618f2170d1
Model: fpadovani/jpn-jpan-10mb-after-ppt-Dp-100mb-ckpt500_seed455 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3462204270051933,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1670144584089600.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|