6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2520478890989288,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742606925964356,
|
|
"epoch": 0.0004200798151648813,
|
|
"grad_norm": 5.21875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7358,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 8348.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.74260492324829,
|
|
"epoch": 0.0008401596303297626,
|
|
"grad_norm": 5.15625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7547,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 17465.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742631721496583,
|
|
"epoch": 0.001260239445494644,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7247,
|
|
"mean_token_accuracy": 0.00010341261513531208,
|
|
"num_tokens": 26627.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742714214324952,
|
|
"epoch": 0.0016803192606595252,
|
|
"grad_norm": 4.96875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.6807,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 36069.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742774486541748,
|
|
"epoch": 0.002100399075824407,
|
|
"grad_norm": 4.96875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.564,
|
|
"mean_token_accuracy": 0.0009151221020147204,
|
|
"num_tokens": 44967.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.742547607421875,
|
|
"epoch": 0.002520478890989288,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4843,
|
|
"mean_token_accuracy": 0.0172414593398571,
|
|
"num_tokens": 55132.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.741770172119141,
|
|
"epoch": 0.0029405587061541692,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3322,
|
|
"mean_token_accuracy": 0.044619453698396684,
|
|
"num_tokens": 65141.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.739381885528564,
|
|
"epoch": 0.0033606385213190504,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.2048,
|
|
"mean_token_accuracy": 0.04063304513692856,
|
|
"num_tokens": 74007.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.735391807556152,
|
|
"epoch": 0.003780718336483932,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1027,
|
|
"mean_token_accuracy": 0.04380051270127296,
|
|
"num_tokens": 83736.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.731560325622558,
|
|
"epoch": 0.004200798151648814,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.0024,
|
|
"mean_token_accuracy": 0.04462047629058361,
|
|
"num_tokens": 92525.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.729215049743653,
|
|
"epoch": 0.004620877966813695,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9462,
|
|
"mean_token_accuracy": 0.042681990377604964,
|
|
"num_tokens": 102015.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.728453350067138,
|
|
"epoch": 0.005040957781978576,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.9154,
|
|
"mean_token_accuracy": 0.03954915180802345,
|
|
"num_tokens": 110887.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.727616500854491,
|
|
"epoch": 0.005461037597143457,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.8453,
|
|
"mean_token_accuracy": 0.04232911877334118,
|
|
"num_tokens": 120442.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.726141738891602,
|
|
"epoch": 0.0058811174123083385,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.7509,
|
|
"mean_token_accuracy": 0.041194649040699007,
|
|
"num_tokens": 129297.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.723711013793945,
|
|
"epoch": 0.00630119722747322,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.7015,
|
|
"mean_token_accuracy": 0.04228766188025475,
|
|
"num_tokens": 138305.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.719814491271972,
|
|
"epoch": 0.006721277042638101,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.6499,
|
|
"mean_token_accuracy": 0.04200226049870252,
|
|
"num_tokens": 147640.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.714290428161622,
|
|
"epoch": 0.007141356857802983,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.576,
|
|
"mean_token_accuracy": 0.04255363866686821,
|
|
"num_tokens": 157633.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.707357215881348,
|
|
"epoch": 0.007561436672967864,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5382,
|
|
"mean_token_accuracy": 0.03800953794270754,
|
|
"num_tokens": 167984.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.699947547912597,
|
|
"epoch": 0.007981516488132745,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4351,
|
|
"mean_token_accuracy": 0.04883353523910046,
|
|
"num_tokens": 176984.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.683709812164306,
|
|
"epoch": 0.008401596303297627,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3133,
|
|
"mean_token_accuracy": 0.051684480533003806,
|
|
"num_tokens": 185931.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.665494632720947,
|
|
"epoch": 0.008821676118462508,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2723,
|
|
"mean_token_accuracy": 0.05058838985860348,
|
|
"num_tokens": 195065.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.650426483154297,
|
|
"epoch": 0.00924175593362739,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1345,
|
|
"mean_token_accuracy": 0.05380081832408905,
|
|
"num_tokens": 203687.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.613165855407715,
|
|
"epoch": 0.00966183574879227,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0467,
|
|
"mean_token_accuracy": 0.057396522164344786,
|
|
"num_tokens": 212847.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.554168796539306,
|
|
"epoch": 0.010081915563957152,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.93,
|
|
"mean_token_accuracy": 0.05599412247538567,
|
|
"num_tokens": 222593.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.50309362411499,
|
|
"epoch": 0.010501995379122032,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7842,
|
|
"mean_token_accuracy": 0.054633737355470655,
|
|
"num_tokens": 231174.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.446444129943847,
|
|
"epoch": 0.010922075194286915,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6507,
|
|
"mean_token_accuracy": 0.05882068388164043,
|
|
"num_tokens": 239833.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.371571159362793,
|
|
"epoch": 0.011342155009451797,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.62,
|
|
"mean_token_accuracy": 0.05638743191957474,
|
|
"num_tokens": 248794.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.297250938415527,
|
|
"epoch": 0.011762234824616677,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.5299,
|
|
"mean_token_accuracy": 0.056220804899930955,
|
|
"num_tokens": 257123.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.228730010986329,
|
|
"epoch": 0.012182314639781559,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2842,
|
|
"mean_token_accuracy": 0.05619280487298965,
|
|
"num_tokens": 266088.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.08653745651245,
|
|
"epoch": 0.01260239445494644,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.3619,
|
|
"mean_token_accuracy": 0.0516346599906683,
|
|
"num_tokens": 276074.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.963776969909668,
|
|
"epoch": 0.013022474270111321,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1944,
|
|
"mean_token_accuracy": 0.054025283083319664,
|
|
"num_tokens": 285280.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.805997848510742,
|
|
"epoch": 0.013442554085276202,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.151,
|
|
"mean_token_accuracy": 0.052671706303954124,
|
|
"num_tokens": 296115.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.606755542755128,
|
|
"epoch": 0.013862633900441084,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.9584,
|
|
"mean_token_accuracy": 0.05575060956180096,
|
|
"num_tokens": 305483.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.449717140197754,
|
|
"epoch": 0.014282713715605966,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.9165,
|
|
"mean_token_accuracy": 0.058218777552247046,
|
|
"num_tokens": 314000.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.167982482910157,
|
|
"epoch": 0.014702793530770846,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.8517,
|
|
"mean_token_accuracy": 0.062257979065179825,
|
|
"num_tokens": 323667.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.951386070251464,
|
|
"epoch": 0.015122873345935728,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.8029,
|
|
"mean_token_accuracy": 0.06150264739990234,
|
|
"num_tokens": 332695.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.776250171661378,
|
|
"epoch": 0.015542953161100609,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.643,
|
|
"mean_token_accuracy": 0.05887415409088135,
|
|
"num_tokens": 342428.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.602806949615479,
|
|
"epoch": 0.01596303297626549,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.7106,
|
|
"mean_token_accuracy": 0.06374814324080944,
|
|
"num_tokens": 353587.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.474033164978028,
|
|
"epoch": 0.01638311279143037,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.6401,
|
|
"mean_token_accuracy": 0.06406850814819336,
|
|
"num_tokens": 362997.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.364265060424804,
|
|
"epoch": 0.016803192606595255,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.6617,
|
|
"mean_token_accuracy": 0.06993534453213215,
|
|
"num_tokens": 372346.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.375140285491943,
|
|
"epoch": 0.017223272421760135,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.5334,
|
|
"mean_token_accuracy": 0.06646758764982223,
|
|
"num_tokens": 381575.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.26815767288208,
|
|
"epoch": 0.017643352236925015,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.5902,
|
|
"mean_token_accuracy": 0.07085754275321961,
|
|
"num_tokens": 390706.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.218460845947266,
|
|
"epoch": 0.018063432052089896,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.5876,
|
|
"mean_token_accuracy": 0.07221915200352669,
|
|
"num_tokens": 400000.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.139337062835693,
|
|
"epoch": 0.01848351186725478,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.5295,
|
|
"mean_token_accuracy": 0.07644539698958397,
|
|
"num_tokens": 409447.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.122040271759033,
|
|
"epoch": 0.01890359168241966,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.5068,
|
|
"mean_token_accuracy": 0.07519292533397674,
|
|
"num_tokens": 418417.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.067694330215454,
|
|
"epoch": 0.01932367149758454,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.4664,
|
|
"mean_token_accuracy": 0.07503528967499733,
|
|
"num_tokens": 427619.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.071773529052734,
|
|
"epoch": 0.019743751312749424,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.5131,
|
|
"mean_token_accuracy": 0.07185145244002342,
|
|
"num_tokens": 437931.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.109980726242066,
|
|
"epoch": 0.020163831127914304,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.552,
|
|
"mean_token_accuracy": 0.07611973807215691,
|
|
"num_tokens": 447595.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.026875400543213,
|
|
"epoch": 0.020583910943079185,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.4164,
|
|
"mean_token_accuracy": 0.07035953775048256,
|
|
"num_tokens": 457062.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.063331604003906,
|
|
"epoch": 0.021003990758244065,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.5166,
|
|
"mean_token_accuracy": 0.07237975299358368,
|
|
"num_tokens": 466191.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.050399017333984,
|
|
"epoch": 0.02142407057340895,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4443,
|
|
"mean_token_accuracy": 0.07492763809859752,
|
|
"num_tokens": 475693.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.024266242980957,
|
|
"epoch": 0.02184415038857383,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.4691,
|
|
"mean_token_accuracy": 0.07379123903810977,
|
|
"num_tokens": 485173.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.993921422958374,
|
|
"epoch": 0.02226423020373871,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.3863,
|
|
"mean_token_accuracy": 0.08008474782109261,
|
|
"num_tokens": 493985.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.907951974868775,
|
|
"epoch": 0.022684310018903593,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.4036,
|
|
"mean_token_accuracy": 0.07586845718324184,
|
|
"num_tokens": 502837.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.981403732299805,
|
|
"epoch": 0.023104389834068473,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.3605,
|
|
"mean_token_accuracy": 0.07924394458532333,
|
|
"num_tokens": 511503.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.977783203125,
|
|
"epoch": 0.023524469649233354,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.5335,
|
|
"mean_token_accuracy": 0.0751778606325388,
|
|
"num_tokens": 521499.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.871473217010498,
|
|
"epoch": 0.023944549464398234,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.2955,
|
|
"mean_token_accuracy": 0.0799000546336174,
|
|
"num_tokens": 530067.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.885423564910889,
|
|
"epoch": 0.024364629279563118,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.2851,
|
|
"mean_token_accuracy": 0.08089336939156055,
|
|
"num_tokens": 538559.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.956486988067627,
|
|
"epoch": 0.024784709094728,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.4858,
|
|
"mean_token_accuracy": 0.07482350952923297,
|
|
"num_tokens": 547288.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.870783424377441,
|
|
"epoch": 0.02520478890989288,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.3589,
|
|
"mean_token_accuracy": 0.07514288201928139,
|
|
"num_tokens": 557269.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.939627742767334,
|
|
"epoch": 0.025624868725057762,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.3914,
|
|
"mean_token_accuracy": 0.07472754344344139,
|
|
"num_tokens": 567280.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.828274822235107,
|
|
"epoch": 0.026044948540222643,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.2341,
|
|
"mean_token_accuracy": 0.07823858335614205,
|
|
"num_tokens": 576609.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.761577320098877,
|
|
"epoch": 0.026465028355387523,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.1336,
|
|
"mean_token_accuracy": 0.08791142702102661,
|
|
"num_tokens": 586053.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.695616436004639,
|
|
"epoch": 0.026885108170552403,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.3339,
|
|
"mean_token_accuracy": 0.08298731297254562,
|
|
"num_tokens": 594649.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.869348049163818,
|
|
"epoch": 0.027305187985717287,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.2862,
|
|
"mean_token_accuracy": 0.07372522614896297,
|
|
"num_tokens": 603445.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.86638765335083,
|
|
"epoch": 0.027725267800882167,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.3613,
|
|
"mean_token_accuracy": 0.07848134562373162,
|
|
"num_tokens": 613611.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.971248960494995,
|
|
"epoch": 0.028145347616047048,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.5217,
|
|
"mean_token_accuracy": 0.07931054159998893,
|
|
"num_tokens": 623024.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.725814580917358,
|
|
"epoch": 0.02856542743121193,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.225,
|
|
"mean_token_accuracy": 0.08345521688461303,
|
|
"num_tokens": 631624.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.762637519836426,
|
|
"epoch": 0.028985507246376812,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.1844,
|
|
"mean_token_accuracy": 0.08410112038254738,
|
|
"num_tokens": 640473.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.841788578033447,
|
|
"epoch": 0.029405587061541692,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.3409,
|
|
"mean_token_accuracy": 0.08037517666816711,
|
|
"num_tokens": 649692.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.800195980072021,
|
|
"epoch": 0.029825666876706573,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.2995,
|
|
"mean_token_accuracy": 0.08097823038697242,
|
|
"num_tokens": 658236.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.668969297409058,
|
|
"epoch": 0.030245746691871456,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.0948,
|
|
"mean_token_accuracy": 0.08619136661291123,
|
|
"num_tokens": 667175.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.798488330841065,
|
|
"epoch": 0.030665826507036337,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.3842,
|
|
"mean_token_accuracy": 0.07823293879628182,
|
|
"num_tokens": 676456.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.812319660186768,
|
|
"epoch": 0.031085906322201217,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.3503,
|
|
"mean_token_accuracy": 0.07726633399724961,
|
|
"num_tokens": 686881.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.688674831390381,
|
|
"epoch": 0.0315059861373661,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.1373,
|
|
"mean_token_accuracy": 0.0819906547665596,
|
|
"num_tokens": 696045.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.655067443847656,
|
|
"epoch": 0.03192606595253098,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.1112,
|
|
"mean_token_accuracy": 0.08879919424653053,
|
|
"num_tokens": 704729.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.4980494499206545,
|
|
"epoch": 0.032346145767695865,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.1679,
|
|
"mean_token_accuracy": 0.07921729236841202,
|
|
"num_tokens": 714331.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.735121536254883,
|
|
"epoch": 0.03276622558286074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.1229,
|
|
"mean_token_accuracy": 0.08520057946443557,
|
|
"num_tokens": 722788.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.683975791931152,
|
|
"epoch": 0.033186305398025626,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.1944,
|
|
"mean_token_accuracy": 0.08690556064248085,
|
|
"num_tokens": 731417.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.576824569702149,
|
|
"epoch": 0.03360638521319051,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.1549,
|
|
"mean_token_accuracy": 0.08151165619492531,
|
|
"num_tokens": 741034.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.698281908035279,
|
|
"epoch": 0.034026465028355386,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.156,
|
|
"mean_token_accuracy": 0.08484743162989616,
|
|
"num_tokens": 749596.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.556124067306518,
|
|
"epoch": 0.03444654484352027,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.1145,
|
|
"mean_token_accuracy": 0.08153974264860153,
|
|
"num_tokens": 758931.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.533982944488526,
|
|
"epoch": 0.03486662465868515,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.0206,
|
|
"mean_token_accuracy": 0.09019657000899314,
|
|
"num_tokens": 767534.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.6061821460723875,
|
|
"epoch": 0.03528670447385003,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.0789,
|
|
"mean_token_accuracy": 0.08290171101689339,
|
|
"num_tokens": 776456.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.5107566833496096,
|
|
"epoch": 0.035706784289014915,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.1362,
|
|
"mean_token_accuracy": 0.08152465149760246,
|
|
"num_tokens": 786172.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.553678846359253,
|
|
"epoch": 0.03612686410417979,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.0139,
|
|
"mean_token_accuracy": 0.09106989204883575,
|
|
"num_tokens": 795081.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.604944372177124,
|
|
"epoch": 0.036546943919344675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.0628,
|
|
"mean_token_accuracy": 0.08461785838007926,
|
|
"num_tokens": 804259.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.534902191162109,
|
|
"epoch": 0.03696702373450956,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.0873,
|
|
"mean_token_accuracy": 0.08283074498176575,
|
|
"num_tokens": 813463.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.502531671524048,
|
|
"epoch": 0.037387103549674436,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.0035,
|
|
"mean_token_accuracy": 0.09452007561922074,
|
|
"num_tokens": 823029.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.486780834197998,
|
|
"epoch": 0.03780718336483932,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.0727,
|
|
"mean_token_accuracy": 0.08529324010014534,
|
|
"num_tokens": 832902.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.476432847976684,
|
|
"epoch": 0.0382272631800042,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.0158,
|
|
"mean_token_accuracy": 0.08854726403951645,
|
|
"num_tokens": 842162.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.52789797782898,
|
|
"epoch": 0.03864734299516908,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.0493,
|
|
"mean_token_accuracy": 0.08622511699795724,
|
|
"num_tokens": 852328.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.449561357498169,
|
|
"epoch": 0.039067422810333964,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.0104,
|
|
"mean_token_accuracy": 0.09133929386734962,
|
|
"num_tokens": 860929.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.458409357070923,
|
|
"epoch": 0.03948750262549885,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.0901,
|
|
"mean_token_accuracy": 0.08522843271493911,
|
|
"num_tokens": 869144.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.584603118896484,
|
|
"epoch": 0.039907582440663725,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.03,
|
|
"mean_token_accuracy": 0.09454337358474732,
|
|
"num_tokens": 877447.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.431310081481934,
|
|
"epoch": 0.04032766225582861,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.9871,
|
|
"mean_token_accuracy": 0.08733554184436798,
|
|
"num_tokens": 887020.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.453667879104614,
|
|
"epoch": 0.040747742070993485,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.0323,
|
|
"mean_token_accuracy": 0.08681000843644142,
|
|
"num_tokens": 895937.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.41835618019104,
|
|
"epoch": 0.04116782188615837,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.0366,
|
|
"mean_token_accuracy": 0.08261745497584343,
|
|
"num_tokens": 905446.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.464281463623047,
|
|
"epoch": 0.04158790170132325,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.9289,
|
|
"mean_token_accuracy": 0.09576694294810295,
|
|
"num_tokens": 914547.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.421106290817261,
|
|
"epoch": 0.04200798151648813,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.9377,
|
|
"mean_token_accuracy": 0.0962467186152935,
|
|
"num_tokens": 922900.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.401471900939941,
|
|
"epoch": 0.042428061331653014,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.9572,
|
|
"mean_token_accuracy": 0.09509932994842529,
|
|
"num_tokens": 930876.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.342588901519775,
|
|
"epoch": 0.0428481411468179,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.0021,
|
|
"mean_token_accuracy": 0.09231638312339782,
|
|
"num_tokens": 939871.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.44086856842041,
|
|
"epoch": 0.043268220961982774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.988,
|
|
"mean_token_accuracy": 0.09245615154504776,
|
|
"num_tokens": 948673.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.274595832824707,
|
|
"epoch": 0.04368830077714766,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.9409,
|
|
"mean_token_accuracy": 0.08984568417072296,
|
|
"num_tokens": 957603.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.436605787277221,
|
|
"epoch": 0.04410838059231254,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.0062,
|
|
"mean_token_accuracy": 0.08319340422749519,
|
|
"num_tokens": 967731.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.435907888412475,
|
|
"epoch": 0.04452846040747742,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.0032,
|
|
"mean_token_accuracy": 0.09049810692667962,
|
|
"num_tokens": 977427.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.3634380340576175,
|
|
"epoch": 0.0449485402226423,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.9827,
|
|
"mean_token_accuracy": 0.0860845424234867,
|
|
"num_tokens": 986758.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.425018453598023,
|
|
"epoch": 0.045368620037807186,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.9738,
|
|
"mean_token_accuracy": 0.09986243322491646,
|
|
"num_tokens": 996377.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.333861589431763,
|
|
"epoch": 0.04578869985297206,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.0222,
|
|
"mean_token_accuracy": 0.08520096391439438,
|
|
"num_tokens": 1006483.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.269639205932617,
|
|
"epoch": 0.04620877966813695,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.9248,
|
|
"mean_token_accuracy": 0.091129120439291,
|
|
"num_tokens": 1016132.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.3355879306793215,
|
|
"epoch": 0.04662885948330183,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.8796,
|
|
"mean_token_accuracy": 0.09489664137363434,
|
|
"num_tokens": 1024970.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.3572368144989015,
|
|
"epoch": 0.04704893929846671,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.9525,
|
|
"mean_token_accuracy": 0.09272714778780937,
|
|
"num_tokens": 1034335.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.423572063446045,
|
|
"epoch": 0.04746901911363159,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.0075,
|
|
"mean_token_accuracy": 0.09945140630006791,
|
|
"num_tokens": 1043954.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.319319725036621,
|
|
"epoch": 0.04788909892879647,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.9431,
|
|
"mean_token_accuracy": 0.09524357318878174,
|
|
"num_tokens": 1053554.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.376662826538086,
|
|
"epoch": 0.04830917874396135,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.8893,
|
|
"mean_token_accuracy": 0.0956316351890564,
|
|
"num_tokens": 1062008.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.246560859680176,
|
|
"epoch": 0.048729258559126236,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.9602,
|
|
"mean_token_accuracy": 0.09502239599823951,
|
|
"num_tokens": 1070740.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.361734390258789,
|
|
"epoch": 0.04914933837429111,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.9451,
|
|
"mean_token_accuracy": 0.09238593950867653,
|
|
"num_tokens": 1079681.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.294089078903198,
|
|
"epoch": 0.049569418189456,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.8326,
|
|
"mean_token_accuracy": 0.09609337821602822,
|
|
"num_tokens": 1088979.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.192009592056275,
|
|
"epoch": 0.04998949800462088,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.8381,
|
|
"mean_token_accuracy": 0.09695586860179901,
|
|
"num_tokens": 1097870.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.285109043121338,
|
|
"epoch": 0.05040957781978576,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.9361,
|
|
"mean_token_accuracy": 0.09410082027316094,
|
|
"num_tokens": 1107948.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.2816235542297365,
|
|
"epoch": 0.05082965763495064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.856,
|
|
"mean_token_accuracy": 0.09758619442582131,
|
|
"num_tokens": 1117032.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.1946680545806885,
|
|
"epoch": 0.051249737450115525,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.8323,
|
|
"mean_token_accuracy": 0.09758584424853325,
|
|
"num_tokens": 1127834.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.325930643081665,
|
|
"epoch": 0.0516698172652804,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.9314,
|
|
"mean_token_accuracy": 0.10701763778924941,
|
|
"num_tokens": 1137382.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.191529178619385,
|
|
"epoch": 0.052089897080445285,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.7726,
|
|
"mean_token_accuracy": 0.1016211412847042,
|
|
"num_tokens": 1146095.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.197086191177368,
|
|
"epoch": 0.05250997689561017,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.8164,
|
|
"mean_token_accuracy": 0.09977484568953514,
|
|
"num_tokens": 1154981.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.111207914352417,
|
|
"epoch": 0.052930056710775046,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.822,
|
|
"mean_token_accuracy": 0.09889646545052529,
|
|
"num_tokens": 1164939.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.286598014831543,
|
|
"epoch": 0.05335013652593993,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.9423,
|
|
"mean_token_accuracy": 0.0905054323375225,
|
|
"num_tokens": 1174991.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.268424129486084,
|
|
"epoch": 0.05377021634110481,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.9893,
|
|
"mean_token_accuracy": 0.09030458927154542,
|
|
"num_tokens": 1184885.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.25072751045227,
|
|
"epoch": 0.05419029615626969,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.8843,
|
|
"mean_token_accuracy": 0.09418094158172607,
|
|
"num_tokens": 1193637.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.144441413879394,
|
|
"epoch": 0.054610375971434574,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6712,
|
|
"mean_token_accuracy": 0.10373484939336777,
|
|
"num_tokens": 1202188.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.2327552318573,
|
|
"epoch": 0.05503045578659945,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.8046,
|
|
"mean_token_accuracy": 0.09572408124804496,
|
|
"num_tokens": 1210768.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.196833848953247,
|
|
"epoch": 0.055450535601764335,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.8024,
|
|
"mean_token_accuracy": 0.09782998114824296,
|
|
"num_tokens": 1219819.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.211909484863281,
|
|
"epoch": 0.05587061541692922,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.8553,
|
|
"mean_token_accuracy": 0.09061138033866882,
|
|
"num_tokens": 1229703.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.242569494247436,
|
|
"epoch": 0.056290695232094096,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.8929,
|
|
"mean_token_accuracy": 0.09304608702659607,
|
|
"num_tokens": 1238942.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.276552438735962,
|
|
"epoch": 0.05671077504725898,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.9316,
|
|
"mean_token_accuracy": 0.09855509251356125,
|
|
"num_tokens": 1248943.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.130473899841308,
|
|
"epoch": 0.05713085486242386,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.8196,
|
|
"mean_token_accuracy": 0.09641827270388603,
|
|
"num_tokens": 1257761.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.069635629653931,
|
|
"epoch": 0.05755093467758874,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.7531,
|
|
"mean_token_accuracy": 0.09635655134916306,
|
|
"num_tokens": 1267216.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.244167423248291,
|
|
"epoch": 0.057971014492753624,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.8517,
|
|
"mean_token_accuracy": 0.09775793552398682,
|
|
"num_tokens": 1277210.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.151098155975342,
|
|
"epoch": 0.05839109430791851,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.7848,
|
|
"mean_token_accuracy": 0.09209914952516556,
|
|
"num_tokens": 1285310.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.133235788345337,
|
|
"epoch": 0.058811174123083385,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.7884,
|
|
"mean_token_accuracy": 0.0997276745736599,
|
|
"num_tokens": 1294421.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.089715480804443,
|
|
"epoch": 0.05923125393824827,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.6149,
|
|
"mean_token_accuracy": 0.10670206919312478,
|
|
"num_tokens": 1303281.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.096017217636108,
|
|
"epoch": 0.059651333753413145,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.1047137551009655,
|
|
"num_tokens": 1312280.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.01336669921875,
|
|
"epoch": 0.06007141356857803,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.7519,
|
|
"mean_token_accuracy": 0.09830996096134186,
|
|
"num_tokens": 1321243.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.150788021087647,
|
|
"epoch": 0.06049149338374291,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.8411,
|
|
"mean_token_accuracy": 0.0983475923538208,
|
|
"num_tokens": 1330324.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.074830770492554,
|
|
"epoch": 0.06091157319890779,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.6865,
|
|
"mean_token_accuracy": 0.1045832097530365,
|
|
"num_tokens": 1339485.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.180077934265137,
|
|
"epoch": 0.06133165301407267,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.8327,
|
|
"mean_token_accuracy": 0.09178336262702942,
|
|
"num_tokens": 1348640.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.070912313461304,
|
|
"epoch": 0.06175173282923756,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.7313,
|
|
"mean_token_accuracy": 0.10252036228775978,
|
|
"num_tokens": 1357581.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.097622108459473,
|
|
"epoch": 0.062171812644402434,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.7976,
|
|
"mean_token_accuracy": 0.09888288527727127,
|
|
"num_tokens": 1367883.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.072182083129883,
|
|
"epoch": 0.06259189245956731,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.7536,
|
|
"mean_token_accuracy": 0.09760352596640587,
|
|
"num_tokens": 1376936.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.975026559829712,
|
|
"epoch": 0.0630119722747322,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.6653,
|
|
"mean_token_accuracy": 0.10172178596258163,
|
|
"num_tokens": 1386359.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.0470263957977295,
|
|
"epoch": 0.06343205208989708,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.7205,
|
|
"mean_token_accuracy": 0.10334330797195435,
|
|
"num_tokens": 1395223.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.237481212615966,
|
|
"epoch": 0.06385213190506196,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.8854,
|
|
"mean_token_accuracy": 0.09526007026433944,
|
|
"num_tokens": 1404917.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.060393810272217,
|
|
"epoch": 0.06427221172022685,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.7712,
|
|
"mean_token_accuracy": 0.10844952017068862,
|
|
"num_tokens": 1413348.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.010181617736817,
|
|
"epoch": 0.06469229153539173,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.751,
|
|
"mean_token_accuracy": 0.0988110676407814,
|
|
"num_tokens": 1421726.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.068030214309692,
|
|
"epoch": 0.0651123713505566,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.7626,
|
|
"mean_token_accuracy": 0.10152493417263031,
|
|
"num_tokens": 1430686.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.124918842315674,
|
|
"epoch": 0.06553245116572148,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.7567,
|
|
"mean_token_accuracy": 0.10261558443307876,
|
|
"num_tokens": 1439499.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.08576397895813,
|
|
"epoch": 0.06595253098088637,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.7308,
|
|
"mean_token_accuracy": 0.10436978489160538,
|
|
"num_tokens": 1448220.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.918930721282959,
|
|
"epoch": 0.06637261079605125,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.7623,
|
|
"mean_token_accuracy": 0.09306630715727807,
|
|
"num_tokens": 1458217.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.050667333602905,
|
|
"epoch": 0.06679269061121614,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.6615,
|
|
"mean_token_accuracy": 0.10148273557424545,
|
|
"num_tokens": 1467422.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.04574761390686,
|
|
"epoch": 0.06721277042638102,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.6428,
|
|
"mean_token_accuracy": 0.10174536257982254,
|
|
"num_tokens": 1476152.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.920849370956421,
|
|
"epoch": 0.06763285024154589,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.7303,
|
|
"mean_token_accuracy": 0.09813930094242096,
|
|
"num_tokens": 1485248.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.021937704086303,
|
|
"epoch": 0.06805293005671077,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.6965,
|
|
"mean_token_accuracy": 0.10005066767334939,
|
|
"num_tokens": 1494248.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.009239387512207,
|
|
"epoch": 0.06847300987187566,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.7988,
|
|
"mean_token_accuracy": 0.10206111744046212,
|
|
"num_tokens": 1503565.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.153907108306885,
|
|
"epoch": 0.06889308968704054,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.8967,
|
|
"mean_token_accuracy": 0.09253153279423713,
|
|
"num_tokens": 1513227.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.081949377059937,
|
|
"epoch": 0.06931316950220542,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.6785,
|
|
"mean_token_accuracy": 0.10418465957045556,
|
|
"num_tokens": 1522312.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.934855031967163,
|
|
"epoch": 0.0697332493173703,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.6359,
|
|
"mean_token_accuracy": 0.1031254269182682,
|
|
"num_tokens": 1531720.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.970464134216309,
|
|
"epoch": 0.07015332913253518,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.7192,
|
|
"mean_token_accuracy": 0.09493932947516441,
|
|
"num_tokens": 1541238.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.103578281402588,
|
|
"epoch": 0.07057340894770006,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.8114,
|
|
"mean_token_accuracy": 0.0987453043460846,
|
|
"num_tokens": 1550875.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.948361873626709,
|
|
"epoch": 0.07099348876286495,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.7522,
|
|
"mean_token_accuracy": 0.10080962181091309,
|
|
"num_tokens": 1560287.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.981166744232178,
|
|
"epoch": 0.07141356857802983,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.6378,
|
|
"mean_token_accuracy": 0.10372715294361115,
|
|
"num_tokens": 1569043.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.902826881408691,
|
|
"epoch": 0.07183364839319471,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6697,
|
|
"mean_token_accuracy": 0.10197147876024246,
|
|
"num_tokens": 1578112.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.874331331253051,
|
|
"epoch": 0.07225372820835958,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.5725,
|
|
"mean_token_accuracy": 0.1078405149281025,
|
|
"num_tokens": 1586587.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.059461355209351,
|
|
"epoch": 0.07267380802352447,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.7397,
|
|
"mean_token_accuracy": 0.09989926218986511,
|
|
"num_tokens": 1595585.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.951946210861206,
|
|
"epoch": 0.07309388783868935,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.6946,
|
|
"mean_token_accuracy": 0.10353797450661659,
|
|
"num_tokens": 1605355.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.944614362716675,
|
|
"epoch": 0.07351396765385423,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.7108,
|
|
"mean_token_accuracy": 0.09883329644799232,
|
|
"num_tokens": 1613637.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.975859832763672,
|
|
"epoch": 0.07393404746901912,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.6703,
|
|
"mean_token_accuracy": 0.10343916267156601,
|
|
"num_tokens": 1622731.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.003747940063477,
|
|
"epoch": 0.074354127284184,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.6373,
|
|
"mean_token_accuracy": 0.10040950924158096,
|
|
"num_tokens": 1632098.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.826285457611084,
|
|
"epoch": 0.07477420709934887,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6454,
|
|
"mean_token_accuracy": 0.09755287617444992,
|
|
"num_tokens": 1641259.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.0150947093963625,
|
|
"epoch": 0.07519428691451376,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.7262,
|
|
"mean_token_accuracy": 0.09560549557209015,
|
|
"num_tokens": 1651362.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.897852563858033,
|
|
"epoch": 0.07561436672967864,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.6487,
|
|
"mean_token_accuracy": 0.10112505033612251,
|
|
"num_tokens": 1660190.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.90705189704895,
|
|
"epoch": 0.07603444654484352,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.663,
|
|
"mean_token_accuracy": 0.10142350941896439,
|
|
"num_tokens": 1669020.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.973592853546142,
|
|
"epoch": 0.0764545263600084,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.6861,
|
|
"mean_token_accuracy": 0.1048488400876522,
|
|
"num_tokens": 1678158.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.985338020324707,
|
|
"epoch": 0.07687460617517328,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.7084,
|
|
"mean_token_accuracy": 0.10136276260018348,
|
|
"num_tokens": 1687481.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.876794004440308,
|
|
"epoch": 0.07729468599033816,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.6666,
|
|
"mean_token_accuracy": 0.10845559537410736,
|
|
"num_tokens": 1696782.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.932897567749023,
|
|
"epoch": 0.07771476580550304,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.6725,
|
|
"mean_token_accuracy": 0.10497085899114608,
|
|
"num_tokens": 1706153.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.9077776908874515,
|
|
"epoch": 0.07813484562066793,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.6889,
|
|
"mean_token_accuracy": 0.10281107649207115,
|
|
"num_tokens": 1715585.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.106683778762817,
|
|
"epoch": 0.07855492543583281,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.8042,
|
|
"mean_token_accuracy": 0.10099845305085182,
|
|
"num_tokens": 1724857.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.858903789520264,
|
|
"epoch": 0.0789750052509977,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.6175,
|
|
"mean_token_accuracy": 0.10900806412100791,
|
|
"num_tokens": 1733528.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.006282758712769,
|
|
"epoch": 0.07939508506616257,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.7383,
|
|
"mean_token_accuracy": 0.10379872918128967,
|
|
"num_tokens": 1742953.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.92790584564209,
|
|
"epoch": 0.07981516488132745,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.6988,
|
|
"mean_token_accuracy": 0.10636084228754043,
|
|
"num_tokens": 1752155.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.911950254440308,
|
|
"epoch": 0.08023524469649233,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.5687,
|
|
"mean_token_accuracy": 0.10838210806250573,
|
|
"num_tokens": 1760562.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.83457088470459,
|
|
"epoch": 0.08065532451165722,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.5891,
|
|
"mean_token_accuracy": 0.10088410004973411,
|
|
"num_tokens": 1769631.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.914610385894775,
|
|
"epoch": 0.0810754043268221,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.6346,
|
|
"mean_token_accuracy": 0.10217849463224411,
|
|
"num_tokens": 1779080.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.8898755550384525,
|
|
"epoch": 0.08149548414198697,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.6271,
|
|
"mean_token_accuracy": 0.10570115596055984,
|
|
"num_tokens": 1787830.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.751455068588257,
|
|
"epoch": 0.08191556395715185,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.10223312452435493,
|
|
"num_tokens": 1796998.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.8943780899047855,
|
|
"epoch": 0.08233564377231674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.6202,
|
|
"mean_token_accuracy": 0.10597362667322159,
|
|
"num_tokens": 1806194.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.700069093704224,
|
|
"epoch": 0.08275572358748162,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.5072,
|
|
"mean_token_accuracy": 0.10932167768478393,
|
|
"num_tokens": 1815751.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.749313592910767,
|
|
"epoch": 0.0831758034026465,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.5857,
|
|
"mean_token_accuracy": 0.10682184919714928,
|
|
"num_tokens": 1825379.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.845586490631104,
|
|
"epoch": 0.08359588321781139,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5541,
|
|
"mean_token_accuracy": 0.10507402196526527,
|
|
"num_tokens": 1834158.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.844553852081299,
|
|
"epoch": 0.08401596303297626,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.10857650190591812,
|
|
"num_tokens": 1842724.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.795124101638794,
|
|
"epoch": 0.08443604284814114,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499999998724557,
|
|
"loss": 6.5362,
|
|
"mean_token_accuracy": 0.10392995700240135,
|
|
"num_tokens": 1852485.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.765092468261718,
|
|
"epoch": 0.08485612266330603,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999935430703,
|
|
"loss": 6.575,
|
|
"mean_token_accuracy": 0.10723726153373718,
|
|
"num_tokens": 1861303.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.745694637298584,
|
|
"epoch": 0.08527620247847091,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999843758243,
|
|
"loss": 6.5409,
|
|
"mean_token_accuracy": 0.1151320680975914,
|
|
"num_tokens": 1870859.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.8996889114379885,
|
|
"epoch": 0.0856962822936358,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999999712228196,
|
|
"loss": 6.7032,
|
|
"mean_token_accuracy": 0.10041022300720215,
|
|
"num_tokens": 1880295.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.899116802215576,
|
|
"epoch": 0.08611636210880068,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999540840562,
|
|
"loss": 6.6176,
|
|
"mean_token_accuracy": 0.10147540494799615,
|
|
"num_tokens": 1889193.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.797919845581054,
|
|
"epoch": 0.08653644192396555,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999329595345,
|
|
"loss": 6.709,
|
|
"mean_token_accuracy": 0.09875654354691506,
|
|
"num_tokens": 1899437.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.910034608840943,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999078492548,
|
|
"loss": 6.6032,
|
|
"mean_token_accuracy": 0.10777303576469421,
|
|
"num_tokens": 1907882.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.728742361068726,
|
|
"epoch": 0.08737660155429532,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999998787532176,
|
|
"loss": 6.5131,
|
|
"mean_token_accuracy": 0.1080910786986351,
|
|
"num_tokens": 1916872.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.86653618812561,
|
|
"epoch": 0.0877966813694602,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999998456714234,
|
|
"loss": 6.6681,
|
|
"mean_token_accuracy": 0.1074354499578476,
|
|
"num_tokens": 1926636.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.773524904251099,
|
|
"epoch": 0.08821676118462508,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999998086038729,
|
|
"loss": 6.5697,
|
|
"mean_token_accuracy": 0.108617003262043,
|
|
"num_tokens": 1935962.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.809631824493408,
|
|
"epoch": 0.08863684099978995,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999997675505665,
|
|
"loss": 6.5493,
|
|
"mean_token_accuracy": 0.10353536382317544,
|
|
"num_tokens": 1944600.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.8208941459655765,
|
|
"epoch": 0.08905692081495484,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999997225115052,
|
|
"loss": 6.7156,
|
|
"mean_token_accuracy": 0.10389059409499168,
|
|
"num_tokens": 1954234.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.95792784690857,
|
|
"epoch": 0.08947700063011972,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999996734866896,
|
|
"loss": 6.677,
|
|
"mean_token_accuracy": 0.10057736709713935,
|
|
"num_tokens": 1964499.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.662513589859008,
|
|
"epoch": 0.0898970804452846,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999996204761206,
|
|
"loss": 6.3883,
|
|
"mean_token_accuracy": 0.11360553354024887,
|
|
"num_tokens": 1973635.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.745052719116211,
|
|
"epoch": 0.09031716026044949,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999995634797993,
|
|
"loss": 6.5278,
|
|
"mean_token_accuracy": 0.1087425634264946,
|
|
"num_tokens": 1983509.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.769761800765991,
|
|
"epoch": 0.09073724007561437,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999995024977265,
|
|
"loss": 6.5385,
|
|
"mean_token_accuracy": 0.11216638460755349,
|
|
"num_tokens": 1992336.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.855973386764527,
|
|
"epoch": 0.09115731989077924,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999994375299034,
|
|
"loss": 6.5509,
|
|
"mean_token_accuracy": 0.1137130968272686,
|
|
"num_tokens": 2001931.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.615939617156982,
|
|
"epoch": 0.09157739970594413,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499999368576331,
|
|
"loss": 6.4174,
|
|
"mean_token_accuracy": 0.11283476129174233,
|
|
"num_tokens": 2010935.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.7152961730957035,
|
|
"epoch": 0.09199747952110901,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999992956370109,
|
|
"loss": 6.4684,
|
|
"mean_token_accuracy": 0.11342488676309585,
|
|
"num_tokens": 2020587.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.688837385177612,
|
|
"epoch": 0.0924175593362739,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499999218711944,
|
|
"loss": 6.5046,
|
|
"mean_token_accuracy": 0.10743609666824341,
|
|
"num_tokens": 2029743.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.771305274963379,
|
|
"epoch": 0.09283763915143878,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999991378011317,
|
|
"loss": 6.5286,
|
|
"mean_token_accuracy": 0.11453117504715919,
|
|
"num_tokens": 2038468.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.67022180557251,
|
|
"epoch": 0.09325771896660366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999990529045757,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.11554965823888778,
|
|
"num_tokens": 2047456.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.870058679580689,
|
|
"epoch": 0.09367779878176853,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999989640222771,
|
|
"loss": 6.7458,
|
|
"mean_token_accuracy": 0.09942527562379837,
|
|
"num_tokens": 2056691.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.829685544967651,
|
|
"epoch": 0.09409787859693342,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499998871154238,
|
|
"loss": 6.5487,
|
|
"mean_token_accuracy": 0.10888865366578102,
|
|
"num_tokens": 2066068.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.725253868103027,
|
|
"epoch": 0.0945179584120983,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999987743004597,
|
|
"loss": 6.4837,
|
|
"mean_token_accuracy": 0.11379996240139008,
|
|
"num_tokens": 2075113.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.7777934074401855,
|
|
"epoch": 0.09493803822726318,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999986734609438,
|
|
"loss": 6.6044,
|
|
"mean_token_accuracy": 0.11070828661322593,
|
|
"num_tokens": 2084557.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.817347526550293,
|
|
"epoch": 0.09535811804242807,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999985686356923,
|
|
"loss": 6.497,
|
|
"mean_token_accuracy": 0.10584703534841537,
|
|
"num_tokens": 2093424.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.7462608337402346,
|
|
"epoch": 0.09577819785759294,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499998459824707,
|
|
"loss": 6.6329,
|
|
"mean_token_accuracy": 0.10303654298186302,
|
|
"num_tokens": 2103066.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.799277830123901,
|
|
"epoch": 0.09619827767275782,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049999834702799,
|
|
"loss": 6.5085,
|
|
"mean_token_accuracy": 0.11131441742181777,
|
|
"num_tokens": 2112447.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.711055421829224,
|
|
"epoch": 0.0966183574879227,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999982302455431,
|
|
"loss": 6.52,
|
|
"mean_token_accuracy": 0.11281892731785774,
|
|
"num_tokens": 2121949.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.780323314666748,
|
|
"epoch": 0.09703843730308759,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999981094773683,
|
|
"loss": 6.4157,
|
|
"mean_token_accuracy": 0.1144998162984848,
|
|
"num_tokens": 2130464.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.697625207901001,
|
|
"epoch": 0.09745851711825247,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499997984723468,
|
|
"loss": 6.5921,
|
|
"mean_token_accuracy": 0.1068018026649952,
|
|
"num_tokens": 2139577.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.569090557098389,
|
|
"epoch": 0.09787859693341736,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999978559838441,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.11300956755876541,
|
|
"num_tokens": 2147919.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.716167974472046,
|
|
"epoch": 0.09829867674858223,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999977232584991,
|
|
"loss": 6.4791,
|
|
"mean_token_accuracy": 0.11262017637491226,
|
|
"num_tokens": 2156936.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.6336616516113285,
|
|
"epoch": 0.09871875656374711,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999975865474354,
|
|
"loss": 6.5492,
|
|
"mean_token_accuracy": 0.10994603037834168,
|
|
"num_tokens": 2165362.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.719806575775147,
|
|
"epoch": 0.099138836378912,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999974458506551,
|
|
"loss": 6.4705,
|
|
"mean_token_accuracy": 0.11214353889226913,
|
|
"num_tokens": 2173665.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.786266422271728,
|
|
"epoch": 0.09955891619407688,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499997301168161,
|
|
"loss": 6.4531,
|
|
"mean_token_accuracy": 0.11377902403473854,
|
|
"num_tokens": 2182222.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.670177459716797,
|
|
"epoch": 0.09997899600924176,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999971524999556,
|
|
"loss": 6.528,
|
|
"mean_token_accuracy": 0.11228533461689949,
|
|
"num_tokens": 2192358.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.779563045501709,
|
|
"epoch": 0.10039907582440663,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999969998460414,
|
|
"loss": 6.5039,
|
|
"mean_token_accuracy": 0.10956505164504052,
|
|
"num_tokens": 2201889.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.6560157299041744,
|
|
"epoch": 0.10081915563957151,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999968432064213,
|
|
"loss": 6.5232,
|
|
"mean_token_accuracy": 0.11500915959477424,
|
|
"num_tokens": 2211810.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.652071762084961,
|
|
"epoch": 0.1012392354547364,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999966825810979,
|
|
"loss": 6.4474,
|
|
"mean_token_accuracy": 0.11259665861725807,
|
|
"num_tokens": 2221123.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.634405040740967,
|
|
"epoch": 0.10165931526990128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999965179700742,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.1181789293885231,
|
|
"num_tokens": 2230129.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.625933122634888,
|
|
"epoch": 0.10207939508506617,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499996349373353,
|
|
"loss": 6.4624,
|
|
"mean_token_accuracy": 0.11246607527136802,
|
|
"num_tokens": 2239929.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.709180927276611,
|
|
"epoch": 0.10249947490023105,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999961767909374,
|
|
"loss": 6.4292,
|
|
"mean_token_accuracy": 0.11479318514466286,
|
|
"num_tokens": 2248078.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.59263162612915,
|
|
"epoch": 0.10291955471539592,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999960002228303,
|
|
"loss": 6.5262,
|
|
"mean_token_accuracy": 0.11000767946243287,
|
|
"num_tokens": 2256975.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.708470964431763,
|
|
"epoch": 0.1033396345305608,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999958196690349,
|
|
"loss": 6.3792,
|
|
"mean_token_accuracy": 0.11624118462204933,
|
|
"num_tokens": 2265797.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.645881128311157,
|
|
"epoch": 0.10375971434572569,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999956351295545,
|
|
"loss": 6.4736,
|
|
"mean_token_accuracy": 0.1176276110112667,
|
|
"num_tokens": 2274099.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.599815797805786,
|
|
"epoch": 0.10417979416089057,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999954466043922,
|
|
"loss": 6.3853,
|
|
"mean_token_accuracy": 0.11810432821512222,
|
|
"num_tokens": 2282360.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.57668776512146,
|
|
"epoch": 0.10459987397605545,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999952540935514,
|
|
"loss": 6.4891,
|
|
"mean_token_accuracy": 0.11048517748713493,
|
|
"num_tokens": 2292714.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.675060033798218,
|
|
"epoch": 0.10501995379122034,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999950575970356,
|
|
"loss": 6.4361,
|
|
"mean_token_accuracy": 0.11576245203614235,
|
|
"num_tokens": 2301633.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.642887592315674,
|
|
"epoch": 0.10544003360638521,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999948571148482,
|
|
"loss": 6.3931,
|
|
"mean_token_accuracy": 0.12049147412180901,
|
|
"num_tokens": 2310067.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.610925579071045,
|
|
"epoch": 0.10586011342155009,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999946526469927,
|
|
"loss": 6.4927,
|
|
"mean_token_accuracy": 0.11412879601120948,
|
|
"num_tokens": 2320090.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.649963521957398,
|
|
"epoch": 0.10628019323671498,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999944441934728,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.11852803751826287,
|
|
"num_tokens": 2329255.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.678138732910156,
|
|
"epoch": 0.10670027305187986,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999942317542922,
|
|
"loss": 6.5261,
|
|
"mean_token_accuracy": 0.11407028958201408,
|
|
"num_tokens": 2339535.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.635104560852051,
|
|
"epoch": 0.10712035286704474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999940153294546,
|
|
"loss": 6.425,
|
|
"mean_token_accuracy": 0.11798783987760544,
|
|
"num_tokens": 2348948.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.629437446594238,
|
|
"epoch": 0.10754043268220961,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499993794918964,
|
|
"loss": 6.4518,
|
|
"mean_token_accuracy": 0.10851866900920867,
|
|
"num_tokens": 2359141.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.612447357177734,
|
|
"epoch": 0.1079605124973745,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999935705228241,
|
|
"loss": 6.5007,
|
|
"mean_token_accuracy": 0.10988411605358124,
|
|
"num_tokens": 2368906.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.720192527770996,
|
|
"epoch": 0.10838059231253938,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999933421410389,
|
|
"loss": 6.4756,
|
|
"mean_token_accuracy": 0.11632761880755424,
|
|
"num_tokens": 2377029.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.682251882553101,
|
|
"epoch": 0.10880067212770426,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999931097736125,
|
|
"loss": 6.5226,
|
|
"mean_token_accuracy": 0.10841714516282082,
|
|
"num_tokens": 2387088.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.616416501998901,
|
|
"epoch": 0.10922075194286915,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999928734205492,
|
|
"loss": 6.4358,
|
|
"mean_token_accuracy": 0.11085559725761414,
|
|
"num_tokens": 2395596.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.630216932296753,
|
|
"epoch": 0.10964083175803403,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999926330818528,
|
|
"loss": 6.4278,
|
|
"mean_token_accuracy": 0.11868382543325424,
|
|
"num_tokens": 2404506.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.615355587005615,
|
|
"epoch": 0.1100609115731989,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999923887575278,
|
|
"loss": 6.4742,
|
|
"mean_token_accuracy": 0.11464583277702331,
|
|
"num_tokens": 2414342.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.68165545463562,
|
|
"epoch": 0.11048099138836379,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999921404475785,
|
|
"loss": 6.4271,
|
|
"mean_token_accuracy": 0.11960532069206238,
|
|
"num_tokens": 2423076.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.567938899993896,
|
|
"epoch": 0.11090107120352867,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999918881520093,
|
|
"loss": 6.3809,
|
|
"mean_token_accuracy": 0.1204459622502327,
|
|
"num_tokens": 2432492.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.610611057281494,
|
|
"epoch": 0.11132115101869355,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999916318708246,
|
|
"loss": 6.3447,
|
|
"mean_token_accuracy": 0.1213211365044117,
|
|
"num_tokens": 2441916.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.550094270706177,
|
|
"epoch": 0.11174123083385844,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999913716040291,
|
|
"loss": 6.4,
|
|
"mean_token_accuracy": 0.11803905665874481,
|
|
"num_tokens": 2450932.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.5825268745422365,
|
|
"epoch": 0.11216131064902331,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999911073516272,
|
|
"loss": 6.4156,
|
|
"mean_token_accuracy": 0.11501810997724533,
|
|
"num_tokens": 2460058.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.541036558151245,
|
|
"epoch": 0.11258139046418819,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999908391136237,
|
|
"loss": 6.3486,
|
|
"mean_token_accuracy": 0.11862518936395645,
|
|
"num_tokens": 2469607.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.54659481048584,
|
|
"epoch": 0.11300147027935308,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999905668900234,
|
|
"loss": 6.4037,
|
|
"mean_token_accuracy": 0.11429757624864578,
|
|
"num_tokens": 2478345.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.665723133087158,
|
|
"epoch": 0.11342155009451796,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499990290680831,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.11939993128180504,
|
|
"num_tokens": 2486662.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.539735174179077,
|
|
"epoch": 0.11384162990968284,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999900104860516,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.11450904607772827,
|
|
"num_tokens": 2495392.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.640576314926148,
|
|
"epoch": 0.11426170972484773,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999897263056898,
|
|
"loss": 6.4824,
|
|
"mean_token_accuracy": 0.11427311152219773,
|
|
"num_tokens": 2505254.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.6059410572052,
|
|
"epoch": 0.1146817895400126,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499989438139751,
|
|
"loss": 6.2902,
|
|
"mean_token_accuracy": 0.12163057401776314,
|
|
"num_tokens": 2514096.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.572102785110474,
|
|
"epoch": 0.11510186935517748,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999891459882401,
|
|
"loss": 6.3036,
|
|
"mean_token_accuracy": 0.12106614261865616,
|
|
"num_tokens": 2523635.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.518535518646241,
|
|
"epoch": 0.11552194917034236,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999888498511624,
|
|
"loss": 6.3872,
|
|
"mean_token_accuracy": 0.117999816685915,
|
|
"num_tokens": 2532528.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.522701168060303,
|
|
"epoch": 0.11594202898550725,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999885497285229,
|
|
"loss": 6.3026,
|
|
"mean_token_accuracy": 0.11809839084744453,
|
|
"num_tokens": 2541893.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.516852188110351,
|
|
"epoch": 0.11636210880067213,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999882456203273,
|
|
"loss": 6.3627,
|
|
"mean_token_accuracy": 0.11867272853851318,
|
|
"num_tokens": 2551551.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.592957019805908,
|
|
"epoch": 0.11678218861583702,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999879375265806,
|
|
"loss": 6.314,
|
|
"mean_token_accuracy": 0.1192450650036335,
|
|
"num_tokens": 2560183.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.526823472976685,
|
|
"epoch": 0.11720226843100189,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999876254472886,
|
|
"loss": 6.2065,
|
|
"mean_token_accuracy": 0.127345572412014,
|
|
"num_tokens": 2568697.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.488171815872192,
|
|
"epoch": 0.11762234824616677,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999873093824565,
|
|
"loss": 6.4136,
|
|
"mean_token_accuracy": 0.1172497920691967,
|
|
"num_tokens": 2578151.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.697162342071533,
|
|
"epoch": 0.11804242806133165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999869893320902,
|
|
"loss": 6.5415,
|
|
"mean_token_accuracy": 0.11695929765701293,
|
|
"num_tokens": 2585901.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.558137512207031,
|
|
"epoch": 0.11846250787649654,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999866652961952,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.11195311546325684,
|
|
"num_tokens": 2595655.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.547592639923096,
|
|
"epoch": 0.11888258769166142,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999863372747773,
|
|
"loss": 6.3241,
|
|
"mean_token_accuracy": 0.1137452982366085,
|
|
"num_tokens": 2604949.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.549184036254883,
|
|
"epoch": 0.11930266750682629,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999860052678423,
|
|
"loss": 6.3987,
|
|
"mean_token_accuracy": 0.12182095795869827,
|
|
"num_tokens": 2614260.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.533220100402832,
|
|
"epoch": 0.11972274732199117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999856692753959,
|
|
"loss": 6.3846,
|
|
"mean_token_accuracy": 0.11606933474540711,
|
|
"num_tokens": 2623740.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.56026554107666,
|
|
"epoch": 0.12014282713715606,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999853292974444,
|
|
"loss": 6.2829,
|
|
"mean_token_accuracy": 0.1191012591123581,
|
|
"num_tokens": 2631998.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.436700010299683,
|
|
"epoch": 0.12056290695232094,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999849853339936,
|
|
"loss": 6.4441,
|
|
"mean_token_accuracy": 0.12089451104402542,
|
|
"num_tokens": 2641169.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.6503981590271,
|
|
"epoch": 0.12098298676748583,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999846373850497,
|
|
"loss": 6.2726,
|
|
"mean_token_accuracy": 0.12328374907374381,
|
|
"num_tokens": 2650576.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.504758834838867,
|
|
"epoch": 0.12140306658265071,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999842854506186,
|
|
"loss": 6.3597,
|
|
"mean_token_accuracy": 0.11508475914597512,
|
|
"num_tokens": 2660817.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.454709720611572,
|
|
"epoch": 0.12182314639781558,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999839295307069,
|
|
"loss": 6.317,
|
|
"mean_token_accuracy": 0.11818674132227898,
|
|
"num_tokens": 2669338.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.5724732875823975,
|
|
"epoch": 0.12224322621298046,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999835696253206,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.11763316094875335,
|
|
"num_tokens": 2679108.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.542471504211425,
|
|
"epoch": 0.12266330602814535,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999832057344664,
|
|
"loss": 6.3312,
|
|
"mean_token_accuracy": 0.11857884675264359,
|
|
"num_tokens": 2688126.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.3690132141113285,
|
|
"epoch": 0.12308338584331023,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999828378581504,
|
|
"loss": 6.2827,
|
|
"mean_token_accuracy": 0.12631092369556426,
|
|
"num_tokens": 2697245.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.5668089389801025,
|
|
"epoch": 0.12350346565847511,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999824659963793,
|
|
"loss": 6.3543,
|
|
"mean_token_accuracy": 0.12048940360546112,
|
|
"num_tokens": 2705934.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.516648006439209,
|
|
"epoch": 0.12392354547364,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999820901491598,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.12523386031389236,
|
|
"num_tokens": 2714367.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.416815328598022,
|
|
"epoch": 0.12434362528880487,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999817103164983,
|
|
"loss": 6.3117,
|
|
"mean_token_accuracy": 0.12113343179225922,
|
|
"num_tokens": 2724366.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.518594264984131,
|
|
"epoch": 0.12476370510396975,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999813264984017,
|
|
"loss": 6.3262,
|
|
"mean_token_accuracy": 0.11913523152470588,
|
|
"num_tokens": 2733980.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.520108652114868,
|
|
"epoch": 0.12518378491913462,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999809386948767,
|
|
"loss": 6.3232,
|
|
"mean_token_accuracy": 0.11875561475753785,
|
|
"num_tokens": 2744013.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.4508843421936035,
|
|
"epoch": 0.12560386473429952,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999805469059302,
|
|
"loss": 6.3917,
|
|
"mean_token_accuracy": 0.1202739343047142,
|
|
"num_tokens": 2753385.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.467165565490722,
|
|
"epoch": 0.1260239445494644,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999801511315693,
|
|
"loss": 6.2443,
|
|
"mean_token_accuracy": 0.11950960382819176,
|
|
"num_tokens": 2762875.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.561000490188599,
|
|
"epoch": 0.1264440243646293,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999797513718007,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.12554540634155273,
|
|
"num_tokens": 2772182.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.398244476318359,
|
|
"epoch": 0.12686410417979416,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999793476266317,
|
|
"loss": 6.2652,
|
|
"mean_token_accuracy": 0.12494927272200584,
|
|
"num_tokens": 2780814.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.759689664840698,
|
|
"epoch": 0.12728418399495905,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999789398960695,
|
|
"loss": 6.5371,
|
|
"mean_token_accuracy": 0.120218076556921,
|
|
"num_tokens": 2791104.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.380699729919433,
|
|
"epoch": 0.12770426381012392,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999785281801212,
|
|
"loss": 6.2392,
|
|
"mean_token_accuracy": 0.12141881808638573,
|
|
"num_tokens": 2800081.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.502162122726441,
|
|
"epoch": 0.1281243436252888,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499978112478794,
|
|
"loss": 6.3645,
|
|
"mean_token_accuracy": 0.11820052862167359,
|
|
"num_tokens": 2809096.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.559705686569214,
|
|
"epoch": 0.1285444234404537,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999776927920955,
|
|
"loss": 6.3324,
|
|
"mean_token_accuracy": 0.12376131415367127,
|
|
"num_tokens": 2818857.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.478033876419067,
|
|
"epoch": 0.12896450325561856,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499977269120033,
|
|
"loss": 6.3924,
|
|
"mean_token_accuracy": 0.11640017554163933,
|
|
"num_tokens": 2829332.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.471277475357056,
|
|
"epoch": 0.12938458307078346,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499976841462614,
|
|
"loss": 6.3118,
|
|
"mean_token_accuracy": 0.11578154116868973,
|
|
"num_tokens": 2839193.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.515983152389526,
|
|
"epoch": 0.12980466288594833,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499976409819846,
|
|
"loss": 6.3126,
|
|
"mean_token_accuracy": 0.1165178470313549,
|
|
"num_tokens": 2848535.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.329218864440918,
|
|
"epoch": 0.1302247427011132,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999759741917369,
|
|
"loss": 6.2119,
|
|
"mean_token_accuracy": 0.12768493369221687,
|
|
"num_tokens": 2858090.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.4847986698150635,
|
|
"epoch": 0.1306448225162781,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999755345782941,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.1186487466096878,
|
|
"num_tokens": 2866984.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.419411611557007,
|
|
"epoch": 0.13106490233144297,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999750909795256,
|
|
"loss": 6.1757,
|
|
"mean_token_accuracy": 0.1280258044600487,
|
|
"num_tokens": 2876550.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.461032104492188,
|
|
"epoch": 0.13148498214660786,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999746433954394,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.1213872842490673,
|
|
"num_tokens": 2885782.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.447916793823242,
|
|
"epoch": 0.13190506196177273,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499974191826043,
|
|
"loss": 6.2448,
|
|
"mean_token_accuracy": 0.13687582612037658,
|
|
"num_tokens": 2894807.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.439778518676758,
|
|
"epoch": 0.1323251417769376,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999737362713448,
|
|
"loss": 6.2925,
|
|
"mean_token_accuracy": 0.1238982230424881,
|
|
"num_tokens": 2904076.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.471430492401123,
|
|
"epoch": 0.1327452215921025,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999732767313527,
|
|
"loss": 6.2033,
|
|
"mean_token_accuracy": 0.1205870471894741,
|
|
"num_tokens": 2913761.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.509069633483887,
|
|
"epoch": 0.13316530140726737,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999728132060746,
|
|
"loss": 6.4228,
|
|
"mean_token_accuracy": 0.12286271527409554,
|
|
"num_tokens": 2922848.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.5165454864501955,
|
|
"epoch": 0.13358538122243227,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999723456955192,
|
|
"loss": 6.3079,
|
|
"mean_token_accuracy": 0.11906806230545045,
|
|
"num_tokens": 2932718.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.353040504455566,
|
|
"epoch": 0.13400546103759714,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999718741996945,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.12362491562962533,
|
|
"num_tokens": 2942686.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.480581188201905,
|
|
"epoch": 0.13442554085276204,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499971398718609,
|
|
"loss": 6.2304,
|
|
"mean_token_accuracy": 0.12233746945858001,
|
|
"num_tokens": 2952096.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.41249566078186,
|
|
"epoch": 0.1348456206679269,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999709192522708,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.12512291446328164,
|
|
"num_tokens": 2960660.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.536613845825196,
|
|
"epoch": 0.13526570048309178,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999704358006887,
|
|
"loss": 6.3118,
|
|
"mean_token_accuracy": 0.12129077091813087,
|
|
"num_tokens": 2969834.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.4085368633270265,
|
|
"epoch": 0.13568578029825668,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999699483638712,
|
|
"loss": 6.2906,
|
|
"mean_token_accuracy": 0.12232841104269028,
|
|
"num_tokens": 2979023.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.476312971115112,
|
|
"epoch": 0.13610586011342155,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999694569418269,
|
|
"loss": 6.2964,
|
|
"mean_token_accuracy": 0.12233099341392517,
|
|
"num_tokens": 2988083.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.359239149093628,
|
|
"epoch": 0.13652593992858644,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999689615345645,
|
|
"loss": 6.2196,
|
|
"mean_token_accuracy": 0.12490532472729683,
|
|
"num_tokens": 2997240.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.505274820327759,
|
|
"epoch": 0.1369460197437513,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999684621420928,
|
|
"loss": 6.2805,
|
|
"mean_token_accuracy": 0.12174654453992843,
|
|
"num_tokens": 3007077.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.501539659500122,
|
|
"epoch": 0.13736609955891618,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999679587644205,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.11869422942399979,
|
|
"num_tokens": 3015821.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.434766483306885,
|
|
"epoch": 0.13778617937408108,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999674514015568,
|
|
"loss": 6.2508,
|
|
"mean_token_accuracy": 0.1246812529861927,
|
|
"num_tokens": 3025858.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.406217813491821,
|
|
"epoch": 0.13820625918924595,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999669400535105,
|
|
"loss": 6.2132,
|
|
"mean_token_accuracy": 0.12023203670978547,
|
|
"num_tokens": 3035537.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.359542560577393,
|
|
"epoch": 0.13862633900441085,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999664247202907,
|
|
"loss": 6.152,
|
|
"mean_token_accuracy": 0.12406394928693772,
|
|
"num_tokens": 3044204.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.404636430740356,
|
|
"epoch": 0.13904641881957572,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999659054019066,
|
|
"loss": 6.2994,
|
|
"mean_token_accuracy": 0.12448503151535988,
|
|
"num_tokens": 3053111.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.443476963043213,
|
|
"epoch": 0.1394664986347406,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999653820983673,
|
|
"loss": 6.2201,
|
|
"mean_token_accuracy": 0.12843194082379342,
|
|
"num_tokens": 3062456.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.356498098373413,
|
|
"epoch": 0.13988657844990549,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499964854809682,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.12453076243400574,
|
|
"num_tokens": 3071132.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.388091611862182,
|
|
"epoch": 0.14030665826507036,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999643235358602,
|
|
"loss": 6.2078,
|
|
"mean_token_accuracy": 0.12833356559276582,
|
|
"num_tokens": 3080892.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.392906522750854,
|
|
"epoch": 0.14072673808023525,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999637882769112,
|
|
"loss": 6.1429,
|
|
"mean_token_accuracy": 0.12803655937314035,
|
|
"num_tokens": 3089874.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.369514799118042,
|
|
"epoch": 0.14114681789540012,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999632490328447,
|
|
"loss": 6.2814,
|
|
"mean_token_accuracy": 0.12487674206495285,
|
|
"num_tokens": 3099535.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.432224130630493,
|
|
"epoch": 0.14156689771056502,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999627058036699,
|
|
"loss": 6.24,
|
|
"mean_token_accuracy": 0.12075779214501381,
|
|
"num_tokens": 3108772.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.430401134490967,
|
|
"epoch": 0.1419869775257299,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999621585893966,
|
|
"loss": 6.2696,
|
|
"mean_token_accuracy": 0.11704754754900933,
|
|
"num_tokens": 3118333.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.450057506561279,
|
|
"epoch": 0.14240705734089476,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999616073900346,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.12180939391255378,
|
|
"num_tokens": 3127356.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.412153673171997,
|
|
"epoch": 0.14282713715605966,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999610522055935,
|
|
"loss": 6.2662,
|
|
"mean_token_accuracy": 0.1200573742389679,
|
|
"num_tokens": 3136859.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.451931762695312,
|
|
"epoch": 0.14324721697122453,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999604930360832,
|
|
"loss": 6.2945,
|
|
"mean_token_accuracy": 0.12161469012498856,
|
|
"num_tokens": 3146607.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.3816108226776125,
|
|
"epoch": 0.14366729678638943,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999599298815136,
|
|
"loss": 6.2364,
|
|
"mean_token_accuracy": 0.12764545828104018,
|
|
"num_tokens": 3156327.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.309280204772949,
|
|
"epoch": 0.1440873766015543,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004999593627418947,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.13247063681483268,
|
|
"num_tokens": 3165559.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.405248212814331,
|
|
"epoch": 0.14450745641671917,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999587916172365,
|
|
"loss": 6.2704,
|
|
"mean_token_accuracy": 0.1183898076415062,
|
|
"num_tokens": 3173850.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.435620069503784,
|
|
"epoch": 0.14492753623188406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999582165075492,
|
|
"loss": 6.22,
|
|
"mean_token_accuracy": 0.11956866905093193,
|
|
"num_tokens": 3182838.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.2884269714355465,
|
|
"epoch": 0.14534761604704893,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999576374128429,
|
|
"loss": 6.202,
|
|
"mean_token_accuracy": 0.1219302274286747,
|
|
"num_tokens": 3191692.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.500776195526123,
|
|
"epoch": 0.14576769586221383,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999570543331279,
|
|
"loss": 6.226,
|
|
"mean_token_accuracy": 0.1263854332268238,
|
|
"num_tokens": 3200069.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.411444854736328,
|
|
"epoch": 0.1461877756773787,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999564672684145,
|
|
"loss": 6.3228,
|
|
"mean_token_accuracy": 0.12090336456894875,
|
|
"num_tokens": 3209653.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.448664712905884,
|
|
"epoch": 0.14660785549254357,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999558762187131,
|
|
"loss": 6.1938,
|
|
"mean_token_accuracy": 0.12701231315732003,
|
|
"num_tokens": 3218313.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.32896614074707,
|
|
"epoch": 0.14702793530770847,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999552811840342,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.12769370079040526,
|
|
"num_tokens": 3227525.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.335414171218872,
|
|
"epoch": 0.14744801512287334,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999546821643884,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.12636618986725806,
|
|
"num_tokens": 3237022.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.317769384384155,
|
|
"epoch": 0.14786809493803824,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999540791597861,
|
|
"loss": 6.1464,
|
|
"mean_token_accuracy": 0.12537204548716546,
|
|
"num_tokens": 3246605.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.258312511444092,
|
|
"epoch": 0.1482881747532031,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999534721702383,
|
|
"loss": 6.0956,
|
|
"mean_token_accuracy": 0.13141294568777084,
|
|
"num_tokens": 3255587.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.364277791976929,
|
|
"epoch": 0.148708254568368,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999528611957553,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.1267327442765236,
|
|
"num_tokens": 3265669.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.433037424087525,
|
|
"epoch": 0.14912833438353287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999522462363485,
|
|
"loss": 6.1795,
|
|
"mean_token_accuracy": 0.12822128161787988,
|
|
"num_tokens": 3275013.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.372742748260498,
|
|
"epoch": 0.14954841419869774,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999516272920283,
|
|
"loss": 6.2775,
|
|
"mean_token_accuracy": 0.12774404734373093,
|
|
"num_tokens": 3284723.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.256136322021485,
|
|
"epoch": 0.14996849401386264,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499951004362806,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.13196263536810876,
|
|
"num_tokens": 3293860.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.278848552703858,
|
|
"epoch": 0.1503885738290275,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999503774486924,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.13007338494062423,
|
|
"num_tokens": 3303158.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.253765487670899,
|
|
"epoch": 0.1508086536441924,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999497465496987,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.1231241799890995,
|
|
"num_tokens": 3313068.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.319281959533692,
|
|
"epoch": 0.15122873345935728,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499949111665836,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.12510209009051323,
|
|
"num_tokens": 3321885.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.368197298049926,
|
|
"epoch": 0.15164881327452215,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999484727971158,
|
|
"loss": 6.1707,
|
|
"mean_token_accuracy": 0.12798358947038652,
|
|
"num_tokens": 3330924.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.339307403564453,
|
|
"epoch": 0.15206889308968705,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499947829943549,
|
|
"loss": 6.1964,
|
|
"mean_token_accuracy": 0.12618306949734687,
|
|
"num_tokens": 3340070.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.394219160079956,
|
|
"epoch": 0.15248897290485192,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999471831051474,
|
|
"loss": 6.1922,
|
|
"mean_token_accuracy": 0.13684661015868188,
|
|
"num_tokens": 3349870.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.330759143829345,
|
|
"epoch": 0.1529090527200168,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999465322819222,
|
|
"loss": 6.2371,
|
|
"mean_token_accuracy": 0.12111249193549156,
|
|
"num_tokens": 3359573.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.372816276550293,
|
|
"epoch": 0.15332913253518168,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999458774738851,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.13470285311341285,
|
|
"num_tokens": 3368577.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.352361059188842,
|
|
"epoch": 0.15374921235034655,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999452186810476,
|
|
"loss": 6.1469,
|
|
"mean_token_accuracy": 0.13113251850008964,
|
|
"num_tokens": 3377801.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.3680521011352536,
|
|
"epoch": 0.15416929216551145,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999445559034214,
|
|
"loss": 6.1995,
|
|
"mean_token_accuracy": 0.12895982414484025,
|
|
"num_tokens": 3386666.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.443807363510132,
|
|
"epoch": 0.15458937198067632,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999438891410181,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.12429568618535995,
|
|
"num_tokens": 3396086.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.371559190750122,
|
|
"epoch": 0.15500945179584122,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999432183938496,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.1258139818906784,
|
|
"num_tokens": 3404894.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.40411787033081,
|
|
"epoch": 0.1554295316110061,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999425436619279,
|
|
"loss": 6.2301,
|
|
"mean_token_accuracy": 0.1250107169151306,
|
|
"num_tokens": 3414172.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.4263053894042965,
|
|
"epoch": 0.15584961142617096,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499941864945265,
|
|
"loss": 6.2069,
|
|
"mean_token_accuracy": 0.12341500893235206,
|
|
"num_tokens": 3423409.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.2579625129699705,
|
|
"epoch": 0.15626969124133586,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999411822438726,
|
|
"loss": 6.1554,
|
|
"mean_token_accuracy": 0.12717969343066216,
|
|
"num_tokens": 3433047.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.4037513256073,
|
|
"epoch": 0.15668977105650073,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499940495557763,
|
|
"loss": 6.1468,
|
|
"mean_token_accuracy": 0.12783457711338997,
|
|
"num_tokens": 3442490.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.303406810760498,
|
|
"epoch": 0.15710985087166562,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999398048869485,
|
|
"loss": 6.2099,
|
|
"mean_token_accuracy": 0.129954195022583,
|
|
"num_tokens": 3451804.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.385490417480469,
|
|
"epoch": 0.1575299306868305,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499939110231441,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.1304432988166809,
|
|
"num_tokens": 3461481.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.364220190048218,
|
|
"epoch": 0.1579500105019954,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999384115912531,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.13135363310575485,
|
|
"num_tokens": 3471798.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.247316694259643,
|
|
"epoch": 0.15837009031716026,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499937708966397,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.12637364491820335,
|
|
"num_tokens": 3481386.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.332306051254273,
|
|
"epoch": 0.15879017013232513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999370023568853,
|
|
"loss": 6.127,
|
|
"mean_token_accuracy": 0.1316571466624737,
|
|
"num_tokens": 3489981.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.299954462051391,
|
|
"epoch": 0.15921024994749003,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999362917627304,
|
|
"loss": 6.1227,
|
|
"mean_token_accuracy": 0.1305247150361538,
|
|
"num_tokens": 3498551.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.316105461120605,
|
|
"epoch": 0.1596303297626549,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999355771839448,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.12954429015517235,
|
|
"num_tokens": 3507921.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.470440483093261,
|
|
"epoch": 0.1600504095778198,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999348586205414,
|
|
"loss": 6.2729,
|
|
"mean_token_accuracy": 0.13220328316092492,
|
|
"num_tokens": 3517570.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.38808388710022,
|
|
"epoch": 0.16047048939298467,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999341360725327,
|
|
"loss": 6.2438,
|
|
"mean_token_accuracy": 0.123927091807127,
|
|
"num_tokens": 3526774.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.285849714279175,
|
|
"epoch": 0.16089056920814954,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999334095399317,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.1361298866569996,
|
|
"num_tokens": 3535319.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.249746656417846,
|
|
"epoch": 0.16131064902331443,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999326790227512,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.1271871216595173,
|
|
"num_tokens": 3544468.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.217294788360595,
|
|
"epoch": 0.1617307288384793,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999319445210041,
|
|
"loss": 6.0261,
|
|
"mean_token_accuracy": 0.1361843690276146,
|
|
"num_tokens": 3553529.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.290815734863282,
|
|
"epoch": 0.1621508086536442,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999312060347034,
|
|
"loss": 6.1011,
|
|
"mean_token_accuracy": 0.13233864828944206,
|
|
"num_tokens": 3563053.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.224975728988648,
|
|
"epoch": 0.16257088846880907,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999304635638621,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.1342104844748974,
|
|
"num_tokens": 3571877.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.233099460601807,
|
|
"epoch": 0.16299096828397394,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999297171084935,
|
|
"loss": 6.091,
|
|
"mean_token_accuracy": 0.13373700231313707,
|
|
"num_tokens": 3581496.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.324843549728394,
|
|
"epoch": 0.16341104809913884,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999289666686109,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.1308230109512806,
|
|
"num_tokens": 3590752.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.129473495483398,
|
|
"epoch": 0.1638311279143037,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999282122442274,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.1328013814985752,
|
|
"num_tokens": 3599885.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.387533235549927,
|
|
"epoch": 0.1642512077294686,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999274538353564,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.12293331325054169,
|
|
"num_tokens": 3610039.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.2677867889404295,
|
|
"epoch": 0.16467128754463348,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999266914420114,
|
|
"loss": 6.1123,
|
|
"mean_token_accuracy": 0.12491545528173446,
|
|
"num_tokens": 3619954.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.291842746734619,
|
|
"epoch": 0.16509136735979837,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499925925064206,
|
|
"loss": 6.0646,
|
|
"mean_token_accuracy": 0.13617814630270003,
|
|
"num_tokens": 3628164.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.377547359466552,
|
|
"epoch": 0.16551144717496324,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999251547019535,
|
|
"loss": 6.2126,
|
|
"mean_token_accuracy": 0.13370679765939714,
|
|
"num_tokens": 3636778.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.318364191055298,
|
|
"epoch": 0.16593152699012811,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999243803552678,
|
|
"loss": 6.1666,
|
|
"mean_token_accuracy": 0.13474627435207367,
|
|
"num_tokens": 3647046.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.2661604404449465,
|
|
"epoch": 0.166351606805293,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999236020241625,
|
|
"loss": 6.0969,
|
|
"mean_token_accuracy": 0.1302388660609722,
|
|
"num_tokens": 3656130.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.294794940948487,
|
|
"epoch": 0.16677168662045788,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999228197086514,
|
|
"loss": 6.1791,
|
|
"mean_token_accuracy": 0.12147556319832802,
|
|
"num_tokens": 3666145.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.308886766433716,
|
|
"epoch": 0.16719176643562278,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999220334087484,
|
|
"loss": 6.2221,
|
|
"mean_token_accuracy": 0.12820759564638137,
|
|
"num_tokens": 3676722.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.34148588180542,
|
|
"epoch": 0.16761184625078765,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999212431244673,
|
|
"loss": 6.1977,
|
|
"mean_token_accuracy": 0.1265730917453766,
|
|
"num_tokens": 3685880.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.220745372772217,
|
|
"epoch": 0.16803192606595252,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999204488558222,
|
|
"loss": 6.0332,
|
|
"mean_token_accuracy": 0.13368572890758515,
|
|
"num_tokens": 3695167.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.279938268661499,
|
|
"epoch": 0.16845200588111742,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999196506028273,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.12803823873400688,
|
|
"num_tokens": 3703700.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.340878582000732,
|
|
"epoch": 0.1688720856962823,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999188483654965,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.12776080071926116,
|
|
"num_tokens": 3712825.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.229676914215088,
|
|
"epoch": 0.16929216551144718,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999180421438442,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.13442618474364282,
|
|
"num_tokens": 3721807.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.3377564430236815,
|
|
"epoch": 0.16971224532661205,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999172319378846,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.12342165559530258,
|
|
"num_tokens": 3730502.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.334515047073364,
|
|
"epoch": 0.17013232514177692,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999164177476319,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.13388336971402168,
|
|
"num_tokens": 3739696.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.170955038070678,
|
|
"epoch": 0.17055240495694182,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999155995731009,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.1329979881644249,
|
|
"num_tokens": 3748675.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.440923643112183,
|
|
"epoch": 0.1709724847721067,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999147774143057,
|
|
"loss": 6.1895,
|
|
"mean_token_accuracy": 0.12849014177918433,
|
|
"num_tokens": 3757714.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.217456531524658,
|
|
"epoch": 0.1713925645872716,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499913951271261,
|
|
"loss": 6.0181,
|
|
"mean_token_accuracy": 0.13668849244713782,
|
|
"num_tokens": 3767589.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.216994047164917,
|
|
"epoch": 0.17181264440243646,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999131211439816,
|
|
"loss": 6.1246,
|
|
"mean_token_accuracy": 0.13397686704993247,
|
|
"num_tokens": 3777261.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.3198566913604735,
|
|
"epoch": 0.17223272421760136,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499912287032482,
|
|
"loss": 6.0738,
|
|
"mean_token_accuracy": 0.13602124899625778,
|
|
"num_tokens": 3786658.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.19984622001648,
|
|
"epoch": 0.17265280403276623,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499911448936777,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.14067015573382377,
|
|
"num_tokens": 3794977.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.179085731506348,
|
|
"epoch": 0.1730728838479311,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999106068568816,
|
|
"loss": 6.1457,
|
|
"mean_token_accuracy": 0.12947675883769988,
|
|
"num_tokens": 3805138.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.279845762252807,
|
|
"epoch": 0.173492963663096,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999097607928106,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.13879665359854698,
|
|
"num_tokens": 3814444.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.212150764465332,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999089107445788,
|
|
"loss": 6.0398,
|
|
"mean_token_accuracy": 0.13306153938174248,
|
|
"num_tokens": 3822859.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.133330869674682,
|
|
"epoch": 0.17433312329342576,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999080567122016,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.13198764845728875,
|
|
"num_tokens": 3833159.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.295455646514893,
|
|
"epoch": 0.17475320310859063,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999071986956941,
|
|
"loss": 6.0856,
|
|
"mean_token_accuracy": 0.13797224685549736,
|
|
"num_tokens": 3842136.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.208657741546631,
|
|
"epoch": 0.1751732829237555,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999063366950713,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.12877421900629998,
|
|
"num_tokens": 3851406.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.217505025863647,
|
|
"epoch": 0.1755933627389204,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999054707103486,
|
|
"loss": 6.0713,
|
|
"mean_token_accuracy": 0.1279774695634842,
|
|
"num_tokens": 3861061.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.265169095993042,
|
|
"epoch": 0.17601344255408527,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999046007415412,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.12900712937116623,
|
|
"num_tokens": 3870357.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.2917054176330565,
|
|
"epoch": 0.17643352236925017,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999037267886646,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.13141706436872483,
|
|
"num_tokens": 3879393.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.180794954299927,
|
|
"epoch": 0.17685360218441504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999028488517343,
|
|
"loss": 6.0832,
|
|
"mean_token_accuracy": 0.13525146320462228,
|
|
"num_tokens": 3888030.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.266747093200683,
|
|
"epoch": 0.1772736819995799,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999019669307659,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.1376435212790966,
|
|
"num_tokens": 3897430.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.238908100128174,
|
|
"epoch": 0.1776937618147448,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999010810257749,
|
|
"loss": 6.0977,
|
|
"mean_token_accuracy": 0.12719068825244903,
|
|
"num_tokens": 3907711.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.189173746109009,
|
|
"epoch": 0.17811384162990967,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999001911367771,
|
|
"loss": 6.0411,
|
|
"mean_token_accuracy": 0.13638337776064874,
|
|
"num_tokens": 3915816.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.22648811340332,
|
|
"epoch": 0.17853392144507457,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998992972637883,
|
|
"loss": 6.1538,
|
|
"mean_token_accuracy": 0.12582943066954613,
|
|
"num_tokens": 3925162.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.284874153137207,
|
|
"epoch": 0.17895400126023944,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998983994068242,
|
|
"loss": 6.0395,
|
|
"mean_token_accuracy": 0.13122835606336594,
|
|
"num_tokens": 3934476.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.186276054382324,
|
|
"epoch": 0.17937408107540434,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998974975659006,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.1297646477818489,
|
|
"num_tokens": 3943501.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.205726194381714,
|
|
"epoch": 0.1797941608905692,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998965917410338,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.12778471410274506,
|
|
"num_tokens": 3953663.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.211074018478394,
|
|
"epoch": 0.18021424070573408,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998956819322397,
|
|
"loss": 6.0495,
|
|
"mean_token_accuracy": 0.13608243688941002,
|
|
"num_tokens": 3962634.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.177238512039184,
|
|
"epoch": 0.18063432052089898,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998947681395343,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.13605224341154099,
|
|
"num_tokens": 3972496.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.390697908401489,
|
|
"epoch": 0.18105440033606385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499893850362934,
|
|
"loss": 6.2977,
|
|
"mean_token_accuracy": 0.12441082820296287,
|
|
"num_tokens": 3980724.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.262918901443482,
|
|
"epoch": 0.18147448015122875,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998929286024548,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.1300631955265999,
|
|
"num_tokens": 3989842.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.230935716629029,
|
|
"epoch": 0.18189455996639362,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998920028581133,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.14167480319738388,
|
|
"num_tokens": 3998534.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.241239356994629,
|
|
"epoch": 0.18231463978155849,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998910731299258,
|
|
"loss": 6.0631,
|
|
"mean_token_accuracy": 0.13066420927643776,
|
|
"num_tokens": 4007677.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.19789605140686,
|
|
"epoch": 0.18273471959672338,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998901394179085,
|
|
"loss": 6.1007,
|
|
"mean_token_accuracy": 0.12627347633242608,
|
|
"num_tokens": 4016347.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.198655843734741,
|
|
"epoch": 0.18315479941188825,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998892017220784,
|
|
"loss": 5.9767,
|
|
"mean_token_accuracy": 0.14088783264160157,
|
|
"num_tokens": 4025199.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.262273931503296,
|
|
"epoch": 0.18357487922705315,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998882600424519,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.1286892294883728,
|
|
"num_tokens": 4033933.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.162368822097778,
|
|
"epoch": 0.18399495904221802,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998873143790455,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.1438771367073059,
|
|
"num_tokens": 4042891.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.274066638946533,
|
|
"epoch": 0.1844150388573829,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998863647318763,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.13264708146452903,
|
|
"num_tokens": 4051123.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.144877004623413,
|
|
"epoch": 0.1848351186725478,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998854111009608,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.12865814492106437,
|
|
"num_tokens": 4060025.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.182585954666138,
|
|
"epoch": 0.18525519848771266,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998844534863161,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.1295328378677368,
|
|
"num_tokens": 4069363.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.241155099868775,
|
|
"epoch": 0.18567527830287756,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998834918879592,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.133307021856308,
|
|
"num_tokens": 4078855.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.206245565414429,
|
|
"epoch": 0.18609535811804243,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499882526305907,
|
|
"loss": 6.0804,
|
|
"mean_token_accuracy": 0.12953457087278367,
|
|
"num_tokens": 4087801.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.248236179351807,
|
|
"epoch": 0.18651543793320732,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998815567401765,
|
|
"loss": 6.0926,
|
|
"mean_token_accuracy": 0.1376325160264969,
|
|
"num_tokens": 4096949.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.279425954818725,
|
|
"epoch": 0.1869355177483722,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998805831907851,
|
|
"loss": 6.0617,
|
|
"mean_token_accuracy": 0.13082574903964997,
|
|
"num_tokens": 4105399.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.169968605041504,
|
|
"epoch": 0.18735559756353706,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998796056577501,
|
|
"loss": 6.0071,
|
|
"mean_token_accuracy": 0.12926321402192115,
|
|
"num_tokens": 4113873.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.154512643814087,
|
|
"epoch": 0.18777567737870196,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998786241410886,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.13699585050344468,
|
|
"num_tokens": 4123528.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.2988721370697025,
|
|
"epoch": 0.18819575719386683,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499877638640818,
|
|
"loss": 6.0699,
|
|
"mean_token_accuracy": 0.13017342165112494,
|
|
"num_tokens": 4133370.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.184452104568481,
|
|
"epoch": 0.18861583700903173,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499876649156956,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.13666255846619607,
|
|
"num_tokens": 4142370.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.133312082290649,
|
|
"epoch": 0.1890359168241966,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998756556895196,
|
|
"loss": 6.0725,
|
|
"mean_token_accuracy": 0.1354515865445137,
|
|
"num_tokens": 4152367.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.21663122177124,
|
|
"epoch": 0.18945599663936147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499874658238527,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.13495326191186904,
|
|
"num_tokens": 4161126.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.186970901489258,
|
|
"epoch": 0.18987607645452637,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998736568039957,
|
|
"loss": 5.9748,
|
|
"mean_token_accuracy": 0.13723411411046982,
|
|
"num_tokens": 4169910.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.1857301712036135,
|
|
"epoch": 0.19029615626969124,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998726513859432,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.12761787325143814,
|
|
"num_tokens": 4179893.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.308238935470581,
|
|
"epoch": 0.19071623608485613,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998716419843875,
|
|
"loss": 6.12,
|
|
"mean_token_accuracy": 0.13745217099785806,
|
|
"num_tokens": 4190065.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.090948486328125,
|
|
"epoch": 0.191136315900021,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998706285993465,
|
|
"loss": 6.0313,
|
|
"mean_token_accuracy": 0.1420229621231556,
|
|
"num_tokens": 4198395.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.282499647140503,
|
|
"epoch": 0.19155639571518587,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998696112308381,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.1310360386967659,
|
|
"num_tokens": 4207555.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.088230180740356,
|
|
"epoch": 0.19197647553035077,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998685898788803,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.13536595478653907,
|
|
"num_tokens": 4216533.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.274929618835449,
|
|
"epoch": 0.19239655534551564,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998675645434914,
|
|
"loss": 6.1095,
|
|
"mean_token_accuracy": 0.13767784610390663,
|
|
"num_tokens": 4225575.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.153714513778686,
|
|
"epoch": 0.19281663516068054,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998665352246891,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.14245088025927544,
|
|
"num_tokens": 4234306.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.08680305480957,
|
|
"epoch": 0.1932367149758454,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998655019224921,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.1359329827129841,
|
|
"num_tokens": 4243998.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.237053394317627,
|
|
"epoch": 0.19365679479101028,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998644646369185,
|
|
"loss": 5.9776,
|
|
"mean_token_accuracy": 0.13352483361959458,
|
|
"num_tokens": 4253653.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.139167737960816,
|
|
"epoch": 0.19407687460617518,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998634233679865,
|
|
"loss": 6.0652,
|
|
"mean_token_accuracy": 0.1278400629758835,
|
|
"num_tokens": 4263305.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.127392339706421,
|
|
"epoch": 0.19449695442134005,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499862378115715,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.14543856382369996,
|
|
"num_tokens": 4272212.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.305202007293701,
|
|
"epoch": 0.19491703423650494,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998613288801221,
|
|
"loss": 6.1375,
|
|
"mean_token_accuracy": 0.13151465207338334,
|
|
"num_tokens": 4281445.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.2177956104278564,
|
|
"epoch": 0.1953371140516698,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998602756612267,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.1372949168086052,
|
|
"num_tokens": 4290938.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.175972557067871,
|
|
"epoch": 0.1957571938668347,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998592184590471,
|
|
"loss": 6.0786,
|
|
"mean_token_accuracy": 0.13233636021614076,
|
|
"num_tokens": 4300022.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.134920358657837,
|
|
"epoch": 0.19617727368199958,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998581572736024,
|
|
"loss": 5.9674,
|
|
"mean_token_accuracy": 0.1363460712134838,
|
|
"num_tokens": 4308910.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.092206907272339,
|
|
"epoch": 0.19659735349716445,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998570921049112,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.13969452679157257,
|
|
"num_tokens": 4317136.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.112558746337891,
|
|
"epoch": 0.19701743331232935,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998560229529924,
|
|
"loss": 5.9993,
|
|
"mean_token_accuracy": 0.1428337089717388,
|
|
"num_tokens": 4326163.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.308993816375732,
|
|
"epoch": 0.19743751312749422,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998549498178649,
|
|
"loss": 6.1402,
|
|
"mean_token_accuracy": 0.13658420667052268,
|
|
"num_tokens": 4335837.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.216946363449097,
|
|
"epoch": 0.19785759294265912,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998538726995477,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.1374947391450405,
|
|
"num_tokens": 4345108.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.217574787139893,
|
|
"epoch": 0.198277672757824,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049985279159806,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.1334306165575981,
|
|
"num_tokens": 4353761.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.1630774974823,
|
|
"epoch": 0.19869775257298886,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998517065134208,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.13587109968066216,
|
|
"num_tokens": 4363244.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.205533790588379,
|
|
"epoch": 0.19911783238815375,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998506174456494,
|
|
"loss": 6.0386,
|
|
"mean_token_accuracy": 0.13257589265704156,
|
|
"num_tokens": 4373034.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.200410652160644,
|
|
"epoch": 0.19953791220331862,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998495243947653,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.13029902279376984,
|
|
"num_tokens": 4382554.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.191087865829468,
|
|
"epoch": 0.19995799201848352,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998484273607875,
|
|
"loss": 5.9843,
|
|
"mean_token_accuracy": 0.14299238696694375,
|
|
"num_tokens": 4391001.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.023518228530884,
|
|
"epoch": 0.2003780718336484,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998473263437356,
|
|
"loss": 5.9141,
|
|
"mean_token_accuracy": 0.13673870489001275,
|
|
"num_tokens": 4400632.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.105119514465332,
|
|
"epoch": 0.20079815164881326,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499846221343629,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.12952324375510216,
|
|
"num_tokens": 4409565.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.128167533874512,
|
|
"epoch": 0.20121823146397816,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998451123604875,
|
|
"loss": 5.944,
|
|
"mean_token_accuracy": 0.14282809123396872,
|
|
"num_tokens": 4418384.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.1983355522155765,
|
|
"epoch": 0.20163831127914303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998439993943306,
|
|
"loss": 6.0692,
|
|
"mean_token_accuracy": 0.1389256276190281,
|
|
"num_tokens": 4427581.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.267655086517334,
|
|
"epoch": 0.20205839109430793,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998428824451779,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.1341543450951576,
|
|
"num_tokens": 4436572.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.1763083934783936,
|
|
"epoch": 0.2024784709094728,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998417615130495,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.13537125810980796,
|
|
"num_tokens": 4445230.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.247248315811158,
|
|
"epoch": 0.2028985507246377,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998406365979649,
|
|
"loss": 6.1134,
|
|
"mean_token_accuracy": 0.13383878991007805,
|
|
"num_tokens": 4454251.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.136447811126709,
|
|
"epoch": 0.20331863053980256,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998395076999443,
|
|
"loss": 5.9699,
|
|
"mean_token_accuracy": 0.13695907220244408,
|
|
"num_tokens": 4463949.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.227413558959961,
|
|
"epoch": 0.20373871035496743,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998383748190076,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.12917085587978364,
|
|
"num_tokens": 4473373.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.249214363098145,
|
|
"epoch": 0.20415879017013233,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998372379551748,
|
|
"loss": 5.9842,
|
|
"mean_token_accuracy": 0.1414948470890522,
|
|
"num_tokens": 4482303.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.117572832107544,
|
|
"epoch": 0.2045788699852972,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998360971084663,
|
|
"loss": 5.9567,
|
|
"mean_token_accuracy": 0.1317524030804634,
|
|
"num_tokens": 4491214.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.057681226730347,
|
|
"epoch": 0.2049989498004621,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998349522789019,
|
|
"loss": 5.8856,
|
|
"mean_token_accuracy": 0.14377139806747435,
|
|
"num_tokens": 4500099.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.115459060668945,
|
|
"epoch": 0.20541902961562697,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998338034665021,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.1437109664082527,
|
|
"num_tokens": 4509893.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.08744249343872,
|
|
"epoch": 0.20583910943079184,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998326506712872,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.13774847760796546,
|
|
"num_tokens": 4518606.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.11673412322998,
|
|
"epoch": 0.20625918924595674,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998314938932778,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.14001012295484544,
|
|
"num_tokens": 4528392.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.221143388748169,
|
|
"epoch": 0.2066792690611216,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998303331324943,
|
|
"loss": 5.9923,
|
|
"mean_token_accuracy": 0.13821439668536187,
|
|
"num_tokens": 4536983.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.041988134384155,
|
|
"epoch": 0.2070993488762865,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998291683889571,
|
|
"loss": 5.9145,
|
|
"mean_token_accuracy": 0.1391140677034855,
|
|
"num_tokens": 4544967.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.134957313537598,
|
|
"epoch": 0.20751942869145137,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499827999662687,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.13200750946998596,
|
|
"num_tokens": 4554646.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.192252588272095,
|
|
"epoch": 0.20793950850661624,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998268269537046,
|
|
"loss": 5.9954,
|
|
"mean_token_accuracy": 0.1370847873389721,
|
|
"num_tokens": 4564040.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.091167068481445,
|
|
"epoch": 0.20835958832178114,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998256502620308,
|
|
"loss": 6.0187,
|
|
"mean_token_accuracy": 0.14094985872507096,
|
|
"num_tokens": 4573758.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.206011056900024,
|
|
"epoch": 0.208779668136946,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998244695876864,
|
|
"loss": 6.0452,
|
|
"mean_token_accuracy": 0.13380730673670768,
|
|
"num_tokens": 4582097.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.0949585914611815,
|
|
"epoch": 0.2091997479521109,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998232849306921,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.13993047401309014,
|
|
"num_tokens": 4590687.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.1933338165283205,
|
|
"epoch": 0.20961982776727578,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998220962910693,
|
|
"loss": 5.9965,
|
|
"mean_token_accuracy": 0.13453714549541473,
|
|
"num_tokens": 4599497.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.101396179199218,
|
|
"epoch": 0.21003990758244068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998209036688386,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.13716981932520866,
|
|
"num_tokens": 4607958.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.216299772262573,
|
|
"epoch": 0.21045998739760555,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998197070640216,
|
|
"loss": 6.0812,
|
|
"mean_token_accuracy": 0.1314453199505806,
|
|
"num_tokens": 4617515.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.2111225605010985,
|
|
"epoch": 0.21088006721277042,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998185064766391,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.135587390512228,
|
|
"num_tokens": 4627037.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.083059787750244,
|
|
"epoch": 0.21130014702793531,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998173019067127,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.13536423593759536,
|
|
"num_tokens": 4637393.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.111885261535645,
|
|
"epoch": 0.21172022684310018,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998160933542633,
|
|
"loss": 6.0252,
|
|
"mean_token_accuracy": 0.12426691725850106,
|
|
"num_tokens": 4646832.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.200415229797363,
|
|
"epoch": 0.21214030665826508,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998148808193128,
|
|
"loss": 6.0364,
|
|
"mean_token_accuracy": 0.1378290109336376,
|
|
"num_tokens": 4655719.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.140298128128052,
|
|
"epoch": 0.21256038647342995,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998136643018823,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.1409161224961281,
|
|
"num_tokens": 4665364.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.113859462738037,
|
|
"epoch": 0.21298046628859482,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998124438019935,
|
|
"loss": 5.9707,
|
|
"mean_token_accuracy": 0.13255369514226914,
|
|
"num_tokens": 4674760.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.032169342041016,
|
|
"epoch": 0.21340054610375972,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998112193196681,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.1398087151348591,
|
|
"num_tokens": 4683900.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.009505701065064,
|
|
"epoch": 0.2138206259189246,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998099908549277,
|
|
"loss": 5.9487,
|
|
"mean_token_accuracy": 0.1326383799314499,
|
|
"num_tokens": 4693915.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.048102998733521,
|
|
"epoch": 0.2142407057340895,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499808758407794,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.1494914174079895,
|
|
"num_tokens": 4703102.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.130202150344848,
|
|
"epoch": 0.21466078554925436,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998075219782889,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.13604088351130486,
|
|
"num_tokens": 4712925.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.086578845977783,
|
|
"epoch": 0.21508086536441923,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998062815664344,
|
|
"loss": 5.9508,
|
|
"mean_token_accuracy": 0.13391971811652184,
|
|
"num_tokens": 4722641.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.060202693939209,
|
|
"epoch": 0.21550094517958412,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998050371722524,
|
|
"loss": 6.028,
|
|
"mean_token_accuracy": 0.13827937468886375,
|
|
"num_tokens": 4732603.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.060051965713501,
|
|
"epoch": 0.215921024994749,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998037887957649,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.1426350235939026,
|
|
"num_tokens": 4742644.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.2458967685699465,
|
|
"epoch": 0.2163411048099139,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998025364369939,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.1332129217684269,
|
|
"num_tokens": 4751482.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.246464967727661,
|
|
"epoch": 0.21676118462507876,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998012800959619,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.13494925051927567,
|
|
"num_tokens": 4760593.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.139482402801514,
|
|
"epoch": 0.21718126444024366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998000197726909,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.14071242287755012,
|
|
"num_tokens": 4769294.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.151182079315186,
|
|
"epoch": 0.21760134425540853,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997987554672033,
|
|
"loss": 5.9433,
|
|
"mean_token_accuracy": 0.13458855599164962,
|
|
"num_tokens": 4779239.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.153560495376587,
|
|
"epoch": 0.2180214240705734,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997974871795215,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.13904761373996735,
|
|
"num_tokens": 4788211.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.1266923427581785,
|
|
"epoch": 0.2184415038857383,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499796214909668,
|
|
"loss": 5.9707,
|
|
"mean_token_accuracy": 0.14307306259870528,
|
|
"num_tokens": 4797921.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.151721715927124,
|
|
"epoch": 0.21886158370090317,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997949386576653,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.1372672997415066,
|
|
"num_tokens": 4807772.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.999966764450074,
|
|
"epoch": 0.21928166351606806,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499793658423536,
|
|
"loss": 6.0037,
|
|
"mean_token_accuracy": 0.13394766226410865,
|
|
"num_tokens": 4817999.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.197027158737183,
|
|
"epoch": 0.21970174333123293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997923742073028,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.14477612674236298,
|
|
"num_tokens": 4826679.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.0403674125671385,
|
|
"epoch": 0.2201218231463978,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997910860089884,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.13903913348913194,
|
|
"num_tokens": 4834998.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.119702100753784,
|
|
"epoch": 0.2205419029615627,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997897938286156,
|
|
"loss": 5.9173,
|
|
"mean_token_accuracy": 0.13934070989489555,
|
|
"num_tokens": 4843635.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.135205316543579,
|
|
"epoch": 0.22096198277672757,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997884976662075,
|
|
"loss": 6.0334,
|
|
"mean_token_accuracy": 0.13847846239805223,
|
|
"num_tokens": 4852027.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.115947484970093,
|
|
"epoch": 0.22138206259189247,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997871975217868,
|
|
"loss": 5.9555,
|
|
"mean_token_accuracy": 0.1428781971335411,
|
|
"num_tokens": 4861244.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.043252468109131,
|
|
"epoch": 0.22180214240705734,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997858933953768,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.14281281381845473,
|
|
"num_tokens": 4869902.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.012739181518555,
|
|
"epoch": 0.2222222222222222,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997845852870004,
|
|
"loss": 5.8421,
|
|
"mean_token_accuracy": 0.1463296964764595,
|
|
"num_tokens": 4878502.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.089871215820312,
|
|
"epoch": 0.2226423020373871,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997832731966806,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.14714645445346833,
|
|
"num_tokens": 4888348.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.06225700378418,
|
|
"epoch": 0.22306238185255198,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997819571244411,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.1450254276394844,
|
|
"num_tokens": 4897302.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.0446860790252686,
|
|
"epoch": 0.22348246166771688,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997806370703049,
|
|
"loss": 5.9876,
|
|
"mean_token_accuracy": 0.14430617392063141,
|
|
"num_tokens": 4907078.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.057806348800659,
|
|
"epoch": 0.22390254148288175,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997793130342954,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.1456086441874504,
|
|
"num_tokens": 4917489.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.973814630508423,
|
|
"epoch": 0.22432262129804661,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997779850164363,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.140571466088295,
|
|
"num_tokens": 4927073.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.177860355377197,
|
|
"epoch": 0.2247427011132115,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997766530167508,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.1344543881714344,
|
|
"num_tokens": 4935464.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.22092981338501,
|
|
"epoch": 0.22516278092837638,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997753170352627,
|
|
"loss": 6.0914,
|
|
"mean_token_accuracy": 0.13605839386582375,
|
|
"num_tokens": 4944718.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.105925226211548,
|
|
"epoch": 0.22558286074354128,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997739770719955,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.13587288782000542,
|
|
"num_tokens": 4954223.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.107930469512939,
|
|
"epoch": 0.22600294055870615,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499772633126973,
|
|
"loss": 6.0132,
|
|
"mean_token_accuracy": 0.13594387769699096,
|
|
"num_tokens": 4963371.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.04271125793457,
|
|
"epoch": 0.22642302037387105,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997712852002192,
|
|
"loss": 5.8679,
|
|
"mean_token_accuracy": 0.1471228800714016,
|
|
"num_tokens": 4972973.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.086397647857666,
|
|
"epoch": 0.22684310018903592,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997699332917578,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.12916670590639115,
|
|
"num_tokens": 4982808.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.201492786407471,
|
|
"epoch": 0.2272631800042008,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997685774016127,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.13685485795140268,
|
|
"num_tokens": 4992427.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.162964010238648,
|
|
"epoch": 0.22768325981936569,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499767217529808,
|
|
"loss": 6.1604,
|
|
"mean_token_accuracy": 0.12921097874641418,
|
|
"num_tokens": 5003562.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.098525857925415,
|
|
"epoch": 0.22810333963453056,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997658536763678,
|
|
"loss": 5.8638,
|
|
"mean_token_accuracy": 0.1451013281941414,
|
|
"num_tokens": 5013429.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.117339611053467,
|
|
"epoch": 0.22852341944969545,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997644858413163,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.14247513711452484,
|
|
"num_tokens": 5022045.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.008642053604126,
|
|
"epoch": 0.22894349926486032,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997631140246775,
|
|
"loss": 5.8287,
|
|
"mean_token_accuracy": 0.14408515840768815,
|
|
"num_tokens": 5032260.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.021863174438477,
|
|
"epoch": 0.2293635790800252,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499761738226476,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.14258013665676117,
|
|
"num_tokens": 5041688.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.056025457382202,
|
|
"epoch": 0.2297836588951901,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499760358446736,
|
|
"loss": 5.9702,
|
|
"mean_token_accuracy": 0.13718490228056907,
|
|
"num_tokens": 5051005.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.152891635894775,
|
|
"epoch": 0.23020373871035496,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499758974685482,
|
|
"loss": 5.9147,
|
|
"mean_token_accuracy": 0.13967233374714852,
|
|
"num_tokens": 5060084.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.059838390350341,
|
|
"epoch": 0.23062381852551986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997575869427385,
|
|
"loss": 5.9122,
|
|
"mean_token_accuracy": 0.14734914749860764,
|
|
"num_tokens": 5069081.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.0928624153137205,
|
|
"epoch": 0.23104389834068473,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049975619521853,
|
|
"loss": 5.9121,
|
|
"mean_token_accuracy": 0.13845374211668968,
|
|
"num_tokens": 5078597.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.052087306976318,
|
|
"epoch": 0.2314639781558496,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997547995128814,
|
|
"loss": 5.9554,
|
|
"mean_token_accuracy": 0.14530446976423264,
|
|
"num_tokens": 5087607.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.094136476516724,
|
|
"epoch": 0.2318840579710145,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997533998258171,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.14329736083745956,
|
|
"num_tokens": 5097412.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.16567211151123,
|
|
"epoch": 0.23230413778617937,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997519961573622,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.13348544016480446,
|
|
"num_tokens": 5105817.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.226717376708985,
|
|
"epoch": 0.23272421760134426,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997505885075414,
|
|
"loss": 6.0522,
|
|
"mean_token_accuracy": 0.13480133637785913,
|
|
"num_tokens": 5114958.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.084324312210083,
|
|
"epoch": 0.23314429741650913,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997491768763795,
|
|
"loss": 5.9898,
|
|
"mean_token_accuracy": 0.13868246227502823,
|
|
"num_tokens": 5123728.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.100927209854126,
|
|
"epoch": 0.23356437723167403,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997477612639018,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.13395264372229576,
|
|
"num_tokens": 5134099.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.162116241455078,
|
|
"epoch": 0.2339844570468389,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997463416701332,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.13172747194766998,
|
|
"num_tokens": 5142934.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.000607919692993,
|
|
"epoch": 0.23440453686200377,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997449180950989,
|
|
"loss": 5.8681,
|
|
"mean_token_accuracy": 0.15649961084127426,
|
|
"num_tokens": 5151835.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.038245487213135,
|
|
"epoch": 0.23482461667716867,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997434905388241,
|
|
"loss": 5.921,
|
|
"mean_token_accuracy": 0.1477814018726349,
|
|
"num_tokens": 5161136.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.029763174057007,
|
|
"epoch": 0.23524469649233354,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499742059001334,
|
|
"loss": 5.8684,
|
|
"mean_token_accuracy": 0.14450337663292884,
|
|
"num_tokens": 5170741.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.046102046966553,
|
|
"epoch": 0.23566477630749844,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997406234826541,
|
|
"loss": 5.9001,
|
|
"mean_token_accuracy": 0.14729267880320548,
|
|
"num_tokens": 5180549.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.980107164382934,
|
|
"epoch": 0.2360848561226633,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997391839828098,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.14962306916713713,
|
|
"num_tokens": 5189486.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.044159746170044,
|
|
"epoch": 0.23650493593782818,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997377405018266,
|
|
"loss": 5.9303,
|
|
"mean_token_accuracy": 0.13750530928373336,
|
|
"num_tokens": 5198525.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.075648498535156,
|
|
"epoch": 0.23692501575299307,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049973629303973,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.14086321070790292,
|
|
"num_tokens": 5207124.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.964286422729492,
|
|
"epoch": 0.23734509556815794,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997348415965457,
|
|
"loss": 5.8079,
|
|
"mean_token_accuracy": 0.14603810012340546,
|
|
"num_tokens": 5216529.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.12622709274292,
|
|
"epoch": 0.23776517538332284,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997333861722995,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.14331007972359658,
|
|
"num_tokens": 5225796.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.085462188720703,
|
|
"epoch": 0.2381852551984877,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499731926767017,
|
|
"loss": 5.9732,
|
|
"mean_token_accuracy": 0.14003979936242103,
|
|
"num_tokens": 5233876.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.016348743438721,
|
|
"epoch": 0.23860533501365258,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997304633807242,
|
|
"loss": 5.9695,
|
|
"mean_token_accuracy": 0.13823127001523972,
|
|
"num_tokens": 5244782.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.077929925918579,
|
|
"epoch": 0.23902541482881748,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997289960134468,
|
|
"loss": 5.8993,
|
|
"mean_token_accuracy": 0.14192162305116654,
|
|
"num_tokens": 5253453.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.049857330322266,
|
|
"epoch": 0.23944549464398235,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997275246652111,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.14183279648423194,
|
|
"num_tokens": 5262355.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.019342088699341,
|
|
"epoch": 0.23986557445914725,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499726049336043,
|
|
"loss": 5.8652,
|
|
"mean_token_accuracy": 0.14227822795510292,
|
|
"num_tokens": 5271959.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.045290803909301,
|
|
"epoch": 0.24028565427431212,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997245700259686,
|
|
"loss": 5.8938,
|
|
"mean_token_accuracy": 0.14394148513674737,
|
|
"num_tokens": 5281393.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.126777935028076,
|
|
"epoch": 0.240705734089477,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997230867350141,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.13795892894268036,
|
|
"num_tokens": 5290979.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.170654964447022,
|
|
"epoch": 0.24112581390464188,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997215994632059,
|
|
"loss": 5.9662,
|
|
"mean_token_accuracy": 0.1420626498758793,
|
|
"num_tokens": 5300263.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.098070096969605,
|
|
"epoch": 0.24154589371980675,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997201082105704,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.1376795694231987,
|
|
"num_tokens": 5309522.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.09854941368103,
|
|
"epoch": 0.24196597353497165,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997186129771338,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.1443823680281639,
|
|
"num_tokens": 5319770.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.159392309188843,
|
|
"epoch": 0.24238605335013652,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997171137629226,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.14119460731744765,
|
|
"num_tokens": 5328400.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.00137939453125,
|
|
"epoch": 0.24280613316530142,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997156105679636,
|
|
"loss": 5.8054,
|
|
"mean_token_accuracy": 0.15445883423089982,
|
|
"num_tokens": 5336338.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.9904273509979244,
|
|
"epoch": 0.2432262129804663,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997141033922832,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.1381608746945858,
|
|
"num_tokens": 5345391.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.080091238021851,
|
|
"epoch": 0.24364629279563116,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997125922359081,
|
|
"loss": 5.9345,
|
|
"mean_token_accuracy": 0.13472433462738992,
|
|
"num_tokens": 5354709.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.0483152866363525,
|
|
"epoch": 0.24406637261079606,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997110770988652,
|
|
"loss": 5.8441,
|
|
"mean_token_accuracy": 0.14647466093301773,
|
|
"num_tokens": 5363738.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.065390634536743,
|
|
"epoch": 0.24448645242596093,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997095579811813,
|
|
"loss": 5.9742,
|
|
"mean_token_accuracy": 0.14132302552461623,
|
|
"num_tokens": 5373583.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.1408384323120115,
|
|
"epoch": 0.24490653224112582,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997080348828833,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.14406906738877295,
|
|
"num_tokens": 5383486.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.012083101272583,
|
|
"epoch": 0.2453266120562907,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997065078039981,
|
|
"loss": 5.9283,
|
|
"mean_token_accuracy": 0.13883504942059516,
|
|
"num_tokens": 5391974.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.098450088500977,
|
|
"epoch": 0.24574669187145556,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997049767445529,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.13587900176644324,
|
|
"num_tokens": 5400882.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.1687455654144285,
|
|
"epoch": 0.24616677168662046,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997034417045746,
|
|
"loss": 5.9199,
|
|
"mean_token_accuracy": 0.13755179792642594,
|
|
"num_tokens": 5410538.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.019326400756836,
|
|
"epoch": 0.24658685150178533,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997019026840907,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.14420632421970367,
|
|
"num_tokens": 5419406.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.9686970710754395,
|
|
"epoch": 0.24700693131695023,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997003596831282,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.13971618413925171,
|
|
"num_tokens": 5428817.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.097631120681763,
|
|
"epoch": 0.2474270111321151,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996988127017145,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.13872243240475654,
|
|
"num_tokens": 5438277.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.047083616256714,
|
|
"epoch": 0.24784709094728,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996972617398772,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.13909853398799896,
|
|
"num_tokens": 5447440.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.065885257720947,
|
|
"epoch": 0.24826717076244487,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996957067976435,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.13819090723991395,
|
|
"num_tokens": 5455988.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.079396390914917,
|
|
"epoch": 0.24868725057760974,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996941478750411,
|
|
"loss": 5.895,
|
|
"mean_token_accuracy": 0.14170320481061935,
|
|
"num_tokens": 5464996.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.131442737579346,
|
|
"epoch": 0.24910733039277463,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996925849720975,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.13297844752669336,
|
|
"num_tokens": 5474174.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.144496154785156,
|
|
"epoch": 0.2495274102079395,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996910180888405,
|
|
"loss": 5.928,
|
|
"mean_token_accuracy": 0.14379495605826378,
|
|
"num_tokens": 5482838.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.089239263534546,
|
|
"epoch": 0.2499474900231044,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996894472252977,
|
|
"loss": 5.9339,
|
|
"mean_token_accuracy": 0.1420593172311783,
|
|
"num_tokens": 5491616.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.992457008361816,
|
|
"epoch": 0.25036756983826924,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996878723814973,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.13892921283841134,
|
|
"num_tokens": 5500942.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.117427587509155,
|
|
"epoch": 0.25078764965343414,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996862935574667,
|
|
"loss": 5.8788,
|
|
"mean_token_accuracy": 0.13912170454859735,
|
|
"num_tokens": 5510078.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.943054437637329,
|
|
"epoch": 0.25120772946859904,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996847107532342,
|
|
"loss": 5.9134,
|
|
"mean_token_accuracy": 0.14340257570147513,
|
|
"num_tokens": 5518924.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.108536148071289,
|
|
"epoch": 0.25162780928376394,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996831239688277,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.13749035373330115,
|
|
"num_tokens": 5527385.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.977105903625488,
|
|
"epoch": 0.2520478890989288,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996815332042754,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.15047305673360825,
|
|
"num_tokens": 5536781.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2520478890989288,
|
|
"eval_entropy": 5.7445289912557636,
|
|
"eval_loss": 5.931798458099365,
|
|
"eval_mean_token_accuracy": 0.1480788363722414,
|
|
"eval_num_tokens": 5536781.0,
|
|
"eval_runtime": 21.0325,
|
|
"eval_samples_per_second": 1776.586,
|
|
"eval_steps_per_second": 222.085,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119020,
|
|
"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": 1203541354414080.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|