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.091326284408569,
|
|
"epoch": 0.19503750721292556,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999281523012691,
|
|
"loss": 6.8723,
|
|
"mean_token_accuracy": 0.14641524106264114,
|
|
"num_tokens": 4280145.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.949259901046753,
|
|
"epoch": 0.1956145412579342,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999271057918278,
|
|
"loss": 6.8951,
|
|
"mean_token_accuracy": 0.1458272233605385,
|
|
"num_tokens": 4294089.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.969711494445801,
|
|
"epoch": 0.19619157530294287,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999260517170751,
|
|
"loss": 6.8523,
|
|
"mean_token_accuracy": 0.14484949558973312,
|
|
"num_tokens": 4305926.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.015812873840332,
|
|
"epoch": 0.19676860934795154,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999249900770463,
|
|
"loss": 6.8777,
|
|
"mean_token_accuracy": 0.14453437477350234,
|
|
"num_tokens": 4319319.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.054222202301025,
|
|
"epoch": 0.19734564339296018,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999239208717772,
|
|
"loss": 6.88,
|
|
"mean_token_accuracy": 0.1493258535861969,
|
|
"num_tokens": 4331650.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.912113094329834,
|
|
"epoch": 0.19792267743796885,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999228441013037,
|
|
"loss": 6.8579,
|
|
"mean_token_accuracy": 0.14917318373918534,
|
|
"num_tokens": 4344289.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.053227233886719,
|
|
"epoch": 0.1984997114829775,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499921759765662,
|
|
"loss": 6.8428,
|
|
"mean_token_accuracy": 0.1453030899167061,
|
|
"num_tokens": 4357316.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.902173471450806,
|
|
"epoch": 0.19907674552798615,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999206678648888,
|
|
"loss": 6.8593,
|
|
"mean_token_accuracy": 0.14832349121570587,
|
|
"num_tokens": 4369383.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.987811851501465,
|
|
"epoch": 0.1996537795729948,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999195683990206,
|
|
"loss": 6.8523,
|
|
"mean_token_accuracy": 0.14121579453349115,
|
|
"num_tokens": 4383509.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.036195564270019,
|
|
"epoch": 0.20023081361800346,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999184613680945,
|
|
"loss": 6.8422,
|
|
"mean_token_accuracy": 0.14607394635677337,
|
|
"num_tokens": 4395105.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.9437949657440186,
|
|
"epoch": 0.20080784766301213,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999173467721476,
|
|
"loss": 6.8231,
|
|
"mean_token_accuracy": 0.1548911601305008,
|
|
"num_tokens": 4407473.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.070507526397705,
|
|
"epoch": 0.20138488170802077,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999162246112175,
|
|
"loss": 6.9122,
|
|
"mean_token_accuracy": 0.13833602294325828,
|
|
"num_tokens": 4420186.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.968269634246826,
|
|
"epoch": 0.20196191575302944,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999150948853419,
|
|
"loss": 6.821,
|
|
"mean_token_accuracy": 0.1459064930677414,
|
|
"num_tokens": 4432944.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.0235504627227785,
|
|
"epoch": 0.20253894979803808,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999139575945587,
|
|
"loss": 6.8803,
|
|
"mean_token_accuracy": 0.14378070682287217,
|
|
"num_tokens": 4445784.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.927468872070312,
|
|
"epoch": 0.20311598384304674,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999128127389065,
|
|
"loss": 6.7843,
|
|
"mean_token_accuracy": 0.15202904790639876,
|
|
"num_tokens": 4458338.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.9563414573669435,
|
|
"epoch": 0.20369301788805538,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999116603184233,
|
|
"loss": 6.7983,
|
|
"mean_token_accuracy": 0.13958832919597625,
|
|
"num_tokens": 4471058.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.899150657653808,
|
|
"epoch": 0.20427005193306405,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004999105003331482,
|
|
"loss": 6.8266,
|
|
"mean_token_accuracy": 0.14727174118161201,
|
|
"num_tokens": 4485561.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.9349593162536625,
|
|
"epoch": 0.20484708597807272,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999093327831202,
|
|
"loss": 6.8535,
|
|
"mean_token_accuracy": 0.14275807067751883,
|
|
"num_tokens": 4497865.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.864494657516479,
|
|
"epoch": 0.20542412002308136,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999081576683784,
|
|
"loss": 6.7372,
|
|
"mean_token_accuracy": 0.15288822427392007,
|
|
"num_tokens": 4510291.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.981197881698608,
|
|
"epoch": 0.20600115406809003,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999069749889626,
|
|
"loss": 6.8206,
|
|
"mean_token_accuracy": 0.14839925467967988,
|
|
"num_tokens": 4521855.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.962658452987671,
|
|
"epoch": 0.20657818811309867,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999057847449123,
|
|
"loss": 6.9264,
|
|
"mean_token_accuracy": 0.1439384013414383,
|
|
"num_tokens": 4534123.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.070970106124878,
|
|
"epoch": 0.20715522215810733,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999045869362678,
|
|
"loss": 6.8721,
|
|
"mean_token_accuracy": 0.1396043874323368,
|
|
"num_tokens": 4547298.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.949685668945312,
|
|
"epoch": 0.20773225620311597,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499903381563069,
|
|
"loss": 6.8077,
|
|
"mean_token_accuracy": 0.14740960970520972,
|
|
"num_tokens": 4560945.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.966697263717651,
|
|
"epoch": 0.20830929024812464,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999021686253568,
|
|
"loss": 6.8687,
|
|
"mean_token_accuracy": 0.1465895041823387,
|
|
"num_tokens": 4572696.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.888779878616333,
|
|
"epoch": 0.2088863242931333,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999009481231719,
|
|
"loss": 6.8272,
|
|
"mean_token_accuracy": 0.14835924357175828,
|
|
"num_tokens": 4585670.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.021191167831421,
|
|
"epoch": 0.20946335833814195,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998997200565553,
|
|
"loss": 6.8068,
|
|
"mean_token_accuracy": 0.1528303876519203,
|
|
"num_tokens": 4597694.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.919396781921387,
|
|
"epoch": 0.21004039238315061,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998984844255483,
|
|
"loss": 6.81,
|
|
"mean_token_accuracy": 0.15265992432832717,
|
|
"num_tokens": 4609924.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.99350414276123,
|
|
"epoch": 0.21061742642815925,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998972412301925,
|
|
"loss": 6.8249,
|
|
"mean_token_accuracy": 0.1444974884390831,
|
|
"num_tokens": 4621668.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.94732346534729,
|
|
"epoch": 0.21119446047316792,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004998959904705297,
|
|
"loss": 6.881,
|
|
"mean_token_accuracy": 0.14270134419202804,
|
|
"num_tokens": 4635970.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.050157785415649,
|
|
"epoch": 0.21177149451817656,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998947321466021,
|
|
"loss": 6.8651,
|
|
"mean_token_accuracy": 0.14370742663741112,
|
|
"num_tokens": 4649557.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.908232021331787,
|
|
"epoch": 0.21234852856318523,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998934662584518,
|
|
"loss": 6.8489,
|
|
"mean_token_accuracy": 0.1472188040614128,
|
|
"num_tokens": 4662572.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.015526866912841,
|
|
"epoch": 0.2129255626081939,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998921928061214,
|
|
"loss": 6.787,
|
|
"mean_token_accuracy": 0.14296051636338233,
|
|
"num_tokens": 4674783.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.846453762054443,
|
|
"epoch": 0.21350259665320254,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998909117896539,
|
|
"loss": 6.8143,
|
|
"mean_token_accuracy": 0.15064377710223198,
|
|
"num_tokens": 4687543.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.0557780265808105,
|
|
"epoch": 0.2140796306982112,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998896232090922,
|
|
"loss": 6.7774,
|
|
"mean_token_accuracy": 0.14568573087453843,
|
|
"num_tokens": 4700225.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.856030988693237,
|
|
"epoch": 0.21465666474321984,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998883270644798,
|
|
"loss": 6.8354,
|
|
"mean_token_accuracy": 0.14540046080946922,
|
|
"num_tokens": 4712950.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.031614017486572,
|
|
"epoch": 0.2152336987882285,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998870233558602,
|
|
"loss": 6.915,
|
|
"mean_token_accuracy": 0.1439936079084873,
|
|
"num_tokens": 4725563.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.960827159881592,
|
|
"epoch": 0.21581073283323715,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998857120832774,
|
|
"loss": 6.8384,
|
|
"mean_token_accuracy": 0.14699823558330535,
|
|
"num_tokens": 4739057.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.924222373962403,
|
|
"epoch": 0.21638776687824582,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004998843932467751,
|
|
"loss": 6.8103,
|
|
"mean_token_accuracy": 0.15074544101953508,
|
|
"num_tokens": 4752782.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.948456811904907,
|
|
"epoch": 0.21696480092325446,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998830668463982,
|
|
"loss": 6.7441,
|
|
"mean_token_accuracy": 0.1475722536444664,
|
|
"num_tokens": 4765740.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.868886423110962,
|
|
"epoch": 0.21754183496826313,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998817328821909,
|
|
"loss": 6.8159,
|
|
"mean_token_accuracy": 0.1473565399646759,
|
|
"num_tokens": 4778711.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.014859580993653,
|
|
"epoch": 0.2181188690132718,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998803913541983,
|
|
"loss": 6.8055,
|
|
"mean_token_accuracy": 0.14383689314126968,
|
|
"num_tokens": 4791402.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.904099798202514,
|
|
"epoch": 0.21869590305828043,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998790422624654,
|
|
"loss": 6.7913,
|
|
"mean_token_accuracy": 0.14016161784529685,
|
|
"num_tokens": 4804256.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.875801038742066,
|
|
"epoch": 0.2192729371032891,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998776856070376,
|
|
"loss": 6.738,
|
|
"mean_token_accuracy": 0.14255951046943666,
|
|
"num_tokens": 4817424.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.946020650863647,
|
|
"epoch": 0.21984997114829774,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004998763213879606,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.14450910985469817,
|
|
"num_tokens": 4829222.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.881495380401612,
|
|
"epoch": 0.2204270051933064,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998749496052803,
|
|
"loss": 6.7586,
|
|
"mean_token_accuracy": 0.15232504308223724,
|
|
"num_tokens": 4844011.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.943768501281738,
|
|
"epoch": 0.22100403923831505,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998735702590426,
|
|
"loss": 6.8173,
|
|
"mean_token_accuracy": 0.14637627452611923,
|
|
"num_tokens": 4857116.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.903482675552368,
|
|
"epoch": 0.22158107328332372,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998721833492942,
|
|
"loss": 6.7527,
|
|
"mean_token_accuracy": 0.15328776836395264,
|
|
"num_tokens": 4867680.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.915145015716552,
|
|
"epoch": 0.22215810732833238,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998707888760816,
|
|
"loss": 6.7966,
|
|
"mean_token_accuracy": 0.1467222422361374,
|
|
"num_tokens": 4880553.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.887819623947143,
|
|
"epoch": 0.22273514137334102,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998693868394516,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.14810495600104331,
|
|
"num_tokens": 4893706.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.863858842849732,
|
|
"epoch": 0.2233121754183497,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998679772394516,
|
|
"loss": 6.8486,
|
|
"mean_token_accuracy": 0.14729523956775664,
|
|
"num_tokens": 4906016.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.896185255050659,
|
|
"epoch": 0.22388920946335833,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004998665600761289,
|
|
"loss": 6.7278,
|
|
"mean_token_accuracy": 0.15100182890892028,
|
|
"num_tokens": 4918628.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.010975885391235,
|
|
"epoch": 0.224466243508367,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499865135349531,
|
|
"loss": 6.8144,
|
|
"mean_token_accuracy": 0.14225947707891465,
|
|
"num_tokens": 4930525.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.8868975162506105,
|
|
"epoch": 0.22504327755337564,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998637030597061,
|
|
"loss": 6.8197,
|
|
"mean_token_accuracy": 0.1457245357334614,
|
|
"num_tokens": 4942510.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.970962142944336,
|
|
"epoch": 0.2256203115983843,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998622632067022,
|
|
"loss": 6.7952,
|
|
"mean_token_accuracy": 0.14592548012733458,
|
|
"num_tokens": 4954865.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.893493223190307,
|
|
"epoch": 0.22619734564339297,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998608157905678,
|
|
"loss": 6.8813,
|
|
"mean_token_accuracy": 0.1398551307618618,
|
|
"num_tokens": 4968078.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.975720071792603,
|
|
"epoch": 0.2267743796884016,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998593608113515,
|
|
"loss": 6.7472,
|
|
"mean_token_accuracy": 0.14719463735818863,
|
|
"num_tokens": 4980273.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.914252281188965,
|
|
"epoch": 0.22735141373341028,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998578982691024,
|
|
"loss": 6.7927,
|
|
"mean_token_accuracy": 0.1422052152454853,
|
|
"num_tokens": 4992372.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.883531761169434,
|
|
"epoch": 0.22792844777841892,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998564281638694,
|
|
"loss": 6.7757,
|
|
"mean_token_accuracy": 0.1407983958721161,
|
|
"num_tokens": 5004766.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.94020791053772,
|
|
"epoch": 0.2285054818234276,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998549504957023,
|
|
"loss": 6.7176,
|
|
"mean_token_accuracy": 0.14406620860099792,
|
|
"num_tokens": 5017007.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.817730140686035,
|
|
"epoch": 0.22908251586843623,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998534652646506,
|
|
"loss": 6.7859,
|
|
"mean_token_accuracy": 0.14582390040159227,
|
|
"num_tokens": 5029506.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.877771329879761,
|
|
"epoch": 0.2296595499134449,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998519724707642,
|
|
"loss": 6.7609,
|
|
"mean_token_accuracy": 0.14823370724916457,
|
|
"num_tokens": 5042209.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.908406686782837,
|
|
"epoch": 0.23023658395845356,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998504721140934,
|
|
"loss": 6.8161,
|
|
"mean_token_accuracy": 0.13886914625763894,
|
|
"num_tokens": 5056026.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.977062129974366,
|
|
"epoch": 0.2308136180034622,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998489641946887,
|
|
"loss": 6.7594,
|
|
"mean_token_accuracy": 0.14582734405994416,
|
|
"num_tokens": 5068194.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.795575380325317,
|
|
"epoch": 0.23139065204847087,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998474487126009,
|
|
"loss": 6.6985,
|
|
"mean_token_accuracy": 0.14483340829610825,
|
|
"num_tokens": 5080468.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.980053567886353,
|
|
"epoch": 0.2319676860934795,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004998459256678806,
|
|
"loss": 6.8987,
|
|
"mean_token_accuracy": 0.13540890365839003,
|
|
"num_tokens": 5093104.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.952063846588135,
|
|
"epoch": 0.23254472013848818,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998443950605796,
|
|
"loss": 6.7604,
|
|
"mean_token_accuracy": 0.14487868547439575,
|
|
"num_tokens": 5105710.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.916586208343506,
|
|
"epoch": 0.23312175418349682,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998428568907488,
|
|
"loss": 6.8412,
|
|
"mean_token_accuracy": 0.141026022285223,
|
|
"num_tokens": 5118946.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.842178583145142,
|
|
"epoch": 0.23369878822850548,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998413111584403,
|
|
"loss": 6.6824,
|
|
"mean_token_accuracy": 0.15238308906555176,
|
|
"num_tokens": 5132567.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.798287200927734,
|
|
"epoch": 0.23427582227351415,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998397578637059,
|
|
"loss": 6.7384,
|
|
"mean_token_accuracy": 0.15025758892297744,
|
|
"num_tokens": 5145669.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.840568113327026,
|
|
"epoch": 0.2348528563185228,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499838197006598,
|
|
"loss": 6.6806,
|
|
"mean_token_accuracy": 0.15366968512535095,
|
|
"num_tokens": 5157753.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.853817701339722,
|
|
"epoch": 0.23542989036353146,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499836628587169,
|
|
"loss": 6.7113,
|
|
"mean_token_accuracy": 0.14877334460616112,
|
|
"num_tokens": 5170167.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.85221381187439,
|
|
"epoch": 0.2360069244085401,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998350526054716,
|
|
"loss": 6.6912,
|
|
"mean_token_accuracy": 0.14868487864732743,
|
|
"num_tokens": 5182143.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.8682215213775635,
|
|
"epoch": 0.23658395845354876,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998334690615591,
|
|
"loss": 6.7324,
|
|
"mean_token_accuracy": 0.1463753066956997,
|
|
"num_tokens": 5195586.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.841140508651733,
|
|
"epoch": 0.2371609924985574,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998318779554844,
|
|
"loss": 6.7221,
|
|
"mean_token_accuracy": 0.15004333406686782,
|
|
"num_tokens": 5207774.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.816382312774659,
|
|
"epoch": 0.23773802654356607,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998302792873012,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.145672906935215,
|
|
"num_tokens": 5219330.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.898803949356079,
|
|
"epoch": 0.23831506058857474,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998286730570631,
|
|
"loss": 6.8011,
|
|
"mean_token_accuracy": 0.1392673708498478,
|
|
"num_tokens": 5233817.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.921881198883057,
|
|
"epoch": 0.23889209463358338,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998270592648245,
|
|
"loss": 6.8029,
|
|
"mean_token_accuracy": 0.1426341101527214,
|
|
"num_tokens": 5246483.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.877314949035645,
|
|
"epoch": 0.23946912867859205,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998254379106394,
|
|
"loss": 6.7872,
|
|
"mean_token_accuracy": 0.14690051525831221,
|
|
"num_tokens": 5258695.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.834933519363403,
|
|
"epoch": 0.2400461627236007,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998238089945622,
|
|
"loss": 6.7364,
|
|
"mean_token_accuracy": 0.14769575297832488,
|
|
"num_tokens": 5271355.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.983479166030884,
|
|
"epoch": 0.24062319676860935,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998221725166479,
|
|
"loss": 6.8541,
|
|
"mean_token_accuracy": 0.1414130374789238,
|
|
"num_tokens": 5284905.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.848435688018799,
|
|
"epoch": 0.241200230813618,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998205284769516,
|
|
"loss": 6.7898,
|
|
"mean_token_accuracy": 0.14240173250436783,
|
|
"num_tokens": 5298266.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.868869304656982,
|
|
"epoch": 0.24177726485862666,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998188768755285,
|
|
"loss": 6.8241,
|
|
"mean_token_accuracy": 0.13813576549291612,
|
|
"num_tokens": 5311148.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.894551563262939,
|
|
"epoch": 0.2423542989036353,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998172177124341,
|
|
"loss": 6.7433,
|
|
"mean_token_accuracy": 0.14466421604156493,
|
|
"num_tokens": 5322638.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.798158168792725,
|
|
"epoch": 0.24293133294864397,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998155509877242,
|
|
"loss": 6.6199,
|
|
"mean_token_accuracy": 0.15917377769947053,
|
|
"num_tokens": 5336116.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.763039493560791,
|
|
"epoch": 0.24350836699365264,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499813876701455,
|
|
"loss": 6.7412,
|
|
"mean_token_accuracy": 0.1486453168094158,
|
|
"num_tokens": 5347561.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.927878141403198,
|
|
"epoch": 0.24408540103866128,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998121948536828,
|
|
"loss": 6.7747,
|
|
"mean_token_accuracy": 0.14461961835622789,
|
|
"num_tokens": 5360055.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.847961521148681,
|
|
"epoch": 0.24466243508366994,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998105054444639,
|
|
"loss": 6.7334,
|
|
"mean_token_accuracy": 0.1498301789164543,
|
|
"num_tokens": 5372722.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.897721290588379,
|
|
"epoch": 0.24523946912867858,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998088084738555,
|
|
"loss": 6.6907,
|
|
"mean_token_accuracy": 0.1467824786901474,
|
|
"num_tokens": 5385586.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.765969133377075,
|
|
"epoch": 0.24581650317368725,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998071039419144,
|
|
"loss": 6.7337,
|
|
"mean_token_accuracy": 0.14697647988796234,
|
|
"num_tokens": 5399266.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.8921960353851315,
|
|
"epoch": 0.2463935372186959,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499805391848698,
|
|
"loss": 6.7285,
|
|
"mean_token_accuracy": 0.14361063987016678,
|
|
"num_tokens": 5412093.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.846024703979492,
|
|
"epoch": 0.24697057126370456,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499803672194264,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.14491766393184663,
|
|
"num_tokens": 5425181.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.797625732421875,
|
|
"epoch": 0.24754760530871323,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998019449786701,
|
|
"loss": 6.6422,
|
|
"mean_token_accuracy": 0.15672230273485183,
|
|
"num_tokens": 5437392.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.836762523651123,
|
|
"epoch": 0.24812463935372187,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998002102019744,
|
|
"loss": 6.716,
|
|
"mean_token_accuracy": 0.15314831882715224,
|
|
"num_tokens": 5449455.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.800679159164429,
|
|
"epoch": 0.24870167339873053,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004997984678642354,
|
|
"loss": 6.7343,
|
|
"mean_token_accuracy": 0.14900478795170785,
|
|
"num_tokens": 5463095.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.874364376068115,
|
|
"epoch": 0.24927870744373917,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997967179655115,
|
|
"loss": 6.687,
|
|
"mean_token_accuracy": 0.1538333460688591,
|
|
"num_tokens": 5474440.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.821845054626465,
|
|
"epoch": 0.24985574148874784,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997949605058617,
|
|
"loss": 6.688,
|
|
"mean_token_accuracy": 0.15788259357213974,
|
|
"num_tokens": 5487365.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.809021139144898,
|
|
"epoch": 0.2504327755337565,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004997931954853451,
|
|
"loss": 6.7504,
|
|
"mean_token_accuracy": 0.14503707811236383,
|
|
"num_tokens": 5502356.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.827416038513183,
|
|
"epoch": 0.2510098095787651,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499791422904021,
|
|
"loss": 6.7697,
|
|
"mean_token_accuracy": 0.14718132317066193,
|
|
"num_tokens": 5514504.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.879432010650635,
|
|
"epoch": 0.2515868436237738,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997896427619491,
|
|
"loss": 6.787,
|
|
"mean_token_accuracy": 0.14120125472545625,
|
|
"num_tokens": 5526415.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.782674407958984,
|
|
"epoch": 0.25216387766878245,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997878550591892,
|
|
"loss": 6.6442,
|
|
"mean_token_accuracy": 0.1523044466972351,
|
|
"num_tokens": 5538484.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.856536865234375,
|
|
"epoch": 0.2527409117137911,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997860597958013,
|
|
"loss": 6.7129,
|
|
"mean_token_accuracy": 0.15341712385416031,
|
|
"num_tokens": 5551315.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.747131633758545,
|
|
"epoch": 0.2533179457587998,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997842569718461,
|
|
"loss": 6.6025,
|
|
"mean_token_accuracy": 0.1544630780816078,
|
|
"num_tokens": 5564179.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.77038607597351,
|
|
"epoch": 0.25389497980380843,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499782446587384,
|
|
"loss": 6.735,
|
|
"mean_token_accuracy": 0.14310188591480255,
|
|
"num_tokens": 5577060.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.7083740234375,
|
|
"epoch": 0.25447201384881707,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499780628642476,
|
|
"loss": 6.548,
|
|
"mean_token_accuracy": 0.16547798812389375,
|
|
"num_tokens": 5589170.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.812865543365478,
|
|
"epoch": 0.2550490478938257,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997788031371834,
|
|
"loss": 6.7259,
|
|
"mean_token_accuracy": 0.14614113718271254,
|
|
"num_tokens": 5601747.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.895756387710572,
|
|
"epoch": 0.2556260819388344,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997769700715672,
|
|
"loss": 6.7757,
|
|
"mean_token_accuracy": 0.1394893616437912,
|
|
"num_tokens": 5614308.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.80255651473999,
|
|
"epoch": 0.25620311598384304,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997751294456892,
|
|
"loss": 6.7322,
|
|
"mean_token_accuracy": 0.13944590389728545,
|
|
"num_tokens": 5626351.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.84980354309082,
|
|
"epoch": 0.2567801500288517,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997732812596114,
|
|
"loss": 6.7099,
|
|
"mean_token_accuracy": 0.15208475142717362,
|
|
"num_tokens": 5638339.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.850376224517822,
|
|
"epoch": 0.2573571840738604,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997714255133961,
|
|
"loss": 6.7641,
|
|
"mean_token_accuracy": 0.14269857704639435,
|
|
"num_tokens": 5651210.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.788392782211304,
|
|
"epoch": 0.257934218118869,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997695622071054,
|
|
"loss": 6.7186,
|
|
"mean_token_accuracy": 0.14826106950640677,
|
|
"num_tokens": 5664150.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.822963619232178,
|
|
"epoch": 0.25851125216387766,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997676913408021,
|
|
"loss": 6.6615,
|
|
"mean_token_accuracy": 0.15033092349767685,
|
|
"num_tokens": 5676009.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.927838134765625,
|
|
"epoch": 0.2590882862088863,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997658129145493,
|
|
"loss": 6.8377,
|
|
"mean_token_accuracy": 0.1423884242773056,
|
|
"num_tokens": 5688557.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.772985315322876,
|
|
"epoch": 0.259665320253895,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004997639269284099,
|
|
"loss": 6.7958,
|
|
"mean_token_accuracy": 0.14698884561657904,
|
|
"num_tokens": 5702032.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.828845500946045,
|
|
"epoch": 0.26024235429890363,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997620333824476,
|
|
"loss": 6.6183,
|
|
"mean_token_accuracy": 0.15371278077363967,
|
|
"num_tokens": 5714623.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.7304175853729244,
|
|
"epoch": 0.2608193883439123,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997601322767258,
|
|
"loss": 6.6328,
|
|
"mean_token_accuracy": 0.15081430226564407,
|
|
"num_tokens": 5727415.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.825870084762573,
|
|
"epoch": 0.26139642238892097,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997582236113087,
|
|
"loss": 6.6852,
|
|
"mean_token_accuracy": 0.14831779673695564,
|
|
"num_tokens": 5740129.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.793635606765747,
|
|
"epoch": 0.2619734564339296,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997563073862603,
|
|
"loss": 6.6556,
|
|
"mean_token_accuracy": 0.1551389992237091,
|
|
"num_tokens": 5752469.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.750844240188599,
|
|
"epoch": 0.26255049047893825,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997543836016453,
|
|
"loss": 6.7453,
|
|
"mean_token_accuracy": 0.1527159981429577,
|
|
"num_tokens": 5765408.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.8902946472167965,
|
|
"epoch": 0.2631275245239469,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997524522575281,
|
|
"loss": 6.6628,
|
|
"mean_token_accuracy": 0.14618581384420395,
|
|
"num_tokens": 5777450.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.762203741073608,
|
|
"epoch": 0.2637045585689556,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004997505133539738,
|
|
"loss": 6.737,
|
|
"mean_token_accuracy": 0.1433141678571701,
|
|
"num_tokens": 5790435.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.87997465133667,
|
|
"epoch": 0.2642815926139642,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997485668910476,
|
|
"loss": 6.7089,
|
|
"mean_token_accuracy": 0.14799562245607376,
|
|
"num_tokens": 5803517.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.723853969573975,
|
|
"epoch": 0.26485862665897286,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997466128688151,
|
|
"loss": 6.6455,
|
|
"mean_token_accuracy": 0.15912182182073592,
|
|
"num_tokens": 5815802.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.725922870635986,
|
|
"epoch": 0.26543566070398156,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499744651287342,
|
|
"loss": 6.6842,
|
|
"mean_token_accuracy": 0.1475355327129364,
|
|
"num_tokens": 5827807.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.819564151763916,
|
|
"epoch": 0.2660126947489902,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499742682146694,
|
|
"loss": 6.7051,
|
|
"mean_token_accuracy": 0.1480211853981018,
|
|
"num_tokens": 5840759.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.844948768615723,
|
|
"epoch": 0.26658972879399884,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004997407054469377,
|
|
"loss": 6.7258,
|
|
"mean_token_accuracy": 0.1477212592959404,
|
|
"num_tokens": 5853117.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.71142544746399,
|
|
"epoch": 0.2671667628390075,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997387211881392,
|
|
"loss": 6.6453,
|
|
"mean_token_accuracy": 0.154846253991127,
|
|
"num_tokens": 5866717.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.773086881637573,
|
|
"epoch": 0.26774379688401617,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997367293703656,
|
|
"loss": 6.699,
|
|
"mean_token_accuracy": 0.1512269750237465,
|
|
"num_tokens": 5879017.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.793334484100342,
|
|
"epoch": 0.2683208309290248,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997347299936837,
|
|
"loss": 6.6803,
|
|
"mean_token_accuracy": 0.15060366541147233,
|
|
"num_tokens": 5891481.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.785113191604614,
|
|
"epoch": 0.26889786497403345,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997327230581608,
|
|
"loss": 6.6951,
|
|
"mean_token_accuracy": 0.14829754531383516,
|
|
"num_tokens": 5903389.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.79466233253479,
|
|
"epoch": 0.26947489901904215,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997307085638644,
|
|
"loss": 6.6014,
|
|
"mean_token_accuracy": 0.15171003192663193,
|
|
"num_tokens": 5916084.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.751241445541382,
|
|
"epoch": 0.2700519330640508,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004997286865108621,
|
|
"loss": 6.6476,
|
|
"mean_token_accuracy": 0.15270082801580429,
|
|
"num_tokens": 5927797.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.715710830688477,
|
|
"epoch": 0.2706289671090594,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997266568992222,
|
|
"loss": 6.5641,
|
|
"mean_token_accuracy": 0.15439386516809464,
|
|
"num_tokens": 5941886.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.745696973800659,
|
|
"epoch": 0.27120600115406807,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004997246197290128,
|
|
"loss": 6.6874,
|
|
"mean_token_accuracy": 0.15251569598913192,
|
|
"num_tokens": 5953655.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.920389127731323,
|
|
"epoch": 0.27178303519907676,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997225750003024,
|
|
"loss": 6.6943,
|
|
"mean_token_accuracy": 0.14675507098436355,
|
|
"num_tokens": 5967818.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.726615953445434,
|
|
"epoch": 0.2723600692440854,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997205227131599,
|
|
"loss": 6.6363,
|
|
"mean_token_accuracy": 0.15357123017311097,
|
|
"num_tokens": 5980742.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.803928184509277,
|
|
"epoch": 0.27293710328909404,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997184628676542,
|
|
"loss": 6.6679,
|
|
"mean_token_accuracy": 0.1451663374900818,
|
|
"num_tokens": 5993263.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.834203672409058,
|
|
"epoch": 0.27351413733410274,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997163954638546,
|
|
"loss": 6.749,
|
|
"mean_token_accuracy": 0.13940424844622612,
|
|
"num_tokens": 6007820.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.820643520355224,
|
|
"epoch": 0.2740911713791114,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997143205018306,
|
|
"loss": 6.6946,
|
|
"mean_token_accuracy": 0.14526703357696533,
|
|
"num_tokens": 6020665.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.768551397323608,
|
|
"epoch": 0.27466820542412,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997122379816523,
|
|
"loss": 6.6328,
|
|
"mean_token_accuracy": 0.15664122849702836,
|
|
"num_tokens": 6032847.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.738122892379761,
|
|
"epoch": 0.27524523946912866,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997101479033893,
|
|
"loss": 6.6885,
|
|
"mean_token_accuracy": 0.1447917029261589,
|
|
"num_tokens": 6045291.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.767072296142578,
|
|
"epoch": 0.27582227351413735,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997080502671122,
|
|
"loss": 6.6632,
|
|
"mean_token_accuracy": 0.152347169816494,
|
|
"num_tokens": 6057872.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.724477624893188,
|
|
"epoch": 0.276399307559146,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004997059450728913,
|
|
"loss": 6.6387,
|
|
"mean_token_accuracy": 0.14954917132854462,
|
|
"num_tokens": 6070252.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.8534856796264645,
|
|
"epoch": 0.27697634160415463,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997038323207977,
|
|
"loss": 6.7345,
|
|
"mean_token_accuracy": 0.14333323687314986,
|
|
"num_tokens": 6083728.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.765815353393554,
|
|
"epoch": 0.2775533756491633,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997017120109022,
|
|
"loss": 6.6816,
|
|
"mean_token_accuracy": 0.14334091544151306,
|
|
"num_tokens": 6097140.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.6975670337677,
|
|
"epoch": 0.27813040969417197,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996995841432762,
|
|
"loss": 6.6616,
|
|
"mean_token_accuracy": 0.14706796407699585,
|
|
"num_tokens": 6109518.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.822784471511841,
|
|
"epoch": 0.2787074437391806,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996974487179915,
|
|
"loss": 6.6353,
|
|
"mean_token_accuracy": 0.1506706103682518,
|
|
"num_tokens": 6122160.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.683734941482544,
|
|
"epoch": 0.27928447778418924,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996953057351195,
|
|
"loss": 6.6792,
|
|
"mean_token_accuracy": 0.14972876906394958,
|
|
"num_tokens": 6134638.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.794296360015869,
|
|
"epoch": 0.27986151182919794,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996931551947327,
|
|
"loss": 6.716,
|
|
"mean_token_accuracy": 0.14403074458241463,
|
|
"num_tokens": 6147142.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.91330852508545,
|
|
"epoch": 0.2804385458742066,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996909970969031,
|
|
"loss": 6.7142,
|
|
"mean_token_accuracy": 0.1503919020295143,
|
|
"num_tokens": 6159137.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.667835092544555,
|
|
"epoch": 0.2810155799192152,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996888314417034,
|
|
"loss": 6.7049,
|
|
"mean_token_accuracy": 0.14543969705700874,
|
|
"num_tokens": 6171663.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.919120836257934,
|
|
"epoch": 0.2815926139642239,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996866582292067,
|
|
"loss": 6.6955,
|
|
"mean_token_accuracy": 0.15087713599205016,
|
|
"num_tokens": 6184282.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.769654130935669,
|
|
"epoch": 0.28216964800923255,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996844774594856,
|
|
"loss": 6.6964,
|
|
"mean_token_accuracy": 0.145013540238142,
|
|
"num_tokens": 6197243.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.731862545013428,
|
|
"epoch": 0.2827466820542412,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996822891326138,
|
|
"loss": 6.6172,
|
|
"mean_token_accuracy": 0.14766587913036347,
|
|
"num_tokens": 6209061.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.731410026550293,
|
|
"epoch": 0.28332371609924983,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996800932486648,
|
|
"loss": 6.5871,
|
|
"mean_token_accuracy": 0.15210840851068497,
|
|
"num_tokens": 6223497.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.796885824203491,
|
|
"epoch": 0.28390075014425853,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996778898077126,
|
|
"loss": 6.6323,
|
|
"mean_token_accuracy": 0.15437232851982116,
|
|
"num_tokens": 6236395.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.646933364868164,
|
|
"epoch": 0.28447778418926717,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996756788098309,
|
|
"loss": 6.6089,
|
|
"mean_token_accuracy": 0.15198341608047486,
|
|
"num_tokens": 6248700.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.803117084503174,
|
|
"epoch": 0.2850548182342758,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004996734602550945,
|
|
"loss": 6.6497,
|
|
"mean_token_accuracy": 0.14864367991685867,
|
|
"num_tokens": 6262728.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.692935037612915,
|
|
"epoch": 0.2856318522792845,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996712341435779,
|
|
"loss": 6.6138,
|
|
"mean_token_accuracy": 0.1492878705263138,
|
|
"num_tokens": 6276007.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.8393807888031,
|
|
"epoch": 0.28620888632429314,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996690004753559,
|
|
"loss": 6.7461,
|
|
"mean_token_accuracy": 0.14636218845844268,
|
|
"num_tokens": 6289033.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.737071847915649,
|
|
"epoch": 0.2867859203693018,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996667592505037,
|
|
"loss": 6.6844,
|
|
"mean_token_accuracy": 0.14224475771188735,
|
|
"num_tokens": 6300994.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.738783359527588,
|
|
"epoch": 0.2873629544143104,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996645104690967,
|
|
"loss": 6.6377,
|
|
"mean_token_accuracy": 0.15198902413249016,
|
|
"num_tokens": 6313447.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.803956127166748,
|
|
"epoch": 0.2879399884593191,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996622541312103,
|
|
"loss": 6.623,
|
|
"mean_token_accuracy": 0.151736593991518,
|
|
"num_tokens": 6326622.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.725099420547485,
|
|
"epoch": 0.28851702250432776,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996599902369207,
|
|
"loss": 6.6404,
|
|
"mean_token_accuracy": 0.1515824615955353,
|
|
"num_tokens": 6339286.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.731478691101074,
|
|
"epoch": 0.2890940565493364,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996577187863039,
|
|
"loss": 6.6548,
|
|
"mean_token_accuracy": 0.14619150757789612,
|
|
"num_tokens": 6351869.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.72581992149353,
|
|
"epoch": 0.2896710905943451,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996554397794364,
|
|
"loss": 6.5781,
|
|
"mean_token_accuracy": 0.15530783385038377,
|
|
"num_tokens": 6363974.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.732598114013672,
|
|
"epoch": 0.29024812463935373,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996531532163947,
|
|
"loss": 6.5792,
|
|
"mean_token_accuracy": 0.15085918009281157,
|
|
"num_tokens": 6376569.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.7090099334716795,
|
|
"epoch": 0.2908251586843624,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996508590972558,
|
|
"loss": 6.5992,
|
|
"mean_token_accuracy": 0.15587113946676254,
|
|
"num_tokens": 6388830.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.735125112533569,
|
|
"epoch": 0.291402192729371,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996485574220969,
|
|
"loss": 6.609,
|
|
"mean_token_accuracy": 0.1497942864894867,
|
|
"num_tokens": 6401542.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.62659764289856,
|
|
"epoch": 0.2919792267743797,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996462481909953,
|
|
"loss": 6.5982,
|
|
"mean_token_accuracy": 0.15247822999954225,
|
|
"num_tokens": 6414123.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.759478330612183,
|
|
"epoch": 0.29255626081938835,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996439314040287,
|
|
"loss": 6.6562,
|
|
"mean_token_accuracy": 0.1472500592470169,
|
|
"num_tokens": 6427269.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.744736099243164,
|
|
"epoch": 0.293133294864397,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499641607061275,
|
|
"loss": 6.7066,
|
|
"mean_token_accuracy": 0.1504643440246582,
|
|
"num_tokens": 6442296.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.817773962020874,
|
|
"epoch": 0.2937103289094057,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996392751628126,
|
|
"loss": 6.7218,
|
|
"mean_token_accuracy": 0.1421102836728096,
|
|
"num_tokens": 6456954.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.750686311721802,
|
|
"epoch": 0.2942873629544143,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996369357087196,
|
|
"loss": 6.6965,
|
|
"mean_token_accuracy": 0.14400525987148285,
|
|
"num_tokens": 6470139.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.839855909347534,
|
|
"epoch": 0.29486439699942296,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499634588699075,
|
|
"loss": 6.6334,
|
|
"mean_token_accuracy": 0.15152083933353425,
|
|
"num_tokens": 6483106.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.647458600997925,
|
|
"epoch": 0.2954414310444316,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004996322341339575,
|
|
"loss": 6.6561,
|
|
"mean_token_accuracy": 0.14724331647157668,
|
|
"num_tokens": 6495921.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.759826612472534,
|
|
"epoch": 0.2960184650894403,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996298720134465,
|
|
"loss": 6.5553,
|
|
"mean_token_accuracy": 0.1497732073068619,
|
|
"num_tokens": 6508408.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.677283096313476,
|
|
"epoch": 0.29659549913444894,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996275023376213,
|
|
"loss": 6.6444,
|
|
"mean_token_accuracy": 0.1454513743519783,
|
|
"num_tokens": 6522081.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.73228816986084,
|
|
"epoch": 0.2971725331794576,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996251251065615,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.14908404648303986,
|
|
"num_tokens": 6535065.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.740736770629883,
|
|
"epoch": 0.2977495672244662,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996227403203473,
|
|
"loss": 6.5985,
|
|
"mean_token_accuracy": 0.1506045341491699,
|
|
"num_tokens": 6547972.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.668179225921631,
|
|
"epoch": 0.2983266012694749,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004996203479790589,
|
|
"loss": 6.5494,
|
|
"mean_token_accuracy": 0.156391242146492,
|
|
"num_tokens": 6559935.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.756309700012207,
|
|
"epoch": 0.29890363531448355,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004996179480827764,
|
|
"loss": 6.5639,
|
|
"mean_token_accuracy": 0.1533658154308796,
|
|
"num_tokens": 6572373.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.736523103713989,
|
|
"epoch": 0.2994806693594922,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499615540631581,
|
|
"loss": 6.6492,
|
|
"mean_token_accuracy": 0.14879586845636367,
|
|
"num_tokens": 6585846.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.774682474136353,
|
|
"epoch": 0.3000577034045009,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996131256255534,
|
|
"loss": 6.7078,
|
|
"mean_token_accuracy": 0.14609526395797728,
|
|
"num_tokens": 6600387.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.721484851837158,
|
|
"epoch": 0.3006347374495095,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004996107030647749,
|
|
"loss": 6.6359,
|
|
"mean_token_accuracy": 0.1481912150979042,
|
|
"num_tokens": 6613142.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.684381151199341,
|
|
"epoch": 0.30121177149451817,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996082729493269,
|
|
"loss": 6.5359,
|
|
"mean_token_accuracy": 0.15520427972078324,
|
|
"num_tokens": 6626273.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.717306995391846,
|
|
"epoch": 0.3017888055395268,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004996058352792913,
|
|
"loss": 6.6311,
|
|
"mean_token_accuracy": 0.14817688912153243,
|
|
"num_tokens": 6639831.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.759371042251587,
|
|
"epoch": 0.3023658395845355,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00049960339005475,
|
|
"loss": 6.6912,
|
|
"mean_token_accuracy": 0.1456967532634735,
|
|
"num_tokens": 6652776.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.834853887557983,
|
|
"epoch": 0.30294287362954414,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996009372757852,
|
|
"loss": 6.6504,
|
|
"mean_token_accuracy": 0.15175580829381943,
|
|
"num_tokens": 6665465.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.598134279251099,
|
|
"epoch": 0.3035199076745528,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004995984769424795,
|
|
"loss": 6.521,
|
|
"mean_token_accuracy": 0.16483442038297652,
|
|
"num_tokens": 6677472.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.655421113967895,
|
|
"epoch": 0.3040969417195615,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995960090549155,
|
|
"loss": 6.5558,
|
|
"mean_token_accuracy": 0.15292261838912963,
|
|
"num_tokens": 6689145.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.692539262771606,
|
|
"epoch": 0.3046739757645701,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995935336131764,
|
|
"loss": 6.5359,
|
|
"mean_token_accuracy": 0.15541132986545564,
|
|
"num_tokens": 6701520.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.7484640121459964,
|
|
"epoch": 0.30525100980957875,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995910506173452,
|
|
"loss": 6.6392,
|
|
"mean_token_accuracy": 0.15335483923554422,
|
|
"num_tokens": 6715615.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.786902809143067,
|
|
"epoch": 0.3058280438545874,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995885600675059,
|
|
"loss": 6.6493,
|
|
"mean_token_accuracy": 0.14820180535316468,
|
|
"num_tokens": 6728772.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.723455142974854,
|
|
"epoch": 0.3064050778995961,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995860619637415,
|
|
"loss": 6.5904,
|
|
"mean_token_accuracy": 0.1488635666668415,
|
|
"num_tokens": 6741454.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.680184316635132,
|
|
"epoch": 0.30698211194460473,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995835563061367,
|
|
"loss": 6.6329,
|
|
"mean_token_accuracy": 0.15059148371219636,
|
|
"num_tokens": 6753983.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.8095183849334715,
|
|
"epoch": 0.30755914598961337,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995810430947756,
|
|
"loss": 6.6587,
|
|
"mean_token_accuracy": 0.14956516027450562,
|
|
"num_tokens": 6767377.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.731013202667237,
|
|
"epoch": 0.30813618003462206,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004995785223297426,
|
|
"loss": 6.6165,
|
|
"mean_token_accuracy": 0.15526754558086395,
|
|
"num_tokens": 6779220.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.739847898483276,
|
|
"epoch": 0.3087132140796307,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004995759940111225,
|
|
"loss": 6.5862,
|
|
"mean_token_accuracy": 0.15217508971691132,
|
|
"num_tokens": 6792202.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.649475145339966,
|
|
"epoch": 0.30929024812463934,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995734581390005,
|
|
"loss": 6.5915,
|
|
"mean_token_accuracy": 0.15380042493343354,
|
|
"num_tokens": 6804988.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.723600292205811,
|
|
"epoch": 0.309867282169648,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995709147134617,
|
|
"loss": 6.625,
|
|
"mean_token_accuracy": 0.15084846913814545,
|
|
"num_tokens": 6817311.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.757253742218017,
|
|
"epoch": 0.3104443162146567,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004995683637345919,
|
|
"loss": 6.5985,
|
|
"mean_token_accuracy": 0.15270360708236694,
|
|
"num_tokens": 6829875.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.733402490615845,
|
|
"epoch": 0.3110213502596653,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004995658052024765,
|
|
"loss": 6.5826,
|
|
"mean_token_accuracy": 0.1535247102379799,
|
|
"num_tokens": 6843080.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.633068037033081,
|
|
"epoch": 0.31159838430467396,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995632391172019,
|
|
"loss": 6.5728,
|
|
"mean_token_accuracy": 0.15194655805826188,
|
|
"num_tokens": 6857202.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.745692777633667,
|
|
"epoch": 0.31217541834968265,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004995606654788543,
|
|
"loss": 6.6612,
|
|
"mean_token_accuracy": 0.1453693374991417,
|
|
"num_tokens": 6870801.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.764104557037354,
|
|
"epoch": 0.3127524523946913,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995580842875202,
|
|
"loss": 6.6112,
|
|
"mean_token_accuracy": 0.14864688366651535,
|
|
"num_tokens": 6883084.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.743693923950195,
|
|
"epoch": 0.31332948643969993,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995554955432866,
|
|
"loss": 6.6421,
|
|
"mean_token_accuracy": 0.14455916807055474,
|
|
"num_tokens": 6895309.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.723890781402588,
|
|
"epoch": 0.3139065204847086,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995528992462404,
|
|
"loss": 6.6268,
|
|
"mean_token_accuracy": 0.15532680079340935,
|
|
"num_tokens": 6907646.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.747570991516113,
|
|
"epoch": 0.31448355452971727,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499550295396469,
|
|
"loss": 6.5977,
|
|
"mean_token_accuracy": 0.15922294557094574,
|
|
"num_tokens": 6919769.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.665530633926392,
|
|
"epoch": 0.3150605885747259,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995476839940598,
|
|
"loss": 6.5651,
|
|
"mean_token_accuracy": 0.15450860559940338,
|
|
"num_tokens": 6933348.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.678213691711425,
|
|
"epoch": 0.31563762261973455,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499545065039101,
|
|
"loss": 6.6257,
|
|
"mean_token_accuracy": 0.14856788590550424,
|
|
"num_tokens": 6945105.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.677836799621582,
|
|
"epoch": 0.31621465666474324,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995424385316803,
|
|
"loss": 6.6046,
|
|
"mean_token_accuracy": 0.147177591919899,
|
|
"num_tokens": 6958009.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.699324274063111,
|
|
"epoch": 0.3167916907097519,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995398044718863,
|
|
"loss": 6.5217,
|
|
"mean_token_accuracy": 0.15502108931541442,
|
|
"num_tokens": 6970156.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.679452276229858,
|
|
"epoch": 0.3173687247547605,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004995371628598074,
|
|
"loss": 6.6122,
|
|
"mean_token_accuracy": 0.15149652659893037,
|
|
"num_tokens": 6983431.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.764488601684571,
|
|
"epoch": 0.31794575879976916,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995345136955328,
|
|
"loss": 6.6527,
|
|
"mean_token_accuracy": 0.14685067385435105,
|
|
"num_tokens": 6997470.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.6844353675842285,
|
|
"epoch": 0.31852279284477786,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995318569791512,
|
|
"loss": 6.6035,
|
|
"mean_token_accuracy": 0.1576828345656395,
|
|
"num_tokens": 7010337.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.792466688156128,
|
|
"epoch": 0.3190998268897865,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004995291927107522,
|
|
"loss": 6.635,
|
|
"mean_token_accuracy": 0.1491129755973816,
|
|
"num_tokens": 7023950.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.659047603607178,
|
|
"epoch": 0.31967686093479514,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995265208904252,
|
|
"loss": 6.5956,
|
|
"mean_token_accuracy": 0.1566797286272049,
|
|
"num_tokens": 7036409.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.750910663604737,
|
|
"epoch": 0.32025389497980383,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995238415182603,
|
|
"loss": 6.6074,
|
|
"mean_token_accuracy": 0.14797423183918,
|
|
"num_tokens": 7049409.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.705856990814209,
|
|
"epoch": 0.3208309290248125,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995211545943476,
|
|
"loss": 6.6512,
|
|
"mean_token_accuracy": 0.15140025615692138,
|
|
"num_tokens": 7062120.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.757962846755982,
|
|
"epoch": 0.3214079630698211,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995184601187772,
|
|
"loss": 6.6431,
|
|
"mean_token_accuracy": 0.14404307901859284,
|
|
"num_tokens": 7073150.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.742756462097168,
|
|
"epoch": 0.32198499711482975,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00049951575809164,
|
|
"loss": 6.5825,
|
|
"mean_token_accuracy": 0.14299354702234268,
|
|
"num_tokens": 7085927.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.657029342651367,
|
|
"epoch": 0.32256203115983845,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995130485130269,
|
|
"loss": 6.6388,
|
|
"mean_token_accuracy": 0.1517026126384735,
|
|
"num_tokens": 7097607.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.784142065048218,
|
|
"epoch": 0.3231390652048471,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995103313830289,
|
|
"loss": 6.5707,
|
|
"mean_token_accuracy": 0.1529722362756729,
|
|
"num_tokens": 7109771.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.7327779769897464,
|
|
"epoch": 0.3237160992498557,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004995076067017373,
|
|
"loss": 6.6322,
|
|
"mean_token_accuracy": 0.1470279797911644,
|
|
"num_tokens": 7122757.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.654575204849243,
|
|
"epoch": 0.3242931332948644,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004995048744692439,
|
|
"loss": 6.6093,
|
|
"mean_token_accuracy": 0.14694169014692307,
|
|
"num_tokens": 7135516.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.756155252456665,
|
|
"epoch": 0.32487016733987306,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995021346856405,
|
|
"loss": 6.6842,
|
|
"mean_token_accuracy": 0.14694853872060776,
|
|
"num_tokens": 7149125.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.73067193031311,
|
|
"epoch": 0.3254472013848817,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994993873510196,
|
|
"loss": 6.6307,
|
|
"mean_token_accuracy": 0.14298643171787262,
|
|
"num_tokens": 7160723.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.687489080429077,
|
|
"epoch": 0.32602423542989034,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004994966324654731,
|
|
"loss": 6.6089,
|
|
"mean_token_accuracy": 0.14513298645615577,
|
|
"num_tokens": 7174551.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.7687946319580075,
|
|
"epoch": 0.32660126947489904,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499493870029094,
|
|
"loss": 6.5889,
|
|
"mean_token_accuracy": 0.15016230791807175,
|
|
"num_tokens": 7186764.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.696437358856201,
|
|
"epoch": 0.3271783035199077,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994911000419749,
|
|
"loss": 6.5842,
|
|
"mean_token_accuracy": 0.15165507793426514,
|
|
"num_tokens": 7199645.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.612226581573486,
|
|
"epoch": 0.3277553375649163,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994883225042093,
|
|
"loss": 6.5105,
|
|
"mean_token_accuracy": 0.16406965851783753,
|
|
"num_tokens": 7212579.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.673196649551391,
|
|
"epoch": 0.328332371609925,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994855374158905,
|
|
"loss": 6.5433,
|
|
"mean_token_accuracy": 0.1573927402496338,
|
|
"num_tokens": 7225139.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.728290367126465,
|
|
"epoch": 0.32890940565493365,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499482744777112,
|
|
"loss": 6.6863,
|
|
"mean_token_accuracy": 0.14344870671629906,
|
|
"num_tokens": 7239220.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.801548290252685,
|
|
"epoch": 0.3294864396999423,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000499479944587968,
|
|
"loss": 6.7103,
|
|
"mean_token_accuracy": 0.15049158781766891,
|
|
"num_tokens": 7252613.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.632060527801514,
|
|
"epoch": 0.33006347374495093,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994771368485526,
|
|
"loss": 6.536,
|
|
"mean_token_accuracy": 0.15601779520511627,
|
|
"num_tokens": 7263658.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.740309047698974,
|
|
"epoch": 0.3306405077899596,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994743215589602,
|
|
"loss": 6.5617,
|
|
"mean_token_accuracy": 0.1619183152914047,
|
|
"num_tokens": 7275782.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.594912481307984,
|
|
"epoch": 0.33121754183496827,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994714987192854,
|
|
"loss": 6.618,
|
|
"mean_token_accuracy": 0.1574898988008499,
|
|
"num_tokens": 7288536.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.694319057464599,
|
|
"epoch": 0.3317945758799769,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994686683296234,
|
|
"loss": 6.576,
|
|
"mean_token_accuracy": 0.15647158324718474,
|
|
"num_tokens": 7300480.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.702283906936645,
|
|
"epoch": 0.3323716099249856,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004994658303900691,
|
|
"loss": 6.6199,
|
|
"mean_token_accuracy": 0.15028671324253082,
|
|
"num_tokens": 7313168.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.6668816089630125,
|
|
"epoch": 0.33294864396999424,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994629849007182,
|
|
"loss": 6.5767,
|
|
"mean_token_accuracy": 0.15539561957120895,
|
|
"num_tokens": 7327347.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.722062492370606,
|
|
"epoch": 0.3335256780150029,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994601318616663,
|
|
"loss": 6.61,
|
|
"mean_token_accuracy": 0.14843571111559867,
|
|
"num_tokens": 7339955.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.70476131439209,
|
|
"epoch": 0.3341027120600115,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994572712730092,
|
|
"loss": 6.5879,
|
|
"mean_token_accuracy": 0.148174050450325,
|
|
"num_tokens": 7353586.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.692771768569946,
|
|
"epoch": 0.3346797461050202,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994544031348434,
|
|
"loss": 6.5577,
|
|
"mean_token_accuracy": 0.15284216701984404,
|
|
"num_tokens": 7365802.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.6868119716644285,
|
|
"epoch": 0.33525678015002885,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994515274472653,
|
|
"loss": 6.5256,
|
|
"mean_token_accuracy": 0.14853521138429643,
|
|
"num_tokens": 7377864.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.647774076461792,
|
|
"epoch": 0.3358338141950375,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004994486442103715,
|
|
"loss": 6.4741,
|
|
"mean_token_accuracy": 0.15462038069963455,
|
|
"num_tokens": 7389921.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.653657722473144,
|
|
"epoch": 0.3364108482400462,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499445753424259,
|
|
"loss": 6.54,
|
|
"mean_token_accuracy": 0.15041984468698502,
|
|
"num_tokens": 7402765.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.737467956542969,
|
|
"epoch": 0.33698788228505483,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004994428550890251,
|
|
"loss": 6.5701,
|
|
"mean_token_accuracy": 0.14831982553005219,
|
|
"num_tokens": 7416330.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.6251367092132565,
|
|
"epoch": 0.33756491633006347,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994399492047672,
|
|
"loss": 6.515,
|
|
"mean_token_accuracy": 0.16390403658151625,
|
|
"num_tokens": 7428701.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.723229122161865,
|
|
"epoch": 0.3381419503750721,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004994370357715832,
|
|
"loss": 6.5249,
|
|
"mean_token_accuracy": 0.15543388575315475,
|
|
"num_tokens": 7440687.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.654600191116333,
|
|
"epoch": 0.3387189844200808,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499434114789571,
|
|
"loss": 6.6147,
|
|
"mean_token_accuracy": 0.14533780366182328,
|
|
"num_tokens": 7454448.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.746973848342895,
|
|
"epoch": 0.33929601846508944,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994311862588286,
|
|
"loss": 6.5318,
|
|
"mean_token_accuracy": 0.15422469675540923,
|
|
"num_tokens": 7466722.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.612504863739014,
|
|
"epoch": 0.3398730525100981,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994282501794551,
|
|
"loss": 6.5434,
|
|
"mean_token_accuracy": 0.15694365054368972,
|
|
"num_tokens": 7478574.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.630198383331299,
|
|
"epoch": 0.3404500865551068,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994253065515486,
|
|
"loss": 6.4416,
|
|
"mean_token_accuracy": 0.1585552930831909,
|
|
"num_tokens": 7490424.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.687573194503784,
|
|
"epoch": 0.3410271206001154,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994223553752084,
|
|
"loss": 6.5932,
|
|
"mean_token_accuracy": 0.15581245720386505,
|
|
"num_tokens": 7502832.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.616685962677002,
|
|
"epoch": 0.34160415464512406,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994193966505339,
|
|
"loss": 6.5195,
|
|
"mean_token_accuracy": 0.1566762462258339,
|
|
"num_tokens": 7514151.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.685769557952881,
|
|
"epoch": 0.3421811886901327,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004994164303776244,
|
|
"loss": 6.5417,
|
|
"mean_token_accuracy": 0.15701379925012587,
|
|
"num_tokens": 7526877.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.673000526428223,
|
|
"epoch": 0.3427582227351414,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994134565565797,
|
|
"loss": 6.5302,
|
|
"mean_token_accuracy": 0.156466044485569,
|
|
"num_tokens": 7538858.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.721205186843872,
|
|
"epoch": 0.34333525678015003,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004994104751875,
|
|
"loss": 6.56,
|
|
"mean_token_accuracy": 0.1546006865799427,
|
|
"num_tokens": 7550804.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.626689672470093,
|
|
"epoch": 0.3439122908251587,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994074862704854,
|
|
"loss": 6.4896,
|
|
"mean_token_accuracy": 0.16036185026168823,
|
|
"num_tokens": 7562269.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.6253760814666744,
|
|
"epoch": 0.3444893248701673,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994044898056363,
|
|
"loss": 6.5821,
|
|
"mean_token_accuracy": 0.14939415752887725,
|
|
"num_tokens": 7573695.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.688880825042725,
|
|
"epoch": 0.345066358915176,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994014857930538,
|
|
"loss": 6.5974,
|
|
"mean_token_accuracy": 0.14651145711541175,
|
|
"num_tokens": 7585943.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.667485666275025,
|
|
"epoch": 0.34564339296018465,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993984742328387,
|
|
"loss": 6.5789,
|
|
"mean_token_accuracy": 0.1516515865921974,
|
|
"num_tokens": 7598326.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.715835285186768,
|
|
"epoch": 0.3462204270051933,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004993954551250925,
|
|
"loss": 6.5636,
|
|
"mean_token_accuracy": 0.14854548275470733,
|
|
"num_tokens": 7609950.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3462204270051933,
|
|
"eval_entropy": 6.571954663856687,
|
|
"eval_loss": 6.600578308105469,
|
|
"eval_mean_token_accuracy": 0.15436312960360685,
|
|
"eval_num_tokens": 7609950.0,
|
|
"eval_runtime": 17.7878,
|
|
"eval_samples_per_second": 1581.762,
|
|
"eval_steps_per_second": 197.72,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.67913236618042,
|
|
"epoch": 0.346797461050202,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004993924284699165,
|
|
"loss": 6.5187,
|
|
"mean_token_accuracy": 0.15324495881795883,
|
|
"num_tokens": 7621987.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.662750720977783,
|
|
"epoch": 0.3473744950952106,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004993893942674127,
|
|
"loss": 6.5837,
|
|
"mean_token_accuracy": 0.15105323493480682,
|
|
"num_tokens": 7634801.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.713637208938598,
|
|
"epoch": 0.34795152914021926,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499386352517683,
|
|
"loss": 6.5376,
|
|
"mean_token_accuracy": 0.15901586338877677,
|
|
"num_tokens": 7647942.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.683552551269531,
|
|
"epoch": 0.3485285631852279,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00049938330322083,
|
|
"loss": 6.5491,
|
|
"mean_token_accuracy": 0.1520805388689041,
|
|
"num_tokens": 7662361.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.628801774978638,
|
|
"epoch": 0.3491055972302366,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993802463769558,
|
|
"loss": 6.5425,
|
|
"mean_token_accuracy": 0.15337807536125184,
|
|
"num_tokens": 7674161.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.704723119735718,
|
|
"epoch": 0.34968263127524524,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993771819861636,
|
|
"loss": 6.5468,
|
|
"mean_token_accuracy": 0.15563344210386276,
|
|
"num_tokens": 7686957.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.638054227828979,
|
|
"epoch": 0.3502596653202539,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004993741100485564,
|
|
"loss": 6.5082,
|
|
"mean_token_accuracy": 0.15760557949543,
|
|
"num_tokens": 7699436.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.569077968597412,
|
|
"epoch": 0.35083669936526257,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993710305642374,
|
|
"loss": 6.5267,
|
|
"mean_token_accuracy": 0.15751972198486328,
|
|
"num_tokens": 7711794.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.666848373413086,
|
|
"epoch": 0.3514137334102712,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993679435333102,
|
|
"loss": 6.478,
|
|
"mean_token_accuracy": 0.1532701849937439,
|
|
"num_tokens": 7723496.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.619588375091553,
|
|
"epoch": 0.35199076745527985,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993648489558788,
|
|
"loss": 6.497,
|
|
"mean_token_accuracy": 0.1570889875292778,
|
|
"num_tokens": 7735980.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.641847801208496,
|
|
"epoch": 0.3525678015002885,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993617468320471,
|
|
"loss": 6.5698,
|
|
"mean_token_accuracy": 0.15105772390961647,
|
|
"num_tokens": 7750145.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.659021091461182,
|
|
"epoch": 0.3531448355452972,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993586371619193,
|
|
"loss": 6.5764,
|
|
"mean_token_accuracy": 0.1522957906126976,
|
|
"num_tokens": 7762284.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.5531312942504885,
|
|
"epoch": 0.3537218695903058,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993555199456004,
|
|
"loss": 6.5305,
|
|
"mean_token_accuracy": 0.1619846776127815,
|
|
"num_tokens": 7776225.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.609269666671753,
|
|
"epoch": 0.35429890363531447,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993523951831949,
|
|
"loss": 6.4629,
|
|
"mean_token_accuracy": 0.16548260748386384,
|
|
"num_tokens": 7789408.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.703277111053467,
|
|
"epoch": 0.35487593768032316,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993492628748081,
|
|
"loss": 6.5309,
|
|
"mean_token_accuracy": 0.14926318675279618,
|
|
"num_tokens": 7801824.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.5838579654693605,
|
|
"epoch": 0.3554529717253318,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004993461230205453,
|
|
"loss": 6.5234,
|
|
"mean_token_accuracy": 0.1576508030295372,
|
|
"num_tokens": 7814167.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.691663599014282,
|
|
"epoch": 0.35603000577034044,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004993429756205121,
|
|
"loss": 6.5595,
|
|
"mean_token_accuracy": 0.1552141159772873,
|
|
"num_tokens": 7826736.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.6293723583221436,
|
|
"epoch": 0.3566070398153491,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004993398206748142,
|
|
"loss": 6.5219,
|
|
"mean_token_accuracy": 0.15335862934589387,
|
|
"num_tokens": 7838626.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.691901588439942,
|
|
"epoch": 0.3571840738603578,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004993366581835581,
|
|
"loss": 6.5186,
|
|
"mean_token_accuracy": 0.15390921831130983,
|
|
"num_tokens": 7850608.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.63633918762207,
|
|
"epoch": 0.3577611079053664,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004993334881468498,
|
|
"loss": 6.5063,
|
|
"mean_token_accuracy": 0.1534891128540039,
|
|
"num_tokens": 7862800.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.715207052230835,
|
|
"epoch": 0.35833814195037506,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993303105647961,
|
|
"loss": 6.5752,
|
|
"mean_token_accuracy": 0.15088694244623185,
|
|
"num_tokens": 7876198.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.708647918701172,
|
|
"epoch": 0.35891517599538375,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993271254375038,
|
|
"loss": 6.5954,
|
|
"mean_token_accuracy": 0.14844163358211518,
|
|
"num_tokens": 7888129.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.652002191543579,
|
|
"epoch": 0.3594922100403924,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00049932393276508,
|
|
"loss": 6.5536,
|
|
"mean_token_accuracy": 0.15066457390785218,
|
|
"num_tokens": 7900453.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.685463333129883,
|
|
"epoch": 0.36006924408540103,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004993207325476323,
|
|
"loss": 6.5567,
|
|
"mean_token_accuracy": 0.14931840747594832,
|
|
"num_tokens": 7913538.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.679757308959961,
|
|
"epoch": 0.36064627813040967,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993175247852681,
|
|
"loss": 6.5217,
|
|
"mean_token_accuracy": 0.15380802154541015,
|
|
"num_tokens": 7927744.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.594105291366577,
|
|
"epoch": 0.36122331217541837,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993143094780954,
|
|
"loss": 6.4676,
|
|
"mean_token_accuracy": 0.1560771107673645,
|
|
"num_tokens": 7939975.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.670260858535767,
|
|
"epoch": 0.361800346220427,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993110866262224,
|
|
"loss": 6.522,
|
|
"mean_token_accuracy": 0.15731455832719804,
|
|
"num_tokens": 7951692.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.630655765533447,
|
|
"epoch": 0.36237738026543564,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004993078562297573,
|
|
"loss": 6.5325,
|
|
"mean_token_accuracy": 0.15282207280397414,
|
|
"num_tokens": 7964887.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.624306344985962,
|
|
"epoch": 0.36295441431044434,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993046182888089,
|
|
"loss": 6.5486,
|
|
"mean_token_accuracy": 0.15523382872343064,
|
|
"num_tokens": 7977608.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.6301249980926515,
|
|
"epoch": 0.363531448355453,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993013728034861,
|
|
"loss": 6.4665,
|
|
"mean_token_accuracy": 0.15506149977445602,
|
|
"num_tokens": 7990094.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.691576719284058,
|
|
"epoch": 0.3641084824004616,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499298119773898,
|
|
"loss": 6.5336,
|
|
"mean_token_accuracy": 0.15450148284435272,
|
|
"num_tokens": 8003477.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.611363458633423,
|
|
"epoch": 0.36468551644547026,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992948592001541,
|
|
"loss": 6.4861,
|
|
"mean_token_accuracy": 0.1541801556944847,
|
|
"num_tokens": 8016241.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.59058780670166,
|
|
"epoch": 0.36526255049047895,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499291591082364,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.16361010670661927,
|
|
"num_tokens": 8028352.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.609756946563721,
|
|
"epoch": 0.3658395845354876,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992883154206377,
|
|
"loss": 6.5508,
|
|
"mean_token_accuracy": 0.1522105261683464,
|
|
"num_tokens": 8040215.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.655618906021118,
|
|
"epoch": 0.36641661858049623,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004992850322150853,
|
|
"loss": 6.4528,
|
|
"mean_token_accuracy": 0.16034831553697587,
|
|
"num_tokens": 8051633.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.64651517868042,
|
|
"epoch": 0.36699365262550493,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004992817414658172,
|
|
"loss": 6.5185,
|
|
"mean_token_accuracy": 0.1551498845219612,
|
|
"num_tokens": 8063390.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.624983882904052,
|
|
"epoch": 0.36757068667051357,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004992784431729442,
|
|
"loss": 6.5044,
|
|
"mean_token_accuracy": 0.15131230503320695,
|
|
"num_tokens": 8077561.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.6048698902130125,
|
|
"epoch": 0.3681477207155222,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004992751373365771,
|
|
"loss": 6.5723,
|
|
"mean_token_accuracy": 0.15384764671325685,
|
|
"num_tokens": 8091345.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.599915266036987,
|
|
"epoch": 0.36872475476053085,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992718239568273,
|
|
"loss": 6.4195,
|
|
"mean_token_accuracy": 0.16362291127443312,
|
|
"num_tokens": 8104179.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.637220239639282,
|
|
"epoch": 0.36930178880553954,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499268503033806,
|
|
"loss": 6.5777,
|
|
"mean_token_accuracy": 0.14956896454095842,
|
|
"num_tokens": 8115831.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.605573606491089,
|
|
"epoch": 0.3698788228505482,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004992651745676249,
|
|
"loss": 6.5124,
|
|
"mean_token_accuracy": 0.15962110906839372,
|
|
"num_tokens": 8129048.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.649493169784546,
|
|
"epoch": 0.3704558568955568,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992618385583962,
|
|
"loss": 6.5172,
|
|
"mean_token_accuracy": 0.14941440969705583,
|
|
"num_tokens": 8141679.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.617839097976685,
|
|
"epoch": 0.3710328909405655,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004992584950062319,
|
|
"loss": 6.4865,
|
|
"mean_token_accuracy": 0.15477514415979385,
|
|
"num_tokens": 8155004.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.538065576553345,
|
|
"epoch": 0.37160992498557416,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992551439112446,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.1586252972483635,
|
|
"num_tokens": 8166718.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.632493591308593,
|
|
"epoch": 0.3721869590305828,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992517852735469,
|
|
"loss": 6.6244,
|
|
"mean_token_accuracy": 0.14812181890010834,
|
|
"num_tokens": 8180011.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.646015453338623,
|
|
"epoch": 0.37276399307559144,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992484190932517,
|
|
"loss": 6.4352,
|
|
"mean_token_accuracy": 0.1578085280954838,
|
|
"num_tokens": 8194800.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.664063167572022,
|
|
"epoch": 0.37334102712060013,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992450453704723,
|
|
"loss": 6.5604,
|
|
"mean_token_accuracy": 0.15252675265073776,
|
|
"num_tokens": 8207153.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.711281061172485,
|
|
"epoch": 0.3739180611656088,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004992416641053223,
|
|
"loss": 6.5446,
|
|
"mean_token_accuracy": 0.15358139276504518,
|
|
"num_tokens": 8221135.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.494730043411255,
|
|
"epoch": 0.3744950952106174,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992382752979153,
|
|
"loss": 6.4123,
|
|
"mean_token_accuracy": 0.16235440969467163,
|
|
"num_tokens": 8234271.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.650647115707398,
|
|
"epoch": 0.3750721292556261,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992348789483651,
|
|
"loss": 6.5545,
|
|
"mean_token_accuracy": 0.14874081835150718,
|
|
"num_tokens": 8246710.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.687919473648071,
|
|
"epoch": 0.37564916330063475,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004992314750567864,
|
|
"loss": 6.6077,
|
|
"mean_token_accuracy": 0.15173837468028067,
|
|
"num_tokens": 8259817.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.620677471160889,
|
|
"epoch": 0.3762261973456434,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004992280636232933,
|
|
"loss": 6.5395,
|
|
"mean_token_accuracy": 0.16084663420915604,
|
|
"num_tokens": 8274359.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.721046495437622,
|
|
"epoch": 0.376803231390652,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992246446480007,
|
|
"loss": 6.5053,
|
|
"mean_token_accuracy": 0.15376538634300232,
|
|
"num_tokens": 8286355.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.596151685714721,
|
|
"epoch": 0.3773802654356607,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004992212181310235,
|
|
"loss": 6.4847,
|
|
"mean_token_accuracy": 0.15147178918123244,
|
|
"num_tokens": 8298338.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.520630645751953,
|
|
"epoch": 0.37795729948066936,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499217784072477,
|
|
"loss": 6.4627,
|
|
"mean_token_accuracy": 0.15949076861143113,
|
|
"num_tokens": 8312367.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.663025856018066,
|
|
"epoch": 0.378534333525678,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004992143424724768,
|
|
"loss": 6.5539,
|
|
"mean_token_accuracy": 0.14739133268594742,
|
|
"num_tokens": 8325577.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.645350456237793,
|
|
"epoch": 0.3791113675706867,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992108933311385,
|
|
"loss": 6.5688,
|
|
"mean_token_accuracy": 0.15200639963150026,
|
|
"num_tokens": 8338965.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.735022687911988,
|
|
"epoch": 0.37968840161569534,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004992074366485782,
|
|
"loss": 6.5193,
|
|
"mean_token_accuracy": 0.14615978449583053,
|
|
"num_tokens": 8351669.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.575160884857178,
|
|
"epoch": 0.380265435660704,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499203972424912,
|
|
"loss": 6.5674,
|
|
"mean_token_accuracy": 0.15271605104207991,
|
|
"num_tokens": 8364194.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.621188068389893,
|
|
"epoch": 0.3808424697057126,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004992005006602567,
|
|
"loss": 6.5759,
|
|
"mean_token_accuracy": 0.15298435539007188,
|
|
"num_tokens": 8377001.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.630554580688477,
|
|
"epoch": 0.3814195037507213,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991970213547289,
|
|
"loss": 6.5695,
|
|
"mean_token_accuracy": 0.1499115854501724,
|
|
"num_tokens": 8389247.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.665640449523925,
|
|
"epoch": 0.38199653779572995,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004991935345084457,
|
|
"loss": 6.4557,
|
|
"mean_token_accuracy": 0.15480488911271095,
|
|
"num_tokens": 8402915.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.620656824111938,
|
|
"epoch": 0.3825735718407386,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004991900401215243,
|
|
"loss": 6.566,
|
|
"mean_token_accuracy": 0.15210421830415727,
|
|
"num_tokens": 8414590.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.6845362186431885,
|
|
"epoch": 0.3831506058857473,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991865381940822,
|
|
"loss": 6.5415,
|
|
"mean_token_accuracy": 0.15634194612503052,
|
|
"num_tokens": 8427337.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.532070064544678,
|
|
"epoch": 0.3837276399307559,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991830287262374,
|
|
"loss": 6.4353,
|
|
"mean_token_accuracy": 0.16090213805437087,
|
|
"num_tokens": 8440095.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.582758522033691,
|
|
"epoch": 0.38430467397576457,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991795117181077,
|
|
"loss": 6.4573,
|
|
"mean_token_accuracy": 0.1525129869580269,
|
|
"num_tokens": 8452448.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.6684760570526125,
|
|
"epoch": 0.3848817080207732,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004991759871698113,
|
|
"loss": 6.4847,
|
|
"mean_token_accuracy": 0.1601237565279007,
|
|
"num_tokens": 8465289.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.593679332733155,
|
|
"epoch": 0.3854587420657819,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991724550814671,
|
|
"loss": 6.5024,
|
|
"mean_token_accuracy": 0.15915523767471312,
|
|
"num_tokens": 8477365.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.6565875053405765,
|
|
"epoch": 0.38603577611079054,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991689154531937,
|
|
"loss": 6.5706,
|
|
"mean_token_accuracy": 0.15299642086029053,
|
|
"num_tokens": 8489104.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.565132427215576,
|
|
"epoch": 0.3866128101557992,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004991653682851102,
|
|
"loss": 6.4436,
|
|
"mean_token_accuracy": 0.1581375189125538,
|
|
"num_tokens": 8501509.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.575328779220581,
|
|
"epoch": 0.3871898442008078,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499161813577336,
|
|
"loss": 6.4948,
|
|
"mean_token_accuracy": 0.15168995559215545,
|
|
"num_tokens": 8514224.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.675197601318359,
|
|
"epoch": 0.3877668782458165,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991582513299903,
|
|
"loss": 6.5789,
|
|
"mean_token_accuracy": 0.14614480137825012,
|
|
"num_tokens": 8526689.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.582357358932495,
|
|
"epoch": 0.38834391229082516,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991546815431932,
|
|
"loss": 6.6078,
|
|
"mean_token_accuracy": 0.1479400023818016,
|
|
"num_tokens": 8539952.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.705312252044678,
|
|
"epoch": 0.3889209463358338,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499151104217065,
|
|
"loss": 6.5948,
|
|
"mean_token_accuracy": 0.1492103323340416,
|
|
"num_tokens": 8553428.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.649981832504272,
|
|
"epoch": 0.3894979803808425,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991475193517254,
|
|
"loss": 6.4562,
|
|
"mean_token_accuracy": 0.15850950852036477,
|
|
"num_tokens": 8566066.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.554257202148437,
|
|
"epoch": 0.39007501442585113,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004991439269472956,
|
|
"loss": 6.41,
|
|
"mean_token_accuracy": 0.15376016795635222,
|
|
"num_tokens": 8579211.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.668615388870239,
|
|
"epoch": 0.39065204847085977,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991403270038961,
|
|
"loss": 6.521,
|
|
"mean_token_accuracy": 0.1519201323390007,
|
|
"num_tokens": 8591647.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.518864393234253,
|
|
"epoch": 0.3912290825158684,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499136719521648,
|
|
"loss": 6.5075,
|
|
"mean_token_accuracy": 0.15120508521795273,
|
|
"num_tokens": 8604279.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.625417041778564,
|
|
"epoch": 0.3918061165608771,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004991331045006726,
|
|
"loss": 6.4162,
|
|
"mean_token_accuracy": 0.1614367976784706,
|
|
"num_tokens": 8617722.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.527361679077148,
|
|
"epoch": 0.39238315060588574,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991294819410916,
|
|
"loss": 6.4441,
|
|
"mean_token_accuracy": 0.16820953413844109,
|
|
"num_tokens": 8630250.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.482899379730225,
|
|
"epoch": 0.3929601846508944,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991258518430268,
|
|
"loss": 6.3346,
|
|
"mean_token_accuracy": 0.16297557950019836,
|
|
"num_tokens": 8641900.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.555102777481079,
|
|
"epoch": 0.3935372186959031,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004991222142066003,
|
|
"loss": 6.4545,
|
|
"mean_token_accuracy": 0.15731057673692703,
|
|
"num_tokens": 8654588.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.648878288269043,
|
|
"epoch": 0.3941142527409117,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991185690319345,
|
|
"loss": 6.4915,
|
|
"mean_token_accuracy": 0.14755185917019845,
|
|
"num_tokens": 8668111.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.570490169525146,
|
|
"epoch": 0.39469128678592036,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000499114916319152,
|
|
"loss": 6.5662,
|
|
"mean_token_accuracy": 0.1540154278278351,
|
|
"num_tokens": 8681461.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.658483409881592,
|
|
"epoch": 0.395268320830929,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991112560683755,
|
|
"loss": 6.4903,
|
|
"mean_token_accuracy": 0.1537899613380432,
|
|
"num_tokens": 8692893.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.593234586715698,
|
|
"epoch": 0.3958453548759377,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004991075882797283,
|
|
"loss": 6.3817,
|
|
"mean_token_accuracy": 0.16625459790229796,
|
|
"num_tokens": 8704704.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.585725784301758,
|
|
"epoch": 0.39642238892094633,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991039129533337,
|
|
"loss": 6.5528,
|
|
"mean_token_accuracy": 0.15255533307790756,
|
|
"num_tokens": 8717595.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.544450187683106,
|
|
"epoch": 0.396999422965955,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991002300893152,
|
|
"loss": 6.4927,
|
|
"mean_token_accuracy": 0.15547696650028228,
|
|
"num_tokens": 8729712.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.623501539230347,
|
|
"epoch": 0.39757645701096367,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004990965396877969,
|
|
"loss": 6.4136,
|
|
"mean_token_accuracy": 0.15489595979452134,
|
|
"num_tokens": 8742668.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.637320518493652,
|
|
"epoch": 0.3981534910559723,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004990928417489027,
|
|
"loss": 6.5008,
|
|
"mean_token_accuracy": 0.16184985637664795,
|
|
"num_tokens": 8754755.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.598210096359253,
|
|
"epoch": 0.39873052510098095,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004990891362727572,
|
|
"loss": 6.4325,
|
|
"mean_token_accuracy": 0.16320631355047227,
|
|
"num_tokens": 8766063.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.624905776977539,
|
|
"epoch": 0.3993075591459896,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990854232594848,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.163354229927063,
|
|
"num_tokens": 8779226.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.56977071762085,
|
|
"epoch": 0.3998845931909983,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004990817027092106,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.1581609547138214,
|
|
"num_tokens": 8791404.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.596388483047486,
|
|
"epoch": 0.4004616272360069,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004990779746220595,
|
|
"loss": 6.5466,
|
|
"mean_token_accuracy": 0.1522767573595047,
|
|
"num_tokens": 8805306.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.5737920761108395,
|
|
"epoch": 0.40103866128101556,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990742389981572,
|
|
"loss": 6.4273,
|
|
"mean_token_accuracy": 0.16027601957321166,
|
|
"num_tokens": 8817850.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.558056163787842,
|
|
"epoch": 0.40161569532602426,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499070495837629,
|
|
"loss": 6.4522,
|
|
"mean_token_accuracy": 0.16423497945070267,
|
|
"num_tokens": 8830765.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.598183536529541,
|
|
"epoch": 0.4021927293710329,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004990667451406012,
|
|
"loss": 6.4909,
|
|
"mean_token_accuracy": 0.15179530829191207,
|
|
"num_tokens": 8843329.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.6653501987457275,
|
|
"epoch": 0.40276976341604154,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004990629869071995,
|
|
"loss": 6.4857,
|
|
"mean_token_accuracy": 0.15301345139741898,
|
|
"num_tokens": 8856712.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.470282936096192,
|
|
"epoch": 0.4033467974610502,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004990592211375506,
|
|
"loss": 6.4469,
|
|
"mean_token_accuracy": 0.1624319449067116,
|
|
"num_tokens": 8868364.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.570513820648193,
|
|
"epoch": 0.4039238315060589,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004990554478317811,
|
|
"loss": 6.4316,
|
|
"mean_token_accuracy": 0.15485603660345076,
|
|
"num_tokens": 8881335.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.5659960269927975,
|
|
"epoch": 0.4045008655510675,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004990516669900179,
|
|
"loss": 6.5002,
|
|
"mean_token_accuracy": 0.15902469158172608,
|
|
"num_tokens": 8894049.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.558427095413208,
|
|
"epoch": 0.40507789959607615,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990478786123882,
|
|
"loss": 6.4024,
|
|
"mean_token_accuracy": 0.1596820518374443,
|
|
"num_tokens": 8906056.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.625905513763428,
|
|
"epoch": 0.40565493364108485,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004990440826990193,
|
|
"loss": 6.4801,
|
|
"mean_token_accuracy": 0.15464828312397003,
|
|
"num_tokens": 8919606.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.57070255279541,
|
|
"epoch": 0.4062319676860935,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990402792500392,
|
|
"loss": 6.4484,
|
|
"mean_token_accuracy": 0.16032859534025193,
|
|
"num_tokens": 8934733.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.487190055847168,
|
|
"epoch": 0.4068090017311021,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004990364682655754,
|
|
"loss": 6.4802,
|
|
"mean_token_accuracy": 0.15721859708428382,
|
|
"num_tokens": 8948331.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.619977712631226,
|
|
"epoch": 0.40738603577611077,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004990326497457564,
|
|
"loss": 6.4614,
|
|
"mean_token_accuracy": 0.1596258044242859,
|
|
"num_tokens": 8961171.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.556022262573242,
|
|
"epoch": 0.40796306982111946,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004990288236907104,
|
|
"loss": 6.5243,
|
|
"mean_token_accuracy": 0.15410750806331636,
|
|
"num_tokens": 8973164.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.643644666671753,
|
|
"epoch": 0.4085401038661281,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004990249901005661,
|
|
"loss": 6.5542,
|
|
"mean_token_accuracy": 0.14475183486938475,
|
|
"num_tokens": 8985981.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.619608354568482,
|
|
"epoch": 0.40911713791113674,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004990211489754527,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.15859266966581345,
|
|
"num_tokens": 8999473.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.4508928775787355,
|
|
"epoch": 0.40969417195614544,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004990173003154993,
|
|
"loss": 6.3771,
|
|
"mean_token_accuracy": 0.16602665036916733,
|
|
"num_tokens": 9010876.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.635811138153076,
|
|
"epoch": 0.4102712060011541,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004990134441208351,
|
|
"loss": 6.5016,
|
|
"mean_token_accuracy": 0.1551976703107357,
|
|
"num_tokens": 9024704.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.547682857513427,
|
|
"epoch": 0.4108482400461627,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004990095803915901,
|
|
"loss": 6.4859,
|
|
"mean_token_accuracy": 0.15543424487113952,
|
|
"num_tokens": 9037006.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.650226306915283,
|
|
"epoch": 0.41142527409117136,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004990057091278942,
|
|
"loss": 6.5471,
|
|
"mean_token_accuracy": 0.14769547432661057,
|
|
"num_tokens": 9050205.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.662499713897705,
|
|
"epoch": 0.41200230813618005,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004990018303298773,
|
|
"loss": 6.4379,
|
|
"mean_token_accuracy": 0.15080624148249627,
|
|
"num_tokens": 9062900.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.431814289093017,
|
|
"epoch": 0.4125793421811887,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989979439976703,
|
|
"loss": 6.395,
|
|
"mean_token_accuracy": 0.15929965376853944,
|
|
"num_tokens": 9074767.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.664768648147583,
|
|
"epoch": 0.41315637622619733,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989940501314037,
|
|
"loss": 6.5162,
|
|
"mean_token_accuracy": 0.15215157121419906,
|
|
"num_tokens": 9087314.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.590992450714111,
|
|
"epoch": 0.413733410271206,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004989901487312084,
|
|
"loss": 6.4838,
|
|
"mean_token_accuracy": 0.15035763382911682,
|
|
"num_tokens": 9099543.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.6410894870758055,
|
|
"epoch": 0.41431044431621467,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989862397972157,
|
|
"loss": 6.425,
|
|
"mean_token_accuracy": 0.15633125454187394,
|
|
"num_tokens": 9112262.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.4641694068908695,
|
|
"epoch": 0.4148874783612233,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004989823233295572,
|
|
"loss": 6.3407,
|
|
"mean_token_accuracy": 0.16114797592163085,
|
|
"num_tokens": 9124444.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.454566192626953,
|
|
"epoch": 0.41546451240623195,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989783993283644,
|
|
"loss": 6.4023,
|
|
"mean_token_accuracy": 0.16097055971622468,
|
|
"num_tokens": 9137848.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.589309740066528,
|
|
"epoch": 0.41604154645124064,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004989744677937694,
|
|
"loss": 6.4211,
|
|
"mean_token_accuracy": 0.15603204369544982,
|
|
"num_tokens": 9148985.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.562459945678711,
|
|
"epoch": 0.4166185804962493,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004989705287259046,
|
|
"loss": 6.4676,
|
|
"mean_token_accuracy": 0.15446533113718033,
|
|
"num_tokens": 9161313.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.5443140983581545,
|
|
"epoch": 0.4171956145412579,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004989665821249021,
|
|
"loss": 6.4517,
|
|
"mean_token_accuracy": 0.16134824752807617,
|
|
"num_tokens": 9173616.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.630168104171753,
|
|
"epoch": 0.4177726485862666,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498962627990895,
|
|
"loss": 6.5187,
|
|
"mean_token_accuracy": 0.14512302130460739,
|
|
"num_tokens": 9185951.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.5845588684082035,
|
|
"epoch": 0.41834968263127525,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004989586663240161,
|
|
"loss": 6.5113,
|
|
"mean_token_accuracy": 0.15076626762747763,
|
|
"num_tokens": 9199844.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.495019483566284,
|
|
"epoch": 0.4189267166762839,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004989546971243988,
|
|
"loss": 6.421,
|
|
"mean_token_accuracy": 0.16512578576803208,
|
|
"num_tokens": 9213034.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.572731828689575,
|
|
"epoch": 0.41950375072129253,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004989507203921763,
|
|
"loss": 6.4122,
|
|
"mean_token_accuracy": 0.1600019007921219,
|
|
"num_tokens": 9224885.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.603681850433349,
|
|
"epoch": 0.42008078476630123,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989467361274828,
|
|
"loss": 6.4817,
|
|
"mean_token_accuracy": 0.14893933087587358,
|
|
"num_tokens": 9238960.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.601598501205444,
|
|
"epoch": 0.42065781881130987,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004989427443304519,
|
|
"loss": 6.4878,
|
|
"mean_token_accuracy": 0.1529766984283924,
|
|
"num_tokens": 9253075.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.541758871078491,
|
|
"epoch": 0.4212348528563185,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000498938745001218,
|
|
"loss": 6.4409,
|
|
"mean_token_accuracy": 0.1553158700466156,
|
|
"num_tokens": 9266865.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.626510763168335,
|
|
"epoch": 0.4218118869013272,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004989347381399158,
|
|
"loss": 6.4682,
|
|
"mean_token_accuracy": 0.15190115571022034,
|
|
"num_tokens": 9278046.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.4989166259765625,
|
|
"epoch": 0.42238892094633584,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989307237466799,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.16506405919790268,
|
|
"num_tokens": 9291998.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.5267595767974855,
|
|
"epoch": 0.4229659549913445,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989267018216453,
|
|
"loss": 6.4365,
|
|
"mean_token_accuracy": 0.16413115411996843,
|
|
"num_tokens": 9305023.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.513909244537354,
|
|
"epoch": 0.4235429890363531,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989226723649473,
|
|
"loss": 6.3962,
|
|
"mean_token_accuracy": 0.15708214789628983,
|
|
"num_tokens": 9316635.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.60302848815918,
|
|
"epoch": 0.4241200230813618,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004989186353767214,
|
|
"loss": 6.4542,
|
|
"mean_token_accuracy": 0.15462954044342042,
|
|
"num_tokens": 9329671.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.509460067749023,
|
|
"epoch": 0.42469705712637046,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004989145908571035,
|
|
"loss": 6.4708,
|
|
"mean_token_accuracy": 0.14989196062088012,
|
|
"num_tokens": 9342634.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.68083233833313,
|
|
"epoch": 0.4252740911713791,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004989105388062295,
|
|
"loss": 6.4503,
|
|
"mean_token_accuracy": 0.15909998267889022,
|
|
"num_tokens": 9355096.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.558935117721558,
|
|
"epoch": 0.4258511252163878,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989064792242358,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.15320901870727538,
|
|
"num_tokens": 9367722.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.580481433868409,
|
|
"epoch": 0.42642815926139643,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989024121112589,
|
|
"loss": 6.5058,
|
|
"mean_token_accuracy": 0.14978662133216858,
|
|
"num_tokens": 9380247.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.554038381576538,
|
|
"epoch": 0.4270051933064051,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004988983374674356,
|
|
"loss": 6.3572,
|
|
"mean_token_accuracy": 0.16555936485528946,
|
|
"num_tokens": 9392216.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.588551568984985,
|
|
"epoch": 0.4275822273514137,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004988942552929029,
|
|
"loss": 6.4779,
|
|
"mean_token_accuracy": 0.1517507925629616,
|
|
"num_tokens": 9405215.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.522645664215088,
|
|
"epoch": 0.4281592613964224,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004988901655877981,
|
|
"loss": 6.4372,
|
|
"mean_token_accuracy": 0.15472906231880187,
|
|
"num_tokens": 9417582.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.53475399017334,
|
|
"epoch": 0.42873629544143105,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004988860683522589,
|
|
"loss": 6.4331,
|
|
"mean_token_accuracy": 0.1537720039486885,
|
|
"num_tokens": 9428680.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.597131443023682,
|
|
"epoch": 0.4293133294864397,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000498881963586423,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.1615703895688057,
|
|
"num_tokens": 9441669.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.50098934173584,
|
|
"epoch": 0.4298903635314484,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004988778512904282,
|
|
"loss": 6.4868,
|
|
"mean_token_accuracy": 0.15616406500339508,
|
|
"num_tokens": 9455214.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.5591755390167235,
|
|
"epoch": 0.430467397576457,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004988737314644134,
|
|
"loss": 6.4619,
|
|
"mean_token_accuracy": 0.15522471219301223,
|
|
"num_tokens": 9468180.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.5727219581604,
|
|
"epoch": 0.43104443162146566,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004988696041085168,
|
|
"loss": 6.4449,
|
|
"mean_token_accuracy": 0.16246393471956252,
|
|
"num_tokens": 9481243.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.487103366851807,
|
|
"epoch": 0.4316214656664743,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004988654692228772,
|
|
"loss": 6.3551,
|
|
"mean_token_accuracy": 0.1678798109292984,
|
|
"num_tokens": 9493511.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.497088432312012,
|
|
"epoch": 0.432198499711483,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004988613268076335,
|
|
"loss": 6.4093,
|
|
"mean_token_accuracy": 0.1654896542429924,
|
|
"num_tokens": 9505450.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.585122728347779,
|
|
"epoch": 0.43277553375649164,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988571768629257,
|
|
"loss": 6.4596,
|
|
"mean_token_accuracy": 0.1581433355808258,
|
|
"num_tokens": 9518684.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.498142337799072,
|
|
"epoch": 0.4333525678015003,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004988530193888927,
|
|
"loss": 6.4145,
|
|
"mean_token_accuracy": 0.15784785747528077,
|
|
"num_tokens": 9532064.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.487857294082642,
|
|
"epoch": 0.4339296018465089,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988488543856747,
|
|
"loss": 6.3626,
|
|
"mean_token_accuracy": 0.1681128889322281,
|
|
"num_tokens": 9543810.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.606877851486206,
|
|
"epoch": 0.4345066358915176,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004988446818534115,
|
|
"loss": 6.5149,
|
|
"mean_token_accuracy": 0.14516288191080093,
|
|
"num_tokens": 9556261.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.537605476379395,
|
|
"epoch": 0.43508366993652625,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004988405017922438,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.16130636185407637,
|
|
"num_tokens": 9569627.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.5598901271820065,
|
|
"epoch": 0.4356607039815349,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000498836314202312,
|
|
"loss": 6.4565,
|
|
"mean_token_accuracy": 0.1545551188290119,
|
|
"num_tokens": 9582263.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.507501220703125,
|
|
"epoch": 0.4362377380265436,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988321190837568,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.16725715696811677,
|
|
"num_tokens": 9594282.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.494114971160888,
|
|
"epoch": 0.4368147720715522,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004988279164367196,
|
|
"loss": 6.3586,
|
|
"mean_token_accuracy": 0.16182285398244858,
|
|
"num_tokens": 9607159.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.535694646835327,
|
|
"epoch": 0.43739180611656087,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004988237062613415,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.16683767586946488,
|
|
"num_tokens": 9619221.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.552090501785278,
|
|
"epoch": 0.4379688401615695,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988194885577644,
|
|
"loss": 6.4308,
|
|
"mean_token_accuracy": 0.15698195844888688,
|
|
"num_tokens": 9631956.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.558296966552734,
|
|
"epoch": 0.4385458742065782,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004988152633261299,
|
|
"loss": 6.4351,
|
|
"mean_token_accuracy": 0.1557241663336754,
|
|
"num_tokens": 9643557.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.54206166267395,
|
|
"epoch": 0.43912290825158684,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00049881103056658,
|
|
"loss": 6.397,
|
|
"mean_token_accuracy": 0.15948179066181184,
|
|
"num_tokens": 9655422.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.583641576766968,
|
|
"epoch": 0.4396999422965955,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004988067902792575,
|
|
"loss": 6.4727,
|
|
"mean_token_accuracy": 0.15186914056539536,
|
|
"num_tokens": 9669522.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.567377662658691,
|
|
"epoch": 0.4402769763416042,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988025424643047,
|
|
"loss": 6.4853,
|
|
"mean_token_accuracy": 0.15547452867031097,
|
|
"num_tokens": 9681301.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.49556827545166,
|
|
"epoch": 0.4408540103866128,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004987982871218645,
|
|
"loss": 6.4058,
|
|
"mean_token_accuracy": 0.15341770350933076,
|
|
"num_tokens": 9693894.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.581149435043335,
|
|
"epoch": 0.44143104443162146,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004987940242520802,
|
|
"loss": 6.503,
|
|
"mean_token_accuracy": 0.14905156195163727,
|
|
"num_tokens": 9706499.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.495326089859009,
|
|
"epoch": 0.4420080784766301,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498789753855095,
|
|
"loss": 6.3531,
|
|
"mean_token_accuracy": 0.16193671226501466,
|
|
"num_tokens": 9718632.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.544300889968872,
|
|
"epoch": 0.4425851125216388,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004987854759310526,
|
|
"loss": 6.4331,
|
|
"mean_token_accuracy": 0.15969545245170594,
|
|
"num_tokens": 9730451.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.594881200790406,
|
|
"epoch": 0.44316214656664743,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004987811904800968,
|
|
"loss": 6.4535,
|
|
"mean_token_accuracy": 0.15569856613874436,
|
|
"num_tokens": 9742693.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.533166885375977,
|
|
"epoch": 0.44373918061165607,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987768975023719,
|
|
"loss": 6.4415,
|
|
"mean_token_accuracy": 0.15766530483961105,
|
|
"num_tokens": 9755642.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.5512227535247805,
|
|
"epoch": 0.44431621465666477,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004987725969980222,
|
|
"loss": 6.4597,
|
|
"mean_token_accuracy": 0.1554524153470993,
|
|
"num_tokens": 9767674.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.490002059936524,
|
|
"epoch": 0.4448932487016734,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004987682889671923,
|
|
"loss": 6.3795,
|
|
"mean_token_accuracy": 0.16682353913784026,
|
|
"num_tokens": 9781018.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.5620664119720455,
|
|
"epoch": 0.44547028274668204,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004987639734100272,
|
|
"loss": 6.4492,
|
|
"mean_token_accuracy": 0.1582857385277748,
|
|
"num_tokens": 9792521.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.507644081115723,
|
|
"epoch": 0.4460473167916907,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004987596503266721,
|
|
"loss": 6.4171,
|
|
"mean_token_accuracy": 0.1616949424147606,
|
|
"num_tokens": 9805356.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.488741016387939,
|
|
"epoch": 0.4466243508366994,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004987553197172722,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.16268157660961152,
|
|
"num_tokens": 9818779.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.604960584640503,
|
|
"epoch": 0.447201384881708,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004987509815819732,
|
|
"loss": 6.4664,
|
|
"mean_token_accuracy": 0.1494177907705307,
|
|
"num_tokens": 9832328.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.522948360443115,
|
|
"epoch": 0.44777841892671666,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004987466359209213,
|
|
"loss": 6.4074,
|
|
"mean_token_accuracy": 0.1558647111058235,
|
|
"num_tokens": 9846281.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.517709732055664,
|
|
"epoch": 0.44835545297172535,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004987422827342622,
|
|
"loss": 6.4635,
|
|
"mean_token_accuracy": 0.1561240956187248,
|
|
"num_tokens": 9858737.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.549286508560181,
|
|
"epoch": 0.448932487016734,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004987379220221426,
|
|
"loss": 6.4766,
|
|
"mean_token_accuracy": 0.15599623322486877,
|
|
"num_tokens": 9872852.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.555766773223877,
|
|
"epoch": 0.44950952106174263,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004987335537847092,
|
|
"loss": 6.3896,
|
|
"mean_token_accuracy": 0.1689491853117943,
|
|
"num_tokens": 9886339.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.620915508270263,
|
|
"epoch": 0.4500865551067513,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987291780221088,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.15587402284145355,
|
|
"num_tokens": 9897525.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.461075353622436,
|
|
"epoch": 0.45066358915175997,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004987247947344887,
|
|
"loss": 6.4155,
|
|
"mean_token_accuracy": 0.16414239704608918,
|
|
"num_tokens": 9909733.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.5133524417877195,
|
|
"epoch": 0.4512406231967686,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004987204039219962,
|
|
"loss": 6.4003,
|
|
"mean_token_accuracy": 0.1509241595864296,
|
|
"num_tokens": 9922503.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.562454795837402,
|
|
"epoch": 0.45181765724177725,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987160055847791,
|
|
"loss": 6.4361,
|
|
"mean_token_accuracy": 0.15687647461891174,
|
|
"num_tokens": 9935517.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.568414878845215,
|
|
"epoch": 0.45239469128678594,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004987115997229852,
|
|
"loss": 6.4902,
|
|
"mean_token_accuracy": 0.15789610743522645,
|
|
"num_tokens": 9947663.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.452044486999512,
|
|
"epoch": 0.4529717253317946,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004987071863367629,
|
|
"loss": 6.2627,
|
|
"mean_token_accuracy": 0.1615383207798004,
|
|
"num_tokens": 9960924.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.513233327865601,
|
|
"epoch": 0.4535487593768032,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004987027654262604,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.15682899057865143,
|
|
"num_tokens": 9973506.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.468669366836548,
|
|
"epoch": 0.45412579342181186,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004986983369916264,
|
|
"loss": 6.3917,
|
|
"mean_token_accuracy": 0.16661963611841202,
|
|
"num_tokens": 9988334.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.605206775665283,
|
|
"epoch": 0.45470282746682056,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004986939010330102,
|
|
"loss": 6.4731,
|
|
"mean_token_accuracy": 0.15531497150659562,
|
|
"num_tokens": 10001295.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.533522653579712,
|
|
"epoch": 0.4552798615118292,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986894575505606,
|
|
"loss": 6.3616,
|
|
"mean_token_accuracy": 0.15742329508066177,
|
|
"num_tokens": 10012396.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.534685850143433,
|
|
"epoch": 0.45585689555683784,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004986850065444272,
|
|
"loss": 6.4301,
|
|
"mean_token_accuracy": 0.16010557413101195,
|
|
"num_tokens": 10025918.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.627367115020752,
|
|
"epoch": 0.45643392960184653,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004986805480147598,
|
|
"loss": 6.4338,
|
|
"mean_token_accuracy": 0.15506452023983003,
|
|
"num_tokens": 10038674.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.467591571807861,
|
|
"epoch": 0.4570109636468552,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004986760819617082,
|
|
"loss": 6.3963,
|
|
"mean_token_accuracy": 0.162594798207283,
|
|
"num_tokens": 10051623.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.561280107498169,
|
|
"epoch": 0.4575879976918638,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004986716083854228,
|
|
"loss": 6.4667,
|
|
"mean_token_accuracy": 0.15451734513044357,
|
|
"num_tokens": 10063731.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.623692226409912,
|
|
"epoch": 0.45816503173687245,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004986671272860538,
|
|
"loss": 6.4732,
|
|
"mean_token_accuracy": 0.15955658853054047,
|
|
"num_tokens": 10075897.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.495250701904297,
|
|
"epoch": 0.45874206578188115,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004986626386637521,
|
|
"loss": 6.4207,
|
|
"mean_token_accuracy": 0.1547025889158249,
|
|
"num_tokens": 10088605.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.545332717895508,
|
|
"epoch": 0.4593190998268898,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004986581425186688,
|
|
"loss": 6.4034,
|
|
"mean_token_accuracy": 0.16402129381895064,
|
|
"num_tokens": 10101758.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.557800436019898,
|
|
"epoch": 0.4598961338718984,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986536388509548,
|
|
"loss": 6.4477,
|
|
"mean_token_accuracy": 0.15040433257818223,
|
|
"num_tokens": 10113838.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.48162088394165,
|
|
"epoch": 0.4604731679169071,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004986491276607618,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.1552007108926773,
|
|
"num_tokens": 10127676.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.502557945251465,
|
|
"epoch": 0.46105020196191576,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004986446089482416,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.1574241816997528,
|
|
"num_tokens": 10139734.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.540197706222534,
|
|
"epoch": 0.4616272360069244,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004986400827135459,
|
|
"loss": 6.452,
|
|
"mean_token_accuracy": 0.15818918943405152,
|
|
"num_tokens": 10151842.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.5954841613769535,
|
|
"epoch": 0.46220427005193304,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004986355489568272,
|
|
"loss": 6.4817,
|
|
"mean_token_accuracy": 0.15511930286884307,
|
|
"num_tokens": 10163539.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.532063102722168,
|
|
"epoch": 0.46278130409694174,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004986310076782379,
|
|
"loss": 6.4467,
|
|
"mean_token_accuracy": 0.15533970296382904,
|
|
"num_tokens": 10174760.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.498932600021362,
|
|
"epoch": 0.4633583381419504,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004986264588779307,
|
|
"loss": 6.4642,
|
|
"mean_token_accuracy": 0.15401545017957688,
|
|
"num_tokens": 10186627.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.647648715972901,
|
|
"epoch": 0.463935372186959,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004986219025560586,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.1703260600566864,
|
|
"num_tokens": 10200084.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.472187328338623,
|
|
"epoch": 0.4645124062319677,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000498617338712775,
|
|
"loss": 6.4214,
|
|
"mean_token_accuracy": 0.16182194352149964,
|
|
"num_tokens": 10212121.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.5356916904449465,
|
|
"epoch": 0.46508944027697635,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986127673482332,
|
|
"loss": 6.4148,
|
|
"mean_token_accuracy": 0.16143590807914734,
|
|
"num_tokens": 10225138.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.6138585090637205,
|
|
"epoch": 0.465666474321985,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004986081884625871,
|
|
"loss": 6.4351,
|
|
"mean_token_accuracy": 0.1563952624797821,
|
|
"num_tokens": 10238309.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.528492736816406,
|
|
"epoch": 0.46624350836699363,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986036020559906,
|
|
"loss": 6.4045,
|
|
"mean_token_accuracy": 0.15613240748643875,
|
|
"num_tokens": 10251405.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.525904607772827,
|
|
"epoch": 0.4668205424120023,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000498599008128598,
|
|
"loss": 6.3588,
|
|
"mean_token_accuracy": 0.1662200689315796,
|
|
"num_tokens": 10262870.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.4476752281188965,
|
|
"epoch": 0.46739757645701097,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985944066805639,
|
|
"loss": 6.4183,
|
|
"mean_token_accuracy": 0.15107485949993132,
|
|
"num_tokens": 10274283.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.554322624206543,
|
|
"epoch": 0.4679746105020196,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000498589797712043,
|
|
"loss": 6.4333,
|
|
"mean_token_accuracy": 0.15794023424386977,
|
|
"num_tokens": 10287581.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.595016288757324,
|
|
"epoch": 0.4685516445470283,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004985851812231903,
|
|
"loss": 6.3567,
|
|
"mean_token_accuracy": 0.16236607283353804,
|
|
"num_tokens": 10299654.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.4879011631011965,
|
|
"epoch": 0.46912867859203694,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004985805572141611,
|
|
"loss": 6.4447,
|
|
"mean_token_accuracy": 0.15488010570406913,
|
|
"num_tokens": 10312323.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.54975700378418,
|
|
"epoch": 0.4697057126370456,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004985759256851108,
|
|
"loss": 6.2925,
|
|
"mean_token_accuracy": 0.16682098954916,
|
|
"num_tokens": 10325078.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.481452751159668,
|
|
"epoch": 0.4702827466820542,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004985712866361954,
|
|
"loss": 6.4389,
|
|
"mean_token_accuracy": 0.15707961320877076,
|
|
"num_tokens": 10339938.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.5055419445037845,
|
|
"epoch": 0.4708597807270629,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985666400675709,
|
|
"loss": 6.4518,
|
|
"mean_token_accuracy": 0.1565823420882225,
|
|
"num_tokens": 10352024.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.502655839920044,
|
|
"epoch": 0.47143681477207156,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004985619859793934,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.17177620381116868,
|
|
"num_tokens": 10365919.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.411081266403198,
|
|
"epoch": 0.4720138488170802,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985573243718195,
|
|
"loss": 6.3393,
|
|
"mean_token_accuracy": 0.1644672930240631,
|
|
"num_tokens": 10377488.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.475267219543457,
|
|
"epoch": 0.4725908828620889,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004985526552450061,
|
|
"loss": 6.3579,
|
|
"mean_token_accuracy": 0.16348247230052948,
|
|
"num_tokens": 10391187.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.440578937530518,
|
|
"epoch": 0.47316791690709753,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985479785991103,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.16505655497312546,
|
|
"num_tokens": 10403458.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.575636100769043,
|
|
"epoch": 0.47374495095210617,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004985432944342892,
|
|
"loss": 6.5123,
|
|
"mean_token_accuracy": 0.14661003053188323,
|
|
"num_tokens": 10416533.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.5452169418334964,
|
|
"epoch": 0.4743219849971148,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985386027507003,
|
|
"loss": 6.3576,
|
|
"mean_token_accuracy": 0.1599026843905449,
|
|
"num_tokens": 10429593.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.452538537979126,
|
|
"epoch": 0.4748990190421235,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004985339035485018,
|
|
"loss": 6.3891,
|
|
"mean_token_accuracy": 0.16478680968284606,
|
|
"num_tokens": 10440520.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.481285953521729,
|
|
"epoch": 0.47547605308713214,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004985291968278513,
|
|
"loss": 6.4028,
|
|
"mean_token_accuracy": 0.1564889907836914,
|
|
"num_tokens": 10453971.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.454246282577515,
|
|
"epoch": 0.4760530871321408,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004985244825889074,
|
|
"loss": 6.393,
|
|
"mean_token_accuracy": 0.1587365560233593,
|
|
"num_tokens": 10466033.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.5247338771820065,
|
|
"epoch": 0.4766301211771495,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004985197608318284,
|
|
"loss": 6.3609,
|
|
"mean_token_accuracy": 0.1652022197842598,
|
|
"num_tokens": 10478608.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.537705278396606,
|
|
"epoch": 0.4772071552221581,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985150315567735,
|
|
"loss": 6.4645,
|
|
"mean_token_accuracy": 0.16325337141752244,
|
|
"num_tokens": 10491223.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.584768152236938,
|
|
"epoch": 0.47778418926716676,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004985102947639013,
|
|
"loss": 6.506,
|
|
"mean_token_accuracy": 0.15094189196825028,
|
|
"num_tokens": 10504398.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.512157869338989,
|
|
"epoch": 0.4783612233121754,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004985055504533715,
|
|
"loss": 6.3349,
|
|
"mean_token_accuracy": 0.16145680993795394,
|
|
"num_tokens": 10516998.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.511150979995728,
|
|
"epoch": 0.4789382573571841,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985007986253435,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.15873684138059616,
|
|
"num_tokens": 10529632.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.396101284027099,
|
|
"epoch": 0.47951529140219273,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004984960392799772,
|
|
"loss": 6.3296,
|
|
"mean_token_accuracy": 0.16098663210868835,
|
|
"num_tokens": 10542479.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.440076684951782,
|
|
"epoch": 0.4800923254472014,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984912724174326,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.17203231304883956,
|
|
"num_tokens": 10555322.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.5678126335144045,
|
|
"epoch": 0.48066935949221,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004984864980378701,
|
|
"loss": 6.4139,
|
|
"mean_token_accuracy": 0.15598823130130768,
|
|
"num_tokens": 10567757.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.547306394577026,
|
|
"epoch": 0.4812463935372187,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004984817161414502,
|
|
"loss": 6.4422,
|
|
"mean_token_accuracy": 0.14962815642356872,
|
|
"num_tokens": 10580820.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.538690710067749,
|
|
"epoch": 0.48182342758222735,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004984769267283338,
|
|
"loss": 6.4479,
|
|
"mean_token_accuracy": 0.15779006332159043,
|
|
"num_tokens": 10595690.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.494137716293335,
|
|
"epoch": 0.482400461627236,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004984721297986819,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.15723106414079666,
|
|
"num_tokens": 10608393.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.548528623580933,
|
|
"epoch": 0.4829774956722447,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004984673253526561,
|
|
"loss": 6.4367,
|
|
"mean_token_accuracy": 0.15608918517827988,
|
|
"num_tokens": 10621073.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.442586946487427,
|
|
"epoch": 0.4835545297172533,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004984625133904176,
|
|
"loss": 6.3089,
|
|
"mean_token_accuracy": 0.1682225674390793,
|
|
"num_tokens": 10633945.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.481200122833252,
|
|
"epoch": 0.48413156376226196,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984576939121286,
|
|
"loss": 6.4348,
|
|
"mean_token_accuracy": 0.15343092679977416,
|
|
"num_tokens": 10645727.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.521467208862305,
|
|
"epoch": 0.4847085978072706,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984528669179511,
|
|
"loss": 6.291,
|
|
"mean_token_accuracy": 0.1592160165309906,
|
|
"num_tokens": 10658488.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.476761770248413,
|
|
"epoch": 0.4852856318522793,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004984480324080472,
|
|
"loss": 6.3897,
|
|
"mean_token_accuracy": 0.15781337171792983,
|
|
"num_tokens": 10671361.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.494213676452636,
|
|
"epoch": 0.48586266589728794,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049844319038258,
|
|
"loss": 6.3209,
|
|
"mean_token_accuracy": 0.1734808161854744,
|
|
"num_tokens": 10684825.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.475206899642944,
|
|
"epoch": 0.4864396999422966,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004984383408417119,
|
|
"loss": 6.4307,
|
|
"mean_token_accuracy": 0.1594849243760109,
|
|
"num_tokens": 10698627.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.523198556900025,
|
|
"epoch": 0.4870167339873053,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004984334837856064,
|
|
"loss": 6.3561,
|
|
"mean_token_accuracy": 0.15792025476694108,
|
|
"num_tokens": 10712124.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.516054153442383,
|
|
"epoch": 0.4875937680323139,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004984286192144263,
|
|
"loss": 6.393,
|
|
"mean_token_accuracy": 0.15413977801799775,
|
|
"num_tokens": 10723939.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.508268594741821,
|
|
"epoch": 0.48817080207732255,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004984237471283359,
|
|
"loss": 6.3928,
|
|
"mean_token_accuracy": 0.1572265714406967,
|
|
"num_tokens": 10736795.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.4552051544189455,
|
|
"epoch": 0.4887478361223312,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984188675274986,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.16994941532611846,
|
|
"num_tokens": 10749905.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.466286897659302,
|
|
"epoch": 0.4893248701673399,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004984139804120787,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.15417940616607667,
|
|
"num_tokens": 10761852.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.501400518417358,
|
|
"epoch": 0.4899019042123485,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004984090857822406,
|
|
"loss": 6.3811,
|
|
"mean_token_accuracy": 0.16262035071849823,
|
|
"num_tokens": 10774673.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.462345552444458,
|
|
"epoch": 0.49047893825735717,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004984041836381488,
|
|
"loss": 6.3484,
|
|
"mean_token_accuracy": 0.1620374873280525,
|
|
"num_tokens": 10786892.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.481334590911866,
|
|
"epoch": 0.49105597230236586,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004983992739799682,
|
|
"loss": 6.3739,
|
|
"mean_token_accuracy": 0.1637142077088356,
|
|
"num_tokens": 10798846.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.4820136547088625,
|
|
"epoch": 0.4916330063473745,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004983943568078642,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.16547314524650575,
|
|
"num_tokens": 10811893.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.472692060470581,
|
|
"epoch": 0.49221004039238314,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004983894321220017,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.16635758727788924,
|
|
"num_tokens": 10825595.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.431785249710083,
|
|
"epoch": 0.4927870744373918,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004983844999225468,
|
|
"loss": 6.3143,
|
|
"mean_token_accuracy": 0.17111872732639313,
|
|
"num_tokens": 10837546.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.51116623878479,
|
|
"epoch": 0.4933641084824005,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004983795602096651,
|
|
"loss": 6.4218,
|
|
"mean_token_accuracy": 0.15393567085266113,
|
|
"num_tokens": 10851234.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.4908205509185795,
|
|
"epoch": 0.4939411425274091,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498374612983523,
|
|
"loss": 6.375,
|
|
"mean_token_accuracy": 0.1528395116329193,
|
|
"num_tokens": 10864397.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.514799118041992,
|
|
"epoch": 0.49451817657241776,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983696582442866,
|
|
"loss": 6.3765,
|
|
"mean_token_accuracy": 0.15875952392816545,
|
|
"num_tokens": 10877230.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.470470523834228,
|
|
"epoch": 0.49509521061742645,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004983646959921227,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.1599888324737549,
|
|
"num_tokens": 10890847.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.440327835083008,
|
|
"epoch": 0.4956722446624351,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004983597262271984,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.16640594899654387,
|
|
"num_tokens": 10903488.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.5825787544250485,
|
|
"epoch": 0.49624927870744373,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004983547489496804,
|
|
"loss": 6.3807,
|
|
"mean_token_accuracy": 0.15209589451551436,
|
|
"num_tokens": 10914744.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.49207763671875,
|
|
"epoch": 0.49682631275245237,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004983497641597365,
|
|
"loss": 6.3837,
|
|
"mean_token_accuracy": 0.15209848284721375,
|
|
"num_tokens": 10928307.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.510096883773803,
|
|
"epoch": 0.49740334679746107,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004983447718575342,
|
|
"loss": 6.4199,
|
|
"mean_token_accuracy": 0.15832170844078064,
|
|
"num_tokens": 10939876.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.479329204559326,
|
|
"epoch": 0.4979803808424697,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004983397720432414,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.16492047309875488,
|
|
"num_tokens": 10952123.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.4766120433807375,
|
|
"epoch": 0.49855741488747835,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004983347647170264,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.15579510778188704,
|
|
"num_tokens": 10967374.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.49477186203003,
|
|
"epoch": 0.49913444893248704,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004983297498790574,
|
|
"loss": 6.4387,
|
|
"mean_token_accuracy": 0.15156637281179428,
|
|
"num_tokens": 10980761.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.530684614181519,
|
|
"epoch": 0.4997114829774957,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004983247275295034,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.15633219629526138,
|
|
"num_tokens": 10994538.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.51979341506958,
|
|
"epoch": 0.5002885170225043,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004983196976685329,
|
|
"loss": 6.4175,
|
|
"mean_token_accuracy": 0.1540020525455475,
|
|
"num_tokens": 11006956.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.479969930648804,
|
|
"epoch": 0.500865551067513,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983146602963155,
|
|
"loss": 6.3815,
|
|
"mean_token_accuracy": 0.16485208570957183,
|
|
"num_tokens": 11019202.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.568608665466309,
|
|
"epoch": 0.5014425851125216,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004983096154130203,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.16060912609100342,
|
|
"num_tokens": 11031560.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.526084327697754,
|
|
"epoch": 0.5020196191575302,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983045630188171,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.15379957109689713,
|
|
"num_tokens": 11044537.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.451754522323609,
|
|
"epoch": 0.502596653202539,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004982995031138759,
|
|
"loss": 6.3001,
|
|
"mean_token_accuracy": 0.1613658294081688,
|
|
"num_tokens": 11056642.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.453772687911988,
|
|
"epoch": 0.5031736872475476,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004982944356983666,
|
|
"loss": 6.2954,
|
|
"mean_token_accuracy": 0.16220536679029465,
|
|
"num_tokens": 11068642.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.558634853363037,
|
|
"epoch": 0.5037507212925563,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004982893607724602,
|
|
"loss": 6.5895,
|
|
"mean_token_accuracy": 0.15590605288743972,
|
|
"num_tokens": 11082056.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.497712707519531,
|
|
"epoch": 0.5043277553375649,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000498284278336327,
|
|
"loss": 6.3903,
|
|
"mean_token_accuracy": 0.15248484015464783,
|
|
"num_tokens": 11093722.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.525355005264283,
|
|
"epoch": 0.5049047893825735,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982791883901379,
|
|
"loss": 6.3873,
|
|
"mean_token_accuracy": 0.1526179663836956,
|
|
"num_tokens": 11105949.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.4398966312408445,
|
|
"epoch": 0.5054818234275822,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982740909340643,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.16731281131505965,
|
|
"num_tokens": 11118074.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.574570846557617,
|
|
"epoch": 0.5060588574725908,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004982689859682775,
|
|
"loss": 6.3591,
|
|
"mean_token_accuracy": 0.15872727185487748,
|
|
"num_tokens": 11130917.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.454862403869629,
|
|
"epoch": 0.5066358915175996,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004982638734929492,
|
|
"loss": 6.3971,
|
|
"mean_token_accuracy": 0.16015870422124862,
|
|
"num_tokens": 11142829.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.4587291240692135,
|
|
"epoch": 0.5072129255626082,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982587535082515,
|
|
"loss": 6.356,
|
|
"mean_token_accuracy": 0.16462198942899703,
|
|
"num_tokens": 11154606.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.567020273208618,
|
|
"epoch": 0.5077899596076169,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004982536260143565,
|
|
"loss": 6.3357,
|
|
"mean_token_accuracy": 0.15825513154268264,
|
|
"num_tokens": 11167160.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.403166437149048,
|
|
"epoch": 0.5083669936526255,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004982484910114367,
|
|
"loss": 6.3295,
|
|
"mean_token_accuracy": 0.16778065413236617,
|
|
"num_tokens": 11178813.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.381605005264282,
|
|
"epoch": 0.5089440276976341,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004982433484996648,
|
|
"loss": 6.2923,
|
|
"mean_token_accuracy": 0.162590828537941,
|
|
"num_tokens": 11192648.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.628140115737915,
|
|
"epoch": 0.5095210617426428,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004982381984792138,
|
|
"loss": 6.393,
|
|
"mean_token_accuracy": 0.15693947672843933,
|
|
"num_tokens": 11205519.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.461419773101807,
|
|
"epoch": 0.5100980957876514,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004982330409502568,
|
|
"loss": 6.3921,
|
|
"mean_token_accuracy": 0.15413278788328172,
|
|
"num_tokens": 11218362.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.442616987228393,
|
|
"epoch": 0.5106751298326602,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004982278759129674,
|
|
"loss": 6.3803,
|
|
"mean_token_accuracy": 0.15451293140649797,
|
|
"num_tokens": 11231821.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.557499504089355,
|
|
"epoch": 0.5112521638776688,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004982227033675194,
|
|
"loss": 6.422,
|
|
"mean_token_accuracy": 0.15312207788228988,
|
|
"num_tokens": 11246300.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.465668153762818,
|
|
"epoch": 0.5118291979226774,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004982175233140865,
|
|
"loss": 6.3175,
|
|
"mean_token_accuracy": 0.1643589124083519,
|
|
"num_tokens": 11258561.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.531848382949829,
|
|
"epoch": 0.5124062319676861,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004982123357528431,
|
|
"loss": 6.3149,
|
|
"mean_token_accuracy": 0.1639846608042717,
|
|
"num_tokens": 11271719.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.302284049987793,
|
|
"epoch": 0.5129832660126947,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004982071406839636,
|
|
"loss": 6.3153,
|
|
"mean_token_accuracy": 0.16485968083143235,
|
|
"num_tokens": 11284166.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.476738452911377,
|
|
"epoch": 0.5135603000577034,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004982019381076229,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.15987009257078172,
|
|
"num_tokens": 11296140.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.515838384628296,
|
|
"epoch": 0.514137334102712,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004981967280239958,
|
|
"loss": 6.392,
|
|
"mean_token_accuracy": 0.1580490365624428,
|
|
"num_tokens": 11308680.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.520589065551758,
|
|
"epoch": 0.5147143681477208,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004981915104332578,
|
|
"loss": 6.3734,
|
|
"mean_token_accuracy": 0.15471306443214417,
|
|
"num_tokens": 11320887.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.518787240982055,
|
|
"epoch": 0.5152914021927294,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498186285335584,
|
|
"loss": 6.3706,
|
|
"mean_token_accuracy": 0.15980480164289473,
|
|
"num_tokens": 11333873.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.5042322158813475,
|
|
"epoch": 0.515868436237738,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004981810527311505,
|
|
"loss": 6.4526,
|
|
"mean_token_accuracy": 0.15650095790624619,
|
|
"num_tokens": 11345526.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.537562704086303,
|
|
"epoch": 0.5164454702827467,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000498175812620133,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.15564233660697938,
|
|
"num_tokens": 11356840.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.456150674819947,
|
|
"epoch": 0.5170225043277553,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981705650027081,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.15510667115449905,
|
|
"num_tokens": 11369146.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.471530199050903,
|
|
"epoch": 0.517599538372764,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000498165309879052,
|
|
"loss": 6.351,
|
|
"mean_token_accuracy": 0.16200470179319382,
|
|
"num_tokens": 11382399.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.437090301513672,
|
|
"epoch": 0.5181765724177726,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004981600472493415,
|
|
"loss": 6.2501,
|
|
"mean_token_accuracy": 0.16678088307380676,
|
|
"num_tokens": 11395602.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.418407583236695,
|
|
"epoch": 0.5187536064627813,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981547771137537,
|
|
"loss": 6.3489,
|
|
"mean_token_accuracy": 0.16000750213861464,
|
|
"num_tokens": 11408530.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.519910526275635,
|
|
"epoch": 0.51933064050779,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004981494994724658,
|
|
"loss": 6.3563,
|
|
"mean_token_accuracy": 0.16234227418899536,
|
|
"num_tokens": 11420150.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.446649980545044,
|
|
"epoch": 0.5199076745527986,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004981442143256554,
|
|
"loss": 6.3945,
|
|
"mean_token_accuracy": 0.15244318544864655,
|
|
"num_tokens": 11432318.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.507375001907349,
|
|
"epoch": 0.5204847085978073,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004981389216735001,
|
|
"loss": 6.4357,
|
|
"mean_token_accuracy": 0.1586089849472046,
|
|
"num_tokens": 11444143.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.438950109481811,
|
|
"epoch": 0.5210617426428159,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000498133621516178,
|
|
"loss": 6.33,
|
|
"mean_token_accuracy": 0.16003450751304626,
|
|
"num_tokens": 11455997.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.510848474502564,
|
|
"epoch": 0.5216387766878245,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004981283138538675,
|
|
"loss": 6.4088,
|
|
"mean_token_accuracy": 0.15459372103214264,
|
|
"num_tokens": 11468271.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.529215717315674,
|
|
"epoch": 0.5222158107328332,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000498122998686747,
|
|
"loss": 6.3398,
|
|
"mean_token_accuracy": 0.15672484934329986,
|
|
"num_tokens": 11479729.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.391436529159546,
|
|
"epoch": 0.5227928447778419,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004981176760149951,
|
|
"loss": 6.2739,
|
|
"mean_token_accuracy": 0.1627101868391037,
|
|
"num_tokens": 11492261.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.450825357437134,
|
|
"epoch": 0.5233698788228506,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004981123458387911,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.1585073545575142,
|
|
"num_tokens": 11504802.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.528818082809448,
|
|
"epoch": 0.5239469128678592,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004981070081583142,
|
|
"loss": 6.3564,
|
|
"mean_token_accuracy": 0.1574664145708084,
|
|
"num_tokens": 11518105.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.427476978302002,
|
|
"epoch": 0.5245239469128679,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000498101662973744,
|
|
"loss": 6.3377,
|
|
"mean_token_accuracy": 0.15979625582695006,
|
|
"num_tokens": 11532085.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.439642763137817,
|
|
"epoch": 0.5251009809578765,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.00049809631028526,
|
|
"loss": 6.2873,
|
|
"mean_token_accuracy": 0.16680559366941453,
|
|
"num_tokens": 11544328.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.438679456710815,
|
|
"epoch": 0.5256780150028851,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004980909500930424,
|
|
"loss": 6.3784,
|
|
"mean_token_accuracy": 0.1642422378063202,
|
|
"num_tokens": 11556496.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.560665273666382,
|
|
"epoch": 0.5262550490478938,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004980855823972717,
|
|
"loss": 6.4115,
|
|
"mean_token_accuracy": 0.1573752909898758,
|
|
"num_tokens": 11569330.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.473380136489868,
|
|
"epoch": 0.5268320830929025,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000498080207198128,
|
|
"loss": 6.3165,
|
|
"mean_token_accuracy": 0.16247887313365936,
|
|
"num_tokens": 11581335.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.4558507919311525,
|
|
"epoch": 0.5274091171379112,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004980748244957925,
|
|
"loss": 6.2877,
|
|
"mean_token_accuracy": 0.16184458136558533,
|
|
"num_tokens": 11593130.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.335966634750366,
|
|
"epoch": 0.5279861511829198,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004980694342904461,
|
|
"loss": 6.3012,
|
|
"mean_token_accuracy": 0.16489815562963486,
|
|
"num_tokens": 11605140.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.467780017852784,
|
|
"epoch": 0.5285631852279284,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004980640365822701,
|
|
"loss": 6.3236,
|
|
"mean_token_accuracy": 0.15909543633460999,
|
|
"num_tokens": 11617361.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.439427661895752,
|
|
"epoch": 0.5291402192729371,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498058631371446,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.16430423706769942,
|
|
"num_tokens": 11630780.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.3723077297210695,
|
|
"epoch": 0.5297172533179457,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004980532186581555,
|
|
"loss": 6.2942,
|
|
"mean_token_accuracy": 0.16157945692539216,
|
|
"num_tokens": 11643120.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.509933567047119,
|
|
"epoch": 0.5302942873629544,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000498047798442581,
|
|
"loss": 6.3214,
|
|
"mean_token_accuracy": 0.16044917702674866,
|
|
"num_tokens": 11655849.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.421504974365234,
|
|
"epoch": 0.5308713214079631,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004980423707249044,
|
|
"loss": 6.324,
|
|
"mean_token_accuracy": 0.15950872004032135,
|
|
"num_tokens": 11669072.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.4032351016998295,
|
|
"epoch": 0.5314483554529718,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004980369355053086,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.16826080530881882,
|
|
"num_tokens": 11680253.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.482820701599121,
|
|
"epoch": 0.5320253894979804,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004980314927839763,
|
|
"loss": 6.2559,
|
|
"mean_token_accuracy": 0.15586785078048707,
|
|
"num_tokens": 11691465.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.44303879737854,
|
|
"epoch": 0.532602423542989,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004980260425610903,
|
|
"loss": 6.394,
|
|
"mean_token_accuracy": 0.16090328097343445,
|
|
"num_tokens": 11703679.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.469963407516479,
|
|
"epoch": 0.5331794575879977,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004980205848368343,
|
|
"loss": 6.3535,
|
|
"mean_token_accuracy": 0.1571087807416916,
|
|
"num_tokens": 11716204.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.517374849319458,
|
|
"epoch": 0.5337564916330063,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004980151196113917,
|
|
"loss": 6.339,
|
|
"mean_token_accuracy": 0.16261640936136246,
|
|
"num_tokens": 11728404.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.387979793548584,
|
|
"epoch": 0.534333525678015,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004980096468849464,
|
|
"loss": 6.2656,
|
|
"mean_token_accuracy": 0.160543355345726,
|
|
"num_tokens": 11740170.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.368899822235107,
|
|
"epoch": 0.5349105597230237,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004980041666576823,
|
|
"loss": 6.2578,
|
|
"mean_token_accuracy": 0.16634061187505722,
|
|
"num_tokens": 11753062.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.433922815322876,
|
|
"epoch": 0.5354875937680323,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004979986789297837,
|
|
"loss": 6.2715,
|
|
"mean_token_accuracy": 0.16562960147857667,
|
|
"num_tokens": 11765588.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.465123987197876,
|
|
"epoch": 0.536064627813041,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979931837014355,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.16014475971460343,
|
|
"num_tokens": 11777358.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.529675102233886,
|
|
"epoch": 0.5366416618580496,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004979876809728223,
|
|
"loss": 6.4021,
|
|
"mean_token_accuracy": 0.1560329467058182,
|
|
"num_tokens": 11791572.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.474690055847168,
|
|
"epoch": 0.5372186959030583,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004979821707441292,
|
|
"loss": 6.439,
|
|
"mean_token_accuracy": 0.1557312175631523,
|
|
"num_tokens": 11805198.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.5011818408966064,
|
|
"epoch": 0.5377957299480669,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004979766530155416,
|
|
"loss": 6.3507,
|
|
"mean_token_accuracy": 0.15437426120042802,
|
|
"num_tokens": 11817882.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.450196981430054,
|
|
"epoch": 0.5383727639930755,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004979711277872449,
|
|
"loss": 6.254,
|
|
"mean_token_accuracy": 0.1714956507086754,
|
|
"num_tokens": 11830334.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.36470775604248,
|
|
"epoch": 0.5389497980380843,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004979655950594252,
|
|
"loss": 6.3324,
|
|
"mean_token_accuracy": 0.16521675139665604,
|
|
"num_tokens": 11843057.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.521092224121094,
|
|
"epoch": 0.5395268320830929,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004979600548322684,
|
|
"loss": 6.4443,
|
|
"mean_token_accuracy": 0.1515732452273369,
|
|
"num_tokens": 11856086.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.502345943450928,
|
|
"epoch": 0.5401038661281016,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000497954507105961,
|
|
"loss": 6.3598,
|
|
"mean_token_accuracy": 0.1554923489689827,
|
|
"num_tokens": 11867799.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.406812906265259,
|
|
"epoch": 0.5406809001731102,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004979489518806893,
|
|
"loss": 6.2653,
|
|
"mean_token_accuracy": 0.169070328772068,
|
|
"num_tokens": 11881488.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.489722061157226,
|
|
"epoch": 0.5412579342181189,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004979433891566405,
|
|
"loss": 6.3691,
|
|
"mean_token_accuracy": 0.15394651889801025,
|
|
"num_tokens": 11893495.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.486820793151855,
|
|
"epoch": 0.5418349682631275,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004979378189340015,
|
|
"loss": 6.3088,
|
|
"mean_token_accuracy": 0.16032520085573196,
|
|
"num_tokens": 11905456.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.447782754898071,
|
|
"epoch": 0.5424120023081361,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004979322412129597,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.15736544877290726,
|
|
"num_tokens": 11917987.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.472414350509643,
|
|
"epoch": 0.5429890363531449,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004979266559937028,
|
|
"loss": 6.3375,
|
|
"mean_token_accuracy": 0.16168057471513747,
|
|
"num_tokens": 11930104.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.486454343795776,
|
|
"epoch": 0.5435660703981535,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004979210632764185,
|
|
"loss": 6.3531,
|
|
"mean_token_accuracy": 0.15208696722984313,
|
|
"num_tokens": 11942841.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.467970561981201,
|
|
"epoch": 0.5441431044431622,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004979154630612949,
|
|
"loss": 6.3429,
|
|
"mean_token_accuracy": 0.15887532234191895,
|
|
"num_tokens": 11955509.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.456158542633057,
|
|
"epoch": 0.5447201384881708,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004979098553485205,
|
|
"loss": 6.3279,
|
|
"mean_token_accuracy": 0.16368138641119004,
|
|
"num_tokens": 11967389.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.5094503402709964,
|
|
"epoch": 0.5452971725331794,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004979042401382838,
|
|
"loss": 6.3774,
|
|
"mean_token_accuracy": 0.1637259915471077,
|
|
"num_tokens": 11980173.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.483466386795044,
|
|
"epoch": 0.5458742065781881,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004978986174307737,
|
|
"loss": 6.3284,
|
|
"mean_token_accuracy": 0.16224620044231414,
|
|
"num_tokens": 11993039.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.408599996566773,
|
|
"epoch": 0.5464512406231967,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004978929872261794,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.16886009871959687,
|
|
"num_tokens": 12005861.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.323904705047608,
|
|
"epoch": 0.5470282746682055,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004978873495246901,
|
|
"loss": 6.1946,
|
|
"mean_token_accuracy": 0.1696503296494484,
|
|
"num_tokens": 12018137.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.472019958496094,
|
|
"epoch": 0.5476053087132141,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004978817043264955,
|
|
"loss": 6.3375,
|
|
"mean_token_accuracy": 0.1588849812746048,
|
|
"num_tokens": 12030086.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.40808687210083,
|
|
"epoch": 0.5481823427582228,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004978760516317856,
|
|
"loss": 6.3081,
|
|
"mean_token_accuracy": 0.1678110256791115,
|
|
"num_tokens": 12043166.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.395149755477905,
|
|
"epoch": 0.5487593768032314,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004978703914407503,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.16222834289073945,
|
|
"num_tokens": 12055373.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.39506983757019,
|
|
"epoch": 0.54933641084824,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004978647237535802,
|
|
"loss": 6.2642,
|
|
"mean_token_accuracy": 0.16176026910543442,
|
|
"num_tokens": 12066369.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.374369716644287,
|
|
"epoch": 0.5499134448932487,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004978590485704657,
|
|
"loss": 6.1943,
|
|
"mean_token_accuracy": 0.16742823272943497,
|
|
"num_tokens": 12077939.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.513216352462768,
|
|
"epoch": 0.5504904789382573,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004978533658915979,
|
|
"loss": 6.3859,
|
|
"mean_token_accuracy": 0.1533949315547943,
|
|
"num_tokens": 12091102.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.490841245651245,
|
|
"epoch": 0.5510675129832661,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004978476757171678,
|
|
"loss": 6.3215,
|
|
"mean_token_accuracy": 0.16209329962730407,
|
|
"num_tokens": 12103144.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.436073350906372,
|
|
"epoch": 0.5516445470282747,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004978419780473668,
|
|
"loss": 6.3979,
|
|
"mean_token_accuracy": 0.16156178414821626,
|
|
"num_tokens": 12116664.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.447421932220459,
|
|
"epoch": 0.5522215810732833,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004978362728823865,
|
|
"loss": 6.3087,
|
|
"mean_token_accuracy": 0.16004290282726288,
|
|
"num_tokens": 12129656.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.387583160400391,
|
|
"epoch": 0.552798615118292,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004978305602224189,
|
|
"loss": 6.2694,
|
|
"mean_token_accuracy": 0.16280092149972916,
|
|
"num_tokens": 12143221.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.481845951080322,
|
|
"epoch": 0.5533756491633006,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004978248400676562,
|
|
"loss": 6.2451,
|
|
"mean_token_accuracy": 0.16497370451688767,
|
|
"num_tokens": 12156409.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.324881172180175,
|
|
"epoch": 0.5539526832083093,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004978191124182905,
|
|
"loss": 6.1727,
|
|
"mean_token_accuracy": 0.17471756488084794,
|
|
"num_tokens": 12169589.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.380939769744873,
|
|
"epoch": 0.5545297172533179,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004978133772745149,
|
|
"loss": 6.3131,
|
|
"mean_token_accuracy": 0.1579168915748596,
|
|
"num_tokens": 12182692.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.419868421554566,
|
|
"epoch": 0.5551067512983267,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004978076346365218,
|
|
"loss": 6.2702,
|
|
"mean_token_accuracy": 0.16413773596286774,
|
|
"num_tokens": 12195892.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.485994005203247,
|
|
"epoch": 0.5556837853433353,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004978018845045047,
|
|
"loss": 6.2949,
|
|
"mean_token_accuracy": 0.15944212526082993,
|
|
"num_tokens": 12208974.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.459294605255127,
|
|
"epoch": 0.5562608193883439,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004977961268786568,
|
|
"loss": 6.361,
|
|
"mean_token_accuracy": 0.1640543147921562,
|
|
"num_tokens": 12221342.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.406201362609863,
|
|
"epoch": 0.5568378534333526,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004977903617591719,
|
|
"loss": 6.3377,
|
|
"mean_token_accuracy": 0.16159975826740264,
|
|
"num_tokens": 12233778.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.394937467575073,
|
|
"epoch": 0.5574148874783612,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004977845891462439,
|
|
"loss": 6.1738,
|
|
"mean_token_accuracy": 0.16942807286977768,
|
|
"num_tokens": 12246001.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.368630838394165,
|
|
"epoch": 0.5579919215233698,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004977788090400668,
|
|
"loss": 6.2319,
|
|
"mean_token_accuracy": 0.16157334297895432,
|
|
"num_tokens": 12258677.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.527727890014648,
|
|
"epoch": 0.5585689555683785,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004977730214408352,
|
|
"loss": 6.3329,
|
|
"mean_token_accuracy": 0.15864758640527726,
|
|
"num_tokens": 12270786.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.39428677558899,
|
|
"epoch": 0.5591459896133872,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004977672263487435,
|
|
"loss": 6.3389,
|
|
"mean_token_accuracy": 0.1648403987288475,
|
|
"num_tokens": 12284439.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.443121910095215,
|
|
"epoch": 0.5597230236583959,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000497761423763987,
|
|
"loss": 6.3145,
|
|
"mean_token_accuracy": 0.15776993781328202,
|
|
"num_tokens": 12297005.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.48302993774414,
|
|
"epoch": 0.5603000577034045,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004977556136867606,
|
|
"loss": 6.3379,
|
|
"mean_token_accuracy": 0.15854468047618867,
|
|
"num_tokens": 12308855.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.496091365814209,
|
|
"epoch": 0.5608770917484132,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004977497961172598,
|
|
"loss": 6.2969,
|
|
"mean_token_accuracy": 0.16524532288312913,
|
|
"num_tokens": 12321120.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.426670408248901,
|
|
"epoch": 0.5614541257934218,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004977439710556802,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.15703101307153702,
|
|
"num_tokens": 12333793.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.395258378982544,
|
|
"epoch": 0.5620311598384304,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004977381385022179,
|
|
"loss": 6.2346,
|
|
"mean_token_accuracy": 0.16402624398469925,
|
|
"num_tokens": 12345998.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.420551776885986,
|
|
"epoch": 0.5626081938834391,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004977322984570688,
|
|
"loss": 6.2915,
|
|
"mean_token_accuracy": 0.1633617177605629,
|
|
"num_tokens": 12358580.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.50617299079895,
|
|
"epoch": 0.5631852279284478,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004977264509204296,
|
|
"loss": 6.3728,
|
|
"mean_token_accuracy": 0.15802410542964934,
|
|
"num_tokens": 12370867.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.460091161727905,
|
|
"epoch": 0.5637622619734565,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977205958924967,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.16238923370838165,
|
|
"num_tokens": 12384086.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.331658267974854,
|
|
"epoch": 0.5643392960184651,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004977147333734673,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.1692612126469612,
|
|
"num_tokens": 12396852.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.493855905532837,
|
|
"epoch": 0.5649163300634737,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004977088633635385,
|
|
"loss": 6.2907,
|
|
"mean_token_accuracy": 0.16344485133886338,
|
|
"num_tokens": 12409924.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.301746273040772,
|
|
"epoch": 0.5654933641084824,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004977029858629076,
|
|
"loss": 6.2559,
|
|
"mean_token_accuracy": 0.17010487616062164,
|
|
"num_tokens": 12422218.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.406967258453369,
|
|
"epoch": 0.566070398153491,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004976971008717726,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.15997430682182312,
|
|
"num_tokens": 12433522.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.589291667938232,
|
|
"epoch": 0.5666474321984997,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004976912083903309,
|
|
"loss": 6.3465,
|
|
"mean_token_accuracy": 0.15723779648542405,
|
|
"num_tokens": 12445526.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.381515216827393,
|
|
"epoch": 0.5672244662435084,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004976853084187814,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.16589126586914063,
|
|
"num_tokens": 12458403.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.522457313537598,
|
|
"epoch": 0.5678015002885171,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004976794009573219,
|
|
"loss": 6.3572,
|
|
"mean_token_accuracy": 0.16034309267997743,
|
|
"num_tokens": 12470437.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.491942453384399,
|
|
"epoch": 0.5683785343335257,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004976734860061515,
|
|
"loss": 6.2934,
|
|
"mean_token_accuracy": 0.16653283834457397,
|
|
"num_tokens": 12483345.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.37202935218811,
|
|
"epoch": 0.5689555683785343,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004976675635654688,
|
|
"loss": 6.2938,
|
|
"mean_token_accuracy": 0.16135128289461137,
|
|
"num_tokens": 12495675.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.417981672286987,
|
|
"epoch": 0.569532602423543,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004976616336354733,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.16374748200178146,
|
|
"num_tokens": 12507569.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.435359477996826,
|
|
"epoch": 0.5701096364685516,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004976556962163645,
|
|
"loss": 6.371,
|
|
"mean_token_accuracy": 0.1623230755329132,
|
|
"num_tokens": 12521198.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.379960393905639,
|
|
"epoch": 0.5706866705135603,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004976497513083419,
|
|
"loss": 6.2657,
|
|
"mean_token_accuracy": 0.1603717714548111,
|
|
"num_tokens": 12533242.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.486459255218506,
|
|
"epoch": 0.571263704558569,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004976437989116055,
|
|
"loss": 6.3877,
|
|
"mean_token_accuracy": 0.16001511961221696,
|
|
"num_tokens": 12545918.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.4408200740814205,
|
|
"epoch": 0.5718407386035776,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004976378390263554,
|
|
"loss": 6.324,
|
|
"mean_token_accuracy": 0.1614006757736206,
|
|
"num_tokens": 12558090.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.4780820369720455,
|
|
"epoch": 0.5724177726485863,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004976318716527924,
|
|
"loss": 6.348,
|
|
"mean_token_accuracy": 0.16186215579509736,
|
|
"num_tokens": 12571453.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.449974870681762,
|
|
"epoch": 0.5729948066935949,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004976258967911168,
|
|
"loss": 6.2967,
|
|
"mean_token_accuracy": 0.1604265719652176,
|
|
"num_tokens": 12584762.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.457449626922608,
|
|
"epoch": 0.5735718407386036,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004976199144415298,
|
|
"loss": 6.2847,
|
|
"mean_token_accuracy": 0.15467647165060044,
|
|
"num_tokens": 12597224.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.4018861770629885,
|
|
"epoch": 0.5741488747836122,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004976139246042325,
|
|
"loss": 6.3598,
|
|
"mean_token_accuracy": 0.15818336009979247,
|
|
"num_tokens": 12609837.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.476587915420533,
|
|
"epoch": 0.5747259088286208,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004976079272794265,
|
|
"loss": 6.3834,
|
|
"mean_token_accuracy": 0.15177921205759048,
|
|
"num_tokens": 12622596.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.460304689407349,
|
|
"epoch": 0.5753029428736296,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004976019224673134,
|
|
"loss": 6.2836,
|
|
"mean_token_accuracy": 0.16508358716964722,
|
|
"num_tokens": 12634721.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.443642854690552,
|
|
"epoch": 0.5758799769186382,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975959101680953,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.16074737012386323,
|
|
"num_tokens": 12646389.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.481823301315307,
|
|
"epoch": 0.5764570109636469,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004975898903819742,
|
|
"loss": 6.4046,
|
|
"mean_token_accuracy": 0.15126152634620665,
|
|
"num_tokens": 12661081.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.560647344589233,
|
|
"epoch": 0.5770340450086555,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004975838631091527,
|
|
"loss": 6.3346,
|
|
"mean_token_accuracy": 0.15827033370733262,
|
|
"num_tokens": 12672505.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.421548557281494,
|
|
"epoch": 0.5776110790536642,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004975778283498336,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.15744248777627945,
|
|
"num_tokens": 12684805.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.38816728591919,
|
|
"epoch": 0.5781881130986728,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004975717861042198,
|
|
"loss": 6.3018,
|
|
"mean_token_accuracy": 0.15945205241441726,
|
|
"num_tokens": 12698557.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.495122861862183,
|
|
"epoch": 0.5787651471436814,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004975657363725146,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.15233609974384307,
|
|
"num_tokens": 12712472.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.413561677932739,
|
|
"epoch": 0.5793421811886902,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975596791549213,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.16952557265758514,
|
|
"num_tokens": 12725698.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.426093578338623,
|
|
"epoch": 0.5799192152336988,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004975536144516437,
|
|
"loss": 6.2959,
|
|
"mean_token_accuracy": 0.1619711399078369,
|
|
"num_tokens": 12738126.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.4965479373931885,
|
|
"epoch": 0.5804962492787075,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000497547542262886,
|
|
"loss": 6.3113,
|
|
"mean_token_accuracy": 0.1720854163169861,
|
|
"num_tokens": 12751402.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.415817785263061,
|
|
"epoch": 0.5810732833237161,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004975414625888521,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.15630837082862853,
|
|
"num_tokens": 12763957.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.4553731918334964,
|
|
"epoch": 0.5816503173687247,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975353754297468,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.16455962955951692,
|
|
"num_tokens": 12776498.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.456435108184815,
|
|
"epoch": 0.5822273514137334,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975292807857745,
|
|
"loss": 6.2916,
|
|
"mean_token_accuracy": 0.16458143144845963,
|
|
"num_tokens": 12788498.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.342044496536255,
|
|
"epoch": 0.582804385458742,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975231786571406,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.16185703426599501,
|
|
"num_tokens": 12799907.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.425001573562622,
|
|
"epoch": 0.5833814195037508,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004975170690440499,
|
|
"loss": 6.327,
|
|
"mean_token_accuracy": 0.1625050887465477,
|
|
"num_tokens": 12812610.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.462145233154297,
|
|
"epoch": 0.5839584535487594,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004975109519467083,
|
|
"loss": 6.3213,
|
|
"mean_token_accuracy": 0.1591153174638748,
|
|
"num_tokens": 12825082.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.347224283218384,
|
|
"epoch": 0.584535487593768,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004975048273653212,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.16950058192014694,
|
|
"num_tokens": 12837999.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.363939332962036,
|
|
"epoch": 0.5851125216387767,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974986953000948,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.17064935117959976,
|
|
"num_tokens": 12850020.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.394009160995483,
|
|
"epoch": 0.5856895556837853,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004974925557512354,
|
|
"loss": 6.2981,
|
|
"mean_token_accuracy": 0.16221174597740173,
|
|
"num_tokens": 12863818.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.442247009277343,
|
|
"epoch": 0.586266589728794,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004974864087189493,
|
|
"loss": 6.3011,
|
|
"mean_token_accuracy": 0.16013864129781724,
|
|
"num_tokens": 12876959.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.445587396621704,
|
|
"epoch": 0.5868436237738026,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004974802542034434,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.15875303149223327,
|
|
"num_tokens": 12889817.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.396495199203491,
|
|
"epoch": 0.5874206578188114,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974740922049246,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.1640445441007614,
|
|
"num_tokens": 12901438.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.383800745010376,
|
|
"epoch": 0.58799769186382,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974679227236004,
|
|
"loss": 6.1984,
|
|
"mean_token_accuracy": 0.1692484885454178,
|
|
"num_tokens": 12914115.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.406459999084473,
|
|
"epoch": 0.5885747259088286,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004974617457596779,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.1679217040538788,
|
|
"num_tokens": 12926822.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.37530369758606,
|
|
"epoch": 0.5891517599538373,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004974555613133652,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.1603657677769661,
|
|
"num_tokens": 12939515.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.258018732070923,
|
|
"epoch": 0.5897287939988459,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004974493693848702,
|
|
"loss": 6.2179,
|
|
"mean_token_accuracy": 0.18086731135845185,
|
|
"num_tokens": 12952195.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.452794170379638,
|
|
"epoch": 0.5903058280438546,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004974431699744011,
|
|
"loss": 6.2358,
|
|
"mean_token_accuracy": 0.16284567266702651,
|
|
"num_tokens": 12964563.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.354326820373535,
|
|
"epoch": 0.5908828620888632,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974369630821665,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.16809700131416322,
|
|
"num_tokens": 12976564.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.21676197052002,
|
|
"epoch": 0.5914598961338718,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004974307487083752,
|
|
"loss": 6.124,
|
|
"mean_token_accuracy": 0.16871170401573182,
|
|
"num_tokens": 12989757.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.430266237258911,
|
|
"epoch": 0.5920369301788806,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004974245268532361,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.16050200611352922,
|
|
"num_tokens": 13003846.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.493060302734375,
|
|
"epoch": 0.5926139642238892,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004974182975169585,
|
|
"loss": 6.3453,
|
|
"mean_token_accuracy": 0.1525108903646469,
|
|
"num_tokens": 13018389.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.47206563949585,
|
|
"epoch": 0.5931909982688979,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000497412060699752,
|
|
"loss": 6.3402,
|
|
"mean_token_accuracy": 0.1555670529603958,
|
|
"num_tokens": 13031893.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.444800662994385,
|
|
"epoch": 0.5937680323139065,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004974058164018263,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.16890939027071,
|
|
"num_tokens": 13045916.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.461399793624878,
|
|
"epoch": 0.5943450663589152,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004973995646233914,
|
|
"loss": 6.3126,
|
|
"mean_token_accuracy": 0.1604936346411705,
|
|
"num_tokens": 13058468.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.452783203125,
|
|
"epoch": 0.5949221004039238,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004973933053646576,
|
|
"loss": 6.3328,
|
|
"mean_token_accuracy": 0.15725631415843963,
|
|
"num_tokens": 13070778.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.452268409729004,
|
|
"epoch": 0.5954991344489324,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004973870386258355,
|
|
"loss": 6.2174,
|
|
"mean_token_accuracy": 0.1663954645395279,
|
|
"num_tokens": 13082287.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.329747056961059,
|
|
"epoch": 0.5960761684939412,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004973807644071357,
|
|
"loss": 6.2168,
|
|
"mean_token_accuracy": 0.1709250345826149,
|
|
"num_tokens": 13095505.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.327900695800781,
|
|
"epoch": 0.5966532025389498,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004973744827087695,
|
|
"loss": 6.2446,
|
|
"mean_token_accuracy": 0.16142298728227616,
|
|
"num_tokens": 13108351.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.483879852294922,
|
|
"epoch": 0.5972302365839585,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497368193530948,
|
|
"loss": 6.303,
|
|
"mean_token_accuracy": 0.16267842650413514,
|
|
"num_tokens": 13120941.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.439163446426392,
|
|
"epoch": 0.5978072706289671,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004973618968738828,
|
|
"loss": 6.2475,
|
|
"mean_token_accuracy": 0.16663485914468765,
|
|
"num_tokens": 13134217.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.345459890365601,
|
|
"epoch": 0.5983843046739757,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004973555927377856,
|
|
"loss": 6.2653,
|
|
"mean_token_accuracy": 0.1663901150226593,
|
|
"num_tokens": 13146245.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.438876342773438,
|
|
"epoch": 0.5989613387189844,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004973492811228685,
|
|
"loss": 6.287,
|
|
"mean_token_accuracy": 0.1630580872297287,
|
|
"num_tokens": 13158498.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.429390382766724,
|
|
"epoch": 0.599538372763993,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004973429620293438,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.15690135210752487,
|
|
"num_tokens": 13170464.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.437797021865845,
|
|
"epoch": 0.6001154068090018,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004973366354574239,
|
|
"loss": 6.3777,
|
|
"mean_token_accuracy": 0.1602035418152809,
|
|
"num_tokens": 13183315.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.518604564666748,
|
|
"epoch": 0.6006924408540104,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004973303014073219,
|
|
"loss": 6.405,
|
|
"mean_token_accuracy": 0.15694308578968047,
|
|
"num_tokens": 13196536.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.4371904850006105,
|
|
"epoch": 0.601269474899019,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004973239598792504,
|
|
"loss": 6.2495,
|
|
"mean_token_accuracy": 0.16467582434415817,
|
|
"num_tokens": 13209159.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.449504613876343,
|
|
"epoch": 0.6018465089440277,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004973176108734232,
|
|
"loss": 6.2826,
|
|
"mean_token_accuracy": 0.1641786962747574,
|
|
"num_tokens": 13221563.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.4400306224823,
|
|
"epoch": 0.6024235429890363,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004973112543900535,
|
|
"loss": 6.3671,
|
|
"mean_token_accuracy": 0.1555931881070137,
|
|
"num_tokens": 13234209.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.4899622917175295,
|
|
"epoch": 0.603000577034045,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004973048904293551,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.15689144134521485,
|
|
"num_tokens": 13246198.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.364943170547486,
|
|
"epoch": 0.6035776110790536,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004972985189915422,
|
|
"loss": 6.273,
|
|
"mean_token_accuracy": 0.16756874471902847,
|
|
"num_tokens": 13259149.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.379005336761475,
|
|
"epoch": 0.6041546451240624,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000497292140076829,
|
|
"loss": 6.2695,
|
|
"mean_token_accuracy": 0.1631223067641258,
|
|
"num_tokens": 13271138.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.40664587020874,
|
|
"epoch": 0.604731679169071,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972857536854301,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.15566522479057313,
|
|
"num_tokens": 13283639.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.401790046691895,
|
|
"epoch": 0.6053087132140796,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004972793598175603,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.16139982044696807,
|
|
"num_tokens": 13295322.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.381245756149292,
|
|
"epoch": 0.6058857472590883,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972729584734347,
|
|
"loss": 6.2634,
|
|
"mean_token_accuracy": 0.16289384216070174,
|
|
"num_tokens": 13308431.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.390211057662964,
|
|
"epoch": 0.6064627813040969,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004972665496532685,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.16877303421497344,
|
|
"num_tokens": 13321878.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.296879863739013,
|
|
"epoch": 0.6070398153491056,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004972601333572774,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.16521066427230835,
|
|
"num_tokens": 13334166.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.450336933135986,
|
|
"epoch": 0.6076168493941142,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004972537095856769,
|
|
"loss": 6.3535,
|
|
"mean_token_accuracy": 0.16121897250413894,
|
|
"num_tokens": 13347704.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.421620845794678,
|
|
"epoch": 0.608193883439123,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972472783386834,
|
|
"loss": 6.2252,
|
|
"mean_token_accuracy": 0.1674308717250824,
|
|
"num_tokens": 13359659.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.4067305564880375,
|
|
"epoch": 0.6087709174841316,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004972408396165132,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.16205257177352905,
|
|
"num_tokens": 13371952.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.460360765457153,
|
|
"epoch": 0.6093479515291402,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004972343934193826,
|
|
"loss": 6.2829,
|
|
"mean_token_accuracy": 0.16754993051290512,
|
|
"num_tokens": 13385757.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.375572776794433,
|
|
"epoch": 0.6099249855741489,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004972279397475086,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.1626361846923828,
|
|
"num_tokens": 13397657.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.354529762268067,
|
|
"epoch": 0.6105020196191575,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004972214786011083,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.16665343195199966,
|
|
"num_tokens": 13410882.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.385918283462525,
|
|
"epoch": 0.6110790536641661,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000497215009980399,
|
|
"loss": 6.2998,
|
|
"mean_token_accuracy": 0.15810784995555877,
|
|
"num_tokens": 13423310.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.431512498855591,
|
|
"epoch": 0.6116560877091748,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000497208533885598,
|
|
"loss": 6.2736,
|
|
"mean_token_accuracy": 0.1636954054236412,
|
|
"num_tokens": 13437837.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.522774076461792,
|
|
"epoch": 0.6122331217541835,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004972020503169235,
|
|
"loss": 6.2688,
|
|
"mean_token_accuracy": 0.1651971697807312,
|
|
"num_tokens": 13450637.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.39950647354126,
|
|
"epoch": 0.6128101557991922,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004971955592745934,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.1568018838763237,
|
|
"num_tokens": 13464429.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.408504819869995,
|
|
"epoch": 0.6133871898442008,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497189060758826,
|
|
"loss": 6.1998,
|
|
"mean_token_accuracy": 0.1667480379343033,
|
|
"num_tokens": 13476710.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.397567081451416,
|
|
"epoch": 0.6139642238892095,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.00049718255476984,
|
|
"loss": 6.251,
|
|
"mean_token_accuracy": 0.16203757673501967,
|
|
"num_tokens": 13489828.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.430128335952759,
|
|
"epoch": 0.6145412579342181,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004971760413078539,
|
|
"loss": 6.2457,
|
|
"mean_token_accuracy": 0.16466025859117508,
|
|
"num_tokens": 13503584.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.360280466079712,
|
|
"epoch": 0.6151182919792267,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004971695203730872,
|
|
"loss": 6.2378,
|
|
"mean_token_accuracy": 0.16777390688657762,
|
|
"num_tokens": 13514658.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.3734703540802,
|
|
"epoch": 0.6156953260242354,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000497162991965759,
|
|
"loss": 6.2795,
|
|
"mean_token_accuracy": 0.1756128638982773,
|
|
"num_tokens": 13526424.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.390287590026856,
|
|
"epoch": 0.6162723600692441,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004971564560860889,
|
|
"loss": 6.2342,
|
|
"mean_token_accuracy": 0.1635016083717346,
|
|
"num_tokens": 13540515.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.433468246459961,
|
|
"epoch": 0.6168493941142528,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004971499127342968,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.1582094430923462,
|
|
"num_tokens": 13553634.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.42935209274292,
|
|
"epoch": 0.6174264281592614,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004971433619106027,
|
|
"loss": 6.3363,
|
|
"mean_token_accuracy": 0.16416244804859162,
|
|
"num_tokens": 13565168.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.381501960754394,
|
|
"epoch": 0.61800346220427,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000497136803615227,
|
|
"loss": 6.2739,
|
|
"mean_token_accuracy": 0.16165704429149627,
|
|
"num_tokens": 13578511.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.401495885848999,
|
|
"epoch": 0.6185804962492787,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004971302378483902,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.1660989612340927,
|
|
"num_tokens": 13590535.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.3950817584991455,
|
|
"epoch": 0.6191575302942873,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004971236646103132,
|
|
"loss": 6.2847,
|
|
"mean_token_accuracy": 0.16551341712474824,
|
|
"num_tokens": 13604549.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.423378038406372,
|
|
"epoch": 0.619734564339296,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004971170839012171,
|
|
"loss": 6.2773,
|
|
"mean_token_accuracy": 0.158201265335083,
|
|
"num_tokens": 13617658.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.378845930099487,
|
|
"epoch": 0.6203115983843047,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004971104957213233,
|
|
"loss": 6.1836,
|
|
"mean_token_accuracy": 0.1718725860118866,
|
|
"num_tokens": 13630559.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.347926759719849,
|
|
"epoch": 0.6208886324293134,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004971039000708531,
|
|
"loss": 6.2582,
|
|
"mean_token_accuracy": 0.16711993515491486,
|
|
"num_tokens": 13643018.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.414066219329834,
|
|
"epoch": 0.621465666474322,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004970972969500286,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.16316382586956024,
|
|
"num_tokens": 13655053.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.40781569480896,
|
|
"epoch": 0.6220427005193306,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000497090686359072,
|
|
"loss": 6.2107,
|
|
"mean_token_accuracy": 0.16605478525161743,
|
|
"num_tokens": 13667420.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.3122974872589115,
|
|
"epoch": 0.6226197345643393,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004970840682982054,
|
|
"loss": 6.1826,
|
|
"mean_token_accuracy": 0.16799420565366746,
|
|
"num_tokens": 13680662.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.402325630187988,
|
|
"epoch": 0.6231967686093479,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004970774427676514,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.15851684659719467,
|
|
"num_tokens": 13694720.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.4278172016143795,
|
|
"epoch": 0.6237738026543566,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000497070809767633,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.1631224125623703,
|
|
"num_tokens": 13706826.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.314861869812011,
|
|
"epoch": 0.6243508366993653,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004970641692983731,
|
|
"loss": 6.2796,
|
|
"mean_token_accuracy": 0.1627788543701172,
|
|
"num_tokens": 13719526.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.395055103302002,
|
|
"epoch": 0.624927870744374,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004970575213600954,
|
|
"loss": 6.1683,
|
|
"mean_token_accuracy": 0.17014200389385223,
|
|
"num_tokens": 13731583.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.429858112335205,
|
|
"epoch": 0.6255049047893826,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004970508659530231,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.16601747125387192,
|
|
"num_tokens": 13743690.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.385574388504028,
|
|
"epoch": 0.6260819388343912,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004970442030773802,
|
|
"loss": 6.2359,
|
|
"mean_token_accuracy": 0.1637325868010521,
|
|
"num_tokens": 13756264.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.392513990402222,
|
|
"epoch": 0.6266589728793999,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004970375327333909,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.1582666516304016,
|
|
"num_tokens": 13768089.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.420020866394043,
|
|
"epoch": 0.6272360069244085,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004970308549212796,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.16104890406131744,
|
|
"num_tokens": 13780671.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.4573148727417,
|
|
"epoch": 0.6278130409694171,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004970241696412705,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.160064260661602,
|
|
"num_tokens": 13793678.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.423211479187012,
|
|
"epoch": 0.6283900750144259,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000497017476893589,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.16376707404851915,
|
|
"num_tokens": 13807001.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.402011871337891,
|
|
"epoch": 0.6289671090594345,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004970107766784598,
|
|
"loss": 6.1794,
|
|
"mean_token_accuracy": 0.16806947141885759,
|
|
"num_tokens": 13820227.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.405494213104248,
|
|
"epoch": 0.6295441431044432,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004970040689961084,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.16475358456373215,
|
|
"num_tokens": 13831663.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.29299693107605,
|
|
"epoch": 0.6301211771494518,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004969973538467605,
|
|
"loss": 6.1821,
|
|
"mean_token_accuracy": 0.16974693536758423,
|
|
"num_tokens": 13845173.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.43713493347168,
|
|
"epoch": 0.6306982111944605,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004969906312306419,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.16185085326433182,
|
|
"num_tokens": 13857551.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.28310809135437,
|
|
"epoch": 0.6312752452394691,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004969839011479786,
|
|
"loss": 6.1619,
|
|
"mean_token_accuracy": 0.17454650551080703,
|
|
"num_tokens": 13870238.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.3346006870269775,
|
|
"epoch": 0.6318522792844777,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496977163598997,
|
|
"loss": 6.2471,
|
|
"mean_token_accuracy": 0.1618565484881401,
|
|
"num_tokens": 13883145.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.452572059631348,
|
|
"epoch": 0.6324293133294865,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004969704185839239,
|
|
"loss": 6.2915,
|
|
"mean_token_accuracy": 0.15788978338241577,
|
|
"num_tokens": 13895777.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.3593542098999025,
|
|
"epoch": 0.6330063473744951,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004969636661029859,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.17119636833667756,
|
|
"num_tokens": 13907641.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.476277828216553,
|
|
"epoch": 0.6335833814195038,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004969569061564103,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.1563932254910469,
|
|
"num_tokens": 13921576.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.4062957763671875,
|
|
"epoch": 0.6341604154645124,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004969501387444245,
|
|
"loss": 6.2387,
|
|
"mean_token_accuracy": 0.16197298020124434,
|
|
"num_tokens": 13935158.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.29954342842102,
|
|
"epoch": 0.634737449509521,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004969433638672559,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.16927525103092195,
|
|
"num_tokens": 13947803.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.441785907745361,
|
|
"epoch": 0.6353144835545297,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969365815251325,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.16404346376657486,
|
|
"num_tokens": 13960573.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.359479236602783,
|
|
"epoch": 0.6358915175995383,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004969297917182825,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.16838484555482863,
|
|
"num_tokens": 13970994.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.370149993896485,
|
|
"epoch": 0.6364685516445471,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004969229944469342,
|
|
"loss": 6.3613,
|
|
"mean_token_accuracy": 0.15786928087472915,
|
|
"num_tokens": 13983617.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.4495750904083256,
|
|
"epoch": 0.6370455856895557,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004969161897113162,
|
|
"loss": 6.2431,
|
|
"mean_token_accuracy": 0.16852736622095107,
|
|
"num_tokens": 13995779.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.342259693145752,
|
|
"epoch": 0.6376226197345644,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004969093775116574,
|
|
"loss": 6.2784,
|
|
"mean_token_accuracy": 0.1653564378619194,
|
|
"num_tokens": 14008650.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.3147563457489015,
|
|
"epoch": 0.638199653779573,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004969025578481869,
|
|
"loss": 6.1887,
|
|
"mean_token_accuracy": 0.16722843796014786,
|
|
"num_tokens": 14021787.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.5476946353912355,
|
|
"epoch": 0.6387766878245816,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000496895730721134,
|
|
"loss": 6.3405,
|
|
"mean_token_accuracy": 0.15578458309173585,
|
|
"num_tokens": 14035036.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.4367437839508055,
|
|
"epoch": 0.6393537218695903,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004968888961307286,
|
|
"loss": 6.2784,
|
|
"mean_token_accuracy": 0.16260789930820466,
|
|
"num_tokens": 14048589.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.335751581192016,
|
|
"epoch": 0.6399307559145989,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004968820540772003,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.18534766435623168,
|
|
"num_tokens": 14061007.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.402452230453491,
|
|
"epoch": 0.6405077899596077,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968752045607794,
|
|
"loss": 6.2971,
|
|
"mean_token_accuracy": 0.16098586469888687,
|
|
"num_tokens": 14074165.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.505826616287232,
|
|
"epoch": 0.6410848240046163,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004968683475816961,
|
|
"loss": 6.355,
|
|
"mean_token_accuracy": 0.15098087936639787,
|
|
"num_tokens": 14086261.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.418167352676392,
|
|
"epoch": 0.641661858049625,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004968614831401811,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.17131647616624832,
|
|
"num_tokens": 14098458.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.348795795440674,
|
|
"epoch": 0.6422388920946336,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004968546112364654,
|
|
"loss": 6.3645,
|
|
"mean_token_accuracy": 0.1578898921608925,
|
|
"num_tokens": 14110754.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.420198011398315,
|
|
"epoch": 0.6428159261396422,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049684773187078,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.1605192869901657,
|
|
"num_tokens": 14123361.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.400240230560303,
|
|
"epoch": 0.6433929601846509,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004968408450433565,
|
|
"loss": 6.2097,
|
|
"mean_token_accuracy": 0.17002205550670624,
|
|
"num_tokens": 14135576.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.366382312774658,
|
|
"epoch": 0.6439699942296595,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004968339507544263,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.16116065233945848,
|
|
"num_tokens": 14147879.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.426327133178711,
|
|
"epoch": 0.6445470282746683,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004968270490042212,
|
|
"loss": 6.3084,
|
|
"mean_token_accuracy": 0.16116396337747574,
|
|
"num_tokens": 14159449.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.321964263916016,
|
|
"epoch": 0.6451240623196769,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004968201397929737,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.16564835458993912,
|
|
"num_tokens": 14172547.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.398483514785767,
|
|
"epoch": 0.6457010963646855,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004968132231209158,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.1655385360121727,
|
|
"num_tokens": 14184670.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.39441933631897,
|
|
"epoch": 0.6462781304096942,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004968062989882803,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.16546582281589509,
|
|
"num_tokens": 14198048.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.324096584320069,
|
|
"epoch": 0.6468551644547028,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004967993673953003,
|
|
"loss": 6.1823,
|
|
"mean_token_accuracy": 0.1676321193575859,
|
|
"num_tokens": 14209470.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.376352262496948,
|
|
"epoch": 0.6474321984997115,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004967924283422087,
|
|
"loss": 6.1919,
|
|
"mean_token_accuracy": 0.1653391182422638,
|
|
"num_tokens": 14221731.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.435838794708252,
|
|
"epoch": 0.6480092325447201,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000496785481829239,
|
|
"loss": 6.2543,
|
|
"mean_token_accuracy": 0.15581413954496384,
|
|
"num_tokens": 14235125.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.372358417510986,
|
|
"epoch": 0.6485862665897288,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004967785278566245,
|
|
"loss": 6.2227,
|
|
"mean_token_accuracy": 0.1686449021100998,
|
|
"num_tokens": 14248941.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.3675590515136715,
|
|
"epoch": 0.6491633006347375,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004967715664245997,
|
|
"loss": 6.1475,
|
|
"mean_token_accuracy": 0.17231432795524598,
|
|
"num_tokens": 14260955.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.30697455406189,
|
|
"epoch": 0.6497403346797461,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004967645975333983,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.17377639561891556,
|
|
"num_tokens": 14274123.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.441181182861328,
|
|
"epoch": 0.6503173687247548,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004967576211832548,
|
|
"loss": 6.2351,
|
|
"mean_token_accuracy": 0.17109169363975524,
|
|
"num_tokens": 14286920.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.349151277542115,
|
|
"epoch": 0.6508944027697634,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004967506373744039,
|
|
"loss": 6.2187,
|
|
"mean_token_accuracy": 0.16517532244324684,
|
|
"num_tokens": 14299297.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.364994144439697,
|
|
"epoch": 0.651471436814772,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004967436461070805,
|
|
"loss": 6.215,
|
|
"mean_token_accuracy": 0.16879084408283235,
|
|
"num_tokens": 14312107.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.362016820907593,
|
|
"epoch": 0.6520484708597807,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004967366473815196,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.16388487368822097,
|
|
"num_tokens": 14325777.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.399789810180664,
|
|
"epoch": 0.6526255049047894,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004967296411979568,
|
|
"loss": 6.224,
|
|
"mean_token_accuracy": 0.16334544569253923,
|
|
"num_tokens": 14337617.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.287733173370361,
|
|
"epoch": 0.6532025389497981,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004967226275566275,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.17259837239980697,
|
|
"num_tokens": 14349756.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.386903429031372,
|
|
"epoch": 0.6537795729948067,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000496715606457768,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.16123751401901246,
|
|
"num_tokens": 14363358.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.398137712478638,
|
|
"epoch": 0.6543566070398154,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004967085779016142,
|
|
"loss": 6.2254,
|
|
"mean_token_accuracy": 0.1677267700433731,
|
|
"num_tokens": 14375510.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.38195309638977,
|
|
"epoch": 0.654933641084824,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004967015418884022,
|
|
"loss": 6.239,
|
|
"mean_token_accuracy": 0.16811206191778183,
|
|
"num_tokens": 14389523.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.312136507034301,
|
|
"epoch": 0.6555106751298326,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004966944984183692,
|
|
"loss": 6.2165,
|
|
"mean_token_accuracy": 0.1704944595694542,
|
|
"num_tokens": 14400457.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.264360666275024,
|
|
"epoch": 0.6560877091748413,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004966874474917518,
|
|
"loss": 6.1747,
|
|
"mean_token_accuracy": 0.17271694391965867,
|
|
"num_tokens": 14413088.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.444734716415406,
|
|
"epoch": 0.65666474321985,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004966803891087873,
|
|
"loss": 6.2309,
|
|
"mean_token_accuracy": 0.16306148767471312,
|
|
"num_tokens": 14425816.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.303487730026245,
|
|
"epoch": 0.6572417772648587,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000496673323269713,
|
|
"loss": 6.1156,
|
|
"mean_token_accuracy": 0.17381228059530257,
|
|
"num_tokens": 14438739.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.31482458114624,
|
|
"epoch": 0.6578188113098673,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004966662499747666,
|
|
"loss": 6.2582,
|
|
"mean_token_accuracy": 0.16371830701828002,
|
|
"num_tokens": 14451543.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.4650774002075195,
|
|
"epoch": 0.6583958453548759,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004966591692241859,
|
|
"loss": 6.2895,
|
|
"mean_token_accuracy": 0.1613236203789711,
|
|
"num_tokens": 14464969.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.410737085342407,
|
|
"epoch": 0.6589728793998846,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004966520810182092,
|
|
"loss": 6.2467,
|
|
"mean_token_accuracy": 0.16270333379507065,
|
|
"num_tokens": 14477622.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.424910831451416,
|
|
"epoch": 0.6595499134448932,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004966449853570749,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.16616804748773575,
|
|
"num_tokens": 14490306.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.296383047103882,
|
|
"epoch": 0.6601269474899019,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004966378822410215,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.18176421523094177,
|
|
"num_tokens": 14501701.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.349727487564087,
|
|
"epoch": 0.6607039815349106,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004966307716702881,
|
|
"loss": 6.2303,
|
|
"mean_token_accuracy": 0.16906958520412446,
|
|
"num_tokens": 14515700.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.392299318313599,
|
|
"epoch": 0.6612810155799193,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004966236536451138,
|
|
"loss": 6.2194,
|
|
"mean_token_accuracy": 0.1620727926492691,
|
|
"num_tokens": 14528583.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.321354389190674,
|
|
"epoch": 0.6618580496249279,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000496616528165738,
|
|
"loss": 6.1655,
|
|
"mean_token_accuracy": 0.17074524164199828,
|
|
"num_tokens": 14541896.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.323581647872925,
|
|
"epoch": 0.6624350836699365,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004966093952324003,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.1751362219452858,
|
|
"num_tokens": 14556948.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.376759576797485,
|
|
"epoch": 0.6630121177149452,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004966022548453406,
|
|
"loss": 6.2559,
|
|
"mean_token_accuracy": 0.16236974000930787,
|
|
"num_tokens": 14568802.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.376679134368897,
|
|
"epoch": 0.6635891517599538,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004965951070047993,
|
|
"loss": 6.2158,
|
|
"mean_token_accuracy": 0.1644376128911972,
|
|
"num_tokens": 14582664.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.3371021270751955,
|
|
"epoch": 0.6641661858049625,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004965879517110166,
|
|
"loss": 6.3063,
|
|
"mean_token_accuracy": 0.16026860177516938,
|
|
"num_tokens": 14596805.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.394929265975952,
|
|
"epoch": 0.6647432198499712,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004965807889642333,
|
|
"loss": 6.2369,
|
|
"mean_token_accuracy": 0.16370510458946227,
|
|
"num_tokens": 14610532.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.368929100036621,
|
|
"epoch": 0.6653202538949798,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00049657361876469,
|
|
"loss": 6.2615,
|
|
"mean_token_accuracy": 0.16059991121292114,
|
|
"num_tokens": 14622928.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.305924272537231,
|
|
"epoch": 0.6658972879399885,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004965664411126282,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.16946146190166472,
|
|
"num_tokens": 14634410.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.247943449020386,
|
|
"epoch": 0.6664743219849971,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004965592560082894,
|
|
"loss": 6.1508,
|
|
"mean_token_accuracy": 0.16843760758638382,
|
|
"num_tokens": 14647571.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.257874631881714,
|
|
"epoch": 0.6670513560300058,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004965520634519149,
|
|
"loss": 6.0601,
|
|
"mean_token_accuracy": 0.18189057409763337,
|
|
"num_tokens": 14660656.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.397317409515381,
|
|
"epoch": 0.6676283900750144,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004965448634437468,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.16246428936719895,
|
|
"num_tokens": 14672267.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.36127347946167,
|
|
"epoch": 0.668205424120023,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004965376559840272,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.15803717374801635,
|
|
"num_tokens": 14684590.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.369046449661255,
|
|
"epoch": 0.6687824581650318,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004965304410729986,
|
|
"loss": 6.2395,
|
|
"mean_token_accuracy": 0.1638997569680214,
|
|
"num_tokens": 14697299.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.288568830490112,
|
|
"epoch": 0.6693594922100404,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004965232187109037,
|
|
"loss": 6.227,
|
|
"mean_token_accuracy": 0.1662815257906914,
|
|
"num_tokens": 14709328.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.3782798767089846,
|
|
"epoch": 0.6699365262550491,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004965159888979854,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.16616736054420472,
|
|
"num_tokens": 14721786.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.3899914741516115,
|
|
"epoch": 0.6705135603000577,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004965087516344869,
|
|
"loss": 6.2694,
|
|
"mean_token_accuracy": 0.1632115736603737,
|
|
"num_tokens": 14734120.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.351525115966797,
|
|
"epoch": 0.6710905943450663,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004965015069206515,
|
|
"loss": 6.2735,
|
|
"mean_token_accuracy": 0.16400251686573028,
|
|
"num_tokens": 14746159.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.435773468017578,
|
|
"epoch": 0.671667628390075,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000496494254756723,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.1680669292807579,
|
|
"num_tokens": 14758132.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.281584072113037,
|
|
"epoch": 0.6722446624350836,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004964869951429451,
|
|
"loss": 6.0942,
|
|
"mean_token_accuracy": 0.17387358695268632,
|
|
"num_tokens": 14770934.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.296800994873047,
|
|
"epoch": 0.6728216964800924,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004964797280795622,
|
|
"loss": 6.2519,
|
|
"mean_token_accuracy": 0.16522246748209,
|
|
"num_tokens": 14785084.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.402192687988281,
|
|
"epoch": 0.673398730525101,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964724535668188,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.17040158063173294,
|
|
"num_tokens": 14798553.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.397847509384155,
|
|
"epoch": 0.6739757645701097,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004964651716049593,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.16112502813339233,
|
|
"num_tokens": 14810239.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.421293783187866,
|
|
"epoch": 0.6745527986151183,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004964578821942288,
|
|
"loss": 6.2363,
|
|
"mean_token_accuracy": 0.16685911267995834,
|
|
"num_tokens": 14822704.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.395439910888672,
|
|
"epoch": 0.6751298326601269,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004964505853348724,
|
|
"loss": 6.2621,
|
|
"mean_token_accuracy": 0.16632062196731567,
|
|
"num_tokens": 14836913.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.315466976165771,
|
|
"epoch": 0.6757068667051356,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004964432810271356,
|
|
"loss": 6.2172,
|
|
"mean_token_accuracy": 0.16847725361585617,
|
|
"num_tokens": 14849697.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.328092336654663,
|
|
"epoch": 0.6762839007501442,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004964359692712641,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.1680448904633522,
|
|
"num_tokens": 14861719.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.370050001144409,
|
|
"epoch": 0.676860934795153,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004964286500675037,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.169232539832592,
|
|
"num_tokens": 14873786.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.322551298141479,
|
|
"epoch": 0.6774379688401616,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004964213234161007,
|
|
"loss": 6.1336,
|
|
"mean_token_accuracy": 0.16598559767007828,
|
|
"num_tokens": 14888952.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.440288496017456,
|
|
"epoch": 0.6780150028851702,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004964139893173014,
|
|
"loss": 6.2969,
|
|
"mean_token_accuracy": 0.16432846188545228,
|
|
"num_tokens": 14903039.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.347249984741211,
|
|
"epoch": 0.6785920369301789,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004964066477713525,
|
|
"loss": 6.2428,
|
|
"mean_token_accuracy": 0.15882514864206315,
|
|
"num_tokens": 14915949.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.389187002182007,
|
|
"epoch": 0.6791690709751875,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004963992987785011,
|
|
"loss": 6.309,
|
|
"mean_token_accuracy": 0.16167141646146774,
|
|
"num_tokens": 14928724.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.41411247253418,
|
|
"epoch": 0.6797461050201962,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004963919423389942,
|
|
"loss": 6.2041,
|
|
"mean_token_accuracy": 0.16787551641464232,
|
|
"num_tokens": 14941759.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.321781730651855,
|
|
"epoch": 0.6803231390652048,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004963845784530794,
|
|
"loss": 6.2576,
|
|
"mean_token_accuracy": 0.16255476772785188,
|
|
"num_tokens": 14954373.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.33484411239624,
|
|
"epoch": 0.6809001731102136,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000496377207121004,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.17248332351446152,
|
|
"num_tokens": 14966195.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.3584531307220455,
|
|
"epoch": 0.6814772071552222,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004963698283430164,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.16396655291318893,
|
|
"num_tokens": 14979594.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.394085788726807,
|
|
"epoch": 0.6820542412002308,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004963624421193646,
|
|
"loss": 6.2991,
|
|
"mean_token_accuracy": 0.16592729836702347,
|
|
"num_tokens": 14993215.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.433213758468628,
|
|
"epoch": 0.6826312752452395,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000496355048450297,
|
|
"loss": 6.2525,
|
|
"mean_token_accuracy": 0.1618594080209732,
|
|
"num_tokens": 15006241.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.315669107437134,
|
|
"epoch": 0.6832083092902481,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004963476473360623,
|
|
"loss": 6.2196,
|
|
"mean_token_accuracy": 0.1624471828341484,
|
|
"num_tokens": 15018750.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.291262006759643,
|
|
"epoch": 0.6837853433352568,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004963402387769094,
|
|
"loss": 6.171,
|
|
"mean_token_accuracy": 0.16801615953445434,
|
|
"num_tokens": 15031065.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.385349893569947,
|
|
"epoch": 0.6843623773802654,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004963328227730876,
|
|
"loss": 6.1904,
|
|
"mean_token_accuracy": 0.16905016154050828,
|
|
"num_tokens": 15043129.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.352339839935302,
|
|
"epoch": 0.684939411425274,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004963253993248461,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.16816207468509675,
|
|
"num_tokens": 15057531.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.342672061920166,
|
|
"epoch": 0.6855164454702828,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004963179684324349,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.16352169662714006,
|
|
"num_tokens": 15070105.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.41286940574646,
|
|
"epoch": 0.6860934795152914,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004963105300961036,
|
|
"loss": 6.2282,
|
|
"mean_token_accuracy": 0.15723423808813095,
|
|
"num_tokens": 15082482.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.369506120681763,
|
|
"epoch": 0.6866705135603001,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004963030843161026,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.15877436846494675,
|
|
"num_tokens": 15095564.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.4327515125274655,
|
|
"epoch": 0.6872475476053087,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004962956310926823,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.15945251435041427,
|
|
"num_tokens": 15108948.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.3614583015441895,
|
|
"epoch": 0.6878245816503173,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004962881704260934,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.16766972094774246,
|
|
"num_tokens": 15121537.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.282821607589722,
|
|
"epoch": 0.688401615695326,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004962807023165868,
|
|
"loss": 6.1881,
|
|
"mean_token_accuracy": 0.17159215807914735,
|
|
"num_tokens": 15134657.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.340293598175049,
|
|
"epoch": 0.6889786497403346,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004962732267644138,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.17035603374242783,
|
|
"num_tokens": 15146301.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.32009449005127,
|
|
"epoch": 0.6895556837853434,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004962657437698254,
|
|
"loss": 6.2484,
|
|
"mean_token_accuracy": 0.16358525454998016,
|
|
"num_tokens": 15157886.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.3822681427001955,
|
|
"epoch": 0.690132717830352,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004962582533330739,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.1663409873843193,
|
|
"num_tokens": 15170457.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.350669097900391,
|
|
"epoch": 0.6907097518753607,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004962507554544109,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.16517189443111419,
|
|
"num_tokens": 15182504.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.3586745262146,
|
|
"epoch": 0.6912867859203693,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004962432501340886,
|
|
"loss": 6.2435,
|
|
"mean_token_accuracy": 0.1614229127764702,
|
|
"num_tokens": 15194809.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.367116832733155,
|
|
"epoch": 0.6918638199653779,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004962357373723596,
|
|
"loss": 6.1836,
|
|
"mean_token_accuracy": 0.1651404932141304,
|
|
"num_tokens": 15207185.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.353478956222534,
|
|
"epoch": 0.6924408540103866,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004962282171694763,
|
|
"loss": 6.2033,
|
|
"mean_token_accuracy": 0.16734539121389388,
|
|
"num_tokens": 15220406.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6924408540103866,
|
|
"eval_entropy": 6.138688796956939,
|
|
"eval_loss": 6.260073184967041,
|
|
"eval_mean_token_accuracy": 0.16800092866038918,
|
|
"eval_num_tokens": 15220406.0,
|
|
"eval_runtime": 17.4454,
|
|
"eval_samples_per_second": 1612.801,
|
|
"eval_steps_per_second": 201.6,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.357237100601196,
|
|
"epoch": 0.6930178880553952,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004962206895256919,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.1609627515077591,
|
|
"num_tokens": 15231698.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.401620817184448,
|
|
"epoch": 0.693594922100404,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004962131544412595,
|
|
"loss": 6.2855,
|
|
"mean_token_accuracy": 0.15989433825016022,
|
|
"num_tokens": 15243462.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.4744181632995605,
|
|
"epoch": 0.6941719561454126,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004962056119164325,
|
|
"loss": 6.2977,
|
|
"mean_token_accuracy": 0.1585573062300682,
|
|
"num_tokens": 15257311.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.325224685668945,
|
|
"epoch": 0.6947489901904212,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004961980619514646,
|
|
"loss": 6.2524,
|
|
"mean_token_accuracy": 0.1612841933965683,
|
|
"num_tokens": 15270186.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.312858438491821,
|
|
"epoch": 0.6953260242354299,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004961905045466098,
|
|
"loss": 6.2041,
|
|
"mean_token_accuracy": 0.16199923306703568,
|
|
"num_tokens": 15282573.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.426106882095337,
|
|
"epoch": 0.6959030582804385,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004961829397021222,
|
|
"loss": 6.2437,
|
|
"mean_token_accuracy": 0.1614992082118988,
|
|
"num_tokens": 15296721.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.397392511367798,
|
|
"epoch": 0.6964800923254472,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004961753674182564,
|
|
"loss": 6.2139,
|
|
"mean_token_accuracy": 0.1720279037952423,
|
|
"num_tokens": 15308458.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.355577421188355,
|
|
"epoch": 0.6970571263704558,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004961677876952669,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.1608239158987999,
|
|
"num_tokens": 15320402.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.395686626434326,
|
|
"epoch": 0.6976341604154646,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004961602005334087,
|
|
"loss": 6.2689,
|
|
"mean_token_accuracy": 0.16339593529701232,
|
|
"num_tokens": 15333196.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.311012077331543,
|
|
"epoch": 0.6982111944604732,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000496152605932937,
|
|
"loss": 6.1947,
|
|
"mean_token_accuracy": 0.16391687095165253,
|
|
"num_tokens": 15345216.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.369989585876465,
|
|
"epoch": 0.6987882285054818,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004961450038941074,
|
|
"loss": 6.2674,
|
|
"mean_token_accuracy": 0.16239935606718064,
|
|
"num_tokens": 15357772.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.377553176879883,
|
|
"epoch": 0.6993652625504905,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004961373944171754,
|
|
"loss": 6.1635,
|
|
"mean_token_accuracy": 0.16831500232219695,
|
|
"num_tokens": 15371110.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.268352222442627,
|
|
"epoch": 0.6999422965954991,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004961297775023968,
|
|
"loss": 6.1729,
|
|
"mean_token_accuracy": 0.16793664395809174,
|
|
"num_tokens": 15383731.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.407302713394165,
|
|
"epoch": 0.7005193306405078,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000496122153150028,
|
|
"loss": 6.2077,
|
|
"mean_token_accuracy": 0.1660628244280815,
|
|
"num_tokens": 15395849.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.384264755249023,
|
|
"epoch": 0.7010963646855164,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004961145213603255,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.16858903616666793,
|
|
"num_tokens": 15408552.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.338636875152588,
|
|
"epoch": 0.7016733987305251,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000496106882133546,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.16671737134456635,
|
|
"num_tokens": 15421940.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.291077041625977,
|
|
"epoch": 0.7022504327755338,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004960992354699463,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.16258899569511415,
|
|
"num_tokens": 15434232.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.414277458190918,
|
|
"epoch": 0.7028274668205424,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004960915813697836,
|
|
"loss": 6.2098,
|
|
"mean_token_accuracy": 0.15860261023044586,
|
|
"num_tokens": 15448052.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.392745780944824,
|
|
"epoch": 0.7034045008655511,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004960839198333154,
|
|
"loss": 6.1144,
|
|
"mean_token_accuracy": 0.17049459218978882,
|
|
"num_tokens": 15459141.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.240172338485718,
|
|
"epoch": 0.7039815349105597,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004960762508607994,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.1716955214738846,
|
|
"num_tokens": 15471705.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.309173583984375,
|
|
"epoch": 0.7045585689555683,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004960685744524934,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.16721562147140503,
|
|
"num_tokens": 15484821.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.386078023910523,
|
|
"epoch": 0.705135603000577,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004960608906086558,
|
|
"loss": 6.2208,
|
|
"mean_token_accuracy": 0.16064056158065795,
|
|
"num_tokens": 15497157.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.34077033996582,
|
|
"epoch": 0.7057126370455857,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000496053199329545,
|
|
"loss": 6.2138,
|
|
"mean_token_accuracy": 0.16658349484205245,
|
|
"num_tokens": 15508919.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.398518896102905,
|
|
"epoch": 0.7062896710905944,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004960455006154196,
|
|
"loss": 6.2674,
|
|
"mean_token_accuracy": 0.16163421869277955,
|
|
"num_tokens": 15521235.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.367052125930786,
|
|
"epoch": 0.706866705135603,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004960377944665386,
|
|
"loss": 6.2191,
|
|
"mean_token_accuracy": 0.16501127034425736,
|
|
"num_tokens": 15534278.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.294226884841919,
|
|
"epoch": 0.7074437391806117,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004960300808831611,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.1696803465485573,
|
|
"num_tokens": 15548034.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.381236171722412,
|
|
"epoch": 0.7080207732256203,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004960223598655467,
|
|
"loss": 6.1555,
|
|
"mean_token_accuracy": 0.17080835551023482,
|
|
"num_tokens": 15559425.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.433323335647583,
|
|
"epoch": 0.7085978072706289,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000496014631413955,
|
|
"loss": 6.2619,
|
|
"mean_token_accuracy": 0.1681198939681053,
|
|
"num_tokens": 15570634.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.356976652145386,
|
|
"epoch": 0.7091748413156376,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004960068955286459,
|
|
"loss": 6.2906,
|
|
"mean_token_accuracy": 0.16518030315637589,
|
|
"num_tokens": 15582710.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.378293657302857,
|
|
"epoch": 0.7097518753606463,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004959991522098797,
|
|
"loss": 6.227,
|
|
"mean_token_accuracy": 0.15896626859903334,
|
|
"num_tokens": 15594798.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.364326047897339,
|
|
"epoch": 0.710328909405655,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004959914014579168,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.17040738612413406,
|
|
"num_tokens": 15606482.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.359493207931519,
|
|
"epoch": 0.7109059434506636,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004959836432730178,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.17176218777894975,
|
|
"num_tokens": 15620178.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.3298866748809814,
|
|
"epoch": 0.7114829774956722,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004959758776554438,
|
|
"loss": 6.1991,
|
|
"mean_token_accuracy": 0.16317809075117112,
|
|
"num_tokens": 15632469.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.403311443328858,
|
|
"epoch": 0.7120600115406809,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000495968104605456,
|
|
"loss": 6.2258,
|
|
"mean_token_accuracy": 0.1647837668657303,
|
|
"num_tokens": 15645610.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.398124265670776,
|
|
"epoch": 0.7126370455856895,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004959603241233157,
|
|
"loss": 6.2062,
|
|
"mean_token_accuracy": 0.16843665093183519,
|
|
"num_tokens": 15657716.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.339931488037109,
|
|
"epoch": 0.7132140796306982,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004959525362092846,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.16136354058980942,
|
|
"num_tokens": 15670258.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.348710298538208,
|
|
"epoch": 0.7137911136757069,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004959447408636247,
|
|
"loss": 6.1538,
|
|
"mean_token_accuracy": 0.16794612407684326,
|
|
"num_tokens": 15681196.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.416023778915405,
|
|
"epoch": 0.7143681477207156,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004959369380865983,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.16282055974006654,
|
|
"num_tokens": 15694591.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.293649387359619,
|
|
"epoch": 0.7149451817657242,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004959291278784676,
|
|
"loss": 6.1255,
|
|
"mean_token_accuracy": 0.17489954084157944,
|
|
"num_tokens": 15708272.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.3302257537841795,
|
|
"epoch": 0.7155222158107328,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004959213102394954,
|
|
"loss": 6.1724,
|
|
"mean_token_accuracy": 0.172370782494545,
|
|
"num_tokens": 15720136.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.36483941078186,
|
|
"epoch": 0.7160992498557415,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004959134851699449,
|
|
"loss": 6.1565,
|
|
"mean_token_accuracy": 0.16822995990514755,
|
|
"num_tokens": 15732043.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.360851812362671,
|
|
"epoch": 0.7166762839007501,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004959056526700788,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.16269091218709947,
|
|
"num_tokens": 15743471.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.3516560077667235,
|
|
"epoch": 0.7172533179457588,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004958978127401609,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.16105854660272598,
|
|
"num_tokens": 15756846.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.33987021446228,
|
|
"epoch": 0.7178303519907675,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004958899653804548,
|
|
"loss": 6.2435,
|
|
"mean_token_accuracy": 0.16606948673725128,
|
|
"num_tokens": 15769993.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.313188934326172,
|
|
"epoch": 0.7184073860357761,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004958821105912246,
|
|
"loss": 6.2005,
|
|
"mean_token_accuracy": 0.16074076294898987,
|
|
"num_tokens": 15782081.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.374634170532227,
|
|
"epoch": 0.7189844200807848,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000495874248372734,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.16276226937770844,
|
|
"num_tokens": 15793987.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.337182664871216,
|
|
"epoch": 0.7195614541257934,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000495866378725248,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.17333306670188903,
|
|
"num_tokens": 15805749.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.28895583152771,
|
|
"epoch": 0.7201384881708021,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000495858501649031,
|
|
"loss": 6.1259,
|
|
"mean_token_accuracy": 0.16905360966920852,
|
|
"num_tokens": 15818402.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.330921030044555,
|
|
"epoch": 0.7207155222158107,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000495850617144348,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.17487937062978745,
|
|
"num_tokens": 15830783.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.27276611328125,
|
|
"epoch": 0.7212925562608193,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004958427252114643,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.17082489728927613,
|
|
"num_tokens": 15843231.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.2428213596344,
|
|
"epoch": 0.7218695903058281,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000495834825850645,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.18071018308401107,
|
|
"num_tokens": 15855770.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.374913215637207,
|
|
"epoch": 0.7224466243508367,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004958269190621562,
|
|
"loss": 6.217,
|
|
"mean_token_accuracy": 0.16166453212499618,
|
|
"num_tokens": 15867979.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.3626570224761965,
|
|
"epoch": 0.7230236583958454,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004958190048462637,
|
|
"loss": 6.2482,
|
|
"mean_token_accuracy": 0.16734726279973983,
|
|
"num_tokens": 15880878.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.319369268417359,
|
|
"epoch": 0.723600692440854,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004958110832032336,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.17133153825998307,
|
|
"num_tokens": 15893599.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.27418155670166,
|
|
"epoch": 0.7241777264858626,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004958031541333322,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.1716024547815323,
|
|
"num_tokens": 15906566.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.375898981094361,
|
|
"epoch": 0.7247547605308713,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004957952176368267,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.1673166960477829,
|
|
"num_tokens": 15920269.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.341583919525147,
|
|
"epoch": 0.7253317945758799,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004957872737139836,
|
|
"loss": 6.2241,
|
|
"mean_token_accuracy": 0.16209050118923188,
|
|
"num_tokens": 15932559.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.335490465164185,
|
|
"epoch": 0.7259088286208887,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004957793223650702,
|
|
"loss": 6.1512,
|
|
"mean_token_accuracy": 0.1637295514345169,
|
|
"num_tokens": 15945554.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.312412452697754,
|
|
"epoch": 0.7264858626658973,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000495771363590354,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.17415805906057358,
|
|
"num_tokens": 15958012.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.353401374816895,
|
|
"epoch": 0.727062896710906,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004957633973901027,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.16412369459867476,
|
|
"num_tokens": 15971508.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.341835260391235,
|
|
"epoch": 0.7276399307559146,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004957554237645841,
|
|
"loss": 6.1554,
|
|
"mean_token_accuracy": 0.16791654974222184,
|
|
"num_tokens": 15983445.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.353136157989502,
|
|
"epoch": 0.7282169648009232,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004957474427140665,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.16680117100477218,
|
|
"num_tokens": 15995936.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.2642029285430905,
|
|
"epoch": 0.7287939988459319,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004957394542388182,
|
|
"loss": 6.1553,
|
|
"mean_token_accuracy": 0.17148637622594834,
|
|
"num_tokens": 16008192.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.396103096008301,
|
|
"epoch": 0.7293710328909405,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004957314583391082,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.16379689127206803,
|
|
"num_tokens": 16020585.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.400233268737793,
|
|
"epoch": 0.7299480669359493,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004957234550152052,
|
|
"loss": 6.2545,
|
|
"mean_token_accuracy": 0.1623969241976738,
|
|
"num_tokens": 16032627.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.392393779754639,
|
|
"epoch": 0.7305251009809579,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004957154442673784,
|
|
"loss": 6.1956,
|
|
"mean_token_accuracy": 0.1705213487148285,
|
|
"num_tokens": 16047196.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.317262935638428,
|
|
"epoch": 0.7311021350259665,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004957074260958972,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.166448113322258,
|
|
"num_tokens": 16059875.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.392600727081299,
|
|
"epoch": 0.7316791690709752,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004956994005010315,
|
|
"loss": 6.2114,
|
|
"mean_token_accuracy": 0.1701406717300415,
|
|
"num_tokens": 16071991.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.372545003890991,
|
|
"epoch": 0.7322562031159838,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000495691367483051,
|
|
"loss": 6.2525,
|
|
"mean_token_accuracy": 0.15873659104108812,
|
|
"num_tokens": 16085628.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.351456260681152,
|
|
"epoch": 0.7328332371609925,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004956833270422259,
|
|
"loss": 6.2165,
|
|
"mean_token_accuracy": 0.16475701630115508,
|
|
"num_tokens": 16098020.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.362127590179443,
|
|
"epoch": 0.7334102712060011,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004956752791788269,
|
|
"loss": 6.1462,
|
|
"mean_token_accuracy": 0.16634501665830612,
|
|
"num_tokens": 16109965.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.373689317703247,
|
|
"epoch": 0.7339873052510099,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004956672238931244,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.16246710792183877,
|
|
"num_tokens": 16121891.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.40177731513977,
|
|
"epoch": 0.7345643392960185,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004956591611853894,
|
|
"loss": 6.1647,
|
|
"mean_token_accuracy": 0.16610097885131836,
|
|
"num_tokens": 16134181.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.373047256469727,
|
|
"epoch": 0.7351413733410271,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004956510910558931,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.1654479667544365,
|
|
"num_tokens": 16146685.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.26585111618042,
|
|
"epoch": 0.7357184073860358,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004956430135049071,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.1662848874926567,
|
|
"num_tokens": 16159618.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.392060470581055,
|
|
"epoch": 0.7362954414310444,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004956349285327028,
|
|
"loss": 6.1032,
|
|
"mean_token_accuracy": 0.17501070201396943,
|
|
"num_tokens": 16172162.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.330788850784302,
|
|
"epoch": 0.7368724754760531,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004956268361395523,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.16330249309539796,
|
|
"num_tokens": 16184663.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.341895961761475,
|
|
"epoch": 0.7374495095210617,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004956187363257278,
|
|
"loss": 6.1909,
|
|
"mean_token_accuracy": 0.16805584877729415,
|
|
"num_tokens": 16196459.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.408393335342407,
|
|
"epoch": 0.7380265435660704,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004956106290915017,
|
|
"loss": 6.2057,
|
|
"mean_token_accuracy": 0.1656257450580597,
|
|
"num_tokens": 16208008.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.361274671554566,
|
|
"epoch": 0.7386035776110791,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004956025144371467,
|
|
"loss": 6.2381,
|
|
"mean_token_accuracy": 0.16646528393030166,
|
|
"num_tokens": 16221844.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.344065237045288,
|
|
"epoch": 0.7391806116560877,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004955943923629356,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.16411988735198973,
|
|
"num_tokens": 16234773.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.274953842163086,
|
|
"epoch": 0.7397576457010964,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004955862628691417,
|
|
"loss": 6.1179,
|
|
"mean_token_accuracy": 0.173089899122715,
|
|
"num_tokens": 16247464.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.447964525222778,
|
|
"epoch": 0.740334679746105,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004955781259560386,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.1572584852576256,
|
|
"num_tokens": 16259947.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.422522401809692,
|
|
"epoch": 0.7409117137911136,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004955699816238995,
|
|
"loss": 6.3076,
|
|
"mean_token_accuracy": 0.1625203400850296,
|
|
"num_tokens": 16272280.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.374295711517334,
|
|
"epoch": 0.7414887478361223,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004955618298729988,
|
|
"loss": 6.1882,
|
|
"mean_token_accuracy": 0.16504510641098022,
|
|
"num_tokens": 16284476.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.312162399291992,
|
|
"epoch": 0.742065781881131,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004955536707036105,
|
|
"loss": 6.1115,
|
|
"mean_token_accuracy": 0.16799768358469008,
|
|
"num_tokens": 16296877.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.271811151504517,
|
|
"epoch": 0.7426428159261397,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.000495545504116009,
|
|
"loss": 6.1095,
|
|
"mean_token_accuracy": 0.1740468755364418,
|
|
"num_tokens": 16310360.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.435547924041748,
|
|
"epoch": 0.7432198499711483,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004955373301104691,
|
|
"loss": 6.27,
|
|
"mean_token_accuracy": 0.15865596383810043,
|
|
"num_tokens": 16322965.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.338442611694336,
|
|
"epoch": 0.743796884016157,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004955291486872657,
|
|
"loss": 6.2202,
|
|
"mean_token_accuracy": 0.1622794598340988,
|
|
"num_tokens": 16337756.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.373736047744751,
|
|
"epoch": 0.7443739180611656,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004955209598466738,
|
|
"loss": 6.1571,
|
|
"mean_token_accuracy": 0.16572255790233612,
|
|
"num_tokens": 16350400.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.42721381187439,
|
|
"epoch": 0.7449509521061742,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000495512763588969,
|
|
"loss": 6.2663,
|
|
"mean_token_accuracy": 0.15915481746196747,
|
|
"num_tokens": 16363655.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.382620811462402,
|
|
"epoch": 0.7455279861511829,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004955045599144269,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.17301644384860992,
|
|
"num_tokens": 16375580.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.357531595230102,
|
|
"epoch": 0.7461050201961916,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004954963488233235,
|
|
"loss": 6.2241,
|
|
"mean_token_accuracy": 0.16709440499544143,
|
|
"num_tokens": 16388447.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.347971868515015,
|
|
"epoch": 0.7466820542412003,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000495488130315935,
|
|
"loss": 6.1107,
|
|
"mean_token_accuracy": 0.1755620315670967,
|
|
"num_tokens": 16401082.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.280410528182983,
|
|
"epoch": 0.7472590882862089,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004954799043925377,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.16513099819421767,
|
|
"num_tokens": 16415108.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.3362969875335695,
|
|
"epoch": 0.7478361223312175,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004954716710534082,
|
|
"loss": 6.0848,
|
|
"mean_token_accuracy": 0.17339474856853485,
|
|
"num_tokens": 16427562.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.31677737236023,
|
|
"epoch": 0.7484131563762262,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004954634302988237,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.16748676151037217,
|
|
"num_tokens": 16441282.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.341112232208252,
|
|
"epoch": 0.7489901904212348,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004954551821290612,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.16641539484262466,
|
|
"num_tokens": 16453433.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.341647577285767,
|
|
"epoch": 0.7495672244662435,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004954469265443981,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.16345324069261552,
|
|
"num_tokens": 16466216.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.353080177307129,
|
|
"epoch": 0.7501442585112522,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004954386635451123,
|
|
"loss": 6.1845,
|
|
"mean_token_accuracy": 0.1658550977706909,
|
|
"num_tokens": 16479046.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.29761233329773,
|
|
"epoch": 0.7507212925562609,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004954303931314814,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.1719191774725914,
|
|
"num_tokens": 16491407.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.368516111373902,
|
|
"epoch": 0.7512983266012695,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004954221153037837,
|
|
"loss": 6.1414,
|
|
"mean_token_accuracy": 0.1638320803642273,
|
|
"num_tokens": 16504726.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.40753402709961,
|
|
"epoch": 0.7518753606462781,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004954138300622978,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.16406668722629547,
|
|
"num_tokens": 16517835.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.360999631881714,
|
|
"epoch": 0.7524523946912868,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000495405537407302,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.1658797487616539,
|
|
"num_tokens": 16532018.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.297806024551392,
|
|
"epoch": 0.7530294287362954,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004953972373390755,
|
|
"loss": 6.1618,
|
|
"mean_token_accuracy": 0.17094711363315582,
|
|
"num_tokens": 16546211.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.406245517730713,
|
|
"epoch": 0.753606462781304,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953889298578975,
|
|
"loss": 6.2121,
|
|
"mean_token_accuracy": 0.16255346834659576,
|
|
"num_tokens": 16559788.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.26466932296753,
|
|
"epoch": 0.7541834968263128,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004953806149640473,
|
|
"loss": 6.0753,
|
|
"mean_token_accuracy": 0.17620715349912644,
|
|
"num_tokens": 16573694.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.351998710632325,
|
|
"epoch": 0.7547605308713214,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004953722926578045,
|
|
"loss": 6.1705,
|
|
"mean_token_accuracy": 0.16607727259397506,
|
|
"num_tokens": 16585506.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.285213470458984,
|
|
"epoch": 0.7553375649163301,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004953639629394492,
|
|
"loss": 6.2271,
|
|
"mean_token_accuracy": 0.1645355686545372,
|
|
"num_tokens": 16598991.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.40970253944397,
|
|
"epoch": 0.7559145989613387,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953556258092613,
|
|
"loss": 6.227,
|
|
"mean_token_accuracy": 0.1658835232257843,
|
|
"num_tokens": 16612025.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.334483432769775,
|
|
"epoch": 0.7564916330063474,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004953472812675216,
|
|
"loss": 6.1364,
|
|
"mean_token_accuracy": 0.17058963626623153,
|
|
"num_tokens": 16624509.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.275288057327271,
|
|
"epoch": 0.757068667051356,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004953389293145104,
|
|
"loss": 6.1552,
|
|
"mean_token_accuracy": 0.16298312842845916,
|
|
"num_tokens": 16636920.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.296596527099609,
|
|
"epoch": 0.7576457010963646,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004953305699505088,
|
|
"loss": 6.0867,
|
|
"mean_token_accuracy": 0.17344891875982285,
|
|
"num_tokens": 16649381.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.368966484069825,
|
|
"epoch": 0.7582227351413734,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004953222031757979,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.15837449729442596,
|
|
"num_tokens": 16662273.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.372677612304687,
|
|
"epoch": 0.758799769186382,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004953138289906592,
|
|
"loss": 6.1871,
|
|
"mean_token_accuracy": 0.17127318382263185,
|
|
"num_tokens": 16675184.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.309050750732422,
|
|
"epoch": 0.7593768032313907,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004953054473953742,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.1698559433221817,
|
|
"num_tokens": 16687658.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.365961122512817,
|
|
"epoch": 0.7599538372763993,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004952970583902251,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.1670696035027504,
|
|
"num_tokens": 16699806.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.3373250484466555,
|
|
"epoch": 0.760530871321408,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004952886619754937,
|
|
"loss": 6.1879,
|
|
"mean_token_accuracy": 0.17124574780464172,
|
|
"num_tokens": 16712647.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.343024015426636,
|
|
"epoch": 0.7611079053664166,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004952802581514625,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.16678574532270432,
|
|
"num_tokens": 16725438.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.330097246170044,
|
|
"epoch": 0.7616849394114252,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004952718469184144,
|
|
"loss": 6.1548,
|
|
"mean_token_accuracy": 0.17337974458932875,
|
|
"num_tokens": 16737346.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.348900222778321,
|
|
"epoch": 0.762261973456434,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004952634282766322,
|
|
"loss": 6.1497,
|
|
"mean_token_accuracy": 0.17005545794963836,
|
|
"num_tokens": 16749327.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.330654907226562,
|
|
"epoch": 0.7628390075014426,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004952550022263988,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.17179016321897506,
|
|
"num_tokens": 16761323.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.349520587921143,
|
|
"epoch": 0.7634160415464513,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004952465687679979,
|
|
"loss": 6.254,
|
|
"mean_token_accuracy": 0.16122461408376693,
|
|
"num_tokens": 16774688.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.431204414367675,
|
|
"epoch": 0.7639930755914599,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000495238127901713,
|
|
"loss": 6.2608,
|
|
"mean_token_accuracy": 0.16095422506332396,
|
|
"num_tokens": 16787538.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.314582109451294,
|
|
"epoch": 0.7645701096364685,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004952296796278282,
|
|
"loss": 6.1283,
|
|
"mean_token_accuracy": 0.17241402566432953,
|
|
"num_tokens": 16798642.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.355658340454101,
|
|
"epoch": 0.7651471436814772,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004952212239466274,
|
|
"loss": 6.2645,
|
|
"mean_token_accuracy": 0.1689286157488823,
|
|
"num_tokens": 16810785.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.409767293930054,
|
|
"epoch": 0.7657241777264858,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952127608583953,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.16363934576511383,
|
|
"num_tokens": 16823978.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.358902454376221,
|
|
"epoch": 0.7663012117714946,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952042903634162,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.17277514338493347,
|
|
"num_tokens": 16836878.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.344875907897949,
|
|
"epoch": 0.7668782458165032,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004951958124619752,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.17383748292922974,
|
|
"num_tokens": 16849849.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.34850664138794,
|
|
"epoch": 0.7674552798615119,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004951873271543573,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.16859251111745835,
|
|
"num_tokens": 16862022.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.438310003280639,
|
|
"epoch": 0.7680323139065205,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004951788344408483,
|
|
"loss": 6.2359,
|
|
"mean_token_accuracy": 0.1643815368413925,
|
|
"num_tokens": 16875421.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.322825193405151,
|
|
"epoch": 0.7686093479515291,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004951703343217335,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.1841158390045166,
|
|
"num_tokens": 16889520.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.2558657169342045,
|
|
"epoch": 0.7691863819965378,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004951618267972987,
|
|
"loss": 6.1407,
|
|
"mean_token_accuracy": 0.1638886660337448,
|
|
"num_tokens": 16901449.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.402849817276001,
|
|
"epoch": 0.7697634160415464,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004951533118678304,
|
|
"loss": 6.2012,
|
|
"mean_token_accuracy": 0.16906618624925612,
|
|
"num_tokens": 16914742.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.444267988204956,
|
|
"epoch": 0.7703404500865552,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004951447895336147,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.16533467471599578,
|
|
"num_tokens": 16926645.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.32177734375,
|
|
"epoch": 0.7709174841315638,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004951362597949384,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.17496459186077118,
|
|
"num_tokens": 16939499.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.331139373779297,
|
|
"epoch": 0.7714945181765724,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004951277226520883,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.17526398450136185,
|
|
"num_tokens": 16951811.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.298669147491455,
|
|
"epoch": 0.7720715522215811,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004951191781053517,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.1653261348605156,
|
|
"num_tokens": 16963126.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.357400894165039,
|
|
"epoch": 0.7726485862665897,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004951106261550157,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.16687628626823425,
|
|
"num_tokens": 16976853.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.332295179367065,
|
|
"epoch": 0.7732256203115984,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004951020668013683,
|
|
"loss": 6.1921,
|
|
"mean_token_accuracy": 0.16649820208549498,
|
|
"num_tokens": 16988720.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.289232921600342,
|
|
"epoch": 0.773802654356607,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004950935000446972,
|
|
"loss": 6.0953,
|
|
"mean_token_accuracy": 0.17749709784984588,
|
|
"num_tokens": 17000880.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.218468427658081,
|
|
"epoch": 0.7743796884016156,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004950849258852905,
|
|
"loss": 5.975,
|
|
"mean_token_accuracy": 0.18584768772125243,
|
|
"num_tokens": 17012540.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.276014614105224,
|
|
"epoch": 0.7749567224466244,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004950763443234366,
|
|
"loss": 6.1089,
|
|
"mean_token_accuracy": 0.17434907257556914,
|
|
"num_tokens": 17024163.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.373161888122558,
|
|
"epoch": 0.775533756491633,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004950677553594243,
|
|
"loss": 6.1703,
|
|
"mean_token_accuracy": 0.16294383704662324,
|
|
"num_tokens": 17037020.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.388097143173217,
|
|
"epoch": 0.7761107905366417,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004950591589935422,
|
|
"loss": 6.1987,
|
|
"mean_token_accuracy": 0.16396149396896362,
|
|
"num_tokens": 17050132.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.318562936782837,
|
|
"epoch": 0.7766878245816503,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004950505552260798,
|
|
"loss": 6.131,
|
|
"mean_token_accuracy": 0.1698935002088547,
|
|
"num_tokens": 17063299.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.272518539428711,
|
|
"epoch": 0.777264858626659,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004950419440573261,
|
|
"loss": 6.1875,
|
|
"mean_token_accuracy": 0.16989706754684447,
|
|
"num_tokens": 17076312.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.288555431365967,
|
|
"epoch": 0.7778418926716676,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000495033325487571,
|
|
"loss": 6.1588,
|
|
"mean_token_accuracy": 0.16710376292467116,
|
|
"num_tokens": 17089040.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.420559310913086,
|
|
"epoch": 0.7784189267166762,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004950246995171042,
|
|
"loss": 6.2479,
|
|
"mean_token_accuracy": 0.16628091037273407,
|
|
"num_tokens": 17102806.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.293579626083374,
|
|
"epoch": 0.778995960761685,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000495016066146216,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.17714409083127974,
|
|
"num_tokens": 17114782.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.290708208084107,
|
|
"epoch": 0.7795729948066936,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004950074253751968,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.17414961010217667,
|
|
"num_tokens": 17127386.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.3170980453491214,
|
|
"epoch": 0.7801500288517023,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000494998777204337,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.17070301622152328,
|
|
"num_tokens": 17139244.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.375906133651734,
|
|
"epoch": 0.7807270628967109,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004949901216339276,
|
|
"loss": 6.238,
|
|
"mean_token_accuracy": 0.16011236011981964,
|
|
"num_tokens": 17153136.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.350481653213501,
|
|
"epoch": 0.7813040969417195,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004949814586642598,
|
|
"loss": 6.1064,
|
|
"mean_token_accuracy": 0.16930470615625381,
|
|
"num_tokens": 17166420.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.382876300811768,
|
|
"epoch": 0.7818811309867282,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000494972788295625,
|
|
"loss": 6.2473,
|
|
"mean_token_accuracy": 0.1569085404276848,
|
|
"num_tokens": 17180796.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.390883731842041,
|
|
"epoch": 0.7824581650317368,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004949641105283144,
|
|
"loss": 6.1946,
|
|
"mean_token_accuracy": 0.16438286751508713,
|
|
"num_tokens": 17192275.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.299509429931641,
|
|
"epoch": 0.7830351990767456,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004949554253626205,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.16779853105545045,
|
|
"num_tokens": 17203651.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.4158844470977785,
|
|
"epoch": 0.7836122331217542,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004949467327988351,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.1698895961046219,
|
|
"num_tokens": 17216521.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.3239830493927,
|
|
"epoch": 0.7841892671667628,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004949380328372505,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.17289299368858338,
|
|
"num_tokens": 17228435.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.310701036453247,
|
|
"epoch": 0.7847663012117715,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004949293254781595,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.1724423810839653,
|
|
"num_tokens": 17240746.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.214282369613647,
|
|
"epoch": 0.7853433352567801,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004949206107218547,
|
|
"loss": 6.0893,
|
|
"mean_token_accuracy": 0.17622702717781066,
|
|
"num_tokens": 17254089.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.303280830383301,
|
|
"epoch": 0.7859203693017888,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004949118885686296,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.17078900188207627,
|
|
"num_tokens": 17266389.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.357765245437622,
|
|
"epoch": 0.7864974033467974,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004949031590187774,
|
|
"loss": 6.1259,
|
|
"mean_token_accuracy": 0.16939014941453934,
|
|
"num_tokens": 17279049.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.336352300643921,
|
|
"epoch": 0.7870744373918062,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004948944220725915,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.16172609031200408,
|
|
"num_tokens": 17291134.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.3349395275115965,
|
|
"epoch": 0.7876514714368148,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000494885677730366,
|
|
"loss": 6.0774,
|
|
"mean_token_accuracy": 0.17785610109567643,
|
|
"num_tokens": 17304728.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.35065221786499,
|
|
"epoch": 0.7882285054818234,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000494876925992395,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.1673291355371475,
|
|
"num_tokens": 17317392.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.2910408020019535,
|
|
"epoch": 0.7888055395268321,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004948681668589728,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.17116876244544982,
|
|
"num_tokens": 17329639.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.320131015777588,
|
|
"epoch": 0.7893825735718407,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000494859400330394,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.17031224071979523,
|
|
"num_tokens": 17341246.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.345110988616943,
|
|
"epoch": 0.7899596076168494,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004948506264069535,
|
|
"loss": 6.1563,
|
|
"mean_token_accuracy": 0.1687989354133606,
|
|
"num_tokens": 17353699.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.347292232513428,
|
|
"epoch": 0.790536641661858,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004948418450889464,
|
|
"loss": 6.1477,
|
|
"mean_token_accuracy": 0.1734479546546936,
|
|
"num_tokens": 17365950.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.2546172618865965,
|
|
"epoch": 0.7911136757068667,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000494833056376668,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.17194298207759856,
|
|
"num_tokens": 17378654.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.282538604736328,
|
|
"epoch": 0.7916907097518754,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004948242602704139,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.17186086624860764,
|
|
"num_tokens": 17391354.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.336555099487304,
|
|
"epoch": 0.792267743796884,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004948154567704801,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.17139652073383332,
|
|
"num_tokens": 17403019.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.305984163284302,
|
|
"epoch": 0.7928447778418927,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004948066458771625,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.17206017225980758,
|
|
"num_tokens": 17415886.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.384555387496948,
|
|
"epoch": 0.7934218118869013,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004947978275907577,
|
|
"loss": 6.272,
|
|
"mean_token_accuracy": 0.1580319046974182,
|
|
"num_tokens": 17429734.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.387654590606689,
|
|
"epoch": 0.79399884593191,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000494789001911562,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.16667921841144562,
|
|
"num_tokens": 17441749.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.392041492462158,
|
|
"epoch": 0.7945758799769186,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004947801688398725,
|
|
"loss": 6.1919,
|
|
"mean_token_accuracy": 0.16391475200653077,
|
|
"num_tokens": 17453626.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.289467096328735,
|
|
"epoch": 0.7951529140219273,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004947713283759862,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.17084853053092958,
|
|
"num_tokens": 17465038.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.32017035484314,
|
|
"epoch": 0.795729948066936,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004947624805202003,
|
|
"loss": 6.2005,
|
|
"mean_token_accuracy": 0.15855661481618882,
|
|
"num_tokens": 17478319.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.3642435550689695,
|
|
"epoch": 0.7963069821119446,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004947536252728126,
|
|
"loss": 6.0826,
|
|
"mean_token_accuracy": 0.17405088394880294,
|
|
"num_tokens": 17491534.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.256607437133789,
|
|
"epoch": 0.7968840161569533,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004947447626341209,
|
|
"loss": 6.1176,
|
|
"mean_token_accuracy": 0.16702562868595122,
|
|
"num_tokens": 17504957.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.329520893096924,
|
|
"epoch": 0.7974610502019619,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004947358926044232,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.1736439809203148,
|
|
"num_tokens": 17518265.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.285739421844482,
|
|
"epoch": 0.7980380842469705,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004947270151840179,
|
|
"loss": 6.1042,
|
|
"mean_token_accuracy": 0.17833034843206405,
|
|
"num_tokens": 17530588.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.200070571899414,
|
|
"epoch": 0.7986151182919792,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004947181303732038,
|
|
"loss": 6.0645,
|
|
"mean_token_accuracy": 0.1750258818268776,
|
|
"num_tokens": 17545429.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.368551015853882,
|
|
"epoch": 0.7991921523369879,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004947092381722793,
|
|
"loss": 6.1731,
|
|
"mean_token_accuracy": 0.16941929012537002,
|
|
"num_tokens": 17558437.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.3232728958129885,
|
|
"epoch": 0.7997691863819966,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004947003385815438,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.16462525725364685,
|
|
"num_tokens": 17569863.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.32643575668335,
|
|
"epoch": 0.8003462204270052,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004946914316012964,
|
|
"loss": 6.202,
|
|
"mean_token_accuracy": 0.16439114809036254,
|
|
"num_tokens": 17581987.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.300495767593384,
|
|
"epoch": 0.8009232544720138,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000494682517231837,
|
|
"loss": 6.1986,
|
|
"mean_token_accuracy": 0.16613231599330902,
|
|
"num_tokens": 17594064.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.307906436920166,
|
|
"epoch": 0.8015002885170225,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004946735954734652,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.16881750375032425,
|
|
"num_tokens": 17606557.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.345771360397339,
|
|
"epoch": 0.8020773225620311,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004946646663264811,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.16938254088163376,
|
|
"num_tokens": 17620095.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.280622100830078,
|
|
"epoch": 0.8026543566070398,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004946557297911852,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.17692890465259553,
|
|
"num_tokens": 17633006.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.313730478286743,
|
|
"epoch": 0.8032313906520485,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004946467858678777,
|
|
"loss": 6.1475,
|
|
"mean_token_accuracy": 0.164541295170784,
|
|
"num_tokens": 17646863.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.352252578735351,
|
|
"epoch": 0.8038084246970572,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004946378345568597,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.16321584284305574,
|
|
"num_tokens": 17659917.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.360219669342041,
|
|
"epoch": 0.8043854587420658,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004946288758584324,
|
|
"loss": 6.1667,
|
|
"mean_token_accuracy": 0.16748237907886504,
|
|
"num_tokens": 17672867.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.3579973697662355,
|
|
"epoch": 0.8049624927870744,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004946199097728968,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.17079340666532516,
|
|
"num_tokens": 17684600.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.339913034439087,
|
|
"epoch": 0.8055395268320831,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004946109363005548,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.17065697759389878,
|
|
"num_tokens": 17697023.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.322485399246216,
|
|
"epoch": 0.8061165608770917,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000494601955441708,
|
|
"loss": 6.1687,
|
|
"mean_token_accuracy": 0.16757836192846298,
|
|
"num_tokens": 17711592.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.416100358963012,
|
|
"epoch": 0.8066935949221004,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004945929671966585,
|
|
"loss": 6.1653,
|
|
"mean_token_accuracy": 0.1698947876691818,
|
|
"num_tokens": 17723039.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.306565809249878,
|
|
"epoch": 0.8072706289671091,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004945839715657085,
|
|
"loss": 6.1177,
|
|
"mean_token_accuracy": 0.16805417239665985,
|
|
"num_tokens": 17736851.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.391094207763672,
|
|
"epoch": 0.8078476630121177,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004945749685491607,
|
|
"loss": 6.1555,
|
|
"mean_token_accuracy": 0.1691310867667198,
|
|
"num_tokens": 17749483.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.339906883239746,
|
|
"epoch": 0.8084246970571264,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004945659581473181,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.16059267669916152,
|
|
"num_tokens": 17760463.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.434919738769532,
|
|
"epoch": 0.809001731102135,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004945569403604833,
|
|
"loss": 6.2524,
|
|
"mean_token_accuracy": 0.16289447844028473,
|
|
"num_tokens": 17772557.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.290898752212525,
|
|
"epoch": 0.8095787651471437,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004945479151889601,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.17295335680246354,
|
|
"num_tokens": 17785399.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.355238962173462,
|
|
"epoch": 0.8101557991921523,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004945388826330517,
|
|
"loss": 6.1667,
|
|
"mean_token_accuracy": 0.16519918888807297,
|
|
"num_tokens": 17798766.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.384207105636596,
|
|
"epoch": 0.8107328332371609,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004945298426930621,
|
|
"loss": 6.1533,
|
|
"mean_token_accuracy": 0.16614916175603867,
|
|
"num_tokens": 17811726.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.365244054794312,
|
|
"epoch": 0.8113098672821697,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004945207953692952,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.17219052463769913,
|
|
"num_tokens": 17824142.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.322742366790772,
|
|
"epoch": 0.8118869013271783,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004945117406620556,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.1732164204120636,
|
|
"num_tokens": 17837497.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.291933012008667,
|
|
"epoch": 0.812463935372187,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004945026785716474,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.16709503829479216,
|
|
"num_tokens": 17849186.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.336631917953492,
|
|
"epoch": 0.8130409694171956,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004944936090983757,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.16816715002059937,
|
|
"num_tokens": 17861460.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.32755856513977,
|
|
"epoch": 0.8136180034622043,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004944845322425455,
|
|
"loss": 6.0981,
|
|
"mean_token_accuracy": 0.17414549440145494,
|
|
"num_tokens": 17874031.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.277894449234009,
|
|
"epoch": 0.8141950375072129,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004944754480044621,
|
|
"loss": 6.1176,
|
|
"mean_token_accuracy": 0.16790224760770797,
|
|
"num_tokens": 17886623.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.33378119468689,
|
|
"epoch": 0.8147720715522215,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004944663563844311,
|
|
"loss": 6.1167,
|
|
"mean_token_accuracy": 0.16459549963474274,
|
|
"num_tokens": 17899888.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.300360584259034,
|
|
"epoch": 0.8153491055972303,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004944572573827581,
|
|
"loss": 6.1425,
|
|
"mean_token_accuracy": 0.17327246218919753,
|
|
"num_tokens": 17912089.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.34687385559082,
|
|
"epoch": 0.8159261396422389,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004944481509997494,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.16654876470565796,
|
|
"num_tokens": 17923790.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.400413751602173,
|
|
"epoch": 0.8165031736872476,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000494439037235711,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.17073314338922502,
|
|
"num_tokens": 17936537.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.303481578826904,
|
|
"epoch": 0.8170802077322562,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004944299160909495,
|
|
"loss": 6.1222,
|
|
"mean_token_accuracy": 0.1658458635210991,
|
|
"num_tokens": 17948230.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.333654165267944,
|
|
"epoch": 0.8176572417772648,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000494420787565772,
|
|
"loss": 6.1076,
|
|
"mean_token_accuracy": 0.17086146622896195,
|
|
"num_tokens": 17960927.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.279893064498902,
|
|
"epoch": 0.8182342758222735,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004944116516604852,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.17715319991111755,
|
|
"num_tokens": 17974392.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.219158601760864,
|
|
"epoch": 0.8188113098672821,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004944025083753965,
|
|
"loss": 6.0373,
|
|
"mean_token_accuracy": 0.17926018238067626,
|
|
"num_tokens": 17987845.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.329027509689331,
|
|
"epoch": 0.8193883439122909,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004943933577108133,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.16645580977201463,
|
|
"num_tokens": 18000610.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.299327182769775,
|
|
"epoch": 0.8199653779572995,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004943841996670436,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.1676725208759308,
|
|
"num_tokens": 18014322.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.305058240890503,
|
|
"epoch": 0.8205424120023082,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004943750342443953,
|
|
"loss": 6.1453,
|
|
"mean_token_accuracy": 0.16816196143627166,
|
|
"num_tokens": 18028072.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.335258913040161,
|
|
"epoch": 0.8211194460473168,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004943658614431767,
|
|
"loss": 6.1131,
|
|
"mean_token_accuracy": 0.167927385866642,
|
|
"num_tokens": 18039629.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.383225202560425,
|
|
"epoch": 0.8216964800923254,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004943566812636963,
|
|
"loss": 6.1576,
|
|
"mean_token_accuracy": 0.17481892108917235,
|
|
"num_tokens": 18052879.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.307858800888061,
|
|
"epoch": 0.8222735141373341,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000494347493706263,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.1710774213075638,
|
|
"num_tokens": 18065037.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.304836845397949,
|
|
"epoch": 0.8228505481823427,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004943382987711856,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.17677446603775024,
|
|
"num_tokens": 18078595.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.215980768203735,
|
|
"epoch": 0.8234275822273515,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004943290964587734,
|
|
"loss": 5.9584,
|
|
"mean_token_accuracy": 0.1821457639336586,
|
|
"num_tokens": 18089790.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.2496058464050295,
|
|
"epoch": 0.8240046162723601,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004943198867693361,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.1753086805343628,
|
|
"num_tokens": 18101343.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.350470972061157,
|
|
"epoch": 0.8245816503173687,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004943106697031833,
|
|
"loss": 6.1909,
|
|
"mean_token_accuracy": 0.16834626346826553,
|
|
"num_tokens": 18113124.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.328378009796142,
|
|
"epoch": 0.8251586843623774,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004943014452606251,
|
|
"loss": 6.145,
|
|
"mean_token_accuracy": 0.17023891508579253,
|
|
"num_tokens": 18125322.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.3475916385650635,
|
|
"epoch": 0.825735718407386,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004942922134419717,
|
|
"loss": 6.1932,
|
|
"mean_token_accuracy": 0.16659340858459473,
|
|
"num_tokens": 18137975.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.376634693145752,
|
|
"epoch": 0.8263127524523947,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004942829742475336,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.16527699828147888,
|
|
"num_tokens": 18151149.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.35319972038269,
|
|
"epoch": 0.8268897864974033,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004942737276776217,
|
|
"loss": 6.1414,
|
|
"mean_token_accuracy": 0.16284787356853486,
|
|
"num_tokens": 18164451.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.271916341781616,
|
|
"epoch": 0.827466820542412,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004942644737325468,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.16889770179986954,
|
|
"num_tokens": 18177148.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.3122375965118405,
|
|
"epoch": 0.8280438545874207,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004942552124126202,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.16649234741926194,
|
|
"num_tokens": 18189428.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.342439794540406,
|
|
"epoch": 0.8286208886324293,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004942459437181535,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.16976441591978073,
|
|
"num_tokens": 18201644.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.326513719558716,
|
|
"epoch": 0.829197922677438,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004942366676494584,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.1665779948234558,
|
|
"num_tokens": 18213366.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.272335004806519,
|
|
"epoch": 0.8297749567224466,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004942273842068469,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.17365220338106155,
|
|
"num_tokens": 18226767.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.336211061477661,
|
|
"epoch": 0.8303519907674553,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004942180933906311,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.1732963427901268,
|
|
"num_tokens": 18239250.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.232381200790405,
|
|
"epoch": 0.8309290248124639,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004942087952011237,
|
|
"loss": 6.1186,
|
|
"mean_token_accuracy": 0.1715511605143547,
|
|
"num_tokens": 18252053.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.319523096084595,
|
|
"epoch": 0.8315060588574726,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004941994896386374,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.1603941097855568,
|
|
"num_tokens": 18264769.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.390555953979492,
|
|
"epoch": 0.8320830929024813,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004941901767034851,
|
|
"loss": 6.1828,
|
|
"mean_token_accuracy": 0.16464990973472596,
|
|
"num_tokens": 18278185.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.283919048309326,
|
|
"epoch": 0.8326601269474899,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004941808563959802,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.17388446182012557,
|
|
"num_tokens": 18290997.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.226381444931031,
|
|
"epoch": 0.8332371609924986,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004941715287164359,
|
|
"loss": 6.0793,
|
|
"mean_token_accuracy": 0.17051244676113128,
|
|
"num_tokens": 18303735.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.224194622039795,
|
|
"epoch": 0.8338141950375072,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004941621936651661,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.1779409721493721,
|
|
"num_tokens": 18316061.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.325501871109009,
|
|
"epoch": 0.8343912290825158,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004941528512424849,
|
|
"loss": 6.0813,
|
|
"mean_token_accuracy": 0.1724706158041954,
|
|
"num_tokens": 18329478.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.277244186401367,
|
|
"epoch": 0.8349682631275245,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004941435014487064,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.1694391682744026,
|
|
"num_tokens": 18341790.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.257685041427612,
|
|
"epoch": 0.8355452971725332,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000494134144284145,
|
|
"loss": 6.0609,
|
|
"mean_token_accuracy": 0.17542690485715867,
|
|
"num_tokens": 18353807.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.326960563659668,
|
|
"epoch": 0.8361223312175419,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004941247797491156,
|
|
"loss": 6.138,
|
|
"mean_token_accuracy": 0.16580530852079392,
|
|
"num_tokens": 18366118.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.224525594711304,
|
|
"epoch": 0.8366993652625505,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004941154078439329,
|
|
"loss": 6.0992,
|
|
"mean_token_accuracy": 0.17626895606517792,
|
|
"num_tokens": 18380542.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.379341077804566,
|
|
"epoch": 0.8372763993075591,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004941060285689126,
|
|
"loss": 6.1702,
|
|
"mean_token_accuracy": 0.1661502555012703,
|
|
"num_tokens": 18393976.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.262735748291016,
|
|
"epoch": 0.8378534333525678,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004940966419243695,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.1704573854804039,
|
|
"num_tokens": 18405770.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.328343677520752,
|
|
"epoch": 0.8384304673975764,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049408724791062,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.16913258135318757,
|
|
"num_tokens": 18417980.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.394333171844482,
|
|
"epoch": 0.8390075014425851,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004940778465279797,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.17640269845724105,
|
|
"num_tokens": 18429511.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.282315731048584,
|
|
"epoch": 0.8395845354875938,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004940684377767647,
|
|
"loss": 6.1463,
|
|
"mean_token_accuracy": 0.1683313712477684,
|
|
"num_tokens": 18443176.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.29357419013977,
|
|
"epoch": 0.8401615695326025,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004940590216572916,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.17451467961072922,
|
|
"num_tokens": 18454664.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.3182899951934814,
|
|
"epoch": 0.8407386035776111,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004940495981698772,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.17001918852329254,
|
|
"num_tokens": 18465919.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.255602073669434,
|
|
"epoch": 0.8413156376226197,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004940401673148384,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.17237745225429535,
|
|
"num_tokens": 18478847.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.330014038085937,
|
|
"epoch": 0.8418926716676284,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004940307290924923,
|
|
"loss": 6.1426,
|
|
"mean_token_accuracy": 0.16671836823225022,
|
|
"num_tokens": 18490932.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.347289514541626,
|
|
"epoch": 0.842469705712637,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004940212835031565,
|
|
"loss": 6.1418,
|
|
"mean_token_accuracy": 0.1622636690735817,
|
|
"num_tokens": 18504333.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.292515897750855,
|
|
"epoch": 0.8430467397576457,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004940118305471486,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.16780552119016648,
|
|
"num_tokens": 18516021.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.254858493804932,
|
|
"epoch": 0.8436237738026544,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004940023702247866,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.17692680954933165,
|
|
"num_tokens": 18529281.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.250281906127929,
|
|
"epoch": 0.844200807847663,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004939929025363886,
|
|
"loss": 6.0826,
|
|
"mean_token_accuracy": 0.1771777018904686,
|
|
"num_tokens": 18541605.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.3663187503814695,
|
|
"epoch": 0.8447778418926717,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004939834274822731,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.16943843960762023,
|
|
"num_tokens": 18553171.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.315127515792847,
|
|
"epoch": 0.8453548759376803,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004939739450627588,
|
|
"loss": 5.9897,
|
|
"mean_token_accuracy": 0.1719767913222313,
|
|
"num_tokens": 18565347.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.293874216079712,
|
|
"epoch": 0.845931909982689,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004939644552781647,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.16545775383710862,
|
|
"num_tokens": 18578102.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.291524267196655,
|
|
"epoch": 0.8465089440276976,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004939549581288099,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.1646455481648445,
|
|
"num_tokens": 18590184.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.323913669586181,
|
|
"epoch": 0.8470859780727062,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004939454536150138,
|
|
"loss": 6.1435,
|
|
"mean_token_accuracy": 0.16949068158864974,
|
|
"num_tokens": 18603026.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.321570491790771,
|
|
"epoch": 0.847663012117715,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000493935941737096,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.16862865388393403,
|
|
"num_tokens": 18616841.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.315411138534546,
|
|
"epoch": 0.8482400461627236,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004939264224953768,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.17875832915306092,
|
|
"num_tokens": 18628777.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.31576189994812,
|
|
"epoch": 0.8488170802077323,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000493916895890176,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.16413204818964006,
|
|
"num_tokens": 18641626.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.406159973144531,
|
|
"epoch": 0.8493941142527409,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000493907361921814,
|
|
"loss": 6.0959,
|
|
"mean_token_accuracy": 0.1713714763522148,
|
|
"num_tokens": 18653576.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.246872854232788,
|
|
"epoch": 0.8499711482977496,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004938978205906118,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.17479570508003234,
|
|
"num_tokens": 18666134.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.259529781341553,
|
|
"epoch": 0.8505481823427582,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004938882718968901,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.16042630970478058,
|
|
"num_tokens": 18680029.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.365555238723755,
|
|
"epoch": 0.8511252163877668,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004938787158409702,
|
|
"loss": 6.1189,
|
|
"mean_token_accuracy": 0.1694151431322098,
|
|
"num_tokens": 18693136.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.323048782348633,
|
|
"epoch": 0.8517022504327756,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004938691524231733,
|
|
"loss": 6.171,
|
|
"mean_token_accuracy": 0.16397368311882018,
|
|
"num_tokens": 18706613.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.361038017272949,
|
|
"epoch": 0.8522792844777842,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004938595816438212,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.16203895807266236,
|
|
"num_tokens": 18719541.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.3449992656707765,
|
|
"epoch": 0.8528563185227929,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004938500035032358,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.17314599007368087,
|
|
"num_tokens": 18730992.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.300184297561645,
|
|
"epoch": 0.8534333525678015,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004938404180017392,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.1704453006386757,
|
|
"num_tokens": 18743945.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.241794729232788,
|
|
"epoch": 0.8540103866128101,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004938308251396539,
|
|
"loss": 6.1287,
|
|
"mean_token_accuracy": 0.1737273007631302,
|
|
"num_tokens": 18756656.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.32796049118042,
|
|
"epoch": 0.8545874206578188,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004938212249173024,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.17052091658115387,
|
|
"num_tokens": 18769224.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.310837602615356,
|
|
"epoch": 0.8551644547028274,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004938116173350078,
|
|
"loss": 6.0749,
|
|
"mean_token_accuracy": 0.17881231009960175,
|
|
"num_tokens": 18782162.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.312178421020508,
|
|
"epoch": 0.8557414887478362,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004938020023930932,
|
|
"loss": 6.138,
|
|
"mean_token_accuracy": 0.1700222000479698,
|
|
"num_tokens": 18793014.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.400294160842895,
|
|
"epoch": 0.8563185227928448,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004937923800918817,
|
|
"loss": 6.2059,
|
|
"mean_token_accuracy": 0.16382661759853362,
|
|
"num_tokens": 18804879.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.3230022430419925,
|
|
"epoch": 0.8568955568378535,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004937827504316974,
|
|
"loss": 6.0589,
|
|
"mean_token_accuracy": 0.17049174308776854,
|
|
"num_tokens": 18817301.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.240580892562866,
|
|
"epoch": 0.8574725908828621,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004937731134128639,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.16979705542325974,
|
|
"num_tokens": 18828424.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.309745979309082,
|
|
"epoch": 0.8580496249278707,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004937634690357054,
|
|
"loss": 6.1167,
|
|
"mean_token_accuracy": 0.17033765614032745,
|
|
"num_tokens": 18840526.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.403766441345215,
|
|
"epoch": 0.8586266589728794,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004937538173005462,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.16364138275384904,
|
|
"num_tokens": 18854557.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.298587036132813,
|
|
"epoch": 0.859203693017888,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004937441582077111,
|
|
"loss": 6.1573,
|
|
"mean_token_accuracy": 0.16764754205942153,
|
|
"num_tokens": 18868469.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.30604887008667,
|
|
"epoch": 0.8597807270628968,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004937344917575249,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.16838963329792023,
|
|
"num_tokens": 18880507.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.389565324783325,
|
|
"epoch": 0.8603577611079054,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004937248179503127,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.16353571712970733,
|
|
"num_tokens": 18892666.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.332041501998901,
|
|
"epoch": 0.860934795152914,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004937151367863998,
|
|
"loss": 6.1592,
|
|
"mean_token_accuracy": 0.16899376958608628,
|
|
"num_tokens": 18905022.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.33961443901062,
|
|
"epoch": 0.8615118291979227,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000493705448266112,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.16367289870977403,
|
|
"num_tokens": 18918279.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.329358911514282,
|
|
"epoch": 0.8620888632429313,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004936957523897752,
|
|
"loss": 6.0615,
|
|
"mean_token_accuracy": 0.16951747089624405,
|
|
"num_tokens": 18930494.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.245223951339722,
|
|
"epoch": 0.86266589728794,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004936860491577153,
|
|
"loss": 6.0396,
|
|
"mean_token_accuracy": 0.17186590582132338,
|
|
"num_tokens": 18943918.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.25893611907959,
|
|
"epoch": 0.8632429313329486,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004936763385702588,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.1655966654419899,
|
|
"num_tokens": 18957170.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.309596061706543,
|
|
"epoch": 0.8638199653779572,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004936666206277322,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.1582779198884964,
|
|
"num_tokens": 18970106.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.365174388885498,
|
|
"epoch": 0.864396999422966,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004936568953304624,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.168244831264019,
|
|
"num_tokens": 18982797.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.329259634017944,
|
|
"epoch": 0.8649740334679746,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004936471626787766,
|
|
"loss": 6.2214,
|
|
"mean_token_accuracy": 0.16954808235168456,
|
|
"num_tokens": 18997122.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.344443130493164,
|
|
"epoch": 0.8655510675129833,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004936374226730022,
|
|
"loss": 6.1836,
|
|
"mean_token_accuracy": 0.16055750995874404,
|
|
"num_tokens": 19009345.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.354634952545166,
|
|
"epoch": 0.8661281015579919,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004936276753134666,
|
|
"loss": 6.1688,
|
|
"mean_token_accuracy": 0.16521380990743637,
|
|
"num_tokens": 19021585.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.329277658462525,
|
|
"epoch": 0.8667051356030006,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004936179206004976,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.16339420676231384,
|
|
"num_tokens": 19034701.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.2735615253448485,
|
|
"epoch": 0.8672821696480092,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004936081585344236,
|
|
"loss": 6.1192,
|
|
"mean_token_accuracy": 0.17345345616340638,
|
|
"num_tokens": 19047810.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.287371873855591,
|
|
"epoch": 0.8678592036930178,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004935983891155727,
|
|
"loss": 6.1019,
|
|
"mean_token_accuracy": 0.173904687166214,
|
|
"num_tokens": 19059546.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.357184267044067,
|
|
"epoch": 0.8684362377380266,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004935886123442737,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.16851410567760466,
|
|
"num_tokens": 19072302.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.344837951660156,
|
|
"epoch": 0.8690132717830352,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004935788282208551,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.17020163536071778,
|
|
"num_tokens": 19086283.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.306544637680053,
|
|
"epoch": 0.8695903058280439,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004935690367456464,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.17379076927900314,
|
|
"num_tokens": 19098586.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.294129991531372,
|
|
"epoch": 0.8701673398730525,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004935592379189766,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.16863109916448593,
|
|
"num_tokens": 19110795.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.309462785720825,
|
|
"epoch": 0.8707443739180611,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004935494317411754,
|
|
"loss": 6.0386,
|
|
"mean_token_accuracy": 0.17708732634782792,
|
|
"num_tokens": 19123391.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.297340679168701,
|
|
"epoch": 0.8713214079630698,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004935396182125726,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.17120068967342378,
|
|
"num_tokens": 19135436.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.2987633228302,
|
|
"epoch": 0.8718984420080784,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004935297973334983,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.17533822655677794,
|
|
"num_tokens": 19147210.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.354048061370849,
|
|
"epoch": 0.8724754760530872,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004935199691042828,
|
|
"loss": 6.2243,
|
|
"mean_token_accuracy": 0.1696576878428459,
|
|
"num_tokens": 19161309.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.324620389938355,
|
|
"epoch": 0.8730525100980958,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004935101335252568,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.16651286780834199,
|
|
"num_tokens": 19174073.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.283979034423828,
|
|
"epoch": 0.8736295441431045,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004935002905967509,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.17390892058610916,
|
|
"num_tokens": 19187120.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.339527654647827,
|
|
"epoch": 0.8742065781881131,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004934904403190963,
|
|
"loss": 6.0223,
|
|
"mean_token_accuracy": 0.17759824991226197,
|
|
"num_tokens": 19201195.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.268510246276856,
|
|
"epoch": 0.8747836122331217,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004934805826926242,
|
|
"loss": 6.1503,
|
|
"mean_token_accuracy": 0.16540689021348953,
|
|
"num_tokens": 19214050.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.3610124588012695,
|
|
"epoch": 0.8753606462781304,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004934707177176663,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.16823814809322357,
|
|
"num_tokens": 19226678.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.340522146224975,
|
|
"epoch": 0.875937680323139,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004934608453945543,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.16496469229459762,
|
|
"num_tokens": 19239038.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.214799928665161,
|
|
"epoch": 0.8765147143681478,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004934509657236203,
|
|
"loss": 6.0617,
|
|
"mean_token_accuracy": 0.17199939340353013,
|
|
"num_tokens": 19252934.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.388493824005127,
|
|
"epoch": 0.8770917484131564,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004934410787051965,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.16989358365535737,
|
|
"num_tokens": 19267646.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.334185314178467,
|
|
"epoch": 0.877668782458165,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004934311843396157,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.17217393964529037,
|
|
"num_tokens": 19279529.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.333045196533203,
|
|
"epoch": 0.8782458165031737,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004934212826272104,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.168229903280735,
|
|
"num_tokens": 19291315.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.311127710342407,
|
|
"epoch": 0.8788228505481823,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004934113735683137,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.18041695654392242,
|
|
"num_tokens": 19303763.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.293818998336792,
|
|
"epoch": 0.879399884593191,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000493401457163259,
|
|
"loss": 6.1382,
|
|
"mean_token_accuracy": 0.16354042440652847,
|
|
"num_tokens": 19316400.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.28227686882019,
|
|
"epoch": 0.8799769186381996,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004933915334123798,
|
|
"loss": 6.0448,
|
|
"mean_token_accuracy": 0.1758949264883995,
|
|
"num_tokens": 19328227.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.260040950775147,
|
|
"epoch": 0.8805539526832084,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004933816023160099,
|
|
"loss": 5.9935,
|
|
"mean_token_accuracy": 0.1776716187596321,
|
|
"num_tokens": 19341211.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.282184839248657,
|
|
"epoch": 0.881130986728217,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004933716638744832,
|
|
"loss": 6.1425,
|
|
"mean_token_accuracy": 0.17052342146635055,
|
|
"num_tokens": 19353165.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.338343238830566,
|
|
"epoch": 0.8817080207732256,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000493361718088134,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.16703000366687776,
|
|
"num_tokens": 19365601.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.329648160934449,
|
|
"epoch": 0.8822850548182343,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000493351764957297,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.1692799523472786,
|
|
"num_tokens": 19377828.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.417537355422974,
|
|
"epoch": 0.8828620888632429,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004933418044823068,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.1705181673169136,
|
|
"num_tokens": 19390019.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.286002779006958,
|
|
"epoch": 0.8834391229082516,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004933318366634984,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.16971160471439362,
|
|
"num_tokens": 19402179.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.289387607574463,
|
|
"epoch": 0.8840161569532602,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004933218615012072,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.16546063423156737,
|
|
"num_tokens": 19412794.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.326491498947144,
|
|
"epoch": 0.8845931909982689,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004933118789957687,
|
|
"loss": 6.1542,
|
|
"mean_token_accuracy": 0.16174625530838965,
|
|
"num_tokens": 19425932.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.367192554473877,
|
|
"epoch": 0.8851702250432776,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004933018891475186,
|
|
"loss": 6.0879,
|
|
"mean_token_accuracy": 0.16910957992076875,
|
|
"num_tokens": 19437543.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.3427753925323485,
|
|
"epoch": 0.8857472590882862,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004932918919567927,
|
|
"loss": 6.0655,
|
|
"mean_token_accuracy": 0.17346468269824983,
|
|
"num_tokens": 19450122.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.238670110702515,
|
|
"epoch": 0.8863242931332949,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004932818874239275,
|
|
"loss": 6.0811,
|
|
"mean_token_accuracy": 0.16923540085554123,
|
|
"num_tokens": 19464553.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.229796695709228,
|
|
"epoch": 0.8869013271783035,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004932718755492595,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.17348248213529588,
|
|
"num_tokens": 19477956.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.258459901809692,
|
|
"epoch": 0.8874783612233121,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004932618563331254,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.166024249792099,
|
|
"num_tokens": 19491610.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.231938743591309,
|
|
"epoch": 0.8880553952683208,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004932518297758622,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.1762412056326866,
|
|
"num_tokens": 19503612.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.255193471908569,
|
|
"epoch": 0.8886324293133295,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004932417958778071,
|
|
"loss": 6.0661,
|
|
"mean_token_accuracy": 0.17482839226722718,
|
|
"num_tokens": 19516956.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.198970603942871,
|
|
"epoch": 0.8892094633583382,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004932317546392976,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.17286549359560013,
|
|
"num_tokens": 19528545.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.335839414596558,
|
|
"epoch": 0.8897864974033468,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004932217060606714,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.17639979273080825,
|
|
"num_tokens": 19539920.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.273063850402832,
|
|
"epoch": 0.8903635314483554,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004932116501422665,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.16828238517045974,
|
|
"num_tokens": 19551975.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.319854402542115,
|
|
"epoch": 0.8909405654933641,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004932015868844211,
|
|
"loss": 6.1178,
|
|
"mean_token_accuracy": 0.1692993938922882,
|
|
"num_tokens": 19565952.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.274467420578003,
|
|
"epoch": 0.8915175995383727,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004931915162874738,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.17231060862541198,
|
|
"num_tokens": 19578400.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.239807081222534,
|
|
"epoch": 0.8920946335833814,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004931814383517632,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.17400905042886733,
|
|
"num_tokens": 19592237.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.385022783279419,
|
|
"epoch": 0.8926716676283901,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004931713530776284,
|
|
"loss": 6.1987,
|
|
"mean_token_accuracy": 0.16712776869535445,
|
|
"num_tokens": 19606172.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.298589515686035,
|
|
"epoch": 0.8932487016733988,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004931612604654083,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.17061897069215776,
|
|
"num_tokens": 19618245.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.362525987625122,
|
|
"epoch": 0.8938257357184074,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004931511605154428,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.1694071665406227,
|
|
"num_tokens": 19630921.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.318386745452881,
|
|
"epoch": 0.894402769763416,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004931410532280711,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.16700265556573868,
|
|
"num_tokens": 19643869.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.338892793655395,
|
|
"epoch": 0.8949798038084247,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004931309386036337,
|
|
"loss": 6.0796,
|
|
"mean_token_accuracy": 0.17166771739721298,
|
|
"num_tokens": 19657819.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.332481241226196,
|
|
"epoch": 0.8955568378534333,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004931208166424704,
|
|
"loss": 6.1639,
|
|
"mean_token_accuracy": 0.16711659282445906,
|
|
"num_tokens": 19670847.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.290749549865723,
|
|
"epoch": 0.896133871898442,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004931106873449219,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.16827981024980546,
|
|
"num_tokens": 19684055.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.255268526077271,
|
|
"epoch": 0.8967109059434507,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004931005507113285,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.1766640618443489,
|
|
"num_tokens": 19696731.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.371890735626221,
|
|
"epoch": 0.8972879399884593,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004930904067420317,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.16785583049058914,
|
|
"num_tokens": 19708787.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.323027563095093,
|
|
"epoch": 0.897864974033468,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004930802554373723,
|
|
"loss": 6.1471,
|
|
"mean_token_accuracy": 0.16464302837848663,
|
|
"num_tokens": 19722570.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.376014757156372,
|
|
"epoch": 0.8984420080784766,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004930700967976918,
|
|
"loss": 6.1277,
|
|
"mean_token_accuracy": 0.17113870084285737,
|
|
"num_tokens": 19734690.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.341323328018189,
|
|
"epoch": 0.8990190421234853,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000493059930823332,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.1661938413977623,
|
|
"num_tokens": 19747907.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.278427219390869,
|
|
"epoch": 0.8995960761684939,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004930497575146346,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.17348378151655197,
|
|
"num_tokens": 19760869.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.302192831039429,
|
|
"epoch": 0.9001731102135025,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004930395768719421,
|
|
"loss": 5.9991,
|
|
"mean_token_accuracy": 0.1784247100353241,
|
|
"num_tokens": 19773097.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.289451456069946,
|
|
"epoch": 0.9007501442585113,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004930293888955966,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.16142976507544518,
|
|
"num_tokens": 19786070.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.357674837112427,
|
|
"epoch": 0.9013271783035199,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000493019193585941,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.1719981074333191,
|
|
"num_tokens": 19799244.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.2633469581604,
|
|
"epoch": 0.9019042123485286,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000493008990943318,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.16575743407011032,
|
|
"num_tokens": 19811965.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.37284574508667,
|
|
"epoch": 0.9024812463935372,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004929987809680709,
|
|
"loss": 6.1125,
|
|
"mean_token_accuracy": 0.16965578645467758,
|
|
"num_tokens": 19825531.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.3032989501953125,
|
|
"epoch": 0.9030582804385459,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004929885636605432,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.1738504096865654,
|
|
"num_tokens": 19839166.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.281108570098877,
|
|
"epoch": 0.9036353144835545,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004929783390210784,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.16765460520982742,
|
|
"num_tokens": 19852187.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.308529853820801,
|
|
"epoch": 0.9042123485285631,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004929681070500204,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.16539253145456315,
|
|
"num_tokens": 19864309.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.293935537338257,
|
|
"epoch": 0.9047893825735719,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004929578677477135,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.1615119993686676,
|
|
"num_tokens": 19877475.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.360176944732666,
|
|
"epoch": 0.9053664166185805,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004929476211145019,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.1671235129237175,
|
|
"num_tokens": 19889984.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.29410719871521,
|
|
"epoch": 0.9059434506635892,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004929373671507303,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.18178427070379258,
|
|
"num_tokens": 19902135.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.2419897556304935,
|
|
"epoch": 0.9065204847085978,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004929271058567436,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.173341503739357,
|
|
"num_tokens": 19915214.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.316197299957276,
|
|
"epoch": 0.9070975187536064,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000492916837232887,
|
|
"loss": 6.1189,
|
|
"mean_token_accuracy": 0.16358882784843445,
|
|
"num_tokens": 19929113.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.398955392837524,
|
|
"epoch": 0.9076745527986151,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004929065612795058,
|
|
"loss": 6.1305,
|
|
"mean_token_accuracy": 0.1644856885075569,
|
|
"num_tokens": 19942727.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.257999897003174,
|
|
"epoch": 0.9082515868436237,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004928962779969456,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.1740820974111557,
|
|
"num_tokens": 19954863.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.227055358886719,
|
|
"epoch": 0.9088286208886325,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004928859873855524,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.17968434393405913,
|
|
"num_tokens": 19967555.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.388265609741211,
|
|
"epoch": 0.9094056549336411,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004928756894456723,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.16835675835609437,
|
|
"num_tokens": 19979992.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.325529479980469,
|
|
"epoch": 0.9099826889786498,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004928653841776515,
|
|
"loss": 6.1594,
|
|
"mean_token_accuracy": 0.16871841698884965,
|
|
"num_tokens": 19993231.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.3724034309387205,
|
|
"epoch": 0.9105597230236584,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004928550715818368,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.16597728282213212,
|
|
"num_tokens": 20005839.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.320882320404053,
|
|
"epoch": 0.911136757068667,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004928447516585749,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.1678915873169899,
|
|
"num_tokens": 20017423.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.278266286849975,
|
|
"epoch": 0.9117137911136757,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000492834424408213,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.16712916046380996,
|
|
"num_tokens": 20030989.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.356175470352173,
|
|
"epoch": 0.9122908251586843,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004928240898310984,
|
|
"loss": 6.1949,
|
|
"mean_token_accuracy": 0.16000735461711885,
|
|
"num_tokens": 20043763.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.308985090255737,
|
|
"epoch": 0.9128678592036931,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004928137479275789,
|
|
"loss": 6.0511,
|
|
"mean_token_accuracy": 0.17675268799066543,
|
|
"num_tokens": 20057012.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.290041828155518,
|
|
"epoch": 0.9134448932487017,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000492803398698002,
|
|
"loss": 6.0633,
|
|
"mean_token_accuracy": 0.17207225859165193,
|
|
"num_tokens": 20069093.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.248224306106567,
|
|
"epoch": 0.9140219272937103,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004927930421427161,
|
|
"loss": 6.0368,
|
|
"mean_token_accuracy": 0.17193564623594285,
|
|
"num_tokens": 20081392.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.298941898345947,
|
|
"epoch": 0.914598961338719,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004927826782620694,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.1737733945250511,
|
|
"num_tokens": 20092621.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.283964967727661,
|
|
"epoch": 0.9151759953837276,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004927723070564104,
|
|
"loss": 6.091,
|
|
"mean_token_accuracy": 0.1684947982430458,
|
|
"num_tokens": 20105423.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.348589468002319,
|
|
"epoch": 0.9157530294287363,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004927619285260881,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.16632856130599977,
|
|
"num_tokens": 20117835.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.2604001522064205,
|
|
"epoch": 0.9163300634737449,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004927515426714515,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.18144481480121613,
|
|
"num_tokens": 20130563.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.2235535144805905,
|
|
"epoch": 0.9169070975187537,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.00049274114949285,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.17362369149923323,
|
|
"num_tokens": 20144507.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.298459100723266,
|
|
"epoch": 0.9174841315637623,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000492730748990633,
|
|
"loss": 6.0629,
|
|
"mean_token_accuracy": 0.17503987103700638,
|
|
"num_tokens": 20156341.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.308384609222412,
|
|
"epoch": 0.9180611656087709,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004927203411651504,
|
|
"loss": 6.1037,
|
|
"mean_token_accuracy": 0.1752057820558548,
|
|
"num_tokens": 20169410.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.322392272949219,
|
|
"epoch": 0.9186381996537796,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004927099260167523,
|
|
"loss": 6.1004,
|
|
"mean_token_accuracy": 0.1718139886856079,
|
|
"num_tokens": 20181233.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.331369638442993,
|
|
"epoch": 0.9192152336987882,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004926995035457889,
|
|
"loss": 6.1059,
|
|
"mean_token_accuracy": 0.16894071847200393,
|
|
"num_tokens": 20193234.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.249935102462769,
|
|
"epoch": 0.9197922677437969,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000492689073752611,
|
|
"loss": 6.0168,
|
|
"mean_token_accuracy": 0.17317250818014146,
|
|
"num_tokens": 20206784.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.263874673843384,
|
|
"epoch": 0.9203693017888055,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004926786366375691,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.18037747889757155,
|
|
"num_tokens": 20218597.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.214323377609253,
|
|
"epoch": 0.9209463358338142,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004926681922010145,
|
|
"loss": 6.0014,
|
|
"mean_token_accuracy": 0.17502579391002654,
|
|
"num_tokens": 20232703.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.322141790390015,
|
|
"epoch": 0.9215233698788229,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004926577404432982,
|
|
"loss": 6.083,
|
|
"mean_token_accuracy": 0.16904457658529282,
|
|
"num_tokens": 20245811.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.22695517539978,
|
|
"epoch": 0.9221004039238315,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004926472813647721,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.17562677413225175,
|
|
"num_tokens": 20258055.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.290423822402954,
|
|
"epoch": 0.9226774379688402,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004926368149657876,
|
|
"loss": 6.0638,
|
|
"mean_token_accuracy": 0.17215737104415893,
|
|
"num_tokens": 20271250.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.26991376876831,
|
|
"epoch": 0.9232544720138488,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004926263412466972,
|
|
"loss": 6.0108,
|
|
"mean_token_accuracy": 0.17998398542404176,
|
|
"num_tokens": 20284013.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.283149528503418,
|
|
"epoch": 0.9238315060588574,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004926158602078527,
|
|
"loss": 6.085,
|
|
"mean_token_accuracy": 0.1768463060259819,
|
|
"num_tokens": 20297413.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.258905601501465,
|
|
"epoch": 0.9244085401038661,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004926053718496069,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.17365098595619202,
|
|
"num_tokens": 20310026.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.2548730850219725,
|
|
"epoch": 0.9249855741488748,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004925948761723126,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.17915035635232926,
|
|
"num_tokens": 20322118.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.292974901199341,
|
|
"epoch": 0.9255626081938835,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004925843731763226,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.16737297773361207,
|
|
"num_tokens": 20335252.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.393998670578003,
|
|
"epoch": 0.9261396422388921,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004925738628619904,
|
|
"loss": 6.1285,
|
|
"mean_token_accuracy": 0.16633883416652678,
|
|
"num_tokens": 20348201.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.302540397644043,
|
|
"epoch": 0.9267166762839008,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004925633452296693,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.17153316140174865,
|
|
"num_tokens": 20360250.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.287873649597168,
|
|
"epoch": 0.9272937103289094,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004925528202797131,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.17138591706752776,
|
|
"num_tokens": 20372376.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.3305846691131595,
|
|
"epoch": 0.927870744373918,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004925422880124761,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.1675078883767128,
|
|
"num_tokens": 20384484.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.297106599807739,
|
|
"epoch": 0.9284477784189267,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004925317484283121,
|
|
"loss": 6.1007,
|
|
"mean_token_accuracy": 0.17022451460361482,
|
|
"num_tokens": 20396519.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.2978801250457765,
|
|
"epoch": 0.9290248124639354,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004925212015275758,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.17090250551700592,
|
|
"num_tokens": 20409108.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.301689147949219,
|
|
"epoch": 0.9296018465089441,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000492510647310622,
|
|
"loss": 6.0951,
|
|
"mean_token_accuracy": 0.17218709588050843,
|
|
"num_tokens": 20421929.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.268299961090088,
|
|
"epoch": 0.9301788805539527,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004925000857778055,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.17204220592975616,
|
|
"num_tokens": 20435453.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.288744974136352,
|
|
"epoch": 0.9307559145989613,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004924895169294818,
|
|
"loss": 6.0847,
|
|
"mean_token_accuracy": 0.16962202191352843,
|
|
"num_tokens": 20447867.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.378092336654663,
|
|
"epoch": 0.93133294864397,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004924789407660062,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.17544363737106322,
|
|
"num_tokens": 20461150.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.2715552806854244,
|
|
"epoch": 0.9319099826889786,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004924683572877345,
|
|
"loss": 5.9922,
|
|
"mean_token_accuracy": 0.1773497223854065,
|
|
"num_tokens": 20474012.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.303848218917847,
|
|
"epoch": 0.9324870167339873,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004924577664950225,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.16593163311481476,
|
|
"num_tokens": 20485833.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.335386610031128,
|
|
"epoch": 0.933064050778996,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924471683882266,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.1694898262619972,
|
|
"num_tokens": 20499277.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.28719310760498,
|
|
"epoch": 0.9336410848240047,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004924365629677031,
|
|
"loss": 6.0842,
|
|
"mean_token_accuracy": 0.17266414165496827,
|
|
"num_tokens": 20510789.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.26942253112793,
|
|
"epoch": 0.9342181188690133,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000492425950233809,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.1782476782798767,
|
|
"num_tokens": 20523273.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.358910179138183,
|
|
"epoch": 0.9347951529140219,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000492415330186901,
|
|
"loss": 6.1267,
|
|
"mean_token_accuracy": 0.1688690036535263,
|
|
"num_tokens": 20535466.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.415497732162476,
|
|
"epoch": 0.9353721869590306,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004924047028273364,
|
|
"loss": 6.1822,
|
|
"mean_token_accuracy": 0.1660977765917778,
|
|
"num_tokens": 20548108.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.251081037521362,
|
|
"epoch": 0.9359492210040392,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004923940681554725,
|
|
"loss": 6.0452,
|
|
"mean_token_accuracy": 0.17263105362653733,
|
|
"num_tokens": 20559859.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.285415458679199,
|
|
"epoch": 0.9365262550490479,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004923834261716672,
|
|
"loss": 6.168,
|
|
"mean_token_accuracy": 0.16842860281467437,
|
|
"num_tokens": 20572569.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.300700378417969,
|
|
"epoch": 0.9371032890940566,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004923727768762782,
|
|
"loss": 6.0822,
|
|
"mean_token_accuracy": 0.16640304476022721,
|
|
"num_tokens": 20585014.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.27948899269104,
|
|
"epoch": 0.9376803231390652,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000492362120269664,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.1714727073907852,
|
|
"num_tokens": 20597216.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.2442076206207275,
|
|
"epoch": 0.9382573571840739,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004923514563521827,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.1827470049262047,
|
|
"num_tokens": 20609193.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.295881223678589,
|
|
"epoch": 0.9388343912290825,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004923407851241933,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.1688932627439499,
|
|
"num_tokens": 20620777.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.251183223724365,
|
|
"epoch": 0.9394114252740912,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004923301065860545,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.17291734665632247,
|
|
"num_tokens": 20633244.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.292584037780761,
|
|
"epoch": 0.9399884593190998,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004923194207381254,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.17595846354961395,
|
|
"num_tokens": 20645622.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.329843950271607,
|
|
"epoch": 0.9405654933641084,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004923087275807656,
|
|
"loss": 6.1581,
|
|
"mean_token_accuracy": 0.16922140568494798,
|
|
"num_tokens": 20658793.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.264755916595459,
|
|
"epoch": 0.9411425274091172,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004922980271143347,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.18203234672546387,
|
|
"num_tokens": 20673009.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.368770456314087,
|
|
"epoch": 0.9417195614541258,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004922873193391927,
|
|
"loss": 6.1535,
|
|
"mean_token_accuracy": 0.17132313102483748,
|
|
"num_tokens": 20685061.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.282876491546631,
|
|
"epoch": 0.9422965954991345,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004922766042556994,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.17185274958610536,
|
|
"num_tokens": 20696854.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.231480884552002,
|
|
"epoch": 0.9428736295441431,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004922658818642156,
|
|
"loss": 6.114,
|
|
"mean_token_accuracy": 0.16710520386695862,
|
|
"num_tokens": 20709259.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.261470890045166,
|
|
"epoch": 0.9434506635891518,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004922551521651018,
|
|
"loss": 5.9355,
|
|
"mean_token_accuracy": 0.18289135992527009,
|
|
"num_tokens": 20722382.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.2622942447662355,
|
|
"epoch": 0.9440276976341604,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004922444151587189,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.18124618977308274,
|
|
"num_tokens": 20734809.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.1864806652069095,
|
|
"epoch": 0.944604731679169,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004922336708454279,
|
|
"loss": 5.9677,
|
|
"mean_token_accuracy": 0.17568960040807724,
|
|
"num_tokens": 20747490.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.301131677627564,
|
|
"epoch": 0.9451817657241778,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004922229192255903,
|
|
"loss": 6.0495,
|
|
"mean_token_accuracy": 0.17025782018899918,
|
|
"num_tokens": 20759398.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.299096727371216,
|
|
"epoch": 0.9457587997691864,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004922121602995678,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.17925020754337312,
|
|
"num_tokens": 20773057.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.3332267761230465,
|
|
"epoch": 0.9463358338141951,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004922013940677221,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.1656668648123741,
|
|
"num_tokens": 20786084.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.283103036880493,
|
|
"epoch": 0.9469128678592037,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004921906205304155,
|
|
"loss": 6.011,
|
|
"mean_token_accuracy": 0.17718872129917146,
|
|
"num_tokens": 20798459.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.129636430740357,
|
|
"epoch": 0.9474899019042123,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004921798396880101,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.18672388941049575,
|
|
"num_tokens": 20811242.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.194643783569336,
|
|
"epoch": 0.948066935949221,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004921690515408688,
|
|
"loss": 6.0814,
|
|
"mean_token_accuracy": 0.16723225861787797,
|
|
"num_tokens": 20824757.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.365654611587525,
|
|
"epoch": 0.9486439699942296,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004921582560893543,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.17129451036453247,
|
|
"num_tokens": 20836794.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.330667543411255,
|
|
"epoch": 0.9492210040392384,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004921474533338297,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.169456784427166,
|
|
"num_tokens": 20849240.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.233933162689209,
|
|
"epoch": 0.949798038084247,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004921366432746585,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.17418997287750243,
|
|
"num_tokens": 20861362.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.289814519882202,
|
|
"epoch": 0.9503750721292556,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000492125825912204,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.179733544588089,
|
|
"num_tokens": 20874925.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.290691471099853,
|
|
"epoch": 0.9509521061742643,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004921150012468302,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.17308035045862197,
|
|
"num_tokens": 20888098.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.262841844558716,
|
|
"epoch": 0.9515291402192729,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004921041692789013,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.17421980947256088,
|
|
"num_tokens": 20901125.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.324599552154541,
|
|
"epoch": 0.9521061742642816,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004920933300087813,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.16891735643148423,
|
|
"num_tokens": 20914815.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.191049814224243,
|
|
"epoch": 0.9526832083092902,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004920824834368353,
|
|
"loss": 5.9801,
|
|
"mean_token_accuracy": 0.18388531357049942,
|
|
"num_tokens": 20928153.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.379620599746704,
|
|
"epoch": 0.953260242354299,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004920716295634275,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.16048989295959473,
|
|
"num_tokens": 20940601.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.324798536300659,
|
|
"epoch": 0.9538372763993076,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004920607683889235,
|
|
"loss": 6.1358,
|
|
"mean_token_accuracy": 0.1698945254087448,
|
|
"num_tokens": 20953158.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.3390051364898685,
|
|
"epoch": 0.9544143104443162,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004920498999136882,
|
|
"loss": 6.1179,
|
|
"mean_token_accuracy": 0.16918241530656813,
|
|
"num_tokens": 20966572.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.382406949996948,
|
|
"epoch": 0.9549913444893249,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004920390241380874,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.17139170467853546,
|
|
"num_tokens": 20978432.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.287047624588013,
|
|
"epoch": 0.9555683785343335,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004920281410624868,
|
|
"loss": 6.1385,
|
|
"mean_token_accuracy": 0.1723800152540207,
|
|
"num_tokens": 20991454.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.278736734390259,
|
|
"epoch": 0.9561454125793422,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004920172506872525,
|
|
"loss": 6.0148,
|
|
"mean_token_accuracy": 0.17681244760751724,
|
|
"num_tokens": 21004111.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.261019992828369,
|
|
"epoch": 0.9567224466243508,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004920063530127508,
|
|
"loss": 6.0,
|
|
"mean_token_accuracy": 0.16469207853078843,
|
|
"num_tokens": 21017523.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.340602111816406,
|
|
"epoch": 0.9572994806693594,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004919954480393482,
|
|
"loss": 6.0699,
|
|
"mean_token_accuracy": 0.16875892877578735,
|
|
"num_tokens": 21028723.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.284719848632813,
|
|
"epoch": 0.9578765147143682,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004919845357674114,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.17578147649765014,
|
|
"num_tokens": 21042205.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.282210159301758,
|
|
"epoch": 0.9584535487593768,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004919736161973076,
|
|
"loss": 6.0003,
|
|
"mean_token_accuracy": 0.17048712372779845,
|
|
"num_tokens": 21053798.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.315688991546631,
|
|
"epoch": 0.9590305828043855,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000491962689329404,
|
|
"loss": 6.164,
|
|
"mean_token_accuracy": 0.16235949844121933,
|
|
"num_tokens": 21068333.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.3100635528564455,
|
|
"epoch": 0.9596076168493941,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004919517551640681,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.18080112636089324,
|
|
"num_tokens": 21079484.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.214249849319458,
|
|
"epoch": 0.9601846508944027,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004919408137016677,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.17698175609111785,
|
|
"num_tokens": 21090940.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.36199107170105,
|
|
"epoch": 0.9607616849394114,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004919298649425708,
|
|
"loss": 6.0958,
|
|
"mean_token_accuracy": 0.16862892359495163,
|
|
"num_tokens": 21104351.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.322522687911987,
|
|
"epoch": 0.96133871898442,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004919189088871456,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.16790530383586882,
|
|
"num_tokens": 21116272.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.316466999053955,
|
|
"epoch": 0.9619157530294288,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004919079455357608,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.16736244559288024,
|
|
"num_tokens": 21129448.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.3490674018859865,
|
|
"epoch": 0.9624927870744374,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004918969748887847,
|
|
"loss": 6.1193,
|
|
"mean_token_accuracy": 0.1631232514977455,
|
|
"num_tokens": 21143668.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.34621114730835,
|
|
"epoch": 0.9630698211194461,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004918859969465868,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.16959568858146667,
|
|
"num_tokens": 21156662.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.289714431762695,
|
|
"epoch": 0.9636468551644547,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004918750117095361,
|
|
"loss": 6.068,
|
|
"mean_token_accuracy": 0.1759003534913063,
|
|
"num_tokens": 21170271.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.267118072509765,
|
|
"epoch": 0.9642238892094633,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004918640191780021,
|
|
"loss": 6.1094,
|
|
"mean_token_accuracy": 0.16548217386007308,
|
|
"num_tokens": 21183878.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.34764256477356,
|
|
"epoch": 0.964800923254472,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004918530193523546,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.173106586933136,
|
|
"num_tokens": 21196088.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.302213096618653,
|
|
"epoch": 0.9653779572994806,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004918420122329634,
|
|
"loss": 6.1573,
|
|
"mean_token_accuracy": 0.16970721781253814,
|
|
"num_tokens": 21208640.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.271123838424683,
|
|
"epoch": 0.9659549913444894,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004918309978201989,
|
|
"loss": 5.9581,
|
|
"mean_token_accuracy": 0.1844442144036293,
|
|
"num_tokens": 21221246.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.25211730003357,
|
|
"epoch": 0.966532025389498,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004918199761144315,
|
|
"loss": 6.0108,
|
|
"mean_token_accuracy": 0.1769232526421547,
|
|
"num_tokens": 21233834.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.292379760742188,
|
|
"epoch": 0.9671090594345066,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004918089471160318,
|
|
"loss": 6.0398,
|
|
"mean_token_accuracy": 0.17788860201835632,
|
|
"num_tokens": 21247388.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.304123020172119,
|
|
"epoch": 0.9676860934795153,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004917979108253709,
|
|
"loss": 6.0699,
|
|
"mean_token_accuracy": 0.1677810087800026,
|
|
"num_tokens": 21259800.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.304227828979492,
|
|
"epoch": 0.9682631275245239,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00049178686724282,
|
|
"loss": 6.0953,
|
|
"mean_token_accuracy": 0.170858334004879,
|
|
"num_tokens": 21271776.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.274011754989624,
|
|
"epoch": 0.9688401615695326,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004917758163687506,
|
|
"loss": 5.9803,
|
|
"mean_token_accuracy": 0.17564422339200975,
|
|
"num_tokens": 21285368.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.191785097122192,
|
|
"epoch": 0.9694171956145412,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004917647582035341,
|
|
"loss": 5.9786,
|
|
"mean_token_accuracy": 0.17851267009973526,
|
|
"num_tokens": 21299077.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.300303649902344,
|
|
"epoch": 0.96999422965955,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004917536927475428,
|
|
"loss": 6.0761,
|
|
"mean_token_accuracy": 0.17253753840923308,
|
|
"num_tokens": 21312379.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.277495002746582,
|
|
"epoch": 0.9705712637045586,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004917426200011486,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.1745515689253807,
|
|
"num_tokens": 21325530.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.155578470230102,
|
|
"epoch": 0.9711482977495672,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000491731539964724,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.18623323291540145,
|
|
"num_tokens": 21339200.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.288159465789795,
|
|
"epoch": 0.9717253317945759,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004917204526386418,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.18108310252428056,
|
|
"num_tokens": 21351072.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.213099575042724,
|
|
"epoch": 0.9723023658395845,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004917093580232748,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.17771366089582444,
|
|
"num_tokens": 21363691.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.306379938125611,
|
|
"epoch": 0.9728793998845932,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004916982561189962,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.16407431066036224,
|
|
"num_tokens": 21376896.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.317812871932984,
|
|
"epoch": 0.9734564339296018,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004916871469261794,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.1748368188738823,
|
|
"num_tokens": 21388590.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.295198154449463,
|
|
"epoch": 0.9740334679746105,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000491676030445198,
|
|
"loss": 6.1191,
|
|
"mean_token_accuracy": 0.17043811678886414,
|
|
"num_tokens": 21401912.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.25452184677124,
|
|
"epoch": 0.9746105020196192,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004916649066764259,
|
|
"loss": 6.0693,
|
|
"mean_token_accuracy": 0.17368588596582413,
|
|
"num_tokens": 21415472.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.265368223190308,
|
|
"epoch": 0.9751875360646278,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004916537756202375,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.17431591004133223,
|
|
"num_tokens": 21426758.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.249980115890503,
|
|
"epoch": 0.9757645701096365,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004916426372770069,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.1822528839111328,
|
|
"num_tokens": 21439347.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.344882678985596,
|
|
"epoch": 0.9763416041546451,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004916314916471087,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.16698339730501174,
|
|
"num_tokens": 21451359.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.38165602684021,
|
|
"epoch": 0.9769186381996537,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004916203387309179,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.16740904450416566,
|
|
"num_tokens": 21464926.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.275937747955322,
|
|
"epoch": 0.9774956722446624,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004916091785288096,
|
|
"loss": 6.0692,
|
|
"mean_token_accuracy": 0.1693897143006325,
|
|
"num_tokens": 21477234.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.180343294143677,
|
|
"epoch": 0.9780727062896711,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004915980110411593,
|
|
"loss": 5.9165,
|
|
"mean_token_accuracy": 0.18313064575195312,
|
|
"num_tokens": 21488751.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.286865949630737,
|
|
"epoch": 0.9786497403346798,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004915868362683425,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.17128912955522538,
|
|
"num_tokens": 21500532.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.272981214523315,
|
|
"epoch": 0.9792267743796884,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004915756542107349,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.1687467187643051,
|
|
"num_tokens": 21513725.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.193865776062012,
|
|
"epoch": 0.979803808424697,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004915644648687127,
|
|
"loss": 5.9724,
|
|
"mean_token_accuracy": 0.18019705414772033,
|
|
"num_tokens": 21526886.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.174581098556518,
|
|
"epoch": 0.9803808424697057,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004915532682426524,
|
|
"loss": 5.9082,
|
|
"mean_token_accuracy": 0.18099150508642198,
|
|
"num_tokens": 21539278.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.3271393299102785,
|
|
"epoch": 0.9809578765147143,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004915420643329306,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.16990142911672593,
|
|
"num_tokens": 21551864.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.335036182403565,
|
|
"epoch": 0.981534910559723,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000491530853139924,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.1718694746494293,
|
|
"num_tokens": 21564398.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.335596990585327,
|
|
"epoch": 0.9821119446047317,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004915196346640095,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.1714094787836075,
|
|
"num_tokens": 21575998.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.278130578994751,
|
|
"epoch": 0.9826889786497404,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004915084089055648,
|
|
"loss": 6.054,
|
|
"mean_token_accuracy": 0.1700270876288414,
|
|
"num_tokens": 21589243.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.203781700134277,
|
|
"epoch": 0.983266012694749,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004914971758649673,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.1781109556555748,
|
|
"num_tokens": 21601229.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.335890817642212,
|
|
"epoch": 0.9838430467397576,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004914859355425948,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.17270396500825883,
|
|
"num_tokens": 21613270.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.192272806167603,
|
|
"epoch": 0.9844200807847663,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004914746879388255,
|
|
"loss": 5.9736,
|
|
"mean_token_accuracy": 0.17878717929124832,
|
|
"num_tokens": 21626463.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.245885515213013,
|
|
"epoch": 0.9849971148297749,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004914634330540373,
|
|
"loss": 6.0914,
|
|
"mean_token_accuracy": 0.17799934148788452,
|
|
"num_tokens": 21638172.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.308247900009155,
|
|
"epoch": 0.9855741488747836,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004914521708886093,
|
|
"loss": 6.0125,
|
|
"mean_token_accuracy": 0.17956866174936295,
|
|
"num_tokens": 21650015.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.33227424621582,
|
|
"epoch": 0.9861511829197923,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004914409014429201,
|
|
"loss": 6.1115,
|
|
"mean_token_accuracy": 0.1672136142849922,
|
|
"num_tokens": 21662502.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.221246337890625,
|
|
"epoch": 0.986728216964801,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004914296247173486,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.18216463774442673,
|
|
"num_tokens": 21675691.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.290973472595215,
|
|
"epoch": 0.9873052510098096,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004914183407122741,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.16632219403982162,
|
|
"num_tokens": 21687904.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.309543466567993,
|
|
"epoch": 0.9878822850548182,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004914070494280763,
|
|
"loss": 6.1354,
|
|
"mean_token_accuracy": 0.16766521334648132,
|
|
"num_tokens": 21700371.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.235837602615357,
|
|
"epoch": 0.9884593190998269,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004913957508651349,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.18258669674396516,
|
|
"num_tokens": 21715235.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.253808879852295,
|
|
"epoch": 0.9890363531448355,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004913844450238299,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.17600261121988298,
|
|
"num_tokens": 21727994.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.281888723373413,
|
|
"epoch": 0.9896133871898442,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004913731319045416,
|
|
"loss": 6.0036,
|
|
"mean_token_accuracy": 0.17418931275606156,
|
|
"num_tokens": 21739894.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.280125093460083,
|
|
"epoch": 0.9901904212348529,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004913618115076505,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.16924936175346375,
|
|
"num_tokens": 21752957.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.270187520980835,
|
|
"epoch": 0.9907674552798615,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004913504838335372,
|
|
"loss": 6.0117,
|
|
"mean_token_accuracy": 0.17379884719848632,
|
|
"num_tokens": 21765547.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.266125345230103,
|
|
"epoch": 0.9913444893248702,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004913391488825829,
|
|
"loss": 6.104,
|
|
"mean_token_accuracy": 0.17694249451160432,
|
|
"num_tokens": 21778817.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.2261824131011965,
|
|
"epoch": 0.9919215233698788,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004913278066551689,
|
|
"loss": 6.0004,
|
|
"mean_token_accuracy": 0.1725752294063568,
|
|
"num_tokens": 21791002.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.2803973197937015,
|
|
"epoch": 0.9924985574148875,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004913164571516765,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.17212606966495514,
|
|
"num_tokens": 21803877.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.300022172927856,
|
|
"epoch": 0.9930755914598961,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004913051003724876,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.1742602214217186,
|
|
"num_tokens": 21815884.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.240463399887085,
|
|
"epoch": 0.9936526255049047,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004912937363179839,
|
|
"loss": 6.0434,
|
|
"mean_token_accuracy": 0.17520978897809983,
|
|
"num_tokens": 21826990.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.244440984725952,
|
|
"epoch": 0.9942296595499135,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000491282364988548,
|
|
"loss": 6.0255,
|
|
"mean_token_accuracy": 0.17350778728723526,
|
|
"num_tokens": 21838835.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.383248662948608,
|
|
"epoch": 0.9948066935949221,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004912709863845621,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.17144082933664323,
|
|
"num_tokens": 21850924.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.318079805374145,
|
|
"epoch": 0.9953837276399308,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000491259600506409,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.17307236343622207,
|
|
"num_tokens": 21862720.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.25905818939209,
|
|
"epoch": 0.9959607616849394,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004912482073544716,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.17808614820241928,
|
|
"num_tokens": 21874655.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.23261022567749,
|
|
"epoch": 0.996537795729948,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004912368069291333,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.1786980226635933,
|
|
"num_tokens": 21886911.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.205492162704468,
|
|
"epoch": 0.9971148297749567,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004912253992307773,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.18051304966211318,
|
|
"num_tokens": 21899614.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.31227822303772,
|
|
"epoch": 0.9976918638199653,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004912139842597875,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.17408534735441208,
|
|
"num_tokens": 21912756.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.221034145355224,
|
|
"epoch": 0.9982688978649741,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004912025620165477,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.17002497762441635,
|
|
"num_tokens": 21924911.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.188537883758545,
|
|
"epoch": 0.9988459319099827,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004911911325014421,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.1789535701274872,
|
|
"num_tokens": 21938204.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.342658185958863,
|
|
"epoch": 0.9994229659549914,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004911796957148552,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.17369647771120073,
|
|
"num_tokens": 21951285.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.299900817871094,
|
|
"epoch": 1.0,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004911682516571715,
|
|
"loss": 6.0679,
|
|
"mean_token_accuracy": 0.17429974675178528,
|
|
"num_tokens": 21963117.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.271995592117309,
|
|
"epoch": 1.0005770340450086,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004911568003287761,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.17250487804412842,
|
|
"num_tokens": 21976103.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.1640949726104735,
|
|
"epoch": 1.0011540680900173,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004911453417300541,
|
|
"loss": 5.8559,
|
|
"mean_token_accuracy": 0.19138497710227967,
|
|
"num_tokens": 21987905.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.174138498306275,
|
|
"epoch": 1.001731102135026,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004911338758613909,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.1773781344294548,
|
|
"num_tokens": 22000872.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.288146829605102,
|
|
"epoch": 1.0023081361800346,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004911224027231722,
|
|
"loss": 5.9653,
|
|
"mean_token_accuracy": 0.17484614700078965,
|
|
"num_tokens": 22012725.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.250091552734375,
|
|
"epoch": 1.0028851702250432,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004911109223157838,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.18360436111688613,
|
|
"num_tokens": 22024802.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.269646549224854,
|
|
"epoch": 1.0034622042700518,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004910994346396118,
|
|
"loss": 5.977,
|
|
"mean_token_accuracy": 0.17402059137821196,
|
|
"num_tokens": 22037481.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.29124493598938,
|
|
"epoch": 1.0040392383150605,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004910879396950427,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.17953110933303834,
|
|
"num_tokens": 22049387.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.334495115280151,
|
|
"epoch": 1.0046162723600693,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000491076437482463,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.1691194236278534,
|
|
"num_tokens": 22061323.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 6.277500820159912,
|
|
"epoch": 1.005193306405078,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004910649280022599,
|
|
"loss": 5.8992,
|
|
"mean_token_accuracy": 0.18170523196458815,
|
|
"num_tokens": 22073163.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.146124935150146,
|
|
"epoch": 1.0057703404500866,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004910534112548201,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.17684150934219361,
|
|
"num_tokens": 22085583.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.330292797088623,
|
|
"epoch": 1.0063473744950953,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004910418872405312,
|
|
"loss": 6.0036,
|
|
"mean_token_accuracy": 0.17630979269742966,
|
|
"num_tokens": 22098241.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.291881656646728,
|
|
"epoch": 1.006924408540104,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004910303559597806,
|
|
"loss": 5.8999,
|
|
"mean_token_accuracy": 0.1765839233994484,
|
|
"num_tokens": 22111626.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.200822734832764,
|
|
"epoch": 1.0075014425851125,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004910188174129564,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.17677416950464248,
|
|
"num_tokens": 22124653.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.312221431732178,
|
|
"epoch": 1.0080784766301212,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004910072716004466,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.17987631410360336,
|
|
"num_tokens": 22137154.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.337836599349975,
|
|
"epoch": 1.0086555106751298,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004909957185226394,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.16782609969377518,
|
|
"num_tokens": 22149374.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.2611909866333,
|
|
"epoch": 1.0092325447201385,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004909841581799236,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.17667713165283203,
|
|
"num_tokens": 22161988.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.318277978897095,
|
|
"epoch": 1.009809578765147,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004909725905726879,
|
|
"loss": 6.0643,
|
|
"mean_token_accuracy": 0.17233245372772216,
|
|
"num_tokens": 22173490.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.302417469024658,
|
|
"epoch": 1.0103866128101557,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004909610157013214,
|
|
"loss": 5.9981,
|
|
"mean_token_accuracy": 0.17494946718215942,
|
|
"num_tokens": 22185065.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.222137498855591,
|
|
"epoch": 1.0109636468551644,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004909494335662134,
|
|
"loss": 5.9457,
|
|
"mean_token_accuracy": 0.1837028831243515,
|
|
"num_tokens": 22198325.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.141578102111817,
|
|
"epoch": 1.011540680900173,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004909378441677535,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.18548515439033508,
|
|
"num_tokens": 22211827.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.244017887115478,
|
|
"epoch": 1.0121177149451817,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004909262475063314,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.176451376080513,
|
|
"num_tokens": 22223411.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.229418849945068,
|
|
"epoch": 1.0126947489901905,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004909146435823373,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.17601740062236787,
|
|
"num_tokens": 22237752.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.316747760772705,
|
|
"epoch": 1.0132717830351992,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004909030323961613,
|
|
"loss": 5.9883,
|
|
"mean_token_accuracy": 0.17417865097522736,
|
|
"num_tokens": 22249778.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.272009181976318,
|
|
"epoch": 1.0138488170802078,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004908914139481942,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.17759780436754227,
|
|
"num_tokens": 22262514.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.274535417556763,
|
|
"epoch": 1.0144258511252164,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004908797882388265,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.17650485783815384,
|
|
"num_tokens": 22273662.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.2734862804412845,
|
|
"epoch": 1.015002885170225,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004908681552684495,
|
|
"loss": 6.0197,
|
|
"mean_token_accuracy": 0.17017416656017303,
|
|
"num_tokens": 22286213.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.206152629852295,
|
|
"epoch": 1.0155799192152337,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004908565150374542,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.18659797310829163,
|
|
"num_tokens": 22299191.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.220057153701783,
|
|
"epoch": 1.0161569532602424,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004908448675462323,
|
|
"loss": 5.9168,
|
|
"mean_token_accuracy": 0.18124910145998002,
|
|
"num_tokens": 22312047.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.246239233016968,
|
|
"epoch": 1.016733987305251,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004908332127951756,
|
|
"loss": 6.0308,
|
|
"mean_token_accuracy": 0.17177972793579102,
|
|
"num_tokens": 22326069.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.313067102432251,
|
|
"epoch": 1.0173110213502596,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004908215507846757,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.17213782370090486,
|
|
"num_tokens": 22338593.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.271481513977051,
|
|
"epoch": 1.0178880553952683,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004908098815151254,
|
|
"loss": 5.9423,
|
|
"mean_token_accuracy": 0.1799215242266655,
|
|
"num_tokens": 22352286.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.271336078643799,
|
|
"epoch": 1.018465089440277,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004907982049869168,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.1777525871992111,
|
|
"num_tokens": 22364270.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.226083993911743,
|
|
"epoch": 1.0190421234852856,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004907865212004428,
|
|
"loss": 5.9637,
|
|
"mean_token_accuracy": 0.17348791360855104,
|
|
"num_tokens": 22377799.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.261759424209595,
|
|
"epoch": 1.0196191575302942,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004907748301560963,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.17696553617715835,
|
|
"num_tokens": 22389913.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.26409945487976,
|
|
"epoch": 1.0201961915753028,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004907631318542707,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.17762383669614792,
|
|
"num_tokens": 22401545.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.210157775878907,
|
|
"epoch": 1.0207732256203117,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004907514262953594,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.1783894494175911,
|
|
"num_tokens": 22414084.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.22634482383728,
|
|
"epoch": 1.0213502596653203,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004907397134797559,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.18252388536930084,
|
|
"num_tokens": 22427406.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.323730850219727,
|
|
"epoch": 1.021927293710329,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004907279934078543,
|
|
"loss": 5.9997,
|
|
"mean_token_accuracy": 0.1736849933862686,
|
|
"num_tokens": 22441118.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.31430492401123,
|
|
"epoch": 1.0225043277553376,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004907162660800488,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.17202019542455674,
|
|
"num_tokens": 22453799.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.3228006839752195,
|
|
"epoch": 1.0230813618003463,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004907045314967338,
|
|
"loss": 6.0158,
|
|
"mean_token_accuracy": 0.1706335499882698,
|
|
"num_tokens": 22466573.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.205880975723266,
|
|
"epoch": 1.023658395845355,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004906927896583041,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.18316041827201843,
|
|
"num_tokens": 22478968.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.245298290252686,
|
|
"epoch": 1.0242354298903635,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004906810405651546,
|
|
"loss": 5.885,
|
|
"mean_token_accuracy": 0.18523868173360825,
|
|
"num_tokens": 22490669.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.280638694763184,
|
|
"epoch": 1.0248124639353722,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004906692842176803,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.1728905886411667,
|
|
"num_tokens": 22502235.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.2999005794525145,
|
|
"epoch": 1.0253894979803808,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004906575206162769,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.17361630797386168,
|
|
"num_tokens": 22514535.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.253720092773437,
|
|
"epoch": 1.0259665320253895,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004906457497613399,
|
|
"loss": 5.9391,
|
|
"mean_token_accuracy": 0.17980763763189317,
|
|
"num_tokens": 22527773.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.2260314464569095,
|
|
"epoch": 1.026543566070398,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004906339716532651,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.1829774111509323,
|
|
"num_tokens": 22541853.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.360072422027588,
|
|
"epoch": 1.0271206001154067,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004906221862924488,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.16649125069379805,
|
|
"num_tokens": 22554473.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.310372686386108,
|
|
"epoch": 1.0276976341604154,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004906103936792875,
|
|
"loss": 5.9899,
|
|
"mean_token_accuracy": 0.17342302650213243,
|
|
"num_tokens": 22567107.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.255186080932617,
|
|
"epoch": 1.028274668205424,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004905985938141777,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.16475126296281814,
|
|
"num_tokens": 22579806.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.290994596481323,
|
|
"epoch": 1.0288517022504329,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004905867866975163,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.17861126959323884,
|
|
"num_tokens": 22593460.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.27809362411499,
|
|
"epoch": 1.0294287362954415,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004905749723297003,
|
|
"loss": 6.0062,
|
|
"mean_token_accuracy": 0.17625349313020705,
|
|
"num_tokens": 22607113.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.285610055923462,
|
|
"epoch": 1.0300057703404502,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004905631507111271,
|
|
"loss": 5.9193,
|
|
"mean_token_accuracy": 0.17798546701669693,
|
|
"num_tokens": 22619749.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.206954050064087,
|
|
"epoch": 1.0305828043854588,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004905513218421946,
|
|
"loss": 5.8888,
|
|
"mean_token_accuracy": 0.18107479810714722,
|
|
"num_tokens": 22632584.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.265821838378907,
|
|
"epoch": 1.0311598384304674,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004905394857233004,
|
|
"loss": 5.9746,
|
|
"mean_token_accuracy": 0.17853020131587982,
|
|
"num_tokens": 22645181.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.315801954269409,
|
|
"epoch": 1.031736872475476,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004905276423548426,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.1747600942850113,
|
|
"num_tokens": 22657666.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.293545866012574,
|
|
"epoch": 1.0323139065204847,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004905157917372197,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.16805843263864517,
|
|
"num_tokens": 22670404.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.278645467758179,
|
|
"epoch": 1.0328909405654934,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004905039338708302,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.1695145219564438,
|
|
"num_tokens": 22683558.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.292709922790527,
|
|
"epoch": 1.033467974610502,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004904920687560728,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.18147481679916383,
|
|
"num_tokens": 22694907.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.294043922424317,
|
|
"epoch": 1.0340450086555106,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004904801963933469,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.16681005507707597,
|
|
"num_tokens": 22707447.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.271177196502686,
|
|
"epoch": 1.0346220427005193,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004904683167830515,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.1795396849513054,
|
|
"num_tokens": 22719150.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.298140621185302,
|
|
"epoch": 1.035199076745528,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004904564299255862,
|
|
"loss": 6.0155,
|
|
"mean_token_accuracy": 0.1723608747124672,
|
|
"num_tokens": 22732489.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.189728879928589,
|
|
"epoch": 1.0357761107905366,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004904445358213511,
|
|
"loss": 5.8812,
|
|
"mean_token_accuracy": 0.1754599243402481,
|
|
"num_tokens": 22745543.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.282424354553223,
|
|
"epoch": 1.0363531448355452,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004904326344707461,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.17686663717031478,
|
|
"num_tokens": 22757643.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.321871137619018,
|
|
"epoch": 1.036930178880554,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004904207258741712,
|
|
"loss": 5.971,
|
|
"mean_token_accuracy": 0.17963920831680297,
|
|
"num_tokens": 22770707.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.256516742706299,
|
|
"epoch": 1.0375072129255627,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004904088100320274,
|
|
"loss": 5.9979,
|
|
"mean_token_accuracy": 0.1751512423157692,
|
|
"num_tokens": 22782630.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.2503931522369385,
|
|
"epoch": 1.0380842469705713,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004903968869447151,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.17432793825864792,
|
|
"num_tokens": 22795693.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.373712539672852,
|
|
"epoch": 1.03866128101558,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004903849566126356,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.1701628342270851,
|
|
"num_tokens": 22807715.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.03866128101558,
|
|
"eval_entropy": 6.111053488421989,
|
|
"eval_loss": 6.069920539855957,
|
|
"eval_mean_token_accuracy": 0.17735485498043227,
|
|
"eval_num_tokens": 22807715.0,
|
|
"eval_runtime": 17.4995,
|
|
"eval_samples_per_second": 1607.814,
|
|
"eval_steps_per_second": 200.977,
|
|
"step": 9000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 86650,
|
|
"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": 4991257630310400.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|