42112 lines
1.1 MiB
42112 lines
1.1 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.8351830813597831,
|
|
"eval_steps": 3000,
|
|
"global_step": 21000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.692021942138672,
|
|
"epoch": 0.0004369483527047103,
|
|
"grad_norm": 13.1875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8244,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10478.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691936111450195,
|
|
"epoch": 0.0008738967054094206,
|
|
"grad_norm": 13.5,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.755,
|
|
"mean_token_accuracy": 0.00011547344038262964,
|
|
"num_tokens": 21152.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.69045877456665,
|
|
"epoch": 0.0013108450581141308,
|
|
"grad_norm": 9.875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.5011,
|
|
"mean_token_accuracy": 0.034536856785416604,
|
|
"num_tokens": 31246.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.65780954360962,
|
|
"epoch": 0.0017477934108188413,
|
|
"grad_norm": 5.6875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.2113,
|
|
"mean_token_accuracy": 0.04944819919764996,
|
|
"num_tokens": 41934.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.511194896697997,
|
|
"epoch": 0.0021847417635235517,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.9808,
|
|
"mean_token_accuracy": 0.04893734566867351,
|
|
"num_tokens": 52830.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.482695293426513,
|
|
"epoch": 0.0026216901162282617,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.7583,
|
|
"mean_token_accuracy": 0.05473130941390991,
|
|
"num_tokens": 62706.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.45745210647583,
|
|
"epoch": 0.003058638468932972,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.712,
|
|
"mean_token_accuracy": 0.051637019217014316,
|
|
"num_tokens": 72619.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.482015132904053,
|
|
"epoch": 0.0034955868216376825,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.7145,
|
|
"mean_token_accuracy": 0.0506310198456049,
|
|
"num_tokens": 82903.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.458813381195068,
|
|
"epoch": 0.003932535174342393,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.6082,
|
|
"mean_token_accuracy": 0.06321541368961334,
|
|
"num_tokens": 94243.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.395197868347168,
|
|
"epoch": 0.004369483527047103,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.6296,
|
|
"mean_token_accuracy": 0.054243823140859605,
|
|
"num_tokens": 103618.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.466286754608154,
|
|
"epoch": 0.004806431879751813,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.5593,
|
|
"mean_token_accuracy": 0.06178116090595722,
|
|
"num_tokens": 112180.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.310550880432128,
|
|
"epoch": 0.005243380232456523,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.511,
|
|
"mean_token_accuracy": 0.06281424462795257,
|
|
"num_tokens": 122462.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.273916530609132,
|
|
"epoch": 0.005680328585161234,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.4532,
|
|
"mean_token_accuracy": 0.06505128778517247,
|
|
"num_tokens": 132741.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.26039628982544,
|
|
"epoch": 0.006117276937865944,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.2917,
|
|
"mean_token_accuracy": 0.07007538042962551,
|
|
"num_tokens": 142973.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.227308750152588,
|
|
"epoch": 0.006554225290570655,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.3612,
|
|
"mean_token_accuracy": 0.06413876824080944,
|
|
"num_tokens": 153199.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.246389770507813,
|
|
"epoch": 0.006991173643275365,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.2351,
|
|
"mean_token_accuracy": 0.06828652881085873,
|
|
"num_tokens": 163079.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.19476842880249,
|
|
"epoch": 0.0074281219959800755,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.1397,
|
|
"mean_token_accuracy": 0.0709759708493948,
|
|
"num_tokens": 173308.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.129861736297608,
|
|
"epoch": 0.007865070348684786,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.0684,
|
|
"mean_token_accuracy": 0.08018519915640354,
|
|
"num_tokens": 183856.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.133734321594238,
|
|
"epoch": 0.008302018701389496,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.9724,
|
|
"mean_token_accuracy": 0.0735650360584259,
|
|
"num_tokens": 193368.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.036783123016358,
|
|
"epoch": 0.008738967054094207,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.9113,
|
|
"mean_token_accuracy": 0.070536545291543,
|
|
"num_tokens": 202686.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 9.999727821350097,
|
|
"epoch": 0.009175915406798917,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.8114,
|
|
"mean_token_accuracy": 0.0759910672903061,
|
|
"num_tokens": 213237.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 9.960642242431641,
|
|
"epoch": 0.009612863759503626,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.7434,
|
|
"mean_token_accuracy": 0.07438907325267792,
|
|
"num_tokens": 222406.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.91720027923584,
|
|
"epoch": 0.010049812112208336,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.6931,
|
|
"mean_token_accuracy": 0.07097940742969513,
|
|
"num_tokens": 232139.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.805039215087891,
|
|
"epoch": 0.010486760464913047,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.6117,
|
|
"mean_token_accuracy": 0.06989408992230892,
|
|
"num_tokens": 242438.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.689086627960204,
|
|
"epoch": 0.010923708817617757,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.4953,
|
|
"mean_token_accuracy": 0.07219259589910507,
|
|
"num_tokens": 253082.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.538719367980956,
|
|
"epoch": 0.011360657170322468,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.4276,
|
|
"mean_token_accuracy": 0.07822968177497387,
|
|
"num_tokens": 264067.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.413427066802978,
|
|
"epoch": 0.011797605523027178,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.3678,
|
|
"mean_token_accuracy": 0.07066886723041535,
|
|
"num_tokens": 274571.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.260402202606201,
|
|
"epoch": 0.012234553875731888,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.2521,
|
|
"mean_token_accuracy": 0.07624184787273407,
|
|
"num_tokens": 284561.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.093957424163818,
|
|
"epoch": 0.012671502228436599,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.1356,
|
|
"mean_token_accuracy": 0.07842415869235993,
|
|
"num_tokens": 295366.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.952532768249512,
|
|
"epoch": 0.01310845058114131,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.2413,
|
|
"mean_token_accuracy": 0.072519838437438,
|
|
"num_tokens": 305423.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.831371021270751,
|
|
"epoch": 0.01354539893384602,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1022,
|
|
"mean_token_accuracy": 0.0731633011251688,
|
|
"num_tokens": 315182.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.752772331237793,
|
|
"epoch": 0.01398234728655073,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.0907,
|
|
"mean_token_accuracy": 0.07480457425117493,
|
|
"num_tokens": 324780.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.644503688812256,
|
|
"epoch": 0.01441929563925544,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.1188,
|
|
"mean_token_accuracy": 0.07407689988613128,
|
|
"num_tokens": 335104.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.571752071380615,
|
|
"epoch": 0.014856243991960151,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.0754,
|
|
"mean_token_accuracy": 0.07565453983843326,
|
|
"num_tokens": 345073.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.54010829925537,
|
|
"epoch": 0.015293192344664861,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.0773,
|
|
"mean_token_accuracy": 0.07010089345276356,
|
|
"num_tokens": 354342.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.52613639831543,
|
|
"epoch": 0.015730140697369572,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.9826,
|
|
"mean_token_accuracy": 0.07756052985787391,
|
|
"num_tokens": 364441.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.392733097076416,
|
|
"epoch": 0.01616708905007428,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.9982,
|
|
"mean_token_accuracy": 0.07280723676085472,
|
|
"num_tokens": 373918.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.41452865600586,
|
|
"epoch": 0.016604037402778993,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.0324,
|
|
"mean_token_accuracy": 0.0724909171462059,
|
|
"num_tokens": 383273.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.292540359497071,
|
|
"epoch": 0.0170409857554837,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.8917,
|
|
"mean_token_accuracy": 0.08331138044595718,
|
|
"num_tokens": 393262.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.423866748809814,
|
|
"epoch": 0.017477934108188414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.0188,
|
|
"mean_token_accuracy": 0.0748317264020443,
|
|
"num_tokens": 402389.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.355186462402344,
|
|
"epoch": 0.017914882460893122,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.9521,
|
|
"mean_token_accuracy": 0.07337616458535194,
|
|
"num_tokens": 412997.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.251720333099366,
|
|
"epoch": 0.018351830813597834,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.9753,
|
|
"mean_token_accuracy": 0.07370316870510578,
|
|
"num_tokens": 422222.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.27926950454712,
|
|
"epoch": 0.018788779166302543,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.9036,
|
|
"mean_token_accuracy": 0.07845620810985565,
|
|
"num_tokens": 432539.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.302949237823487,
|
|
"epoch": 0.019225727519007252,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.9171,
|
|
"mean_token_accuracy": 0.07200107723474503,
|
|
"num_tokens": 442311.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.195553016662597,
|
|
"epoch": 0.019662675871711964,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.8904,
|
|
"mean_token_accuracy": 0.07533022500574589,
|
|
"num_tokens": 452727.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.2304217338562,
|
|
"epoch": 0.020099624224416673,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.9264,
|
|
"mean_token_accuracy": 0.07583003640174865,
|
|
"num_tokens": 462461.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.261456871032715,
|
|
"epoch": 0.020536572577121385,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.9027,
|
|
"mean_token_accuracy": 0.07816779166460038,
|
|
"num_tokens": 472362.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.210902309417724,
|
|
"epoch": 0.020973520929826094,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.8976,
|
|
"mean_token_accuracy": 0.0767062995582819,
|
|
"num_tokens": 482718.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.280668449401855,
|
|
"epoch": 0.021410469282530806,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.8942,
|
|
"mean_token_accuracy": 0.0744877964258194,
|
|
"num_tokens": 492947.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.159860420227051,
|
|
"epoch": 0.021847417635235514,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.9426,
|
|
"mean_token_accuracy": 0.07315046004951001,
|
|
"num_tokens": 502957.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.233509922027588,
|
|
"epoch": 0.022284365987940227,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.888,
|
|
"mean_token_accuracy": 0.07607140243053437,
|
|
"num_tokens": 513220.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.254329681396484,
|
|
"epoch": 0.022721314340644935,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.8441,
|
|
"mean_token_accuracy": 0.07440531551837921,
|
|
"num_tokens": 523217.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.120617008209228,
|
|
"epoch": 0.023158262693349647,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.8656,
|
|
"mean_token_accuracy": 0.07392945140600204,
|
|
"num_tokens": 533789.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.175964164733887,
|
|
"epoch": 0.023595211046054356,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.8389,
|
|
"mean_token_accuracy": 0.08100497275590897,
|
|
"num_tokens": 544146.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.17584867477417,
|
|
"epoch": 0.02403215939875907,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.8824,
|
|
"mean_token_accuracy": 0.07800561562180519,
|
|
"num_tokens": 554215.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.092530584335327,
|
|
"epoch": 0.024469107751463777,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.8448,
|
|
"mean_token_accuracy": 0.07754362374544144,
|
|
"num_tokens": 564587.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.21709327697754,
|
|
"epoch": 0.024906056104168486,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.8946,
|
|
"mean_token_accuracy": 0.07792591154575348,
|
|
"num_tokens": 574819.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.139802265167237,
|
|
"epoch": 0.025343004456873198,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.8252,
|
|
"mean_token_accuracy": 0.07506528235971928,
|
|
"num_tokens": 585178.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.118964576721192,
|
|
"epoch": 0.025779952809577907,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.8049,
|
|
"mean_token_accuracy": 0.07798612490296364,
|
|
"num_tokens": 595086.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.090186500549317,
|
|
"epoch": 0.02621690116228262,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.8215,
|
|
"mean_token_accuracy": 0.08201636113226414,
|
|
"num_tokens": 604942.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.079523181915283,
|
|
"epoch": 0.026653849514987327,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.7878,
|
|
"mean_token_accuracy": 0.07864333167672158,
|
|
"num_tokens": 616082.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.156378364562988,
|
|
"epoch": 0.02709079786769204,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.818,
|
|
"mean_token_accuracy": 0.07984638400375843,
|
|
"num_tokens": 626375.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.012382888793946,
|
|
"epoch": 0.027527746220396748,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.7828,
|
|
"mean_token_accuracy": 0.07687741480767726,
|
|
"num_tokens": 637563.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.105079889297485,
|
|
"epoch": 0.02796469457310146,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.794,
|
|
"mean_token_accuracy": 0.0784915316849947,
|
|
"num_tokens": 647256.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.144533252716064,
|
|
"epoch": 0.02840164292580617,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.8405,
|
|
"mean_token_accuracy": 0.07891839221119881,
|
|
"num_tokens": 657247.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.161137771606445,
|
|
"epoch": 0.02883859127851088,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.7556,
|
|
"mean_token_accuracy": 0.0753303699195385,
|
|
"num_tokens": 667613.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.930547428131104,
|
|
"epoch": 0.02927553963121559,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.796,
|
|
"mean_token_accuracy": 0.07889659702777863,
|
|
"num_tokens": 678048.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.04266881942749,
|
|
"epoch": 0.029712487983920302,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.7839,
|
|
"mean_token_accuracy": 0.07976688966155052,
|
|
"num_tokens": 688468.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.041753911972046,
|
|
"epoch": 0.03014943633662501,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.7657,
|
|
"mean_token_accuracy": 0.08183549717068672,
|
|
"num_tokens": 699809.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.966469430923462,
|
|
"epoch": 0.030586384689329723,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.7193,
|
|
"mean_token_accuracy": 0.0835344910621643,
|
|
"num_tokens": 709227.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.117505311965942,
|
|
"epoch": 0.03102333304203443,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.8113,
|
|
"mean_token_accuracy": 0.0792868234217167,
|
|
"num_tokens": 720178.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.02713942527771,
|
|
"epoch": 0.031460281394739144,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.7451,
|
|
"mean_token_accuracy": 0.0808893047273159,
|
|
"num_tokens": 730514.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.955661630630493,
|
|
"epoch": 0.03189722974744385,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.7936,
|
|
"mean_token_accuracy": 0.07927311882376671,
|
|
"num_tokens": 741345.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.073381757736206,
|
|
"epoch": 0.03233417810014856,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.7194,
|
|
"mean_token_accuracy": 0.08433770835399627,
|
|
"num_tokens": 751163.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.95829062461853,
|
|
"epoch": 0.03277112645285327,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.7252,
|
|
"mean_token_accuracy": 0.07551483511924743,
|
|
"num_tokens": 762090.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.018740129470824,
|
|
"epoch": 0.033208074805557986,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.6853,
|
|
"mean_token_accuracy": 0.08602647930383682,
|
|
"num_tokens": 772049.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.922933340072632,
|
|
"epoch": 0.03364502315826269,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.6569,
|
|
"mean_token_accuracy": 0.08615999668836594,
|
|
"num_tokens": 781280.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.000065326690674,
|
|
"epoch": 0.0340819715109674,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.7359,
|
|
"mean_token_accuracy": 0.08202896118164063,
|
|
"num_tokens": 791642.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.94686861038208,
|
|
"epoch": 0.034518919863672115,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.7103,
|
|
"mean_token_accuracy": 0.07860004678368568,
|
|
"num_tokens": 801224.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.999029922485351,
|
|
"epoch": 0.03495586821637683,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.6424,
|
|
"mean_token_accuracy": 0.0833341408520937,
|
|
"num_tokens": 810727.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.085517978668213,
|
|
"epoch": 0.03539281656908153,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.7379,
|
|
"mean_token_accuracy": 0.08233671486377717,
|
|
"num_tokens": 819943.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.762646436691284,
|
|
"epoch": 0.035829764921786245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.6577,
|
|
"mean_token_accuracy": 0.08188907951116561,
|
|
"num_tokens": 829474.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.970741319656372,
|
|
"epoch": 0.03626671327449096,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.6379,
|
|
"mean_token_accuracy": 0.07744064256548881,
|
|
"num_tokens": 839288.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.942607641220093,
|
|
"epoch": 0.03670366162719567,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.6614,
|
|
"mean_token_accuracy": 0.08381943926215171,
|
|
"num_tokens": 850064.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.798444652557373,
|
|
"epoch": 0.037140609979900374,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.6415,
|
|
"mean_token_accuracy": 0.0831109531223774,
|
|
"num_tokens": 860732.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.909991359710693,
|
|
"epoch": 0.037577558332605086,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.6336,
|
|
"mean_token_accuracy": 0.08323059007525443,
|
|
"num_tokens": 870076.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.853689670562744,
|
|
"epoch": 0.0380145066853098,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.5262,
|
|
"mean_token_accuracy": 0.08503322303295135,
|
|
"num_tokens": 880201.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.877675151824951,
|
|
"epoch": 0.038451455038014504,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.5925,
|
|
"mean_token_accuracy": 0.08455978333950043,
|
|
"num_tokens": 890344.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.76024980545044,
|
|
"epoch": 0.038888403390719216,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.5838,
|
|
"mean_token_accuracy": 0.08586194440722465,
|
|
"num_tokens": 900443.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.874179077148438,
|
|
"epoch": 0.03932535174342393,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.6019,
|
|
"mean_token_accuracy": 0.08362102881073952,
|
|
"num_tokens": 910284.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.942639446258545,
|
|
"epoch": 0.03976230009612864,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.692,
|
|
"mean_token_accuracy": 0.08145863935351372,
|
|
"num_tokens": 920986.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.793898105621338,
|
|
"epoch": 0.040199248448833345,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.5795,
|
|
"mean_token_accuracy": 0.08823852688074112,
|
|
"num_tokens": 930481.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.896108341217041,
|
|
"epoch": 0.04063619680153806,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.615,
|
|
"mean_token_accuracy": 0.08752772808074952,
|
|
"num_tokens": 940554.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.816930770874023,
|
|
"epoch": 0.04107314515424277,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.5654,
|
|
"mean_token_accuracy": 0.08801438808441162,
|
|
"num_tokens": 950005.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.777540969848633,
|
|
"epoch": 0.04151009350694748,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.5509,
|
|
"mean_token_accuracy": 0.08131005018949508,
|
|
"num_tokens": 959414.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.822865295410156,
|
|
"epoch": 0.04194704185965219,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.5807,
|
|
"mean_token_accuracy": 0.08017202988266944,
|
|
"num_tokens": 969352.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.85607123374939,
|
|
"epoch": 0.0423839902123569,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.6151,
|
|
"mean_token_accuracy": 0.07956655099987983,
|
|
"num_tokens": 980294.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.760293769836426,
|
|
"epoch": 0.04282093856506161,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.4934,
|
|
"mean_token_accuracy": 0.08754161521792411,
|
|
"num_tokens": 990453.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.754083633422852,
|
|
"epoch": 0.04325788691776632,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.514,
|
|
"mean_token_accuracy": 0.09044907167553902,
|
|
"num_tokens": 1000509.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.716276216506958,
|
|
"epoch": 0.04369483527047103,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.6554,
|
|
"mean_token_accuracy": 0.07662305198609828,
|
|
"num_tokens": 1011747.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.786904191970825,
|
|
"epoch": 0.04413178362317574,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.5966,
|
|
"mean_token_accuracy": 0.08083347380161285,
|
|
"num_tokens": 1021511.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.863558530807495,
|
|
"epoch": 0.04456873197588045,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.6139,
|
|
"mean_token_accuracy": 0.08253132700920104,
|
|
"num_tokens": 1032116.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.755859327316284,
|
|
"epoch": 0.04500568032858516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.4897,
|
|
"mean_token_accuracy": 0.08958897739648819,
|
|
"num_tokens": 1041356.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.731158351898193,
|
|
"epoch": 0.04544262868128987,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.5513,
|
|
"mean_token_accuracy": 0.08268988244235516,
|
|
"num_tokens": 1051314.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.751654243469238,
|
|
"epoch": 0.04587957703399458,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.5319,
|
|
"mean_token_accuracy": 0.08553770706057548,
|
|
"num_tokens": 1060857.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.804953765869141,
|
|
"epoch": 0.046316525386699295,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.5423,
|
|
"mean_token_accuracy": 0.08373178914189339,
|
|
"num_tokens": 1071744.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.729137563705445,
|
|
"epoch": 0.046753473739404,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.5074,
|
|
"mean_token_accuracy": 0.0874439723789692,
|
|
"num_tokens": 1080777.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.7326695919036865,
|
|
"epoch": 0.04719042209210871,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.5089,
|
|
"mean_token_accuracy": 0.0891585111618042,
|
|
"num_tokens": 1090951.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.670050811767578,
|
|
"epoch": 0.047627370444813424,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.4552,
|
|
"mean_token_accuracy": 0.08354937732219696,
|
|
"num_tokens": 1101667.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.7255943775177,
|
|
"epoch": 0.04806431879751814,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.5694,
|
|
"mean_token_accuracy": 0.08456205204129219,
|
|
"num_tokens": 1112652.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.709576559066773,
|
|
"epoch": 0.04850126715022284,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.529,
|
|
"mean_token_accuracy": 0.08200532495975495,
|
|
"num_tokens": 1122518.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.815584325790406,
|
|
"epoch": 0.048938215502927554,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.5337,
|
|
"mean_token_accuracy": 0.08656449392437934,
|
|
"num_tokens": 1132867.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.730601501464844,
|
|
"epoch": 0.049375163855632266,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.6063,
|
|
"mean_token_accuracy": 0.08351293206214905,
|
|
"num_tokens": 1142524.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.762125158309937,
|
|
"epoch": 0.04981211220833697,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.466,
|
|
"mean_token_accuracy": 0.09219523333013058,
|
|
"num_tokens": 1152983.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.690439462661743,
|
|
"epoch": 0.050249060561041684,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.5518,
|
|
"mean_token_accuracy": 0.08294261172413826,
|
|
"num_tokens": 1164271.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.625344181060791,
|
|
"epoch": 0.050686008913746396,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.3901,
|
|
"mean_token_accuracy": 0.08981689289212227,
|
|
"num_tokens": 1173567.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.597426557540894,
|
|
"epoch": 0.05112295726645111,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.4494,
|
|
"mean_token_accuracy": 0.09101380854845047,
|
|
"num_tokens": 1183619.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.662474060058594,
|
|
"epoch": 0.05155990561915581,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.4014,
|
|
"mean_token_accuracy": 0.0849751003086567,
|
|
"num_tokens": 1193922.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.686445474624634,
|
|
"epoch": 0.051996853971860525,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.4905,
|
|
"mean_token_accuracy": 0.0850920021533966,
|
|
"num_tokens": 1203665.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.688158273696899,
|
|
"epoch": 0.05243380232456524,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.4868,
|
|
"mean_token_accuracy": 0.08693959787487984,
|
|
"num_tokens": 1214119.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.659633779525757,
|
|
"epoch": 0.05287075067726995,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.5142,
|
|
"mean_token_accuracy": 0.08122221603989602,
|
|
"num_tokens": 1225275.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.575573873519898,
|
|
"epoch": 0.053307699029974655,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.39,
|
|
"mean_token_accuracy": 0.08491945862770081,
|
|
"num_tokens": 1235199.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.622638702392578,
|
|
"epoch": 0.05374464738267937,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.4131,
|
|
"mean_token_accuracy": 0.08687365427613258,
|
|
"num_tokens": 1245648.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.542647027969361,
|
|
"epoch": 0.05418159573538408,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.3606,
|
|
"mean_token_accuracy": 0.09443019926548005,
|
|
"num_tokens": 1254793.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.674170923233032,
|
|
"epoch": 0.05461854408808879,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.4023,
|
|
"mean_token_accuracy": 0.09142766371369362,
|
|
"num_tokens": 1264429.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.4895281314849855,
|
|
"epoch": 0.055055492440793496,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.3853,
|
|
"mean_token_accuracy": 0.0873162291944027,
|
|
"num_tokens": 1274449.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.683523368835449,
|
|
"epoch": 0.05549244079349821,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.4964,
|
|
"mean_token_accuracy": 0.08166366070508957,
|
|
"num_tokens": 1284987.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.648572826385498,
|
|
"epoch": 0.05592938914620292,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.4905,
|
|
"mean_token_accuracy": 0.07985021024942399,
|
|
"num_tokens": 1295984.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.492455101013183,
|
|
"epoch": 0.056366337498907626,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.3794,
|
|
"mean_token_accuracy": 0.09080474004149437,
|
|
"num_tokens": 1305738.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.597794008255005,
|
|
"epoch": 0.05680328585161234,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.3331,
|
|
"mean_token_accuracy": 0.0831803061068058,
|
|
"num_tokens": 1315691.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.567058038711548,
|
|
"epoch": 0.05724023420431705,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.3392,
|
|
"mean_token_accuracy": 0.0938805028796196,
|
|
"num_tokens": 1326195.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.406193971633911,
|
|
"epoch": 0.05767718255702176,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.3802,
|
|
"mean_token_accuracy": 0.09240260273218155,
|
|
"num_tokens": 1336916.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.54069561958313,
|
|
"epoch": 0.05811413090972647,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.3984,
|
|
"mean_token_accuracy": 0.08775042369961739,
|
|
"num_tokens": 1347386.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.649399089813232,
|
|
"epoch": 0.05855107926243118,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.3597,
|
|
"mean_token_accuracy": 0.08884215950965882,
|
|
"num_tokens": 1357959.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.446434020996094,
|
|
"epoch": 0.05898802761513589,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.3605,
|
|
"mean_token_accuracy": 0.08795115426182747,
|
|
"num_tokens": 1368135.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.542385911941528,
|
|
"epoch": 0.059424975967840604,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.3913,
|
|
"mean_token_accuracy": 0.08776068612933159,
|
|
"num_tokens": 1378702.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.405993509292602,
|
|
"epoch": 0.05986192432054531,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.2451,
|
|
"mean_token_accuracy": 0.09290849268436432,
|
|
"num_tokens": 1387902.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.529328966140747,
|
|
"epoch": 0.06029887267325002,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.2709,
|
|
"mean_token_accuracy": 0.09545634016394615,
|
|
"num_tokens": 1397288.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.438186883926392,
|
|
"epoch": 0.060735821025954734,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.3202,
|
|
"mean_token_accuracy": 0.09044579640030861,
|
|
"num_tokens": 1407416.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.5576756477355955,
|
|
"epoch": 0.061172769378659446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.3774,
|
|
"mean_token_accuracy": 0.08624047338962555,
|
|
"num_tokens": 1417733.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.467697048187256,
|
|
"epoch": 0.06160971773136415,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.2659,
|
|
"mean_token_accuracy": 0.08791227973997592,
|
|
"num_tokens": 1426723.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.462012910842896,
|
|
"epoch": 0.06204666608406886,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.3369,
|
|
"mean_token_accuracy": 0.09189029186964034,
|
|
"num_tokens": 1437290.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.403400897979736,
|
|
"epoch": 0.062483614436773575,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.2678,
|
|
"mean_token_accuracy": 0.08849345222115516,
|
|
"num_tokens": 1446756.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.42365288734436,
|
|
"epoch": 0.06292056278947829,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.3374,
|
|
"mean_token_accuracy": 0.08893298208713532,
|
|
"num_tokens": 1457074.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.430225610733032,
|
|
"epoch": 0.06335751114218299,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.3969,
|
|
"mean_token_accuracy": 0.08372474275529385,
|
|
"num_tokens": 1467785.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.446598958969116,
|
|
"epoch": 0.0637944594948877,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.285,
|
|
"mean_token_accuracy": 0.09203022196888924,
|
|
"num_tokens": 1477532.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.365743780136109,
|
|
"epoch": 0.06423140784759242,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.2159,
|
|
"mean_token_accuracy": 0.09424635395407677,
|
|
"num_tokens": 1487102.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.39603099822998,
|
|
"epoch": 0.06466835620029712,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.3035,
|
|
"mean_token_accuracy": 0.08960460349917412,
|
|
"num_tokens": 1497459.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.429128408432007,
|
|
"epoch": 0.06510530455300184,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.295,
|
|
"mean_token_accuracy": 0.08902842849493027,
|
|
"num_tokens": 1508756.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.3875891208648685,
|
|
"epoch": 0.06554225290570655,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.204,
|
|
"mean_token_accuracy": 0.09589074179530144,
|
|
"num_tokens": 1518735.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.386076498031616,
|
|
"epoch": 0.06597920125841125,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.2494,
|
|
"mean_token_accuracy": 0.09206888377666474,
|
|
"num_tokens": 1528632.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.327648305892945,
|
|
"epoch": 0.06641614961111597,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.2499,
|
|
"mean_token_accuracy": 0.08991473093628884,
|
|
"num_tokens": 1538180.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.369539976119995,
|
|
"epoch": 0.06685309796382068,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.2692,
|
|
"mean_token_accuracy": 0.09155759960412979,
|
|
"num_tokens": 1547788.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.339311122894287,
|
|
"epoch": 0.06729004631652538,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.2099,
|
|
"mean_token_accuracy": 0.09492280036211014,
|
|
"num_tokens": 1558008.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.356014108657837,
|
|
"epoch": 0.0677269946692301,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.2706,
|
|
"mean_token_accuracy": 0.09146112427115441,
|
|
"num_tokens": 1567728.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.376091766357422,
|
|
"epoch": 0.0681639430219348,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.2229,
|
|
"mean_token_accuracy": 0.0900360755622387,
|
|
"num_tokens": 1578488.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.3270101070404055,
|
|
"epoch": 0.06860089137463951,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.1983,
|
|
"mean_token_accuracy": 0.09384592846035958,
|
|
"num_tokens": 1588070.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.3354650974273685,
|
|
"epoch": 0.06903783972734423,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.2717,
|
|
"mean_token_accuracy": 0.09093666598200797,
|
|
"num_tokens": 1598572.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.418518686294556,
|
|
"epoch": 0.06947478808004894,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.2727,
|
|
"mean_token_accuracy": 0.08963424041867256,
|
|
"num_tokens": 1607982.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.34418568611145,
|
|
"epoch": 0.06991173643275365,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.287,
|
|
"mean_token_accuracy": 0.09368083029985427,
|
|
"num_tokens": 1618785.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.331365442276001,
|
|
"epoch": 0.07034868478545836,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.1991,
|
|
"mean_token_accuracy": 0.09436822384595871,
|
|
"num_tokens": 1627988.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.347531366348266,
|
|
"epoch": 0.07078563313816306,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.2996,
|
|
"mean_token_accuracy": 0.08484280183911323,
|
|
"num_tokens": 1638024.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.368394899368286,
|
|
"epoch": 0.07122258149086778,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.2934,
|
|
"mean_token_accuracy": 0.08453431576490403,
|
|
"num_tokens": 1649215.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.250621223449707,
|
|
"epoch": 0.07165952984357249,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.1812,
|
|
"mean_token_accuracy": 0.09315369427204132,
|
|
"num_tokens": 1659198.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.30466251373291,
|
|
"epoch": 0.0720964781962772,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.2168,
|
|
"mean_token_accuracy": 0.08589582666754722,
|
|
"num_tokens": 1668972.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.230190420150757,
|
|
"epoch": 0.07253342654898191,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.2035,
|
|
"mean_token_accuracy": 0.09499170146882534,
|
|
"num_tokens": 1679807.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.315043592453003,
|
|
"epoch": 0.07297037490168662,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.2514,
|
|
"mean_token_accuracy": 0.08835556209087372,
|
|
"num_tokens": 1690567.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.1730207920074465,
|
|
"epoch": 0.07340732325439134,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.1465,
|
|
"mean_token_accuracy": 0.09503189548850059,
|
|
"num_tokens": 1700939.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.252574443817139,
|
|
"epoch": 0.07384427160709604,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.1955,
|
|
"mean_token_accuracy": 0.09737142100930214,
|
|
"num_tokens": 1711181.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.33465609550476,
|
|
"epoch": 0.07428121995980075,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.2235,
|
|
"mean_token_accuracy": 0.08807378485798836,
|
|
"num_tokens": 1721392.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.280315160751343,
|
|
"epoch": 0.07471816831250547,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.1462,
|
|
"mean_token_accuracy": 0.09444593712687492,
|
|
"num_tokens": 1731942.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.246977376937866,
|
|
"epoch": 0.07515511666521017,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.2516,
|
|
"mean_token_accuracy": 0.09143168479204178,
|
|
"num_tokens": 1743409.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.194182825088501,
|
|
"epoch": 0.07559206501791488,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.1375,
|
|
"mean_token_accuracy": 0.09851979911327362,
|
|
"num_tokens": 1753425.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.228073787689209,
|
|
"epoch": 0.0760290133706196,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.1724,
|
|
"mean_token_accuracy": 0.08897863328456879,
|
|
"num_tokens": 1762722.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.394821119308472,
|
|
"epoch": 0.0764659617233243,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.2404,
|
|
"mean_token_accuracy": 0.0846147008240223,
|
|
"num_tokens": 1771895.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.15571780204773,
|
|
"epoch": 0.07690291007602901,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.1449,
|
|
"mean_token_accuracy": 0.09327926933765411,
|
|
"num_tokens": 1782175.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.320403099060059,
|
|
"epoch": 0.07733985842873373,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.1938,
|
|
"mean_token_accuracy": 0.09331970289349556,
|
|
"num_tokens": 1792409.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.294836235046387,
|
|
"epoch": 0.07777680678143843,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.2449,
|
|
"mean_token_accuracy": 0.08916250318288803,
|
|
"num_tokens": 1802721.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.145002126693726,
|
|
"epoch": 0.07821375513414315,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.0706,
|
|
"mean_token_accuracy": 0.09213897436857224,
|
|
"num_tokens": 1812064.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.291088485717774,
|
|
"epoch": 0.07865070348684786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.1945,
|
|
"mean_token_accuracy": 0.08576769083738327,
|
|
"num_tokens": 1822284.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.199422168731689,
|
|
"epoch": 0.07908765183955256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.0905,
|
|
"mean_token_accuracy": 0.09272913187742234,
|
|
"num_tokens": 1832150.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.295376396179199,
|
|
"epoch": 0.07952460019225728,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.2072,
|
|
"mean_token_accuracy": 0.08950737938284874,
|
|
"num_tokens": 1842870.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.063530540466308,
|
|
"epoch": 0.07996154854496199,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.0461,
|
|
"mean_token_accuracy": 0.09950183033943176,
|
|
"num_tokens": 1852771.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.172847270965576,
|
|
"epoch": 0.08039849689766669,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.169,
|
|
"mean_token_accuracy": 0.09458636716008187,
|
|
"num_tokens": 1863095.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.164995765686035,
|
|
"epoch": 0.08083544525037141,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.1697,
|
|
"mean_token_accuracy": 0.09454121589660644,
|
|
"num_tokens": 1873060.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.242373037338257,
|
|
"epoch": 0.08127239360307612,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.0998,
|
|
"mean_token_accuracy": 0.09765185564756393,
|
|
"num_tokens": 1882574.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.123794221878052,
|
|
"epoch": 0.08170934195578082,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.1642,
|
|
"mean_token_accuracy": 0.09597432464361191,
|
|
"num_tokens": 1892227.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.194331502914428,
|
|
"epoch": 0.08214629030848554,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.1898,
|
|
"mean_token_accuracy": 0.0918419398367405,
|
|
"num_tokens": 1902868.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.1636861801147464,
|
|
"epoch": 0.08258323866119024,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.1298,
|
|
"mean_token_accuracy": 0.09083555936813355,
|
|
"num_tokens": 1912781.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.1555884838104244,
|
|
"epoch": 0.08302018701389496,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.1202,
|
|
"mean_token_accuracy": 0.09932551309466361,
|
|
"num_tokens": 1923638.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.204519844055175,
|
|
"epoch": 0.08345713536659967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.0845,
|
|
"mean_token_accuracy": 0.0983235090970993,
|
|
"num_tokens": 1933498.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.0537872314453125,
|
|
"epoch": 0.08389408371930437,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.1033,
|
|
"mean_token_accuracy": 0.09563426300883293,
|
|
"num_tokens": 1943798.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.188605308532715,
|
|
"epoch": 0.0843310320720091,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.14,
|
|
"mean_token_accuracy": 0.09312030673027039,
|
|
"num_tokens": 1954235.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.173063611984253,
|
|
"epoch": 0.0847679804247138,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.1231,
|
|
"mean_token_accuracy": 0.09110933616757393,
|
|
"num_tokens": 1964421.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.087044048309326,
|
|
"epoch": 0.0852049287774185,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.1059,
|
|
"mean_token_accuracy": 0.09609248787164688,
|
|
"num_tokens": 1975862.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.187036323547363,
|
|
"epoch": 0.08564187713012322,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.1055,
|
|
"mean_token_accuracy": 0.09382803216576577,
|
|
"num_tokens": 1985758.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.038282966613769,
|
|
"epoch": 0.08607882548282793,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.079,
|
|
"mean_token_accuracy": 0.0931548923254013,
|
|
"num_tokens": 1996904.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.26365966796875,
|
|
"epoch": 0.08651577383553263,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.1611,
|
|
"mean_token_accuracy": 0.09324508160352707,
|
|
"num_tokens": 2006114.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.074654531478882,
|
|
"epoch": 0.08695272218823735,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.0961,
|
|
"mean_token_accuracy": 0.10224229097366333,
|
|
"num_tokens": 2016349.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.075801420211792,
|
|
"epoch": 0.08738967054094206,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.0411,
|
|
"mean_token_accuracy": 0.09501954540610313,
|
|
"num_tokens": 2026701.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.036496257781982,
|
|
"epoch": 0.08782661889364678,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999999986190023,
|
|
"loss": 7.0382,
|
|
"mean_token_accuracy": 0.09739973098039627,
|
|
"num_tokens": 2036950.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.158604335784912,
|
|
"epoch": 0.08826356724635148,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999930086991,
|
|
"loss": 7.0451,
|
|
"mean_token_accuracy": 0.09806649461388588,
|
|
"num_tokens": 2047655.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.032751893997192,
|
|
"epoch": 0.08870051559905619,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499999983082778,
|
|
"loss": 7.0286,
|
|
"mean_token_accuracy": 0.0988488368690014,
|
|
"num_tokens": 2056800.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.048862934112549,
|
|
"epoch": 0.0891374639517609,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999999688412394,
|
|
"loss": 7.0621,
|
|
"mean_token_accuracy": 0.09844208061695099,
|
|
"num_tokens": 2066862.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.1450450897216795,
|
|
"epoch": 0.08957441230446561,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999999502840836,
|
|
"loss": 7.0754,
|
|
"mean_token_accuracy": 0.10040949657559395,
|
|
"num_tokens": 2076585.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.057808780670166,
|
|
"epoch": 0.09001136065717032,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999999274113107,
|
|
"loss": 7.1469,
|
|
"mean_token_accuracy": 0.09293891340494156,
|
|
"num_tokens": 2087768.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.1115809917449955,
|
|
"epoch": 0.09044830900987504,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999999002229214,
|
|
"loss": 7.0581,
|
|
"mean_token_accuracy": 0.09576725885272026,
|
|
"num_tokens": 2097027.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.053522729873658,
|
|
"epoch": 0.09088525736257974,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999998687189161,
|
|
"loss": 6.9899,
|
|
"mean_token_accuracy": 0.0992590568959713,
|
|
"num_tokens": 2107055.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.008532524108887,
|
|
"epoch": 0.09132220571528446,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999998328992954,
|
|
"loss": 6.9253,
|
|
"mean_token_accuracy": 0.1000043123960495,
|
|
"num_tokens": 2116771.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.04312653541565,
|
|
"epoch": 0.09175915406798917,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049999979276406,
|
|
"loss": 7.055,
|
|
"mean_token_accuracy": 0.10065520852804184,
|
|
"num_tokens": 2126881.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.017210865020752,
|
|
"epoch": 0.09219610242069387,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999997483132108,
|
|
"loss": 7.0334,
|
|
"mean_token_accuracy": 0.0969104826450348,
|
|
"num_tokens": 2136964.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.135955476760865,
|
|
"epoch": 0.09263305077339859,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999996995467483,
|
|
"loss": 7.077,
|
|
"mean_token_accuracy": 0.09480597153306007,
|
|
"num_tokens": 2147263.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.98509464263916,
|
|
"epoch": 0.0930699991261033,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999996464646738,
|
|
"loss": 7.0904,
|
|
"mean_token_accuracy": 0.09320821538567543,
|
|
"num_tokens": 2157474.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.075286531448365,
|
|
"epoch": 0.093506947478808,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999995890669882,
|
|
"loss": 7.0241,
|
|
"mean_token_accuracy": 0.09614943489432334,
|
|
"num_tokens": 2167701.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.915413427352905,
|
|
"epoch": 0.09394389583151272,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999995273536925,
|
|
"loss": 6.998,
|
|
"mean_token_accuracy": 0.1028121143579483,
|
|
"num_tokens": 2178581.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.083644104003906,
|
|
"epoch": 0.09438084418421742,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499999461324788,
|
|
"loss": 6.988,
|
|
"mean_token_accuracy": 0.09867269322276115,
|
|
"num_tokens": 2189529.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.977810955047607,
|
|
"epoch": 0.09481779253692213,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999993909802759,
|
|
"loss": 7.0636,
|
|
"mean_token_accuracy": 0.09306210651993752,
|
|
"num_tokens": 2199805.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.00365309715271,
|
|
"epoch": 0.09525474088962685,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999993163201577,
|
|
"loss": 7.0044,
|
|
"mean_token_accuracy": 0.09724057838320732,
|
|
"num_tokens": 2210108.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.164579772949219,
|
|
"epoch": 0.09569168924233155,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999992373444347,
|
|
"loss": 7.0016,
|
|
"mean_token_accuracy": 0.09872443079948426,
|
|
"num_tokens": 2220325.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.893038415908814,
|
|
"epoch": 0.09612863759503627,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999991540531084,
|
|
"loss": 6.9957,
|
|
"mean_token_accuracy": 0.0961542434990406,
|
|
"num_tokens": 2230521.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.113245630264283,
|
|
"epoch": 0.09656558594774098,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999990664461804,
|
|
"loss": 7.0346,
|
|
"mean_token_accuracy": 0.0963917538523674,
|
|
"num_tokens": 2240372.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.000665855407715,
|
|
"epoch": 0.09700253430044568,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999989745236524,
|
|
"loss": 6.9949,
|
|
"mean_token_accuracy": 0.10437084212899209,
|
|
"num_tokens": 2250522.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.946602296829224,
|
|
"epoch": 0.0974394826531504,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999988782855261,
|
|
"loss": 6.9321,
|
|
"mean_token_accuracy": 0.09969532936811447,
|
|
"num_tokens": 2260142.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.026501417160034,
|
|
"epoch": 0.09787643100585511,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999987777318035,
|
|
"loss": 6.9769,
|
|
"mean_token_accuracy": 0.09623479098081589,
|
|
"num_tokens": 2270372.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.853050279617309,
|
|
"epoch": 0.09831337935855981,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999986728624865,
|
|
"loss": 6.8943,
|
|
"mean_token_accuracy": 0.10797081291675567,
|
|
"num_tokens": 2280517.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.0577069282531735,
|
|
"epoch": 0.09875032771126453,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499998563677577,
|
|
"loss": 7.001,
|
|
"mean_token_accuracy": 0.09663023054599762,
|
|
"num_tokens": 2290778.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.018427753448487,
|
|
"epoch": 0.09918727606396924,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999984501770771,
|
|
"loss": 7.0469,
|
|
"mean_token_accuracy": 0.09329727813601493,
|
|
"num_tokens": 2301692.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.9677423477172855,
|
|
"epoch": 0.09962422441667394,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999983323609891,
|
|
"loss": 6.9154,
|
|
"mean_token_accuracy": 0.10333282649517059,
|
|
"num_tokens": 2312759.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.9618792057037355,
|
|
"epoch": 0.10006117276937866,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999982102293153,
|
|
"loss": 6.902,
|
|
"mean_token_accuracy": 0.10509304627776146,
|
|
"num_tokens": 2322016.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.956529331207276,
|
|
"epoch": 0.10049812112208337,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999980837820578,
|
|
"loss": 6.9316,
|
|
"mean_token_accuracy": 0.10547636151313781,
|
|
"num_tokens": 2332476.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.9808799743652346,
|
|
"epoch": 0.10093506947478809,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999979530192192,
|
|
"loss": 6.9422,
|
|
"mean_token_accuracy": 0.09846181347966194,
|
|
"num_tokens": 2342914.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.8698526382446286,
|
|
"epoch": 0.10137201782749279,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999978179408019,
|
|
"loss": 7.0014,
|
|
"mean_token_accuracy": 0.09670989662408828,
|
|
"num_tokens": 2353381.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.047989082336426,
|
|
"epoch": 0.1018089661801975,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999976785468085,
|
|
"loss": 6.9778,
|
|
"mean_token_accuracy": 0.10065887346863747,
|
|
"num_tokens": 2364207.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.905608797073365,
|
|
"epoch": 0.10224591453290222,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999975348372418,
|
|
"loss": 6.9048,
|
|
"mean_token_accuracy": 0.10400475561618805,
|
|
"num_tokens": 2374985.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.932749795913696,
|
|
"epoch": 0.10268286288560692,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999973868121044,
|
|
"loss": 6.9768,
|
|
"mean_token_accuracy": 0.10295218899846077,
|
|
"num_tokens": 2385684.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.058686876296997,
|
|
"epoch": 0.10311981123831163,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999972344713994,
|
|
"loss": 6.9109,
|
|
"mean_token_accuracy": 0.10049357637763023,
|
|
"num_tokens": 2395177.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.822031545639038,
|
|
"epoch": 0.10355675959101635,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999970778151295,
|
|
"loss": 6.9316,
|
|
"mean_token_accuracy": 0.10832231491804123,
|
|
"num_tokens": 2405154.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.980653572082519,
|
|
"epoch": 0.10399370794372105,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999969168432976,
|
|
"loss": 6.9107,
|
|
"mean_token_accuracy": 0.1029654860496521,
|
|
"num_tokens": 2415818.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.871922588348388,
|
|
"epoch": 0.10443065629642576,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999967515559071,
|
|
"loss": 6.8791,
|
|
"mean_token_accuracy": 0.1029189296066761,
|
|
"num_tokens": 2425072.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.889013576507568,
|
|
"epoch": 0.10486760464913047,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499996581952961,
|
|
"loss": 6.9411,
|
|
"mean_token_accuracy": 0.10594153180718421,
|
|
"num_tokens": 2435055.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.952979373931885,
|
|
"epoch": 0.10530455300183518,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999964080344625,
|
|
"loss": 6.8394,
|
|
"mean_token_accuracy": 0.10662424638867378,
|
|
"num_tokens": 2444434.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.836973428726196,
|
|
"epoch": 0.1057415013545399,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999962298004151,
|
|
"loss": 6.8662,
|
|
"mean_token_accuracy": 0.10213011056184769,
|
|
"num_tokens": 2453860.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.965761756896972,
|
|
"epoch": 0.1061784497072446,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 6.985,
|
|
"mean_token_accuracy": 0.10095644146203994,
|
|
"num_tokens": 2464235.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.952071714401245,
|
|
"epoch": 0.10661539805994931,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999958603856869,
|
|
"loss": 6.8871,
|
|
"mean_token_accuracy": 0.10538947805762292,
|
|
"num_tokens": 2474561.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.8396659851074215,
|
|
"epoch": 0.10705234641265403,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999956692050132,
|
|
"loss": 6.8777,
|
|
"mean_token_accuracy": 0.10440976917743683,
|
|
"num_tokens": 2484574.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.999291944503784,
|
|
"epoch": 0.10748929476535873,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999954737088048,
|
|
"loss": 6.8676,
|
|
"mean_token_accuracy": 0.110504861921072,
|
|
"num_tokens": 2494146.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.806334829330444,
|
|
"epoch": 0.10792624311806344,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999952738970652,
|
|
"loss": 6.9511,
|
|
"mean_token_accuracy": 0.10179314985871316,
|
|
"num_tokens": 2504157.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.896573305130005,
|
|
"epoch": 0.10836319147076816,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999950697697983,
|
|
"loss": 6.8821,
|
|
"mean_token_accuracy": 0.10277172699570655,
|
|
"num_tokens": 2512979.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.921594572067261,
|
|
"epoch": 0.10880013982347286,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999948613270081,
|
|
"loss": 6.9518,
|
|
"mean_token_accuracy": 0.09981353655457496,
|
|
"num_tokens": 2523202.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.904537105560303,
|
|
"epoch": 0.10923708817617758,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999946485686987,
|
|
"loss": 6.8928,
|
|
"mean_token_accuracy": 0.1013514257967472,
|
|
"num_tokens": 2532790.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.879450464248658,
|
|
"epoch": 0.10967403652888229,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499994431494874,
|
|
"loss": 6.8721,
|
|
"mean_token_accuracy": 0.10644448697566986,
|
|
"num_tokens": 2542337.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.82066798210144,
|
|
"epoch": 0.11011098488158699,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999942101055381,
|
|
"loss": 6.8112,
|
|
"mean_token_accuracy": 0.11042425706982613,
|
|
"num_tokens": 2552762.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.91101107597351,
|
|
"epoch": 0.11054793323429171,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999939844006955,
|
|
"loss": 6.8508,
|
|
"mean_token_accuracy": 0.10850365459918976,
|
|
"num_tokens": 2563261.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.881007385253906,
|
|
"epoch": 0.11098488158699642,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999937543803503,
|
|
"loss": 6.8283,
|
|
"mean_token_accuracy": 0.11036632806062699,
|
|
"num_tokens": 2573089.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.852328968048096,
|
|
"epoch": 0.11142182993970112,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499993520044507,
|
|
"loss": 6.9193,
|
|
"mean_token_accuracy": 0.09846171364188194,
|
|
"num_tokens": 2584358.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.966355800628662,
|
|
"epoch": 0.11185877829240584,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999932813931702,
|
|
"loss": 6.8869,
|
|
"mean_token_accuracy": 0.10662171319127083,
|
|
"num_tokens": 2594981.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.8475768089294435,
|
|
"epoch": 0.11229572664511055,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999930384263441,
|
|
"loss": 6.8897,
|
|
"mean_token_accuracy": 0.10364025831222534,
|
|
"num_tokens": 2603508.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.908575344085693,
|
|
"epoch": 0.11273267499781525,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499992791144034,
|
|
"loss": 6.8442,
|
|
"mean_token_accuracy": 0.10457368195056915,
|
|
"num_tokens": 2613666.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.943562364578247,
|
|
"epoch": 0.11316962335051997,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999925395462439,
|
|
"loss": 6.9156,
|
|
"mean_token_accuracy": 0.10008556246757508,
|
|
"num_tokens": 2624441.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.885890769958496,
|
|
"epoch": 0.11360657170322468,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999922836329793,
|
|
"loss": 6.8662,
|
|
"mean_token_accuracy": 0.10351174920797349,
|
|
"num_tokens": 2635261.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.785940265655517,
|
|
"epoch": 0.1140435200559294,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999920234042446,
|
|
"loss": 6.8386,
|
|
"mean_token_accuracy": 0.10835616141557694,
|
|
"num_tokens": 2645493.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.885877275466919,
|
|
"epoch": 0.1144804684086341,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999917588600451,
|
|
"loss": 6.789,
|
|
"mean_token_accuracy": 0.10901109129190445,
|
|
"num_tokens": 2655430.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.838509273529053,
|
|
"epoch": 0.1149174167613388,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999914900003857,
|
|
"loss": 6.8596,
|
|
"mean_token_accuracy": 0.10467283949255943,
|
|
"num_tokens": 2665675.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.920448350906372,
|
|
"epoch": 0.11535436511404352,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999912168252717,
|
|
"loss": 6.8163,
|
|
"mean_token_accuracy": 0.10676529109477997,
|
|
"num_tokens": 2675962.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.824034214019775,
|
|
"epoch": 0.11579131346674823,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999909393347083,
|
|
"loss": 6.8647,
|
|
"mean_token_accuracy": 0.10482599660754204,
|
|
"num_tokens": 2687015.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.845885992050171,
|
|
"epoch": 0.11622826181945294,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999906575287006,
|
|
"loss": 6.9197,
|
|
"mean_token_accuracy": 0.0967514120042324,
|
|
"num_tokens": 2698065.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.878113698959351,
|
|
"epoch": 0.11666521017215765,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999903714072544,
|
|
"loss": 6.7906,
|
|
"mean_token_accuracy": 0.11809995025396347,
|
|
"num_tokens": 2709046.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.882908725738526,
|
|
"epoch": 0.11710215852486236,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999900809703749,
|
|
"loss": 6.883,
|
|
"mean_token_accuracy": 0.10379704162478447,
|
|
"num_tokens": 2719705.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.807536888122558,
|
|
"epoch": 0.11753910687756706,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004999897862180678,
|
|
"loss": 6.7552,
|
|
"mean_token_accuracy": 0.11392875537276267,
|
|
"num_tokens": 2729556.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.787845277786255,
|
|
"epoch": 0.11797605523027178,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999894871503386,
|
|
"loss": 6.8665,
|
|
"mean_token_accuracy": 0.10998239666223526,
|
|
"num_tokens": 2741144.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.9081967830657955,
|
|
"epoch": 0.11841300358297649,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999891837671932,
|
|
"loss": 6.7691,
|
|
"mean_token_accuracy": 0.10925441533327103,
|
|
"num_tokens": 2751384.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.789922571182251,
|
|
"epoch": 0.11884995193568121,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999888760686375,
|
|
"loss": 6.8099,
|
|
"mean_token_accuracy": 0.10559153854846955,
|
|
"num_tokens": 2761044.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.742934608459473,
|
|
"epoch": 0.11928690028838591,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499988564054677,
|
|
"loss": 6.7547,
|
|
"mean_token_accuracy": 0.10845592692494392,
|
|
"num_tokens": 2770946.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.923913621902466,
|
|
"epoch": 0.11972384864109062,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999882477253182,
|
|
"loss": 6.8218,
|
|
"mean_token_accuracy": 0.10306366384029389,
|
|
"num_tokens": 2781247.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.7561554431915285,
|
|
"epoch": 0.12016079699379534,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999879270805667,
|
|
"loss": 6.6709,
|
|
"mean_token_accuracy": 0.11467958092689515,
|
|
"num_tokens": 2792078.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.782488059997559,
|
|
"epoch": 0.12059774534650004,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999876021204291,
|
|
"loss": 6.7598,
|
|
"mean_token_accuracy": 0.11112385168671608,
|
|
"num_tokens": 2802458.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.8228302001953125,
|
|
"epoch": 0.12103469369920475,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999872728449112,
|
|
"loss": 6.909,
|
|
"mean_token_accuracy": 0.10087578147649764,
|
|
"num_tokens": 2813352.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.8556358337402346,
|
|
"epoch": 0.12147164205190947,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999869392540195,
|
|
"loss": 6.7914,
|
|
"mean_token_accuracy": 0.10912273600697517,
|
|
"num_tokens": 2822954.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.758626174926758,
|
|
"epoch": 0.12190859040461417,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999866013477605,
|
|
"loss": 6.811,
|
|
"mean_token_accuracy": 0.10802412927150726,
|
|
"num_tokens": 2833375.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.806664562225341,
|
|
"epoch": 0.12234553875731889,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999862591261407,
|
|
"loss": 6.7713,
|
|
"mean_token_accuracy": 0.10752915516495705,
|
|
"num_tokens": 2843103.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.839266633987426,
|
|
"epoch": 0.1227824871100236,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999859125891664,
|
|
"loss": 6.8285,
|
|
"mean_token_accuracy": 0.10644137039780617,
|
|
"num_tokens": 2853801.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.855780410766601,
|
|
"epoch": 0.1232194354627283,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999855617368445,
|
|
"loss": 6.8144,
|
|
"mean_token_accuracy": 0.10442313924431801,
|
|
"num_tokens": 2863851.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.725363159179688,
|
|
"epoch": 0.12365638381543302,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999852065691816,
|
|
"loss": 6.7627,
|
|
"mean_token_accuracy": 0.10936231687664985,
|
|
"num_tokens": 2875073.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.893968534469605,
|
|
"epoch": 0.12409333216813773,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999848470861846,
|
|
"loss": 6.7854,
|
|
"mean_token_accuracy": 0.10944370701909065,
|
|
"num_tokens": 2885676.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.8066630363464355,
|
|
"epoch": 0.12453028052084243,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999844832878602,
|
|
"loss": 6.7683,
|
|
"mean_token_accuracy": 0.11356849074363709,
|
|
"num_tokens": 2896663.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.7106787204742435,
|
|
"epoch": 0.12496722887354715,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999841151742156,
|
|
"loss": 6.7929,
|
|
"mean_token_accuracy": 0.10626860707998276,
|
|
"num_tokens": 2907555.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.88362135887146,
|
|
"epoch": 0.12540417722625186,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999837427452578,
|
|
"loss": 6.7858,
|
|
"mean_token_accuracy": 0.10847901776432992,
|
|
"num_tokens": 2917173.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.720801258087159,
|
|
"epoch": 0.12584112557895658,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499983366000994,
|
|
"loss": 6.7811,
|
|
"mean_token_accuracy": 0.1066952884197235,
|
|
"num_tokens": 2928268.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.832601022720337,
|
|
"epoch": 0.12627807393166127,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999829849414312,
|
|
"loss": 6.725,
|
|
"mean_token_accuracy": 0.11428027451038361,
|
|
"num_tokens": 2938203.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.6934897899627686,
|
|
"epoch": 0.12671502228436599,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499982599566577,
|
|
"loss": 6.764,
|
|
"mean_token_accuracy": 0.11221247315406799,
|
|
"num_tokens": 2948094.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.872226905822754,
|
|
"epoch": 0.1271519706370707,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999822098764385,
|
|
"loss": 6.7674,
|
|
"mean_token_accuracy": 0.11034838110208511,
|
|
"num_tokens": 2957865.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.716366529464722,
|
|
"epoch": 0.1275889189897754,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999818158710234,
|
|
"loss": 6.6692,
|
|
"mean_token_accuracy": 0.11622118279337883,
|
|
"num_tokens": 2967880.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.719323587417603,
|
|
"epoch": 0.12802586734248012,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999814175503392,
|
|
"loss": 6.7614,
|
|
"mean_token_accuracy": 0.11026630774140359,
|
|
"num_tokens": 2979537.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.794031620025635,
|
|
"epoch": 0.12846281569518483,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999810149143935,
|
|
"loss": 6.7243,
|
|
"mean_token_accuracy": 0.10677018910646438,
|
|
"num_tokens": 2989700.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.648648405075074,
|
|
"epoch": 0.12889976404788953,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499980607963194,
|
|
"loss": 6.7292,
|
|
"mean_token_accuracy": 0.11203910410404205,
|
|
"num_tokens": 2999141.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.8095193862915036,
|
|
"epoch": 0.12933671240059424,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999801966967486,
|
|
"loss": 6.6825,
|
|
"mean_token_accuracy": 0.11426105126738548,
|
|
"num_tokens": 3008259.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.771524477005005,
|
|
"epoch": 0.12977366075329896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999797811150652,
|
|
"loss": 6.7414,
|
|
"mean_token_accuracy": 0.10887274071574211,
|
|
"num_tokens": 3018281.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.8037293434143065,
|
|
"epoch": 0.13021060910600368,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999793612181516,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.1142962783575058,
|
|
"num_tokens": 3029062.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.670297622680664,
|
|
"epoch": 0.13064755745870837,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999789370060161,
|
|
"loss": 6.7104,
|
|
"mean_token_accuracy": 0.1160611629486084,
|
|
"num_tokens": 3038142.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.867388343811035,
|
|
"epoch": 0.1310845058114131,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999785084786667,
|
|
"loss": 6.8046,
|
|
"mean_token_accuracy": 0.10011466220021248,
|
|
"num_tokens": 3049123.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.710518217086792,
|
|
"epoch": 0.1315214541641178,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999780756361114,
|
|
"loss": 6.7168,
|
|
"mean_token_accuracy": 0.10940457209944725,
|
|
"num_tokens": 3059031.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.76721339225769,
|
|
"epoch": 0.1319584025168225,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999776384783589,
|
|
"loss": 6.7418,
|
|
"mean_token_accuracy": 0.11014442816376686,
|
|
"num_tokens": 3068830.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.657623338699341,
|
|
"epoch": 0.13239535086952722,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999771970054174,
|
|
"loss": 6.7262,
|
|
"mean_token_accuracy": 0.11154688596725464,
|
|
"num_tokens": 3080124.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.7857428073883055,
|
|
"epoch": 0.13283229922223194,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999767512172953,
|
|
"loss": 6.7318,
|
|
"mean_token_accuracy": 0.10622003003954887,
|
|
"num_tokens": 3089607.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.769694852828979,
|
|
"epoch": 0.13326924757493663,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999763011140013,
|
|
"loss": 6.8108,
|
|
"mean_token_accuracy": 0.10131187736988068,
|
|
"num_tokens": 3099363.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.8420090675354,
|
|
"epoch": 0.13370619592764135,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999758466955439,
|
|
"loss": 6.7243,
|
|
"mean_token_accuracy": 0.11234695836901665,
|
|
"num_tokens": 3109552.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.67326865196228,
|
|
"epoch": 0.13414314428034607,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999753879619319,
|
|
"loss": 6.6964,
|
|
"mean_token_accuracy": 0.11057108193635941,
|
|
"num_tokens": 3119536.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.774283361434937,
|
|
"epoch": 0.13458009263305076,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999749249131741,
|
|
"loss": 6.7401,
|
|
"mean_token_accuracy": 0.11017183065414429,
|
|
"num_tokens": 3130552.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.77594485282898,
|
|
"epoch": 0.13501704098575548,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999744575492793,
|
|
"loss": 6.6427,
|
|
"mean_token_accuracy": 0.11230673864483834,
|
|
"num_tokens": 3140723.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.734894800186157,
|
|
"epoch": 0.1354539893384602,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999739858702567,
|
|
"loss": 6.6867,
|
|
"mean_token_accuracy": 0.11417788490653039,
|
|
"num_tokens": 3151031.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.681126499176026,
|
|
"epoch": 0.1358909376911649,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499973509876115,
|
|
"loss": 6.6992,
|
|
"mean_token_accuracy": 0.11300377771258355,
|
|
"num_tokens": 3161373.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.732465410232544,
|
|
"epoch": 0.1363278860438696,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999730295668634,
|
|
"loss": 6.7103,
|
|
"mean_token_accuracy": 0.11075188368558883,
|
|
"num_tokens": 3171094.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.730536413192749,
|
|
"epoch": 0.13676483439657433,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999725449425114,
|
|
"loss": 6.6527,
|
|
"mean_token_accuracy": 0.1153961479663849,
|
|
"num_tokens": 3181646.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.669804573059082,
|
|
"epoch": 0.13720178274927902,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499972056003068,
|
|
"loss": 6.6392,
|
|
"mean_token_accuracy": 0.12061795890331269,
|
|
"num_tokens": 3190727.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.760992622375488,
|
|
"epoch": 0.13763873110198374,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999715627485426,
|
|
"loss": 6.7383,
|
|
"mean_token_accuracy": 0.10512830913066865,
|
|
"num_tokens": 3200316.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.72571120262146,
|
|
"epoch": 0.13807567945468846,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499971065178945,
|
|
"loss": 6.6925,
|
|
"mean_token_accuracy": 0.10780871957540512,
|
|
"num_tokens": 3211830.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.666191148757934,
|
|
"epoch": 0.13851262780739318,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999705632942843,
|
|
"loss": 6.7023,
|
|
"mean_token_accuracy": 0.10752889290452003,
|
|
"num_tokens": 3222711.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.766510057449341,
|
|
"epoch": 0.13894957616009787,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999700570945704,
|
|
"loss": 6.6191,
|
|
"mean_token_accuracy": 0.11982477754354477,
|
|
"num_tokens": 3232810.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.643466806411743,
|
|
"epoch": 0.1393865245128026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999695465798128,
|
|
"loss": 6.709,
|
|
"mean_token_accuracy": 0.10902300477027893,
|
|
"num_tokens": 3243366.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.7340904712677006,
|
|
"epoch": 0.1398234728655073,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999690317500215,
|
|
"loss": 6.6817,
|
|
"mean_token_accuracy": 0.11203390434384346,
|
|
"num_tokens": 3254000.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.770872020721436,
|
|
"epoch": 0.140260421218212,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999685126052063,
|
|
"loss": 6.7182,
|
|
"mean_token_accuracy": 0.11055498123168946,
|
|
"num_tokens": 3263601.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.6786277294158936,
|
|
"epoch": 0.14069736957091672,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999679891453772,
|
|
"loss": 6.7518,
|
|
"mean_token_accuracy": 0.10704593062400818,
|
|
"num_tokens": 3273243.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.725984144210815,
|
|
"epoch": 0.14113431792362144,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499967461370544,
|
|
"loss": 6.6946,
|
|
"mean_token_accuracy": 0.11100869923830033,
|
|
"num_tokens": 3284208.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.7146117210388185,
|
|
"epoch": 0.14157126627632613,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999669292807172,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.11279672384262085,
|
|
"num_tokens": 3294216.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.724279832839966,
|
|
"epoch": 0.14200821462903085,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999663928759066,
|
|
"loss": 6.7318,
|
|
"mean_token_accuracy": 0.10651321336627007,
|
|
"num_tokens": 3304576.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.742155408859253,
|
|
"epoch": 0.14244516298173557,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999658521561229,
|
|
"loss": 6.6799,
|
|
"mean_token_accuracy": 0.10923416763544083,
|
|
"num_tokens": 3314214.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.732270574569702,
|
|
"epoch": 0.14288211133444026,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999653071213763,
|
|
"loss": 6.6919,
|
|
"mean_token_accuracy": 0.10857749730348587,
|
|
"num_tokens": 3325527.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.634456062316895,
|
|
"epoch": 0.14331905968714498,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999647577716771,
|
|
"loss": 6.6186,
|
|
"mean_token_accuracy": 0.11368991807103157,
|
|
"num_tokens": 3334511.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.681470584869385,
|
|
"epoch": 0.1437560080398497,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999642041070361,
|
|
"loss": 6.6049,
|
|
"mean_token_accuracy": 0.123313669860363,
|
|
"num_tokens": 3343922.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.711009740829468,
|
|
"epoch": 0.1441929563925544,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999636461274637,
|
|
"loss": 6.6236,
|
|
"mean_token_accuracy": 0.10806566402316094,
|
|
"num_tokens": 3353895.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.664011001586914,
|
|
"epoch": 0.1446299047452591,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999630838329706,
|
|
"loss": 6.6989,
|
|
"mean_token_accuracy": 0.10959775745868683,
|
|
"num_tokens": 3364637.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.716980361938477,
|
|
"epoch": 0.14506685309796383,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999625172235679,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.1092151403427124,
|
|
"num_tokens": 3374308.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.650211811065674,
|
|
"epoch": 0.14550380145066852,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499961946299266,
|
|
"loss": 6.6329,
|
|
"mean_token_accuracy": 0.11122519969940185,
|
|
"num_tokens": 3383637.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.707240295410156,
|
|
"epoch": 0.14594074980337324,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999613710600763,
|
|
"loss": 6.7082,
|
|
"mean_token_accuracy": 0.11246861442923546,
|
|
"num_tokens": 3394150.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.7496161460876465,
|
|
"epoch": 0.14637769815607796,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999607915060094,
|
|
"loss": 6.6754,
|
|
"mean_token_accuracy": 0.11157950460910797,
|
|
"num_tokens": 3404445.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.595765924453735,
|
|
"epoch": 0.14681464650878268,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999602076370768,
|
|
"loss": 6.5737,
|
|
"mean_token_accuracy": 0.12239945828914642,
|
|
"num_tokens": 3415183.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.603966903686524,
|
|
"epoch": 0.14725159486148737,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999596194532895,
|
|
"loss": 6.5654,
|
|
"mean_token_accuracy": 0.12099364176392555,
|
|
"num_tokens": 3424824.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.689273071289063,
|
|
"epoch": 0.1476885432141921,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999590269546588,
|
|
"loss": 6.678,
|
|
"mean_token_accuracy": 0.10761870443820953,
|
|
"num_tokens": 3434789.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.553783273696899,
|
|
"epoch": 0.1481254915668968,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999584301411961,
|
|
"loss": 6.5636,
|
|
"mean_token_accuracy": 0.1355303257703781,
|
|
"num_tokens": 3445810.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.779795694351196,
|
|
"epoch": 0.1485624399196015,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999578290129129,
|
|
"loss": 6.6832,
|
|
"mean_token_accuracy": 0.1057976596057415,
|
|
"num_tokens": 3455510.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.636298894882202,
|
|
"epoch": 0.14899938827230622,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999572235698206,
|
|
"loss": 6.6615,
|
|
"mean_token_accuracy": 0.1132010854780674,
|
|
"num_tokens": 3465785.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.681069374084473,
|
|
"epoch": 0.14943633662501093,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999566138119308,
|
|
"loss": 6.7201,
|
|
"mean_token_accuracy": 0.1101304367184639,
|
|
"num_tokens": 3477568.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.6410560131073,
|
|
"epoch": 0.14987328497771563,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999559997392554,
|
|
"loss": 6.5654,
|
|
"mean_token_accuracy": 0.12847595363855363,
|
|
"num_tokens": 3487703.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.643354415893555,
|
|
"epoch": 0.15031023333042035,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999553813518061,
|
|
"loss": 6.6404,
|
|
"mean_token_accuracy": 0.113068488240242,
|
|
"num_tokens": 3497757.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.62676682472229,
|
|
"epoch": 0.15074718168312506,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999547586495946,
|
|
"loss": 6.5846,
|
|
"mean_token_accuracy": 0.11577531546354294,
|
|
"num_tokens": 3507594.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.71900110244751,
|
|
"epoch": 0.15118413003582976,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999541316326329,
|
|
"loss": 6.6673,
|
|
"mean_token_accuracy": 0.11186658293008804,
|
|
"num_tokens": 3517889.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.641316223144531,
|
|
"epoch": 0.15162107838853447,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999535003009332,
|
|
"loss": 6.654,
|
|
"mean_token_accuracy": 0.11276111975312234,
|
|
"num_tokens": 3528158.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.716168689727783,
|
|
"epoch": 0.1520580267412392,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999528646545074,
|
|
"loss": 6.6543,
|
|
"mean_token_accuracy": 0.11286873891949653,
|
|
"num_tokens": 3539099.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.686854839324951,
|
|
"epoch": 0.15249497509394389,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999522246933678,
|
|
"loss": 6.6539,
|
|
"mean_token_accuracy": 0.11401691287755966,
|
|
"num_tokens": 3549819.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.659570646286011,
|
|
"epoch": 0.1529319234466486,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 6.6727,
|
|
"mean_token_accuracy": 0.11552643105387687,
|
|
"num_tokens": 3560022.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.690343952178955,
|
|
"epoch": 0.15336887179935332,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999509318269964,
|
|
"loss": 6.6105,
|
|
"mean_token_accuracy": 0.1143421933054924,
|
|
"num_tokens": 3569681.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.675909900665284,
|
|
"epoch": 0.15380582015205801,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999502789217894,
|
|
"loss": 6.6883,
|
|
"mean_token_accuracy": 0.11230143532156944,
|
|
"num_tokens": 3580731.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.674851751327514,
|
|
"epoch": 0.15424276850476273,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999496217019181,
|
|
"loss": 6.6569,
|
|
"mean_token_accuracy": 0.11778324693441392,
|
|
"num_tokens": 3590482.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.62106499671936,
|
|
"epoch": 0.15467971685746745,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999489601673952,
|
|
"loss": 6.6372,
|
|
"mean_token_accuracy": 0.10963449701666832,
|
|
"num_tokens": 3600988.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.827673149108887,
|
|
"epoch": 0.15511666521017214,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999482943182334,
|
|
"loss": 6.7154,
|
|
"mean_token_accuracy": 0.10713721886277199,
|
|
"num_tokens": 3611226.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.550780200958252,
|
|
"epoch": 0.15555361356287686,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999476241544454,
|
|
"loss": 6.631,
|
|
"mean_token_accuracy": 0.11362414360046387,
|
|
"num_tokens": 3621324.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.73470458984375,
|
|
"epoch": 0.15599056191558158,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999469496760441,
|
|
"loss": 6.5608,
|
|
"mean_token_accuracy": 0.10904188230633735,
|
|
"num_tokens": 3631650.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.592597961425781,
|
|
"epoch": 0.1564275102682863,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999462708830425,
|
|
"loss": 6.579,
|
|
"mean_token_accuracy": 0.1228872999548912,
|
|
"num_tokens": 3641173.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.629960441589356,
|
|
"epoch": 0.156864458620991,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999455877754535,
|
|
"loss": 6.5856,
|
|
"mean_token_accuracy": 0.11571357101202011,
|
|
"num_tokens": 3651846.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.641428709030151,
|
|
"epoch": 0.1573014069736957,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999449003532903,
|
|
"loss": 6.5976,
|
|
"mean_token_accuracy": 0.11091143637895584,
|
|
"num_tokens": 3661174.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.59941554069519,
|
|
"epoch": 0.15773835532640043,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999442086165661,
|
|
"loss": 6.5618,
|
|
"mean_token_accuracy": 0.11522511392831802,
|
|
"num_tokens": 3671042.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.636082983016967,
|
|
"epoch": 0.15817530367910512,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499943512565294,
|
|
"loss": 6.5383,
|
|
"mean_token_accuracy": 0.11486825719475746,
|
|
"num_tokens": 3681206.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.601233339309692,
|
|
"epoch": 0.15861225203180984,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999428121994874,
|
|
"loss": 6.6437,
|
|
"mean_token_accuracy": 0.11468076482415199,
|
|
"num_tokens": 3691748.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.592959594726563,
|
|
"epoch": 0.15904920038451456,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999421075191599,
|
|
"loss": 6.5286,
|
|
"mean_token_accuracy": 0.11978306695818901,
|
|
"num_tokens": 3701730.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.626725864410401,
|
|
"epoch": 0.15948614873721925,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999413985243249,
|
|
"loss": 6.6348,
|
|
"mean_token_accuracy": 0.11135040819644929,
|
|
"num_tokens": 3712525.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.75208683013916,
|
|
"epoch": 0.15992309708992397,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499940685214996,
|
|
"loss": 6.6015,
|
|
"mean_token_accuracy": 0.11548954620957375,
|
|
"num_tokens": 3722016.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.588428592681884,
|
|
"epoch": 0.1603600454426287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999399675911869,
|
|
"loss": 6.5126,
|
|
"mean_token_accuracy": 0.11435215696692466,
|
|
"num_tokens": 3731299.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.589688014984131,
|
|
"epoch": 0.16079699379533338,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999392456529113,
|
|
"loss": 6.587,
|
|
"mean_token_accuracy": 0.11893209591507911,
|
|
"num_tokens": 3740922.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.591811609268189,
|
|
"epoch": 0.1612339421480381,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999385194001831,
|
|
"loss": 6.5647,
|
|
"mean_token_accuracy": 0.11818592995405197,
|
|
"num_tokens": 3750339.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.626106214523316,
|
|
"epoch": 0.16167089050074282,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999377888330164,
|
|
"loss": 6.5444,
|
|
"mean_token_accuracy": 0.11974458321928978,
|
|
"num_tokens": 3761379.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.565863084793091,
|
|
"epoch": 0.1621078388534475,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999370539514249,
|
|
"loss": 6.6178,
|
|
"mean_token_accuracy": 0.11443219929933549,
|
|
"num_tokens": 3771649.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.616359758377075,
|
|
"epoch": 0.16254478720615223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999363147554229,
|
|
"loss": 6.5317,
|
|
"mean_token_accuracy": 0.11977923512458802,
|
|
"num_tokens": 3782393.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.595934057235718,
|
|
"epoch": 0.16298173555885695,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999355712450244,
|
|
"loss": 6.5811,
|
|
"mean_token_accuracy": 0.11747404783964158,
|
|
"num_tokens": 3792849.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.613617277145385,
|
|
"epoch": 0.16341868391156164,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999348234202438,
|
|
"loss": 6.5427,
|
|
"mean_token_accuracy": 0.12124217823147773,
|
|
"num_tokens": 3803848.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.488130903244018,
|
|
"epoch": 0.16385563226426636,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999340712810956,
|
|
"loss": 6.4728,
|
|
"mean_token_accuracy": 0.13200217932462693,
|
|
"num_tokens": 3814704.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.589626598358154,
|
|
"epoch": 0.16429258061697108,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999333148275939,
|
|
"loss": 6.6042,
|
|
"mean_token_accuracy": 0.11308980882167816,
|
|
"num_tokens": 3824955.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.65059003829956,
|
|
"epoch": 0.1647295289696758,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999325540597535,
|
|
"loss": 6.5923,
|
|
"mean_token_accuracy": 0.11620239540934563,
|
|
"num_tokens": 3836540.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.508061504364013,
|
|
"epoch": 0.1651664773223805,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999317889775887,
|
|
"loss": 6.472,
|
|
"mean_token_accuracy": 0.127332104742527,
|
|
"num_tokens": 3846472.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.606565713882446,
|
|
"epoch": 0.1656034256750852,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999310195811143,
|
|
"loss": 6.5876,
|
|
"mean_token_accuracy": 0.11355203092098236,
|
|
"num_tokens": 3857187.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.635375547409057,
|
|
"epoch": 0.16604037402778993,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999302458703451,
|
|
"loss": 6.5539,
|
|
"mean_token_accuracy": 0.12006403431296349,
|
|
"num_tokens": 3866259.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.508198642730713,
|
|
"epoch": 0.16647732238049462,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499929467845296,
|
|
"loss": 6.6008,
|
|
"mean_token_accuracy": 0.11160141155123711,
|
|
"num_tokens": 3876869.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.69843864440918,
|
|
"epoch": 0.16691427073319934,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999286855059818,
|
|
"loss": 6.5887,
|
|
"mean_token_accuracy": 0.11653141602873802,
|
|
"num_tokens": 3888278.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.593745183944702,
|
|
"epoch": 0.16735121908590406,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999278988524177,
|
|
"loss": 6.6379,
|
|
"mean_token_accuracy": 0.11633663773536682,
|
|
"num_tokens": 3898648.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.625266742706299,
|
|
"epoch": 0.16778816743860875,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999271078846184,
|
|
"loss": 6.5605,
|
|
"mean_token_accuracy": 0.11227926462888718,
|
|
"num_tokens": 3908282.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.506586313247681,
|
|
"epoch": 0.16822511579131347,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999263126025994,
|
|
"loss": 6.5511,
|
|
"mean_token_accuracy": 0.11529682129621506,
|
|
"num_tokens": 3918333.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.6185715675354,
|
|
"epoch": 0.1686620641440182,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999255130063759,
|
|
"loss": 6.551,
|
|
"mean_token_accuracy": 0.11844497621059417,
|
|
"num_tokens": 3927403.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.623962688446045,
|
|
"epoch": 0.16909901249672288,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999247090959633,
|
|
"loss": 6.5766,
|
|
"mean_token_accuracy": 0.11571719124913216,
|
|
"num_tokens": 3937352.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.5212033748626705,
|
|
"epoch": 0.1695359608494276,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999239008713767,
|
|
"loss": 6.4001,
|
|
"mean_token_accuracy": 0.12067319750785828,
|
|
"num_tokens": 3947164.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.612851142883301,
|
|
"epoch": 0.16997290920213232,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999230883326319,
|
|
"loss": 6.5711,
|
|
"mean_token_accuracy": 0.1215322732925415,
|
|
"num_tokens": 3956887.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.603779935836792,
|
|
"epoch": 0.170409857554837,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999222714797445,
|
|
"loss": 6.5448,
|
|
"mean_token_accuracy": 0.11428779810667038,
|
|
"num_tokens": 3966542.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.621708679199219,
|
|
"epoch": 0.17084680590754173,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049992145031273,
|
|
"loss": 6.5031,
|
|
"mean_token_accuracy": 0.12730235159397124,
|
|
"num_tokens": 3976127.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.489267015457154,
|
|
"epoch": 0.17128375426024645,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999206248316043,
|
|
"loss": 6.4794,
|
|
"mean_token_accuracy": 0.12245322167873382,
|
|
"num_tokens": 3987371.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.467897510528564,
|
|
"epoch": 0.17172070261295114,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499919795036383,
|
|
"loss": 6.4856,
|
|
"mean_token_accuracy": 0.12608123421669007,
|
|
"num_tokens": 3997924.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.592717838287354,
|
|
"epoch": 0.17215765096565586,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999189609270823,
|
|
"loss": 6.5879,
|
|
"mean_token_accuracy": 0.11945871189236641,
|
|
"num_tokens": 4009150.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.613911104202271,
|
|
"epoch": 0.17259459931836058,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499918122503718,
|
|
"loss": 6.5901,
|
|
"mean_token_accuracy": 0.11914976313710213,
|
|
"num_tokens": 4018899.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.609164476394653,
|
|
"epoch": 0.17303154767106527,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999172797663064,
|
|
"loss": 6.5304,
|
|
"mean_token_accuracy": 0.11551554650068283,
|
|
"num_tokens": 4028652.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.543050098419189,
|
|
"epoch": 0.17346849602376999,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999164327148634,
|
|
"loss": 6.5897,
|
|
"mean_token_accuracy": 0.11552718579769135,
|
|
"num_tokens": 4039819.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.634558057785034,
|
|
"epoch": 0.1739054443764747,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999155813494053,
|
|
"loss": 6.4774,
|
|
"mean_token_accuracy": 0.1238390825688839,
|
|
"num_tokens": 4050029.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.476582670211792,
|
|
"epoch": 0.17434239272917942,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999147256699487,
|
|
"loss": 6.5391,
|
|
"mean_token_accuracy": 0.11595378592610359,
|
|
"num_tokens": 4060497.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.684065818786621,
|
|
"epoch": 0.17477934108188412,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999138656765096,
|
|
"loss": 6.4877,
|
|
"mean_token_accuracy": 0.12127815932035446,
|
|
"num_tokens": 4071477.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.5196648120880125,
|
|
"epoch": 0.17521628943458883,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999130013691049,
|
|
"loss": 6.6098,
|
|
"mean_token_accuracy": 0.11518096625804901,
|
|
"num_tokens": 4081869.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.655038213729858,
|
|
"epoch": 0.17565323778729355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999121327477509,
|
|
"loss": 6.5682,
|
|
"mean_token_accuracy": 0.12180981114506721,
|
|
"num_tokens": 4092797.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.532944250106811,
|
|
"epoch": 0.17609018613999824,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999112598124642,
|
|
"loss": 6.5063,
|
|
"mean_token_accuracy": 0.1199454739689827,
|
|
"num_tokens": 4103688.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.571459817886352,
|
|
"epoch": 0.17652713449270296,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999103825632618,
|
|
"loss": 6.4782,
|
|
"mean_token_accuracy": 0.11821270734071732,
|
|
"num_tokens": 4114037.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.5301916122436525,
|
|
"epoch": 0.17696408284540768,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999095010001605,
|
|
"loss": 6.4682,
|
|
"mean_token_accuracy": 0.1155319221317768,
|
|
"num_tokens": 4124164.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.594848585128784,
|
|
"epoch": 0.17740103119811237,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499908615123177,
|
|
"loss": 6.5857,
|
|
"mean_token_accuracy": 0.11203168854117393,
|
|
"num_tokens": 4134225.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.591685009002686,
|
|
"epoch": 0.1778379795508171,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999077249323284,
|
|
"loss": 6.6335,
|
|
"mean_token_accuracy": 0.11418751999735832,
|
|
"num_tokens": 4145962.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.635752868652344,
|
|
"epoch": 0.1782749279035218,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999068304276319,
|
|
"loss": 6.5198,
|
|
"mean_token_accuracy": 0.11557328552007676,
|
|
"num_tokens": 4156572.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.526685047149658,
|
|
"epoch": 0.1787118762562265,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999059316091045,
|
|
"loss": 6.5968,
|
|
"mean_token_accuracy": 0.11482413336634636,
|
|
"num_tokens": 4166960.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.634673261642456,
|
|
"epoch": 0.17914882460893122,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999050284767634,
|
|
"loss": 6.5518,
|
|
"mean_token_accuracy": 0.11969516798853874,
|
|
"num_tokens": 4177833.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.4771088600158695,
|
|
"epoch": 0.17958577296163594,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999041210306261,
|
|
"loss": 6.476,
|
|
"mean_token_accuracy": 0.12267953082919121,
|
|
"num_tokens": 4187858.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.624364042282105,
|
|
"epoch": 0.18002272131434063,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999032092707098,
|
|
"loss": 6.597,
|
|
"mean_token_accuracy": 0.11280876621603966,
|
|
"num_tokens": 4198207.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.574216651916504,
|
|
"epoch": 0.18045966966704535,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999022931970323,
|
|
"loss": 6.4885,
|
|
"mean_token_accuracy": 0.12329766750335694,
|
|
"num_tokens": 4207594.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.514097881317139,
|
|
"epoch": 0.18089661801975007,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999013728096107,
|
|
"loss": 6.4908,
|
|
"mean_token_accuracy": 0.12111081257462501,
|
|
"num_tokens": 4217334.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.534528684616089,
|
|
"epoch": 0.18133356637245476,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499900448108463,
|
|
"loss": 6.462,
|
|
"mean_token_accuracy": 0.12237232476472855,
|
|
"num_tokens": 4226407.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.516916418075562,
|
|
"epoch": 0.18177051472515948,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499899519093607,
|
|
"loss": 6.4228,
|
|
"mean_token_accuracy": 0.1265766814351082,
|
|
"num_tokens": 4237818.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.613302946090698,
|
|
"epoch": 0.1822074630778642,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998985857650603,
|
|
"loss": 6.5469,
|
|
"mean_token_accuracy": 0.11210652962327003,
|
|
"num_tokens": 4247783.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.468383121490478,
|
|
"epoch": 0.18264441143056892,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998976481228409,
|
|
"loss": 6.4822,
|
|
"mean_token_accuracy": 0.12208920419216156,
|
|
"num_tokens": 4258049.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.525755500793457,
|
|
"epoch": 0.1830813597832736,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998967061669668,
|
|
"loss": 6.4925,
|
|
"mean_token_accuracy": 0.11374819204211235,
|
|
"num_tokens": 4269357.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.536129570007324,
|
|
"epoch": 0.18351830813597833,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998957598974559,
|
|
"loss": 6.4138,
|
|
"mean_token_accuracy": 0.12686009854078292,
|
|
"num_tokens": 4279576.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.499485492706299,
|
|
"epoch": 0.18395525648868305,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998948093143266,
|
|
"loss": 6.4758,
|
|
"mean_token_accuracy": 0.11781678795814514,
|
|
"num_tokens": 4289761.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.524201726913452,
|
|
"epoch": 0.18439220484138774,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499893854417597,
|
|
"loss": 6.3922,
|
|
"mean_token_accuracy": 0.12270399779081345,
|
|
"num_tokens": 4299231.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.541791009902954,
|
|
"epoch": 0.18482915319409246,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998928952072854,
|
|
"loss": 6.5593,
|
|
"mean_token_accuracy": 0.11242108196020126,
|
|
"num_tokens": 4308687.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.591986656188965,
|
|
"epoch": 0.18526610154679718,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998919316834102,
|
|
"loss": 6.5182,
|
|
"mean_token_accuracy": 0.11508347168564796,
|
|
"num_tokens": 4318183.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.558227300643921,
|
|
"epoch": 0.18570304989950187,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049989096384599,
|
|
"loss": 6.5573,
|
|
"mean_token_accuracy": 0.11798967346549034,
|
|
"num_tokens": 4328482.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.584009790420533,
|
|
"epoch": 0.1861399982522066,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004998899916950431,
|
|
"loss": 6.4366,
|
|
"mean_token_accuracy": 0.1197984792292118,
|
|
"num_tokens": 4339313.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.453553342819214,
|
|
"epoch": 0.1865769466049113,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998890152305885,
|
|
"loss": 6.5547,
|
|
"mean_token_accuracy": 0.11854925975203515,
|
|
"num_tokens": 4350299.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.635061883926392,
|
|
"epoch": 0.187013894957616,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004998880344526447,
|
|
"loss": 6.4894,
|
|
"mean_token_accuracy": 0.12394139692187309,
|
|
"num_tokens": 4361424.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.466842317581177,
|
|
"epoch": 0.18745084331032072,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998870493612306,
|
|
"loss": 6.4538,
|
|
"mean_token_accuracy": 0.12028718739748001,
|
|
"num_tokens": 4371480.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.470487928390503,
|
|
"epoch": 0.18788779166302544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998860599563649,
|
|
"loss": 6.4967,
|
|
"mean_token_accuracy": 0.12331848666071892,
|
|
"num_tokens": 4381951.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.558203125,
|
|
"epoch": 0.18832474001573013,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998850662380668,
|
|
"loss": 6.5616,
|
|
"mean_token_accuracy": 0.11244588792324066,
|
|
"num_tokens": 4392290.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.525679016113282,
|
|
"epoch": 0.18876168836843485,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998840682063553,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.13558808639645575,
|
|
"num_tokens": 4403350.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.414237642288208,
|
|
"epoch": 0.18919863672113957,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998830658612496,
|
|
"loss": 6.4999,
|
|
"mean_token_accuracy": 0.11366144940257072,
|
|
"num_tokens": 4413171.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.537461614608764,
|
|
"epoch": 0.18963558507384426,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998820592027688,
|
|
"loss": 6.4523,
|
|
"mean_token_accuracy": 0.12490663677453995,
|
|
"num_tokens": 4424371.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.459207391738891,
|
|
"epoch": 0.19007253342654898,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998810482309322,
|
|
"loss": 6.415,
|
|
"mean_token_accuracy": 0.11684294268488885,
|
|
"num_tokens": 4434040.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.612886381149292,
|
|
"epoch": 0.1905094817792537,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998800329457595,
|
|
"loss": 6.5237,
|
|
"mean_token_accuracy": 0.11428215354681015,
|
|
"num_tokens": 4444663.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.530249738693238,
|
|
"epoch": 0.1909464301319584,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998790133472697,
|
|
"loss": 6.4732,
|
|
"mean_token_accuracy": 0.1187725804746151,
|
|
"num_tokens": 4454733.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.478503894805908,
|
|
"epoch": 0.1913833784846631,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998779894354827,
|
|
"loss": 6.4561,
|
|
"mean_token_accuracy": 0.12121548429131508,
|
|
"num_tokens": 4464286.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.554786252975464,
|
|
"epoch": 0.19182032683736783,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499876961210418,
|
|
"loss": 6.4435,
|
|
"mean_token_accuracy": 0.12957765012979508,
|
|
"num_tokens": 4475005.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.456162691116333,
|
|
"epoch": 0.19225727519007255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998759286720953,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.12335258722305298,
|
|
"num_tokens": 4484606.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.4117199897766115,
|
|
"epoch": 0.19269422354277724,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998748918205345,
|
|
"loss": 6.5107,
|
|
"mean_token_accuracy": 0.115721445530653,
|
|
"num_tokens": 4494930.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.56764326095581,
|
|
"epoch": 0.19313117189548196,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998738506557554,
|
|
"loss": 6.5316,
|
|
"mean_token_accuracy": 0.11446557492017746,
|
|
"num_tokens": 4505304.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.6263429641723635,
|
|
"epoch": 0.19356812024818668,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499872805177778,
|
|
"loss": 6.4505,
|
|
"mean_token_accuracy": 0.1278298854827881,
|
|
"num_tokens": 4514333.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.442032718658448,
|
|
"epoch": 0.19400506860089137,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998717553866225,
|
|
"loss": 6.5229,
|
|
"mean_token_accuracy": 0.12303071394562722,
|
|
"num_tokens": 4525175.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.5615222454071045,
|
|
"epoch": 0.1944420169535961,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998707012823087,
|
|
"loss": 6.3765,
|
|
"mean_token_accuracy": 0.12679129466414452,
|
|
"num_tokens": 4534212.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.452094221115113,
|
|
"epoch": 0.1948789653063008,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998696428648573,
|
|
"loss": 6.5735,
|
|
"mean_token_accuracy": 0.11512410044670104,
|
|
"num_tokens": 4545141.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.557396984100341,
|
|
"epoch": 0.1953159136590055,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998685801342881,
|
|
"loss": 6.4302,
|
|
"mean_token_accuracy": 0.12757914289832115,
|
|
"num_tokens": 4554410.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.421574354171753,
|
|
"epoch": 0.19575286201171022,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998675130906217,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.12503303810954094,
|
|
"num_tokens": 4564397.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.4371904850006105,
|
|
"epoch": 0.19618981036441493,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998664417338787,
|
|
"loss": 6.4093,
|
|
"mean_token_accuracy": 0.13016692399978638,
|
|
"num_tokens": 4573986.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.574130344390869,
|
|
"epoch": 0.19662675871711963,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004998653660640794,
|
|
"loss": 6.4194,
|
|
"mean_token_accuracy": 0.1290357455611229,
|
|
"num_tokens": 4583449.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.453009510040284,
|
|
"epoch": 0.19706370706982435,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998642860812447,
|
|
"loss": 6.4579,
|
|
"mean_token_accuracy": 0.12105687931180001,
|
|
"num_tokens": 4593637.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.440600728988647,
|
|
"epoch": 0.19750065542252906,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004998632017853951,
|
|
"loss": 6.439,
|
|
"mean_token_accuracy": 0.12805744558572768,
|
|
"num_tokens": 4603865.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.638007259368896,
|
|
"epoch": 0.19793760377523376,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998621131765514,
|
|
"loss": 6.4676,
|
|
"mean_token_accuracy": 0.12696166336536407,
|
|
"num_tokens": 4613502.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.4463948726654055,
|
|
"epoch": 0.19837455212793847,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998610202547345,
|
|
"loss": 6.4225,
|
|
"mean_token_accuracy": 0.12365630269050598,
|
|
"num_tokens": 4623163.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.512554073333741,
|
|
"epoch": 0.1988115004806432,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998599230199654,
|
|
"loss": 6.4507,
|
|
"mean_token_accuracy": 0.12848633974790574,
|
|
"num_tokens": 4632850.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.491110992431641,
|
|
"epoch": 0.19924844883334789,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998588214722653,
|
|
"loss": 6.4608,
|
|
"mean_token_accuracy": 0.12021621614694596,
|
|
"num_tokens": 4642858.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.567204236984253,
|
|
"epoch": 0.1996853971860526,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 6.4891,
|
|
"mean_token_accuracy": 0.11761298626661301,
|
|
"num_tokens": 4653083.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.529744482040405,
|
|
"epoch": 0.20012234553875732,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998566054381561,
|
|
"loss": 6.4926,
|
|
"mean_token_accuracy": 0.11979148462414742,
|
|
"num_tokens": 4663353.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.469255495071411,
|
|
"epoch": 0.20055929389146204,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004998554909517895,
|
|
"loss": 6.3575,
|
|
"mean_token_accuracy": 0.12421375289559364,
|
|
"num_tokens": 4673878.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.480479335784912,
|
|
"epoch": 0.20099624224416673,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998543721525769,
|
|
"loss": 6.4255,
|
|
"mean_token_accuracy": 0.12483477517962456,
|
|
"num_tokens": 4683661.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.437173128128052,
|
|
"epoch": 0.20143319059687145,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004998532490405397,
|
|
"loss": 6.4822,
|
|
"mean_token_accuracy": 0.12061880454421044,
|
|
"num_tokens": 4693817.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.519210433959961,
|
|
"epoch": 0.20187013894957617,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998521216156991,
|
|
"loss": 6.4082,
|
|
"mean_token_accuracy": 0.12354693114757538,
|
|
"num_tokens": 4703550.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.495586681365967,
|
|
"epoch": 0.20230708730228086,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998509898780771,
|
|
"loss": 6.5167,
|
|
"mean_token_accuracy": 0.12095422595739365,
|
|
"num_tokens": 4714872.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.496729040145874,
|
|
"epoch": 0.20274403565498558,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998498538276954,
|
|
"loss": 6.4195,
|
|
"mean_token_accuracy": 0.1262986145913601,
|
|
"num_tokens": 4725745.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.488230037689209,
|
|
"epoch": 0.2031809840076903,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998487134645755,
|
|
"loss": 6.5061,
|
|
"mean_token_accuracy": 0.11861919611692429,
|
|
"num_tokens": 4735560.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.54272050857544,
|
|
"epoch": 0.203617932360395,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998475687887396,
|
|
"loss": 6.4698,
|
|
"mean_token_accuracy": 0.11695239022374153,
|
|
"num_tokens": 4746304.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.514755916595459,
|
|
"epoch": 0.2040548807130997,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998464198002095,
|
|
"loss": 6.4377,
|
|
"mean_token_accuracy": 0.1227838471531868,
|
|
"num_tokens": 4756200.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.447860813140869,
|
|
"epoch": 0.20449182906580443,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998452664990072,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.11562853530049325,
|
|
"num_tokens": 4766249.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.608063697814941,
|
|
"epoch": 0.20492877741850912,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998441088851548,
|
|
"loss": 6.4832,
|
|
"mean_token_accuracy": 0.11795579493045807,
|
|
"num_tokens": 4776510.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.442056512832641,
|
|
"epoch": 0.20536572577121384,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998429469586748,
|
|
"loss": 6.4677,
|
|
"mean_token_accuracy": 0.12453974261879922,
|
|
"num_tokens": 4786798.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.467907285690307,
|
|
"epoch": 0.20580267412391856,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499841780719589,
|
|
"loss": 6.3917,
|
|
"mean_token_accuracy": 0.12231776416301728,
|
|
"num_tokens": 4796001.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.50298957824707,
|
|
"epoch": 0.20623962247662325,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004998406101679202,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.13163737431168557,
|
|
"num_tokens": 4807634.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.424554872512817,
|
|
"epoch": 0.20667657082932797,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998394353036906,
|
|
"loss": 6.3798,
|
|
"mean_token_accuracy": 0.12814454063773156,
|
|
"num_tokens": 4817840.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.408347225189209,
|
|
"epoch": 0.2071135191820327,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998382561269229,
|
|
"loss": 6.361,
|
|
"mean_token_accuracy": 0.12966743409633635,
|
|
"num_tokens": 4827186.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.389866161346435,
|
|
"epoch": 0.20755046753473738,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998370726376395,
|
|
"loss": 6.4079,
|
|
"mean_token_accuracy": 0.122555311024189,
|
|
"num_tokens": 4837140.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.533910131454467,
|
|
"epoch": 0.2079874158874421,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998358848358634,
|
|
"loss": 6.431,
|
|
"mean_token_accuracy": 0.12573982998728753,
|
|
"num_tokens": 4846907.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.3821924209594725,
|
|
"epoch": 0.20842436424014682,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499834692721617,
|
|
"loss": 6.46,
|
|
"mean_token_accuracy": 0.12661178037524223,
|
|
"num_tokens": 4856165.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.529715347290039,
|
|
"epoch": 0.2088613125928515,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998334962949237,
|
|
"loss": 6.3174,
|
|
"mean_token_accuracy": 0.13617229014635085,
|
|
"num_tokens": 4865308.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.401957368850708,
|
|
"epoch": 0.20929826094555623,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004998322955558059,
|
|
"loss": 6.3776,
|
|
"mean_token_accuracy": 0.13593824356794357,
|
|
"num_tokens": 4876286.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.444190835952758,
|
|
"epoch": 0.20973520929826095,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998310905042869,
|
|
"loss": 6.4117,
|
|
"mean_token_accuracy": 0.1278536468744278,
|
|
"num_tokens": 4887227.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.500918197631836,
|
|
"epoch": 0.21017215765096567,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998298811403898,
|
|
"loss": 6.4362,
|
|
"mean_token_accuracy": 0.12585031986236572,
|
|
"num_tokens": 4896994.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.4714161396026615,
|
|
"epoch": 0.21060910600367036,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998286674641378,
|
|
"loss": 6.4233,
|
|
"mean_token_accuracy": 0.12609584704041482,
|
|
"num_tokens": 4907623.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.38978328704834,
|
|
"epoch": 0.21104605435637508,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499827449475554,
|
|
"loss": 6.3345,
|
|
"mean_token_accuracy": 0.1257795587182045,
|
|
"num_tokens": 4917040.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.572758913040161,
|
|
"epoch": 0.2114830027090798,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499826227174662,
|
|
"loss": 6.4813,
|
|
"mean_token_accuracy": 0.12101781442761421,
|
|
"num_tokens": 4928390.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.456791114807129,
|
|
"epoch": 0.2119199510617845,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998250005614852,
|
|
"loss": 6.4405,
|
|
"mean_token_accuracy": 0.12130651250481606,
|
|
"num_tokens": 4939040.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.4252156734466555,
|
|
"epoch": 0.2123568994144892,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499823769636047,
|
|
"loss": 6.4799,
|
|
"mean_token_accuracy": 0.1219657190144062,
|
|
"num_tokens": 4949915.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.486149072647095,
|
|
"epoch": 0.21279384776719393,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998225343983712,
|
|
"loss": 6.3746,
|
|
"mean_token_accuracy": 0.1280059665441513,
|
|
"num_tokens": 4960127.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.488802576065064,
|
|
"epoch": 0.21323079611989862,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998212948484814,
|
|
"loss": 6.4092,
|
|
"mean_token_accuracy": 0.12064960524439812,
|
|
"num_tokens": 4970152.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.453671264648437,
|
|
"epoch": 0.21366774447260334,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998200509864012,
|
|
"loss": 6.3906,
|
|
"mean_token_accuracy": 0.12469479888677597,
|
|
"num_tokens": 4979745.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.503656196594238,
|
|
"epoch": 0.21410469282530806,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998188028121547,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.13096271976828575,
|
|
"num_tokens": 4989924.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.437544631958008,
|
|
"epoch": 0.21454164117801275,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998175503257658,
|
|
"loss": 6.3653,
|
|
"mean_token_accuracy": 0.12972407415509224,
|
|
"num_tokens": 4999698.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.409564542770386,
|
|
"epoch": 0.21497858953071747,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998162935272585,
|
|
"loss": 6.4533,
|
|
"mean_token_accuracy": 0.1265200860798359,
|
|
"num_tokens": 5010625.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.484053325653076,
|
|
"epoch": 0.2154155378834222,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998150324166568,
|
|
"loss": 6.3428,
|
|
"mean_token_accuracy": 0.13328861966729164,
|
|
"num_tokens": 5019740.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.527134990692138,
|
|
"epoch": 0.21585248623612688,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499813766993985,
|
|
"loss": 6.4651,
|
|
"mean_token_accuracy": 0.11876360327005386,
|
|
"num_tokens": 5030601.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.523973608016968,
|
|
"epoch": 0.2162894345888316,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004998124972592674,
|
|
"loss": 6.4179,
|
|
"mean_token_accuracy": 0.12937648892402648,
|
|
"num_tokens": 5040567.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.355432462692261,
|
|
"epoch": 0.21672638294153632,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998112232125283,
|
|
"loss": 6.3016,
|
|
"mean_token_accuracy": 0.12884993553161622,
|
|
"num_tokens": 5049512.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.446121454238892,
|
|
"epoch": 0.217163331294241,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499809944853792,
|
|
"loss": 6.4913,
|
|
"mean_token_accuracy": 0.11906690523028374,
|
|
"num_tokens": 5060986.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.456017398834229,
|
|
"epoch": 0.21760027964694573,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998086621830833,
|
|
"loss": 6.3963,
|
|
"mean_token_accuracy": 0.12860883325338363,
|
|
"num_tokens": 5071492.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.459888029098511,
|
|
"epoch": 0.21803722799965045,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998073752004267,
|
|
"loss": 6.4277,
|
|
"mean_token_accuracy": 0.12244511172175407,
|
|
"num_tokens": 5081722.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.4814647197723385,
|
|
"epoch": 0.21847417635235516,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998060839058467,
|
|
"loss": 6.4034,
|
|
"mean_token_accuracy": 0.1271081253886223,
|
|
"num_tokens": 5091906.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.439739561080932,
|
|
"epoch": 0.21891112470505986,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998047882993683,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.12823385149240493,
|
|
"num_tokens": 5102025.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.395084476470947,
|
|
"epoch": 0.21934807305776458,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998034883810162,
|
|
"loss": 6.3832,
|
|
"mean_token_accuracy": 0.12374164834618569,
|
|
"num_tokens": 5112354.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.446513080596924,
|
|
"epoch": 0.2197850214104693,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998021841508155,
|
|
"loss": 6.3168,
|
|
"mean_token_accuracy": 0.13202272802591325,
|
|
"num_tokens": 5121695.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.439951753616333,
|
|
"epoch": 0.22022196976317399,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998008756087911,
|
|
"loss": 6.4343,
|
|
"mean_token_accuracy": 0.1225411631166935,
|
|
"num_tokens": 5132561.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.497098779678344,
|
|
"epoch": 0.2206589181158787,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499799562754968,
|
|
"loss": 6.4641,
|
|
"mean_token_accuracy": 0.12008634880185128,
|
|
"num_tokens": 5141981.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.426127338409424,
|
|
"epoch": 0.22109586646858342,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997982455893716,
|
|
"loss": 6.3423,
|
|
"mean_token_accuracy": 0.13012854084372522,
|
|
"num_tokens": 5151550.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.481066370010376,
|
|
"epoch": 0.22153281482128812,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997969241120271,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.1182328850030899,
|
|
"num_tokens": 5161679.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.384076070785523,
|
|
"epoch": 0.22196976317399283,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997955983229597,
|
|
"loss": 6.4474,
|
|
"mean_token_accuracy": 0.12612560242414475,
|
|
"num_tokens": 5171575.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.43102331161499,
|
|
"epoch": 0.22240671152669755,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499794268222195,
|
|
"loss": 6.3124,
|
|
"mean_token_accuracy": 0.1305751197040081,
|
|
"num_tokens": 5180152.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.3732438564300535,
|
|
"epoch": 0.22284365987940224,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997929338097583,
|
|
"loss": 6.4073,
|
|
"mean_token_accuracy": 0.12662707194685935,
|
|
"num_tokens": 5190518.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.544715642929077,
|
|
"epoch": 0.22328060823210696,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997915950856755,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.11940659433603287,
|
|
"num_tokens": 5201729.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.457584857940674,
|
|
"epoch": 0.22371755658481168,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997902520499721,
|
|
"loss": 6.4058,
|
|
"mean_token_accuracy": 0.12618774101138114,
|
|
"num_tokens": 5211940.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.353214883804322,
|
|
"epoch": 0.22415450493751637,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997889047026738,
|
|
"loss": 6.337,
|
|
"mean_token_accuracy": 0.12396835684776306,
|
|
"num_tokens": 5221028.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.432541036605835,
|
|
"epoch": 0.2245914532902211,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997875530438066,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.12881741002202035,
|
|
"num_tokens": 5230498.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.4462562084198,
|
|
"epoch": 0.2250284016429258,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997861970733963,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.12332283109426498,
|
|
"num_tokens": 5240112.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.438518524169922,
|
|
"epoch": 0.2254653499956305,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499784836791469,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.12764344960451127,
|
|
"num_tokens": 5249201.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.401770162582397,
|
|
"epoch": 0.22590229834833522,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997834721980507,
|
|
"loss": 6.3552,
|
|
"mean_token_accuracy": 0.1318911150097847,
|
|
"num_tokens": 5258541.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.547457313537597,
|
|
"epoch": 0.22633924670103994,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004997821032931676,
|
|
"loss": 6.4627,
|
|
"mean_token_accuracy": 0.12480694651603699,
|
|
"num_tokens": 5268524.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.396187162399292,
|
|
"epoch": 0.22677619505374463,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499780730076846,
|
|
"loss": 6.3779,
|
|
"mean_token_accuracy": 0.1255694232881069,
|
|
"num_tokens": 5280702.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.43830943107605,
|
|
"epoch": 0.22721314340644935,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997793525491122,
|
|
"loss": 6.3554,
|
|
"mean_token_accuracy": 0.1204657144844532,
|
|
"num_tokens": 5291214.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.344881296157837,
|
|
"epoch": 0.22765009175915407,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997779707099926,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.13391299471259116,
|
|
"num_tokens": 5300729.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.431374835968017,
|
|
"epoch": 0.2280870401118588,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004997765845595138,
|
|
"loss": 6.4578,
|
|
"mean_token_accuracy": 0.12322496548295021,
|
|
"num_tokens": 5310551.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.486410856246948,
|
|
"epoch": 0.22852398846456348,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997751940977024,
|
|
"loss": 6.3379,
|
|
"mean_token_accuracy": 0.1314255066215992,
|
|
"num_tokens": 5320038.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.34283185005188,
|
|
"epoch": 0.2289609368172682,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997737993245848,
|
|
"loss": 6.3722,
|
|
"mean_token_accuracy": 0.1269502080976963,
|
|
"num_tokens": 5329753.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.414773797988891,
|
|
"epoch": 0.22939788516997292,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997724002401881,
|
|
"loss": 6.3641,
|
|
"mean_token_accuracy": 0.1279063567519188,
|
|
"num_tokens": 5340546.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.377361679077149,
|
|
"epoch": 0.2298348335226776,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997709968445391,
|
|
"loss": 6.4354,
|
|
"mean_token_accuracy": 0.12187184765934944,
|
|
"num_tokens": 5352097.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.543209218978882,
|
|
"epoch": 0.23027178187538233,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004997695891376644,
|
|
"loss": 6.3752,
|
|
"mean_token_accuracy": 0.12566474825143814,
|
|
"num_tokens": 5361646.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.391681861877442,
|
|
"epoch": 0.23070873022808705,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997681771195912,
|
|
"loss": 6.3519,
|
|
"mean_token_accuracy": 0.1263906978070736,
|
|
"num_tokens": 5371695.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.422570037841797,
|
|
"epoch": 0.23114567858079174,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997667607903466,
|
|
"loss": 6.4234,
|
|
"mean_token_accuracy": 0.12023279443383217,
|
|
"num_tokens": 5381978.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.589051151275635,
|
|
"epoch": 0.23158262693349646,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997653401499578,
|
|
"loss": 6.4247,
|
|
"mean_token_accuracy": 0.12453131377696991,
|
|
"num_tokens": 5391891.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.452299404144287,
|
|
"epoch": 0.23201957528620118,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499763915198452,
|
|
"loss": 6.3723,
|
|
"mean_token_accuracy": 0.1255788743495941,
|
|
"num_tokens": 5403172.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.394309711456299,
|
|
"epoch": 0.23245652363890587,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997624859358565,
|
|
"loss": 6.3823,
|
|
"mean_token_accuracy": 0.12750936523079873,
|
|
"num_tokens": 5413130.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.447233057022094,
|
|
"epoch": 0.2328934719916106,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997610523621988,
|
|
"loss": 6.4223,
|
|
"mean_token_accuracy": 0.12197845950722694,
|
|
"num_tokens": 5423510.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.41208930015564,
|
|
"epoch": 0.2333304203443153,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997596144775063,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.1339675985276699,
|
|
"num_tokens": 5433707.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.259990262985229,
|
|
"epoch": 0.23376736869702,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997581722818067,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.12899682372808458,
|
|
"num_tokens": 5444381.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.577976036071777,
|
|
"epoch": 0.23420431704972472,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997567257751275,
|
|
"loss": 6.3112,
|
|
"mean_token_accuracy": 0.12926476150751115,
|
|
"num_tokens": 5453905.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.344999027252197,
|
|
"epoch": 0.23464126540242944,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997552749574965,
|
|
"loss": 6.3311,
|
|
"mean_token_accuracy": 0.1283065065741539,
|
|
"num_tokens": 5464839.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.396442413330078,
|
|
"epoch": 0.23507821375513413,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997538198289416,
|
|
"loss": 6.3734,
|
|
"mean_token_accuracy": 0.12314258888363838,
|
|
"num_tokens": 5475459.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.396377086639404,
|
|
"epoch": 0.23551516210783885,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997523603894907,
|
|
"loss": 6.3758,
|
|
"mean_token_accuracy": 0.12924159169197083,
|
|
"num_tokens": 5484886.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.380730533599854,
|
|
"epoch": 0.23595211046054357,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997508966391717,
|
|
"loss": 6.3693,
|
|
"mean_token_accuracy": 0.1304370015859604,
|
|
"num_tokens": 5494803.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.3598357200622555,
|
|
"epoch": 0.2363890588132483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997494285780129,
|
|
"loss": 6.3124,
|
|
"mean_token_accuracy": 0.12956960424780845,
|
|
"num_tokens": 5504997.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.359509229660034,
|
|
"epoch": 0.23682600716595298,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997479562060421,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.13558572456240653,
|
|
"num_tokens": 5514492.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.440937232971192,
|
|
"epoch": 0.2372629555186577,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004997464795232877,
|
|
"loss": 6.361,
|
|
"mean_token_accuracy": 0.12250275984406471,
|
|
"num_tokens": 5524419.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.48492579460144,
|
|
"epoch": 0.23769990387136242,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997449985297782,
|
|
"loss": 6.3825,
|
|
"mean_token_accuracy": 0.13098835572600365,
|
|
"num_tokens": 5534289.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.397220230102539,
|
|
"epoch": 0.2381368522240671,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004997435132255418,
|
|
"loss": 6.2995,
|
|
"mean_token_accuracy": 0.13025546446442604,
|
|
"num_tokens": 5543034.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.376963567733765,
|
|
"epoch": 0.23857380057677183,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997420236106071,
|
|
"loss": 6.375,
|
|
"mean_token_accuracy": 0.12310315221548081,
|
|
"num_tokens": 5553291.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.4181102275848385,
|
|
"epoch": 0.23901074892947655,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997405296850026,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.1311754897236824,
|
|
"num_tokens": 5563772.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.461687088012695,
|
|
"epoch": 0.23944769728218124,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997390314487569,
|
|
"loss": 6.4034,
|
|
"mean_token_accuracy": 0.1266815669834614,
|
|
"num_tokens": 5574348.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.408790111541748,
|
|
"epoch": 0.23988464563488596,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004997375289018989,
|
|
"loss": 6.2539,
|
|
"mean_token_accuracy": 0.13011327236890793,
|
|
"num_tokens": 5583491.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.2955926895141605,
|
|
"epoch": 0.24032159398759068,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997360220444574,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.12347037270665169,
|
|
"num_tokens": 5594273.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.434036064147949,
|
|
"epoch": 0.24075854234029537,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997345108764611,
|
|
"loss": 6.3038,
|
|
"mean_token_accuracy": 0.13056106939911843,
|
|
"num_tokens": 5604529.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.390225028991699,
|
|
"epoch": 0.2411954906930001,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997329953979391,
|
|
"loss": 6.3111,
|
|
"mean_token_accuracy": 0.13571627363562583,
|
|
"num_tokens": 5614036.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.448512220382691,
|
|
"epoch": 0.2416324390457048,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997314756089206,
|
|
"loss": 6.3547,
|
|
"mean_token_accuracy": 0.1281716376543045,
|
|
"num_tokens": 5624036.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.41415810585022,
|
|
"epoch": 0.2420693873984095,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997299515094347,
|
|
"loss": 6.3511,
|
|
"mean_token_accuracy": 0.1302356503903866,
|
|
"num_tokens": 5633987.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.347924423217774,
|
|
"epoch": 0.24250633575111422,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997284230995105,
|
|
"loss": 6.2299,
|
|
"mean_token_accuracy": 0.13894670456647873,
|
|
"num_tokens": 5643905.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.3557435989379885,
|
|
"epoch": 0.24294328410381894,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997268903791773,
|
|
"loss": 6.4261,
|
|
"mean_token_accuracy": 0.12468690425157547,
|
|
"num_tokens": 5654922.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.401423168182373,
|
|
"epoch": 0.24338023245652363,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997253533484647,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.13697169572114945,
|
|
"num_tokens": 5664407.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.382416534423828,
|
|
"epoch": 0.24381718080922835,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997238120074021,
|
|
"loss": 6.322,
|
|
"mean_token_accuracy": 0.12700313106179237,
|
|
"num_tokens": 5674524.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.416257572174072,
|
|
"epoch": 0.24425412916193306,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997222663560188,
|
|
"loss": 6.3696,
|
|
"mean_token_accuracy": 0.12488905414938926,
|
|
"num_tokens": 5684691.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.357256698608398,
|
|
"epoch": 0.24469107751463778,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997207163943449,
|
|
"loss": 6.2772,
|
|
"mean_token_accuracy": 0.12989294528961182,
|
|
"num_tokens": 5693683.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.347806978225708,
|
|
"epoch": 0.24512802586734248,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997191621224098,
|
|
"loss": 6.3728,
|
|
"mean_token_accuracy": 0.12666576281189917,
|
|
"num_tokens": 5704394.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.309673023223877,
|
|
"epoch": 0.2455649742200472,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997176035402435,
|
|
"loss": 6.2908,
|
|
"mean_token_accuracy": 0.13173253908753396,
|
|
"num_tokens": 5715480.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.457736778259277,
|
|
"epoch": 0.2460019225727519,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997160406478758,
|
|
"loss": 6.2801,
|
|
"mean_token_accuracy": 0.13354317992925643,
|
|
"num_tokens": 5725973.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.301509189605713,
|
|
"epoch": 0.2464388709254566,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 6.3082,
|
|
"mean_token_accuracy": 0.13364396914839743,
|
|
"num_tokens": 5735798.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.436800575256347,
|
|
"epoch": 0.24687581927816132,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997129019326562,
|
|
"loss": 6.4021,
|
|
"mean_token_accuracy": 0.12107940614223481,
|
|
"num_tokens": 5746623.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.46128396987915,
|
|
"epoch": 0.24731276763086604,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997113261098645,
|
|
"loss": 6.3179,
|
|
"mean_token_accuracy": 0.12975894808769226,
|
|
"num_tokens": 5756526.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.367384910583496,
|
|
"epoch": 0.24774971598357073,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997097459769919,
|
|
"loss": 6.3136,
|
|
"mean_token_accuracy": 0.12942242249846458,
|
|
"num_tokens": 5766670.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.435496425628662,
|
|
"epoch": 0.24818666433627545,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997081615340685,
|
|
"loss": 6.3735,
|
|
"mean_token_accuracy": 0.12207994535565377,
|
|
"num_tokens": 5776473.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.467668104171753,
|
|
"epoch": 0.24862361268898017,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997065727811249,
|
|
"loss": 6.3977,
|
|
"mean_token_accuracy": 0.1273019216954708,
|
|
"num_tokens": 5787059.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.383358383178711,
|
|
"epoch": 0.24906056104168486,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997049797181915,
|
|
"loss": 6.3936,
|
|
"mean_token_accuracy": 0.12382100597023964,
|
|
"num_tokens": 5797367.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.367741394042969,
|
|
"epoch": 0.24949750939438958,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997033823452988,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.1279428631067276,
|
|
"num_tokens": 5806704.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.383842611312867,
|
|
"epoch": 0.2499344577470943,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997017806624774,
|
|
"loss": 6.3541,
|
|
"mean_token_accuracy": 0.12971674650907516,
|
|
"num_tokens": 5817797.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.511070632934571,
|
|
"epoch": 0.250371406099799,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997001746697582,
|
|
"loss": 6.3952,
|
|
"mean_token_accuracy": 0.12995700985193254,
|
|
"num_tokens": 5829270.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.367383050918579,
|
|
"epoch": 0.2508083544525037,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996985643671719,
|
|
"loss": 6.3112,
|
|
"mean_token_accuracy": 0.13145541176199912,
|
|
"num_tokens": 5839214.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.328347253799438,
|
|
"epoch": 0.2512453028052084,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996969497547495,
|
|
"loss": 6.3175,
|
|
"mean_token_accuracy": 0.1253244996070862,
|
|
"num_tokens": 5848171.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.370502042770386,
|
|
"epoch": 0.25168225115791315,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996953308325217,
|
|
"loss": 6.2276,
|
|
"mean_token_accuracy": 0.13664429858326912,
|
|
"num_tokens": 5858399.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.279939651489258,
|
|
"epoch": 0.25211919951061784,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996937076005198,
|
|
"loss": 6.2516,
|
|
"mean_token_accuracy": 0.13539692386984825,
|
|
"num_tokens": 5868212.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.395609283447266,
|
|
"epoch": 0.25255614786332253,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996920800587749,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.13084554225206374,
|
|
"num_tokens": 5877883.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.470597410202027,
|
|
"epoch": 0.2529930962160273,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996904482073181,
|
|
"loss": 6.316,
|
|
"mean_token_accuracy": 0.12910602539777755,
|
|
"num_tokens": 5887090.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.354488325119019,
|
|
"epoch": 0.25343004456873197,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996888120461808,
|
|
"loss": 6.3615,
|
|
"mean_token_accuracy": 0.12137048691511154,
|
|
"num_tokens": 5897491.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.437285137176514,
|
|
"epoch": 0.25386699292143666,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004996871715753943,
|
|
"loss": 6.3816,
|
|
"mean_token_accuracy": 0.13091239109635353,
|
|
"num_tokens": 5908494.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.450480365753174,
|
|
"epoch": 0.2543039412741414,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049968552679499,
|
|
"loss": 6.4289,
|
|
"mean_token_accuracy": 0.11489628329873085,
|
|
"num_tokens": 5919708.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.467782783508301,
|
|
"epoch": 0.2547408896268461,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004996838777049998,
|
|
"loss": 6.2838,
|
|
"mean_token_accuracy": 0.1296510674059391,
|
|
"num_tokens": 5930122.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.322751808166504,
|
|
"epoch": 0.2551778379795508,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499682224305455,
|
|
"loss": 6.2882,
|
|
"mean_token_accuracy": 0.12527415454387664,
|
|
"num_tokens": 5940033.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.387962388992309,
|
|
"epoch": 0.25561478633225554,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996805665963874,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.12325938194990158,
|
|
"num_tokens": 5949335.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.3954322814941404,
|
|
"epoch": 0.25605173468496023,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996789045778287,
|
|
"loss": 6.3278,
|
|
"mean_token_accuracy": 0.13017525672912597,
|
|
"num_tokens": 5959299.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.388931512832642,
|
|
"epoch": 0.2564886830376649,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004996772382498111,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.12773813903331757,
|
|
"num_tokens": 5970114.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.375958824157715,
|
|
"epoch": 0.25692563139036967,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996755676123662,
|
|
"loss": 6.3937,
|
|
"mean_token_accuracy": 0.12411935850977898,
|
|
"num_tokens": 5979630.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.466895532608032,
|
|
"epoch": 0.25736257974307436,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996738926655262,
|
|
"loss": 6.3775,
|
|
"mean_token_accuracy": 0.12354947850108147,
|
|
"num_tokens": 5990190.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.422803926467895,
|
|
"epoch": 0.25779952809577905,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996722134093231,
|
|
"loss": 6.3873,
|
|
"mean_token_accuracy": 0.12062846720218659,
|
|
"num_tokens": 6000706.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.330030822753907,
|
|
"epoch": 0.2582364764484838,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996705298437894,
|
|
"loss": 6.3495,
|
|
"mean_token_accuracy": 0.1309203699231148,
|
|
"num_tokens": 6011274.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.472089052200317,
|
|
"epoch": 0.2586734248011885,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996688419689572,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.13017945513129234,
|
|
"num_tokens": 6021481.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.277119541168213,
|
|
"epoch": 0.25911037315389324,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996671497848589,
|
|
"loss": 6.3421,
|
|
"mean_token_accuracy": 0.1263204239308834,
|
|
"num_tokens": 6032091.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.395982933044434,
|
|
"epoch": 0.25954732150659793,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996654532915269,
|
|
"loss": 6.3556,
|
|
"mean_token_accuracy": 0.11947837546467781,
|
|
"num_tokens": 6043371.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.389321994781494,
|
|
"epoch": 0.2599842698593026,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004996637524889937,
|
|
"loss": 6.299,
|
|
"mean_token_accuracy": 0.12635288685560225,
|
|
"num_tokens": 6052812.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.3647873878479,
|
|
"epoch": 0.26042121821200737,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996620473772921,
|
|
"loss": 6.2899,
|
|
"mean_token_accuracy": 0.1310460463166237,
|
|
"num_tokens": 6064033.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.37945704460144,
|
|
"epoch": 0.26085816656471206,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996603379564546,
|
|
"loss": 6.3966,
|
|
"mean_token_accuracy": 0.1263035662472248,
|
|
"num_tokens": 6075837.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.492451429367065,
|
|
"epoch": 0.26129511491741675,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004996586242265142,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.133855964243412,
|
|
"num_tokens": 6085514.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.431004238128662,
|
|
"epoch": 0.2617320632701215,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996569061875036,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.13191918209195136,
|
|
"num_tokens": 6094992.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.3046787738800045,
|
|
"epoch": 0.2621690116228262,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996551838394559,
|
|
"loss": 6.2998,
|
|
"mean_token_accuracy": 0.1289274014532566,
|
|
"num_tokens": 6104841.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2621690116228262,
|
|
"eval_entropy": 6.176911606859743,
|
|
"eval_loss": 6.340244770050049,
|
|
"eval_mean_token_accuracy": 0.1347498616543024,
|
|
"eval_num_tokens": 6104841.0,
|
|
"eval_runtime": 28.264,
|
|
"eval_samples_per_second": 1309.582,
|
|
"eval_steps_per_second": 163.707,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.26025013923645,
|
|
"epoch": 0.2626059599755309,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499653457182404,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.1339375652372837,
|
|
"num_tokens": 6114830.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.356398057937622,
|
|
"epoch": 0.2630429083282356,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996517262163811,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.1326840378344059,
|
|
"num_tokens": 6125165.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.354022789001465,
|
|
"epoch": 0.2634798566809403,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996499909414204,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.12968195155262946,
|
|
"num_tokens": 6135670.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.269655513763428,
|
|
"epoch": 0.263916805033645,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996482513575551,
|
|
"loss": 6.2436,
|
|
"mean_token_accuracy": 0.14049533605575562,
|
|
"num_tokens": 6146055.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.316104173660278,
|
|
"epoch": 0.26435375338634975,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996465074648186,
|
|
"loss": 6.2646,
|
|
"mean_token_accuracy": 0.1341840773820877,
|
|
"num_tokens": 6155941.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.4075220108032225,
|
|
"epoch": 0.26479070173905445,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996447592632444,
|
|
"loss": 6.3538,
|
|
"mean_token_accuracy": 0.13025905638933183,
|
|
"num_tokens": 6166291.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.35784592628479,
|
|
"epoch": 0.26522765009175914,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004996430067528661,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.1270274318754673,
|
|
"num_tokens": 6175294.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.434535026550293,
|
|
"epoch": 0.2656645984444639,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996412499337172,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.13426331281661988,
|
|
"num_tokens": 6185273.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.3774840354919435,
|
|
"epoch": 0.2661015467971686,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996394888058314,
|
|
"loss": 6.2649,
|
|
"mean_token_accuracy": 0.13806363344192504,
|
|
"num_tokens": 6195075.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.239452505111695,
|
|
"epoch": 0.26653849514987327,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996377233692425,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.14420341700315475,
|
|
"num_tokens": 6206018.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.349570274353027,
|
|
"epoch": 0.266975443502578,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004996359536239843,
|
|
"loss": 6.2962,
|
|
"mean_token_accuracy": 0.12873756289482116,
|
|
"num_tokens": 6216577.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.418041610717774,
|
|
"epoch": 0.2674123918552827,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996341795700908,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.1307532049715519,
|
|
"num_tokens": 6226521.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.285133123397827,
|
|
"epoch": 0.2678493402079874,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004996324012075961,
|
|
"loss": 6.2903,
|
|
"mean_token_accuracy": 0.13310011625289916,
|
|
"num_tokens": 6236509.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.4100165367126465,
|
|
"epoch": 0.26828628856069214,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996306185365341,
|
|
"loss": 6.2967,
|
|
"mean_token_accuracy": 0.13204259872436525,
|
|
"num_tokens": 6246584.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.364015245437622,
|
|
"epoch": 0.26872323691339683,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004996288315569393,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.12507192716002463,
|
|
"num_tokens": 6256881.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.390865612030029,
|
|
"epoch": 0.2691601852661015,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996270402688457,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.130061012506485,
|
|
"num_tokens": 6266380.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.405587100982666,
|
|
"epoch": 0.2695971336188063,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004996252446722877,
|
|
"loss": 6.3237,
|
|
"mean_token_accuracy": 0.13164027556777,
|
|
"num_tokens": 6274872.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.342977666854859,
|
|
"epoch": 0.27003408197151096,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004996234447673,
|
|
"loss": 6.329,
|
|
"mean_token_accuracy": 0.12905460298061372,
|
|
"num_tokens": 6286167.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.405268287658691,
|
|
"epoch": 0.27047103032421566,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996216405539169,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.12965068444609643,
|
|
"num_tokens": 6295898.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.39916033744812,
|
|
"epoch": 0.2709079786769204,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996198320321728,
|
|
"loss": 6.3046,
|
|
"mean_token_accuracy": 0.13214947730302812,
|
|
"num_tokens": 6306543.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.35726146697998,
|
|
"epoch": 0.2713449270296251,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004996180192021029,
|
|
"loss": 6.2959,
|
|
"mean_token_accuracy": 0.12381328046321868,
|
|
"num_tokens": 6317709.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.319500064849853,
|
|
"epoch": 0.2717818753823298,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996162020637415,
|
|
"loss": 6.2633,
|
|
"mean_token_accuracy": 0.1328990489244461,
|
|
"num_tokens": 6326874.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.3565386772155765,
|
|
"epoch": 0.27221882373503453,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996143806171238,
|
|
"loss": 6.3577,
|
|
"mean_token_accuracy": 0.12793173417448997,
|
|
"num_tokens": 6337943.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.36138949394226,
|
|
"epoch": 0.2726557720877392,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996125548622845,
|
|
"loss": 6.4066,
|
|
"mean_token_accuracy": 0.12947756350040435,
|
|
"num_tokens": 6348442.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.437826919555664,
|
|
"epoch": 0.2730927204404439,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996107247992587,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.13008005246520044,
|
|
"num_tokens": 6358675.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.430121755599975,
|
|
"epoch": 0.27352966879314866,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004996088904280815,
|
|
"loss": 6.3482,
|
|
"mean_token_accuracy": 0.12924067303538322,
|
|
"num_tokens": 6368631.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.361489963531494,
|
|
"epoch": 0.27396661714585335,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996070517487881,
|
|
"loss": 6.2283,
|
|
"mean_token_accuracy": 0.13231453523039818,
|
|
"num_tokens": 6378709.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.326501083374024,
|
|
"epoch": 0.27440356549855804,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996052087614138,
|
|
"loss": 6.3593,
|
|
"mean_token_accuracy": 0.12339177057147026,
|
|
"num_tokens": 6389686.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.40691351890564,
|
|
"epoch": 0.2748405138512628,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996033614659938,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.1295914389193058,
|
|
"num_tokens": 6399447.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.406366586685181,
|
|
"epoch": 0.2752774622039675,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996015098625638,
|
|
"loss": 6.3102,
|
|
"mean_token_accuracy": 0.13160308226943015,
|
|
"num_tokens": 6408891.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.349420166015625,
|
|
"epoch": 0.2757144105566722,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000499599653951159,
|
|
"loss": 6.2697,
|
|
"mean_token_accuracy": 0.13136155307292938,
|
|
"num_tokens": 6419471.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.306204700469971,
|
|
"epoch": 0.2761513589093769,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004995977937318153,
|
|
"loss": 6.2657,
|
|
"mean_token_accuracy": 0.12809676453471183,
|
|
"num_tokens": 6430445.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.458633613586426,
|
|
"epoch": 0.2765883072620816,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499595929204568,
|
|
"loss": 6.2973,
|
|
"mean_token_accuracy": 0.12807265892624856,
|
|
"num_tokens": 6440821.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.287018537521362,
|
|
"epoch": 0.27702525561478636,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004995940603694533,
|
|
"loss": 6.2048,
|
|
"mean_token_accuracy": 0.1330143354833126,
|
|
"num_tokens": 6450958.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.275545883178711,
|
|
"epoch": 0.27746220396749105,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995921872265067,
|
|
"loss": 6.3197,
|
|
"mean_token_accuracy": 0.1292585127055645,
|
|
"num_tokens": 6462106.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.415719652175904,
|
|
"epoch": 0.27789915232019574,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995903097757643,
|
|
"loss": 6.1978,
|
|
"mean_token_accuracy": 0.13924278244376181,
|
|
"num_tokens": 6471890.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.258716344833374,
|
|
"epoch": 0.2783361006729005,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004995884280172622,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.13054869547486306,
|
|
"num_tokens": 6481959.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.321152019500732,
|
|
"epoch": 0.2787730490256052,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004995865419510362,
|
|
"loss": 6.2624,
|
|
"mean_token_accuracy": 0.13158614411950112,
|
|
"num_tokens": 6492086.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.370549821853638,
|
|
"epoch": 0.27920999737830987,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004995846515771227,
|
|
"loss": 6.2923,
|
|
"mean_token_accuracy": 0.12675996571779252,
|
|
"num_tokens": 6502530.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.380843448638916,
|
|
"epoch": 0.2796469457310146,
|
|
"grad_norm": 6.15625,
|
|
"learning_rate": 0.000499582756895558,
|
|
"loss": 6.2918,
|
|
"mean_token_accuracy": 0.13517867475748063,
|
|
"num_tokens": 6511600.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.403674364089966,
|
|
"epoch": 0.2800838940837193,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004995808579063782,
|
|
"loss": 6.2769,
|
|
"mean_token_accuracy": 0.12687014937400817,
|
|
"num_tokens": 6522712.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.185982513427734,
|
|
"epoch": 0.280520842436424,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00049957895460962,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.14963648468255997,
|
|
"num_tokens": 6532472.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.313288688659668,
|
|
"epoch": 0.28095779078912875,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004995770470053197,
|
|
"loss": 6.1959,
|
|
"mean_token_accuracy": 0.1432195670902729,
|
|
"num_tokens": 6541778.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.362827157974243,
|
|
"epoch": 0.28139473914183344,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004995751350935139,
|
|
"loss": 6.1898,
|
|
"mean_token_accuracy": 0.1278350219130516,
|
|
"num_tokens": 6552368.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.309809732437134,
|
|
"epoch": 0.28183168749453813,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004995732188742395,
|
|
"loss": 6.2401,
|
|
"mean_token_accuracy": 0.13236903101205827,
|
|
"num_tokens": 6562593.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.362755393981933,
|
|
"epoch": 0.2822686358472429,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004995712983475329,
|
|
"loss": 6.2941,
|
|
"mean_token_accuracy": 0.1256416767835617,
|
|
"num_tokens": 6572695.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.330557012557984,
|
|
"epoch": 0.28270558419994757,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004995693735134313,
|
|
"loss": 6.2627,
|
|
"mean_token_accuracy": 0.13055431172251702,
|
|
"num_tokens": 6581671.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.363641738891602,
|
|
"epoch": 0.28314253255265226,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995674443719713,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.13069088533520698,
|
|
"num_tokens": 6590460.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.376384353637695,
|
|
"epoch": 0.283579480905357,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00049956551092319,
|
|
"loss": 6.2724,
|
|
"mean_token_accuracy": 0.12941850423812867,
|
|
"num_tokens": 6599892.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.371181440353394,
|
|
"epoch": 0.2840164292580617,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004995635731671247,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.12331348508596421,
|
|
"num_tokens": 6610530.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.366174936294556,
|
|
"epoch": 0.2844533776107664,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004995616311038124,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.13390601947903633,
|
|
"num_tokens": 6621117.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.360169410705566,
|
|
"epoch": 0.28489032596347114,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004995596847332901,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.1278347410261631,
|
|
"num_tokens": 6631521.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.463128566741943,
|
|
"epoch": 0.2853272743161758,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004995577340555956,
|
|
"loss": 6.3904,
|
|
"mean_token_accuracy": 0.12619309723377228,
|
|
"num_tokens": 6642180.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.35454044342041,
|
|
"epoch": 0.2857642226688805,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995557790707661,
|
|
"loss": 6.3048,
|
|
"mean_token_accuracy": 0.13104436099529265,
|
|
"num_tokens": 6652735.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.3466637134552,
|
|
"epoch": 0.28620117102158527,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499553819778839,
|
|
"loss": 6.2974,
|
|
"mean_token_accuracy": 0.13476421907544137,
|
|
"num_tokens": 6663135.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.359936475753784,
|
|
"epoch": 0.28663811937428996,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000499551856179852,
|
|
"loss": 6.3108,
|
|
"mean_token_accuracy": 0.12338437512516975,
|
|
"num_tokens": 6673375.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.402853918075562,
|
|
"epoch": 0.28707506772699465,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995498882738428,
|
|
"loss": 6.2559,
|
|
"mean_token_accuracy": 0.13144599050283431,
|
|
"num_tokens": 6683101.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.4232560157775875,
|
|
"epoch": 0.2875120160796994,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004995479160608491,
|
|
"loss": 6.3164,
|
|
"mean_token_accuracy": 0.13341468274593354,
|
|
"num_tokens": 6692763.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.3722888946533205,
|
|
"epoch": 0.2879489644324041,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004995459395409085,
|
|
"loss": 6.3002,
|
|
"mean_token_accuracy": 0.12749466225504874,
|
|
"num_tokens": 6702833.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.370219612121582,
|
|
"epoch": 0.2883859127851088,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004995439587140593,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.12153316885232926,
|
|
"num_tokens": 6713083.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.3562493324279785,
|
|
"epoch": 0.2888228611378135,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004995419735803392,
|
|
"loss": 6.2323,
|
|
"mean_token_accuracy": 0.12721289396286012,
|
|
"num_tokens": 6722501.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.342270755767823,
|
|
"epoch": 0.2892598094905182,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004995399841397865,
|
|
"loss": 6.2746,
|
|
"mean_token_accuracy": 0.12882607579231262,
|
|
"num_tokens": 6731961.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.394270992279052,
|
|
"epoch": 0.2896967578432229,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004995379903924392,
|
|
"loss": 6.2678,
|
|
"mean_token_accuracy": 0.1273388981819153,
|
|
"num_tokens": 6742576.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.378604507446289,
|
|
"epoch": 0.29013370619592765,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004995359923383356,
|
|
"loss": 6.2775,
|
|
"mean_token_accuracy": 0.1297510638833046,
|
|
"num_tokens": 6753066.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.392166423797607,
|
|
"epoch": 0.29057065454863235,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499533989977514,
|
|
"loss": 6.415,
|
|
"mean_token_accuracy": 0.12183653116226197,
|
|
"num_tokens": 6764455.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.418638849258423,
|
|
"epoch": 0.29100760290133704,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004995319833100128,
|
|
"loss": 6.2895,
|
|
"mean_token_accuracy": 0.13210763931274414,
|
|
"num_tokens": 6774655.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.320852899551392,
|
|
"epoch": 0.2914445512540418,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004995299723358705,
|
|
"loss": 6.2492,
|
|
"mean_token_accuracy": 0.13643589839339257,
|
|
"num_tokens": 6785942.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.265985202789307,
|
|
"epoch": 0.2918814996067465,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995279570551257,
|
|
"loss": 6.2215,
|
|
"mean_token_accuracy": 0.13763746991753578,
|
|
"num_tokens": 6795355.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.3764269828796385,
|
|
"epoch": 0.29231844795945117,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000499525937467817,
|
|
"loss": 6.28,
|
|
"mean_token_accuracy": 0.12502550855278968,
|
|
"num_tokens": 6805579.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.417794609069825,
|
|
"epoch": 0.2927553963121559,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995239135739833,
|
|
"loss": 6.2996,
|
|
"mean_token_accuracy": 0.12507596090435982,
|
|
"num_tokens": 6814878.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.373486852645874,
|
|
"epoch": 0.2931923446648606,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004995218853736631,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.141049724817276,
|
|
"num_tokens": 6824533.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.191241073608398,
|
|
"epoch": 0.29362929301756535,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004995198528668956,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.14864774271845818,
|
|
"num_tokens": 6835529.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.3345029830932615,
|
|
"epoch": 0.29406624137027004,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004995178160537197,
|
|
"loss": 6.3096,
|
|
"mean_token_accuracy": 0.13062748312950134,
|
|
"num_tokens": 6845679.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.46401891708374,
|
|
"epoch": 0.29450318972297473,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004995157749341744,
|
|
"loss": 6.2967,
|
|
"mean_token_accuracy": 0.12413412407040596,
|
|
"num_tokens": 6855876.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.382764053344727,
|
|
"epoch": 0.2949401380756795,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004995137295082989,
|
|
"loss": 6.3535,
|
|
"mean_token_accuracy": 0.12331586331129074,
|
|
"num_tokens": 6866200.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.389991807937622,
|
|
"epoch": 0.2953770864283842,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004995116797761324,
|
|
"loss": 6.2298,
|
|
"mean_token_accuracy": 0.13341188728809356,
|
|
"num_tokens": 6875191.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.292295694351196,
|
|
"epoch": 0.29581403478108886,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004995096257377143,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.1290462002158165,
|
|
"num_tokens": 6885352.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.323753833770752,
|
|
"epoch": 0.2962509831337936,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004995075673930839,
|
|
"loss": 6.2947,
|
|
"mean_token_accuracy": 0.12870371863245963,
|
|
"num_tokens": 6895585.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.415827417373658,
|
|
"epoch": 0.2966879314864983,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004995055047422808,
|
|
"loss": 6.2397,
|
|
"mean_token_accuracy": 0.1292224906384945,
|
|
"num_tokens": 6905532.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.278207731246948,
|
|
"epoch": 0.297124879839203,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995034377853443,
|
|
"loss": 6.2564,
|
|
"mean_token_accuracy": 0.13268594294786454,
|
|
"num_tokens": 6915835.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.316234302520752,
|
|
"epoch": 0.29756182819190774,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995013665223143,
|
|
"loss": 6.2921,
|
|
"mean_token_accuracy": 0.1291264720261097,
|
|
"num_tokens": 6925964.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.4064103126525875,
|
|
"epoch": 0.29799877654461243,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004994992909532305,
|
|
"loss": 6.2362,
|
|
"mean_token_accuracy": 0.13458333984017373,
|
|
"num_tokens": 6936145.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.3627848625183105,
|
|
"epoch": 0.2984357248973171,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004994972110781326,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.13037536144256592,
|
|
"num_tokens": 6945557.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.272304630279541,
|
|
"epoch": 0.29887267325002187,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004994951268970606,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.12965808659791947,
|
|
"num_tokens": 6955147.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.297464752197266,
|
|
"epoch": 0.29930962160272656,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004994930384100545,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.13216258585453033,
|
|
"num_tokens": 6964024.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.344718933105469,
|
|
"epoch": 0.29974656995543125,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994909456171541,
|
|
"loss": 6.2799,
|
|
"mean_token_accuracy": 0.13039335906505584,
|
|
"num_tokens": 6974399.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.280664157867432,
|
|
"epoch": 0.300183518308136,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994888485183998,
|
|
"loss": 6.2214,
|
|
"mean_token_accuracy": 0.13267827704548835,
|
|
"num_tokens": 6984324.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.359601449966431,
|
|
"epoch": 0.3006204666608407,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499486747113832,
|
|
"loss": 6.241,
|
|
"mean_token_accuracy": 0.1327981173992157,
|
|
"num_tokens": 6995659.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.401485824584961,
|
|
"epoch": 0.3010574150135454,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004994846414034905,
|
|
"loss": 6.3482,
|
|
"mean_token_accuracy": 0.1251749128103256,
|
|
"num_tokens": 7006463.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.366568899154663,
|
|
"epoch": 0.30149436336625013,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000499482531387416,
|
|
"loss": 6.2367,
|
|
"mean_token_accuracy": 0.13053662180900574,
|
|
"num_tokens": 7016188.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.330869817733765,
|
|
"epoch": 0.3019313117189548,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004994804170656489,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.12821143344044686,
|
|
"num_tokens": 7028435.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.3709094524383545,
|
|
"epoch": 0.3023682600716595,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004994782984382299,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.13231005817651748,
|
|
"num_tokens": 7037992.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.352482557296753,
|
|
"epoch": 0.30280520842436426,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004994761755051995,
|
|
"loss": 6.2831,
|
|
"mean_token_accuracy": 0.12955223843455316,
|
|
"num_tokens": 7048743.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.381830358505249,
|
|
"epoch": 0.30324215677706895,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004994740482665982,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.1312493935227394,
|
|
"num_tokens": 7059524.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.291852378845215,
|
|
"epoch": 0.30367910512977364,
|
|
"grad_norm": 9.5625,
|
|
"learning_rate": 0.0004994719167224672,
|
|
"loss": 6.2339,
|
|
"mean_token_accuracy": 0.12652599215507507,
|
|
"num_tokens": 7069742.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.2860442161560055,
|
|
"epoch": 0.3041160534824784,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004994697808728472,
|
|
"loss": 6.2943,
|
|
"mean_token_accuracy": 0.13188235983252525,
|
|
"num_tokens": 7079909.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.4090958595275875,
|
|
"epoch": 0.3045530018351831,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994676407177791,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.13042071908712388,
|
|
"num_tokens": 7089136.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.4032796859741214,
|
|
"epoch": 0.30498995018788777,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004994654962573043,
|
|
"loss": 6.3154,
|
|
"mean_token_accuracy": 0.13368391543626784,
|
|
"num_tokens": 7099621.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.346981525421143,
|
|
"epoch": 0.3054268985405925,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004994633474914634,
|
|
"loss": 6.1712,
|
|
"mean_token_accuracy": 0.13378375470638276,
|
|
"num_tokens": 7109599.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.18639817237854,
|
|
"epoch": 0.3058638468932972,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004994611944202979,
|
|
"loss": 6.2166,
|
|
"mean_token_accuracy": 0.13542467579245568,
|
|
"num_tokens": 7120733.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.3771179676055905,
|
|
"epoch": 0.3063007952460019,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004994590370438492,
|
|
"loss": 6.2971,
|
|
"mean_token_accuracy": 0.12855091989040374,
|
|
"num_tokens": 7129871.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.4098076820373535,
|
|
"epoch": 0.30673774359870665,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994568753621585,
|
|
"loss": 6.2136,
|
|
"mean_token_accuracy": 0.1323453053832054,
|
|
"num_tokens": 7139167.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.232396030426026,
|
|
"epoch": 0.30717469195141134,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004994547093752673,
|
|
"loss": 6.2976,
|
|
"mean_token_accuracy": 0.12436885684728623,
|
|
"num_tokens": 7150534.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.342797899246216,
|
|
"epoch": 0.30761164030411603,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004994525390832171,
|
|
"loss": 6.227,
|
|
"mean_token_accuracy": 0.13226970210671424,
|
|
"num_tokens": 7160472.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.419403028488159,
|
|
"epoch": 0.3080485886568208,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994503644860497,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.1302813246846199,
|
|
"num_tokens": 7171636.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.316999244689941,
|
|
"epoch": 0.30848553700952547,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004994481855838067,
|
|
"loss": 6.2156,
|
|
"mean_token_accuracy": 0.1317649282515049,
|
|
"num_tokens": 7182163.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.308993196487426,
|
|
"epoch": 0.30892248536223016,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004994460023765298,
|
|
"loss": 6.2317,
|
|
"mean_token_accuracy": 0.13583657294511794,
|
|
"num_tokens": 7191694.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.351598787307739,
|
|
"epoch": 0.3093594337149349,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000499443814864261,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.13465951904654502,
|
|
"num_tokens": 7202813.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.349387216567993,
|
|
"epoch": 0.3097963820676396,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994416230470422,
|
|
"loss": 6.2717,
|
|
"mean_token_accuracy": 0.12884895727038384,
|
|
"num_tokens": 7213226.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.407685232162476,
|
|
"epoch": 0.3102333304203443,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004994394269249155,
|
|
"loss": 6.2859,
|
|
"mean_token_accuracy": 0.12866515889763833,
|
|
"num_tokens": 7223520.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.315626335144043,
|
|
"epoch": 0.31067027877304904,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004994372264979231,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.1384662352502346,
|
|
"num_tokens": 7232651.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.338417482376099,
|
|
"epoch": 0.3111072271257537,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994350217661069,
|
|
"loss": 6.2752,
|
|
"mean_token_accuracy": 0.12966468408703805,
|
|
"num_tokens": 7242064.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.3671448707580565,
|
|
"epoch": 0.3115441754784585,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004994328127295095,
|
|
"loss": 6.2833,
|
|
"mean_token_accuracy": 0.1294167585670948,
|
|
"num_tokens": 7253048.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.33545069694519,
|
|
"epoch": 0.31198112383116317,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004994305993881731,
|
|
"loss": 6.2658,
|
|
"mean_token_accuracy": 0.13346811681985854,
|
|
"num_tokens": 7262516.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.290219306945801,
|
|
"epoch": 0.31241807218386786,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994283817421402,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.13820456489920616,
|
|
"num_tokens": 7272079.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.292543888092041,
|
|
"epoch": 0.3128550205365726,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004994261597914534,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.14289118051528932,
|
|
"num_tokens": 7282150.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.304704809188843,
|
|
"epoch": 0.3132919688892773,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004994239335361552,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.12817902565002443,
|
|
"num_tokens": 7291782.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.298792600631714,
|
|
"epoch": 0.313728917241982,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004994217029762884,
|
|
"loss": 6.2257,
|
|
"mean_token_accuracy": 0.13249474465847016,
|
|
"num_tokens": 7301472.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.3423254013061525,
|
|
"epoch": 0.31416586559468673,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004994194681118957,
|
|
"loss": 6.207,
|
|
"mean_token_accuracy": 0.13881093189120292,
|
|
"num_tokens": 7311456.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.373311948776245,
|
|
"epoch": 0.3146028139473914,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00049941722894302,
|
|
"loss": 6.2749,
|
|
"mean_token_accuracy": 0.13226548358798026,
|
|
"num_tokens": 7321106.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.356042814254761,
|
|
"epoch": 0.3150397623000961,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004994149854697042,
|
|
"loss": 6.2768,
|
|
"mean_token_accuracy": 0.13341066539287566,
|
|
"num_tokens": 7331232.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.335075378417969,
|
|
"epoch": 0.31547671065280086,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994127376919916,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.12598878741264344,
|
|
"num_tokens": 7341560.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.394324016571045,
|
|
"epoch": 0.31591365900550555,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004994104856099249,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.12981204688549042,
|
|
"num_tokens": 7350923.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.276216506958008,
|
|
"epoch": 0.31635060735821025,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004994082292235476,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.14145579785108567,
|
|
"num_tokens": 7360121.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.232924699783325,
|
|
"epoch": 0.316787555710915,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004994059685329027,
|
|
"loss": 6.254,
|
|
"mean_token_accuracy": 0.13218581676483154,
|
|
"num_tokens": 7370823.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.348323106765747,
|
|
"epoch": 0.3172245040636197,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000499403703538034,
|
|
"loss": 6.2037,
|
|
"mean_token_accuracy": 0.12940399199724198,
|
|
"num_tokens": 7380102.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.337209701538086,
|
|
"epoch": 0.3176614524163244,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994014342389845,
|
|
"loss": 6.2138,
|
|
"mean_token_accuracy": 0.13238532990217208,
|
|
"num_tokens": 7389909.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.338866519927978,
|
|
"epoch": 0.3180984007690291,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004993991606357979,
|
|
"loss": 6.2981,
|
|
"mean_token_accuracy": 0.13026088103652,
|
|
"num_tokens": 7401092.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.298194074630738,
|
|
"epoch": 0.3185353491217338,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004993968827285179,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.12618000954389572,
|
|
"num_tokens": 7412155.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.267037105560303,
|
|
"epoch": 0.3189722974744385,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004993946005171881,
|
|
"loss": 6.1407,
|
|
"mean_token_accuracy": 0.14138761162757874,
|
|
"num_tokens": 7421981.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.311609172821045,
|
|
"epoch": 0.31940924582714325,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004993923140018523,
|
|
"loss": 6.1799,
|
|
"mean_token_accuracy": 0.13153257742524146,
|
|
"num_tokens": 7432298.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.261382436752319,
|
|
"epoch": 0.31984619417984794,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004993900231825542,
|
|
"loss": 6.2281,
|
|
"mean_token_accuracy": 0.13518029749393462,
|
|
"num_tokens": 7442575.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.312797546386719,
|
|
"epoch": 0.32028314253255263,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004993877280593381,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.13454039469361306,
|
|
"num_tokens": 7453072.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.33916826248169,
|
|
"epoch": 0.3207200908852574,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004993854286322477,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.13830483630299567,
|
|
"num_tokens": 7463173.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.2755554676055905,
|
|
"epoch": 0.32115703923796207,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004993831249013272,
|
|
"loss": 6.271,
|
|
"mean_token_accuracy": 0.13103101775050163,
|
|
"num_tokens": 7473751.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.340389108657837,
|
|
"epoch": 0.32159398759066676,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004993808168666207,
|
|
"loss": 6.0924,
|
|
"mean_token_accuracy": 0.14098680019378662,
|
|
"num_tokens": 7483233.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.3110268115997314,
|
|
"epoch": 0.3220309359433715,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004993785045281726,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.12528955116868018,
|
|
"num_tokens": 7493152.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.309295558929444,
|
|
"epoch": 0.3224678842960762,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004993761878860272,
|
|
"loss": 6.1858,
|
|
"mean_token_accuracy": 0.13619687259197236,
|
|
"num_tokens": 7502463.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.379939603805542,
|
|
"epoch": 0.3229048326487809,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000499373866940229,
|
|
"loss": 6.235,
|
|
"mean_token_accuracy": 0.1337234690785408,
|
|
"num_tokens": 7512301.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.257325315475464,
|
|
"epoch": 0.32334178100148564,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004993715416908225,
|
|
"loss": 6.2947,
|
|
"mean_token_accuracy": 0.13028813749551774,
|
|
"num_tokens": 7522591.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.353185701370239,
|
|
"epoch": 0.32377872935419033,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004993692121378521,
|
|
"loss": 6.2691,
|
|
"mean_token_accuracy": 0.13103109523653983,
|
|
"num_tokens": 7532400.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.37238621711731,
|
|
"epoch": 0.324215677706895,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004993668782813629,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.13341537714004517,
|
|
"num_tokens": 7542163.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.2288731098175045,
|
|
"epoch": 0.32465262605959977,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004993645401213992,
|
|
"loss": 6.1762,
|
|
"mean_token_accuracy": 0.13410028740763663,
|
|
"num_tokens": 7551638.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.326100063323975,
|
|
"epoch": 0.32508957441230446,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993621976580061,
|
|
"loss": 6.2469,
|
|
"mean_token_accuracy": 0.13389818891882896,
|
|
"num_tokens": 7561230.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.35606951713562,
|
|
"epoch": 0.32552652276500915,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004993598508912285,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.13896814957261086,
|
|
"num_tokens": 7570962.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.1932018280029295,
|
|
"epoch": 0.3259634711177139,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004993574998211114,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.13531308993697166,
|
|
"num_tokens": 7581454.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.292673969268799,
|
|
"epoch": 0.3264004194704186,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993551444476998,
|
|
"loss": 6.1783,
|
|
"mean_token_accuracy": 0.13669705763459206,
|
|
"num_tokens": 7591497.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.3870453357696535,
|
|
"epoch": 0.3268373678231233,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004993527847710392,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.1389164596796036,
|
|
"num_tokens": 7600719.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.305917978286743,
|
|
"epoch": 0.32727431617582803,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004993504207911744,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.13561010509729385,
|
|
"num_tokens": 7610550.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.306847190856933,
|
|
"epoch": 0.3277112645285327,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004993480525081511,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.13858453631401063,
|
|
"num_tokens": 7620472.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.393995046615601,
|
|
"epoch": 0.3281482128812374,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004993456799220145,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.1334797091782093,
|
|
"num_tokens": 7630354.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.28503041267395,
|
|
"epoch": 0.32858516123394216,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004993433030328103,
|
|
"loss": 6.1979,
|
|
"mean_token_accuracy": 0.13771358877420425,
|
|
"num_tokens": 7639689.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.265411520004273,
|
|
"epoch": 0.32902210958664685,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004993409218405839,
|
|
"loss": 6.2332,
|
|
"mean_token_accuracy": 0.12891449257731438,
|
|
"num_tokens": 7649319.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.39034948348999,
|
|
"epoch": 0.3294590579393516,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004993385363453812,
|
|
"loss": 6.2413,
|
|
"mean_token_accuracy": 0.13170438036322593,
|
|
"num_tokens": 7659008.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.33780426979065,
|
|
"epoch": 0.3298960062920563,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004993361465472477,
|
|
"loss": 6.1893,
|
|
"mean_token_accuracy": 0.13954115957021712,
|
|
"num_tokens": 7669064.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.2886542797088625,
|
|
"epoch": 0.330332954644761,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993337524462295,
|
|
"loss": 6.2472,
|
|
"mean_token_accuracy": 0.13983521163463591,
|
|
"num_tokens": 7679122.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.251172590255737,
|
|
"epoch": 0.3307699029974657,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.0004993313540423722,
|
|
"loss": 6.2585,
|
|
"mean_token_accuracy": 0.1355503998696804,
|
|
"num_tokens": 7688373.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.36784176826477,
|
|
"epoch": 0.3312068513501704,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004993289513357221,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.1309509187936783,
|
|
"num_tokens": 7697879.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.317149496078491,
|
|
"epoch": 0.3316437997028751,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004993265443263251,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.13057684674859046,
|
|
"num_tokens": 7708104.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.325311613082886,
|
|
"epoch": 0.33208074805557986,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004993241330142274,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.14135780110955237,
|
|
"num_tokens": 7717626.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.313494300842285,
|
|
"epoch": 0.33251769640828455,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004993217173994754,
|
|
"loss": 6.235,
|
|
"mean_token_accuracy": 0.13783995285630227,
|
|
"num_tokens": 7728221.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.333722019195557,
|
|
"epoch": 0.33295464476098924,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993192974821154,
|
|
"loss": 6.2307,
|
|
"mean_token_accuracy": 0.13345992192626,
|
|
"num_tokens": 7739083.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.377281284332275,
|
|
"epoch": 0.333391593113694,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004993168732621935,
|
|
"loss": 6.2932,
|
|
"mean_token_accuracy": 0.12718051746487619,
|
|
"num_tokens": 7748573.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.328021669387818,
|
|
"epoch": 0.3338285414663987,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004993144447397565,
|
|
"loss": 6.2101,
|
|
"mean_token_accuracy": 0.13788711950182914,
|
|
"num_tokens": 7758741.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.275328159332275,
|
|
"epoch": 0.33426548981910337,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000499312011914851,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.13237224668264388,
|
|
"num_tokens": 7768504.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.302463436126709,
|
|
"epoch": 0.3347024381718081,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004993095747875234,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.13009582236409187,
|
|
"num_tokens": 7779017.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.339192819595337,
|
|
"epoch": 0.3351393865245128,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993071333578207,
|
|
"loss": 6.1821,
|
|
"mean_token_accuracy": 0.1370094619691372,
|
|
"num_tokens": 7787630.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.278088474273682,
|
|
"epoch": 0.3355763348772175,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004993046876257898,
|
|
"loss": 6.2131,
|
|
"mean_token_accuracy": 0.13482895866036415,
|
|
"num_tokens": 7797105.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.311618185043335,
|
|
"epoch": 0.33601328322992224,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993022375914773,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.13905783295631408,
|
|
"num_tokens": 7807070.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.389101219177246,
|
|
"epoch": 0.33645023158262694,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004992997832549303,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.1325555205345154,
|
|
"num_tokens": 7818090.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.221946573257446,
|
|
"epoch": 0.3368871799353316,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004992973246161961,
|
|
"loss": 6.1764,
|
|
"mean_token_accuracy": 0.13771116584539414,
|
|
"num_tokens": 7827562.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.292095041275024,
|
|
"epoch": 0.3373241282880364,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004992948616753215,
|
|
"loss": 6.2093,
|
|
"mean_token_accuracy": 0.1278516322374344,
|
|
"num_tokens": 7837581.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.394981861114502,
|
|
"epoch": 0.33776107664074106,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004992923944323541,
|
|
"loss": 6.2634,
|
|
"mean_token_accuracy": 0.13501928597688675,
|
|
"num_tokens": 7848729.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.310138988494873,
|
|
"epoch": 0.33819802499344576,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000499289922887341,
|
|
"loss": 6.2011,
|
|
"mean_token_accuracy": 0.13485699966549874,
|
|
"num_tokens": 7857379.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.325172996520996,
|
|
"epoch": 0.3386349733461505,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004992874470403296,
|
|
"loss": 6.1917,
|
|
"mean_token_accuracy": 0.14079806953668594,
|
|
"num_tokens": 7867200.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.311602544784546,
|
|
"epoch": 0.3390719216988552,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004992849668913674,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.1355910912156105,
|
|
"num_tokens": 7876709.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.3373613357543945,
|
|
"epoch": 0.3395088700515599,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004992824824405021,
|
|
"loss": 6.2633,
|
|
"mean_token_accuracy": 0.13315544426441192,
|
|
"num_tokens": 7886256.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.301959228515625,
|
|
"epoch": 0.33994581840426463,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004992799936877813,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.13398601338267327,
|
|
"num_tokens": 7896497.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.371589469909668,
|
|
"epoch": 0.3403827667569693,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992775006332526,
|
|
"loss": 6.207,
|
|
"mean_token_accuracy": 0.13721492886543274,
|
|
"num_tokens": 7906608.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.317071485519409,
|
|
"epoch": 0.340819715109674,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000499275003276964,
|
|
"loss": 6.2863,
|
|
"mean_token_accuracy": 0.1299916237592697,
|
|
"num_tokens": 7916359.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.236544132232666,
|
|
"epoch": 0.34125666346237876,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004992725016189632,
|
|
"loss": 6.1603,
|
|
"mean_token_accuracy": 0.13543331772089004,
|
|
"num_tokens": 7925800.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.360721111297607,
|
|
"epoch": 0.34169361181508345,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004992699956592984,
|
|
"loss": 6.2488,
|
|
"mean_token_accuracy": 0.1296587198972702,
|
|
"num_tokens": 7935424.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.361935234069824,
|
|
"epoch": 0.34213056016778814,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004992674853980175,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.13166892752051354,
|
|
"num_tokens": 7945766.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.368907356262207,
|
|
"epoch": 0.3425675085204929,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004992649708351689,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.1250272959470749,
|
|
"num_tokens": 7955622.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.329561471939087,
|
|
"epoch": 0.3430044568731976,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992624519708004,
|
|
"loss": 6.2914,
|
|
"mean_token_accuracy": 0.12758758887648583,
|
|
"num_tokens": 7965750.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.343333435058594,
|
|
"epoch": 0.3434414052259023,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004992599288049607,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.13924501463770866,
|
|
"num_tokens": 7977568.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.363393783569336,
|
|
"epoch": 0.343878353578607,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000499257401337698,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.12728462964296341,
|
|
"num_tokens": 7988411.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.28168420791626,
|
|
"epoch": 0.3443153019313117,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004992548695690608,
|
|
"loss": 6.1387,
|
|
"mean_token_accuracy": 0.14234383925795555,
|
|
"num_tokens": 7998315.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.276813268661499,
|
|
"epoch": 0.3447522502840164,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004992523334990977,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.13106251060962676,
|
|
"num_tokens": 8007133.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.272677087783814,
|
|
"epoch": 0.34518919863672115,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004992497931278574,
|
|
"loss": 6.1528,
|
|
"mean_token_accuracy": 0.14113296419382096,
|
|
"num_tokens": 8016882.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.260069417953491,
|
|
"epoch": 0.34562614698942584,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004992472484553886,
|
|
"loss": 6.1671,
|
|
"mean_token_accuracy": 0.13664042428135872,
|
|
"num_tokens": 8026893.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.308275556564331,
|
|
"epoch": 0.34606309534213053,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00049924469948174,
|
|
"loss": 6.1944,
|
|
"mean_token_accuracy": 0.13003704249858855,
|
|
"num_tokens": 8036240.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.345671558380127,
|
|
"epoch": 0.3465000436948353,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004992421462069606,
|
|
"loss": 6.1757,
|
|
"mean_token_accuracy": 0.13144434317946435,
|
|
"num_tokens": 8046086.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.240842390060425,
|
|
"epoch": 0.34693699204753997,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004992395886310993,
|
|
"loss": 6.1895,
|
|
"mean_token_accuracy": 0.1421689584851265,
|
|
"num_tokens": 8056294.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.286834669113159,
|
|
"epoch": 0.3473739404002447,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004992370267542052,
|
|
"loss": 6.2156,
|
|
"mean_token_accuracy": 0.1315187208354473,
|
|
"num_tokens": 8067329.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.3432018756866455,
|
|
"epoch": 0.3478108887529494,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004992344605763275,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.1398385003209114,
|
|
"num_tokens": 8077106.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.333979988098145,
|
|
"epoch": 0.3482478371056541,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004992318900975153,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.13900325149297715,
|
|
"num_tokens": 8087766.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.207983016967773,
|
|
"epoch": 0.34868478545835885,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004992293153178179,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.14341192990541457,
|
|
"num_tokens": 8098649.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.323047065734864,
|
|
"epoch": 0.34912173381106354,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004992267362372848,
|
|
"loss": 6.2092,
|
|
"mean_token_accuracy": 0.13100808262825012,
|
|
"num_tokens": 8109237.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.2751020908355715,
|
|
"epoch": 0.34955868216376823,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004992241528559653,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.13489847853779793,
|
|
"num_tokens": 8119731.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.318090724945068,
|
|
"epoch": 0.349995630516473,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004992215651739092,
|
|
"loss": 6.2467,
|
|
"mean_token_accuracy": 0.12376242280006408,
|
|
"num_tokens": 8129448.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.28632116317749,
|
|
"epoch": 0.35043257886917767,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000499218973191166,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.13718134835362433,
|
|
"num_tokens": 8138345.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.301534938812256,
|
|
"epoch": 0.35086952722188236,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004992163769077853,
|
|
"loss": 6.1927,
|
|
"mean_token_accuracy": 0.1334017850458622,
|
|
"num_tokens": 8148380.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.319975233078003,
|
|
"epoch": 0.3513064755745871,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000499213776323817,
|
|
"loss": 6.1918,
|
|
"mean_token_accuracy": 0.14010001271963118,
|
|
"num_tokens": 8159359.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.361384391784668,
|
|
"epoch": 0.3517434239272918,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000499211171439311,
|
|
"loss": 6.2777,
|
|
"mean_token_accuracy": 0.13136567771434784,
|
|
"num_tokens": 8168586.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.306084442138672,
|
|
"epoch": 0.3521803722799965,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004992085622543172,
|
|
"loss": 6.1986,
|
|
"mean_token_accuracy": 0.1354872040450573,
|
|
"num_tokens": 8178836.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.247843790054321,
|
|
"epoch": 0.35261732063270124,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004992059487688859,
|
|
"loss": 6.1853,
|
|
"mean_token_accuracy": 0.13473303467035294,
|
|
"num_tokens": 8188933.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.2794787883758545,
|
|
"epoch": 0.35305426898540593,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004992033309830668,
|
|
"loss": 6.1864,
|
|
"mean_token_accuracy": 0.1396368734538555,
|
|
"num_tokens": 8199366.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.355959844589234,
|
|
"epoch": 0.3534912173381106,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004992007088969105,
|
|
"loss": 6.1731,
|
|
"mean_token_accuracy": 0.1387977495789528,
|
|
"num_tokens": 8209806.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.367386245727539,
|
|
"epoch": 0.35392816569081537,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000499198082510467,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.12820714637637137,
|
|
"num_tokens": 8219367.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.205999374389648,
|
|
"epoch": 0.35436511404352006,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004991954518237868,
|
|
"loss": 6.1457,
|
|
"mean_token_accuracy": 0.13604540154337882,
|
|
"num_tokens": 8228918.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.251398229598999,
|
|
"epoch": 0.35480206239622475,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004991928168369205,
|
|
"loss": 6.2326,
|
|
"mean_token_accuracy": 0.13432048931717872,
|
|
"num_tokens": 8239380.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.440735387802124,
|
|
"epoch": 0.3552390107489295,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004991901775499183,
|
|
"loss": 6.299,
|
|
"mean_token_accuracy": 0.12985948398709296,
|
|
"num_tokens": 8249131.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.358709192276001,
|
|
"epoch": 0.3556759591016342,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004991875339628311,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.13281939700245857,
|
|
"num_tokens": 8258550.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.2490339279174805,
|
|
"epoch": 0.3561129074543389,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004991848860757095,
|
|
"loss": 6.21,
|
|
"mean_token_accuracy": 0.1398457445204258,
|
|
"num_tokens": 8269089.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.319385766983032,
|
|
"epoch": 0.3565498558070436,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004991822338886044,
|
|
"loss": 6.1852,
|
|
"mean_token_accuracy": 0.13303097859025,
|
|
"num_tokens": 8279735.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.335915517807007,
|
|
"epoch": 0.3569868041597483,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004991795774015665,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.13977616727352143,
|
|
"num_tokens": 8289693.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.3235859870910645,
|
|
"epoch": 0.357423752512453,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004991769166146469,
|
|
"loss": 6.2341,
|
|
"mean_token_accuracy": 0.13487215265631675,
|
|
"num_tokens": 8300909.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.265295362472534,
|
|
"epoch": 0.35786070086515775,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004991742515278965,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.1362832248210907,
|
|
"num_tokens": 8311479.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.325096845626831,
|
|
"epoch": 0.35829764921786245,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004991715821413665,
|
|
"loss": 6.2181,
|
|
"mean_token_accuracy": 0.13479658886790274,
|
|
"num_tokens": 8321267.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.284675645828247,
|
|
"epoch": 0.35873459757056714,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004991689084551082,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.13774141371250154,
|
|
"num_tokens": 8331445.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.320082473754883,
|
|
"epoch": 0.3591715459232719,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004991662304691727,
|
|
"loss": 6.2593,
|
|
"mean_token_accuracy": 0.12908197790384293,
|
|
"num_tokens": 8340519.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.339802503585815,
|
|
"epoch": 0.3596084942759766,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004991635481836114,
|
|
"loss": 6.2162,
|
|
"mean_token_accuracy": 0.13142214938998223,
|
|
"num_tokens": 8350467.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.34062819480896,
|
|
"epoch": 0.36004544262868127,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004991608615984757,
|
|
"loss": 6.1853,
|
|
"mean_token_accuracy": 0.13231182098388672,
|
|
"num_tokens": 8360067.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.322159385681152,
|
|
"epoch": 0.360482390981386,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004991581707138175,
|
|
"loss": 6.2469,
|
|
"mean_token_accuracy": 0.13345297202467918,
|
|
"num_tokens": 8370509.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.279163980484009,
|
|
"epoch": 0.3609193393340907,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991554755296878,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.13149990066885947,
|
|
"num_tokens": 8381489.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.284092140197754,
|
|
"epoch": 0.3613562876867954,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004991527760461389,
|
|
"loss": 6.2099,
|
|
"mean_token_accuracy": 0.1364233486354351,
|
|
"num_tokens": 8392287.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.318317317962647,
|
|
"epoch": 0.36179323603950014,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004991500722632223,
|
|
"loss": 6.1923,
|
|
"mean_token_accuracy": 0.13617967516183854,
|
|
"num_tokens": 8402433.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.276598310470581,
|
|
"epoch": 0.36223018439220483,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004991473641809896,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.13364490419626235,
|
|
"num_tokens": 8412944.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.318027210235596,
|
|
"epoch": 0.3626671327449095,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991446517994932,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.13547627851366997,
|
|
"num_tokens": 8422511.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.2953328609466555,
|
|
"epoch": 0.3631040810976143,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004991419351187849,
|
|
"loss": 6.1748,
|
|
"mean_token_accuracy": 0.13981883525848388,
|
|
"num_tokens": 8433094.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.268534135818482,
|
|
"epoch": 0.36354102945031896,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991392141389169,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.1309742160141468,
|
|
"num_tokens": 8444430.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.328505039215088,
|
|
"epoch": 0.36397797780302366,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004991364888599412,
|
|
"loss": 6.3247,
|
|
"mean_token_accuracy": 0.12793881446123123,
|
|
"num_tokens": 8455171.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.3519635677337645,
|
|
"epoch": 0.3644149261557284,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004991337592819103,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.13894972056150437,
|
|
"num_tokens": 8464724.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.352320718765259,
|
|
"epoch": 0.3648518745084331,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004991310254048763,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.13326725661754607,
|
|
"num_tokens": 8474732.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.222937059402466,
|
|
"epoch": 0.36528882286113784,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004991282872288919,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.13578586652874947,
|
|
"num_tokens": 8484731.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.268366861343384,
|
|
"epoch": 0.36572577121384253,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004991255447540095,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.13649590015411378,
|
|
"num_tokens": 8494509.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.322968292236328,
|
|
"epoch": 0.3661627195665472,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004991227979802817,
|
|
"loss": 6.2282,
|
|
"mean_token_accuracy": 0.1378632016479969,
|
|
"num_tokens": 8504260.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.373710203170776,
|
|
"epoch": 0.36659966791925197,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004991200469077612,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.1293950892984867,
|
|
"num_tokens": 8514222.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.310275459289551,
|
|
"epoch": 0.36703661627195666,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004991172915365008,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.12950511202216147,
|
|
"num_tokens": 8523979.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.316265487670899,
|
|
"epoch": 0.36747356462466135,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004991145318665532,
|
|
"loss": 6.1535,
|
|
"mean_token_accuracy": 0.14113664031028747,
|
|
"num_tokens": 8533516.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.336113405227661,
|
|
"epoch": 0.3679105129773661,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004991117678979716,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.12696770057082177,
|
|
"num_tokens": 8544444.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.2604944705963135,
|
|
"epoch": 0.3683474613300708,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004991089996308089,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.13401636481285095,
|
|
"num_tokens": 8555571.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.359772682189941,
|
|
"epoch": 0.3687844096827755,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004991062270651179,
|
|
"loss": 6.2705,
|
|
"mean_token_accuracy": 0.12754399403929711,
|
|
"num_tokens": 8566486.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.3696788311004635,
|
|
"epoch": 0.36922135803548023,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004991034502009522,
|
|
"loss": 6.1645,
|
|
"mean_token_accuracy": 0.1367284558713436,
|
|
"num_tokens": 8575324.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.254921817779541,
|
|
"epoch": 0.3696583063881849,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004991006690383649,
|
|
"loss": 6.1641,
|
|
"mean_token_accuracy": 0.13787002265453338,
|
|
"num_tokens": 8586015.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.297842502593994,
|
|
"epoch": 0.3700952547408896,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004990978835774093,
|
|
"loss": 6.1391,
|
|
"mean_token_accuracy": 0.13815010488033294,
|
|
"num_tokens": 8594748.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.2729315757751465,
|
|
"epoch": 0.37053220309359436,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004990950938181389,
|
|
"loss": 6.211,
|
|
"mean_token_accuracy": 0.12907496616244316,
|
|
"num_tokens": 8605805.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.246347951889038,
|
|
"epoch": 0.37096915144629905,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004990922997606071,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.13529932647943496,
|
|
"num_tokens": 8616591.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.321091175079346,
|
|
"epoch": 0.37140609979900374,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004990895014048677,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.13347845450043677,
|
|
"num_tokens": 8627063.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.415533828735351,
|
|
"epoch": 0.3718430481517085,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004990866987509741,
|
|
"loss": 6.2818,
|
|
"mean_token_accuracy": 0.12526709884405135,
|
|
"num_tokens": 8637041.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.27305645942688,
|
|
"epoch": 0.3722799965044132,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004990838917989802,
|
|
"loss": 6.2054,
|
|
"mean_token_accuracy": 0.1385042130947113,
|
|
"num_tokens": 8647485.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.278818893432617,
|
|
"epoch": 0.37271694485711787,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00049908108054894,
|
|
"loss": 6.1707,
|
|
"mean_token_accuracy": 0.13312357068061828,
|
|
"num_tokens": 8657185.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.30776538848877,
|
|
"epoch": 0.3731538932098226,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004990782650009071,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.1385415717959404,
|
|
"num_tokens": 8667639.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.320880556106568,
|
|
"epoch": 0.3735908415625273,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004990754451549358,
|
|
"loss": 6.2078,
|
|
"mean_token_accuracy": 0.13354232385754586,
|
|
"num_tokens": 8678003.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.328972673416137,
|
|
"epoch": 0.374027789915232,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004990726210110798,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.13083540871739388,
|
|
"num_tokens": 8688837.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.31743278503418,
|
|
"epoch": 0.37446473826793675,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004990697925693938,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.1439003139734268,
|
|
"num_tokens": 8698395.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.311701154708862,
|
|
"epoch": 0.37490168662064144,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004990669598299316,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.13384513854980468,
|
|
"num_tokens": 8708031.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.264176940917968,
|
|
"epoch": 0.37533863497334613,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004990641227927478,
|
|
"loss": 6.1554,
|
|
"mean_token_accuracy": 0.14129097983241082,
|
|
"num_tokens": 8717825.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.35695514678955,
|
|
"epoch": 0.3757755833260509,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004990612814578967,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.12975349202752112,
|
|
"num_tokens": 8728873.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.237163925170899,
|
|
"epoch": 0.37621253167875557,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004990584358254327,
|
|
"loss": 6.1579,
|
|
"mean_token_accuracy": 0.1332879640161991,
|
|
"num_tokens": 8737917.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.223076629638672,
|
|
"epoch": 0.37664948003146026,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004990555858954107,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.13721137419342994,
|
|
"num_tokens": 8747466.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.261527442932129,
|
|
"epoch": 0.377086428384165,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000499052731667885,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.13348276689648628,
|
|
"num_tokens": 8757037.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.295954370498658,
|
|
"epoch": 0.3775233767368697,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004990498731429105,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.1333417996764183,
|
|
"num_tokens": 8766780.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.292055940628051,
|
|
"epoch": 0.3779603250895744,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004990470103205421,
|
|
"loss": 6.1637,
|
|
"mean_token_accuracy": 0.13308844119310378,
|
|
"num_tokens": 8777063.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.216593027114868,
|
|
"epoch": 0.37839727344227914,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004990441432008347,
|
|
"loss": 6.204,
|
|
"mean_token_accuracy": 0.13550992980599402,
|
|
"num_tokens": 8786479.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.37866063117981,
|
|
"epoch": 0.3788342217949838,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004990412717838431,
|
|
"loss": 6.2101,
|
|
"mean_token_accuracy": 0.13552200198173522,
|
|
"num_tokens": 8795663.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.282534646987915,
|
|
"epoch": 0.3792711701476885,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004990383960696226,
|
|
"loss": 6.1561,
|
|
"mean_token_accuracy": 0.1367136836051941,
|
|
"num_tokens": 8805854.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.236309766769409,
|
|
"epoch": 0.37970811850039327,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004990355160582283,
|
|
"loss": 6.119,
|
|
"mean_token_accuracy": 0.13313476443290712,
|
|
"num_tokens": 8816068.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.224233531951905,
|
|
"epoch": 0.38014506685309796,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004990326317497153,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.13832384943962098,
|
|
"num_tokens": 8826301.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.314862632751465,
|
|
"epoch": 0.38058201520580265,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004990297431441391,
|
|
"loss": 6.1756,
|
|
"mean_token_accuracy": 0.1411406196653843,
|
|
"num_tokens": 8837482.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.324439620971679,
|
|
"epoch": 0.3810189635585074,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000499026850241555,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.13611030280590058,
|
|
"num_tokens": 8847041.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.2874983787536625,
|
|
"epoch": 0.3814559119112121,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004990239530420185,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.13298215717077255,
|
|
"num_tokens": 8856963.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.320013093948364,
|
|
"epoch": 0.3818928602639168,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004990210515455853,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.13463006168603897,
|
|
"num_tokens": 8867318.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.29173731803894,
|
|
"epoch": 0.3823298086166215,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004990181457523109,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.14037566334009172,
|
|
"num_tokens": 8877634.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.282214641571045,
|
|
"epoch": 0.3827667569693262,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000499015235662251,
|
|
"loss": 6.2365,
|
|
"mean_token_accuracy": 0.13639468774199487,
|
|
"num_tokens": 8887708.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.314670038223267,
|
|
"epoch": 0.38320370532203096,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004990123212754616,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.13615118563175202,
|
|
"num_tokens": 8897510.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.3385828018188475,
|
|
"epoch": 0.38364065367473565,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004990094025919985,
|
|
"loss": 6.1851,
|
|
"mean_token_accuracy": 0.1292119763791561,
|
|
"num_tokens": 8908282.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.322610807418823,
|
|
"epoch": 0.38407760202744035,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004990064796119175,
|
|
"loss": 6.2251,
|
|
"mean_token_accuracy": 0.1304896928369999,
|
|
"num_tokens": 8918332.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.242078018188477,
|
|
"epoch": 0.3845145503801451,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990035523352751,
|
|
"loss": 6.1793,
|
|
"mean_token_accuracy": 0.1364331990480423,
|
|
"num_tokens": 8929138.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.288182020187378,
|
|
"epoch": 0.3849514987328498,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000499000620762127,
|
|
"loss": 6.232,
|
|
"mean_token_accuracy": 0.130785021930933,
|
|
"num_tokens": 8940871.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.344573259353638,
|
|
"epoch": 0.3853884470855545,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004989976848925297,
|
|
"loss": 6.1573,
|
|
"mean_token_accuracy": 0.1379668101668358,
|
|
"num_tokens": 8951199.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.306144666671753,
|
|
"epoch": 0.3858253954382592,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004989947447265394,
|
|
"loss": 6.3012,
|
|
"mean_token_accuracy": 0.1280881054699421,
|
|
"num_tokens": 8961482.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.357047700881958,
|
|
"epoch": 0.3862623437909639,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989918002642126,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.13600103184580803,
|
|
"num_tokens": 8971884.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.260739088058472,
|
|
"epoch": 0.3866992921436686,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004989888515056057,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.13692375347018243,
|
|
"num_tokens": 8982086.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.221055173873902,
|
|
"epoch": 0.38713624049637335,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004989858984507752,
|
|
"loss": 6.2043,
|
|
"mean_token_accuracy": 0.13385815545916557,
|
|
"num_tokens": 8991555.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.318227338790893,
|
|
"epoch": 0.38757318884907804,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004989829410997778,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.13073932528495788,
|
|
"num_tokens": 9002459.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.283407688140869,
|
|
"epoch": 0.38801013720178273,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004989799794526702,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.13009282052516938,
|
|
"num_tokens": 9012514.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.27811188697815,
|
|
"epoch": 0.3884470855544875,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004989770135095093,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.13882900923490524,
|
|
"num_tokens": 9022636.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.311051321029663,
|
|
"epoch": 0.3888840339071922,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004989740432703519,
|
|
"loss": 6.1784,
|
|
"mean_token_accuracy": 0.13938639983534812,
|
|
"num_tokens": 9032868.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.3481199741363525,
|
|
"epoch": 0.38932098225989686,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000498971068735255,
|
|
"loss": 6.1694,
|
|
"mean_token_accuracy": 0.13330444023013116,
|
|
"num_tokens": 9043057.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.2306193828582765,
|
|
"epoch": 0.3897579306126016,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004989680899042756,
|
|
"loss": 6.1749,
|
|
"mean_token_accuracy": 0.1374656155705452,
|
|
"num_tokens": 9053179.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.302839851379394,
|
|
"epoch": 0.3901948789653063,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004989651067774708,
|
|
"loss": 6.1927,
|
|
"mean_token_accuracy": 0.13686879202723504,
|
|
"num_tokens": 9063112.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.364594268798828,
|
|
"epoch": 0.390631827318011,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004989621193548981,
|
|
"loss": 6.2015,
|
|
"mean_token_accuracy": 0.13447140827775,
|
|
"num_tokens": 9073512.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.2928688526153564,
|
|
"epoch": 0.39106877567071574,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004989591276366145,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.12548629194498062,
|
|
"num_tokens": 9083369.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.308518123626709,
|
|
"epoch": 0.39150572402342043,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004989561316226774,
|
|
"loss": 6.1756,
|
|
"mean_token_accuracy": 0.13745871260762216,
|
|
"num_tokens": 9092814.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.209445142745972,
|
|
"epoch": 0.3919426723761251,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004989531313131444,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.1465831182897091,
|
|
"num_tokens": 9102816.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.265080356597901,
|
|
"epoch": 0.39237962072882987,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000498950126708073,
|
|
"loss": 6.2491,
|
|
"mean_token_accuracy": 0.1286209739744663,
|
|
"num_tokens": 9114470.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.401240396499634,
|
|
"epoch": 0.39281656908153456,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004989471178075208,
|
|
"loss": 6.2179,
|
|
"mean_token_accuracy": 0.13008468151092528,
|
|
"num_tokens": 9125604.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.2590978145599365,
|
|
"epoch": 0.39325351743423925,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004989441046115456,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.1401989698410034,
|
|
"num_tokens": 9135088.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.247618913650513,
|
|
"epoch": 0.393690465786944,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004989410871202051,
|
|
"loss": 6.2266,
|
|
"mean_token_accuracy": 0.13349834457039833,
|
|
"num_tokens": 9145302.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.270593976974487,
|
|
"epoch": 0.3941274141396487,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004989380653335571,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.13583647683262826,
|
|
"num_tokens": 9155104.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.252223634719849,
|
|
"epoch": 0.3945643624923534,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004989350392516598,
|
|
"loss": 6.0822,
|
|
"mean_token_accuracy": 0.1374653048813343,
|
|
"num_tokens": 9165055.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.263556861877442,
|
|
"epoch": 0.39500131084505813,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004989320088745711,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.1383694276213646,
|
|
"num_tokens": 9175305.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.23392162322998,
|
|
"epoch": 0.3954382591977628,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000498928974202349,
|
|
"loss": 6.1748,
|
|
"mean_token_accuracy": 0.13336197286844254,
|
|
"num_tokens": 9185153.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.2877270698547365,
|
|
"epoch": 0.3958752075504675,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000498925935235052,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.13427923619747162,
|
|
"num_tokens": 9195385.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.242312908172607,
|
|
"epoch": 0.39631215590317226,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004989228919727382,
|
|
"loss": 6.1075,
|
|
"mean_token_accuracy": 0.13958708792924882,
|
|
"num_tokens": 9205009.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.280454111099243,
|
|
"epoch": 0.39674910425587695,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000498919844415466,
|
|
"loss": 6.1749,
|
|
"mean_token_accuracy": 0.13809840381145477,
|
|
"num_tokens": 9214684.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.232513427734375,
|
|
"epoch": 0.39718605260858164,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004989167925632937,
|
|
"loss": 6.0956,
|
|
"mean_token_accuracy": 0.13999973982572556,
|
|
"num_tokens": 9225721.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.2594568729400635,
|
|
"epoch": 0.3976230009612864,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004989137364162801,
|
|
"loss": 6.204,
|
|
"mean_token_accuracy": 0.13365002050995828,
|
|
"num_tokens": 9236167.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.248045921325684,
|
|
"epoch": 0.3980599493139911,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004989106759744837,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.13835562020540237,
|
|
"num_tokens": 9245716.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.303405904769898,
|
|
"epoch": 0.39849689766669577,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004989076112379633,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.12724980786442758,
|
|
"num_tokens": 9256897.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.376533365249633,
|
|
"epoch": 0.3989338460194005,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004989045422067775,
|
|
"loss": 6.2398,
|
|
"mean_token_accuracy": 0.12131529077887535,
|
|
"num_tokens": 9266080.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.336807346343994,
|
|
"epoch": 0.3993707943721052,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004989014688809853,
|
|
"loss": 6.1559,
|
|
"mean_token_accuracy": 0.13339983820915222,
|
|
"num_tokens": 9276815.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.242786026000976,
|
|
"epoch": 0.3998077427248099,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004988983912606454,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.13579384982585907,
|
|
"num_tokens": 9287339.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.177998495101929,
|
|
"epoch": 0.40024469107751465,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004988953093458173,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.13939642161130905,
|
|
"num_tokens": 9298002.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.274811935424805,
|
|
"epoch": 0.40068163943021934,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004988922231365597,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.13488566651940345,
|
|
"num_tokens": 9309008.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.313817262649536,
|
|
"epoch": 0.4011185877829241,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000498889132632932,
|
|
"loss": 6.2136,
|
|
"mean_token_accuracy": 0.12972528114914894,
|
|
"num_tokens": 9319391.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.283246612548828,
|
|
"epoch": 0.4015555361356288,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004988860378349934,
|
|
"loss": 6.0693,
|
|
"mean_token_accuracy": 0.14501725882291794,
|
|
"num_tokens": 9329808.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.2188276767730715,
|
|
"epoch": 0.40199248448833347,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004988829387428033,
|
|
"loss": 6.1365,
|
|
"mean_token_accuracy": 0.1380341224372387,
|
|
"num_tokens": 9339580.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.261927127838135,
|
|
"epoch": 0.4024294328410382,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004988798353564211,
|
|
"loss": 6.1482,
|
|
"mean_token_accuracy": 0.14019528031349182,
|
|
"num_tokens": 9350008.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.351348400115967,
|
|
"epoch": 0.4028663811937429,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004988767276759064,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.1406958892941475,
|
|
"num_tokens": 9359026.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.299345588684082,
|
|
"epoch": 0.4033033295464476,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004988736157013186,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.1405692771077156,
|
|
"num_tokens": 9369084.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.181832313537598,
|
|
"epoch": 0.40374027789915234,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004988704994327178,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.14575967118144034,
|
|
"num_tokens": 9378273.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.229097747802735,
|
|
"epoch": 0.40417722625185704,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004988673788701633,
|
|
"loss": 6.1288,
|
|
"mean_token_accuracy": 0.13718436360359193,
|
|
"num_tokens": 9388434.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.275507068634033,
|
|
"epoch": 0.4046141746045617,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004988642540137152,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.13442543298006057,
|
|
"num_tokens": 9398484.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.276987504959107,
|
|
"epoch": 0.4050511229572665,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004988611248634335,
|
|
"loss": 6.098,
|
|
"mean_token_accuracy": 0.13898643031716346,
|
|
"num_tokens": 9409544.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.310326623916626,
|
|
"epoch": 0.40548807130997117,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000498857991419378,
|
|
"loss": 6.1672,
|
|
"mean_token_accuracy": 0.13725512996315956,
|
|
"num_tokens": 9419391.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.253142261505127,
|
|
"epoch": 0.40592501966267586,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004988548536816091,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.14332313239574432,
|
|
"num_tokens": 9429342.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.221396780014038,
|
|
"epoch": 0.4063619680153806,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004988517116501867,
|
|
"loss": 6.2374,
|
|
"mean_token_accuracy": 0.12361930385231971,
|
|
"num_tokens": 9440643.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.3487019538879395,
|
|
"epoch": 0.4067989163680853,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004988485653251711,
|
|
"loss": 6.1879,
|
|
"mean_token_accuracy": 0.1392652027308941,
|
|
"num_tokens": 9450674.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.317318248748779,
|
|
"epoch": 0.40723586472079,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004988454147066228,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.13783033117651938,
|
|
"num_tokens": 9460075.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.2390021800994875,
|
|
"epoch": 0.40767281307349473,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004988422597946022,
|
|
"loss": 6.1456,
|
|
"mean_token_accuracy": 0.14160386994481086,
|
|
"num_tokens": 9469327.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.297602844238281,
|
|
"epoch": 0.4081097614261994,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004988391005891698,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.13125161826610565,
|
|
"num_tokens": 9478304.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.253264236450195,
|
|
"epoch": 0.4085467097789041,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000498835937090386,
|
|
"loss": 6.1152,
|
|
"mean_token_accuracy": 0.13788354843854905,
|
|
"num_tokens": 9487453.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.231164598464966,
|
|
"epoch": 0.40898365813160886,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004988327692983116,
|
|
"loss": 6.0639,
|
|
"mean_token_accuracy": 0.14462961927056311,
|
|
"num_tokens": 9496623.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.245018386840821,
|
|
"epoch": 0.40942060648431355,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004988295972130076,
|
|
"loss": 6.1898,
|
|
"mean_token_accuracy": 0.13496496230363847,
|
|
"num_tokens": 9506293.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.317003297805786,
|
|
"epoch": 0.40985755483701825,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004988264208345346,
|
|
"loss": 6.0992,
|
|
"mean_token_accuracy": 0.13748762384057045,
|
|
"num_tokens": 9516127.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.200523328781128,
|
|
"epoch": 0.410294503189723,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004988232401629535,
|
|
"loss": 6.0927,
|
|
"mean_token_accuracy": 0.1418273501098156,
|
|
"num_tokens": 9525597.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.208586359024048,
|
|
"epoch": 0.4107314515424277,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004988200551983254,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.13941014930605888,
|
|
"num_tokens": 9535208.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.236052703857422,
|
|
"epoch": 0.4111683998951324,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004988168659407113,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.1489814765751362,
|
|
"num_tokens": 9545078.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.321736574172974,
|
|
"epoch": 0.4116053482478371,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004988136723901725,
|
|
"loss": 6.1652,
|
|
"mean_token_accuracy": 0.1318232461810112,
|
|
"num_tokens": 9555074.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.245498085021973,
|
|
"epoch": 0.4120422966005418,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004988104745467702,
|
|
"loss": 6.1654,
|
|
"mean_token_accuracy": 0.1366843894124031,
|
|
"num_tokens": 9564777.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.245613765716553,
|
|
"epoch": 0.4124792449532465,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004988072724105657,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.13342124447226525,
|
|
"num_tokens": 9574551.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.277015590667725,
|
|
"epoch": 0.41291619330595125,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004988040659816203,
|
|
"loss": 6.2486,
|
|
"mean_token_accuracy": 0.12661304399371148,
|
|
"num_tokens": 9585162.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.323986434936524,
|
|
"epoch": 0.41335314165865594,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004988008552599958,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.1459247313439846,
|
|
"num_tokens": 9595422.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.303846168518066,
|
|
"epoch": 0.41379009001136063,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004987976402457536,
|
|
"loss": 6.1264,
|
|
"mean_token_accuracy": 0.14018649980425835,
|
|
"num_tokens": 9604315.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.219915056228638,
|
|
"epoch": 0.4142270383640654,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004987944209389555,
|
|
"loss": 6.1425,
|
|
"mean_token_accuracy": 0.1348230868577957,
|
|
"num_tokens": 9614369.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.2782059669494625,
|
|
"epoch": 0.41466398671677007,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000498791197339663,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.13660474270582199,
|
|
"num_tokens": 9624154.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.327009057998657,
|
|
"epoch": 0.41510093506947476,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000498787969447938,
|
|
"loss": 6.1719,
|
|
"mean_token_accuracy": 0.1309115432202816,
|
|
"num_tokens": 9634903.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.216856050491333,
|
|
"epoch": 0.4155378834221795,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004987847372638427,
|
|
"loss": 6.2105,
|
|
"mean_token_accuracy": 0.1377333827316761,
|
|
"num_tokens": 9644873.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.254890203475952,
|
|
"epoch": 0.4159748317748842,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004987815007874388,
|
|
"loss": 6.1216,
|
|
"mean_token_accuracy": 0.14137759655714036,
|
|
"num_tokens": 9654661.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.321761226654052,
|
|
"epoch": 0.4164117801275889,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004987782600187884,
|
|
"loss": 6.1429,
|
|
"mean_token_accuracy": 0.14375444427132605,
|
|
"num_tokens": 9664980.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.302230596542358,
|
|
"epoch": 0.41684872848029364,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004987750149579537,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.13495260551571847,
|
|
"num_tokens": 9675117.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.239761018753052,
|
|
"epoch": 0.41728567683299833,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000498771765604997,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.1374809578061104,
|
|
"num_tokens": 9684900.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.26757173538208,
|
|
"epoch": 0.417722625185703,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004987685119599806,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.13259884789586068,
|
|
"num_tokens": 9694586.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.345765399932861,
|
|
"epoch": 0.41815957353840777,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004987652540229668,
|
|
"loss": 6.1779,
|
|
"mean_token_accuracy": 0.14059032276272773,
|
|
"num_tokens": 9705676.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.305094909667969,
|
|
"epoch": 0.41859652189111246,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004987619917940183,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.14054128676652908,
|
|
"num_tokens": 9715442.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.331025552749634,
|
|
"epoch": 0.4190334702438172,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004987587252731975,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.1291821740567684,
|
|
"num_tokens": 9726621.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.396036100387573,
|
|
"epoch": 0.4194704185965219,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004987554544605671,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.1289959356188774,
|
|
"num_tokens": 9736688.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.341685104370117,
|
|
"epoch": 0.4199073669492266,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004987521793561898,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.13719259053468705,
|
|
"num_tokens": 9746478.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.214406061172485,
|
|
"epoch": 0.42034431530193134,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004987488999601285,
|
|
"loss": 6.179,
|
|
"mean_token_accuracy": 0.13636296689510347,
|
|
"num_tokens": 9756370.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.324111032485962,
|
|
"epoch": 0.42078126365463603,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000498745616272446,
|
|
"loss": 6.1979,
|
|
"mean_token_accuracy": 0.13605131432414055,
|
|
"num_tokens": 9766293.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.287442398071289,
|
|
"epoch": 0.4212182120073407,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004987423282932054,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.1371973216533661,
|
|
"num_tokens": 9777172.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.228835916519165,
|
|
"epoch": 0.42165516036004547,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004987390360224697,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.13556611761450768,
|
|
"num_tokens": 9787194.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.231557416915893,
|
|
"epoch": 0.42209210871275016,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000498735739460302,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.13963005244731902,
|
|
"num_tokens": 9797528.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.281035709381103,
|
|
"epoch": 0.42252905706545485,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004987324386067656,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.136855348944664,
|
|
"num_tokens": 9808412.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.375536823272705,
|
|
"epoch": 0.4229660054181596,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004987291334619239,
|
|
"loss": 6.2603,
|
|
"mean_token_accuracy": 0.13053438663482667,
|
|
"num_tokens": 9820047.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.282112407684326,
|
|
"epoch": 0.4234029537708643,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00049872582402584,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.13801912888884543,
|
|
"num_tokens": 9828812.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.20565824508667,
|
|
"epoch": 0.423839902123569,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004987225102985778,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.1396217368543148,
|
|
"num_tokens": 9838288.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.323318767547607,
|
|
"epoch": 0.4242768504762737,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004987191922802003,
|
|
"loss": 6.1694,
|
|
"mean_token_accuracy": 0.1373145028948784,
|
|
"num_tokens": 9848536.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.334697198867798,
|
|
"epoch": 0.4247137988289784,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004987158699707717,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.13281583562493324,
|
|
"num_tokens": 9859741.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.3007416248321535,
|
|
"epoch": 0.4251507471816831,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004987125433703554,
|
|
"loss": 6.1828,
|
|
"mean_token_accuracy": 0.13512975797057153,
|
|
"num_tokens": 9869173.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.326250267028809,
|
|
"epoch": 0.42558769553438786,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004987092124790155,
|
|
"loss": 6.1798,
|
|
"mean_token_accuracy": 0.13396698832511902,
|
|
"num_tokens": 9879619.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.256536626815796,
|
|
"epoch": 0.42602464388709255,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004987058772968154,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.15063711032271385,
|
|
"num_tokens": 9890214.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.207323265075684,
|
|
"epoch": 0.42646159223979724,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004987025378238195,
|
|
"loss": 6.1358,
|
|
"mean_token_accuracy": 0.1356499522924423,
|
|
"num_tokens": 9900266.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.373274326324463,
|
|
"epoch": 0.426898540592502,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004986991940600917,
|
|
"loss": 6.1614,
|
|
"mean_token_accuracy": 0.14057112634181976,
|
|
"num_tokens": 9910790.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.35953106880188,
|
|
"epoch": 0.4273354889452067,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004986958460056961,
|
|
"loss": 6.1699,
|
|
"mean_token_accuracy": 0.12968755811452864,
|
|
"num_tokens": 9921167.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.220204162597656,
|
|
"epoch": 0.42777243729791137,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000498692493660697,
|
|
"loss": 6.1137,
|
|
"mean_token_accuracy": 0.14389638230204582,
|
|
"num_tokens": 9931674.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.240059232711792,
|
|
"epoch": 0.4282093856506161,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004986891370251587,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.13982971683144568,
|
|
"num_tokens": 9941484.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.3408478736877445,
|
|
"epoch": 0.4286463340033208,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004986857760991454,
|
|
"loss": 6.2198,
|
|
"mean_token_accuracy": 0.13376458287239074,
|
|
"num_tokens": 9951885.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.308237314224243,
|
|
"epoch": 0.4290832823560255,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004986824108827218,
|
|
"loss": 6.0576,
|
|
"mean_token_accuracy": 0.14093493595719336,
|
|
"num_tokens": 9961658.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.158659744262695,
|
|
"epoch": 0.42952023070873024,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004986790413759523,
|
|
"loss": 6.1409,
|
|
"mean_token_accuracy": 0.13590563461184502,
|
|
"num_tokens": 9971971.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.2474815368652346,
|
|
"epoch": 0.42995717906143494,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004986756675789016,
|
|
"loss": 6.057,
|
|
"mean_token_accuracy": 0.1382055960595608,
|
|
"num_tokens": 9982211.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.227798938751221,
|
|
"epoch": 0.4303941274141396,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004986722894916344,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.14289458617568015,
|
|
"num_tokens": 9991935.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.233926773071289,
|
|
"epoch": 0.4308310757668444,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004986689071142155,
|
|
"loss": 6.1476,
|
|
"mean_token_accuracy": 0.13406068161129953,
|
|
"num_tokens": 10002014.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.267605781555176,
|
|
"epoch": 0.43126802411954906,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004986655204467097,
|
|
"loss": 6.1681,
|
|
"mean_token_accuracy": 0.13497984185814857,
|
|
"num_tokens": 10012030.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.2325609683990475,
|
|
"epoch": 0.43170497247225376,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004986621294891822,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.13742314130067826,
|
|
"num_tokens": 10022188.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.2819342613220215,
|
|
"epoch": 0.4321419208249585,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004986587342416976,
|
|
"loss": 6.0424,
|
|
"mean_token_accuracy": 0.14051671847701072,
|
|
"num_tokens": 10032131.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.3012300491333,
|
|
"epoch": 0.4325788691776632,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004986553347043214,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.1372190795838833,
|
|
"num_tokens": 10043204.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.27725133895874,
|
|
"epoch": 0.4330158175303679,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004986519308771188,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.1372821055352688,
|
|
"num_tokens": 10052863.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.238871479034424,
|
|
"epoch": 0.43345276588307263,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004986485227601548,
|
|
"loss": 6.1281,
|
|
"mean_token_accuracy": 0.14254157543182372,
|
|
"num_tokens": 10063212.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.304278421401977,
|
|
"epoch": 0.4338897142357773,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.000498645110353495,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.1352584458887577,
|
|
"num_tokens": 10074180.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.254854822158814,
|
|
"epoch": 0.434326662588482,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004986416936572049,
|
|
"loss": 6.115,
|
|
"mean_token_accuracy": 0.14317337051033974,
|
|
"num_tokens": 10084513.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.285315895080567,
|
|
"epoch": 0.43476361094118676,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004986382726713497,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.13702046871185303,
|
|
"num_tokens": 10094352.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.238975763320923,
|
|
"epoch": 0.43520055929389145,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004986348473959955,
|
|
"loss": 6.0051,
|
|
"mean_token_accuracy": 0.15185373425483703,
|
|
"num_tokens": 10103677.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.216447448730468,
|
|
"epoch": 0.43563750764659614,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004986314178312076,
|
|
"loss": 6.2146,
|
|
"mean_token_accuracy": 0.13050349950790405,
|
|
"num_tokens": 10113479.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.266159963607788,
|
|
"epoch": 0.4360744559993009,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004986279839770519,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.14220530316233634,
|
|
"num_tokens": 10123526.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.2446376323699955,
|
|
"epoch": 0.4365114043520056,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004986245458335944,
|
|
"loss": 6.1378,
|
|
"mean_token_accuracy": 0.13541444465518,
|
|
"num_tokens": 10134176.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.265491676330567,
|
|
"epoch": 0.43694835270471033,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004986211034009008,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.1447139300405979,
|
|
"num_tokens": 10144763.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.22551908493042,
|
|
"epoch": 0.437385301057415,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004986176566790375,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.14613140970468522,
|
|
"num_tokens": 10155011.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.261688280105591,
|
|
"epoch": 0.4378222494101197,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004986142056680701,
|
|
"loss": 6.1545,
|
|
"mean_token_accuracy": 0.13823105841875077,
|
|
"num_tokens": 10165474.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.294175291061402,
|
|
"epoch": 0.43825919776282446,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004986107503680652,
|
|
"loss": 6.184,
|
|
"mean_token_accuracy": 0.14294707179069518,
|
|
"num_tokens": 10175137.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.259722518920898,
|
|
"epoch": 0.43869614611552915,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004986072907790889,
|
|
"loss": 6.1862,
|
|
"mean_token_accuracy": 0.1319163627922535,
|
|
"num_tokens": 10185623.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.3086286067962645,
|
|
"epoch": 0.43913309446823384,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004986038269012076,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.14134794026613234,
|
|
"num_tokens": 10195201.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.29203200340271,
|
|
"epoch": 0.4395700428209386,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004986003587344877,
|
|
"loss": 6.1807,
|
|
"mean_token_accuracy": 0.13764383196830748,
|
|
"num_tokens": 10205951.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.234759187698364,
|
|
"epoch": 0.4400069911736433,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004985968862789957,
|
|
"loss": 6.0516,
|
|
"mean_token_accuracy": 0.14456723183393477,
|
|
"num_tokens": 10215665.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.230546188354492,
|
|
"epoch": 0.44044393952634797,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004985934095347985,
|
|
"loss": 6.1461,
|
|
"mean_token_accuracy": 0.13692135065793992,
|
|
"num_tokens": 10225037.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.164027881622315,
|
|
"epoch": 0.4408808878790527,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004985899285019624,
|
|
"loss": 6.1115,
|
|
"mean_token_accuracy": 0.13943026587367058,
|
|
"num_tokens": 10234581.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.272631359100342,
|
|
"epoch": 0.4413178362317574,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004985864431805543,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.14523213654756545,
|
|
"num_tokens": 10243716.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.294983530044556,
|
|
"epoch": 0.4417547845844621,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004985829535706411,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.1396915651857853,
|
|
"num_tokens": 10253198.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.240324974060059,
|
|
"epoch": 0.44219173293716685,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004985794596722897,
|
|
"loss": 6.1935,
|
|
"mean_token_accuracy": 0.1337872676551342,
|
|
"num_tokens": 10262912.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.27632966041565,
|
|
"epoch": 0.44262868128987154,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000498575961485567,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.13864117488265038,
|
|
"num_tokens": 10272960.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.33082594871521,
|
|
"epoch": 0.44306562964257623,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004985724590105403,
|
|
"loss": 6.1777,
|
|
"mean_token_accuracy": 0.13294639587402343,
|
|
"num_tokens": 10283034.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.242563962936401,
|
|
"epoch": 0.443502577995281,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004985689522472767,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.13814122676849366,
|
|
"num_tokens": 10292553.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.212743759155273,
|
|
"epoch": 0.44393952634798567,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004985654411958434,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.13814549073576926,
|
|
"num_tokens": 10302475.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.28053388595581,
|
|
"epoch": 0.44437647470069036,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004985619258563078,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.14118221551179885,
|
|
"num_tokens": 10311693.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.312252950668335,
|
|
"epoch": 0.4448134230533951,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004985584062287372,
|
|
"loss": 6.1182,
|
|
"mean_token_accuracy": 0.14231281131505966,
|
|
"num_tokens": 10323052.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.227076244354248,
|
|
"epoch": 0.4452503714060998,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004985548823131994,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.13764646723866464,
|
|
"num_tokens": 10332997.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.322070789337158,
|
|
"epoch": 0.4456873197588045,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004985513541097618,
|
|
"loss": 6.2201,
|
|
"mean_token_accuracy": 0.13421619758009912,
|
|
"num_tokens": 10343298.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.336534023284912,
|
|
"epoch": 0.44612426811150924,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000498547821618492,
|
|
"loss": 6.1144,
|
|
"mean_token_accuracy": 0.14139558374881744,
|
|
"num_tokens": 10352485.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.177110052108764,
|
|
"epoch": 0.44656121646421393,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004985442848394579,
|
|
"loss": 6.1703,
|
|
"mean_token_accuracy": 0.13453608453273774,
|
|
"num_tokens": 10362810.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.2077878475189205,
|
|
"epoch": 0.4469981648169186,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004985407437727273,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.1392608255147934,
|
|
"num_tokens": 10372817.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.309681034088134,
|
|
"epoch": 0.44743511316962337,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004985371984183681,
|
|
"loss": 6.157,
|
|
"mean_token_accuracy": 0.1435435265302658,
|
|
"num_tokens": 10383046.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.246765279769898,
|
|
"epoch": 0.44787206152232806,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004985336487764483,
|
|
"loss": 6.1826,
|
|
"mean_token_accuracy": 0.1371629036962986,
|
|
"num_tokens": 10393498.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.284682369232177,
|
|
"epoch": 0.44830900987503275,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004985300948470359,
|
|
"loss": 6.1789,
|
|
"mean_token_accuracy": 0.13662788644433022,
|
|
"num_tokens": 10403595.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.321662712097168,
|
|
"epoch": 0.4487459582277375,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004985265366301992,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.13992622643709182,
|
|
"num_tokens": 10413475.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.256285905838013,
|
|
"epoch": 0.4491829065804422,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004985229741260065,
|
|
"loss": 6.1482,
|
|
"mean_token_accuracy": 0.14397763162851335,
|
|
"num_tokens": 10423512.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.2504840850830075,
|
|
"epoch": 0.4496198549331469,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004985194073345259,
|
|
"loss": 6.164,
|
|
"mean_token_accuracy": 0.1343572497367859,
|
|
"num_tokens": 10434198.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.243315315246582,
|
|
"epoch": 0.4500568032858516,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004985158362558261,
|
|
"loss": 6.1113,
|
|
"mean_token_accuracy": 0.1347861848771572,
|
|
"num_tokens": 10444077.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.259370422363281,
|
|
"epoch": 0.4504937516385563,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004985122608899752,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.1376808151602745,
|
|
"num_tokens": 10454481.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.303308010101318,
|
|
"epoch": 0.450930699991261,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004985086812370422,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.13569988757371904,
|
|
"num_tokens": 10464453.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.338668537139893,
|
|
"epoch": 0.45136764834396575,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004985050972970956,
|
|
"loss": 6.2315,
|
|
"mean_token_accuracy": 0.1327189899981022,
|
|
"num_tokens": 10474932.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.316284084320069,
|
|
"epoch": 0.45180459669667045,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000498501509070204,
|
|
"loss": 6.2224,
|
|
"mean_token_accuracy": 0.1338010162115097,
|
|
"num_tokens": 10484719.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.248991584777832,
|
|
"epoch": 0.45224154504937514,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004984979165564364,
|
|
"loss": 6.2699,
|
|
"mean_token_accuracy": 0.12927524521946906,
|
|
"num_tokens": 10495808.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.309340620040894,
|
|
"epoch": 0.4526784934020799,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004984943197558616,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.13639893680810927,
|
|
"num_tokens": 10506528.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.324915504455566,
|
|
"epoch": 0.4531154417547846,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004984907186685487,
|
|
"loss": 6.1391,
|
|
"mean_token_accuracy": 0.13927296698093414,
|
|
"num_tokens": 10517117.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.337198209762573,
|
|
"epoch": 0.45355239010748927,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004984871132945667,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.1367869570851326,
|
|
"num_tokens": 10527394.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.266608858108521,
|
|
"epoch": 0.453989338460194,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004984835036339848,
|
|
"loss": 6.1256,
|
|
"mean_token_accuracy": 0.13677924424409865,
|
|
"num_tokens": 10536779.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.243874835968017,
|
|
"epoch": 0.4544262868128987,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004984798896868722,
|
|
"loss": 6.2,
|
|
"mean_token_accuracy": 0.1301602840423584,
|
|
"num_tokens": 10547116.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.328261041641236,
|
|
"epoch": 0.45486323516560345,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004984762714532981,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.14150492921471597,
|
|
"num_tokens": 10556396.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.2097395896911625,
|
|
"epoch": 0.45530018351830814,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000498472648933332,
|
|
"loss": 6.2847,
|
|
"mean_token_accuracy": 0.13041267469525336,
|
|
"num_tokens": 10568127.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.29595627784729,
|
|
"epoch": 0.45573713187101283,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004984690221270436,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.14152851030230523,
|
|
"num_tokens": 10578565.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.28857102394104,
|
|
"epoch": 0.4561740802237176,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004984653910345021,
|
|
"loss": 6.1523,
|
|
"mean_token_accuracy": 0.1274610109627247,
|
|
"num_tokens": 10588633.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.25370512008667,
|
|
"epoch": 0.4566110285764223,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004984617556557774,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.1470041058957577,
|
|
"num_tokens": 10597917.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.3347279071807865,
|
|
"epoch": 0.45704797692912696,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000498458115990939,
|
|
"loss": 6.1662,
|
|
"mean_token_accuracy": 0.13205529153347015,
|
|
"num_tokens": 10608396.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.224194192886353,
|
|
"epoch": 0.4574849252818317,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004984544720400568,
|
|
"loss": 6.1553,
|
|
"mean_token_accuracy": 0.14002828896045685,
|
|
"num_tokens": 10618191.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.242114734649658,
|
|
"epoch": 0.4579218736345364,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000498450823803201,
|
|
"loss": 6.1463,
|
|
"mean_token_accuracy": 0.13393353223800658,
|
|
"num_tokens": 10627594.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.292330074310303,
|
|
"epoch": 0.4583588219872411,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004984471712804412,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.14734850078821182,
|
|
"num_tokens": 10637260.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.3297521591186525,
|
|
"epoch": 0.45879577033994584,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004984435144718475,
|
|
"loss": 6.1519,
|
|
"mean_token_accuracy": 0.14019931629300117,
|
|
"num_tokens": 10647968.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.210675239562988,
|
|
"epoch": 0.45923271869265053,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004984398533774901,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.14126433730125426,
|
|
"num_tokens": 10657760.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.232064247131348,
|
|
"epoch": 0.4596696670453552,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004984361879974393,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.1337346188724041,
|
|
"num_tokens": 10667577.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.291175508499146,
|
|
"epoch": 0.46010661539805997,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004984325183317654,
|
|
"loss": 6.1139,
|
|
"mean_token_accuracy": 0.135456882417202,
|
|
"num_tokens": 10677984.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.245900678634643,
|
|
"epoch": 0.46054356375076466,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004984288443805386,
|
|
"loss": 6.1471,
|
|
"mean_token_accuracy": 0.14233410954475403,
|
|
"num_tokens": 10687700.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.252521085739136,
|
|
"epoch": 0.46098051210346935,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004984251661438295,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.1394471637904644,
|
|
"num_tokens": 10697351.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.27062954902649,
|
|
"epoch": 0.4614174604561741,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004984214836217087,
|
|
"loss": 6.1384,
|
|
"mean_token_accuracy": 0.1371995449066162,
|
|
"num_tokens": 10707498.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.301582670211792,
|
|
"epoch": 0.4618544088088788,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004984177968142467,
|
|
"loss": 6.1647,
|
|
"mean_token_accuracy": 0.1353110708296299,
|
|
"num_tokens": 10717724.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.294982767105102,
|
|
"epoch": 0.4622913571615835,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004984141057215143,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.13943758979439735,
|
|
"num_tokens": 10727030.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.221749544143677,
|
|
"epoch": 0.46272830551428823,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004984104103435824,
|
|
"loss": 6.0332,
|
|
"mean_token_accuracy": 0.1422347217798233,
|
|
"num_tokens": 10736861.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.303720426559448,
|
|
"epoch": 0.4631652538669929,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004984067106805217,
|
|
"loss": 6.2312,
|
|
"mean_token_accuracy": 0.13308657109737396,
|
|
"num_tokens": 10748310.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.329783916473389,
|
|
"epoch": 0.4636022022196976,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004984030067324032,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.1387430287897587,
|
|
"num_tokens": 10758110.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.263466262817383,
|
|
"epoch": 0.46403915057240236,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004983992984992979,
|
|
"loss": 6.1352,
|
|
"mean_token_accuracy": 0.14275783076882362,
|
|
"num_tokens": 10767919.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.255305910110474,
|
|
"epoch": 0.46447609892510705,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004983955859812771,
|
|
"loss": 6.0637,
|
|
"mean_token_accuracy": 0.1412653312087059,
|
|
"num_tokens": 10776888.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.233955955505371,
|
|
"epoch": 0.46491304727781174,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004983918691784119,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.13571209982037544,
|
|
"num_tokens": 10786806.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.285499954223633,
|
|
"epoch": 0.4653499956305165,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004983881480907736,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.13879325687885286,
|
|
"num_tokens": 10796452.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.286596488952637,
|
|
"epoch": 0.4657869439832212,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004983844227184334,
|
|
"loss": 6.0932,
|
|
"mean_token_accuracy": 0.1357939973473549,
|
|
"num_tokens": 10806718.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.296868705749512,
|
|
"epoch": 0.46622389233592587,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004983806930614631,
|
|
"loss": 6.2042,
|
|
"mean_token_accuracy": 0.13334835544228554,
|
|
"num_tokens": 10817978.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.271781158447266,
|
|
"epoch": 0.4666608406886306,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000498376959119934,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.14710889458656312,
|
|
"num_tokens": 10827818.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.251382207870483,
|
|
"epoch": 0.4670977890413353,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004983732208939178,
|
|
"loss": 6.2205,
|
|
"mean_token_accuracy": 0.1345639370381832,
|
|
"num_tokens": 10838492.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.263595485687256,
|
|
"epoch": 0.46753473739404,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004983694783834863,
|
|
"loss": 6.0753,
|
|
"mean_token_accuracy": 0.13865476250648498,
|
|
"num_tokens": 10847807.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.2714066982269285,
|
|
"epoch": 0.46797168574674475,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004983657315887109,
|
|
"loss": 6.1925,
|
|
"mean_token_accuracy": 0.1346592463552952,
|
|
"num_tokens": 10858637.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.325130271911621,
|
|
"epoch": 0.46840863409944944,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004983619805096639,
|
|
"loss": 6.1113,
|
|
"mean_token_accuracy": 0.14088876843452453,
|
|
"num_tokens": 10868042.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.261090326309204,
|
|
"epoch": 0.46884558245215413,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004983582251464171,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.13843616396188735,
|
|
"num_tokens": 10877171.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.176885032653809,
|
|
"epoch": 0.4692825308048589,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004983544654990423,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.1395420491695404,
|
|
"num_tokens": 10888434.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.2764442443847654,
|
|
"epoch": 0.46971947915756357,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000498350701567612,
|
|
"loss": 6.1631,
|
|
"mean_token_accuracy": 0.14059600606560707,
|
|
"num_tokens": 10898467.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.308957958221436,
|
|
"epoch": 0.47015642751026826,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004983469333521983,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.14148796796798707,
|
|
"num_tokens": 10908178.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.2301304817199705,
|
|
"epoch": 0.470593375862973,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004983431608528732,
|
|
"loss": 6.2115,
|
|
"mean_token_accuracy": 0.12733783274888993,
|
|
"num_tokens": 10919957.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.302609539031982,
|
|
"epoch": 0.4710303242156777,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004983393840697092,
|
|
"loss": 6.1579,
|
|
"mean_token_accuracy": 0.13929501324892044,
|
|
"num_tokens": 10929728.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.291434621810913,
|
|
"epoch": 0.4714672725683824,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004983356030027789,
|
|
"loss": 6.1957,
|
|
"mean_token_accuracy": 0.13646872639656066,
|
|
"num_tokens": 10940427.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.217552328109742,
|
|
"epoch": 0.47190422092108714,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004983318176521546,
|
|
"loss": 6.1575,
|
|
"mean_token_accuracy": 0.13504248932003976,
|
|
"num_tokens": 10950641.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.335336399078369,
|
|
"epoch": 0.4723411692737918,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004983280280179092,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.1392090730369091,
|
|
"num_tokens": 10959341.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.327978801727295,
|
|
"epoch": 0.4727781176264966,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000498324234100115,
|
|
"loss": 6.1075,
|
|
"mean_token_accuracy": 0.13960520774126053,
|
|
"num_tokens": 10967745.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.209249353408813,
|
|
"epoch": 0.47321506597920127,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004983204358988451,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.13568175733089446,
|
|
"num_tokens": 10978345.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.214342164993286,
|
|
"epoch": 0.47365201433190596,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004983166334141722,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.13103256821632386,
|
|
"num_tokens": 10988030.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.362129402160645,
|
|
"epoch": 0.4740889626846107,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004983128266461693,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.12891222313046455,
|
|
"num_tokens": 10999169.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.280517530441284,
|
|
"epoch": 0.4745259110373154,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 0.0004983090155949093,
|
|
"loss": 6.2207,
|
|
"mean_token_accuracy": 0.13183309584856034,
|
|
"num_tokens": 11009608.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.205153751373291,
|
|
"epoch": 0.4749628593900201,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004983052002604653,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.13711439147591592,
|
|
"num_tokens": 11020187.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.298795366287232,
|
|
"epoch": 0.47539980774272483,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004983013806429107,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.1389899007976055,
|
|
"num_tokens": 11030459.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.219760274887085,
|
|
"epoch": 0.4758367560954295,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004982975567423185,
|
|
"loss": 6.0758,
|
|
"mean_token_accuracy": 0.1416230507194996,
|
|
"num_tokens": 11040880.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.261538934707642,
|
|
"epoch": 0.4762737044481342,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004982937285587623,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.14153316840529442,
|
|
"num_tokens": 11050901.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.320458269119262,
|
|
"epoch": 0.47671065280083896,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004982898960923152,
|
|
"loss": 6.2696,
|
|
"mean_token_accuracy": 0.1284100241959095,
|
|
"num_tokens": 11061274.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.34821310043335,
|
|
"epoch": 0.47714760115354365,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004982860593430509,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.1355578728020191,
|
|
"num_tokens": 11070644.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.249191522598267,
|
|
"epoch": 0.47758454950624835,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004982822183110431,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.1370291531085968,
|
|
"num_tokens": 11081154.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.270349931716919,
|
|
"epoch": 0.4780214978589531,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004982783729963654,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.1320676937699318,
|
|
"num_tokens": 11091929.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.239210939407348,
|
|
"epoch": 0.4784584462116578,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004982745233990914,
|
|
"loss": 6.0728,
|
|
"mean_token_accuracy": 0.14582818001508713,
|
|
"num_tokens": 11102075.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.25434103012085,
|
|
"epoch": 0.4788953945643625,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004982706695192949,
|
|
"loss": 6.1428,
|
|
"mean_token_accuracy": 0.1331348791718483,
|
|
"num_tokens": 11111886.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.288838911056518,
|
|
"epoch": 0.4793323429170672,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004982668113570503,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.13364839926362038,
|
|
"num_tokens": 11122329.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.253954172134399,
|
|
"epoch": 0.4797692912697719,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000498262948912431,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.13713959529995917,
|
|
"num_tokens": 11132348.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.224376440048218,
|
|
"epoch": 0.4802062396224766,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004982590821855115,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.13753138929605485,
|
|
"num_tokens": 11141975.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.271784734725952,
|
|
"epoch": 0.48064318797518135,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004982552111763657,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.13205370903015137,
|
|
"num_tokens": 11152174.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.328236293792725,
|
|
"epoch": 0.48108013632788604,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004982513358850681,
|
|
"loss": 6.1503,
|
|
"mean_token_accuracy": 0.13584645465016365,
|
|
"num_tokens": 11162563.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.294511032104492,
|
|
"epoch": 0.48151708468059073,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004982474563116928,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.1419669657945633,
|
|
"num_tokens": 11172572.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.245644664764404,
|
|
"epoch": 0.4819540330332955,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004982435724563143,
|
|
"loss": 6.1391,
|
|
"mean_token_accuracy": 0.14169370457530023,
|
|
"num_tokens": 11183404.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.188567304611206,
|
|
"epoch": 0.4823909813860002,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004982396843190072,
|
|
"loss": 6.1603,
|
|
"mean_token_accuracy": 0.13115517497062684,
|
|
"num_tokens": 11193905.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.244078588485718,
|
|
"epoch": 0.48282792973870486,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004982357918998459,
|
|
"loss": 6.0617,
|
|
"mean_token_accuracy": 0.15290317088365554,
|
|
"num_tokens": 11203127.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.258895540237427,
|
|
"epoch": 0.4832648780914096,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004982318951989053,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.14411210864782334,
|
|
"num_tokens": 11213468.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.245413780212402,
|
|
"epoch": 0.4837018264441143,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004982279942162597,
|
|
"loss": 6.171,
|
|
"mean_token_accuracy": 0.14047423750162125,
|
|
"num_tokens": 11224722.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.271645212173462,
|
|
"epoch": 0.484138774796819,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004982240889519844,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.1361476957798004,
|
|
"num_tokens": 11234565.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.279338216781616,
|
|
"epoch": 0.48457572314952374,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000498220179406154,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.13795690312981607,
|
|
"num_tokens": 11244496.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.319229602813721,
|
|
"epoch": 0.48501267150222843,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004982162655788436,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.1403142899274826,
|
|
"num_tokens": 11254187.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.252913284301758,
|
|
"epoch": 0.4854496198549331,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004982123474701283,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.14224717393517494,
|
|
"num_tokens": 11264580.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.238586473464966,
|
|
"epoch": 0.48588656820763787,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004982084250800832,
|
|
"loss": 6.2267,
|
|
"mean_token_accuracy": 0.13188387230038642,
|
|
"num_tokens": 11275104.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.348457193374633,
|
|
"epoch": 0.48632351656034256,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004982044984087836,
|
|
"loss": 6.2423,
|
|
"mean_token_accuracy": 0.13024362698197364,
|
|
"num_tokens": 11285983.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.368983268737793,
|
|
"epoch": 0.48676046491304725,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004982005674563048,
|
|
"loss": 6.1208,
|
|
"mean_token_accuracy": 0.1400579683482647,
|
|
"num_tokens": 11295378.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.3164036750793455,
|
|
"epoch": 0.487197413265752,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000498196632222722,
|
|
"loss": 6.2217,
|
|
"mean_token_accuracy": 0.1353451281785965,
|
|
"num_tokens": 11305500.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.254426193237305,
|
|
"epoch": 0.4876343616184567,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004981926927081109,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.13708797097206116,
|
|
"num_tokens": 11316455.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.273268747329712,
|
|
"epoch": 0.4880713099711614,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004981887489125471,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.1336928963661194,
|
|
"num_tokens": 11325865.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.25109896659851,
|
|
"epoch": 0.48850825832386613,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000498184800836106,
|
|
"loss": 6.0871,
|
|
"mean_token_accuracy": 0.14778236225247382,
|
|
"num_tokens": 11337368.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.20948600769043,
|
|
"epoch": 0.4889452066765708,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004981808484788635,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.1448922872543335,
|
|
"num_tokens": 11347129.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.27021336555481,
|
|
"epoch": 0.48938215502927557,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004981768918408955,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.13713421151041985,
|
|
"num_tokens": 11356641.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.252780914306641,
|
|
"epoch": 0.48981910338198026,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004981729309222777,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.1457279920578003,
|
|
"num_tokens": 11366485.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.238640213012696,
|
|
"epoch": 0.49025605173468495,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004981689657230861,
|
|
"loss": 6.1711,
|
|
"mean_token_accuracy": 0.1374865762889385,
|
|
"num_tokens": 11376305.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.294531774520874,
|
|
"epoch": 0.4906930000873897,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.000498164996243397,
|
|
"loss": 6.1401,
|
|
"mean_token_accuracy": 0.13293426483869553,
|
|
"num_tokens": 11385837.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.267136859893799,
|
|
"epoch": 0.4911299484400944,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004981610224832861,
|
|
"loss": 6.1751,
|
|
"mean_token_accuracy": 0.14129467606544494,
|
|
"num_tokens": 11396719.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.326460218429565,
|
|
"epoch": 0.4915668967927991,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004981570444428299,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.13250873759388923,
|
|
"num_tokens": 11408107.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.281957674026489,
|
|
"epoch": 0.4920038451455038,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004981530621221048,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.14190632849931717,
|
|
"num_tokens": 11417547.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.336714124679565,
|
|
"epoch": 0.4924407934982085,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004981490755211869,
|
|
"loss": 6.1658,
|
|
"mean_token_accuracy": 0.14127280861139296,
|
|
"num_tokens": 11427660.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.287770366668701,
|
|
"epoch": 0.4928777418509132,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004981450846401528,
|
|
"loss": 6.0589,
|
|
"mean_token_accuracy": 0.14569119960069657,
|
|
"num_tokens": 11438032.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.2903404712677,
|
|
"epoch": 0.49331469020361796,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000498141089479079,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.13444297164678573,
|
|
"num_tokens": 11448987.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.238702011108399,
|
|
"epoch": 0.49375163855632265,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004981370900380423,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.14375114664435387,
|
|
"num_tokens": 11458659.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.276248025894165,
|
|
"epoch": 0.49418858690902734,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004981330863171194,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.1386402390897274,
|
|
"num_tokens": 11468104.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.289006233215332,
|
|
"epoch": 0.4946255352617321,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004981290783163867,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.1435806483030319,
|
|
"num_tokens": 11479579.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.295569610595703,
|
|
"epoch": 0.4950624836144368,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004981250660359216,
|
|
"loss": 6.1365,
|
|
"mean_token_accuracy": 0.14263879805803298,
|
|
"num_tokens": 11489202.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.295229196548462,
|
|
"epoch": 0.49549943196714147,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004981210494758007,
|
|
"loss": 6.1683,
|
|
"mean_token_accuracy": 0.13030786961317062,
|
|
"num_tokens": 11499425.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.279474401473999,
|
|
"epoch": 0.4959363803198462,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.000498117028636101,
|
|
"loss": 6.1286,
|
|
"mean_token_accuracy": 0.13767644241452218,
|
|
"num_tokens": 11508983.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.254884052276611,
|
|
"epoch": 0.4963733286725509,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004981130035169,
|
|
"loss": 6.1943,
|
|
"mean_token_accuracy": 0.14120121970772742,
|
|
"num_tokens": 11519791.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.310758495330811,
|
|
"epoch": 0.4968102770252556,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004981089741182747,
|
|
"loss": 6.1183,
|
|
"mean_token_accuracy": 0.14048743546009063,
|
|
"num_tokens": 11530537.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.284348869323731,
|
|
"epoch": 0.49724722537796034,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004981049404403023,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.13990036472678186,
|
|
"num_tokens": 11540591.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.2591174125671385,
|
|
"epoch": 0.49768417373066504,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004981009024830602,
|
|
"loss": 6.0942,
|
|
"mean_token_accuracy": 0.13814121037721633,
|
|
"num_tokens": 11550719.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.222075080871582,
|
|
"epoch": 0.4981211220833697,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000498096860246626,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.1384321503341198,
|
|
"num_tokens": 11561805.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.352153635025024,
|
|
"epoch": 0.4985580704360745,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000498092813731077,
|
|
"loss": 6.1634,
|
|
"mean_token_accuracy": 0.13272807076573373,
|
|
"num_tokens": 11571380.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.310147285461426,
|
|
"epoch": 0.49899501878877917,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000498088762936491,
|
|
"loss": 6.1564,
|
|
"mean_token_accuracy": 0.1386110305786133,
|
|
"num_tokens": 11580853.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.148832035064697,
|
|
"epoch": 0.49943196714148386,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004980847078629457,
|
|
"loss": 6.0639,
|
|
"mean_token_accuracy": 0.1558942325413227,
|
|
"num_tokens": 11591966.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.198760461807251,
|
|
"epoch": 0.4998689154941886,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004980806485105186,
|
|
"loss": 6.1139,
|
|
"mean_token_accuracy": 0.14199392199516297,
|
|
"num_tokens": 11601239.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.2181836605072025,
|
|
"epoch": 0.5003058638468934,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004980765848792879,
|
|
"loss": 6.0396,
|
|
"mean_token_accuracy": 0.1473376788198948,
|
|
"num_tokens": 11609857.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.266326093673706,
|
|
"epoch": 0.500742812199598,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004980725169693314,
|
|
"loss": 6.0735,
|
|
"mean_token_accuracy": 0.14394057914614677,
|
|
"num_tokens": 11618952.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.269810056686401,
|
|
"epoch": 0.5011797605523027,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004980684447807272,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.14204780012369156,
|
|
"num_tokens": 11627638.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.2179922580719,
|
|
"epoch": 0.5016167089050074,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004980643683135533,
|
|
"loss": 6.1444,
|
|
"mean_token_accuracy": 0.1408068686723709,
|
|
"num_tokens": 11637842.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.215860080718994,
|
|
"epoch": 0.5020536572577121,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004980602875678878,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.14877952188253402,
|
|
"num_tokens": 11647217.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.198777055740356,
|
|
"epoch": 0.5024906056104168,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004980562025438093,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.1428973264992237,
|
|
"num_tokens": 11657558.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.150891494750977,
|
|
"epoch": 0.5029275539631216,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004980521132413958,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.14264654815196992,
|
|
"num_tokens": 11668054.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.298615503311157,
|
|
"epoch": 0.5033645023158263,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000498048019660726,
|
|
"loss": 6.0764,
|
|
"mean_token_accuracy": 0.1434045687317848,
|
|
"num_tokens": 11677779.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.304033184051514,
|
|
"epoch": 0.503801450668531,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004980439218018783,
|
|
"loss": 6.1201,
|
|
"mean_token_accuracy": 0.13853600099682808,
|
|
"num_tokens": 11687577.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.269702291488647,
|
|
"epoch": 0.5042383990212357,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004980398196649312,
|
|
"loss": 6.2192,
|
|
"mean_token_accuracy": 0.13097881749272347,
|
|
"num_tokens": 11699630.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.266751432418824,
|
|
"epoch": 0.5046753473739404,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004980357132499636,
|
|
"loss": 6.1513,
|
|
"mean_token_accuracy": 0.13628338277339935,
|
|
"num_tokens": 11710139.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.301572465896607,
|
|
"epoch": 0.5051122957266451,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004980316025570542,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.13941313028335572,
|
|
"num_tokens": 11719070.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.239738321304321,
|
|
"epoch": 0.5055492440793499,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004980274875862816,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.1385067269206047,
|
|
"num_tokens": 11728770.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.282432889938354,
|
|
"epoch": 0.5059861924320546,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.000498023368337725,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.14360614940524102,
|
|
"num_tokens": 11737753.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.236385011672974,
|
|
"epoch": 0.5064231407847593,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004980192448114635,
|
|
"loss": 6.0672,
|
|
"mean_token_accuracy": 0.14035124331712723,
|
|
"num_tokens": 11747837.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.165898418426513,
|
|
"epoch": 0.5068600891374639,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004980151170075758,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.1387983664870262,
|
|
"num_tokens": 11757911.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.33115816116333,
|
|
"epoch": 0.5072970374901686,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004980109849261414,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.14173925220966338,
|
|
"num_tokens": 11766213.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.249571466445923,
|
|
"epoch": 0.5077339858428733,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004980068485672394,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.1495368130505085,
|
|
"num_tokens": 11775640.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.280322885513305,
|
|
"epoch": 0.5081709341955781,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004980027079309493,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.14636014476418496,
|
|
"num_tokens": 11785664.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.23998990058899,
|
|
"epoch": 0.5086078825482828,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004979985630173503,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.12907436937093736,
|
|
"num_tokens": 11795402.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.258623647689819,
|
|
"epoch": 0.5090448309009875,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004979944138265221,
|
|
"loss": 6.0445,
|
|
"mean_token_accuracy": 0.14042759463191032,
|
|
"num_tokens": 11805923.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.231123399734497,
|
|
"epoch": 0.5094817792536922,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004979902603585442,
|
|
"loss": 6.1287,
|
|
"mean_token_accuracy": 0.14135455191135407,
|
|
"num_tokens": 11816097.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.2674267292022705,
|
|
"epoch": 0.5099187276063969,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004979861026134961,
|
|
"loss": 6.0798,
|
|
"mean_token_accuracy": 0.14172066152095794,
|
|
"num_tokens": 11826889.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.2974059104919435,
|
|
"epoch": 0.5103556759591016,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004979819405914579,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.1364697828888893,
|
|
"num_tokens": 11837935.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.264686822891235,
|
|
"epoch": 0.5107926243118064,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004979777742925092,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.1356620818376541,
|
|
"num_tokens": 11847715.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.263647890090942,
|
|
"epoch": 0.5112295726645111,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004979736037167298,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.1327194854617119,
|
|
"num_tokens": 11857841.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.285010814666748,
|
|
"epoch": 0.5116665210172158,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004979694288642,
|
|
"loss": 6.1182,
|
|
"mean_token_accuracy": 0.14218535423278808,
|
|
"num_tokens": 11868135.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.3095512866973875,
|
|
"epoch": 0.5121034693699205,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004979652497349997,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.14099670946598053,
|
|
"num_tokens": 11877637.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.186911582946777,
|
|
"epoch": 0.5125404177226252,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000497961066329209,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.13389617949724197,
|
|
"num_tokens": 11887128.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.2536896705627445,
|
|
"epoch": 0.5129773660753298,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004979568786469083,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.12886641845107077,
|
|
"num_tokens": 11897885.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.281183671951294,
|
|
"epoch": 0.5134143144280346,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004979526866881777,
|
|
"loss": 6.0867,
|
|
"mean_token_accuracy": 0.13957348465919495,
|
|
"num_tokens": 11907919.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.24418797492981,
|
|
"epoch": 0.5138512627807393,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.000497948490453098,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.1437679760158062,
|
|
"num_tokens": 11918612.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.180129671096802,
|
|
"epoch": 0.514288211133444,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004979442899417493,
|
|
"loss": 6.1513,
|
|
"mean_token_accuracy": 0.13741420656442643,
|
|
"num_tokens": 11927759.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.280853271484375,
|
|
"epoch": 0.5147251594861487,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004979400851542122,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.1479244738817215,
|
|
"num_tokens": 11937522.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.3057684898376465,
|
|
"epoch": 0.5151621078388534,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004979358760905675,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.13870553597807883,
|
|
"num_tokens": 11947787.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.171240282058716,
|
|
"epoch": 0.5155990561915581,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.000497931662750896,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.1385062739253044,
|
|
"num_tokens": 11958929.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.199537706375122,
|
|
"epoch": 0.5160360045442629,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004979274451352783,
|
|
"loss": 6.0583,
|
|
"mean_token_accuracy": 0.13892978727817534,
|
|
"num_tokens": 11969242.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.292746734619141,
|
|
"epoch": 0.5164729528969676,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004979232232437954,
|
|
"loss": 6.1336,
|
|
"mean_token_accuracy": 0.1345326527953148,
|
|
"num_tokens": 11980149.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.410525369644165,
|
|
"epoch": 0.5169099012496723,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004979189970765282,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.13244713917374612,
|
|
"num_tokens": 11990636.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.33321442604065,
|
|
"epoch": 0.517346849602377,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004979147666335579,
|
|
"loss": 6.1639,
|
|
"mean_token_accuracy": 0.14218005761504174,
|
|
"num_tokens": 12000615.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.229039573669434,
|
|
"epoch": 0.5177837979550817,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004979105319149656,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.1388854667544365,
|
|
"num_tokens": 12011072.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.2475790023803714,
|
|
"epoch": 0.5182207463077865,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004979062929208324,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.14881260618567466,
|
|
"num_tokens": 12021726.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.287198257446289,
|
|
"epoch": 0.5186576946604912,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004979020496512398,
|
|
"loss": 6.2044,
|
|
"mean_token_accuracy": 0.13563393875956536,
|
|
"num_tokens": 12031353.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.357402753829956,
|
|
"epoch": 0.5190946430131959,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.000497897802106269,
|
|
"loss": 6.1369,
|
|
"mean_token_accuracy": 0.13450635075569153,
|
|
"num_tokens": 12041234.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.225025939941406,
|
|
"epoch": 0.5195315913659005,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004978935502860017,
|
|
"loss": 6.0755,
|
|
"mean_token_accuracy": 0.14126456677913665,
|
|
"num_tokens": 12051100.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.214692163467407,
|
|
"epoch": 0.5199685397186052,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004978892941905191,
|
|
"loss": 6.1442,
|
|
"mean_token_accuracy": 0.1400235928595066,
|
|
"num_tokens": 12062012.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.325677824020386,
|
|
"epoch": 0.5204054880713099,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004978850338199033,
|
|
"loss": 6.1463,
|
|
"mean_token_accuracy": 0.1371977373957634,
|
|
"num_tokens": 12072763.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.259446907043457,
|
|
"epoch": 0.5208424364240147,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004978807691742356,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.148126420378685,
|
|
"num_tokens": 12081892.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.177407932281494,
|
|
"epoch": 0.5212793847767194,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000497876500253598,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.14243873953819275,
|
|
"num_tokens": 12091428.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.217768621444702,
|
|
"epoch": 0.5217163331294241,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004978722270580722,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.1395185723900795,
|
|
"num_tokens": 12101687.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.190403652191162,
|
|
"epoch": 0.5221532814821288,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004978679495877405,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.1401352971792221,
|
|
"num_tokens": 12111726.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.2400407791137695,
|
|
"epoch": 0.5225902298348335,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004978636678426847,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.14529430642724037,
|
|
"num_tokens": 12122171.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.371889734268189,
|
|
"epoch": 0.5230271781875382,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004978593818229869,
|
|
"loss": 6.1141,
|
|
"mean_token_accuracy": 0.1365119956433773,
|
|
"num_tokens": 12131414.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.23081226348877,
|
|
"epoch": 0.523464126540243,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004978550915287294,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.1337629109621048,
|
|
"num_tokens": 12141665.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.2171844959259035,
|
|
"epoch": 0.5239010748929477,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004978507969599945,
|
|
"loss": 6.1587,
|
|
"mean_token_accuracy": 0.1341513715684414,
|
|
"num_tokens": 12151263.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.334724473953247,
|
|
"epoch": 0.5243380232456524,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004978464981168645,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.13718220144510268,
|
|
"num_tokens": 12161070.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5243380232456524,
|
|
"eval_entropy": 6.185264414372392,
|
|
"eval_loss": 6.144855499267578,
|
|
"eval_mean_token_accuracy": 0.14467228393698192,
|
|
"eval_num_tokens": 12161070.0,
|
|
"eval_runtime": 28.2471,
|
|
"eval_samples_per_second": 1310.366,
|
|
"eval_steps_per_second": 163.805,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.30408787727356,
|
|
"epoch": 0.5247749715983571,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000497842194999422,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.13960754871368408,
|
|
"num_tokens": 12171197.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.211764478683472,
|
|
"epoch": 0.5252119199510618,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004978378876077493,
|
|
"loss": 6.1377,
|
|
"mean_token_accuracy": 0.13761500567197799,
|
|
"num_tokens": 12181462.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.263395357131958,
|
|
"epoch": 0.5256488683037664,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004978335759419293,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.14520457834005357,
|
|
"num_tokens": 12191473.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.347568559646606,
|
|
"epoch": 0.5260858166564713,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004978292600020444,
|
|
"loss": 6.0729,
|
|
"mean_token_accuracy": 0.14109345898032188,
|
|
"num_tokens": 12200920.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.300686883926391,
|
|
"epoch": 0.5265227650091759,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004978249397881776,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.1390794076025486,
|
|
"num_tokens": 12210823.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.263337230682373,
|
|
"epoch": 0.5269597133618806,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004978206153004117,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.13617446646094322,
|
|
"num_tokens": 12221967.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.28148627281189,
|
|
"epoch": 0.5273966617145853,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004978162865388297,
|
|
"loss": 6.1163,
|
|
"mean_token_accuracy": 0.13850070759654046,
|
|
"num_tokens": 12232519.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.273348712921143,
|
|
"epoch": 0.52783361006729,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004978119535035144,
|
|
"loss": 6.0763,
|
|
"mean_token_accuracy": 0.13540117889642717,
|
|
"num_tokens": 12243193.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.2839103698730465,
|
|
"epoch": 0.5282705584199947,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004978076161945492,
|
|
"loss": 6.0884,
|
|
"mean_token_accuracy": 0.14195277616381646,
|
|
"num_tokens": 12253640.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.409676742553711,
|
|
"epoch": 0.5287075067726995,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004978032746120173,
|
|
"loss": 6.2042,
|
|
"mean_token_accuracy": 0.12442022413015366,
|
|
"num_tokens": 12265072.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.2757384300231935,
|
|
"epoch": 0.5291444551254042,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004977989287560016,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.13877920806407928,
|
|
"num_tokens": 12274449.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.271896934509277,
|
|
"epoch": 0.5295814034781089,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004977945786265857,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.1312025398015976,
|
|
"num_tokens": 12284910.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.38758020401001,
|
|
"epoch": 0.5300183518308136,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004977902242238533,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.1351582631468773,
|
|
"num_tokens": 12294046.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.280045509338379,
|
|
"epoch": 0.5304553001835183,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004977858655478874,
|
|
"loss": 6.1488,
|
|
"mean_token_accuracy": 0.13523225262761115,
|
|
"num_tokens": 12303900.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.238226747512817,
|
|
"epoch": 0.530892248536223,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000497781502598772,
|
|
"loss": 6.0946,
|
|
"mean_token_accuracy": 0.14537760987877846,
|
|
"num_tokens": 12313326.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.217903280258179,
|
|
"epoch": 0.5313291968889278,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004977771353765906,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.13752787113189696,
|
|
"num_tokens": 12322792.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.297841787338257,
|
|
"epoch": 0.5317661452416325,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000497772763881427,
|
|
"loss": 6.2045,
|
|
"mean_token_accuracy": 0.13359650894999503,
|
|
"num_tokens": 12333417.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.292433023452759,
|
|
"epoch": 0.5322030935943372,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004977683881133651,
|
|
"loss": 6.1106,
|
|
"mean_token_accuracy": 0.13563139513134956,
|
|
"num_tokens": 12343944.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.2595867156982425,
|
|
"epoch": 0.5326400419470418,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004977640080724888,
|
|
"loss": 6.0801,
|
|
"mean_token_accuracy": 0.1347056582570076,
|
|
"num_tokens": 12353838.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.292349815368652,
|
|
"epoch": 0.5330769902997465,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004977596237588821,
|
|
"loss": 6.1777,
|
|
"mean_token_accuracy": 0.1316857986152172,
|
|
"num_tokens": 12364996.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.327098417282104,
|
|
"epoch": 0.5335139386524512,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000497755235172629,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.1362926870584488,
|
|
"num_tokens": 12375111.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.296980190277099,
|
|
"epoch": 0.533950887005156,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004977508423138139,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.13595320358872415,
|
|
"num_tokens": 12384376.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.287497091293335,
|
|
"epoch": 0.5343878353578607,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004977464451825208,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.13291269168257713,
|
|
"num_tokens": 12395248.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.29342999458313,
|
|
"epoch": 0.5348247837105654,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004977420437788341,
|
|
"loss": 6.1345,
|
|
"mean_token_accuracy": 0.13793925195932388,
|
|
"num_tokens": 12405083.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.214169359207153,
|
|
"epoch": 0.5352617320632701,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004977376381028385,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.14968093633651733,
|
|
"num_tokens": 12415787.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.330326509475708,
|
|
"epoch": 0.5356986804159748,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004977332281546181,
|
|
"loss": 6.1069,
|
|
"mean_token_accuracy": 0.13906310126185417,
|
|
"num_tokens": 12425911.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.279489517211914,
|
|
"epoch": 0.5361356287686796,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004977288139342578,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.1360112026333809,
|
|
"num_tokens": 12437270.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.254675626754761,
|
|
"epoch": 0.5365725771213843,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004977243954418422,
|
|
"loss": 6.0827,
|
|
"mean_token_accuracy": 0.13789032846689225,
|
|
"num_tokens": 12446778.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.228334951400757,
|
|
"epoch": 0.537009525474089,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004977199726774558,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.14418192505836486,
|
|
"num_tokens": 12456550.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.249480247497559,
|
|
"epoch": 0.5374464738267937,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004977155456411837,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.13996390253305435,
|
|
"num_tokens": 12465562.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.334767532348633,
|
|
"epoch": 0.5378834221794984,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004977111143331108,
|
|
"loss": 6.1114,
|
|
"mean_token_accuracy": 0.13722820729017257,
|
|
"num_tokens": 12475277.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.240406560897827,
|
|
"epoch": 0.538320370532203,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004977066787533219,
|
|
"loss": 6.0562,
|
|
"mean_token_accuracy": 0.1435964971780777,
|
|
"num_tokens": 12485478.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.293786430358887,
|
|
"epoch": 0.5387573188849079,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004977022389019023,
|
|
"loss": 6.1654,
|
|
"mean_token_accuracy": 0.13637920394539832,
|
|
"num_tokens": 12495714.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.393072557449341,
|
|
"epoch": 0.5391942672376125,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004976977947789371,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.14155342802405357,
|
|
"num_tokens": 12505125.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.261453914642334,
|
|
"epoch": 0.5396312155903172,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004976933463845115,
|
|
"loss": 6.0887,
|
|
"mean_token_accuracy": 0.14094004184007644,
|
|
"num_tokens": 12515051.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.120384788513183,
|
|
"epoch": 0.5400681639430219,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004976888937187107,
|
|
"loss": 6.0326,
|
|
"mean_token_accuracy": 0.14698556512594224,
|
|
"num_tokens": 12525389.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.238776445388794,
|
|
"epoch": 0.5405051122957266,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004976844367816203,
|
|
"loss": 6.1414,
|
|
"mean_token_accuracy": 0.13036047220230101,
|
|
"num_tokens": 12535454.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.278572750091553,
|
|
"epoch": 0.5409420606484313,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004976799755733257,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.14532420784235,
|
|
"num_tokens": 12546092.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.220078992843628,
|
|
"epoch": 0.5413790090011361,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004976755100939126,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.13647042587399483,
|
|
"num_tokens": 12555462.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.2149238109588625,
|
|
"epoch": 0.5418159573538408,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004976710403434663,
|
|
"loss": 6.1188,
|
|
"mean_token_accuracy": 0.14242732897400856,
|
|
"num_tokens": 12564506.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.283080196380615,
|
|
"epoch": 0.5422529057065455,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000497666566322073,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.1390668608248234,
|
|
"num_tokens": 12574887.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.363029432296753,
|
|
"epoch": 0.5426898540592502,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004976620880298182,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.13858333677053453,
|
|
"num_tokens": 12584499.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.247929334640503,
|
|
"epoch": 0.5431268024119549,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004976576054667878,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.14071348756551744,
|
|
"num_tokens": 12593796.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.159736394882202,
|
|
"epoch": 0.5435637507646596,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000497653118633068,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.13587007597088813,
|
|
"num_tokens": 12603719.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.186320877075195,
|
|
"epoch": 0.5440006991173644,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004976486275287446,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.1381325379014015,
|
|
"num_tokens": 12614407.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.255827951431274,
|
|
"epoch": 0.5444376474700691,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004976441321539038,
|
|
"loss": 6.1109,
|
|
"mean_token_accuracy": 0.14508781358599662,
|
|
"num_tokens": 12624414.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.289930629730224,
|
|
"epoch": 0.5448745958227738,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004976396325086321,
|
|
"loss": 6.1272,
|
|
"mean_token_accuracy": 0.1362790621817112,
|
|
"num_tokens": 12635679.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.303273487091064,
|
|
"epoch": 0.5453115441754784,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004976351285930154,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.1359069027006626,
|
|
"num_tokens": 12645253.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.189432621002197,
|
|
"epoch": 0.5457484925281831,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004976306204071404,
|
|
"loss": 6.0268,
|
|
"mean_token_accuracy": 0.1512258157134056,
|
|
"num_tokens": 12655815.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.201519250869751,
|
|
"epoch": 0.5461854408808878,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004976261079510934,
|
|
"loss": 6.1203,
|
|
"mean_token_accuracy": 0.142380790412426,
|
|
"num_tokens": 12666173.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.226180744171143,
|
|
"epoch": 0.5466223892335926,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000497621591224961,
|
|
"loss": 6.0546,
|
|
"mean_token_accuracy": 0.14446704164147378,
|
|
"num_tokens": 12676008.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.300201177597046,
|
|
"epoch": 0.5470593375862973,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004976170702288298,
|
|
"loss": 6.1232,
|
|
"mean_token_accuracy": 0.13573255613446236,
|
|
"num_tokens": 12686217.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.262121248245239,
|
|
"epoch": 0.547496285939002,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004976125449627866,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.13377300202846526,
|
|
"num_tokens": 12696809.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.294864988327026,
|
|
"epoch": 0.5479332342917067,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004976080154269181,
|
|
"loss": 6.1849,
|
|
"mean_token_accuracy": 0.1314307503402233,
|
|
"num_tokens": 12708328.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.319700622558594,
|
|
"epoch": 0.5483701826444114,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004976034816213112,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.13883933499455453,
|
|
"num_tokens": 12718478.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.179039812088012,
|
|
"epoch": 0.5488071309971161,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004975989435460528,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.14150369465351104,
|
|
"num_tokens": 12728853.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.204391956329346,
|
|
"epoch": 0.5492440793498209,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004975944012012302,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.14521700143814087,
|
|
"num_tokens": 12739036.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.317832612991333,
|
|
"epoch": 0.5496810277025256,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004975898545869303,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.14573338478803635,
|
|
"num_tokens": 12748908.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.303751611709595,
|
|
"epoch": 0.5501179760552303,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004975853037032403,
|
|
"loss": 6.1436,
|
|
"mean_token_accuracy": 0.13691058456897737,
|
|
"num_tokens": 12758671.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.165650987625122,
|
|
"epoch": 0.550554924407935,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004975807485502476,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.13557566404342652,
|
|
"num_tokens": 12769552.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.271069431304932,
|
|
"epoch": 0.5509918727606397,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004975761891280394,
|
|
"loss": 6.2495,
|
|
"mean_token_accuracy": 0.12941641584038735,
|
|
"num_tokens": 12781032.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.3879612445831295,
|
|
"epoch": 0.5514288211133443,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004975716254367033,
|
|
"loss": 6.1693,
|
|
"mean_token_accuracy": 0.13546326085925103,
|
|
"num_tokens": 12790818.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.262982940673828,
|
|
"epoch": 0.5518657694660491,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000497567057476327,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.14123047664761543,
|
|
"num_tokens": 12799701.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.253837537765503,
|
|
"epoch": 0.5523027178187538,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004975624852469976,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.14434364140033723,
|
|
"num_tokens": 12809575.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.324242067337036,
|
|
"epoch": 0.5527396661714585,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004975579087488033,
|
|
"loss": 6.1198,
|
|
"mean_token_accuracy": 0.13896695226430894,
|
|
"num_tokens": 12820278.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.2966714859008786,
|
|
"epoch": 0.5531766145241632,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004975533279818317,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.13830024525523185,
|
|
"num_tokens": 12830774.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.179326057434082,
|
|
"epoch": 0.5536135628768679,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004975487429461706,
|
|
"loss": 6.0738,
|
|
"mean_token_accuracy": 0.14779838770627976,
|
|
"num_tokens": 12839487.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.211460542678833,
|
|
"epoch": 0.5540505112295727,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000497544153641908,
|
|
"loss": 6.0443,
|
|
"mean_token_accuracy": 0.13948678150773047,
|
|
"num_tokens": 12849614.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.282157468795776,
|
|
"epoch": 0.5544874595822774,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004975395600691319,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.14338527768850326,
|
|
"num_tokens": 12859428.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.241535282135009,
|
|
"epoch": 0.5549244079349821,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004975349622279305,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.1375342957675457,
|
|
"num_tokens": 12869167.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.230395698547364,
|
|
"epoch": 0.5553613562876868,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004975303601183919,
|
|
"loss": 6.0852,
|
|
"mean_token_accuracy": 0.14296441450715064,
|
|
"num_tokens": 12878410.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.313714265823364,
|
|
"epoch": 0.5557983046403915,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004975257537406043,
|
|
"loss": 6.0971,
|
|
"mean_token_accuracy": 0.13664701357483863,
|
|
"num_tokens": 12888372.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.228673601150513,
|
|
"epoch": 0.5562352529930962,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004975211430946563,
|
|
"loss": 6.1475,
|
|
"mean_token_accuracy": 0.1400043822824955,
|
|
"num_tokens": 12897958.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.231792783737182,
|
|
"epoch": 0.556672201345801,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000497516528180636,
|
|
"loss": 6.1409,
|
|
"mean_token_accuracy": 0.1417572058737278,
|
|
"num_tokens": 12907890.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.292871379852295,
|
|
"epoch": 0.5571091496985057,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004975119089986322,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.13979636877775192,
|
|
"num_tokens": 12917914.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.238379096984863,
|
|
"epoch": 0.5575460980512104,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004975072855487333,
|
|
"loss": 6.1133,
|
|
"mean_token_accuracy": 0.14305043667554856,
|
|
"num_tokens": 12927090.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.2708868980407715,
|
|
"epoch": 0.557983046403915,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004975026578310282,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.1360911414027214,
|
|
"num_tokens": 12937236.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.29693112373352,
|
|
"epoch": 0.5584199947566197,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004974980258456055,
|
|
"loss": 6.0469,
|
|
"mean_token_accuracy": 0.1430341236293316,
|
|
"num_tokens": 12947635.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.304951333999634,
|
|
"epoch": 0.5588569431093244,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000497493389592554,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.14151546210050583,
|
|
"num_tokens": 12957236.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.261232042312622,
|
|
"epoch": 0.5592938914620292,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004974887490719627,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.13431976288557052,
|
|
"num_tokens": 12967497.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.239714336395264,
|
|
"epoch": 0.5597308398147339,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004974841042839207,
|
|
"loss": 6.0611,
|
|
"mean_token_accuracy": 0.14347777962684632,
|
|
"num_tokens": 12977467.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.184810781478882,
|
|
"epoch": 0.5601677881674386,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000497479455228517,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.1409076377749443,
|
|
"num_tokens": 12987867.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.262886953353882,
|
|
"epoch": 0.5606047365201433,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004974748019058407,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.13358882069587708,
|
|
"num_tokens": 12998081.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.270763158798218,
|
|
"epoch": 0.561041684872848,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004974701443159812,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.1384132459759712,
|
|
"num_tokens": 13008047.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.324219751358032,
|
|
"epoch": 0.5614786332255527,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004974654824590277,
|
|
"loss": 6.106,
|
|
"mean_token_accuracy": 0.13544400185346603,
|
|
"num_tokens": 13018048.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.262833309173584,
|
|
"epoch": 0.5619155815782575,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004974608163350697,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.1436422161757946,
|
|
"num_tokens": 13028156.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.209911346435547,
|
|
"epoch": 0.5623525299309622,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004974561459441967,
|
|
"loss": 6.1046,
|
|
"mean_token_accuracy": 0.13928409665822983,
|
|
"num_tokens": 13038191.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.233520221710205,
|
|
"epoch": 0.5627894782836669,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004974514712864981,
|
|
"loss": 6.1073,
|
|
"mean_token_accuracy": 0.138884087651968,
|
|
"num_tokens": 13049085.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.2541821002960205,
|
|
"epoch": 0.5632264266363716,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004974467923620639,
|
|
"loss": 6.1268,
|
|
"mean_token_accuracy": 0.1373557224869728,
|
|
"num_tokens": 13060010.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.349029874801635,
|
|
"epoch": 0.5636633749890763,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004974421091709836,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.1365789458155632,
|
|
"num_tokens": 13069768.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.315038061141967,
|
|
"epoch": 0.564100323341781,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004974374217133471,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.135160880535841,
|
|
"num_tokens": 13079842.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.214017534255982,
|
|
"epoch": 0.5645372716944858,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004974327299892443,
|
|
"loss": 6.0578,
|
|
"mean_token_accuracy": 0.14208607152104377,
|
|
"num_tokens": 13089235.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.231755542755127,
|
|
"epoch": 0.5649742200471904,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004974280339987651,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.13741404563188553,
|
|
"num_tokens": 13098364.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.2427702903747555,
|
|
"epoch": 0.5654111683998951,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004974233337419997,
|
|
"loss": 6.2171,
|
|
"mean_token_accuracy": 0.12881077006459235,
|
|
"num_tokens": 13108876.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.329076623916626,
|
|
"epoch": 0.5658481167525998,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004974186292190383,
|
|
"loss": 6.2221,
|
|
"mean_token_accuracy": 0.13388051688671113,
|
|
"num_tokens": 13119591.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.32397837638855,
|
|
"epoch": 0.5662850651053045,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000497413920429971,
|
|
"loss": 6.1107,
|
|
"mean_token_accuracy": 0.14448174014687537,
|
|
"num_tokens": 13129796.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.2648690700531,
|
|
"epoch": 0.5667220134580092,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004974092073748882,
|
|
"loss": 6.0587,
|
|
"mean_token_accuracy": 0.142123019695282,
|
|
"num_tokens": 13139302.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.228122711181641,
|
|
"epoch": 0.567158961810714,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004974044900538802,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.13770891204476357,
|
|
"num_tokens": 13148983.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.3073498725891115,
|
|
"epoch": 0.5675959101634187,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004973997684670375,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.13494180366396905,
|
|
"num_tokens": 13159016.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.2961560726165775,
|
|
"epoch": 0.5680328585161234,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004973950426144508,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.13156452551484107,
|
|
"num_tokens": 13169705.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.255215787887574,
|
|
"epoch": 0.5684698068688281,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004973903124962106,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.13032817989587783,
|
|
"num_tokens": 13181372.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.190559673309326,
|
|
"epoch": 0.5689067552215328,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004973855781124077,
|
|
"loss": 6.171,
|
|
"mean_token_accuracy": 0.13174699544906615,
|
|
"num_tokens": 13192581.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.302378129959107,
|
|
"epoch": 0.5693437035742375,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004973808394631329,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.135031296312809,
|
|
"num_tokens": 13203269.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.276038312911988,
|
|
"epoch": 0.5697806519269423,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000497376096548477,
|
|
"loss": 6.083,
|
|
"mean_token_accuracy": 0.13695611134171487,
|
|
"num_tokens": 13213183.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.272439908981323,
|
|
"epoch": 0.570217600279647,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004973713493685311,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.13435291722416878,
|
|
"num_tokens": 13223196.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.315483617782593,
|
|
"epoch": 0.5706545486323517,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004973665979233861,
|
|
"loss": 6.0792,
|
|
"mean_token_accuracy": 0.14457561075687408,
|
|
"num_tokens": 13233915.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.278499937057495,
|
|
"epoch": 0.5710914969850563,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004973618422131334,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.13833219408988953,
|
|
"num_tokens": 13245108.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.187056827545166,
|
|
"epoch": 0.571528445337761,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000497357082237864,
|
|
"loss": 6.1186,
|
|
"mean_token_accuracy": 0.13869462460279464,
|
|
"num_tokens": 13255508.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.274870586395264,
|
|
"epoch": 0.5719653936904658,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004973523179976692,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.14257874116301536,
|
|
"num_tokens": 13265118.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.288551330566406,
|
|
"epoch": 0.5724023420431705,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004973475494926404,
|
|
"loss": 6.0539,
|
|
"mean_token_accuracy": 0.14106326252222062,
|
|
"num_tokens": 13275947.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.276229333877564,
|
|
"epoch": 0.5728392903958752,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004973427767228692,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.14221703708171846,
|
|
"num_tokens": 13284662.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.192042350769043,
|
|
"epoch": 0.5732762387485799,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000497337999688447,
|
|
"loss": 6.1372,
|
|
"mean_token_accuracy": 0.1390274167060852,
|
|
"num_tokens": 13295627.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.261907720565796,
|
|
"epoch": 0.5737131871012846,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004973332183894653,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.1444385051727295,
|
|
"num_tokens": 13305205.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.24415340423584,
|
|
"epoch": 0.5741501354539893,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004973284328260162,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.13924380391836166,
|
|
"num_tokens": 13315464.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.187749910354614,
|
|
"epoch": 0.5745870838066941,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004973236429981912,
|
|
"loss": 5.9966,
|
|
"mean_token_accuracy": 0.1391263373196125,
|
|
"num_tokens": 13325468.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.241669321060181,
|
|
"epoch": 0.5750240321593988,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004973188489060821,
|
|
"loss": 6.1219,
|
|
"mean_token_accuracy": 0.1372533343732357,
|
|
"num_tokens": 13334719.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.264699459075928,
|
|
"epoch": 0.5754609805121035,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004973140505497812,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.13733603060245514,
|
|
"num_tokens": 13344545.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.309505987167358,
|
|
"epoch": 0.5758979288648082,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004973092479293802,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.13204444646835328,
|
|
"num_tokens": 13355212.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.189426136016846,
|
|
"epoch": 0.5763348772175129,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004973044410449713,
|
|
"loss": 6.0509,
|
|
"mean_token_accuracy": 0.1430459849536419,
|
|
"num_tokens": 13364869.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.240922355651856,
|
|
"epoch": 0.5767718255702176,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004972996298966468,
|
|
"loss": 6.0806,
|
|
"mean_token_accuracy": 0.14123327955603598,
|
|
"num_tokens": 13376511.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.2815958023071286,
|
|
"epoch": 0.5772087739229224,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000497294814484499,
|
|
"loss": 6.1152,
|
|
"mean_token_accuracy": 0.14026200994849206,
|
|
"num_tokens": 13385470.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.271773958206177,
|
|
"epoch": 0.577645722275627,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00049728999480862,
|
|
"loss": 6.17,
|
|
"mean_token_accuracy": 0.14066533967852593,
|
|
"num_tokens": 13395328.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.319705438613892,
|
|
"epoch": 0.5780826706283317,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004972851708691025,
|
|
"loss": 6.0677,
|
|
"mean_token_accuracy": 0.1438952326774597,
|
|
"num_tokens": 13405319.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.200738954544067,
|
|
"epoch": 0.5785196189810364,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004972803426660389,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.13934995457530022,
|
|
"num_tokens": 13416119.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.258353757858276,
|
|
"epoch": 0.5789565673337411,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004972755101995219,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.1352447398006916,
|
|
"num_tokens": 13425824.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.244670963287353,
|
|
"epoch": 0.5793935156864458,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004972706734696442,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.14621324539184571,
|
|
"num_tokens": 13435506.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.228378963470459,
|
|
"epoch": 0.5798304640391506,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004972658324764984,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.14824110716581346,
|
|
"num_tokens": 13445313.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.13565616607666,
|
|
"epoch": 0.5802674123918553,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004972609872201775,
|
|
"loss": 5.9809,
|
|
"mean_token_accuracy": 0.14731499776244164,
|
|
"num_tokens": 13455312.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.213436412811279,
|
|
"epoch": 0.58070436074456,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004972561377007744,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.13471954986453055,
|
|
"num_tokens": 13465721.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.3089337825775145,
|
|
"epoch": 0.5811413090972647,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004972512839183822,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.14083665534853934,
|
|
"num_tokens": 13477185.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.232909917831421,
|
|
"epoch": 0.5815782574499694,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004972464258730939,
|
|
"loss": 6.0548,
|
|
"mean_token_accuracy": 0.15199510008096695,
|
|
"num_tokens": 13487846.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.185512924194336,
|
|
"epoch": 0.5820152058026741,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004972415635650027,
|
|
"loss": 6.1292,
|
|
"mean_token_accuracy": 0.14809978529810905,
|
|
"num_tokens": 13498175.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.373633527755738,
|
|
"epoch": 0.5824521541553789,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004972366969942017,
|
|
"loss": 6.0972,
|
|
"mean_token_accuracy": 0.13438104838132858,
|
|
"num_tokens": 13506864.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.240647315979004,
|
|
"epoch": 0.5828891025080836,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004972318261607845,
|
|
"loss": 6.0806,
|
|
"mean_token_accuracy": 0.14570387601852416,
|
|
"num_tokens": 13516208.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.246371078491211,
|
|
"epoch": 0.5833260508607883,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004972269510648444,
|
|
"loss": 6.1324,
|
|
"mean_token_accuracy": 0.13572923019528388,
|
|
"num_tokens": 13526902.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.275639009475708,
|
|
"epoch": 0.583762999213493,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000497222071706475,
|
|
"loss": 6.0575,
|
|
"mean_token_accuracy": 0.14732615202665328,
|
|
"num_tokens": 13537001.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.204616689682007,
|
|
"epoch": 0.5841999475661976,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004972171880857698,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.14583269581198693,
|
|
"num_tokens": 13546971.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.217172479629516,
|
|
"epoch": 0.5846368959189023,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004972123002028226,
|
|
"loss": 6.0256,
|
|
"mean_token_accuracy": 0.14713723808526993,
|
|
"num_tokens": 13557202.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.122836589813232,
|
|
"epoch": 0.5850738442716071,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004972074080577269,
|
|
"loss": 6.0035,
|
|
"mean_token_accuracy": 0.15193717703223228,
|
|
"num_tokens": 13567291.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.241865825653076,
|
|
"epoch": 0.5855107926243118,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004972025116505767,
|
|
"loss": 6.0977,
|
|
"mean_token_accuracy": 0.1464373327791691,
|
|
"num_tokens": 13576864.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.275596284866333,
|
|
"epoch": 0.5859477409770165,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004971976109814658,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.14644457399845123,
|
|
"num_tokens": 13586728.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.211604118347168,
|
|
"epoch": 0.5863846893297212,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004971927060504885,
|
|
"loss": 6.092,
|
|
"mean_token_accuracy": 0.1458321511745453,
|
|
"num_tokens": 13596875.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.285997438430786,
|
|
"epoch": 0.5868216376824259,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004971877968577386,
|
|
"loss": 6.1062,
|
|
"mean_token_accuracy": 0.13368350118398667,
|
|
"num_tokens": 13606483.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.256731033325195,
|
|
"epoch": 0.5872585860351307,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004971828834033102,
|
|
"loss": 6.145,
|
|
"mean_token_accuracy": 0.13932919576764108,
|
|
"num_tokens": 13616780.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.237018632888794,
|
|
"epoch": 0.5876955343878354,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004971779656872978,
|
|
"loss": 6.1256,
|
|
"mean_token_accuracy": 0.13926877230405807,
|
|
"num_tokens": 13626418.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.289210176467895,
|
|
"epoch": 0.5881324827405401,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004971730437097955,
|
|
"loss": 6.1592,
|
|
"mean_token_accuracy": 0.13757795691490174,
|
|
"num_tokens": 13636956.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.232604026794434,
|
|
"epoch": 0.5885694310932448,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000497168117470898,
|
|
"loss": 6.0869,
|
|
"mean_token_accuracy": 0.1386633425951004,
|
|
"num_tokens": 13647458.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.206624937057495,
|
|
"epoch": 0.5890063794459495,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004971631869706995,
|
|
"loss": 6.035,
|
|
"mean_token_accuracy": 0.14804055988788606,
|
|
"num_tokens": 13657655.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.239219284057617,
|
|
"epoch": 0.5894433277986542,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004971582522092946,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.13588550686836243,
|
|
"num_tokens": 13668472.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.236002111434937,
|
|
"epoch": 0.589880276151359,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000497153313186778,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.14495814442634583,
|
|
"num_tokens": 13677319.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.204773950576782,
|
|
"epoch": 0.5903172245040637,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004971483699032445,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.14527754485607147,
|
|
"num_tokens": 13688037.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.345049619674683,
|
|
"epoch": 0.5907541728567683,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004971434223587888,
|
|
"loss": 6.1769,
|
|
"mean_token_accuracy": 0.1332503601908684,
|
|
"num_tokens": 13698441.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.232329988479615,
|
|
"epoch": 0.591191121209473,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000497138470553506,
|
|
"loss": 6.0971,
|
|
"mean_token_accuracy": 0.1420059993863106,
|
|
"num_tokens": 13708140.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.2557373046875,
|
|
"epoch": 0.5916280695621777,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004971335144874909,
|
|
"loss": 6.0795,
|
|
"mean_token_accuracy": 0.14316331669688226,
|
|
"num_tokens": 13718069.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.228231620788574,
|
|
"epoch": 0.5920650179148824,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004971285541608385,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.15345999151468276,
|
|
"num_tokens": 13727932.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.295587253570557,
|
|
"epoch": 0.5925019662675872,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004971235895736441,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.13220032975077628,
|
|
"num_tokens": 13738239.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.2889244079589846,
|
|
"epoch": 0.5929389146202919,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004971186207260029,
|
|
"loss": 6.0799,
|
|
"mean_token_accuracy": 0.1396336004137993,
|
|
"num_tokens": 13748622.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.160888195037842,
|
|
"epoch": 0.5933758629729966,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00049711364761801,
|
|
"loss": 6.0108,
|
|
"mean_token_accuracy": 0.14156231358647348,
|
|
"num_tokens": 13759221.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.237045097351074,
|
|
"epoch": 0.5938128113257013,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000497108670249761,
|
|
"loss": 6.0398,
|
|
"mean_token_accuracy": 0.13876911327242852,
|
|
"num_tokens": 13768343.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.276476001739502,
|
|
"epoch": 0.594249759678406,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004971036886213515,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.14211647883057593,
|
|
"num_tokens": 13778225.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.224419498443604,
|
|
"epoch": 0.5946867080311107,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004970987027328767,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.13437844887375833,
|
|
"num_tokens": 13788633.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.241243839263916,
|
|
"epoch": 0.5951236563838155,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004970937125844325,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.14751050025224685,
|
|
"num_tokens": 13798172.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.139668369293213,
|
|
"epoch": 0.5955606047365202,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004970887181761144,
|
|
"loss": 6.0118,
|
|
"mean_token_accuracy": 0.15298185646533966,
|
|
"num_tokens": 13807284.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.237003898620605,
|
|
"epoch": 0.5959975530892249,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004970837195080184,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.13770748674869537,
|
|
"num_tokens": 13816807.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.288899850845337,
|
|
"epoch": 0.5964345014419296,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004970787165802403,
|
|
"loss": 6.037,
|
|
"mean_token_accuracy": 0.1411267563700676,
|
|
"num_tokens": 13827635.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.234393358230591,
|
|
"epoch": 0.5968714497946342,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000497073709392876,
|
|
"loss": 6.1074,
|
|
"mean_token_accuracy": 0.13737359121441842,
|
|
"num_tokens": 13838060.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.285126733779907,
|
|
"epoch": 0.5973083981473389,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004970686979460216,
|
|
"loss": 6.1196,
|
|
"mean_token_accuracy": 0.13926485776901246,
|
|
"num_tokens": 13848669.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.260535764694214,
|
|
"epoch": 0.5977453465000437,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004970636822397733,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.14194415062665938,
|
|
"num_tokens": 13857949.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.241445779800415,
|
|
"epoch": 0.5981822948527484,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004970586622742272,
|
|
"loss": 6.0764,
|
|
"mean_token_accuracy": 0.14263241216540337,
|
|
"num_tokens": 13867726.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.324937200546264,
|
|
"epoch": 0.5986192432054531,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004970536380494795,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.13447364792227745,
|
|
"num_tokens": 13878072.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.193201541900635,
|
|
"epoch": 0.5990561915581578,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004970486095656268,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.14746544361114503,
|
|
"num_tokens": 13887771.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.231291103363037,
|
|
"epoch": 0.5994931399108625,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004970435768227652,
|
|
"loss": 6.0496,
|
|
"mean_token_accuracy": 0.14115117266774177,
|
|
"num_tokens": 13897867.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.28660569190979,
|
|
"epoch": 0.5999300882635672,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004970385398209916,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.14163656905293465,
|
|
"num_tokens": 13909171.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.300090360641479,
|
|
"epoch": 0.600367036616272,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004970334985604024,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.1396082989871502,
|
|
"num_tokens": 13920374.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.193111419677734,
|
|
"epoch": 0.6008039849689767,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004970284530410945,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.13556758910417557,
|
|
"num_tokens": 13930150.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.279803276062012,
|
|
"epoch": 0.6012409333216814,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004970234032631644,
|
|
"loss": 6.0689,
|
|
"mean_token_accuracy": 0.14032774344086646,
|
|
"num_tokens": 13940553.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.191017389297485,
|
|
"epoch": 0.6016778816743861,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004970183492267091,
|
|
"loss": 6.1629,
|
|
"mean_token_accuracy": 0.14311335012316703,
|
|
"num_tokens": 13951086.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.236486196517944,
|
|
"epoch": 0.6021148300270908,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004970132909318254,
|
|
"loss": 6.0885,
|
|
"mean_token_accuracy": 0.13655531257390977,
|
|
"num_tokens": 13960684.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.116621685028076,
|
|
"epoch": 0.6025517783797955,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004970082283786107,
|
|
"loss": 5.9097,
|
|
"mean_token_accuracy": 0.16360336542129517,
|
|
"num_tokens": 13971409.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.257471227645874,
|
|
"epoch": 0.6029887267325003,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004970031615671617,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.14076051041483878,
|
|
"num_tokens": 13981185.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.241898155212402,
|
|
"epoch": 0.603425675085205,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004969980904975758,
|
|
"loss": 6.1141,
|
|
"mean_token_accuracy": 0.1358635351061821,
|
|
"num_tokens": 13991670.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.14874758720398,
|
|
"epoch": 0.6038626234379096,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004969930151699501,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.14061281681060792,
|
|
"num_tokens": 14002343.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.25538477897644,
|
|
"epoch": 0.6042995717906143,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000496987935584382,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.13818174377083778,
|
|
"num_tokens": 14013373.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.32241735458374,
|
|
"epoch": 0.604736520143319,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004969828517409693,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.14847719222307204,
|
|
"num_tokens": 14023233.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.1616730213165285,
|
|
"epoch": 0.6051734684960238,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000496977763639809,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.1400049977004528,
|
|
"num_tokens": 14033054.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.221465730667115,
|
|
"epoch": 0.6056104168487285,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004969726712809988,
|
|
"loss": 6.0258,
|
|
"mean_token_accuracy": 0.1430351883172989,
|
|
"num_tokens": 14042039.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.287037944793701,
|
|
"epoch": 0.6060473652014332,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004969675746646364,
|
|
"loss": 6.1629,
|
|
"mean_token_accuracy": 0.13481699004769326,
|
|
"num_tokens": 14051957.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.261262130737305,
|
|
"epoch": 0.6064843135541379,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004969624737908197,
|
|
"loss": 6.0563,
|
|
"mean_token_accuracy": 0.1410438358783722,
|
|
"num_tokens": 14062438.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.217139196395874,
|
|
"epoch": 0.6069212619068426,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004969573686596464,
|
|
"loss": 6.0822,
|
|
"mean_token_accuracy": 0.13399507775902747,
|
|
"num_tokens": 14073196.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.263551664352417,
|
|
"epoch": 0.6073582102595473,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004969522592712146,
|
|
"loss": 6.0711,
|
|
"mean_token_accuracy": 0.14046932458877565,
|
|
"num_tokens": 14083462.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.2073393821716305,
|
|
"epoch": 0.6077951586122521,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004969471456256221,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.1367241285741329,
|
|
"num_tokens": 14094194.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.240724849700928,
|
|
"epoch": 0.6082321069649568,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000496942027722967,
|
|
"loss": 6.0842,
|
|
"mean_token_accuracy": 0.14098508134484292,
|
|
"num_tokens": 14104553.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.284235906600952,
|
|
"epoch": 0.6086690553176615,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004969369055633476,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.13823190033435823,
|
|
"num_tokens": 14114140.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.169156074523926,
|
|
"epoch": 0.6091060036703662,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000496931779146862,
|
|
"loss": 6.134,
|
|
"mean_token_accuracy": 0.13523512482643127,
|
|
"num_tokens": 14124723.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.283691024780273,
|
|
"epoch": 0.6095429520230708,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004969266484736085,
|
|
"loss": 6.0109,
|
|
"mean_token_accuracy": 0.14279836937785148,
|
|
"num_tokens": 14134030.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.196794176101685,
|
|
"epoch": 0.6099799003757755,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004969215135436858,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.14249944314360619,
|
|
"num_tokens": 14144691.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.203350162506103,
|
|
"epoch": 0.6104168487284803,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004969163743571921,
|
|
"loss": 6.162,
|
|
"mean_token_accuracy": 0.13822323605418205,
|
|
"num_tokens": 14155114.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.333395957946777,
|
|
"epoch": 0.610853797081185,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000496911230914226,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.13629033267498017,
|
|
"num_tokens": 14166097.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.242578315734863,
|
|
"epoch": 0.6112907454338897,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004969060832148862,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.13742341250181198,
|
|
"num_tokens": 14176538.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.110963773727417,
|
|
"epoch": 0.6117276937865944,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004969009312592715,
|
|
"loss": 6.0637,
|
|
"mean_token_accuracy": 0.1376984901726246,
|
|
"num_tokens": 14187912.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.152584171295166,
|
|
"epoch": 0.6121646421392991,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004968957750474806,
|
|
"loss": 5.9536,
|
|
"mean_token_accuracy": 0.15419106930494308,
|
|
"num_tokens": 14198446.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.299173974990845,
|
|
"epoch": 0.6126015904920038,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004968906145796126,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.13943691700696945,
|
|
"num_tokens": 14207723.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.25934739112854,
|
|
"epoch": 0.6130385388447086,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004968854498557662,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.1388497233390808,
|
|
"num_tokens": 14217590.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.222770690917969,
|
|
"epoch": 0.6134754871974133,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004968802808760407,
|
|
"loss": 6.1184,
|
|
"mean_token_accuracy": 0.1370713785290718,
|
|
"num_tokens": 14226629.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.199009275436401,
|
|
"epoch": 0.613912435550118,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004968751076405351,
|
|
"loss": 6.1711,
|
|
"mean_token_accuracy": 0.13404033258557319,
|
|
"num_tokens": 14235782.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.162545156478882,
|
|
"epoch": 0.6143493839028227,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004968699301493488,
|
|
"loss": 6.043,
|
|
"mean_token_accuracy": 0.14680892378091812,
|
|
"num_tokens": 14246687.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.290499877929688,
|
|
"epoch": 0.6147863322555274,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004968647484025808,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.1449754148721695,
|
|
"num_tokens": 14255961.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.288722991943359,
|
|
"epoch": 0.6152232806082321,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004968595624003307,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.1403207339346409,
|
|
"num_tokens": 14266024.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.227539491653443,
|
|
"epoch": 0.6156602289609369,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.000496854372142698,
|
|
"loss": 6.1157,
|
|
"mean_token_accuracy": 0.1384843461215496,
|
|
"num_tokens": 14276590.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.177028369903565,
|
|
"epoch": 0.6160971773136416,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004968491776297821,
|
|
"loss": 6.123,
|
|
"mean_token_accuracy": 0.1399732105433941,
|
|
"num_tokens": 14285992.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.218402957916259,
|
|
"epoch": 0.6165341256663462,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004968439788616829,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.14302821904420854,
|
|
"num_tokens": 14295843.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.2850103855133055,
|
|
"epoch": 0.6169710740190509,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004968387758384999,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.14192734211683272,
|
|
"num_tokens": 14305643.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.251075029373169,
|
|
"epoch": 0.6174080223717556,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004968335685603328,
|
|
"loss": 6.0443,
|
|
"mean_token_accuracy": 0.14319950193166733,
|
|
"num_tokens": 14315907.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.178477239608765,
|
|
"epoch": 0.6178449707244603,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004968283570272817,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.13525563031435012,
|
|
"num_tokens": 14325893.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.282196474075318,
|
|
"epoch": 0.6182819190771651,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004968231412394464,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.1343388892710209,
|
|
"num_tokens": 14337510.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.293983840942383,
|
|
"epoch": 0.6187188674298698,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004968179211969272,
|
|
"loss": 6.0476,
|
|
"mean_token_accuracy": 0.14687205329537392,
|
|
"num_tokens": 14346373.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.13792314529419,
|
|
"epoch": 0.6191558157825745,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004968126968998239,
|
|
"loss": 5.9217,
|
|
"mean_token_accuracy": 0.16086165681481362,
|
|
"num_tokens": 14356303.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.207563972473144,
|
|
"epoch": 0.6195927641352792,
|
|
"grad_norm": 7.0,
|
|
"learning_rate": 0.0004968074683482369,
|
|
"loss": 6.0758,
|
|
"mean_token_accuracy": 0.14417827501893044,
|
|
"num_tokens": 14366171.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.286942481994629,
|
|
"epoch": 0.6200297124879839,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004968022355422663,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.1373531512916088,
|
|
"num_tokens": 14376133.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.285527038574219,
|
|
"epoch": 0.6204666608406886,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004967969984820128,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.13749169334769248,
|
|
"num_tokens": 14385670.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.261067867279053,
|
|
"epoch": 0.6209036091933934,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004967917571675765,
|
|
"loss": 6.061,
|
|
"mean_token_accuracy": 0.14238285794854164,
|
|
"num_tokens": 14396002.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.194595718383789,
|
|
"epoch": 0.6213405575460981,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004967865115990582,
|
|
"loss": 6.1679,
|
|
"mean_token_accuracy": 0.135838333517313,
|
|
"num_tokens": 14406718.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.288463401794433,
|
|
"epoch": 0.6217775058988028,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004967812617765583,
|
|
"loss": 6.0948,
|
|
"mean_token_accuracy": 0.13747066184878348,
|
|
"num_tokens": 14417027.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.223663854598999,
|
|
"epoch": 0.6222144542515075,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004967760077001775,
|
|
"loss": 6.0515,
|
|
"mean_token_accuracy": 0.14532688781619071,
|
|
"num_tokens": 14426885.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.199916648864746,
|
|
"epoch": 0.6226514026042121,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004967707493700169,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.14331899285316468,
|
|
"num_tokens": 14437743.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.162434911727905,
|
|
"epoch": 0.623088350956917,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004967654867861769,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.14364799186587335,
|
|
"num_tokens": 14448808.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.2316086769104,
|
|
"epoch": 0.6235252993096216,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004967602199487588,
|
|
"loss": 6.0986,
|
|
"mean_token_accuracy": 0.14064462780952453,
|
|
"num_tokens": 14458560.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.288028764724731,
|
|
"epoch": 0.6239622476623263,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004967549488578635,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.13784303665161132,
|
|
"num_tokens": 14469375.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.292950677871704,
|
|
"epoch": 0.624399196015031,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000496749673513592,
|
|
"loss": 6.084,
|
|
"mean_token_accuracy": 0.13916077464818954,
|
|
"num_tokens": 14478444.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.194452714920044,
|
|
"epoch": 0.6248361443677357,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004967443939160456,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.153594534099102,
|
|
"num_tokens": 14487776.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.247198104858398,
|
|
"epoch": 0.6252730927204404,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004967391100653255,
|
|
"loss": 6.1037,
|
|
"mean_token_accuracy": 0.14412544369697572,
|
|
"num_tokens": 14497879.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.211316156387329,
|
|
"epoch": 0.6257100410731452,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004967338219615331,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.14063015207648277,
|
|
"num_tokens": 14507753.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.241280126571655,
|
|
"epoch": 0.6261469894258499,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004967285296047699,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.14772187173366547,
|
|
"num_tokens": 14517086.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.20732889175415,
|
|
"epoch": 0.6265839377785546,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004967232329951372,
|
|
"loss": 6.0801,
|
|
"mean_token_accuracy": 0.1369892843067646,
|
|
"num_tokens": 14527097.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.245126581192016,
|
|
"epoch": 0.6270208861312593,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004967179321327367,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.14085085242986678,
|
|
"num_tokens": 14537924.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.247621250152588,
|
|
"epoch": 0.627457834483964,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004967126270176702,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.13855889439582825,
|
|
"num_tokens": 14547542.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.145660495758056,
|
|
"epoch": 0.6278947828366687,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004967073176500392,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.1502846211194992,
|
|
"num_tokens": 14557150.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.217853116989136,
|
|
"epoch": 0.6283317311893735,
|
|
"grad_norm": 5.75,
|
|
"learning_rate": 0.0004967020040299458,
|
|
"loss": 6.0505,
|
|
"mean_token_accuracy": 0.14292264431715013,
|
|
"num_tokens": 14567242.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.220586633682251,
|
|
"epoch": 0.6287686795420782,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004966966861574917,
|
|
"loss": 6.0302,
|
|
"mean_token_accuracy": 0.14270174130797386,
|
|
"num_tokens": 14576631.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.252045631408691,
|
|
"epoch": 0.6292056278947828,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.000496691364032779,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.1352137267589569,
|
|
"num_tokens": 14587731.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.341271495819091,
|
|
"epoch": 0.6296425762474875,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004966860376559097,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.13765100985765458,
|
|
"num_tokens": 14598136.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.183723735809326,
|
|
"epoch": 0.6300795246001922,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004966807070269862,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.1392249695956707,
|
|
"num_tokens": 14607243.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.167708015441894,
|
|
"epoch": 0.6305164729528969,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004966753721461105,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.1419666089117527,
|
|
"num_tokens": 14617094.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.25998330116272,
|
|
"epoch": 0.6309534213056017,
|
|
"grad_norm": 3.890625,
|
|
"learning_rate": 0.0004966700330133849,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.1416136458516121,
|
|
"num_tokens": 14626486.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.10648889541626,
|
|
"epoch": 0.6313903696583064,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004966646896289121,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.15503031462430955,
|
|
"num_tokens": 14637170.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.209821176528931,
|
|
"epoch": 0.6318273180110111,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004966593419927944,
|
|
"loss": 6.0457,
|
|
"mean_token_accuracy": 0.1434933751821518,
|
|
"num_tokens": 14646396.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.252063035964966,
|
|
"epoch": 0.6322642663637158,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004966539901051343,
|
|
"loss": 6.095,
|
|
"mean_token_accuracy": 0.1328526608645916,
|
|
"num_tokens": 14656097.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.218412637710571,
|
|
"epoch": 0.6327012147164205,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004966486339660345,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.1426958732306957,
|
|
"num_tokens": 14667124.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.180486488342285,
|
|
"epoch": 0.6331381630691252,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004966432735755978,
|
|
"loss": 6.1506,
|
|
"mean_token_accuracy": 0.14178672879934312,
|
|
"num_tokens": 14677427.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.19655032157898,
|
|
"epoch": 0.63357511142183,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000496637908933927,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.1448795348405838,
|
|
"num_tokens": 14686429.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.284691190719604,
|
|
"epoch": 0.6340120597745347,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000496632540041125,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.14665302485227585,
|
|
"num_tokens": 14696264.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.2796959400177,
|
|
"epoch": 0.6344490081272394,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004966271668972946,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.14009574726223945,
|
|
"num_tokens": 14705935.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.191766738891602,
|
|
"epoch": 0.6348859564799441,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004966217895025391,
|
|
"loss": 6.0473,
|
|
"mean_token_accuracy": 0.14082057923078536,
|
|
"num_tokens": 14715978.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.209609460830689,
|
|
"epoch": 0.6353229048326487,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004966164078569616,
|
|
"loss": 6.0643,
|
|
"mean_token_accuracy": 0.13889703378081322,
|
|
"num_tokens": 14726170.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.220421314239502,
|
|
"epoch": 0.6357598531853534,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004966110219606652,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.14052743092179298,
|
|
"num_tokens": 14735775.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.175203943252564,
|
|
"epoch": 0.6361968015380582,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004966056318137532,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.1373811826109886,
|
|
"num_tokens": 14746143.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.199851703643799,
|
|
"epoch": 0.6366337498907629,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004966002374163293,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.14739727973937988,
|
|
"num_tokens": 14756707.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.216392993927002,
|
|
"epoch": 0.6370706982434676,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004965948387684964,
|
|
"loss": 6.0948,
|
|
"mean_token_accuracy": 0.14192008525133132,
|
|
"num_tokens": 14765778.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.263886833190918,
|
|
"epoch": 0.6375076465961723,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004965894358703587,
|
|
"loss": 6.093,
|
|
"mean_token_accuracy": 0.13505014330148696,
|
|
"num_tokens": 14775264.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.247747802734375,
|
|
"epoch": 0.637944594948877,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004965840287220193,
|
|
"loss": 6.0689,
|
|
"mean_token_accuracy": 0.1382345050573349,
|
|
"num_tokens": 14785754.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.203045654296875,
|
|
"epoch": 0.6383815433015817,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004965786173235821,
|
|
"loss": 6.1191,
|
|
"mean_token_accuracy": 0.13925366178154946,
|
|
"num_tokens": 14795936.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.276138544082642,
|
|
"epoch": 0.6388184916542865,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004965732016751511,
|
|
"loss": 6.0951,
|
|
"mean_token_accuracy": 0.14140693917870523,
|
|
"num_tokens": 14805721.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.292239046096801,
|
|
"epoch": 0.6392554400069912,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004965677817768299,
|
|
"loss": 6.1287,
|
|
"mean_token_accuracy": 0.13380056470632554,
|
|
"num_tokens": 14816610.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.239180994033814,
|
|
"epoch": 0.6396923883596959,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004965623576287225,
|
|
"loss": 6.0956,
|
|
"mean_token_accuracy": 0.1365938127040863,
|
|
"num_tokens": 14826126.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.196110773086548,
|
|
"epoch": 0.6401293367124006,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004965569292309331,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.14939529076218605,
|
|
"num_tokens": 14835657.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.169877243041992,
|
|
"epoch": 0.6405662850651053,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004965514965835655,
|
|
"loss": 6.0636,
|
|
"mean_token_accuracy": 0.1412982389330864,
|
|
"num_tokens": 14845430.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.191928052902222,
|
|
"epoch": 0.6410032334178101,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004965460596867243,
|
|
"loss": 6.0251,
|
|
"mean_token_accuracy": 0.1474901869893074,
|
|
"num_tokens": 14855459.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.267540836334229,
|
|
"epoch": 0.6414401817705148,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004965406185405135,
|
|
"loss": 6.0863,
|
|
"mean_token_accuracy": 0.14111222848296165,
|
|
"num_tokens": 14865375.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.233385133743286,
|
|
"epoch": 0.6418771301232195,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004965351731450376,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.14531854838132857,
|
|
"num_tokens": 14875211.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.214669418334961,
|
|
"epoch": 0.6423140784759241,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000496529723500401,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.13480584993958472,
|
|
"num_tokens": 14886221.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.259183168411255,
|
|
"epoch": 0.6427510268286288,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004965242696067081,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.14169811755418776,
|
|
"num_tokens": 14896002.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.207713556289673,
|
|
"epoch": 0.6431879751813335,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004965188114640637,
|
|
"loss": 6.1089,
|
|
"mean_token_accuracy": 0.1374245673418045,
|
|
"num_tokens": 14906311.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.266039562225342,
|
|
"epoch": 0.6436249235340383,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004965133490725725,
|
|
"loss": 6.091,
|
|
"mean_token_accuracy": 0.14037528187036513,
|
|
"num_tokens": 14915890.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.244173765182495,
|
|
"epoch": 0.644061871886743,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004965078824323391,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.14121145233511925,
|
|
"num_tokens": 14925891.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.1994599342346195,
|
|
"epoch": 0.6444988202394477,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004965024115434685,
|
|
"loss": 6.1013,
|
|
"mean_token_accuracy": 0.13864176496863365,
|
|
"num_tokens": 14937272.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.257472133636474,
|
|
"epoch": 0.6449357685921524,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004964969364060656,
|
|
"loss": 6.1105,
|
|
"mean_token_accuracy": 0.13872194141149521,
|
|
"num_tokens": 14948135.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.358830785751342,
|
|
"epoch": 0.6453727169448571,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004964914570202353,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.13665004670619965,
|
|
"num_tokens": 14959254.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.236004257202149,
|
|
"epoch": 0.6458096652975618,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004964859733860829,
|
|
"loss": 6.074,
|
|
"mean_token_accuracy": 0.1428222142159939,
|
|
"num_tokens": 14969313.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.188684606552124,
|
|
"epoch": 0.6462466136502666,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004964804855037134,
|
|
"loss": 6.072,
|
|
"mean_token_accuracy": 0.14139073044061662,
|
|
"num_tokens": 14978963.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.290366458892822,
|
|
"epoch": 0.6466835620029713,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004964749933732322,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.14476230666041373,
|
|
"num_tokens": 14989355.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.203551769256592,
|
|
"epoch": 0.647120510355676,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004964694969947445,
|
|
"loss": 6.0458,
|
|
"mean_token_accuracy": 0.14362569898366928,
|
|
"num_tokens": 14998995.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.224933671951294,
|
|
"epoch": 0.6475574587083807,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004964639963683558,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.13989042565226556,
|
|
"num_tokens": 15008762.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.311505746841431,
|
|
"epoch": 0.6479944070610854,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004964584914941716,
|
|
"loss": 6.0972,
|
|
"mean_token_accuracy": 0.13879491463303567,
|
|
"num_tokens": 15020062.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.3743222713470455,
|
|
"epoch": 0.64843135541379,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004964529823722975,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.12883895188570021,
|
|
"num_tokens": 15030440.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.287896394729614,
|
|
"epoch": 0.6488683037664948,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004964474690028393,
|
|
"loss": 6.0729,
|
|
"mean_token_accuracy": 0.14202678576111794,
|
|
"num_tokens": 15041709.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.2483141899108885,
|
|
"epoch": 0.6493052521191995,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004964419513859025,
|
|
"loss": 6.1909,
|
|
"mean_token_accuracy": 0.13687760010361671,
|
|
"num_tokens": 15052277.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.188128232955933,
|
|
"epoch": 0.6497422004719042,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000496436429521593,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.14018882662057877,
|
|
"num_tokens": 15061870.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.123696947097779,
|
|
"epoch": 0.6501791488246089,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004964309034100168,
|
|
"loss": 5.944,
|
|
"mean_token_accuracy": 0.1480805829167366,
|
|
"num_tokens": 15071403.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.193117904663086,
|
|
"epoch": 0.6506160971773136,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004964253730512799,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.1450770802795887,
|
|
"num_tokens": 15081651.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.257673120498657,
|
|
"epoch": 0.6510530455300183,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004964198384454882,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.1403050921857357,
|
|
"num_tokens": 15093403.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.285808038711548,
|
|
"epoch": 0.6514899938827231,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000496414299592748,
|
|
"loss": 6.1717,
|
|
"mean_token_accuracy": 0.13339342251420022,
|
|
"num_tokens": 15103618.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.264203071594238,
|
|
"epoch": 0.6519269422354278,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004964087564931656,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.1440037965774536,
|
|
"num_tokens": 15113926.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.311422634124756,
|
|
"epoch": 0.6523638905881325,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004964032091468472,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.13408324718475342,
|
|
"num_tokens": 15125302.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.240755319595337,
|
|
"epoch": 0.6528008389408372,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004963976575538991,
|
|
"loss": 6.0381,
|
|
"mean_token_accuracy": 0.14353784397244454,
|
|
"num_tokens": 15135943.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.187025737762451,
|
|
"epoch": 0.6532377872935419,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000496392101714428,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.14651306569576264,
|
|
"num_tokens": 15145001.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.224766111373901,
|
|
"epoch": 0.6536747356462466,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004963865416285405,
|
|
"loss": 5.9831,
|
|
"mean_token_accuracy": 0.13959733992815018,
|
|
"num_tokens": 15154567.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.292343664169311,
|
|
"epoch": 0.6541116839989514,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004963809772963431,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.14008966982364654,
|
|
"num_tokens": 15164311.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.2469398021698,
|
|
"epoch": 0.6545486323516561,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004963754087179425,
|
|
"loss": 6.0559,
|
|
"mean_token_accuracy": 0.13879222944378852,
|
|
"num_tokens": 15175217.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.2084550857543945,
|
|
"epoch": 0.6549855807043607,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004963698358934455,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.14221766889095305,
|
|
"num_tokens": 15184895.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.173346376419067,
|
|
"epoch": 0.6554225290570654,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004963642588229591,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.14261841848492623,
|
|
"num_tokens": 15194380.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.267757225036621,
|
|
"epoch": 0.6558594774097701,
|
|
"grad_norm": 6.3125,
|
|
"learning_rate": 0.0004963586775065902,
|
|
"loss": 6.0882,
|
|
"mean_token_accuracy": 0.137705647200346,
|
|
"num_tokens": 15204364.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.271279907226562,
|
|
"epoch": 0.6562964257624748,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004963530919444459,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.1366719014942646,
|
|
"num_tokens": 15214485.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.287254810333252,
|
|
"epoch": 0.6567333741151796,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004963475021366333,
|
|
"loss": 6.2012,
|
|
"mean_token_accuracy": 0.12970216646790506,
|
|
"num_tokens": 15224764.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.31780252456665,
|
|
"epoch": 0.6571703224678843,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004963419080832597,
|
|
"loss": 6.1879,
|
|
"mean_token_accuracy": 0.13702881038188935,
|
|
"num_tokens": 15235481.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.2787665843963625,
|
|
"epoch": 0.657607270820589,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004963363097844323,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.13650887086987495,
|
|
"num_tokens": 15245332.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.2709825992584225,
|
|
"epoch": 0.6580442191732937,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004963307072402584,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.13837921172380446,
|
|
"num_tokens": 15255562.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.2294000625610355,
|
|
"epoch": 0.6584811675259984,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004963251004508456,
|
|
"loss": 6.0622,
|
|
"mean_token_accuracy": 0.1389525756239891,
|
|
"num_tokens": 15265655.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.200943660736084,
|
|
"epoch": 0.6589181158787032,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004963194894163015,
|
|
"loss": 6.008,
|
|
"mean_token_accuracy": 0.14637767225503923,
|
|
"num_tokens": 15276311.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.233555889129638,
|
|
"epoch": 0.6593550642314079,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004963138741367334,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.13676377534866332,
|
|
"num_tokens": 15287142.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.2695239067077635,
|
|
"epoch": 0.6597920125841126,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004963082546122495,
|
|
"loss": 6.1526,
|
|
"mean_token_accuracy": 0.135238941013813,
|
|
"num_tokens": 15297484.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.293298292160034,
|
|
"epoch": 0.6602289609368173,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004963026308429571,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.1388798713684082,
|
|
"num_tokens": 15307468.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.204461097717285,
|
|
"epoch": 0.660665909289522,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004962970028289644,
|
|
"loss": 6.0408,
|
|
"mean_token_accuracy": 0.14689301177859307,
|
|
"num_tokens": 15318487.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.193296766281128,
|
|
"epoch": 0.6611028576422266,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004962913705703791,
|
|
"loss": 6.0832,
|
|
"mean_token_accuracy": 0.1438783273100853,
|
|
"num_tokens": 15329193.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.2236976146698,
|
|
"epoch": 0.6615398059949315,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004962857340673095,
|
|
"loss": 6.0539,
|
|
"mean_token_accuracy": 0.1355200909078121,
|
|
"num_tokens": 15338886.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.209378719329834,
|
|
"epoch": 0.6619767543476361,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004962800933198635,
|
|
"loss": 5.9951,
|
|
"mean_token_accuracy": 0.15128109306097032,
|
|
"num_tokens": 15348629.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.210313034057617,
|
|
"epoch": 0.6624137027003408,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004962744483281495,
|
|
"loss": 6.0883,
|
|
"mean_token_accuracy": 0.14175621643662453,
|
|
"num_tokens": 15358004.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.222506761550903,
|
|
"epoch": 0.6628506510530455,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004962687990922754,
|
|
"loss": 6.1186,
|
|
"mean_token_accuracy": 0.1353178545832634,
|
|
"num_tokens": 15368018.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.31260313987732,
|
|
"epoch": 0.6632875994057502,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00049626314561235,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.13854215443134307,
|
|
"num_tokens": 15377443.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.222037744522095,
|
|
"epoch": 0.6637245477584549,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004962574878884814,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.14046914577484132,
|
|
"num_tokens": 15388278.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.175523900985718,
|
|
"epoch": 0.6641614961111597,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004962518259207782,
|
|
"loss": 6.0909,
|
|
"mean_token_accuracy": 0.14351003468036652,
|
|
"num_tokens": 15398619.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.205916500091552,
|
|
"epoch": 0.6645984444638644,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004962461597093491,
|
|
"loss": 5.9868,
|
|
"mean_token_accuracy": 0.1472811594605446,
|
|
"num_tokens": 15408635.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.270863628387451,
|
|
"epoch": 0.6650353928165691,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004962404892543028,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.13835323452949524,
|
|
"num_tokens": 15419113.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.3479838371276855,
|
|
"epoch": 0.6654723411692738,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000496234814555748,
|
|
"loss": 6.092,
|
|
"mean_token_accuracy": 0.13462133705615997,
|
|
"num_tokens": 15428959.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.219027853012085,
|
|
"epoch": 0.6659092895219785,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004962291356137934,
|
|
"loss": 6.1336,
|
|
"mean_token_accuracy": 0.13156894743442535,
|
|
"num_tokens": 15439116.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.240478801727295,
|
|
"epoch": 0.6663462378746832,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004962234524285481,
|
|
"loss": 6.1185,
|
|
"mean_token_accuracy": 0.14176129549741745,
|
|
"num_tokens": 15449715.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.279317903518677,
|
|
"epoch": 0.666783186227388,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.0004962177650001212,
|
|
"loss": 5.926,
|
|
"mean_token_accuracy": 0.15156869888305663,
|
|
"num_tokens": 15459170.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.206975221633911,
|
|
"epoch": 0.6672201345800927,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004962120733286215,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.1426810458302498,
|
|
"num_tokens": 15469497.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.160815477371216,
|
|
"epoch": 0.6676570829327974,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004962063774141583,
|
|
"loss": 6.156,
|
|
"mean_token_accuracy": 0.13761526569724084,
|
|
"num_tokens": 15481298.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.1859899997711185,
|
|
"epoch": 0.668094031285502,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004962006772568409,
|
|
"loss": 6.1148,
|
|
"mean_token_accuracy": 0.1422424003481865,
|
|
"num_tokens": 15491696.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.275316429138184,
|
|
"epoch": 0.6685309796382067,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004961949728567787,
|
|
"loss": 6.1222,
|
|
"mean_token_accuracy": 0.14227507188916205,
|
|
"num_tokens": 15502412.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.297860479354858,
|
|
"epoch": 0.6689679279909114,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004961892642140809,
|
|
"loss": 6.1011,
|
|
"mean_token_accuracy": 0.13902661204338074,
|
|
"num_tokens": 15513436.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.19545259475708,
|
|
"epoch": 0.6694048763436162,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004961835513288572,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.14622755721211433,
|
|
"num_tokens": 15524564.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.2803600311279295,
|
|
"epoch": 0.6698418246963209,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.000496177834201217,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.13727382943034172,
|
|
"num_tokens": 15534539.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.324079895019532,
|
|
"epoch": 0.6702787730490256,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004961721128312702,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.1315089724957943,
|
|
"num_tokens": 15544571.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.228364181518555,
|
|
"epoch": 0.6707157214017303,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.0004961663872191263,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.1470337465405464,
|
|
"num_tokens": 15555066.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.252587223052979,
|
|
"epoch": 0.671152669754435,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004961606573648951,
|
|
"loss": 6.116,
|
|
"mean_token_accuracy": 0.13753531277179717,
|
|
"num_tokens": 15565128.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.247122573852539,
|
|
"epoch": 0.6715896181071397,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004961549232686867,
|
|
"loss": 6.1793,
|
|
"mean_token_accuracy": 0.1353545904159546,
|
|
"num_tokens": 15576394.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.27998194694519,
|
|
"epoch": 0.6720265664598445,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000496149184930611,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.1401011899113655,
|
|
"num_tokens": 15585806.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.261417484283447,
|
|
"epoch": 0.6724635148125492,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004961434423507779,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.14093467295169831,
|
|
"num_tokens": 15596471.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.231219911575318,
|
|
"epoch": 0.6729004631652539,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004961376955292979,
|
|
"loss": 5.9898,
|
|
"mean_token_accuracy": 0.15060002207756043,
|
|
"num_tokens": 15605720.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.23662543296814,
|
|
"epoch": 0.6733374115179586,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004961319444662809,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.14469746202230455,
|
|
"num_tokens": 15616167.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.315139818191528,
|
|
"epoch": 0.6737743598706633,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004961261891618374,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.13433588072657585,
|
|
"num_tokens": 15627033.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.232497930526733,
|
|
"epoch": 0.6742113082233679,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004961204296160777,
|
|
"loss": 6.1109,
|
|
"mean_token_accuracy": 0.13909128829836845,
|
|
"num_tokens": 15637460.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.21066632270813,
|
|
"epoch": 0.6746482565760727,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004961146658291123,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.14700669944286346,
|
|
"num_tokens": 15646027.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.202454948425293,
|
|
"epoch": 0.6750852049287774,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004961088978010518,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.1390362374484539,
|
|
"num_tokens": 15655241.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.1901716709136965,
|
|
"epoch": 0.6755221532814821,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004961031255320067,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.13531052097678184,
|
|
"num_tokens": 15666213.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.2788177013397215,
|
|
"epoch": 0.6759591016341868,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004960973490220878,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.13685087263584136,
|
|
"num_tokens": 15676985.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.3100268840789795,
|
|
"epoch": 0.6763960499868915,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004960915682714059,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.13514363691210746,
|
|
"num_tokens": 15687519.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.270909023284912,
|
|
"epoch": 0.6768329983395963,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004960857832800719,
|
|
"loss": 6.1146,
|
|
"mean_token_accuracy": 0.1358247369527817,
|
|
"num_tokens": 15697401.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.2234748840332035,
|
|
"epoch": 0.677269946692301,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004960799940481968,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.13038893416523933,
|
|
"num_tokens": 15708159.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.244372081756592,
|
|
"epoch": 0.6777068950450057,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004960742005758914,
|
|
"loss": 6.0919,
|
|
"mean_token_accuracy": 0.13842951506376266,
|
|
"num_tokens": 15717749.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.1883094787597654,
|
|
"epoch": 0.6781438433977104,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004960684028632671,
|
|
"loss": 6.0478,
|
|
"mean_token_accuracy": 0.14212872162461282,
|
|
"num_tokens": 15726868.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.226647138595581,
|
|
"epoch": 0.6785807917504151,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004960626009104349,
|
|
"loss": 6.0395,
|
|
"mean_token_accuracy": 0.14510313421487808,
|
|
"num_tokens": 15736038.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.2614130020141605,
|
|
"epoch": 0.6790177401031198,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004960567947175064,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.1364120401442051,
|
|
"num_tokens": 15746676.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.291885280609131,
|
|
"epoch": 0.6794546884558246,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004960509842845926,
|
|
"loss": 6.0756,
|
|
"mean_token_accuracy": 0.13798356875777246,
|
|
"num_tokens": 15756064.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.259097528457642,
|
|
"epoch": 0.6798916368085293,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004960451696118049,
|
|
"loss": 6.0776,
|
|
"mean_token_accuracy": 0.14294374734163284,
|
|
"num_tokens": 15767414.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.291348648071289,
|
|
"epoch": 0.680328585161234,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004960393506992553,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.14387979209423066,
|
|
"num_tokens": 15778276.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.193063640594483,
|
|
"epoch": 0.6807655335139386,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004960335275470551,
|
|
"loss": 5.9891,
|
|
"mean_token_accuracy": 0.14073141291737556,
|
|
"num_tokens": 15788365.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.228651285171509,
|
|
"epoch": 0.6812024818666433,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004960277001553159,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.14451875910162926,
|
|
"num_tokens": 15799021.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.253414106369019,
|
|
"epoch": 0.681639430219348,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004960218685241498,
|
|
"loss": 6.0968,
|
|
"mean_token_accuracy": 0.13949331343173982,
|
|
"num_tokens": 15808779.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.259351921081543,
|
|
"epoch": 0.6820763785720528,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004960160326536681,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.14508993923664093,
|
|
"num_tokens": 15818515.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.226183128356934,
|
|
"epoch": 0.6825133269247575,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004960101925439834,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.13916484117507935,
|
|
"num_tokens": 15828843.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.291645860671997,
|
|
"epoch": 0.6829502752774622,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004960043481952072,
|
|
"loss": 6.0883,
|
|
"mean_token_accuracy": 0.13636393025517463,
|
|
"num_tokens": 15839323.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.273739051818848,
|
|
"epoch": 0.6833872236301669,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000495998499607452,
|
|
"loss": 6.1042,
|
|
"mean_token_accuracy": 0.1382362000644207,
|
|
"num_tokens": 15848399.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.231923580169678,
|
|
"epoch": 0.6838241719828716,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004959926467808296,
|
|
"loss": 5.9833,
|
|
"mean_token_accuracy": 0.14106935560703276,
|
|
"num_tokens": 15858137.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.147455167770386,
|
|
"epoch": 0.6842611203355763,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004959867897154526,
|
|
"loss": 6.0652,
|
|
"mean_token_accuracy": 0.13927642107009888,
|
|
"num_tokens": 15867643.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.20361294746399,
|
|
"epoch": 0.6846980686882811,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000495980928411433,
|
|
"loss": 5.9594,
|
|
"mean_token_accuracy": 0.14536722749471664,
|
|
"num_tokens": 15877523.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.281510686874389,
|
|
"epoch": 0.6851350170409858,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004959750628688834,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.13679477348923683,
|
|
"num_tokens": 15886946.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.176962566375733,
|
|
"epoch": 0.6855719653936905,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004959691930879164,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.14489075690507888,
|
|
"num_tokens": 15896646.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.213808679580689,
|
|
"epoch": 0.6860089137463952,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004959633190686445,
|
|
"loss": 6.0565,
|
|
"mean_token_accuracy": 0.14461535140872,
|
|
"num_tokens": 15907204.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.218833875656128,
|
|
"epoch": 0.6864458620990999,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004959574408111804,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.14740002974867822,
|
|
"num_tokens": 15917634.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.2356006622314455,
|
|
"epoch": 0.6868828104518045,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004959515583156367,
|
|
"loss": 6.0524,
|
|
"mean_token_accuracy": 0.14325984716415405,
|
|
"num_tokens": 15926584.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.226416015625,
|
|
"epoch": 0.6873197588045094,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004959456715821264,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.14065923020243645,
|
|
"num_tokens": 15936636.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.235525274276734,
|
|
"epoch": 0.687756707157214,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004959397806107624,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.14805042818188668,
|
|
"num_tokens": 15946113.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.264631223678589,
|
|
"epoch": 0.6881936555099187,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004959338854016574,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.13688136637210846,
|
|
"num_tokens": 15956630.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.21695032119751,
|
|
"epoch": 0.6886306038626234,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004959279859549249,
|
|
"loss": 6.0031,
|
|
"mean_token_accuracy": 0.14520470499992372,
|
|
"num_tokens": 15967129.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.236218690872192,
|
|
"epoch": 0.6890675522153281,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004959220822706779,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.1407023474574089,
|
|
"num_tokens": 15976663.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.247277879714966,
|
|
"epoch": 0.6895045005680328,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004959161743490295,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.1417624481022358,
|
|
"num_tokens": 15986666.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.123452425003052,
|
|
"epoch": 0.6899414489207376,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004959102621900931,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.1560263492166996,
|
|
"num_tokens": 15996233.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.247806692123413,
|
|
"epoch": 0.6903783972734423,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004959043457939822,
|
|
"loss": 6.1629,
|
|
"mean_token_accuracy": 0.13539744317531585,
|
|
"num_tokens": 16008188.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.2406538963317875,
|
|
"epoch": 0.690815345626147,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004958984251608101,
|
|
"loss": 6.0559,
|
|
"mean_token_accuracy": 0.1421897292137146,
|
|
"num_tokens": 16018494.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.234479522705078,
|
|
"epoch": 0.6912522939788517,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004958925002906905,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.15123399272561072,
|
|
"num_tokens": 16028531.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.252134323120117,
|
|
"epoch": 0.6916892423315564,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000495886571183737,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.1430049479007721,
|
|
"num_tokens": 16039050.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.2517712116241455,
|
|
"epoch": 0.6921261906842611,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004958806378400634,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.1348439186811447,
|
|
"num_tokens": 16050751.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.271159839630127,
|
|
"epoch": 0.6925631390369659,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004958747002597834,
|
|
"loss": 6.0794,
|
|
"mean_token_accuracy": 0.13974782675504685,
|
|
"num_tokens": 16060758.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.229480361938476,
|
|
"epoch": 0.6930000873896706,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004958687584430109,
|
|
"loss": 6.0786,
|
|
"mean_token_accuracy": 0.1384492725133896,
|
|
"num_tokens": 16070852.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.184289503097534,
|
|
"epoch": 0.6934370357423753,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004958628123898597,
|
|
"loss": 6.002,
|
|
"mean_token_accuracy": 0.13939088210463524,
|
|
"num_tokens": 16080081.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.234544944763184,
|
|
"epoch": 0.6938739840950799,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004958568621004442,
|
|
"loss": 6.0387,
|
|
"mean_token_accuracy": 0.14234753847122192,
|
|
"num_tokens": 16090483.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.2850720405578615,
|
|
"epoch": 0.6943109324477846,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004958509075748785,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.13589274138212204,
|
|
"num_tokens": 16101136.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.244620084762573,
|
|
"epoch": 0.6947478808004894,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004958449488132764,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.1499411940574646,
|
|
"num_tokens": 16110124.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.179692363739013,
|
|
"epoch": 0.6951848291531941,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004958389858157526,
|
|
"loss": 5.9704,
|
|
"mean_token_accuracy": 0.14949270188808442,
|
|
"num_tokens": 16119581.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.2103077411651615,
|
|
"epoch": 0.6956217775058988,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004958330185824213,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.1400443397462368,
|
|
"num_tokens": 16130119.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.248662233352661,
|
|
"epoch": 0.6960587258586035,
|
|
"grad_norm": 5.0625,
|
|
"learning_rate": 0.000495827047113397,
|
|
"loss": 6.0809,
|
|
"mean_token_accuracy": 0.14603182747960092,
|
|
"num_tokens": 16140702.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.2235160827636715,
|
|
"epoch": 0.6964956742113082,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004958210714087942,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.14232370778918266,
|
|
"num_tokens": 16151107.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.261234617233276,
|
|
"epoch": 0.6969326225640129,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004958150914687276,
|
|
"loss": 6.0158,
|
|
"mean_token_accuracy": 0.14557732939720153,
|
|
"num_tokens": 16160779.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.222548103332519,
|
|
"epoch": 0.6973695709167177,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004958091072933118,
|
|
"loss": 5.9529,
|
|
"mean_token_accuracy": 0.1484435260295868,
|
|
"num_tokens": 16169624.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.0988383293151855,
|
|
"epoch": 0.6978065192694224,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004958031188826616,
|
|
"loss": 5.9475,
|
|
"mean_token_accuracy": 0.15440112948417664,
|
|
"num_tokens": 16179192.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.12196102142334,
|
|
"epoch": 0.6982434676221271,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004957971262368919,
|
|
"loss": 6.0292,
|
|
"mean_token_accuracy": 0.14307815954089165,
|
|
"num_tokens": 16188847.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.280730962753296,
|
|
"epoch": 0.6986804159748318,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004957911293561176,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.1361527405679226,
|
|
"num_tokens": 16199480.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.313855600357056,
|
|
"epoch": 0.6991173643275365,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004957851282404538,
|
|
"loss": 6.0374,
|
|
"mean_token_accuracy": 0.14604747369885446,
|
|
"num_tokens": 16208818.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.254707622528076,
|
|
"epoch": 0.6995543126802412,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004957791228900154,
|
|
"loss": 6.0069,
|
|
"mean_token_accuracy": 0.14893947616219522,
|
|
"num_tokens": 16219298.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.158475303649903,
|
|
"epoch": 0.699991261032946,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004957731133049179,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.1494004338979721,
|
|
"num_tokens": 16228170.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.210049057006836,
|
|
"epoch": 0.7004282093856506,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004957670994852764,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.13958207219839097,
|
|
"num_tokens": 16237552.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.274960088729858,
|
|
"epoch": 0.7008651577383553,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004957610814312062,
|
|
"loss": 6.1267,
|
|
"mean_token_accuracy": 0.13958656713366507,
|
|
"num_tokens": 16248157.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.231983327865601,
|
|
"epoch": 0.70130210609106,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004957550591428229,
|
|
"loss": 6.0187,
|
|
"mean_token_accuracy": 0.14684519171714783,
|
|
"num_tokens": 16258266.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.173481273651123,
|
|
"epoch": 0.7017390544437647,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004957490326202418,
|
|
"loss": 6.1012,
|
|
"mean_token_accuracy": 0.14092958196997643,
|
|
"num_tokens": 16268769.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.266806983947754,
|
|
"epoch": 0.7021760027964694,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004957430018635785,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.14316139072179795,
|
|
"num_tokens": 16279688.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.2848986148834225,
|
|
"epoch": 0.7026129511491742,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004957369668729488,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.14487592950463296,
|
|
"num_tokens": 16289441.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.2462770462036135,
|
|
"epoch": 0.7030498995018789,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004957309276484685,
|
|
"loss": 6.0428,
|
|
"mean_token_accuracy": 0.14013879671692847,
|
|
"num_tokens": 16299802.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.190154266357422,
|
|
"epoch": 0.7034868478545836,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004957248841902533,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.1485394701361656,
|
|
"num_tokens": 16309577.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.148804140090943,
|
|
"epoch": 0.7039237962072883,
|
|
"grad_norm": 7.90625,
|
|
"learning_rate": 0.0004957188364984191,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.14889626950025558,
|
|
"num_tokens": 16319205.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.155892086029053,
|
|
"epoch": 0.704360744559993,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000495712784573082,
|
|
"loss": 6.0385,
|
|
"mean_token_accuracy": 0.14606433138251304,
|
|
"num_tokens": 16329650.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.1896062850952145,
|
|
"epoch": 0.7047976929126977,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004957067284143581,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.14281625300645828,
|
|
"num_tokens": 16339242.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.206028747558594,
|
|
"epoch": 0.7052346412654025,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004957006680223634,
|
|
"loss": 5.9999,
|
|
"mean_token_accuracy": 0.14916329383850097,
|
|
"num_tokens": 16348441.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.207070684432983,
|
|
"epoch": 0.7056715896181072,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004956946033972143,
|
|
"loss": 6.0092,
|
|
"mean_token_accuracy": 0.14172426983714104,
|
|
"num_tokens": 16357425.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.220908689498901,
|
|
"epoch": 0.7061085379708119,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000495688534539027,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.14150218665599823,
|
|
"num_tokens": 16366180.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.196384572982788,
|
|
"epoch": 0.7065454863235165,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004956824614479181,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.1426027871668339,
|
|
"num_tokens": 16375714.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.260721111297608,
|
|
"epoch": 0.7069824346762212,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004956763841240038,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.1394146427512169,
|
|
"num_tokens": 16386051.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.267225837707519,
|
|
"epoch": 0.7074193830289259,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000495670302567401,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.13717012405395507,
|
|
"num_tokens": 16396616.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.190759563446045,
|
|
"epoch": 0.7078563313816307,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000495664216778226,
|
|
"loss": 6.0039,
|
|
"mean_token_accuracy": 0.15091822892427445,
|
|
"num_tokens": 16406301.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.247671604156494,
|
|
"epoch": 0.7082932797343354,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004956581267565957,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.136067433655262,
|
|
"num_tokens": 16417107.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.2221972942352295,
|
|
"epoch": 0.7087302280870401,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000495652032502627,
|
|
"loss": 6.0103,
|
|
"mean_token_accuracy": 0.1416815422475338,
|
|
"num_tokens": 16427292.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.1572459697723385,
|
|
"epoch": 0.7091671764397448,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004956459340164366,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.14646508246660234,
|
|
"num_tokens": 16438191.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.198068523406983,
|
|
"epoch": 0.7096041247924495,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004956398312981417,
|
|
"loss": 6.0083,
|
|
"mean_token_accuracy": 0.14299816489219666,
|
|
"num_tokens": 16448237.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.161847925186157,
|
|
"epoch": 0.7100410731451542,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004956337243478592,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.14033075869083406,
|
|
"num_tokens": 16458947.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.261043071746826,
|
|
"epoch": 0.710478021497859,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004956276131657061,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.1499764770269394,
|
|
"num_tokens": 16467464.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.234200191497803,
|
|
"epoch": 0.7109149698505637,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004956214977518,
|
|
"loss": 6.0217,
|
|
"mean_token_accuracy": 0.15601760447025298,
|
|
"num_tokens": 16477747.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.255400466918945,
|
|
"epoch": 0.7113519182032684,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004956153781062578,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.1387567326426506,
|
|
"num_tokens": 16488111.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.221999979019165,
|
|
"epoch": 0.7117888665559731,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004956092542291971,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.14879337698221207,
|
|
"num_tokens": 16497689.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.253456401824951,
|
|
"epoch": 0.7122258149086778,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004956031261207353,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.13987948149442672,
|
|
"num_tokens": 16508515.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.206867694854736,
|
|
"epoch": 0.7126627632613826,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00049559699378099,
|
|
"loss": 6.0309,
|
|
"mean_token_accuracy": 0.15083636566996575,
|
|
"num_tokens": 16519184.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.259245777130127,
|
|
"epoch": 0.7130997116140873,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004955908572100787,
|
|
"loss": 6.1133,
|
|
"mean_token_accuracy": 0.13577307909727096,
|
|
"num_tokens": 16529917.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.258401250839233,
|
|
"epoch": 0.7135366599667919,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004955847164081192,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.1360163688659668,
|
|
"num_tokens": 16539687.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.217234992980957,
|
|
"epoch": 0.7139736083194966,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004955785713752292,
|
|
"loss": 6.1034,
|
|
"mean_token_accuracy": 0.14174101278185844,
|
|
"num_tokens": 16550273.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.310365152359009,
|
|
"epoch": 0.7144105566722013,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004955724221115267,
|
|
"loss": 6.1547,
|
|
"mean_token_accuracy": 0.13744727075099944,
|
|
"num_tokens": 16562215.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.33936333656311,
|
|
"epoch": 0.714847505024906,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004955662686171295,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.14110765382647514,
|
|
"num_tokens": 16573218.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.30700569152832,
|
|
"epoch": 0.7152844533776108,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004955601108921557,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.1380538746714592,
|
|
"num_tokens": 16582740.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.177458715438843,
|
|
"epoch": 0.7157214017303155,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004955539489367235,
|
|
"loss": 6.0794,
|
|
"mean_token_accuracy": 0.14526512026786803,
|
|
"num_tokens": 16592169.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.230506229400635,
|
|
"epoch": 0.7161583500830202,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004955477827509509,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.1382740132510662,
|
|
"num_tokens": 16602706.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.224744129180908,
|
|
"epoch": 0.7165952984357249,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004955416123349562,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.1419399008154869,
|
|
"num_tokens": 16612012.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.212010669708252,
|
|
"epoch": 0.7170322467884296,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000495535437688858,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.1388662949204445,
|
|
"num_tokens": 16621798.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.242937612533569,
|
|
"epoch": 0.7174691951411343,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004955292588127744,
|
|
"loss": 6.0544,
|
|
"mean_token_accuracy": 0.1456645667552948,
|
|
"num_tokens": 16631792.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.3231405258178714,
|
|
"epoch": 0.7179061434938391,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000495523075706824,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.1423792839050293,
|
|
"num_tokens": 16641655.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.209512710571289,
|
|
"epoch": 0.7183430918465438,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004955168883711257,
|
|
"loss": 6.0916,
|
|
"mean_token_accuracy": 0.1400701344013214,
|
|
"num_tokens": 16651210.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.239299964904785,
|
|
"epoch": 0.7187800401992485,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004955106968057977,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.13928594663739205,
|
|
"num_tokens": 16660078.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.282232236862183,
|
|
"epoch": 0.7192169885519532,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004955045010109592,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.13874608874320984,
|
|
"num_tokens": 16671211.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.26195707321167,
|
|
"epoch": 0.7196539369046578,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004954983009867286,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.1426847517490387,
|
|
"num_tokens": 16680850.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.222715616226196,
|
|
"epoch": 0.7200908852573625,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004954920967332252,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.14225781932473183,
|
|
"num_tokens": 16690447.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.199004411697388,
|
|
"epoch": 0.7205278336100673,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004954858882505678,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.13997026309370994,
|
|
"num_tokens": 16701061.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.212587594985962,
|
|
"epoch": 0.720964781962772,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004954796755388755,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.14577565342187881,
|
|
"num_tokens": 16711139.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.244093561172486,
|
|
"epoch": 0.7214017303154767,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004954734585982675,
|
|
"loss": 6.1077,
|
|
"mean_token_accuracy": 0.13529232516884804,
|
|
"num_tokens": 16722343.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.283843612670898,
|
|
"epoch": 0.7218386786681814,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004954672374288631,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.13186091929674149,
|
|
"num_tokens": 16733475.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.264413690567016,
|
|
"epoch": 0.7222756270208861,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004954610120307815,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.13933211341500282,
|
|
"num_tokens": 16744356.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.231073570251465,
|
|
"epoch": 0.7227125753735908,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004954547824041422,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.13735386803746225,
|
|
"num_tokens": 16755275.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.183216857910156,
|
|
"epoch": 0.7231495237262956,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004954485485490647,
|
|
"loss": 6.0098,
|
|
"mean_token_accuracy": 0.14503678679466248,
|
|
"num_tokens": 16766114.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.222272157669067,
|
|
"epoch": 0.7235864720790003,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004954423104656685,
|
|
"loss": 6.0066,
|
|
"mean_token_accuracy": 0.15063316375017166,
|
|
"num_tokens": 16776391.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.177164506912232,
|
|
"epoch": 0.724023420431705,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004954360681540732,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.14972576797008513,
|
|
"num_tokens": 16784845.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.165531492233276,
|
|
"epoch": 0.7244603687844097,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004954298216143986,
|
|
"loss": 6.0193,
|
|
"mean_token_accuracy": 0.14583383798599242,
|
|
"num_tokens": 16794735.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.314350938796997,
|
|
"epoch": 0.7248973171371144,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004954235708467647,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.14092472940683365,
|
|
"num_tokens": 16803643.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.289931726455689,
|
|
"epoch": 0.725334265489819,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000495417315851291,
|
|
"loss": 6.0928,
|
|
"mean_token_accuracy": 0.14327989518642426,
|
|
"num_tokens": 16813064.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.163081979751587,
|
|
"epoch": 0.7257712138425239,
|
|
"grad_norm": 5.84375,
|
|
"learning_rate": 0.0004954110566280978,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.13695041239261627,
|
|
"num_tokens": 16823166.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.233119249343872,
|
|
"epoch": 0.7262081621952285,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.000495404793177305,
|
|
"loss": 6.1137,
|
|
"mean_token_accuracy": 0.14075919687747956,
|
|
"num_tokens": 16833546.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.289675045013428,
|
|
"epoch": 0.7266451105479332,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004953985254990328,
|
|
"loss": 5.977,
|
|
"mean_token_accuracy": 0.1457753524184227,
|
|
"num_tokens": 16843794.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.305609607696534,
|
|
"epoch": 0.7270820589006379,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004953922535934014,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.1379474401473999,
|
|
"num_tokens": 16855677.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.25561408996582,
|
|
"epoch": 0.7275190072533426,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.000495385977460531,
|
|
"loss": 6.0786,
|
|
"mean_token_accuracy": 0.13430355340242386,
|
|
"num_tokens": 16866137.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.246871757507324,
|
|
"epoch": 0.7279559556060473,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004953796971005422,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.14452763125300408,
|
|
"num_tokens": 16875997.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.188179063796997,
|
|
"epoch": 0.7283929039587521,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004953734125135552,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.1476132944226265,
|
|
"num_tokens": 16885838.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.1498676300048825,
|
|
"epoch": 0.7288298523114568,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004953671236996909,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.14977214187383653,
|
|
"num_tokens": 16895533.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.210428714752197,
|
|
"epoch": 0.7292668006641615,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004953608306590696,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.13882470726966858,
|
|
"num_tokens": 16906258.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.277710390090943,
|
|
"epoch": 0.7297037490168662,
|
|
"grad_norm": 7.25,
|
|
"learning_rate": 0.000495354533391812,
|
|
"loss": 6.0658,
|
|
"mean_token_accuracy": 0.1460177093744278,
|
|
"num_tokens": 16917123.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.2469895362854,
|
|
"epoch": 0.7301406973695709,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004953482318980389,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.146676953881979,
|
|
"num_tokens": 16927533.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.306425762176514,
|
|
"epoch": 0.7305776457222757,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004953419261778714,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.14144542664289475,
|
|
"num_tokens": 16937763.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.167293548583984,
|
|
"epoch": 0.7310145940749804,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004953356162314304,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.1453294850885868,
|
|
"num_tokens": 16947173.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.2046772003173825,
|
|
"epoch": 0.7314515424276851,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004953293020588368,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.1462822139263153,
|
|
"num_tokens": 16956856.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.280859804153442,
|
|
"epoch": 0.7318884907803898,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004953229836602115,
|
|
"loss": 6.0658,
|
|
"mean_token_accuracy": 0.14148651659488679,
|
|
"num_tokens": 16966705.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.276563119888306,
|
|
"epoch": 0.7323254391330944,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000495316661035676,
|
|
"loss": 6.0953,
|
|
"mean_token_accuracy": 0.13892802894115447,
|
|
"num_tokens": 16977026.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.253737878799439,
|
|
"epoch": 0.7327623874857991,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004953103341853517,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.14437578320503236,
|
|
"num_tokens": 16986800.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.184905242919922,
|
|
"epoch": 0.7331993358385039,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004953040031093596,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.14561595544219016,
|
|
"num_tokens": 16996392.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.1834025382995605,
|
|
"epoch": 0.7336362841912086,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004952976678078213,
|
|
"loss": 6.0258,
|
|
"mean_token_accuracy": 0.13908783942461014,
|
|
"num_tokens": 17006430.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.277691650390625,
|
|
"epoch": 0.7340732325439133,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004952913282808584,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.13975248634815216,
|
|
"num_tokens": 17017168.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.195901918411255,
|
|
"epoch": 0.734510180896618,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004952849845285922,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.1482916310429573,
|
|
"num_tokens": 17027337.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.192442750930786,
|
|
"epoch": 0.7349471292493227,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004952786365511447,
|
|
"loss": 5.9609,
|
|
"mean_token_accuracy": 0.1502939209342003,
|
|
"num_tokens": 17036839.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.207208728790283,
|
|
"epoch": 0.7353840776020274,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004952722843486375,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.13479250371456147,
|
|
"num_tokens": 17048221.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.183388614654541,
|
|
"epoch": 0.7358210259547322,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004952659279211924,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.14208328127861022,
|
|
"num_tokens": 17057694.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.24350118637085,
|
|
"epoch": 0.7362579743074369,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004952595672689315,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.1346749857068062,
|
|
"num_tokens": 17066492.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.296481704711914,
|
|
"epoch": 0.7366949226601416,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004952532023919766,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.13946571722626686,
|
|
"num_tokens": 17077211.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.272731971740723,
|
|
"epoch": 0.7371318710128463,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004952468332904498,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.13983459323644637,
|
|
"num_tokens": 17088665.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.221385145187378,
|
|
"epoch": 0.737568819365551,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004952404599644735,
|
|
"loss": 6.0671,
|
|
"mean_token_accuracy": 0.1424330674111843,
|
|
"num_tokens": 17099767.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.212916564941406,
|
|
"epoch": 0.7380057677182557,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004952340824141698,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.14879536181688308,
|
|
"num_tokens": 17109414.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.184593915939331,
|
|
"epoch": 0.7384427160709605,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004952277006396609,
|
|
"loss": 6.0458,
|
|
"mean_token_accuracy": 0.13909671306610108,
|
|
"num_tokens": 17119107.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.2288893699646,
|
|
"epoch": 0.7388796644236652,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004952213146410693,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.13814739882946014,
|
|
"num_tokens": 17129010.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.261946964263916,
|
|
"epoch": 0.7393166127763698,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004952149244185174,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.13839999288320542,
|
|
"num_tokens": 17138951.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.250641870498657,
|
|
"epoch": 0.7397535611290745,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004952085299721279,
|
|
"loss": 6.0539,
|
|
"mean_token_accuracy": 0.14264668449759482,
|
|
"num_tokens": 17149416.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.261624002456665,
|
|
"epoch": 0.7401905094817792,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004952021313020235,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.14614282846450805,
|
|
"num_tokens": 17160068.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.160351133346557,
|
|
"epoch": 0.7406274578344839,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004951957284083269,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.14056818932294846,
|
|
"num_tokens": 17168972.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.171355581283569,
|
|
"epoch": 0.7410644061871887,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004951893212911607,
|
|
"loss": 6.0005,
|
|
"mean_token_accuracy": 0.1472700320184231,
|
|
"num_tokens": 17178239.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.282161617279053,
|
|
"epoch": 0.7415013545398934,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.000495182909950648,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.1356131374835968,
|
|
"num_tokens": 17190619.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.201739168167114,
|
|
"epoch": 0.7419383028925981,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004951764943869117,
|
|
"loss": 5.9605,
|
|
"mean_token_accuracy": 0.14864636063575745,
|
|
"num_tokens": 17201041.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.141462278366089,
|
|
"epoch": 0.7423752512453028,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004951700746000749,
|
|
"loss": 6.0711,
|
|
"mean_token_accuracy": 0.14122827351093292,
|
|
"num_tokens": 17211779.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.1928120136260985,
|
|
"epoch": 0.7428121995980075,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004951636505902606,
|
|
"loss": 6.0281,
|
|
"mean_token_accuracy": 0.1515021190047264,
|
|
"num_tokens": 17221249.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.260330533981323,
|
|
"epoch": 0.7432491479507122,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004951572223575922,
|
|
"loss": 6.0783,
|
|
"mean_token_accuracy": 0.13569876849651336,
|
|
"num_tokens": 17231634.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.245717906951905,
|
|
"epoch": 0.743686096303417,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004951507899021929,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.14073003754019736,
|
|
"num_tokens": 17241751.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.228300333023071,
|
|
"epoch": 0.7441230446561217,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000495144353224186,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.14138879254460335,
|
|
"num_tokens": 17251962.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.234739637374878,
|
|
"epoch": 0.7445599930088264,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004951379123236952,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.14257938861846925,
|
|
"num_tokens": 17261895.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.225541877746582,
|
|
"epoch": 0.744996941361531,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004951314672008439,
|
|
"loss": 6.0575,
|
|
"mean_token_accuracy": 0.1443983182311058,
|
|
"num_tokens": 17272025.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.255196285247803,
|
|
"epoch": 0.7454338897142357,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004951250178557556,
|
|
"loss": 6.0426,
|
|
"mean_token_accuracy": 0.15038821697235108,
|
|
"num_tokens": 17282705.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.1981690406799315,
|
|
"epoch": 0.7458708380669404,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004951185642885542,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.1476744569838047,
|
|
"num_tokens": 17293045.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.228192090988159,
|
|
"epoch": 0.7463077864196452,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004951121064993633,
|
|
"loss": 6.0772,
|
|
"mean_token_accuracy": 0.13934364169836044,
|
|
"num_tokens": 17303893.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.282638168334961,
|
|
"epoch": 0.7467447347723499,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004951056444883069,
|
|
"loss": 6.0682,
|
|
"mean_token_accuracy": 0.13697793558239937,
|
|
"num_tokens": 17314250.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.217985582351685,
|
|
"epoch": 0.7471816831250546,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000495099178255509,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.1416642740368843,
|
|
"num_tokens": 17324268.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.198323345184326,
|
|
"epoch": 0.7476186314777593,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004950927078010934,
|
|
"loss": 6.0926,
|
|
"mean_token_accuracy": 0.13649949058890343,
|
|
"num_tokens": 17334512.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.267451524734497,
|
|
"epoch": 0.748055579830464,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004950862331251845,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.14405351355671883,
|
|
"num_tokens": 17346244.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.216365003585816,
|
|
"epoch": 0.7484925281831688,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004950797542279061,
|
|
"loss": 6.0453,
|
|
"mean_token_accuracy": 0.14253236427903176,
|
|
"num_tokens": 17355832.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.192827749252319,
|
|
"epoch": 0.7489294765358735,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004950732711093828,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.14349730908870698,
|
|
"num_tokens": 17366871.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.305753374099732,
|
|
"epoch": 0.7493664248885782,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004950667837697388,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.13418168425559998,
|
|
"num_tokens": 17377242.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.3307852268219,
|
|
"epoch": 0.7498033732412829,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004950602922090988,
|
|
"loss": 6.0811,
|
|
"mean_token_accuracy": 0.13639613315463067,
|
|
"num_tokens": 17387942.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.26843581199646,
|
|
"epoch": 0.7502403215939876,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004950537964275868,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.13597817122936248,
|
|
"num_tokens": 17397413.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.206974363327026,
|
|
"epoch": 0.7506772699466923,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004950472964253278,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.1416654609143734,
|
|
"num_tokens": 17408456.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.206663322448731,
|
|
"epoch": 0.7511142182993971,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004950407922024463,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.14704025387763978,
|
|
"num_tokens": 17417805.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.196809720993042,
|
|
"epoch": 0.7515511666521018,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004950342837590671,
|
|
"loss": 5.9645,
|
|
"mean_token_accuracy": 0.15146640837192535,
|
|
"num_tokens": 17426932.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.19592547416687,
|
|
"epoch": 0.7519881150048064,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004950277710953152,
|
|
"loss": 6.0623,
|
|
"mean_token_accuracy": 0.14430806338787078,
|
|
"num_tokens": 17436770.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.190313053131104,
|
|
"epoch": 0.7524250633575111,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004950212542113153,
|
|
"loss": 5.961,
|
|
"mean_token_accuracy": 0.14544311463832854,
|
|
"num_tokens": 17447852.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.149398517608643,
|
|
"epoch": 0.7528620117102158,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004950147331071924,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.1404561571776867,
|
|
"num_tokens": 17458020.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.211113929748535,
|
|
"epoch": 0.7532989600629205,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004950082077830717,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.13863237872719764,
|
|
"num_tokens": 17468604.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.26945686340332,
|
|
"epoch": 0.7537359084156253,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004950016782390782,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.14416363313794137,
|
|
"num_tokens": 17478374.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.269142770767212,
|
|
"epoch": 0.75417285676833,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004949951444753372,
|
|
"loss": 6.0359,
|
|
"mean_token_accuracy": 0.14331215620040894,
|
|
"num_tokens": 17487894.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.221175622940064,
|
|
"epoch": 0.7546098051210347,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004949886064919741,
|
|
"loss": 5.996,
|
|
"mean_token_accuracy": 0.14074719920754433,
|
|
"num_tokens": 17498473.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.211667490005493,
|
|
"epoch": 0.7550467534737394,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004949820642891142,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.14195635169744492,
|
|
"num_tokens": 17507796.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.171490859985352,
|
|
"epoch": 0.7554837018264441,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004949755178668832,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.1477346181869507,
|
|
"num_tokens": 17517629.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.260648393630982,
|
|
"epoch": 0.7559206501791488,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004949689672254064,
|
|
"loss": 6.1036,
|
|
"mean_token_accuracy": 0.1329352766275406,
|
|
"num_tokens": 17528726.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.275094127655029,
|
|
"epoch": 0.7563575985318536,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004949624123648096,
|
|
"loss": 6.0014,
|
|
"mean_token_accuracy": 0.1422254428267479,
|
|
"num_tokens": 17539022.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.223832321166992,
|
|
"epoch": 0.7567945468845583,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004949558532852185,
|
|
"loss": 6.0461,
|
|
"mean_token_accuracy": 0.1439749851822853,
|
|
"num_tokens": 17549293.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.183422327041626,
|
|
"epoch": 0.757231495237263,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.0004949492899867587,
|
|
"loss": 6.0326,
|
|
"mean_token_accuracy": 0.13842322826385497,
|
|
"num_tokens": 17559072.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.190749454498291,
|
|
"epoch": 0.7576684435899677,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004949427224695564,
|
|
"loss": 6.0226,
|
|
"mean_token_accuracy": 0.14318446591496467,
|
|
"num_tokens": 17568757.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.226632213592529,
|
|
"epoch": 0.7581053919426723,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004949361507337374,
|
|
"loss": 6.0193,
|
|
"mean_token_accuracy": 0.14537923634052277,
|
|
"num_tokens": 17578288.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.2610218048095705,
|
|
"epoch": 0.758542340295377,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004949295747794277,
|
|
"loss": 6.116,
|
|
"mean_token_accuracy": 0.1382712870836258,
|
|
"num_tokens": 17588864.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.254505634307861,
|
|
"epoch": 0.7589792886480818,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004949229946067537,
|
|
"loss": 6.0921,
|
|
"mean_token_accuracy": 0.14055313169956207,
|
|
"num_tokens": 17599103.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.184361553192138,
|
|
"epoch": 0.7594162370007865,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004949164102158413,
|
|
"loss": 6.0025,
|
|
"mean_token_accuracy": 0.1467547371983528,
|
|
"num_tokens": 17608608.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.228552436828613,
|
|
"epoch": 0.7598531853534912,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000494909821606817,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.14077405631542206,
|
|
"num_tokens": 17618604.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.319025087356567,
|
|
"epoch": 0.7602901337061959,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004949032287798069,
|
|
"loss": 6.0387,
|
|
"mean_token_accuracy": 0.14739960730075835,
|
|
"num_tokens": 17628479.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.231346940994262,
|
|
"epoch": 0.7607270820589006,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004948966317349379,
|
|
"loss": 6.0412,
|
|
"mean_token_accuracy": 0.14681292027235032,
|
|
"num_tokens": 17637519.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 6.216566514968872,
|
|
"epoch": 0.7611640304116053,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004948900304723361,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.1492878243327141,
|
|
"num_tokens": 17647902.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.274780988693237,
|
|
"epoch": 0.7616009787643101,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004948834249921285,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.1431396059691906,
|
|
"num_tokens": 17658576.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.21819658279419,
|
|
"epoch": 0.7620379271170148,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004948768152944414,
|
|
"loss": 6.0763,
|
|
"mean_token_accuracy": 0.14016674533486367,
|
|
"num_tokens": 17667059.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.277122974395752,
|
|
"epoch": 0.7624748754697195,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004948702013794018,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.1352974832057953,
|
|
"num_tokens": 17677447.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.284607887268066,
|
|
"epoch": 0.7629118238224242,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004948635832471366,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.15216316804289817,
|
|
"num_tokens": 17687893.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.226282358169556,
|
|
"epoch": 0.7633487721751289,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004948569608977726,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.1410996735095978,
|
|
"num_tokens": 17698599.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.234055852890014,
|
|
"epoch": 0.7637857205278336,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.0004948503343314369,
|
|
"loss": 6.0832,
|
|
"mean_token_accuracy": 0.13510883152484893,
|
|
"num_tokens": 17709711.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.240414333343506,
|
|
"epoch": 0.7642226688805384,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004948437035482566,
|
|
"loss": 6.0425,
|
|
"mean_token_accuracy": 0.14039023146033286,
|
|
"num_tokens": 17719613.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.2663328647613525,
|
|
"epoch": 0.764659617233243,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004948370685483588,
|
|
"loss": 6.0177,
|
|
"mean_token_accuracy": 0.15150065273046492,
|
|
"num_tokens": 17729829.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.268952989578247,
|
|
"epoch": 0.7650965655859477,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004948304293318709,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.1446221023797989,
|
|
"num_tokens": 17739254.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.228422737121582,
|
|
"epoch": 0.7655335139386524,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004948237858989201,
|
|
"loss": 6.044,
|
|
"mean_token_accuracy": 0.13771776854991913,
|
|
"num_tokens": 17749294.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.206667804718018,
|
|
"epoch": 0.7659704622913571,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000494817138249634,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.150910571962595,
|
|
"num_tokens": 17758866.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.358490991592407,
|
|
"epoch": 0.7664074106440619,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.00049481048638414,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.1335010588169098,
|
|
"num_tokens": 17769202.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.226506757736206,
|
|
"epoch": 0.7668443589967666,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004948038303025657,
|
|
"loss": 6.0997,
|
|
"mean_token_accuracy": 0.14109473377466203,
|
|
"num_tokens": 17779125.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.270475721359253,
|
|
"epoch": 0.7672813073494713,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004947971700050387,
|
|
"loss": 6.0489,
|
|
"mean_token_accuracy": 0.13899814411997796,
|
|
"num_tokens": 17788696.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.223231029510498,
|
|
"epoch": 0.767718255702176,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004947905054916869,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.1383361414074898,
|
|
"num_tokens": 17799867.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.293824672698975,
|
|
"epoch": 0.7681552040548807,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004947838367626379,
|
|
"loss": 6.0456,
|
|
"mean_token_accuracy": 0.13762528523802758,
|
|
"num_tokens": 17809418.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.258719491958618,
|
|
"epoch": 0.7685921524075854,
|
|
"grad_norm": 5.625,
|
|
"learning_rate": 0.0004947771638180198,
|
|
"loss": 5.9662,
|
|
"mean_token_accuracy": 0.15071939826011657,
|
|
"num_tokens": 17818554.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.220383358001709,
|
|
"epoch": 0.7690291007602902,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004947704866579605,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.14543282389640808,
|
|
"num_tokens": 17828918.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.254160785675049,
|
|
"epoch": 0.7694660491129949,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004947638052825883,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.13365367203950881,
|
|
"num_tokens": 17840791.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.312784910202026,
|
|
"epoch": 0.7699029974656996,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004947571196920309,
|
|
"loss": 6.0491,
|
|
"mean_token_accuracy": 0.14061523079872132,
|
|
"num_tokens": 17850675.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.22687726020813,
|
|
"epoch": 0.7703399458184043,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004947504298864169,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.14554693624377252,
|
|
"num_tokens": 17860684.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.176032638549804,
|
|
"epoch": 0.770776894171109,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004947437358658746,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.14274812787771224,
|
|
"num_tokens": 17870394.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.246598482131958,
|
|
"epoch": 0.7712138425238136,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004947370376305321,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.14171857833862306,
|
|
"num_tokens": 17881256.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.213253498077393,
|
|
"epoch": 0.7716507908765184,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004947303351805183,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.14157484471797943,
|
|
"num_tokens": 17890888.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.2633696556091305,
|
|
"epoch": 0.7720877392292231,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004947236285159615,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.13945037126541138,
|
|
"num_tokens": 17900507.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.311097908020019,
|
|
"epoch": 0.7725246875819278,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004947169176369902,
|
|
"loss": 6.0912,
|
|
"mean_token_accuracy": 0.14449197351932525,
|
|
"num_tokens": 17911333.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.277305555343628,
|
|
"epoch": 0.7729616359346325,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004947102025437334,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.14333002939820289,
|
|
"num_tokens": 17921540.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.267017030715943,
|
|
"epoch": 0.7733985842873372,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004947034832363199,
|
|
"loss": 6.1127,
|
|
"mean_token_accuracy": 0.14070233479142188,
|
|
"num_tokens": 17931820.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.212412738800049,
|
|
"epoch": 0.7738355326400419,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.0004946967597148782,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.13900020495057105,
|
|
"num_tokens": 17942717.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.234614562988281,
|
|
"epoch": 0.7742724809927467,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.0004946900319795377,
|
|
"loss": 6.0407,
|
|
"mean_token_accuracy": 0.14958684593439103,
|
|
"num_tokens": 17953775.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.263529682159424,
|
|
"epoch": 0.7747094293454514,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004946833000304274,
|
|
"loss": 6.0137,
|
|
"mean_token_accuracy": 0.1431668758392334,
|
|
"num_tokens": 17963877.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.2535178661346436,
|
|
"epoch": 0.7751463776981561,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004946765638676761,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.14579931572079657,
|
|
"num_tokens": 17974015.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.155847454071045,
|
|
"epoch": 0.7755833260508608,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004946698234914132,
|
|
"loss": 6.0453,
|
|
"mean_token_accuracy": 0.1468222126364708,
|
|
"num_tokens": 17984189.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.211731052398681,
|
|
"epoch": 0.7760202744035655,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.000494663078901768,
|
|
"loss": 5.9818,
|
|
"mean_token_accuracy": 0.15032537877559662,
|
|
"num_tokens": 17994615.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.22483377456665,
|
|
"epoch": 0.7764572227562702,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004946563300988699,
|
|
"loss": 6.0309,
|
|
"mean_token_accuracy": 0.1406807705760002,
|
|
"num_tokens": 18004727.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.251943349838257,
|
|
"epoch": 0.776894171108975,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004946495770828482,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.13911537006497382,
|
|
"num_tokens": 18014576.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.256908798217774,
|
|
"epoch": 0.7773311194616797,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004946428198538326,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.14529479444026946,
|
|
"num_tokens": 18024709.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.234633207321167,
|
|
"epoch": 0.7777680678143843,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004946360584119526,
|
|
"loss": 6.0003,
|
|
"mean_token_accuracy": 0.14170599430799485,
|
|
"num_tokens": 18034673.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.235233211517334,
|
|
"epoch": 0.778205016167089,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000494629292757338,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.14689105078577996,
|
|
"num_tokens": 18044774.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.176680564880371,
|
|
"epoch": 0.7786419645197937,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004946225228901184,
|
|
"loss": 6.0145,
|
|
"mean_token_accuracy": 0.14234003871679307,
|
|
"num_tokens": 18055244.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.275831079483032,
|
|
"epoch": 0.7790789128724984,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004946157488104236,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.13471165522933007,
|
|
"num_tokens": 18066051.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.3291338920593265,
|
|
"epoch": 0.7795158612252032,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004946089705183839,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.1323649190366268,
|
|
"num_tokens": 18077693.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.2520617008209225,
|
|
"epoch": 0.7799528095779079,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004946021880141289,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.1427716851234436,
|
|
"num_tokens": 18088032.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.197879409790039,
|
|
"epoch": 0.7803897579306126,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000494595401297789,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.1420186921954155,
|
|
"num_tokens": 18097998.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.204164600372314,
|
|
"epoch": 0.7808267062833173,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004945886103694941,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.1460868537425995,
|
|
"num_tokens": 18107538.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.201864337921142,
|
|
"epoch": 0.781263654636022,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004945818152293747,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.1413077510893345,
|
|
"num_tokens": 18117792.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.282734966278076,
|
|
"epoch": 0.7817006029887267,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004945750158775609,
|
|
"loss": 6.085,
|
|
"mean_token_accuracy": 0.14083878919482232,
|
|
"num_tokens": 18128005.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.255158472061157,
|
|
"epoch": 0.7821375513414315,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004945682123141833,
|
|
"loss": 6.0458,
|
|
"mean_token_accuracy": 0.15105608999729156,
|
|
"num_tokens": 18138398.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.29579725265503,
|
|
"epoch": 0.7825744996941362,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004945614045393724,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.1422487013041973,
|
|
"num_tokens": 18147676.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.122381496429443,
|
|
"epoch": 0.7830114480468409,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004945545925532587,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.15262250900268554,
|
|
"num_tokens": 18156842.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.136346292495728,
|
|
"epoch": 0.7834483963995456,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004945477763559728,
|
|
"loss": 6.046,
|
|
"mean_token_accuracy": 0.14279976412653922,
|
|
"num_tokens": 18166902.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.245600891113281,
|
|
"epoch": 0.7838853447522502,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004945409559476455,
|
|
"loss": 6.033,
|
|
"mean_token_accuracy": 0.146183517575264,
|
|
"num_tokens": 18177561.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.1954508304595945,
|
|
"epoch": 0.784322293104955,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004945341313284077,
|
|
"loss": 6.0179,
|
|
"mean_token_accuracy": 0.14810565561056138,
|
|
"num_tokens": 18187739.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.176522874832154,
|
|
"epoch": 0.7847592414576597,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004945273024983902,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.15180836766958236,
|
|
"num_tokens": 18198435.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.29358811378479,
|
|
"epoch": 0.7851961898103644,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.000494520469457724,
|
|
"loss": 5.9838,
|
|
"mean_token_accuracy": 0.14602330476045608,
|
|
"num_tokens": 18208374.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.118836355209351,
|
|
"epoch": 0.7856331381630691,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004945136322065402,
|
|
"loss": 6.0569,
|
|
"mean_token_accuracy": 0.15092428624629975,
|
|
"num_tokens": 18219229.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.1668847560882565,
|
|
"epoch": 0.7860700865157738,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004945067907449699,
|
|
"loss": 6.0319,
|
|
"mean_token_accuracy": 0.14282664731144906,
|
|
"num_tokens": 18229208.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.2895505905151365,
|
|
"epoch": 0.7865070348684785,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004944999450731442,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.13042119517922401,
|
|
"num_tokens": 18238454.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7865070348684785,
|
|
"eval_entropy": 6.187632340912894,
|
|
"eval_loss": 6.064093112945557,
|
|
"eval_mean_token_accuracy": 0.14895293781437627,
|
|
"eval_num_tokens": 18238454.0,
|
|
"eval_runtime": 28.2519,
|
|
"eval_samples_per_second": 1310.142,
|
|
"eval_steps_per_second": 163.777,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 6.350997018814087,
|
|
"epoch": 0.7869439832211833,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004944930951911947,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.14062996804714203,
|
|
"num_tokens": 18248845.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 6.235470581054687,
|
|
"epoch": 0.787380931573888,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004944862410992526,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.14461514875292777,
|
|
"num_tokens": 18258912.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 6.23782057762146,
|
|
"epoch": 0.7878178799265927,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004944793827974494,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.13982785046100615,
|
|
"num_tokens": 18269330.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 6.270591497421265,
|
|
"epoch": 0.7882548282792974,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004944725202859165,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.13964123651385307,
|
|
"num_tokens": 18279721.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 6.158119153976441,
|
|
"epoch": 0.7886917766320021,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004944656535647858,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.1489733189344406,
|
|
"num_tokens": 18288581.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 6.190168857574463,
|
|
"epoch": 0.7891287249847068,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004944587826341888,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.1436466746032238,
|
|
"num_tokens": 18298179.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 6.253784799575806,
|
|
"epoch": 0.7895656733374116,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004944519074942574,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.14425861164927484,
|
|
"num_tokens": 18307957.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 6.126337194442749,
|
|
"epoch": 0.7900026216901163,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004944450281451234,
|
|
"loss": 6.0161,
|
|
"mean_token_accuracy": 0.13894797191023828,
|
|
"num_tokens": 18317799.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 6.242519569396973,
|
|
"epoch": 0.790439570042821,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004944381445869188,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.14522837102413177,
|
|
"num_tokens": 18327889.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 6.252655553817749,
|
|
"epoch": 0.7908765183955256,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004944312568197756,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.1454584777355194,
|
|
"num_tokens": 18338288.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 6.218295621871948,
|
|
"epoch": 0.7913134667482303,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004944243648438258,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.13389210775494576,
|
|
"num_tokens": 18349070.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 6.296699571609497,
|
|
"epoch": 0.791750415100935,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004944174686592019,
|
|
"loss": 6.0069,
|
|
"mean_token_accuracy": 0.14725763127207755,
|
|
"num_tokens": 18359683.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 6.2603308200836185,
|
|
"epoch": 0.7921873634536398,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004944105682660358,
|
|
"loss": 6.0214,
|
|
"mean_token_accuracy": 0.14442202001810073,
|
|
"num_tokens": 18371355.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 6.131388235092163,
|
|
"epoch": 0.7926243118063445,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004944036636644601,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.1461861990392208,
|
|
"num_tokens": 18381591.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 6.1675091743469235,
|
|
"epoch": 0.7930612601590492,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004943967548546071,
|
|
"loss": 6.006,
|
|
"mean_token_accuracy": 0.1439528949558735,
|
|
"num_tokens": 18390760.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 6.254599571228027,
|
|
"epoch": 0.7934982085117539,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004943898418366096,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.14123787581920624,
|
|
"num_tokens": 18400643.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 6.274891138076782,
|
|
"epoch": 0.7939351568644586,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004943829246105997,
|
|
"loss": 6.0899,
|
|
"mean_token_accuracy": 0.1439736530184746,
|
|
"num_tokens": 18411559.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 6.235226821899414,
|
|
"epoch": 0.7943721052171633,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004943760031767106,
|
|
"loss": 6.0753,
|
|
"mean_token_accuracy": 0.1427392303943634,
|
|
"num_tokens": 18422645.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 6.25205397605896,
|
|
"epoch": 0.7948090535698681,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004943690775350746,
|
|
"loss": 6.0323,
|
|
"mean_token_accuracy": 0.14323223605751992,
|
|
"num_tokens": 18432369.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 6.2375733852386475,
|
|
"epoch": 0.7952460019225728,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004943621476858249,
|
|
"loss": 6.0085,
|
|
"mean_token_accuracy": 0.14254568815231322,
|
|
"num_tokens": 18442143.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 6.159643507003784,
|
|
"epoch": 0.7956829502752775,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004943552136290942,
|
|
"loss": 6.0468,
|
|
"mean_token_accuracy": 0.14481618478894234,
|
|
"num_tokens": 18452161.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 6.264166975021363,
|
|
"epoch": 0.7961198986279822,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004943482753650154,
|
|
"loss": 6.1266,
|
|
"mean_token_accuracy": 0.13852701485157012,
|
|
"num_tokens": 18461873.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 6.3209999084472654,
|
|
"epoch": 0.7965568469806869,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004943413328937221,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.14282170534133912,
|
|
"num_tokens": 18472584.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 6.239671850204468,
|
|
"epoch": 0.7969937953333915,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004943343862153467,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.14517282769083978,
|
|
"num_tokens": 18482174.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 6.217202758789062,
|
|
"epoch": 0.7974307436860963,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004943274353300231,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.1405440501868725,
|
|
"num_tokens": 18492861.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 6.25796537399292,
|
|
"epoch": 0.797867692038801,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004943204802378843,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.1437128081917763,
|
|
"num_tokens": 18502830.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 6.285251092910767,
|
|
"epoch": 0.7983046403915057,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004943135209390638,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.14276544004678726,
|
|
"num_tokens": 18513063.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 6.174069166183472,
|
|
"epoch": 0.7987415887442104,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004943065574336949,
|
|
"loss": 6.0217,
|
|
"mean_token_accuracy": 0.14521622508764268,
|
|
"num_tokens": 18523773.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 6.205516242980957,
|
|
"epoch": 0.7991785370969151,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004942995897219115,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.14667071476578714,
|
|
"num_tokens": 18533101.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 6.2843996524810795,
|
|
"epoch": 0.7996154854496198,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004942926178038469,
|
|
"loss": 6.0592,
|
|
"mean_token_accuracy": 0.14422493949532508,
|
|
"num_tokens": 18543863.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 6.172523546218872,
|
|
"epoch": 0.8000524338023246,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004942856416796352,
|
|
"loss": 6.0283,
|
|
"mean_token_accuracy": 0.1453754872083664,
|
|
"num_tokens": 18554249.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 6.226995134353638,
|
|
"epoch": 0.8004893821550293,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004942786613494098,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.13995733261108398,
|
|
"num_tokens": 18563525.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 6.261930751800537,
|
|
"epoch": 0.800926330507734,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004942716768133048,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.14677432626485826,
|
|
"num_tokens": 18572734.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 6.1590970993042,
|
|
"epoch": 0.8013632788604387,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004942646880714543,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.14118833616375923,
|
|
"num_tokens": 18581939.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 6.216191101074219,
|
|
"epoch": 0.8018002272131434,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000494257695123992,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.1449749894440174,
|
|
"num_tokens": 18591635.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 6.228406238555908,
|
|
"epoch": 0.8022371755658482,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.0004942506979710524,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.14958217293024062,
|
|
"num_tokens": 18602060.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 6.229957485198975,
|
|
"epoch": 0.8026741239185529,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004942436966127693,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.14447982758283615,
|
|
"num_tokens": 18611187.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 6.2823692798614506,
|
|
"epoch": 0.8031110722712576,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004942366910492775,
|
|
"loss": 5.9782,
|
|
"mean_token_accuracy": 0.1483898475766182,
|
|
"num_tokens": 18620329.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 6.275428104400635,
|
|
"epoch": 0.8035480206239622,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004942296812807109,
|
|
"loss": 6.0349,
|
|
"mean_token_accuracy": 0.14326571002602578,
|
|
"num_tokens": 18629600.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 6.196285676956177,
|
|
"epoch": 0.8039849689766669,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004942226673072041,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.14189935475587845,
|
|
"num_tokens": 18640771.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 6.146600818634033,
|
|
"epoch": 0.8044219173293716,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004942156491288917,
|
|
"loss": 5.9999,
|
|
"mean_token_accuracy": 0.1470084510743618,
|
|
"num_tokens": 18650606.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 6.216950178146362,
|
|
"epoch": 0.8048588656820764,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004942086267459083,
|
|
"loss": 6.0328,
|
|
"mean_token_accuracy": 0.14324128851294518,
|
|
"num_tokens": 18660487.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 6.258160352706909,
|
|
"epoch": 0.8052958140347811,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004942016001583886,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.14204690083861352,
|
|
"num_tokens": 18670987.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 6.230315351486206,
|
|
"epoch": 0.8057327623874858,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004941945693664674,
|
|
"loss": 6.103,
|
|
"mean_token_accuracy": 0.13973608016967773,
|
|
"num_tokens": 18682560.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 6.223834896087647,
|
|
"epoch": 0.8061697107401905,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004941875343702795,
|
|
"loss": 6.0555,
|
|
"mean_token_accuracy": 0.14226875007152556,
|
|
"num_tokens": 18692743.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 6.241143035888672,
|
|
"epoch": 0.8066066590928952,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004941804951699597,
|
|
"loss": 5.9943,
|
|
"mean_token_accuracy": 0.1508474126458168,
|
|
"num_tokens": 18703039.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 6.186641025543213,
|
|
"epoch": 0.8070436074455999,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004941734517656432,
|
|
"loss": 6.0682,
|
|
"mean_token_accuracy": 0.14369699433445932,
|
|
"num_tokens": 18713777.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 6.199865484237671,
|
|
"epoch": 0.8074805557983047,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004941664041574651,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.14116380661725997,
|
|
"num_tokens": 18723422.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 6.224121236801148,
|
|
"epoch": 0.8079175041510094,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004941593523455605,
|
|
"loss": 6.0183,
|
|
"mean_token_accuracy": 0.14372921362519264,
|
|
"num_tokens": 18734369.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 6.283028888702392,
|
|
"epoch": 0.8083544525037141,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004941522963300647,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.1408497080206871,
|
|
"num_tokens": 18744647.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 6.2740415096282955,
|
|
"epoch": 0.8087914008564188,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000494145236111113,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.1435216970741749,
|
|
"num_tokens": 18753929.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 6.268417692184448,
|
|
"epoch": 0.8092283492091235,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004941381716888409,
|
|
"loss": 6.0357,
|
|
"mean_token_accuracy": 0.14020807147026063,
|
|
"num_tokens": 18764103.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 6.180013179779053,
|
|
"epoch": 0.8096652975618281,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004941311030633838,
|
|
"loss": 6.0622,
|
|
"mean_token_accuracy": 0.13822172060608864,
|
|
"num_tokens": 18773756.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 6.218051147460938,
|
|
"epoch": 0.810102245914533,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004941240302348773,
|
|
"loss": 5.9285,
|
|
"mean_token_accuracy": 0.15631069988012314,
|
|
"num_tokens": 18783778.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 6.228174448013306,
|
|
"epoch": 0.8105391942672376,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004941169532034571,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.14282265678048134,
|
|
"num_tokens": 18794664.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 6.157448863983154,
|
|
"epoch": 0.8109761426199423,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004941098719692589,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.14017972275614737,
|
|
"num_tokens": 18803773.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 6.194372272491455,
|
|
"epoch": 0.811413090972647,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004941027865324186,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.13763938322663308,
|
|
"num_tokens": 18814419.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 6.257919836044311,
|
|
"epoch": 0.8118500393253517,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.000494095696893072,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.13992701172828675,
|
|
"num_tokens": 18825011.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 6.247425651550293,
|
|
"epoch": 0.8122869876780564,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004940886030513551,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.14393307715654374,
|
|
"num_tokens": 18835003.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 6.23016505241394,
|
|
"epoch": 0.8127239360307612,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004940815050074041,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.1394846647977829,
|
|
"num_tokens": 18845072.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 6.238551139831543,
|
|
"epoch": 0.8131608843834659,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004940744027613549,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.14630599319934845,
|
|
"num_tokens": 18854583.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 6.161306428909302,
|
|
"epoch": 0.8135978327361706,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004940672963133439,
|
|
"loss": 6.07,
|
|
"mean_token_accuracy": 0.14326853901147843,
|
|
"num_tokens": 18865460.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 6.258480882644653,
|
|
"epoch": 0.8140347810888753,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004940601856635074,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.14527803659439087,
|
|
"num_tokens": 18875568.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 6.162207841873169,
|
|
"epoch": 0.81447172944158,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004940530708119818,
|
|
"loss": 5.9447,
|
|
"mean_token_accuracy": 0.1445034012198448,
|
|
"num_tokens": 18884894.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 6.137970972061157,
|
|
"epoch": 0.8149086777942847,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004940459517589034,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.1465800143778324,
|
|
"num_tokens": 18895353.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 6.2135459899902346,
|
|
"epoch": 0.8153456261469895,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.000494038828504409,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.1466113120317459,
|
|
"num_tokens": 18905474.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 6.271397686004638,
|
|
"epoch": 0.8157825744996942,
|
|
"grad_norm": 5.1875,
|
|
"learning_rate": 0.0004940317010486351,
|
|
"loss": 6.0089,
|
|
"mean_token_accuracy": 0.1458955377340317,
|
|
"num_tokens": 18914797.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 6.237304162979126,
|
|
"epoch": 0.8162195228523988,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004940245693917183,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.13753879815340042,
|
|
"num_tokens": 18924642.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 6.144796895980835,
|
|
"epoch": 0.8166564712051035,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004940174335337955,
|
|
"loss": 5.9325,
|
|
"mean_token_accuracy": 0.1523873269557953,
|
|
"num_tokens": 18934026.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 6.215007543563843,
|
|
"epoch": 0.8170934195578082,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004940102934750037,
|
|
"loss": 5.971,
|
|
"mean_token_accuracy": 0.1510114438831806,
|
|
"num_tokens": 18943262.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 6.272810459136963,
|
|
"epoch": 0.8175303679105129,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004940031492154795,
|
|
"loss": 5.9926,
|
|
"mean_token_accuracy": 0.13940275311470032,
|
|
"num_tokens": 18953082.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 6.2077549457550045,
|
|
"epoch": 0.8179673162632177,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004939960007553603,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.14470342099666594,
|
|
"num_tokens": 18962408.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 6.201269245147705,
|
|
"epoch": 0.8184042646159224,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000493988848094783,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.1364889159798622,
|
|
"num_tokens": 18972918.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 6.190881776809692,
|
|
"epoch": 0.8188412129686271,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004939816912338848,
|
|
"loss": 6.0251,
|
|
"mean_token_accuracy": 0.14143316373229026,
|
|
"num_tokens": 18983152.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 6.224991512298584,
|
|
"epoch": 0.8192781613213318,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004939745301728031,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.14381223320960998,
|
|
"num_tokens": 18993613.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 6.210654783248901,
|
|
"epoch": 0.8197151096740365,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004939673649116752,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.14649604260921478,
|
|
"num_tokens": 19004079.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 6.203503894805908,
|
|
"epoch": 0.8201520580267413,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004939601954506383,
|
|
"loss": 6.12,
|
|
"mean_token_accuracy": 0.1403985969722271,
|
|
"num_tokens": 19013994.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 6.2642467498779295,
|
|
"epoch": 0.820589006379446,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004939530217898303,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.1376613236963749,
|
|
"num_tokens": 19024674.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 6.233977746963501,
|
|
"epoch": 0.8210259547321507,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004939458439293886,
|
|
"loss": 6.0544,
|
|
"mean_token_accuracy": 0.13939779102802277,
|
|
"num_tokens": 19035333.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 6.3187164783477785,
|
|
"epoch": 0.8214629030848554,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004939386618694508,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.13914038836956025,
|
|
"num_tokens": 19046279.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 6.2559949398040775,
|
|
"epoch": 0.8218998514375601,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004939314756101547,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.13177771270275115,
|
|
"num_tokens": 19056506.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 6.215059089660644,
|
|
"epoch": 0.8223367997902647,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004939242851516384,
|
|
"loss": 6.0352,
|
|
"mean_token_accuracy": 0.14404356777667998,
|
|
"num_tokens": 19067217.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 6.203421640396118,
|
|
"epoch": 0.8227737481429696,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004939170904940395,
|
|
"loss": 6.0983,
|
|
"mean_token_accuracy": 0.13966502249240875,
|
|
"num_tokens": 19079028.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 6.177074670791626,
|
|
"epoch": 0.8232106964956742,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000493909891637496,
|
|
"loss": 6.0491,
|
|
"mean_token_accuracy": 0.14438274502754211,
|
|
"num_tokens": 19088236.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 6.2156205654144285,
|
|
"epoch": 0.8236476448483789,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004939026885821461,
|
|
"loss": 6.0242,
|
|
"mean_token_accuracy": 0.15105926394462585,
|
|
"num_tokens": 19099598.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 6.225408506393433,
|
|
"epoch": 0.8240845932010836,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000493895481328128,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.14559734389185905,
|
|
"num_tokens": 19110347.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 6.331104803085327,
|
|
"epoch": 0.8245215415537883,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004938882698755798,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.14259000048041343,
|
|
"num_tokens": 19120643.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 6.1864618301391605,
|
|
"epoch": 0.824958489906493,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.00049388105422464,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.14517145678400994,
|
|
"num_tokens": 19130209.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 6.147251749038697,
|
|
"epoch": 0.8253954382591978,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004938738343754467,
|
|
"loss": 5.9695,
|
|
"mean_token_accuracy": 0.1517564684152603,
|
|
"num_tokens": 19139196.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 6.221241903305054,
|
|
"epoch": 0.8258323866119025,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004938666103281389,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.14541823118925096,
|
|
"num_tokens": 19149618.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 6.258189678192139,
|
|
"epoch": 0.8262693349646072,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004938593820828545,
|
|
"loss": 6.0046,
|
|
"mean_token_accuracy": 0.13990169763565063,
|
|
"num_tokens": 19159875.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 6.221347332000732,
|
|
"epoch": 0.8267062833173119,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004938521496397326,
|
|
"loss": 6.0374,
|
|
"mean_token_accuracy": 0.14358133673667908,
|
|
"num_tokens": 19170403.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 6.250455045700074,
|
|
"epoch": 0.8271432316700166,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004938449129989117,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.15078073218464852,
|
|
"num_tokens": 19181187.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 6.222884702682495,
|
|
"epoch": 0.8275801800227213,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004938376721605308,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.1423380881547928,
|
|
"num_tokens": 19191328.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 6.144410610198975,
|
|
"epoch": 0.8280171283754261,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004938304271247286,
|
|
"loss": 6.0199,
|
|
"mean_token_accuracy": 0.14642967134714127,
|
|
"num_tokens": 19202041.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 6.253562498092651,
|
|
"epoch": 0.8284540767281308,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004938231778916442,
|
|
"loss": 6.0017,
|
|
"mean_token_accuracy": 0.14358637407422065,
|
|
"num_tokens": 19212016.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 6.250165224075317,
|
|
"epoch": 0.8288910250808355,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004938159244614167,
|
|
"loss": 6.0103,
|
|
"mean_token_accuracy": 0.14502643197774887,
|
|
"num_tokens": 19222111.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 6.282345104217529,
|
|
"epoch": 0.8293279734335401,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004938086668341849,
|
|
"loss": 6.0019,
|
|
"mean_token_accuracy": 0.1438644751906395,
|
|
"num_tokens": 19231865.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 6.206636810302735,
|
|
"epoch": 0.8297649217862448,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004938014050100884,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.1493251107633114,
|
|
"num_tokens": 19242993.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 6.232339715957641,
|
|
"epoch": 0.8302018701389495,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004937941389892662,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.14360441714525224,
|
|
"num_tokens": 19252776.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 6.186702013015747,
|
|
"epoch": 0.8306388184916543,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004937868687718577,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.1452575981616974,
|
|
"num_tokens": 19263022.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 6.231074666976928,
|
|
"epoch": 0.831075766844359,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004937795943580026,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.14902030676603317,
|
|
"num_tokens": 19271859.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 6.201964712142944,
|
|
"epoch": 0.8315127151970637,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00049377231574784,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.14588339105248452,
|
|
"num_tokens": 19282771.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 6.124718809127808,
|
|
"epoch": 0.8319496635497684,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004937650329415099,
|
|
"loss": 6.0148,
|
|
"mean_token_accuracy": 0.13867617696523665,
|
|
"num_tokens": 19292985.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 6.162050247192383,
|
|
"epoch": 0.8323866119024731,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004937577459391519,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.14593885689973832,
|
|
"num_tokens": 19303409.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 6.232680320739746,
|
|
"epoch": 0.8328235602551778,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004937504547409056,
|
|
"loss": 6.0148,
|
|
"mean_token_accuracy": 0.1468958795070648,
|
|
"num_tokens": 19312632.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 6.1946220874786375,
|
|
"epoch": 0.8332605086078826,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004937431593469109,
|
|
"loss": 5.9211,
|
|
"mean_token_accuracy": 0.1472806453704834,
|
|
"num_tokens": 19322759.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 6.196166229248047,
|
|
"epoch": 0.8336974569605873,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004937358597573079,
|
|
"loss": 5.953,
|
|
"mean_token_accuracy": 0.15301361829042434,
|
|
"num_tokens": 19333307.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 6.186828327178955,
|
|
"epoch": 0.834134405313292,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004937285559722364,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.14334636330604553,
|
|
"num_tokens": 19342528.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 6.26044807434082,
|
|
"epoch": 0.8345713536659967,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004937212479918367,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.14196290001273154,
|
|
"num_tokens": 19352640.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 6.267553424835205,
|
|
"epoch": 0.8350083020187014,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004937139358162488,
|
|
"loss": 6.0214,
|
|
"mean_token_accuracy": 0.14564134776592255,
|
|
"num_tokens": 19363285.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 6.223315048217773,
|
|
"epoch": 0.835445250371406,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000493706619445613,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.1506032481789589,
|
|
"num_tokens": 19373141.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 6.200173187255859,
|
|
"epoch": 0.8358821987241108,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004936992988800697,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.14346984699368476,
|
|
"num_tokens": 19383091.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 6.221242427825928,
|
|
"epoch": 0.8363191470768155,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004936919741197591,
|
|
"loss": 5.9847,
|
|
"mean_token_accuracy": 0.14986307099461554,
|
|
"num_tokens": 19393163.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 6.148035335540771,
|
|
"epoch": 0.8367560954295202,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004936846451648219,
|
|
"loss": 5.9673,
|
|
"mean_token_accuracy": 0.15079953372478486,
|
|
"num_tokens": 19403475.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 6.1440918922424315,
|
|
"epoch": 0.8371930437822249,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004936773120153987,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.14774260222911834,
|
|
"num_tokens": 19413302.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 6.21998872756958,
|
|
"epoch": 0.8376299921349296,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00049366997467163,
|
|
"loss": 5.9797,
|
|
"mean_token_accuracy": 0.14915448427200317,
|
|
"num_tokens": 19423473.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 6.251493215560913,
|
|
"epoch": 0.8380669404876344,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004936626331336567,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.1349373109638691,
|
|
"num_tokens": 19433289.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 6.26294207572937,
|
|
"epoch": 0.8385038888403391,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004936552874016194,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.14192093834280967,
|
|
"num_tokens": 19442188.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 6.2142900943756105,
|
|
"epoch": 0.8389408371930438,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004936479374756592,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.14174751862883567,
|
|
"num_tokens": 19452971.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 6.275484418869018,
|
|
"epoch": 0.8393777855457485,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004936405833559169,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.1378170482814312,
|
|
"num_tokens": 19463263.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 6.3095964908599855,
|
|
"epoch": 0.8398147338984532,
|
|
"grad_norm": 7.28125,
|
|
"learning_rate": 0.0004936332250425337,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.13926204591989516,
|
|
"num_tokens": 19473234.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 6.218443155288696,
|
|
"epoch": 0.8402516822511579,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004936258625356507,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.140377489477396,
|
|
"num_tokens": 19483714.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 6.155925655364991,
|
|
"epoch": 0.8406886306038627,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004936184958354091,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.15539525002241134,
|
|
"num_tokens": 19493128.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 6.25476565361023,
|
|
"epoch": 0.8411255789565674,
|
|
"grad_norm": 5.8125,
|
|
"learning_rate": 0.00049361112494195,
|
|
"loss": 6.0713,
|
|
"mean_token_accuracy": 0.13749251365661622,
|
|
"num_tokens": 19503401.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 6.254153394699097,
|
|
"epoch": 0.8415625273092721,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004936037498554153,
|
|
"loss": 6.1115,
|
|
"mean_token_accuracy": 0.14547596126794815,
|
|
"num_tokens": 19513050.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 6.232684087753296,
|
|
"epoch": 0.8419994756619767,
|
|
"grad_norm": 5.90625,
|
|
"learning_rate": 0.000493596370575946,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.14650416597723961,
|
|
"num_tokens": 19524534.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 6.22262659072876,
|
|
"epoch": 0.8424364240146814,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004935889871036837,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.14624593481421472,
|
|
"num_tokens": 19534863.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 6.256587171554566,
|
|
"epoch": 0.8428733723673861,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004935815994387701,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.13790009617805482,
|
|
"num_tokens": 19545037.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 6.228785419464112,
|
|
"epoch": 0.8433103207200909,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000493574207581347,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.1383309245109558,
|
|
"num_tokens": 19555377.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 6.237904119491577,
|
|
"epoch": 0.8437472690727956,
|
|
"grad_norm": 7.59375,
|
|
"learning_rate": 0.0004935668115315559,
|
|
"loss": 6.054,
|
|
"mean_token_accuracy": 0.14487089663743974,
|
|
"num_tokens": 19565874.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 6.134960556030274,
|
|
"epoch": 0.8441842174255003,
|
|
"grad_norm": 6.0625,
|
|
"learning_rate": 0.000493559411289539,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.16119038313627243,
|
|
"num_tokens": 19575002.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 6.1698222160339355,
|
|
"epoch": 0.844621165778205,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000493552006855438,
|
|
"loss": 6.0118,
|
|
"mean_token_accuracy": 0.14253657013177873,
|
|
"num_tokens": 19585863.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 6.21726803779602,
|
|
"epoch": 0.8450581141309097,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004935445982293949,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.14346363991498948,
|
|
"num_tokens": 19596787.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 6.225195360183716,
|
|
"epoch": 0.8454950624836144,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004935371854115519,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.1384153299033642,
|
|
"num_tokens": 19607114.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 6.18015570640564,
|
|
"epoch": 0.8459320108363192,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004935297684020513,
|
|
"loss": 5.9584,
|
|
"mean_token_accuracy": 0.15262675136327744,
|
|
"num_tokens": 19617334.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 6.248830986022949,
|
|
"epoch": 0.8463689591890239,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004935223472010352,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.1399633213877678,
|
|
"num_tokens": 19626844.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 6.182112073898315,
|
|
"epoch": 0.8468059075417286,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004935149218086459,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.14446952790021897,
|
|
"num_tokens": 19637897.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 6.254135274887085,
|
|
"epoch": 0.8472428558944333,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000493507492225026,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.14066995829343795,
|
|
"num_tokens": 19649161.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 6.2464367866516115,
|
|
"epoch": 0.847679804247138,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004935000584503178,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.14391484782099723,
|
|
"num_tokens": 19659328.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 6.223616981506348,
|
|
"epoch": 0.8481167525998426,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004934926204846641,
|
|
"loss": 6.1117,
|
|
"mean_token_accuracy": 0.13933897837996484,
|
|
"num_tokens": 19669196.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 6.22830605506897,
|
|
"epoch": 0.8485537009525475,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004934851783282073,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.14183563366532326,
|
|
"num_tokens": 19680019.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 6.22342882156372,
|
|
"epoch": 0.8489906493052521,
|
|
"grad_norm": 4.84375,
|
|
"learning_rate": 0.0004934777319810904,
|
|
"loss": 6.0892,
|
|
"mean_token_accuracy": 0.14166997671127318,
|
|
"num_tokens": 19689391.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 6.262296199798584,
|
|
"epoch": 0.8494275976579568,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004934702814434561,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.13788991197943687,
|
|
"num_tokens": 19699683.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 6.2552093982696535,
|
|
"epoch": 0.8498645460106615,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004934628267154474,
|
|
"loss": 6.1293,
|
|
"mean_token_accuracy": 0.13570168763399124,
|
|
"num_tokens": 19709844.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 6.20659909248352,
|
|
"epoch": 0.8503014943633662,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.000493455367797207,
|
|
"loss": 6.0774,
|
|
"mean_token_accuracy": 0.13346961587667466,
|
|
"num_tokens": 19719926.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 6.262333250045776,
|
|
"epoch": 0.8507384427160709,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004934479046888784,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.1410963289439678,
|
|
"num_tokens": 19730548.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 6.256011199951172,
|
|
"epoch": 0.8511753910687757,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004934404373906045,
|
|
"loss": 6.0637,
|
|
"mean_token_accuracy": 0.14503197818994523,
|
|
"num_tokens": 19740471.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 6.264379692077637,
|
|
"epoch": 0.8516123394214804,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004934329659025283,
|
|
"loss": 5.9762,
|
|
"mean_token_accuracy": 0.14722604900598527,
|
|
"num_tokens": 19749395.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 6.226193284988403,
|
|
"epoch": 0.8520492877741851,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004934254902247936,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.1382533073425293,
|
|
"num_tokens": 19759203.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 6.239722824096679,
|
|
"epoch": 0.8524862361268898,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004934180103575436,
|
|
"loss": 5.961,
|
|
"mean_token_accuracy": 0.15295470356941224,
|
|
"num_tokens": 19768977.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 6.192998743057251,
|
|
"epoch": 0.8529231844795945,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004934105263009216,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.15048784539103507,
|
|
"num_tokens": 19778569.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 6.207692241668701,
|
|
"epoch": 0.8533601328322992,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004934030380550713,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.14660714119672774,
|
|
"num_tokens": 19787939.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 6.21990385055542,
|
|
"epoch": 0.853797081185004,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004933955456201362,
|
|
"loss": 6.0355,
|
|
"mean_token_accuracy": 0.14408317506313323,
|
|
"num_tokens": 19798407.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 6.271046352386475,
|
|
"epoch": 0.8542340295377087,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004933880489962602,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.1449744649231434,
|
|
"num_tokens": 19808495.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 6.225653457641601,
|
|
"epoch": 0.8546709778904134,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004933805481835868,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.14210559278726578,
|
|
"num_tokens": 19818709.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 6.251949834823608,
|
|
"epoch": 0.855107926243118,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004933730431822603,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.14727669656276704,
|
|
"num_tokens": 19828865.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 6.201934719085694,
|
|
"epoch": 0.8555448745958227,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004933655339924243,
|
|
"loss": 5.9821,
|
|
"mean_token_accuracy": 0.1444874882698059,
|
|
"num_tokens": 19838757.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 6.1520508289337155,
|
|
"epoch": 0.8559818229485275,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000493358020614223,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.144384902715683,
|
|
"num_tokens": 19848967.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 6.252551889419555,
|
|
"epoch": 0.8564187713012322,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004933505030478003,
|
|
"loss": 6.0357,
|
|
"mean_token_accuracy": 0.1498258039355278,
|
|
"num_tokens": 19859487.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 6.249651098251343,
|
|
"epoch": 0.8568557196539369,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004933429812933005,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.14054232686758042,
|
|
"num_tokens": 19870170.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 6.206701469421387,
|
|
"epoch": 0.8572926680066416,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004933354553508681,
|
|
"loss": 5.9842,
|
|
"mean_token_accuracy": 0.14744419753551483,
|
|
"num_tokens": 19881031.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 6.246293687820435,
|
|
"epoch": 0.8577296163593463,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004933279252206472,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.14254553094506264,
|
|
"num_tokens": 19891082.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 6.248610782623291,
|
|
"epoch": 0.858166564712051,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004933203909027823,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.13794225379824637,
|
|
"num_tokens": 19900626.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 6.167263460159302,
|
|
"epoch": 0.8586035130647558,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004933128523974179,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.15036819577217103,
|
|
"num_tokens": 19910660.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 6.169804334640503,
|
|
"epoch": 0.8590404614174605,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004933053097046986,
|
|
"loss": 5.9964,
|
|
"mean_token_accuracy": 0.1429131418466568,
|
|
"num_tokens": 19920476.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 6.323930168151856,
|
|
"epoch": 0.8594774097701652,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000493297762824769,
|
|
"loss": 6.0961,
|
|
"mean_token_accuracy": 0.1377591110765934,
|
|
"num_tokens": 19931151.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 6.28590202331543,
|
|
"epoch": 0.8599143581228699,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000493290211757774,
|
|
"loss": 5.9989,
|
|
"mean_token_accuracy": 0.13884489238262177,
|
|
"num_tokens": 19942469.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 6.139708995819092,
|
|
"epoch": 0.8603513064755746,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004932826565038584,
|
|
"loss": 6.0772,
|
|
"mean_token_accuracy": 0.1426509328186512,
|
|
"num_tokens": 19953055.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 6.0895037174224855,
|
|
"epoch": 0.8607882548282793,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004932750970631669,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.14375355914235116,
|
|
"num_tokens": 19963944.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 6.2525804996490475,
|
|
"epoch": 0.8612252031809841,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004932675334358448,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.15010778605937958,
|
|
"num_tokens": 19973913.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 6.233993339538574,
|
|
"epoch": 0.8616621515336887,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000493259965622037,
|
|
"loss": 6.0215,
|
|
"mean_token_accuracy": 0.1483843058347702,
|
|
"num_tokens": 19984130.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 6.161510467529297,
|
|
"epoch": 0.8620990998863934,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004932523936218887,
|
|
"loss": 5.9519,
|
|
"mean_token_accuracy": 0.14606448411941528,
|
|
"num_tokens": 19993840.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 6.261183786392212,
|
|
"epoch": 0.8625360482390981,
|
|
"grad_norm": 10.375,
|
|
"learning_rate": 0.000493244817435545,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.137623693048954,
|
|
"num_tokens": 20004228.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 6.2544409275054935,
|
|
"epoch": 0.8629729965918028,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004932372370631515,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.1442359358072281,
|
|
"num_tokens": 20012620.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 6.1343893051147464,
|
|
"epoch": 0.8634099449445075,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004932296525048535,
|
|
"loss": 6.1106,
|
|
"mean_token_accuracy": 0.1413384832441807,
|
|
"num_tokens": 20022892.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 6.248836421966553,
|
|
"epoch": 0.8638468932972123,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004932220637607962,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.1510588899254799,
|
|
"num_tokens": 20032788.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 6.199680423736572,
|
|
"epoch": 0.864283841649917,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004932144708311256,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.14951885342597962,
|
|
"num_tokens": 20043176.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 6.144923543930053,
|
|
"epoch": 0.8647207900026217,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000493206873715987,
|
|
"loss": 6.0261,
|
|
"mean_token_accuracy": 0.1444010391831398,
|
|
"num_tokens": 20052298.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 6.224962568283081,
|
|
"epoch": 0.8651577383553264,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004931992724155262,
|
|
"loss": 6.008,
|
|
"mean_token_accuracy": 0.143085827678442,
|
|
"num_tokens": 20063163.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 6.309250116348267,
|
|
"epoch": 0.8655946867080311,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000493191666929889,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.1428293138742447,
|
|
"num_tokens": 20073644.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 6.244245195388794,
|
|
"epoch": 0.8660316350607358,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004931840572592214,
|
|
"loss": 5.9877,
|
|
"mean_token_accuracy": 0.14725518748164176,
|
|
"num_tokens": 20084457.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 6.120822286605835,
|
|
"epoch": 0.8664685834134406,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004931764434036692,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.14560910165309907,
|
|
"num_tokens": 20094153.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 6.150817060470581,
|
|
"epoch": 0.8669055317661453,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004931688253633784,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.14018966257572174,
|
|
"num_tokens": 20104031.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 6.226406574249268,
|
|
"epoch": 0.86734248011885,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004931612031384953,
|
|
"loss": 6.0256,
|
|
"mean_token_accuracy": 0.14454981982707976,
|
|
"num_tokens": 20114431.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 6.150810289382934,
|
|
"epoch": 0.8677794284715546,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000493153576729166,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.1526732012629509,
|
|
"num_tokens": 20124161.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 6.182177495956421,
|
|
"epoch": 0.8682163768242593,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004931459461355368,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.14706914722919465,
|
|
"num_tokens": 20134227.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 6.215608930587768,
|
|
"epoch": 0.868653325176964,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004931383113577541,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.14292289167642594,
|
|
"num_tokens": 20143912.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 6.139667749404907,
|
|
"epoch": 0.8690902735296688,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004931306723959641,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.14590430483222008,
|
|
"num_tokens": 20153858.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 6.267096376419067,
|
|
"epoch": 0.8695272218823735,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004931230292503137,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.13928072899580002,
|
|
"num_tokens": 20164309.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 6.214211893081665,
|
|
"epoch": 0.8699641702350782,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004931153819209492,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.1478944942355156,
|
|
"num_tokens": 20173949.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 6.223191499710083,
|
|
"epoch": 0.8704011185877829,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004931077304080175,
|
|
"loss": 5.9925,
|
|
"mean_token_accuracy": 0.14299240857362747,
|
|
"num_tokens": 20184206.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 6.253048753738403,
|
|
"epoch": 0.8708380669404876,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004931000747116651,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.13737881183624268,
|
|
"num_tokens": 20194430.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 6.2516481399536135,
|
|
"epoch": 0.8712750152931923,
|
|
"grad_norm": 6.8125,
|
|
"learning_rate": 0.000493092414832039,
|
|
"loss": 6.0182,
|
|
"mean_token_accuracy": 0.14453519731760026,
|
|
"num_tokens": 20205004.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 6.221957063674926,
|
|
"epoch": 0.8717119636458971,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004930847507692862,
|
|
"loss": 5.9628,
|
|
"mean_token_accuracy": 0.14764900654554367,
|
|
"num_tokens": 20214698.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 6.22438383102417,
|
|
"epoch": 0.8721489119986018,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004930770825235536,
|
|
"loss": 6.0505,
|
|
"mean_token_accuracy": 0.14198303520679473,
|
|
"num_tokens": 20226534.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 6.255250358581543,
|
|
"epoch": 0.8725858603513065,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004930694100949882,
|
|
"loss": 6.02,
|
|
"mean_token_accuracy": 0.14456572830677034,
|
|
"num_tokens": 20237414.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 6.179359436035156,
|
|
"epoch": 0.8730228087040112,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.0004930617334837373,
|
|
"loss": 5.8932,
|
|
"mean_token_accuracy": 0.14946675151586533,
|
|
"num_tokens": 20246948.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 6.218437337875367,
|
|
"epoch": 0.8734597570567159,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.000493054052689948,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.14085782393813134,
|
|
"num_tokens": 20257281.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 6.253528738021851,
|
|
"epoch": 0.8738967054094207,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004930463677137679,
|
|
"loss": 6.044,
|
|
"mean_token_accuracy": 0.14160678461194037,
|
|
"num_tokens": 20269041.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 6.248606109619141,
|
|
"epoch": 0.8743336537621254,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004930386785553441,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.13608923330903053,
|
|
"num_tokens": 20279688.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 6.159049129486084,
|
|
"epoch": 0.87477060211483,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004930309852148242,
|
|
"loss": 5.998,
|
|
"mean_token_accuracy": 0.1461903363466263,
|
|
"num_tokens": 20288913.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 6.21247410774231,
|
|
"epoch": 0.8752075504675347,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004930232876923558,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.14632102996110916,
|
|
"num_tokens": 20299009.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 6.23969349861145,
|
|
"epoch": 0.8756444988202394,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004930155859880865,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.13175813630223274,
|
|
"num_tokens": 20309478.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 6.240252161026001,
|
|
"epoch": 0.8760814471729441,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000493007880102164,
|
|
"loss": 6.0511,
|
|
"mean_token_accuracy": 0.1454978756606579,
|
|
"num_tokens": 20319451.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 6.232294225692749,
|
|
"epoch": 0.8765183955256489,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000493000170034736,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.1465945139527321,
|
|
"num_tokens": 20328497.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 6.127724742889404,
|
|
"epoch": 0.8769553438783536,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004929924557859507,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.15832905918359758,
|
|
"num_tokens": 20338584.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 6.156444787979126,
|
|
"epoch": 0.8773922922310583,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004929847373559557,
|
|
"loss": 5.9949,
|
|
"mean_token_accuracy": 0.145755597949028,
|
|
"num_tokens": 20348808.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 6.194709253311157,
|
|
"epoch": 0.877829240583763,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004929770147448992,
|
|
"loss": 5.9821,
|
|
"mean_token_accuracy": 0.15028578341007232,
|
|
"num_tokens": 20358301.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 6.242437314987183,
|
|
"epoch": 0.8782661889364677,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004929692879529295,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.14376169592142105,
|
|
"num_tokens": 20369032.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 6.257175779342651,
|
|
"epoch": 0.8787031372891724,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004929615569801946,
|
|
"loss": 6.0148,
|
|
"mean_token_accuracy": 0.14054974392056466,
|
|
"num_tokens": 20379101.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 6.165028858184814,
|
|
"epoch": 0.8791400856418772,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004929538218268428,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.14643891006708146,
|
|
"num_tokens": 20388864.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 6.246957397460937,
|
|
"epoch": 0.8795770339945819,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004929460824930226,
|
|
"loss": 6.1249,
|
|
"mean_token_accuracy": 0.13385197520256042,
|
|
"num_tokens": 20398402.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 6.1573272228240965,
|
|
"epoch": 0.8800139823472866,
|
|
"grad_norm": 6.6875,
|
|
"learning_rate": 0.0004929383389788821,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.14462155923247338,
|
|
"num_tokens": 20408209.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 6.194298601150512,
|
|
"epoch": 0.8804509306999913,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004929305912845703,
|
|
"loss": 6.0292,
|
|
"mean_token_accuracy": 0.14462321996688843,
|
|
"num_tokens": 20418117.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 6.2855524063110355,
|
|
"epoch": 0.8808878790526959,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004929228394102355,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.14158154129981995,
|
|
"num_tokens": 20428347.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 6.237124443054199,
|
|
"epoch": 0.8813248274054006,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004929150833560263,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.1424064613878727,
|
|
"num_tokens": 20437804.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 6.226949882507324,
|
|
"epoch": 0.8817617757581054,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004929073231220917,
|
|
"loss": 6.0289,
|
|
"mean_token_accuracy": 0.13792968541383743,
|
|
"num_tokens": 20447600.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 6.274075603485107,
|
|
"epoch": 0.8821987241108101,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004928995587085806,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.14034995287656785,
|
|
"num_tokens": 20458023.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 6.213431310653687,
|
|
"epoch": 0.8826356724635148,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004928917901156416,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.1537353515625,
|
|
"num_tokens": 20468195.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 6.16763710975647,
|
|
"epoch": 0.8830726208162195,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000492884017343424,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.1395591288805008,
|
|
"num_tokens": 20479250.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 6.253421497344971,
|
|
"epoch": 0.8835095691689242,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004928762403920767,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.14397843629121782,
|
|
"num_tokens": 20489587.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 6.253739929199218,
|
|
"epoch": 0.8839465175216289,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.000492868459261749,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.1451330915093422,
|
|
"num_tokens": 20499788.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 6.213185977935791,
|
|
"epoch": 0.8843834658743337,
|
|
"grad_norm": 4.90625,
|
|
"learning_rate": 0.00049286067395259,
|
|
"loss": 6.0309,
|
|
"mean_token_accuracy": 0.14450110420584678,
|
|
"num_tokens": 20509716.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 6.175362205505371,
|
|
"epoch": 0.8848204142270384,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004928528844647493,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.14676104336977006,
|
|
"num_tokens": 20519020.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 6.152131748199463,
|
|
"epoch": 0.8852573625797431,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000492845090798376,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.14153722375631334,
|
|
"num_tokens": 20528997.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 6.235318994522094,
|
|
"epoch": 0.8856943109324478,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004928372929536197,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.14579871967434882,
|
|
"num_tokens": 20538599.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 6.305400848388672,
|
|
"epoch": 0.8861312592851525,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004928294909306301,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.14578816890716553,
|
|
"num_tokens": 20547664.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 6.2061316013336185,
|
|
"epoch": 0.8865682076378572,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 0.0004928216847295565,
|
|
"loss": 6.0832,
|
|
"mean_token_accuracy": 0.14088777601718902,
|
|
"num_tokens": 20557860.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 6.1760553359985355,
|
|
"epoch": 0.887005155990562,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000492813874350549,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.14260354042053222,
|
|
"num_tokens": 20569003.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 6.226287126541138,
|
|
"epoch": 0.8874421043432666,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004928060597937573,
|
|
"loss": 6.0092,
|
|
"mean_token_accuracy": 0.14746515527367593,
|
|
"num_tokens": 20578402.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 6.222630262374878,
|
|
"epoch": 0.8878790526959713,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004927982410593312,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.14485912397503853,
|
|
"num_tokens": 20587874.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 6.263999652862549,
|
|
"epoch": 0.888316001048676,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004927904181474207,
|
|
"loss": 5.9561,
|
|
"mean_token_accuracy": 0.1467773661017418,
|
|
"num_tokens": 20597270.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 6.237065267562866,
|
|
"epoch": 0.8887529494013807,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004927825910581758,
|
|
"loss": 6.0517,
|
|
"mean_token_accuracy": 0.1435149371623993,
|
|
"num_tokens": 20607898.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 6.189601135253906,
|
|
"epoch": 0.8891898977540854,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004927747597917467,
|
|
"loss": 5.9449,
|
|
"mean_token_accuracy": 0.15103435814380645,
|
|
"num_tokens": 20617300.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 6.236210060119629,
|
|
"epoch": 0.8896268461067902,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004927669243482836,
|
|
"loss": 6.0624,
|
|
"mean_token_accuracy": 0.14391943737864493,
|
|
"num_tokens": 20626582.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 6.154780483245849,
|
|
"epoch": 0.8900637944594949,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004927590847279369,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.14631350710988045,
|
|
"num_tokens": 20635802.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 6.191054105758667,
|
|
"epoch": 0.8905007428121996,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004927512409308568,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.1469324618577957,
|
|
"num_tokens": 20646057.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 6.282738447189331,
|
|
"epoch": 0.8909376911649043,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004927433929571937,
|
|
"loss": 6.0941,
|
|
"mean_token_accuracy": 0.13414522036910057,
|
|
"num_tokens": 20656511.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 6.295567369461059,
|
|
"epoch": 0.891374639517609,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004927355408070982,
|
|
"loss": 6.0067,
|
|
"mean_token_accuracy": 0.1483195722103119,
|
|
"num_tokens": 20666479.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 6.2385200500488285,
|
|
"epoch": 0.8918115878703138,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004927276844807211,
|
|
"loss": 5.9471,
|
|
"mean_token_accuracy": 0.1456519827246666,
|
|
"num_tokens": 20676830.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 6.122660112380982,
|
|
"epoch": 0.8922485362230185,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004927198239782129,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.14475072771310807,
|
|
"num_tokens": 20687316.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 6.191984367370606,
|
|
"epoch": 0.8926854845757232,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004927119592997242,
|
|
"loss": 6.0709,
|
|
"mean_token_accuracy": 0.14245957657694816,
|
|
"num_tokens": 20697901.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 6.2576416492462155,
|
|
"epoch": 0.8931224329284279,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004927040904454062,
|
|
"loss": 5.9502,
|
|
"mean_token_accuracy": 0.15248084366321563,
|
|
"num_tokens": 20707468.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 6.195013809204101,
|
|
"epoch": 0.8935593812811325,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004926962174154097,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.14423225894570352,
|
|
"num_tokens": 20717098.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 6.233042621612549,
|
|
"epoch": 0.8939963296338372,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004926883402098857,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.13845815137028694,
|
|
"num_tokens": 20727217.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 6.220581674575806,
|
|
"epoch": 0.894433277986542,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004926804588289852,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.14081439152359962,
|
|
"num_tokens": 20737397.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 6.156305837631225,
|
|
"epoch": 0.8948702263392467,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004926725732728595,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.15089936554431915,
|
|
"num_tokens": 20746712.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 6.206583786010742,
|
|
"epoch": 0.8953071746919514,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004926646835416597,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.14401394873857498,
|
|
"num_tokens": 20757161.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 6.2091819763183596,
|
|
"epoch": 0.8957441230446561,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004926567896355372,
|
|
"loss": 5.9504,
|
|
"mean_token_accuracy": 0.15837636291980745,
|
|
"num_tokens": 20766478.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 6.1995820045471195,
|
|
"epoch": 0.8961810713973608,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004926488915546435,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.1455075055360794,
|
|
"num_tokens": 20776317.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 6.219730091094971,
|
|
"epoch": 0.8966180197500655,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00049264098929913,
|
|
"loss": 5.9286,
|
|
"mean_token_accuracy": 0.14915867894887924,
|
|
"num_tokens": 20786534.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 6.155456066131592,
|
|
"epoch": 0.8970549681027703,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004926330828691482,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.14729184210300444,
|
|
"num_tokens": 20796791.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 6.213042879104615,
|
|
"epoch": 0.897491916455475,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004926251722648499,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.14904457479715347,
|
|
"num_tokens": 20806834.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 6.143362188339234,
|
|
"epoch": 0.8979288648081797,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004926172574863868,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.1442363977432251,
|
|
"num_tokens": 20816664.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 6.176703071594238,
|
|
"epoch": 0.8983658131608844,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004926093385339105,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.14293062537908555,
|
|
"num_tokens": 20826936.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 6.235605621337891,
|
|
"epoch": 0.8988027615135891,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004926014154075732,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.1459277093410492,
|
|
"num_tokens": 20836732.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 6.298902893066407,
|
|
"epoch": 0.8992397098662938,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004925934881075268,
|
|
"loss": 6.0548,
|
|
"mean_token_accuracy": 0.13570440113544463,
|
|
"num_tokens": 20848093.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 6.265059566497802,
|
|
"epoch": 0.8996766582189986,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004925855566339232,
|
|
"loss": 5.9708,
|
|
"mean_token_accuracy": 0.14378736466169356,
|
|
"num_tokens": 20858678.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 6.2076538562774655,
|
|
"epoch": 0.9001136065717033,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004925776209869146,
|
|
"loss": 5.9674,
|
|
"mean_token_accuracy": 0.1465497247874737,
|
|
"num_tokens": 20869319.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 6.204934883117676,
|
|
"epoch": 0.9005505549244079,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004925696811666532,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.1483704574406147,
|
|
"num_tokens": 20879475.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 6.1841202735900875,
|
|
"epoch": 0.9009875032771126,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004925617371732914,
|
|
"loss": 5.9606,
|
|
"mean_token_accuracy": 0.15277539938688278,
|
|
"num_tokens": 20889479.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 6.2324748039245605,
|
|
"epoch": 0.9014244516298173,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004925537890069815,
|
|
"loss": 6.0491,
|
|
"mean_token_accuracy": 0.14187959283590318,
|
|
"num_tokens": 20899864.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 6.162887859344482,
|
|
"epoch": 0.901861399982522,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004925458366678758,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.14296629130840302,
|
|
"num_tokens": 20909006.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 6.2473695278167725,
|
|
"epoch": 0.9022983483352268,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004925378801561269,
|
|
"loss": 5.9568,
|
|
"mean_token_accuracy": 0.14621812105178833,
|
|
"num_tokens": 20917998.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 6.145819425582886,
|
|
"epoch": 0.9027352966879315,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004925299194718876,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.14791434556245803,
|
|
"num_tokens": 20928407.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 6.103126573562622,
|
|
"epoch": 0.9031722450406362,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004925219546153105,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.14059873446822166,
|
|
"num_tokens": 20938016.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 6.274331665039062,
|
|
"epoch": 0.9036091933933409,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004925139855865483,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.1379294253885746,
|
|
"num_tokens": 20948578.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 6.305205392837524,
|
|
"epoch": 0.9040461417460456,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004925060123857539,
|
|
"loss": 5.9313,
|
|
"mean_token_accuracy": 0.14447855800390244,
|
|
"num_tokens": 20958193.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 6.234714555740356,
|
|
"epoch": 0.9044830900987503,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004924980350130802,
|
|
"loss": 5.9883,
|
|
"mean_token_accuracy": 0.15243747979402542,
|
|
"num_tokens": 20968092.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 6.135723304748535,
|
|
"epoch": 0.9049200384514551,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004924900534686801,
|
|
"loss": 6.0206,
|
|
"mean_token_accuracy": 0.1399074487388134,
|
|
"num_tokens": 20978303.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 6.191471338272095,
|
|
"epoch": 0.9053569868041598,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004924820677527069,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.14377782195806504,
|
|
"num_tokens": 20988331.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 6.150998830795288,
|
|
"epoch": 0.9057939351568645,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004924740778653137,
|
|
"loss": 5.936,
|
|
"mean_token_accuracy": 0.14535974115133285,
|
|
"num_tokens": 20997785.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 6.274278736114502,
|
|
"epoch": 0.9062308835095692,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004924660838066538,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.1434810273349285,
|
|
"num_tokens": 21008026.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 6.2038064956665036,
|
|
"epoch": 0.9066678318622738,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004924580855768803,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.14854384064674378,
|
|
"num_tokens": 21017993.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 6.159410095214843,
|
|
"epoch": 0.9071047802149785,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004924500831761468,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.14842465221881868,
|
|
"num_tokens": 21028149.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 6.285621452331543,
|
|
"epoch": 0.9075417285676833,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004924420766046069,
|
|
"loss": 6.1227,
|
|
"mean_token_accuracy": 0.13110206723213197,
|
|
"num_tokens": 21039229.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 6.298278141021728,
|
|
"epoch": 0.907978676920388,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004924340658624139,
|
|
"loss": 6.0476,
|
|
"mean_token_accuracy": 0.14461030662059784,
|
|
"num_tokens": 21049358.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 6.239208078384399,
|
|
"epoch": 0.9084156252730927,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004924260509497217,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.14283088743686675,
|
|
"num_tokens": 21060385.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 6.213239908218384,
|
|
"epoch": 0.9088525736257974,
|
|
"grad_norm": 5.0625,
|
|
"learning_rate": 0.0004924180318666838,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.14117654636502266,
|
|
"num_tokens": 21070423.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 6.394452857971191,
|
|
"epoch": 0.9092895219785021,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004924100086134541,
|
|
"loss": 6.0393,
|
|
"mean_token_accuracy": 0.13764989152550697,
|
|
"num_tokens": 21080505.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 6.265415191650391,
|
|
"epoch": 0.9097264703312069,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004924019811901866,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.13928126394748688,
|
|
"num_tokens": 21090875.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 6.21007890701294,
|
|
"epoch": 0.9101634186839116,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004923939495970352,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.14366873800754548,
|
|
"num_tokens": 21101427.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 6.279690456390381,
|
|
"epoch": 0.9106003670366163,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004923859138341539,
|
|
"loss": 6.0991,
|
|
"mean_token_accuracy": 0.14020335972309111,
|
|
"num_tokens": 21112691.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 6.297071075439453,
|
|
"epoch": 0.911037315389321,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004923778739016969,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.1366792932152748,
|
|
"num_tokens": 21123932.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 6.215231418609619,
|
|
"epoch": 0.9114742637420257,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004923698297998183,
|
|
"loss": 6.0952,
|
|
"mean_token_accuracy": 0.13873008415102958,
|
|
"num_tokens": 21135380.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 6.207882308959961,
|
|
"epoch": 0.9119112120947304,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004923617815286725,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.14756772220134734,
|
|
"num_tokens": 21144951.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 6.2428864479064945,
|
|
"epoch": 0.9123481604474352,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004923537290884138,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.146316459774971,
|
|
"num_tokens": 21155919.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 6.137046241760254,
|
|
"epoch": 0.9127851088001399,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004923456724791967,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.14737611785531043,
|
|
"num_tokens": 21166186.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 6.138951063156128,
|
|
"epoch": 0.9132220571528445,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004923376117011758,
|
|
"loss": 5.9316,
|
|
"mean_token_accuracy": 0.1520561769604683,
|
|
"num_tokens": 21176043.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 6.14461030960083,
|
|
"epoch": 0.9136590055055492,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004923295467545055,
|
|
"loss": 5.9324,
|
|
"mean_token_accuracy": 0.15320966392755508,
|
|
"num_tokens": 21185677.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 6.212748861312866,
|
|
"epoch": 0.9140959538582539,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004923214776393407,
|
|
"loss": 6.0528,
|
|
"mean_token_accuracy": 0.1364740625023842,
|
|
"num_tokens": 21195977.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 6.260949802398682,
|
|
"epoch": 0.9145329022109586,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.000492313404355836,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.1471311330795288,
|
|
"num_tokens": 21205454.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 6.20062403678894,
|
|
"epoch": 0.9149698505636634,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004923053269041464,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.15106230676174165,
|
|
"num_tokens": 21215700.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 6.171433305740356,
|
|
"epoch": 0.9154067989163681,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004922972452844267,
|
|
"loss": 6.0425,
|
|
"mean_token_accuracy": 0.14153960198163987,
|
|
"num_tokens": 21226544.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 6.244486856460571,
|
|
"epoch": 0.9158437472690728,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004922891594968321,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.14115132316946982,
|
|
"num_tokens": 21236792.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 6.262734365463257,
|
|
"epoch": 0.9162806956217775,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 0.0004922810695415175,
|
|
"loss": 5.9803,
|
|
"mean_token_accuracy": 0.14429373666644096,
|
|
"num_tokens": 21247039.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 6.187035703659058,
|
|
"epoch": 0.9167176439744822,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004922729754186381,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.14789291173219682,
|
|
"num_tokens": 21257008.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 6.202964210510254,
|
|
"epoch": 0.9171545923271869,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004922648771283492,
|
|
"loss": 6.1188,
|
|
"mean_token_accuracy": 0.13898467347025872,
|
|
"num_tokens": 21267638.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 6.265435743331909,
|
|
"epoch": 0.9175915406798917,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004922567746708062,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.14649815410375594,
|
|
"num_tokens": 21277327.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 6.216078615188598,
|
|
"epoch": 0.9180284890325964,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004922486680461642,
|
|
"loss": 6.0713,
|
|
"mean_token_accuracy": 0.14119886606931686,
|
|
"num_tokens": 21287579.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 6.215159559249878,
|
|
"epoch": 0.9184654373853011,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004922405572545792,
|
|
"loss": 6.003,
|
|
"mean_token_accuracy": 0.13807881399989128,
|
|
"num_tokens": 21297888.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 6.323606300354004,
|
|
"epoch": 0.9189023857380058,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004922324422962063,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.14395225718617438,
|
|
"num_tokens": 21308506.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 6.228168869018555,
|
|
"epoch": 0.9193393340907104,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004922243231712013,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.13690708130598067,
|
|
"num_tokens": 21319252.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 6.194595241546631,
|
|
"epoch": 0.9197762824434151,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00049221619987972,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.15066403448581694,
|
|
"num_tokens": 21328829.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 6.192099523544312,
|
|
"epoch": 0.9202132307961199,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004922080724219182,
|
|
"loss": 5.8998,
|
|
"mean_token_accuracy": 0.1474005937576294,
|
|
"num_tokens": 21338524.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 6.214118003845215,
|
|
"epoch": 0.9206501791488246,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004921999407979518,
|
|
"loss": 6.0217,
|
|
"mean_token_accuracy": 0.14827122092247008,
|
|
"num_tokens": 21348559.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 6.310662937164307,
|
|
"epoch": 0.9210871275015293,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004921918050079766,
|
|
"loss": 6.0529,
|
|
"mean_token_accuracy": 0.14093535169959068,
|
|
"num_tokens": 21360763.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 6.241768074035645,
|
|
"epoch": 0.921524075854234,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004921836650521489,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.13818306252360343,
|
|
"num_tokens": 21370048.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 6.127975034713745,
|
|
"epoch": 0.9219610242069387,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004921755209306247,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.14913525879383088,
|
|
"num_tokens": 21379760.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 6.254342365264892,
|
|
"epoch": 0.9223979725596434,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004921673726435601,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.1414869636297226,
|
|
"num_tokens": 21389712.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 6.301798152923584,
|
|
"epoch": 0.9228349209123482,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004921592201911115,
|
|
"loss": 5.985,
|
|
"mean_token_accuracy": 0.139986489713192,
|
|
"num_tokens": 21399515.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 6.14472541809082,
|
|
"epoch": 0.9232718692650529,
|
|
"grad_norm": 12.0,
|
|
"learning_rate": 0.0004921510635734353,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.14641227424144745,
|
|
"num_tokens": 21409704.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 6.149060153961182,
|
|
"epoch": 0.9237088176177576,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.000492142902790688,
|
|
"loss": 5.969,
|
|
"mean_token_accuracy": 0.14714572876691817,
|
|
"num_tokens": 21419182.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 6.152178955078125,
|
|
"epoch": 0.9241457659704623,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004921347378430259,
|
|
"loss": 5.8465,
|
|
"mean_token_accuracy": 0.14979463219642639,
|
|
"num_tokens": 21429749.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 6.303376817703247,
|
|
"epoch": 0.924582714323167,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004921265687306059,
|
|
"loss": 6.1263,
|
|
"mean_token_accuracy": 0.133523565530777,
|
|
"num_tokens": 21440514.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 6.260319566726684,
|
|
"epoch": 0.9250196626758717,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004921183954535844,
|
|
"loss": 5.9849,
|
|
"mean_token_accuracy": 0.14747928380966185,
|
|
"num_tokens": 21450647.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 6.1637708187103275,
|
|
"epoch": 0.9254566110285765,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004921102180121184,
|
|
"loss": 6.0183,
|
|
"mean_token_accuracy": 0.14358814507722856,
|
|
"num_tokens": 21460233.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 6.205360841751099,
|
|
"epoch": 0.9258935593812812,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004921020364063646,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.1464311197400093,
|
|
"num_tokens": 21470207.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 6.226392030715942,
|
|
"epoch": 0.9263305077339858,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004920938506364801,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.14325212314724922,
|
|
"num_tokens": 21480658.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 6.157357835769654,
|
|
"epoch": 0.9267674560866905,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004920856607026216,
|
|
"loss": 5.9372,
|
|
"mean_token_accuracy": 0.15598447024822235,
|
|
"num_tokens": 21490566.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 6.259216451644898,
|
|
"epoch": 0.9272044044393952,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004920774666049465,
|
|
"loss": 6.0181,
|
|
"mean_token_accuracy": 0.14652312323451042,
|
|
"num_tokens": 21500752.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 6.210867071151734,
|
|
"epoch": 0.9276413527921,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004920692683436118,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.13795026540756225,
|
|
"num_tokens": 21509802.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 6.196670293807983,
|
|
"epoch": 0.9280783011448047,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004920610659187748,
|
|
"loss": 6.0976,
|
|
"mean_token_accuracy": 0.13529762476682664,
|
|
"num_tokens": 21520962.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 6.2840722560882565,
|
|
"epoch": 0.9285152494975094,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004920528593305929,
|
|
"loss": 6.0552,
|
|
"mean_token_accuracy": 0.1432752065360546,
|
|
"num_tokens": 21530580.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 6.223748350143433,
|
|
"epoch": 0.9289521978502141,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004920446485792233,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.14267162457108498,
|
|
"num_tokens": 21541431.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 6.166488218307495,
|
|
"epoch": 0.9293891462029188,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004920364336648236,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.14596092104911804,
|
|
"num_tokens": 21551012.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 6.165671348571777,
|
|
"epoch": 0.9298260945556235,
|
|
"grad_norm": 6.78125,
|
|
"learning_rate": 0.0004920282145875514,
|
|
"loss": 5.968,
|
|
"mean_token_accuracy": 0.14599599987268447,
|
|
"num_tokens": 21560676.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 6.180420780181885,
|
|
"epoch": 0.9302630429083283,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004920199913475644,
|
|
"loss": 5.9498,
|
|
"mean_token_accuracy": 0.15370635986328124,
|
|
"num_tokens": 21570848.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 6.210285902023315,
|
|
"epoch": 0.930699991261033,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004920117639450202,
|
|
"loss": 6.0171,
|
|
"mean_token_accuracy": 0.14113985002040863,
|
|
"num_tokens": 21582358.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 6.191497421264648,
|
|
"epoch": 0.9311369396137377,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004920035323800767,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.14366309270262717,
|
|
"num_tokens": 21591709.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 6.220680570602417,
|
|
"epoch": 0.9315738879664424,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004919952966528917,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.14706862941384316,
|
|
"num_tokens": 21601092.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 6.2127635955810545,
|
|
"epoch": 0.932010836319147,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004919870567636233,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.14712963551282882,
|
|
"num_tokens": 21611003.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 6.218704462051392,
|
|
"epoch": 0.9324477846718517,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004919788127124293,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.143191160261631,
|
|
"num_tokens": 21621528.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 6.140312194824219,
|
|
"epoch": 0.9328847330245565,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000491970564499468,
|
|
"loss": 5.9407,
|
|
"mean_token_accuracy": 0.15630738213658332,
|
|
"num_tokens": 21631431.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 6.170972919464111,
|
|
"epoch": 0.9333216813772612,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004919623121248976,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.14786597937345505,
|
|
"num_tokens": 21640717.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 6.199743843078613,
|
|
"epoch": 0.9337586297299659,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004919540555888765,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.14796182438731192,
|
|
"num_tokens": 21650493.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 6.18906946182251,
|
|
"epoch": 0.9341955780826706,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004919457948915628,
|
|
"loss": 5.9918,
|
|
"mean_token_accuracy": 0.14778658896684646,
|
|
"num_tokens": 21660062.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 6.130363082885742,
|
|
"epoch": 0.9346325264353753,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004919375300331151,
|
|
"loss": 5.98,
|
|
"mean_token_accuracy": 0.14802612364292145,
|
|
"num_tokens": 21669364.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 6.211278104782105,
|
|
"epoch": 0.93506947478808,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004919292610136919,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.13631946146488189,
|
|
"num_tokens": 21680793.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 6.300205183029175,
|
|
"epoch": 0.9355064231407848,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004919209878334518,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.14969588071107864,
|
|
"num_tokens": 21690862.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 6.218013858795166,
|
|
"epoch": 0.9359433714934895,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004919127104925535,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.1505468435585499,
|
|
"num_tokens": 21700665.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 6.21826138496399,
|
|
"epoch": 0.9363803198461942,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004919044289911557,
|
|
"loss": 6.009,
|
|
"mean_token_accuracy": 0.15433460250496864,
|
|
"num_tokens": 21711128.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 6.298015975952149,
|
|
"epoch": 0.9368172681988989,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004918961433294173,
|
|
"loss": 6.0595,
|
|
"mean_token_accuracy": 0.14322931915521622,
|
|
"num_tokens": 21720233.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 6.219951391220093,
|
|
"epoch": 0.9372542165516036,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004918878535074973,
|
|
"loss": 6.0113,
|
|
"mean_token_accuracy": 0.14601922184228897,
|
|
"num_tokens": 21730980.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 6.1353987693786625,
|
|
"epoch": 0.9376911649043083,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004918795595255545,
|
|
"loss": 6.006,
|
|
"mean_token_accuracy": 0.15070429146289827,
|
|
"num_tokens": 21742802.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 6.202398681640625,
|
|
"epoch": 0.9381281132570131,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004918712613837483,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.14104835465550422,
|
|
"num_tokens": 21752743.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 6.2312483310699465,
|
|
"epoch": 0.9385650616097178,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004918629590822375,
|
|
"loss": 6.0082,
|
|
"mean_token_accuracy": 0.15075039565563203,
|
|
"num_tokens": 21763198.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 6.286467838287353,
|
|
"epoch": 0.9390020099624224,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004918546526211816,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.14858868047595025,
|
|
"num_tokens": 21773030.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 6.260855102539063,
|
|
"epoch": 0.9394389583151271,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004918463420007398,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.15268792808055878,
|
|
"num_tokens": 21783796.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 6.1994904518127445,
|
|
"epoch": 0.9398759066678318,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004918380272210715,
|
|
"loss": 5.9826,
|
|
"mean_token_accuracy": 0.14605018645524978,
|
|
"num_tokens": 21792504.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 6.211883544921875,
|
|
"epoch": 0.9403128550205365,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004918297082823362,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.14198035895824432,
|
|
"num_tokens": 21802764.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 6.255032253265381,
|
|
"epoch": 0.9407498033732413,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004918213851846935,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.1414106547832489,
|
|
"num_tokens": 21813051.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 6.171677970886231,
|
|
"epoch": 0.941186751725946,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004918130579283031,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.14869959205389022,
|
|
"num_tokens": 21822941.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 6.220159387588501,
|
|
"epoch": 0.9416237000786507,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004918047265133246,
|
|
"loss": 5.9944,
|
|
"mean_token_accuracy": 0.14000218361616135,
|
|
"num_tokens": 21833225.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 6.193222761154175,
|
|
"epoch": 0.9420606484313554,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004917963909399178,
|
|
"loss": 5.9935,
|
|
"mean_token_accuracy": 0.1491098329424858,
|
|
"num_tokens": 21842360.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 6.158725357055664,
|
|
"epoch": 0.9424975967840601,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004917880512082427,
|
|
"loss": 6.0061,
|
|
"mean_token_accuracy": 0.1409321278333664,
|
|
"num_tokens": 21852515.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 6.232230710983276,
|
|
"epoch": 0.9429345451367648,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004917797073184591,
|
|
"loss": 6.0969,
|
|
"mean_token_accuracy": 0.13883135467767715,
|
|
"num_tokens": 21863040.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 6.283722257614135,
|
|
"epoch": 0.9433714934894696,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004917713592707271,
|
|
"loss": 6.0239,
|
|
"mean_token_accuracy": 0.14643628969788552,
|
|
"num_tokens": 21872101.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 6.276474285125732,
|
|
"epoch": 0.9438084418421743,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004917630070652069,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.1447010673582554,
|
|
"num_tokens": 21882148.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 6.178737545013428,
|
|
"epoch": 0.944245390194879,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004917546507020587,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.1562783569097519,
|
|
"num_tokens": 21891832.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 6.177520990371704,
|
|
"epoch": 0.9446823385475837,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004917462901814427,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.1424844041466713,
|
|
"num_tokens": 21901544.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 6.253967809677124,
|
|
"epoch": 0.9451192869002883,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004917379255035192,
|
|
"loss": 6.0482,
|
|
"mean_token_accuracy": 0.13904709592461587,
|
|
"num_tokens": 21911690.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 6.2717604637146,
|
|
"epoch": 0.9455562352529931,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004917295566684487,
|
|
"loss": 6.0767,
|
|
"mean_token_accuracy": 0.14239536672830583,
|
|
"num_tokens": 21922968.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 6.135378122329712,
|
|
"epoch": 0.9459931836056978,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004917211836763919,
|
|
"loss": 5.9054,
|
|
"mean_token_accuracy": 0.15248963683843614,
|
|
"num_tokens": 21932904.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 6.117606496810913,
|
|
"epoch": 0.9464301319584025,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004917128065275091,
|
|
"loss": 5.9183,
|
|
"mean_token_accuracy": 0.15463434532284737,
|
|
"num_tokens": 21943065.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 6.218717002868653,
|
|
"epoch": 0.9468670803111072,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004917044252219612,
|
|
"loss": 5.9868,
|
|
"mean_token_accuracy": 0.13802486956119536,
|
|
"num_tokens": 21953448.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 6.252996778488159,
|
|
"epoch": 0.9473040286638119,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004916960397599088,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.14509997367858887,
|
|
"num_tokens": 21963374.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 6.228418684005737,
|
|
"epoch": 0.9477409770165166,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004916876501415129,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.1398419111967087,
|
|
"num_tokens": 21973726.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 6.186339902877807,
|
|
"epoch": 0.9481779253692214,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004916792563669342,
|
|
"loss": 5.9187,
|
|
"mean_token_accuracy": 0.15003404915332794,
|
|
"num_tokens": 21983203.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 6.186272287368775,
|
|
"epoch": 0.9486148737219261,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004916708584363339,
|
|
"loss": 6.0156,
|
|
"mean_token_accuracy": 0.14147771149873734,
|
|
"num_tokens": 21993435.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 6.2610009670257565,
|
|
"epoch": 0.9490518220746308,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000491662456349873,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.14023432284593582,
|
|
"num_tokens": 22003230.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 6.237763166427612,
|
|
"epoch": 0.9494887704273355,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004916540501077127,
|
|
"loss": 5.9938,
|
|
"mean_token_accuracy": 0.14545562863349915,
|
|
"num_tokens": 22012910.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 6.191306114196777,
|
|
"epoch": 0.9499257187800402,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004916456397100141,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.14597126245498657,
|
|
"num_tokens": 22022802.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 6.189124631881714,
|
|
"epoch": 0.9503626671327449,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004916372251569386,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.14138342589139938,
|
|
"num_tokens": 22032669.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 6.185146379470825,
|
|
"epoch": 0.9507996154854497,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004916288064486477,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.1547721117734909,
|
|
"num_tokens": 22042477.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 6.22675633430481,
|
|
"epoch": 0.9512365638381544,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004916203835853027,
|
|
"loss": 6.0294,
|
|
"mean_token_accuracy": 0.14525218829512596,
|
|
"num_tokens": 22052891.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 6.172472190856934,
|
|
"epoch": 0.951673512190859,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004916119565670652,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.15339114665985107,
|
|
"num_tokens": 22062413.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 6.226963949203491,
|
|
"epoch": 0.9521104605435637,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.000491603525394097,
|
|
"loss": 6.0312,
|
|
"mean_token_accuracy": 0.1441036880016327,
|
|
"num_tokens": 22072565.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 6.263289117813111,
|
|
"epoch": 0.9525474088962684,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.0004915950900665596,
|
|
"loss": 5.9955,
|
|
"mean_token_accuracy": 0.1423460550606251,
|
|
"num_tokens": 22082910.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 6.138033008575439,
|
|
"epoch": 0.9529843572489731,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000491586650584615,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.15537372156977652,
|
|
"num_tokens": 22092636.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 6.159360361099243,
|
|
"epoch": 0.9534213056016779,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004915782069484248,
|
|
"loss": 5.9898,
|
|
"mean_token_accuracy": 0.14539300203323363,
|
|
"num_tokens": 22102232.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 6.246322154998779,
|
|
"epoch": 0.9538582539543826,
|
|
"grad_norm": 9.375,
|
|
"learning_rate": 0.0004915697591581511,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.14191672429442406,
|
|
"num_tokens": 22113592.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 6.223143243789673,
|
|
"epoch": 0.9542952023070873,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000491561307213956,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.1490973487496376,
|
|
"num_tokens": 22123731.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 6.195102214813232,
|
|
"epoch": 0.954732150659792,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004915528511160016,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.13526889234781264,
|
|
"num_tokens": 22133801.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 6.245194959640503,
|
|
"epoch": 0.9551690990124967,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004915443908644501,
|
|
"loss": 6.0112,
|
|
"mean_token_accuracy": 0.14422514140605927,
|
|
"num_tokens": 22143939.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 6.184619903564453,
|
|
"epoch": 0.9556060473652014,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004915359264594636,
|
|
"loss": 6.0344,
|
|
"mean_token_accuracy": 0.14297499433159827,
|
|
"num_tokens": 22154954.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 6.171615982055664,
|
|
"epoch": 0.9560429957179062,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004915274579012045,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.14542377069592477,
|
|
"num_tokens": 22165225.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 6.2445436954498295,
|
|
"epoch": 0.9564799440706109,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004915189851898355,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.13991244956851007,
|
|
"num_tokens": 22174891.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 6.175931406021118,
|
|
"epoch": 0.9569168924233156,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004915105083255187,
|
|
"loss": 6.0164,
|
|
"mean_token_accuracy": 0.14690523222088814,
|
|
"num_tokens": 22185255.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 6.201735305786133,
|
|
"epoch": 0.9573538407760203,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.000491502027308417,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.14451221227645875,
|
|
"num_tokens": 22196124.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 6.230536365509034,
|
|
"epoch": 0.957790789128725,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000491493542138693,
|
|
"loss": 6.0112,
|
|
"mean_token_accuracy": 0.14705559909343718,
|
|
"num_tokens": 22207563.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 6.2241034507751465,
|
|
"epoch": 0.9582277374814296,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004914850528165094,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.14533495381474495,
|
|
"num_tokens": 22218527.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 6.2043381690979,
|
|
"epoch": 0.9586646858341344,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000491476559342029,
|
|
"loss": 6.0183,
|
|
"mean_token_accuracy": 0.14308564662933348,
|
|
"num_tokens": 22229538.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 6.18302173614502,
|
|
"epoch": 0.9591016341868391,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004914680617154148,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.15026368349790573,
|
|
"num_tokens": 22240047.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 6.127550363540649,
|
|
"epoch": 0.9595385825395438,
|
|
"grad_norm": 6.25,
|
|
"learning_rate": 0.0004914595599368297,
|
|
"loss": 5.9069,
|
|
"mean_token_accuracy": 0.15337428599596023,
|
|
"num_tokens": 22250440.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 6.183742475509644,
|
|
"epoch": 0.9599755308922485,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004914510540064369,
|
|
"loss": 5.9875,
|
|
"mean_token_accuracy": 0.1468888506293297,
|
|
"num_tokens": 22259909.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 6.203589534759521,
|
|
"epoch": 0.9604124792449532,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004914425439243994,
|
|
"loss": 6.0268,
|
|
"mean_token_accuracy": 0.14455460160970687,
|
|
"num_tokens": 22270358.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 6.184572982788086,
|
|
"epoch": 0.9608494275976579,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004914340296908805,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.14026312083005904,
|
|
"num_tokens": 22280591.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 6.257546615600586,
|
|
"epoch": 0.9612863759503627,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004914255113060435,
|
|
"loss": 6.0256,
|
|
"mean_token_accuracy": 0.14363593012094497,
|
|
"num_tokens": 22291067.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 6.183000373840332,
|
|
"epoch": 0.9617233243030674,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004914169887700519,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.15076697915792464,
|
|
"num_tokens": 22300919.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 6.209692049026489,
|
|
"epoch": 0.9621602726557721,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004914084620830689,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.13879420086741448,
|
|
"num_tokens": 22311562.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 6.280151510238648,
|
|
"epoch": 0.9625972210084768,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004913999312452583,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.14432545006275177,
|
|
"num_tokens": 22322980.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 6.294468259811401,
|
|
"epoch": 0.9630341693611815,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004913913962567836,
|
|
"loss": 5.9451,
|
|
"mean_token_accuracy": 0.15182111859321595,
|
|
"num_tokens": 22333242.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 6.259706830978393,
|
|
"epoch": 0.9634711177138863,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004913828571178085,
|
|
"loss": 6.0167,
|
|
"mean_token_accuracy": 0.1432610757648945,
|
|
"num_tokens": 22343618.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 6.175912189483642,
|
|
"epoch": 0.963908066066591,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004913743138284969,
|
|
"loss": 6.0274,
|
|
"mean_token_accuracy": 0.1369355410337448,
|
|
"num_tokens": 22354249.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 6.2488789558410645,
|
|
"epoch": 0.9643450144192957,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004913657663890124,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.14141578301787378,
|
|
"num_tokens": 22363824.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 6.244002914428711,
|
|
"epoch": 0.9647819627720003,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004913572147995193,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.14645989313721658,
|
|
"num_tokens": 22373470.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 6.158661794662476,
|
|
"epoch": 0.965218911124705,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004913486590601814,
|
|
"loss": 5.9427,
|
|
"mean_token_accuracy": 0.14150407910346985,
|
|
"num_tokens": 22382999.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 6.129118585586548,
|
|
"epoch": 0.9656558594774097,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004913400991711629,
|
|
"loss": 5.9972,
|
|
"mean_token_accuracy": 0.15310502126812936,
|
|
"num_tokens": 22393415.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 6.135149049758911,
|
|
"epoch": 0.9660928078301145,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.0004913315351326279,
|
|
"loss": 5.9181,
|
|
"mean_token_accuracy": 0.1508888080716133,
|
|
"num_tokens": 22403040.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 6.231525945663452,
|
|
"epoch": 0.9665297561828192,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004913229669447406,
|
|
"loss": 5.9638,
|
|
"mean_token_accuracy": 0.14777958244085312,
|
|
"num_tokens": 22413434.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 6.213392639160157,
|
|
"epoch": 0.9669667045355239,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004913143946076656,
|
|
"loss": 6.0661,
|
|
"mean_token_accuracy": 0.14121007025241852,
|
|
"num_tokens": 22424446.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 6.190732192993164,
|
|
"epoch": 0.9674036528882286,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004913058181215671,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.15233338326215745,
|
|
"num_tokens": 22433928.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 6.224525260925293,
|
|
"epoch": 0.9678406012409333,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004912972374866096,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.1454777702689171,
|
|
"num_tokens": 22443778.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 6.227717351913452,
|
|
"epoch": 0.968277549593638,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004912886527029579,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.14311131238937377,
|
|
"num_tokens": 22453423.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 6.248215675354004,
|
|
"epoch": 0.9687144979463428,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004912800637707764,
|
|
"loss": 5.9791,
|
|
"mean_token_accuracy": 0.1495063677430153,
|
|
"num_tokens": 22464067.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 6.164710330963135,
|
|
"epoch": 0.9691514462990475,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00049127147069023,
|
|
"loss": 5.9641,
|
|
"mean_token_accuracy": 0.14813558384776115,
|
|
"num_tokens": 22474332.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 6.222461557388305,
|
|
"epoch": 0.9695883946517522,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004912628734614834,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.1444977566599846,
|
|
"num_tokens": 22485304.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 6.194020080566406,
|
|
"epoch": 0.9700253430044569,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004912542720847016,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.1493035674095154,
|
|
"num_tokens": 22494447.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 6.250943279266357,
|
|
"epoch": 0.9704622913571616,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004912456665600495,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.14843482226133348,
|
|
"num_tokens": 22503936.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 6.224056243896484,
|
|
"epoch": 0.9708992397098662,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004912370568876923,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.14860760420560837,
|
|
"num_tokens": 22513960.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 6.187701988220215,
|
|
"epoch": 0.971336188062571,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004912284430677949,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.14538998007774354,
|
|
"num_tokens": 22522309.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 6.186139631271362,
|
|
"epoch": 0.9717731364152757,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004912198251005228,
|
|
"loss": 5.971,
|
|
"mean_token_accuracy": 0.1455381765961647,
|
|
"num_tokens": 22533510.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 6.1655395984649655,
|
|
"epoch": 0.9722100847679804,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004912112029860411,
|
|
"loss": 5.9542,
|
|
"mean_token_accuracy": 0.14665468484163285,
|
|
"num_tokens": 22543644.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 6.285950803756714,
|
|
"epoch": 0.9726470331206851,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004912025767245153,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.13609763905405997,
|
|
"num_tokens": 22553475.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 6.172232151031494,
|
|
"epoch": 0.9730839814733898,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004911939463161108,
|
|
"loss": 5.9258,
|
|
"mean_token_accuracy": 0.14573410749435425,
|
|
"num_tokens": 22563190.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 6.144096708297729,
|
|
"epoch": 0.9735209298260945,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000491185311760993,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.14986318498849868,
|
|
"num_tokens": 22572069.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 6.161580896377563,
|
|
"epoch": 0.9739578781787993,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004911766730593276,
|
|
"loss": 6.0439,
|
|
"mean_token_accuracy": 0.13760749623179436,
|
|
"num_tokens": 22581597.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 6.188813734054565,
|
|
"epoch": 0.974394826531504,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004911680302112806,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.15137511417269706,
|
|
"num_tokens": 22591486.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 6.244290208816528,
|
|
"epoch": 0.9748317748842087,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004911593832170173,
|
|
"loss": 6.014,
|
|
"mean_token_accuracy": 0.1380392387509346,
|
|
"num_tokens": 22601615.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 6.232906675338745,
|
|
"epoch": 0.9752687232369134,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004911507320767038,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.1435872994363308,
|
|
"num_tokens": 22611397.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 6.128848695755005,
|
|
"epoch": 0.9757056715896181,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000491142076790506,
|
|
"loss": 5.9786,
|
|
"mean_token_accuracy": 0.14970599263906478,
|
|
"num_tokens": 22621269.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 6.222478818893433,
|
|
"epoch": 0.9761426199423228,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004911334173585899,
|
|
"loss": 5.9652,
|
|
"mean_token_accuracy": 0.14476251602172852,
|
|
"num_tokens": 22631782.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 6.20287971496582,
|
|
"epoch": 0.9765795682950276,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004911247537811216,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.14233123064041137,
|
|
"num_tokens": 22642240.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 6.226010990142822,
|
|
"epoch": 0.9770165166477323,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004911160860582674,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.1437778577208519,
|
|
"num_tokens": 22651977.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 6.279437589645386,
|
|
"epoch": 0.977453465000437,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004911074141901933,
|
|
"loss": 6.0121,
|
|
"mean_token_accuracy": 0.14684271663427353,
|
|
"num_tokens": 22662871.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 6.217707872390747,
|
|
"epoch": 0.9778904133531416,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004910987381770657,
|
|
"loss": 5.9665,
|
|
"mean_token_accuracy": 0.14834269061684607,
|
|
"num_tokens": 22672083.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 6.124328088760376,
|
|
"epoch": 0.9783273617058463,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004910900580190512,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.14960613399744033,
|
|
"num_tokens": 22681247.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 6.159181261062622,
|
|
"epoch": 0.9787643100585511,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004910813737163161,
|
|
"loss": 6.0077,
|
|
"mean_token_accuracy": 0.14306883215904237,
|
|
"num_tokens": 22691231.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 6.213525772094727,
|
|
"epoch": 0.9792012584112558,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000491072685269027,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.14373035728931427,
|
|
"num_tokens": 22700712.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 6.301746463775634,
|
|
"epoch": 0.9796382067639605,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004910639926773506,
|
|
"loss": 6.0959,
|
|
"mean_token_accuracy": 0.1427776262164116,
|
|
"num_tokens": 22710961.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 6.22751030921936,
|
|
"epoch": 0.9800751551166652,
|
|
"grad_norm": 4.90625,
|
|
"learning_rate": 0.0004910552959414538,
|
|
"loss": 5.9628,
|
|
"mean_token_accuracy": 0.14933306127786636,
|
|
"num_tokens": 22720450.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 6.106460380554199,
|
|
"epoch": 0.9805121034693699,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004910465950615029,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.15042502135038377,
|
|
"num_tokens": 22730337.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 6.137769746780395,
|
|
"epoch": 0.9809490518220746,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004910378900376651,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.140307005494833,
|
|
"num_tokens": 22742379.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 6.262981986999511,
|
|
"epoch": 0.9813860001747794,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004910291808701077,
|
|
"loss": 6.0635,
|
|
"mean_token_accuracy": 0.14013471826910973,
|
|
"num_tokens": 22753176.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 6.246870422363282,
|
|
"epoch": 0.9818229485274841,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004910204675589972,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.14495594948530197,
|
|
"num_tokens": 22763263.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 6.135342979431153,
|
|
"epoch": 0.9822598968801888,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004910117501045009,
|
|
"loss": 6.0356,
|
|
"mean_token_accuracy": 0.14509285241365433,
|
|
"num_tokens": 22774630.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 6.194659757614136,
|
|
"epoch": 0.9826968452328935,
|
|
"grad_norm": 14.375,
|
|
"learning_rate": 0.0004910030285067861,
|
|
"loss": 6.0125,
|
|
"mean_token_accuracy": 0.14676431119441985,
|
|
"num_tokens": 22785027.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 6.24728946685791,
|
|
"epoch": 0.9831337935855982,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004909943027660201,
|
|
"loss": 6.0574,
|
|
"mean_token_accuracy": 0.13427724316716194,
|
|
"num_tokens": 22796399.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 6.267506265640259,
|
|
"epoch": 0.9835707419383029,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00049098557288237,
|
|
"loss": 6.0008,
|
|
"mean_token_accuracy": 0.14368091523647308,
|
|
"num_tokens": 22806352.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 6.247375726699829,
|
|
"epoch": 0.9840076902910077,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004909768388560036,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.14165429025888443,
|
|
"num_tokens": 22818369.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 6.21934142112732,
|
|
"epoch": 0.9844446386437123,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004909681006870882,
|
|
"loss": 5.9801,
|
|
"mean_token_accuracy": 0.14450762867927552,
|
|
"num_tokens": 22828063.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 6.245118045806885,
|
|
"epoch": 0.984881586996417,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004909593583757915,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.13885763436555862,
|
|
"num_tokens": 22839265.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 6.202704000473022,
|
|
"epoch": 0.9853185353491217,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004909506119222812,
|
|
"loss": 5.9891,
|
|
"mean_token_accuracy": 0.15027930736541747,
|
|
"num_tokens": 22848501.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 6.171825742721557,
|
|
"epoch": 0.9857554837018264,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004909418613267248,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.1502961188554764,
|
|
"num_tokens": 22859176.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 6.187764453887939,
|
|
"epoch": 0.9861924320545311,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004909331065892905,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.14518322348594664,
|
|
"num_tokens": 22869312.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 6.227721261978149,
|
|
"epoch": 0.9866293804072359,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.000490924347710146,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.14625362008810044,
|
|
"num_tokens": 22878699.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 6.1834508895874025,
|
|
"epoch": 0.9870663287599406,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004909155846894595,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.14202336668968202,
|
|
"num_tokens": 22889147.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 6.241399526596069,
|
|
"epoch": 0.9875032771126453,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004909068175273989,
|
|
"loss": 5.9764,
|
|
"mean_token_accuracy": 0.14701655730605126,
|
|
"num_tokens": 22899085.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 6.2564019680023195,
|
|
"epoch": 0.98794022546535,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004908980462241323,
|
|
"loss": 6.1063,
|
|
"mean_token_accuracy": 0.14100436270236968,
|
|
"num_tokens": 22909924.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 6.254339504241943,
|
|
"epoch": 0.9883771738180547,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004908892707798281,
|
|
"loss": 6.0698,
|
|
"mean_token_accuracy": 0.14327240511775016,
|
|
"num_tokens": 22920426.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 6.254977798461914,
|
|
"epoch": 0.9888141221707594,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004908804911946546,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.1458214096724987,
|
|
"num_tokens": 22929929.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 6.199986457824707,
|
|
"epoch": 0.9892510705234642,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004908717074687801,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.15381366908550262,
|
|
"num_tokens": 22940102.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 6.232103538513184,
|
|
"epoch": 0.9896880188761689,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004908629196023732,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.15618996918201447,
|
|
"num_tokens": 22949490.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 6.224821615219116,
|
|
"epoch": 0.9901249672288736,
|
|
"grad_norm": 5.21875,
|
|
"learning_rate": 0.0004908541275956024,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.14935585260391235,
|
|
"num_tokens": 22958119.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 6.201994943618774,
|
|
"epoch": 0.9905619155815782,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004908453314486363,
|
|
"loss": 5.9957,
|
|
"mean_token_accuracy": 0.143864306807518,
|
|
"num_tokens": 22969447.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 6.118885803222656,
|
|
"epoch": 0.9909988639342829,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004908365311616437,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.152784363925457,
|
|
"num_tokens": 22978925.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 6.194061374664306,
|
|
"epoch": 0.9914358122869876,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004908277267347931,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.14802219718694687,
|
|
"num_tokens": 22988861.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 6.21967887878418,
|
|
"epoch": 0.9918727606396924,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004908189181682538,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.1465169072151184,
|
|
"num_tokens": 22998700.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 6.207000207901001,
|
|
"epoch": 0.9923097089923971,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004908101054621946,
|
|
"loss": 5.9662,
|
|
"mean_token_accuracy": 0.1498105153441429,
|
|
"num_tokens": 23009095.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 6.11841926574707,
|
|
"epoch": 0.9927466573451018,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004908012886167845,
|
|
"loss": 5.9851,
|
|
"mean_token_accuracy": 0.1481009840965271,
|
|
"num_tokens": 23019484.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 6.14017276763916,
|
|
"epoch": 0.9931836056978065,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004907924676321924,
|
|
"loss": 5.9555,
|
|
"mean_token_accuracy": 0.14604686200618744,
|
|
"num_tokens": 23029867.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 6.212933015823364,
|
|
"epoch": 0.9936205540505112,
|
|
"grad_norm": 4.90625,
|
|
"learning_rate": 0.000490783642508588,
|
|
"loss": 5.9252,
|
|
"mean_token_accuracy": 0.15722475349903106,
|
|
"num_tokens": 23040179.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 6.217982435226441,
|
|
"epoch": 0.9940575024032159,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00049077481324614,
|
|
"loss": 5.9209,
|
|
"mean_token_accuracy": 0.15354355573654174,
|
|
"num_tokens": 23050389.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 6.113583707809449,
|
|
"epoch": 0.9944944507559207,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.000490765979845018,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.15064753219485283,
|
|
"num_tokens": 23059984.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 6.197798204421997,
|
|
"epoch": 0.9949313991086254,
|
|
"grad_norm": 16.875,
|
|
"learning_rate": 0.0004907571423053917,
|
|
"loss": 5.9715,
|
|
"mean_token_accuracy": 0.14383725970983505,
|
|
"num_tokens": 23069828.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 6.298434257507324,
|
|
"epoch": 0.9953683474613301,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004907483006274302,
|
|
"loss": 6.0085,
|
|
"mean_token_accuracy": 0.14273910969495773,
|
|
"num_tokens": 23079223.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 6.198758459091186,
|
|
"epoch": 0.9958052958140348,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004907394548113033,
|
|
"loss": 6.0323,
|
|
"mean_token_accuracy": 0.14386327266693116,
|
|
"num_tokens": 23088540.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 6.150919389724732,
|
|
"epoch": 0.9962422441667395,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004907306048571806,
|
|
"loss": 6.0861,
|
|
"mean_token_accuracy": 0.14062410742044448,
|
|
"num_tokens": 23098617.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 6.188783264160156,
|
|
"epoch": 0.9966791925194443,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004907217507652317,
|
|
"loss": 5.9777,
|
|
"mean_token_accuracy": 0.14869602024555206,
|
|
"num_tokens": 23109702.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 6.269557237625122,
|
|
"epoch": 0.997116140872149,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004907128925356268,
|
|
"loss": 6.0179,
|
|
"mean_token_accuracy": 0.14628712385892867,
|
|
"num_tokens": 23120295.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 6.251343870162964,
|
|
"epoch": 0.9975530892248536,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 0.0004907040301685355,
|
|
"loss": 6.005,
|
|
"mean_token_accuracy": 0.141085384786129,
|
|
"num_tokens": 23131999.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 6.186858892440796,
|
|
"epoch": 0.9979900375775583,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004906951636641279,
|
|
"loss": 6.004,
|
|
"mean_token_accuracy": 0.14834101349115372,
|
|
"num_tokens": 23141060.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 6.163265514373779,
|
|
"epoch": 0.998426985930263,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.000490686293022574,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.14975388795137407,
|
|
"num_tokens": 23151607.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 6.212855100631714,
|
|
"epoch": 0.9988639342829677,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000490677418244044,
|
|
"loss": 6.0458,
|
|
"mean_token_accuracy": 0.13977433294057845,
|
|
"num_tokens": 23161892.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 6.243049621582031,
|
|
"epoch": 0.9993008826356725,
|
|
"grad_norm": 6.9375,
|
|
"learning_rate": 0.0004906685393287081,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.14472009390592575,
|
|
"num_tokens": 23172112.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 6.29594612121582,
|
|
"epoch": 0.9997378309883772,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004906596562767367,
|
|
"loss": 5.9398,
|
|
"mean_token_accuracy": 0.14860506355762482,
|
|
"num_tokens": 23181435.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 6.125890064239502,
|
|
"epoch": 1.0001747793410818,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004906507690883,
|
|
"loss": 5.8701,
|
|
"mean_token_accuracy": 0.153719761967659,
|
|
"num_tokens": 23191084.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 6.128403663635254,
|
|
"epoch": 1.0006117276937867,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004906418777635685,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.14208925738930703,
|
|
"num_tokens": 23202372.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 6.237107753753662,
|
|
"epoch": 1.0010486760464914,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004906329823027129,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.1449448399245739,
|
|
"num_tokens": 23214113.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 6.249896621704101,
|
|
"epoch": 1.001485624399196,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004906240827059036,
|
|
"loss": 5.8868,
|
|
"mean_token_accuracy": 0.1506553828716278,
|
|
"num_tokens": 23223562.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 6.213391733169556,
|
|
"epoch": 1.0019225727519008,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004906151789733114,
|
|
"loss": 5.9835,
|
|
"mean_token_accuracy": 0.14346898794174195,
|
|
"num_tokens": 23232901.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 6.19885401725769,
|
|
"epoch": 1.0023595211046055,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004906062711051073,
|
|
"loss": 5.998,
|
|
"mean_token_accuracy": 0.1453511595726013,
|
|
"num_tokens": 23242869.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 6.220397806167602,
|
|
"epoch": 1.0027964694573102,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004905973591014617,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.15457765609025956,
|
|
"num_tokens": 23253653.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 6.164454364776612,
|
|
"epoch": 1.0032334178100148,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004905884429625459,
|
|
"loss": 5.9233,
|
|
"mean_token_accuracy": 0.1484118938446045,
|
|
"num_tokens": 23263530.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 6.224922561645508,
|
|
"epoch": 1.0036703661627195,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004905795226885308,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.1458275243639946,
|
|
"num_tokens": 23274946.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 6.260493659973145,
|
|
"epoch": 1.0041073145154242,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004905705982795874,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.15124345943331718,
|
|
"num_tokens": 23283811.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 6.132644557952881,
|
|
"epoch": 1.004544262868129,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000490561669735887,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.14670841172337531,
|
|
"num_tokens": 23294554.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 6.100069761276245,
|
|
"epoch": 1.0049812112208336,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004905527370576009,
|
|
"loss": 5.8439,
|
|
"mean_token_accuracy": 0.15170976519584656,
|
|
"num_tokens": 23304245.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 6.321207714080811,
|
|
"epoch": 1.0054181595735383,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004905438002449004,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.1374276116490364,
|
|
"num_tokens": 23315169.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 6.165538024902344,
|
|
"epoch": 1.0058551079262432,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004905348592979567,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.14459408447146416,
|
|
"num_tokens": 23325528.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 6.1551250457763675,
|
|
"epoch": 1.006292056278948,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004905259142169415,
|
|
"loss": 6.026,
|
|
"mean_token_accuracy": 0.14281592890620232,
|
|
"num_tokens": 23336744.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 6.20447883605957,
|
|
"epoch": 1.0067290046316526,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004905169650020264,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.15230331122875213,
|
|
"num_tokens": 23346092.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 6.143009042739868,
|
|
"epoch": 1.0071659529843573,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004905080116533831,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.13944583237171174,
|
|
"num_tokens": 23357326.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 6.1353497982025145,
|
|
"epoch": 1.007602901337062,
|
|
"grad_norm": 5.78125,
|
|
"learning_rate": 0.000490499054171183,
|
|
"loss": 5.9435,
|
|
"mean_token_accuracy": 0.14872722774744035,
|
|
"num_tokens": 23367789.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 6.225711488723755,
|
|
"epoch": 1.0080398496897667,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004904900925555982,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.14835504293441773,
|
|
"num_tokens": 23377499.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 6.253147792816162,
|
|
"epoch": 1.0084767980424714,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004904811268068005,
|
|
"loss": 5.9179,
|
|
"mean_token_accuracy": 0.14387512803077698,
|
|
"num_tokens": 23387867.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 6.188341188430786,
|
|
"epoch": 1.008913746395176,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004904721569249618,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.142968862503767,
|
|
"num_tokens": 23398179.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 6.174725770950317,
|
|
"epoch": 1.0093506947478808,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004904631829102543,
|
|
"loss": 6.0121,
|
|
"mean_token_accuracy": 0.14683498293161393,
|
|
"num_tokens": 23407407.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 6.186086559295655,
|
|
"epoch": 1.0097876431005854,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004904542047628501,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.15031913071870803,
|
|
"num_tokens": 23417324.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 6.215742206573486,
|
|
"epoch": 1.0102245914532901,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004904452224829212,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.14663962423801422,
|
|
"num_tokens": 23427157.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 6.16818528175354,
|
|
"epoch": 1.0106615398059948,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004904362360706403,
|
|
"loss": 5.9659,
|
|
"mean_token_accuracy": 0.14321382492780685,
|
|
"num_tokens": 23437712.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 6.234272527694702,
|
|
"epoch": 1.0110984881586997,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004904272455261793,
|
|
"loss": 5.9244,
|
|
"mean_token_accuracy": 0.15019643679261208,
|
|
"num_tokens": 23447949.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 6.123412847518921,
|
|
"epoch": 1.0115354365114044,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004904182508497109,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.14437250867486,
|
|
"num_tokens": 23457319.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 6.214909410476684,
|
|
"epoch": 1.0119723848641091,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004904092520414075,
|
|
"loss": 5.9888,
|
|
"mean_token_accuracy": 0.14348120987415314,
|
|
"num_tokens": 23468245.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 6.255124092102051,
|
|
"epoch": 1.0124093332168138,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004904002491014418,
|
|
"loss": 5.9534,
|
|
"mean_token_accuracy": 0.1529581293463707,
|
|
"num_tokens": 23477049.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 6.189140129089355,
|
|
"epoch": 1.0128462815695185,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.0004903912420299866,
|
|
"loss": 6.0188,
|
|
"mean_token_accuracy": 0.14091739803552628,
|
|
"num_tokens": 23488574.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 6.213904619216919,
|
|
"epoch": 1.0132832299222232,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004903822308272144,
|
|
"loss": 5.9408,
|
|
"mean_token_accuracy": 0.15238529890775682,
|
|
"num_tokens": 23499282.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 6.188621473312378,
|
|
"epoch": 1.0137201782749279,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004903732154932982,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.15845069140195847,
|
|
"num_tokens": 23508777.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 6.18798246383667,
|
|
"epoch": 1.0141571266276326,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004903641960284108,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.15181176364421844,
|
|
"num_tokens": 23518818.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 6.164873456954956,
|
|
"epoch": 1.0145940749803373,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004903551724327254,
|
|
"loss": 5.9269,
|
|
"mean_token_accuracy": 0.1478419706225395,
|
|
"num_tokens": 23529668.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 6.253747272491455,
|
|
"epoch": 1.015031023333042,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004903461447064147,
|
|
"loss": 5.9657,
|
|
"mean_token_accuracy": 0.15092179626226426,
|
|
"num_tokens": 23540418.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 6.229628038406372,
|
|
"epoch": 1.0154679716857467,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004903371128496523,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.1532558262348175,
|
|
"num_tokens": 23550035.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 6.139720869064331,
|
|
"epoch": 1.0159049200384516,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.0004903280768626113,
|
|
"loss": 5.9612,
|
|
"mean_token_accuracy": 0.1426764450967312,
|
|
"num_tokens": 23559487.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 6.167341470718384,
|
|
"epoch": 1.0163418683911563,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004903190367454648,
|
|
"loss": 5.9033,
|
|
"mean_token_accuracy": 0.15389101952314377,
|
|
"num_tokens": 23569146.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 6.159114265441895,
|
|
"epoch": 1.016778816743861,
|
|
"grad_norm": 5.9375,
|
|
"learning_rate": 0.0004903099924983864,
|
|
"loss": 5.8807,
|
|
"mean_token_accuracy": 0.14899331256747245,
|
|
"num_tokens": 23579458.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 6.204789733886718,
|
|
"epoch": 1.0172157650965656,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004903009441215495,
|
|
"loss": 5.8922,
|
|
"mean_token_accuracy": 0.14243703931570054,
|
|
"num_tokens": 23589416.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 6.151660490036011,
|
|
"epoch": 1.0176527134492703,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004902918916151278,
|
|
"loss": 5.9843,
|
|
"mean_token_accuracy": 0.1495899051427841,
|
|
"num_tokens": 23599588.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 6.232296943664551,
|
|
"epoch": 1.018089661801975,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 0.0004902828349792947,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.14577097371220588,
|
|
"num_tokens": 23610116.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 6.173538064956665,
|
|
"epoch": 1.0185266101546797,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000490273774214224,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.1557459205389023,
|
|
"num_tokens": 23619906.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 6.142177963256836,
|
|
"epoch": 1.0189635585073844,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004902647093200896,
|
|
"loss": 5.9258,
|
|
"mean_token_accuracy": 0.15174940824508668,
|
|
"num_tokens": 23630351.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 6.165373945236206,
|
|
"epoch": 1.019400506860089,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004902556402970652,
|
|
"loss": 5.9869,
|
|
"mean_token_accuracy": 0.14259752109646798,
|
|
"num_tokens": 23639696.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 6.214051818847656,
|
|
"epoch": 1.0198374552127938,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004902465671453248,
|
|
"loss": 5.9313,
|
|
"mean_token_accuracy": 0.14681773036718368,
|
|
"num_tokens": 23649388.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 6.206135511398315,
|
|
"epoch": 1.0202744035654985,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004902374898650425,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.14501645565032958,
|
|
"num_tokens": 23659125.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 6.299280166625977,
|
|
"epoch": 1.0207113519182032,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004902284084563924,
|
|
"loss": 5.9878,
|
|
"mean_token_accuracy": 0.1447453536093235,
|
|
"num_tokens": 23668817.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 6.153827667236328,
|
|
"epoch": 1.021148300270908,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004902193229195487,
|
|
"loss": 5.9407,
|
|
"mean_token_accuracy": 0.1484477698802948,
|
|
"num_tokens": 23679378.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 6.11264123916626,
|
|
"epoch": 1.0215852486236128,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004902102332546855,
|
|
"loss": 5.9248,
|
|
"mean_token_accuracy": 0.14696565568447112,
|
|
"num_tokens": 23689400.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 6.288630819320678,
|
|
"epoch": 1.0220221969763175,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004902011394619772,
|
|
"loss": 6.0662,
|
|
"mean_token_accuracy": 0.13742880672216415,
|
|
"num_tokens": 23699503.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 6.254185009002685,
|
|
"epoch": 1.0224591453290222,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004901920415415985,
|
|
"loss": 6.0063,
|
|
"mean_token_accuracy": 0.14093072190880776,
|
|
"num_tokens": 23710913.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 6.160375022888184,
|
|
"epoch": 1.0228960936817268,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004901829394937234,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.14887271896004678,
|
|
"num_tokens": 23720730.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 6.199987697601318,
|
|
"epoch": 1.0233330420344315,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000490173833318527,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.1405739016830921,
|
|
"num_tokens": 23730902.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 6.196088171005249,
|
|
"epoch": 1.0237699903871362,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004901647230161837,
|
|
"loss": 6.005,
|
|
"mean_token_accuracy": 0.14492653608322142,
|
|
"num_tokens": 23741901.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 6.220611524581909,
|
|
"epoch": 1.024206938739841,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004901556085868681,
|
|
"loss": 5.9108,
|
|
"mean_token_accuracy": 0.14587837159633638,
|
|
"num_tokens": 23752029.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 6.147278547286987,
|
|
"epoch": 1.0246438870925456,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004901464900307553,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.15617354661226274,
|
|
"num_tokens": 23762125.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 6.174932861328125,
|
|
"epoch": 1.0250808354452503,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004901373673480201,
|
|
"loss": 5.9619,
|
|
"mean_token_accuracy": 0.15121276825666427,
|
|
"num_tokens": 23772056.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 6.160613059997559,
|
|
"epoch": 1.025517783797955,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004901282405388375,
|
|
"loss": 5.8968,
|
|
"mean_token_accuracy": 0.15151197090744972,
|
|
"num_tokens": 23781441.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 6.1676229476928714,
|
|
"epoch": 1.0259547321506597,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004901191096033825,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.15124904215335847,
|
|
"num_tokens": 23791472.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 6.137651062011718,
|
|
"epoch": 1.0263916805033646,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.0004901099745418302,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.14580238312482835,
|
|
"num_tokens": 23801940.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 6.1130469799041744,
|
|
"epoch": 1.0268286288560693,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004901008353543559,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.15534514486789702,
|
|
"num_tokens": 23811515.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 6.162692975997925,
|
|
"epoch": 1.027265577208774,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004900916920411349,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.1488305225968361,
|
|
"num_tokens": 23821871.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 6.107495069503784,
|
|
"epoch": 1.0277025255614787,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004900825446023426,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.15171604752540588,
|
|
"num_tokens": 23831677.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 6.172711324691773,
|
|
"epoch": 1.0281394739141834,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004900733930381543,
|
|
"loss": 5.9426,
|
|
"mean_token_accuracy": 0.14815112799406052,
|
|
"num_tokens": 23841415.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 6.236703205108642,
|
|
"epoch": 1.028576422266888,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004900642373487455,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.14841483831405639,
|
|
"num_tokens": 23851809.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 6.196333360671997,
|
|
"epoch": 1.0290133706195927,
|
|
"grad_norm": 6.875,
|
|
"learning_rate": 0.0004900550775342921,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.14207281544804573,
|
|
"num_tokens": 23861981.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 6.177800512313842,
|
|
"epoch": 1.0294503189722974,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004900459135949697,
|
|
"loss": 5.9113,
|
|
"mean_token_accuracy": 0.14654712975025178,
|
|
"num_tokens": 23872437.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 6.179175281524659,
|
|
"epoch": 1.0298872673250021,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004900367455309537,
|
|
"loss": 5.9405,
|
|
"mean_token_accuracy": 0.14729941487312317,
|
|
"num_tokens": 23881650.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 6.145957088470459,
|
|
"epoch": 1.0303242156777068,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004900275733424205,
|
|
"loss": 5.9554,
|
|
"mean_token_accuracy": 0.1503347083926201,
|
|
"num_tokens": 23891631.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 6.130884408950806,
|
|
"epoch": 1.0307611640304115,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004900183970295457,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.1534467577934265,
|
|
"num_tokens": 23901725.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 6.1669008255004885,
|
|
"epoch": 1.0311981123831164,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004900092165925053,
|
|
"loss": 5.9087,
|
|
"mean_token_accuracy": 0.14660380333662032,
|
|
"num_tokens": 23911850.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 6.215511226654053,
|
|
"epoch": 1.0316350607358211,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004900000320314757,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.14064744338393212,
|
|
"num_tokens": 23922571.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 6.2230743885040285,
|
|
"epoch": 1.0320720090885258,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004899908433466326,
|
|
"loss": 5.9259,
|
|
"mean_token_accuracy": 0.1500337116420269,
|
|
"num_tokens": 23932637.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 6.243884754180908,
|
|
"epoch": 1.0325089574412305,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004899816505381525,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.14186873733997346,
|
|
"num_tokens": 23943288.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 6.133871936798096,
|
|
"epoch": 1.0329459057939352,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004899724536062117,
|
|
"loss": 5.9084,
|
|
"mean_token_accuracy": 0.1506035581231117,
|
|
"num_tokens": 23952853.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 6.1379118919372555,
|
|
"epoch": 1.0333828541466399,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004899632525509867,
|
|
"loss": 5.935,
|
|
"mean_token_accuracy": 0.1465439938008785,
|
|
"num_tokens": 23963111.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 6.206754207611084,
|
|
"epoch": 1.0338198024993446,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004899540473726538,
|
|
"loss": 5.8826,
|
|
"mean_token_accuracy": 0.15071972832083702,
|
|
"num_tokens": 23972468.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 6.21347222328186,
|
|
"epoch": 1.0342567508520493,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004899448380713897,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.15384145379066466,
|
|
"num_tokens": 23982567.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 6.12376971244812,
|
|
"epoch": 1.034693699204754,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004899356246473709,
|
|
"loss": 5.9214,
|
|
"mean_token_accuracy": 0.1518683910369873,
|
|
"num_tokens": 23993283.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 6.186660671234131,
|
|
"epoch": 1.0351306475574586,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004899264071007741,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.15201990753412248,
|
|
"num_tokens": 24004504.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 6.169562196731567,
|
|
"epoch": 1.0355675959101633,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004899171854317764,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.15003803074359895,
|
|
"num_tokens": 24014557.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 6.148725986480713,
|
|
"epoch": 1.036004544262868,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004899079596405543,
|
|
"loss": 5.9134,
|
|
"mean_token_accuracy": 0.14588637053966522,
|
|
"num_tokens": 24024495.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 6.113318681716919,
|
|
"epoch": 1.036441492615573,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.000489898729727285,
|
|
"loss": 5.9295,
|
|
"mean_token_accuracy": 0.14993472695350646,
|
|
"num_tokens": 24034984.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 6.190798377990722,
|
|
"epoch": 1.0368784409682776,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004898894956921455,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.15183772817254065,
|
|
"num_tokens": 24044379.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 6.232519006729126,
|
|
"epoch": 1.0373153893209823,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004898802575353129,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.14870004057884217,
|
|
"num_tokens": 24054133.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 6.080832529067993,
|
|
"epoch": 1.037752337673687,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004898710152569642,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.14960063993930817,
|
|
"num_tokens": 24064868.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 6.201964950561523,
|
|
"epoch": 1.0381892860263917,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.0004898617688572769,
|
|
"loss": 5.9326,
|
|
"mean_token_accuracy": 0.14799922406673433,
|
|
"num_tokens": 24074977.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 6.23028597831726,
|
|
"epoch": 1.0386262343790964,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004898525183364284,
|
|
"loss": 5.9849,
|
|
"mean_token_accuracy": 0.15064526498317718,
|
|
"num_tokens": 24085673.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 6.209465217590332,
|
|
"epoch": 1.039063182731801,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004898432636945959,
|
|
"loss": 5.977,
|
|
"mean_token_accuracy": 0.15092883259058,
|
|
"num_tokens": 24095465.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 6.144705772399902,
|
|
"epoch": 1.0395001310845058,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.000489834004931957,
|
|
"loss": 5.9241,
|
|
"mean_token_accuracy": 0.1513504572212696,
|
|
"num_tokens": 24105576.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 6.171712017059326,
|
|
"epoch": 1.0399370794372105,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004898247420486895,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.1441113233566284,
|
|
"num_tokens": 24114998.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 6.17154221534729,
|
|
"epoch": 1.0403740277899152,
|
|
"grad_norm": 6.0625,
|
|
"learning_rate": 0.0004898154750449707,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.15080181807279586,
|
|
"num_tokens": 24125059.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 6.254666042327881,
|
|
"epoch": 1.0408109761426199,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004898062039209786,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.14852346032857894,
|
|
"num_tokens": 24134062.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 6.197595024108887,
|
|
"epoch": 1.0412479244953246,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.000489796928676891,
|
|
"loss": 5.9407,
|
|
"mean_token_accuracy": 0.14671702384948732,
|
|
"num_tokens": 24144016.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 6.18574538230896,
|
|
"epoch": 1.0416848728480295,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004897876493128856,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.14869166910648346,
|
|
"num_tokens": 24154337.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 6.145417070388794,
|
|
"epoch": 1.0421218212007342,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004897783658291406,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.15060929954051971,
|
|
"num_tokens": 24164440.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 6.201339292526245,
|
|
"epoch": 1.0425587695534388,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000489769078225834,
|
|
"loss": 6.0275,
|
|
"mean_token_accuracy": 0.14404802173376083,
|
|
"num_tokens": 24174388.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 6.180160903930664,
|
|
"epoch": 1.0429957179061435,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004897597865031441,
|
|
"loss": 5.8999,
|
|
"mean_token_accuracy": 0.15236803889274597,
|
|
"num_tokens": 24183543.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 6.1767994403839115,
|
|
"epoch": 1.0434326662588482,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004897504906612487,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.14996734261512756,
|
|
"num_tokens": 24193847.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 6.154396438598633,
|
|
"epoch": 1.043869614611553,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004897411907003265,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.1502672702074051,
|
|
"num_tokens": 24203072.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 6.178869199752808,
|
|
"epoch": 1.0443065629642576,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004897318866205558,
|
|
"loss": 5.8518,
|
|
"mean_token_accuracy": 0.15772329717874528,
|
|
"num_tokens": 24213610.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 6.079909324645996,
|
|
"epoch": 1.0447435113169623,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004897225784221149,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.15807106643915175,
|
|
"num_tokens": 24223571.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 6.1383027076721195,
|
|
"epoch": 1.045180459669667,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004897132661051826,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.1453519806265831,
|
|
"num_tokens": 24233867.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 6.146329164505005,
|
|
"epoch": 1.0456174080223717,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004897039496699372,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.14822976738214494,
|
|
"num_tokens": 24243853.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 6.166684150695801,
|
|
"epoch": 1.0460543563750764,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004896946291165575,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.14673857092857362,
|
|
"num_tokens": 24254049.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 6.150206089019775,
|
|
"epoch": 1.0464913047277813,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004896853044452224,
|
|
"loss": 5.9171,
|
|
"mean_token_accuracy": 0.14790754914283752,
|
|
"num_tokens": 24265166.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 6.174460506439209,
|
|
"epoch": 1.046928253080486,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004896759756561106,
|
|
"loss": 5.9162,
|
|
"mean_token_accuracy": 0.15014341622591018,
|
|
"num_tokens": 24274981.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 6.233915996551514,
|
|
"epoch": 1.0473652014331907,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004896666427494012,
|
|
"loss": 5.9401,
|
|
"mean_token_accuracy": 0.14949152767658233,
|
|
"num_tokens": 24285009.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 6.312009716033936,
|
|
"epoch": 1.0478021497858954,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000489657305725273,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.14560900554060935,
|
|
"num_tokens": 24294669.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 6.282224369049072,
|
|
"epoch": 1.0482390981386,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004896479645839052,
|
|
"loss": 5.9548,
|
|
"mean_token_accuracy": 0.14923173934221268,
|
|
"num_tokens": 24304647.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 6.093004846572876,
|
|
"epoch": 1.0486760464913047,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004896386193254771,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.1570341557264328,
|
|
"num_tokens": 24314266.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0486760464913047,
|
|
"eval_entropy": 5.884056688720525,
|
|
"eval_loss": 6.006004333496094,
|
|
"eval_mean_token_accuracy": 0.15266030561480842,
|
|
"eval_num_tokens": 24314266.0,
|
|
"eval_runtime": 28.2209,
|
|
"eval_samples_per_second": 1311.58,
|
|
"eval_steps_per_second": 163.956,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 6.100390911102295,
|
|
"epoch": 1.0491129948440094,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004896292699501677,
|
|
"loss": 5.9324,
|
|
"mean_token_accuracy": 0.14589439630508422,
|
|
"num_tokens": 24323770.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 6.182142543792724,
|
|
"epoch": 1.0495499431967141,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004896199164581564,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.15646701753139497,
|
|
"num_tokens": 24333438.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 6.1544561862945555,
|
|
"epoch": 1.0499868915494188,
|
|
"grad_norm": 12.625,
|
|
"learning_rate": 0.0004896105588496227,
|
|
"loss": 5.9399,
|
|
"mean_token_accuracy": 0.14933661073446275,
|
|
"num_tokens": 24342929.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 6.16118106842041,
|
|
"epoch": 1.0504238399021235,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004896011971247461,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.14823028296232224,
|
|
"num_tokens": 24352617.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 6.17752161026001,
|
|
"epoch": 1.0508607882548282,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004895918312837061,
|
|
"loss": 5.9224,
|
|
"mean_token_accuracy": 0.15364284068346024,
|
|
"num_tokens": 24363940.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 6.245773077011108,
|
|
"epoch": 1.051297736607533,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004895824613266822,
|
|
"loss": 5.9765,
|
|
"mean_token_accuracy": 0.14229566529393195,
|
|
"num_tokens": 24373168.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 6.2633058547973635,
|
|
"epoch": 1.0517346849602376,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004895730872538543,
|
|
"loss": 5.9968,
|
|
"mean_token_accuracy": 0.14618628546595575,
|
|
"num_tokens": 24383067.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 6.203412818908691,
|
|
"epoch": 1.0521716333129425,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004895637090654021,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.15422668531537057,
|
|
"num_tokens": 24392734.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 6.227333211898804,
|
|
"epoch": 1.0526085816656472,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004895543267615057,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.1483489379286766,
|
|
"num_tokens": 24403970.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 6.178986930847168,
|
|
"epoch": 1.0530455300183519,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004895449403423447,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.15066254287958145,
|
|
"num_tokens": 24413614.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 6.123789644241333,
|
|
"epoch": 1.0534824783710566,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004895355498080994,
|
|
"loss": 5.8726,
|
|
"mean_token_accuracy": 0.16127931773662568,
|
|
"num_tokens": 24424237.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 6.142438364028931,
|
|
"epoch": 1.0539194267237613,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.0004895261551589498,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.1540844053030014,
|
|
"num_tokens": 24433220.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 6.242302989959716,
|
|
"epoch": 1.054356375076466,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004895167563950763,
|
|
"loss": 6.0254,
|
|
"mean_token_accuracy": 0.14323251694440842,
|
|
"num_tokens": 24444224.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 6.2590171813964846,
|
|
"epoch": 1.0547933234291706,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004895073535166588,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.1430962413549423,
|
|
"num_tokens": 24454431.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 6.243322563171387,
|
|
"epoch": 1.0552302717818753,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004894979465238779,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.14977423772215842,
|
|
"num_tokens": 24464006.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 6.174377155303955,
|
|
"epoch": 1.05566722013458,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004894885354169141,
|
|
"loss": 5.8648,
|
|
"mean_token_accuracy": 0.14857657104730607,
|
|
"num_tokens": 24472706.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 6.15708589553833,
|
|
"epoch": 1.0561041684872847,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004894791201959477,
|
|
"loss": 5.8885,
|
|
"mean_token_accuracy": 0.1566796638071537,
|
|
"num_tokens": 24482785.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 6.160139656066894,
|
|
"epoch": 1.0565411168399894,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004894697008611594,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.14761830270290374,
|
|
"num_tokens": 24493318.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 6.148003339767456,
|
|
"epoch": 1.0569780651926943,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004894602774127299,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.1446126401424408,
|
|
"num_tokens": 24503780.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 6.285747718811035,
|
|
"epoch": 1.057415013545399,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004894508498508399,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.14292212575674057,
|
|
"num_tokens": 24513905.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 6.241286563873291,
|
|
"epoch": 1.0578519618981037,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004894414181756702,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.15671780258417128,
|
|
"num_tokens": 24524194.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 6.186323499679565,
|
|
"epoch": 1.0582889102508084,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004894319823874017,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.1467944286763668,
|
|
"num_tokens": 24533456.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 6.2142415046691895,
|
|
"epoch": 1.058725858603513,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004894225424862154,
|
|
"loss": 5.9558,
|
|
"mean_token_accuracy": 0.14688051193952562,
|
|
"num_tokens": 24544191.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 6.14606819152832,
|
|
"epoch": 1.0591628069562178,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004894130984722926,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.15194664970040322,
|
|
"num_tokens": 24554353.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 6.147780084609986,
|
|
"epoch": 1.0595997553089225,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000489403650345814,
|
|
"loss": 5.98,
|
|
"mean_token_accuracy": 0.14456124007701873,
|
|
"num_tokens": 24564313.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 6.200004577636719,
|
|
"epoch": 1.0600367036616272,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004893941981069612,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.1462851420044899,
|
|
"num_tokens": 24573129.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 6.153363609313965,
|
|
"epoch": 1.0604736520143319,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004893847417559152,
|
|
"loss": 5.8485,
|
|
"mean_token_accuracy": 0.1546036720275879,
|
|
"num_tokens": 24582324.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 6.2165992736816404,
|
|
"epoch": 1.0609106003670365,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004893752812928576,
|
|
"loss": 5.9972,
|
|
"mean_token_accuracy": 0.14059825390577316,
|
|
"num_tokens": 24593360.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 6.2215382099151615,
|
|
"epoch": 1.0613475487197412,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004893658167179697,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.15346293598413469,
|
|
"num_tokens": 24603597.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 6.166983270645142,
|
|
"epoch": 1.061784497072446,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004893563480314331,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.15244588255882263,
|
|
"num_tokens": 24612426.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 6.158516788482666,
|
|
"epoch": 1.0622214454251508,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004893468752334294,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.14777790904045104,
|
|
"num_tokens": 24623031.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 6.157711505889893,
|
|
"epoch": 1.0626583937778555,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004893373983241404,
|
|
"loss": 5.9401,
|
|
"mean_token_accuracy": 0.1478666692972183,
|
|
"num_tokens": 24633763.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 6.1805846214294435,
|
|
"epoch": 1.0630953421305602,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004893279173037478,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.14446838200092316,
|
|
"num_tokens": 24644340.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 6.208295249938965,
|
|
"epoch": 1.063532290483265,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004893184321724335,
|
|
"loss": 5.9607,
|
|
"mean_token_accuracy": 0.15800270587205886,
|
|
"num_tokens": 24654751.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 6.2193244934082035,
|
|
"epoch": 1.0639692388359696,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004893089429303792,
|
|
"loss": 5.9103,
|
|
"mean_token_accuracy": 0.15098214745521546,
|
|
"num_tokens": 24665134.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 6.155243730545044,
|
|
"epoch": 1.0644061871886743,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004892994495777672,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.14569930657744407,
|
|
"num_tokens": 24673796.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 6.106982469558716,
|
|
"epoch": 1.064843135541379,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004892899521147794,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.16166339367628096,
|
|
"num_tokens": 24684104.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 6.0830785751342775,
|
|
"epoch": 1.0652800838940837,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000489280450541598,
|
|
"loss": 5.8652,
|
|
"mean_token_accuracy": 0.1524901419878006,
|
|
"num_tokens": 24693994.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 6.155972719192505,
|
|
"epoch": 1.0657170322467884,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004892709448584054,
|
|
"loss": 5.9318,
|
|
"mean_token_accuracy": 0.14918644726276398,
|
|
"num_tokens": 24703815.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 6.23654956817627,
|
|
"epoch": 1.066153980599493,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004892614350653837,
|
|
"loss": 5.8798,
|
|
"mean_token_accuracy": 0.15056822299957276,
|
|
"num_tokens": 24713631.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 6.240795707702636,
|
|
"epoch": 1.0665909289521978,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004892519211627156,
|
|
"loss": 5.9281,
|
|
"mean_token_accuracy": 0.15143959522247313,
|
|
"num_tokens": 24723353.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 6.17115216255188,
|
|
"epoch": 1.0670278773049025,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004892424031505832,
|
|
"loss": 5.9122,
|
|
"mean_token_accuracy": 0.14854995906352997,
|
|
"num_tokens": 24733246.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 6.153678703308105,
|
|
"epoch": 1.0674648256576074,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004892328810291693,
|
|
"loss": 5.8932,
|
|
"mean_token_accuracy": 0.1565846860408783,
|
|
"num_tokens": 24743097.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 6.109102964401245,
|
|
"epoch": 1.067901774010312,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004892233547986564,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.15516779869794844,
|
|
"num_tokens": 24752618.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 6.216071701049804,
|
|
"epoch": 1.0683387223630167,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004892138244592274,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.15100240260362624,
|
|
"num_tokens": 24763960.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 6.182392311096192,
|
|
"epoch": 1.0687756707157214,
|
|
"grad_norm": 5.46875,
|
|
"learning_rate": 0.0004892042900110649,
|
|
"loss": 5.8288,
|
|
"mean_token_accuracy": 0.15177802741527557,
|
|
"num_tokens": 24773040.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 6.1401246070861815,
|
|
"epoch": 1.0692126190684261,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.000489194751454352,
|
|
"loss": 5.9465,
|
|
"mean_token_accuracy": 0.14840585142374038,
|
|
"num_tokens": 24783049.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 6.225646018981934,
|
|
"epoch": 1.0696495674211308,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004891852087892714,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.14651037156581878,
|
|
"num_tokens": 24794590.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 6.158383131027222,
|
|
"epoch": 1.0700865157738355,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004891756620160064,
|
|
"loss": 5.8439,
|
|
"mean_token_accuracy": 0.15536906868219375,
|
|
"num_tokens": 24805146.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 6.129940366744995,
|
|
"epoch": 1.0705234641265402,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004891661111347399,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.14204553216695787,
|
|
"num_tokens": 24815573.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 6.173180103302002,
|
|
"epoch": 1.070960412479245,
|
|
"grad_norm": 6.375,
|
|
"learning_rate": 0.0004891565561456552,
|
|
"loss": 5.8587,
|
|
"mean_token_accuracy": 0.15503737926483155,
|
|
"num_tokens": 24825417.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 6.095524835586548,
|
|
"epoch": 1.0713973608319496,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004891469970489355,
|
|
"loss": 5.8864,
|
|
"mean_token_accuracy": 0.15385202467441558,
|
|
"num_tokens": 24835589.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 6.116691255569458,
|
|
"epoch": 1.0718343091846543,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004891374338447642,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.1440843388438225,
|
|
"num_tokens": 24846603.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 6.219188451766968,
|
|
"epoch": 1.0722712575373592,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004891278665333247,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.14616507589817046,
|
|
"num_tokens": 24856368.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 6.1318151473999025,
|
|
"epoch": 1.0727082058900639,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004891182951148005,
|
|
"loss": 5.8091,
|
|
"mean_token_accuracy": 0.15435133129358292,
|
|
"num_tokens": 24866322.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 6.134053373336792,
|
|
"epoch": 1.0731451542427686,
|
|
"grad_norm": 5.0625,
|
|
"learning_rate": 0.0004891087195893753,
|
|
"loss": 5.9351,
|
|
"mean_token_accuracy": 0.14491613283753396,
|
|
"num_tokens": 24876686.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 6.1039286136627195,
|
|
"epoch": 1.0735821025954733,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004890991399572325,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.15078727751970292,
|
|
"num_tokens": 24886561.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 6.209589958190918,
|
|
"epoch": 1.074019050948178,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004890895562185562,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.14919467717409135,
|
|
"num_tokens": 24896010.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 6.2686793327331545,
|
|
"epoch": 1.0744559993008826,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004890799683735299,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.14493292868137359,
|
|
"num_tokens": 24904852.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 6.19042387008667,
|
|
"epoch": 1.0748929476535873,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004890703764223377,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.1475605010986328,
|
|
"num_tokens": 24914828.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 6.180906343460083,
|
|
"epoch": 1.075329896006292,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004890607803651635,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.1379154935479164,
|
|
"num_tokens": 24925602.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 6.17429141998291,
|
|
"epoch": 1.0757668443589967,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004890511802021914,
|
|
"loss": 5.9529,
|
|
"mean_token_accuracy": 0.15566674172878264,
|
|
"num_tokens": 24935175.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 6.208604955673218,
|
|
"epoch": 1.0762037927117014,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004890415759336053,
|
|
"loss": 5.9589,
|
|
"mean_token_accuracy": 0.14076291993260384,
|
|
"num_tokens": 24945828.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 6.209710884094238,
|
|
"epoch": 1.076640741064406,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004890319675595899,
|
|
"loss": 5.907,
|
|
"mean_token_accuracy": 0.15007260888814927,
|
|
"num_tokens": 24955400.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 6.172647190093994,
|
|
"epoch": 1.0770776894171108,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.000489022355080329,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.14173820465803147,
|
|
"num_tokens": 24966079.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 6.148740291595459,
|
|
"epoch": 1.0775146377698157,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004890127384960073,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.15463101342320443,
|
|
"num_tokens": 24975090.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 6.265727901458741,
|
|
"epoch": 1.0779515861225204,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004890031178068091,
|
|
"loss": 6.0046,
|
|
"mean_token_accuracy": 0.1382139004766941,
|
|
"num_tokens": 24986068.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 6.197646760940552,
|
|
"epoch": 1.078388534475225,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.000488993493012919,
|
|
"loss": 5.9696,
|
|
"mean_token_accuracy": 0.15166736245155335,
|
|
"num_tokens": 24995697.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 6.169878768920898,
|
|
"epoch": 1.0788254828279298,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004889838641145215,
|
|
"loss": 5.9155,
|
|
"mean_token_accuracy": 0.14484099447727203,
|
|
"num_tokens": 25005602.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 6.252286529541015,
|
|
"epoch": 1.0792624311806345,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004889742311118014,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.15457540899515151,
|
|
"num_tokens": 25016407.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 6.308634328842163,
|
|
"epoch": 1.0796993795333392,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004889645940049434,
|
|
"loss": 5.982,
|
|
"mean_token_accuracy": 0.14494881108403207,
|
|
"num_tokens": 25025889.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 6.186164379119873,
|
|
"epoch": 1.0801363278860439,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004889549527941324,
|
|
"loss": 5.9301,
|
|
"mean_token_accuracy": 0.15099339187145233,
|
|
"num_tokens": 25036383.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 6.186786317825318,
|
|
"epoch": 1.0805732762387485,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004889453074795534,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.13621387705206872,
|
|
"num_tokens": 25045718.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 6.19301700592041,
|
|
"epoch": 1.0810102245914532,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004889356580613911,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.14771054461598396,
|
|
"num_tokens": 25056244.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 6.242445611953736,
|
|
"epoch": 1.081447172944158,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000488926004539831,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.15063196271657944,
|
|
"num_tokens": 25065954.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 6.198996686935425,
|
|
"epoch": 1.0818841212968626,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004889163469150578,
|
|
"loss": 5.9832,
|
|
"mean_token_accuracy": 0.14517340958118438,
|
|
"num_tokens": 25075851.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 6.1527872562408445,
|
|
"epoch": 1.0823210696495673,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004889066851872571,
|
|
"loss": 5.938,
|
|
"mean_token_accuracy": 0.1523074522614479,
|
|
"num_tokens": 25085324.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 6.178440189361572,
|
|
"epoch": 1.0827580180022722,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000488897019356614,
|
|
"loss": 5.9744,
|
|
"mean_token_accuracy": 0.14243398308753968,
|
|
"num_tokens": 25096566.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 6.274006700515747,
|
|
"epoch": 1.083194966354977,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004888873494233141,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.13726802542805672,
|
|
"num_tokens": 25107642.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 6.204235172271728,
|
|
"epoch": 1.0836319147076816,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004888776753875427,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.15124789029359817,
|
|
"num_tokens": 25117488.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 6.14057731628418,
|
|
"epoch": 1.0840688630603863,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004888679972494854,
|
|
"loss": 5.8783,
|
|
"mean_token_accuracy": 0.15421270728111267,
|
|
"num_tokens": 25127107.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 6.108871221542358,
|
|
"epoch": 1.084505811413091,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000488858315009328,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.14985944032669068,
|
|
"num_tokens": 25138272.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 6.175687646865844,
|
|
"epoch": 1.0849427597657957,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004888486286672559,
|
|
"loss": 5.9652,
|
|
"mean_token_accuracy": 0.14317135363817216,
|
|
"num_tokens": 25147128.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 6.2086694717407225,
|
|
"epoch": 1.0853797081185004,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004888389382234551,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.1534759894013405,
|
|
"num_tokens": 25157418.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 6.211604595184326,
|
|
"epoch": 1.085816656471205,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004888292436781114,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.15103035420179367,
|
|
"num_tokens": 25168123.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 6.107608413696289,
|
|
"epoch": 1.0862536048239098,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004888195450314108,
|
|
"loss": 5.9168,
|
|
"mean_token_accuracy": 0.1523303858935833,
|
|
"num_tokens": 25178445.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 6.144627666473388,
|
|
"epoch": 1.0866905531766144,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004888098422835392,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.1374790109694004,
|
|
"num_tokens": 25189246.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 6.1797661781311035,
|
|
"epoch": 1.0871275015293191,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004888001354346828,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.14563697203993797,
|
|
"num_tokens": 25201277.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 6.2508142471313475,
|
|
"epoch": 1.087564449882024,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004887904244850279,
|
|
"loss": 5.9527,
|
|
"mean_token_accuracy": 0.14970300942659379,
|
|
"num_tokens": 25211353.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 6.230410814285278,
|
|
"epoch": 1.0880013982347287,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.0004887807094347606,
|
|
"loss": 5.9231,
|
|
"mean_token_accuracy": 0.1498468391597271,
|
|
"num_tokens": 25222236.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 6.127790260314941,
|
|
"epoch": 1.0884383465874334,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004887709902840672,
|
|
"loss": 5.8448,
|
|
"mean_token_accuracy": 0.15379466414451598,
|
|
"num_tokens": 25232464.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 6.154881811141967,
|
|
"epoch": 1.0888752949401381,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004887612670331342,
|
|
"loss": 5.9224,
|
|
"mean_token_accuracy": 0.14510940238833428,
|
|
"num_tokens": 25243518.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 6.16659517288208,
|
|
"epoch": 1.0893122432928428,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004887515396821481,
|
|
"loss": 5.9331,
|
|
"mean_token_accuracy": 0.14443064704537392,
|
|
"num_tokens": 25253168.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 6.178592395782471,
|
|
"epoch": 1.0897491916455475,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004887418082312955,
|
|
"loss": 5.8977,
|
|
"mean_token_accuracy": 0.15176382958889006,
|
|
"num_tokens": 25262750.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 6.173739385604859,
|
|
"epoch": 1.0901861399982522,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.000488732072680763,
|
|
"loss": 5.9172,
|
|
"mean_token_accuracy": 0.14840522408485413,
|
|
"num_tokens": 25273520.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 6.192647075653076,
|
|
"epoch": 1.090623088350957,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004887223330307373,
|
|
"loss": 5.96,
|
|
"mean_token_accuracy": 0.14730576574802398,
|
|
"num_tokens": 25284136.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 6.162393379211426,
|
|
"epoch": 1.0910600367036616,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004887125892814053,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.1461636930704117,
|
|
"num_tokens": 25294523.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 6.145088958740234,
|
|
"epoch": 1.0914969850563663,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004887028414329538,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.1463019907474518,
|
|
"num_tokens": 25305050.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 6.197679042816162,
|
|
"epoch": 1.091933933409071,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048869308948557,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.1485550343990326,
|
|
"num_tokens": 25314445.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 6.189301538467407,
|
|
"epoch": 1.0923708817617757,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004886833334394406,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.1524156928062439,
|
|
"num_tokens": 25324426.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 6.187959003448486,
|
|
"epoch": 1.0928078301144806,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004886735732947529,
|
|
"loss": 5.9239,
|
|
"mean_token_accuracy": 0.15090341120958328,
|
|
"num_tokens": 25335051.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 6.169259023666382,
|
|
"epoch": 1.0932447784671853,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004886638090516942,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.15351396203041076,
|
|
"num_tokens": 25343955.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 6.115030527114868,
|
|
"epoch": 1.09368172681989,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004886540407104517,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.14472192227840425,
|
|
"num_tokens": 25353817.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 6.239952564239502,
|
|
"epoch": 1.0941186751725946,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004886442682712126,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.14718974381685257,
|
|
"num_tokens": 25363882.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 6.227929401397705,
|
|
"epoch": 1.0945556235252993,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004886344917341646,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.15139144361019136,
|
|
"num_tokens": 25373721.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 6.140818977355957,
|
|
"epoch": 1.094992571878004,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.0004886247110994952,
|
|
"loss": 5.9173,
|
|
"mean_token_accuracy": 0.149771024286747,
|
|
"num_tokens": 25383520.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 6.140714836120606,
|
|
"epoch": 1.0954295202307087,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004886149263673916,
|
|
"loss": 5.8963,
|
|
"mean_token_accuracy": 0.15616434812545776,
|
|
"num_tokens": 25394039.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 6.17752161026001,
|
|
"epoch": 1.0958664685834134,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000488605137538042,
|
|
"loss": 5.9279,
|
|
"mean_token_accuracy": 0.14835054725408553,
|
|
"num_tokens": 25403404.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 6.11985149383545,
|
|
"epoch": 1.096303416936118,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004885953446116339,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.14923788011074066,
|
|
"num_tokens": 25413800.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 6.14561448097229,
|
|
"epoch": 1.0967403652888228,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004885855475883551,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.15641434043645858,
|
|
"num_tokens": 25424252.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 6.235609436035157,
|
|
"epoch": 1.0971773136415275,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004885757464683937,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.1519485369324684,
|
|
"num_tokens": 25433381.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 6.1403765201568605,
|
|
"epoch": 1.0976142619942322,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004885659412519376,
|
|
"loss": 5.8595,
|
|
"mean_token_accuracy": 0.15306203961372375,
|
|
"num_tokens": 25443253.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 6.111497020721435,
|
|
"epoch": 1.098051210346937,
|
|
"grad_norm": 7.78125,
|
|
"learning_rate": 0.0004885561319391747,
|
|
"loss": 5.9622,
|
|
"mean_token_accuracy": 0.14385128617286683,
|
|
"num_tokens": 25453590.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 6.168994331359864,
|
|
"epoch": 1.0984881586996418,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.0004885463185302934,
|
|
"loss": 5.9074,
|
|
"mean_token_accuracy": 0.15635205805301666,
|
|
"num_tokens": 25464065.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 6.264686918258667,
|
|
"epoch": 1.0989251070523465,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004885365010254817,
|
|
"loss": 6.0071,
|
|
"mean_token_accuracy": 0.1437750354409218,
|
|
"num_tokens": 25475236.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 6.2338732242584225,
|
|
"epoch": 1.0993620554050512,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004885266794249281,
|
|
"loss": 5.9851,
|
|
"mean_token_accuracy": 0.1526201382279396,
|
|
"num_tokens": 25485200.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 6.190126037597656,
|
|
"epoch": 1.0997990037577559,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004885168537288209,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.15273040235042573,
|
|
"num_tokens": 25494775.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 6.228781986236572,
|
|
"epoch": 1.1002359521104605,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004885070239373484,
|
|
"loss": 5.9358,
|
|
"mean_token_accuracy": 0.14743367880582808,
|
|
"num_tokens": 25504435.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 6.1857123374938965,
|
|
"epoch": 1.1006729004631652,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004884971900506995,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.1494644284248352,
|
|
"num_tokens": 25514085.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 6.25676736831665,
|
|
"epoch": 1.10110984881587,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004884873520690626,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.14542241394519806,
|
|
"num_tokens": 25523988.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 6.197001504898071,
|
|
"epoch": 1.1015467971685746,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004884775099926264,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.1485779508948326,
|
|
"num_tokens": 25534469.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 6.212598848342895,
|
|
"epoch": 1.1019837455212793,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004884676638215797,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.14274339526891708,
|
|
"num_tokens": 25544854.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 6.2349677085876465,
|
|
"epoch": 1.102420693873984,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004884578135561113,
|
|
"loss": 5.9017,
|
|
"mean_token_accuracy": 0.1462556853890419,
|
|
"num_tokens": 25555465.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 6.174994707107544,
|
|
"epoch": 1.102857642226689,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004884479591964103,
|
|
"loss": 5.9508,
|
|
"mean_token_accuracy": 0.15059880614280702,
|
|
"num_tokens": 25565949.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 6.192708539962768,
|
|
"epoch": 1.1032945905793936,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004884381007426654,
|
|
"loss": 5.9354,
|
|
"mean_token_accuracy": 0.14404048919677734,
|
|
"num_tokens": 25576511.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 6.182388114929199,
|
|
"epoch": 1.1037315389320983,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004884282381950661,
|
|
"loss": 5.8686,
|
|
"mean_token_accuracy": 0.1456463098526001,
|
|
"num_tokens": 25587224.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 6.172303533554077,
|
|
"epoch": 1.104168487284803,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004884183715538012,
|
|
"loss": 5.9054,
|
|
"mean_token_accuracy": 0.15106040462851525,
|
|
"num_tokens": 25596696.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 6.1065895557403564,
|
|
"epoch": 1.1046054356375077,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004884085008190602,
|
|
"loss": 5.8387,
|
|
"mean_token_accuracy": 0.1551930382847786,
|
|
"num_tokens": 25606829.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 6.141040468215943,
|
|
"epoch": 1.1050423839902124,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004883986259910323,
|
|
"loss": 5.9142,
|
|
"mean_token_accuracy": 0.15261392295360565,
|
|
"num_tokens": 25617122.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 6.185095930099488,
|
|
"epoch": 1.105479332342917,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004883887470699069,
|
|
"loss": 5.8853,
|
|
"mean_token_accuracy": 0.1480973869562149,
|
|
"num_tokens": 25626485.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 6.163683032989502,
|
|
"epoch": 1.1059162806956218,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004883788640558735,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.15037520676851274,
|
|
"num_tokens": 25636695.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 6.015004873275757,
|
|
"epoch": 1.1063532290483264,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004883689769491218,
|
|
"loss": 5.768,
|
|
"mean_token_accuracy": 0.16217269003391266,
|
|
"num_tokens": 25646169.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 6.142358684539795,
|
|
"epoch": 1.1067901774010311,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004883590857498413,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.1473284512758255,
|
|
"num_tokens": 25656728.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 6.22428331375122,
|
|
"epoch": 1.1072271257537358,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004883491904582217,
|
|
"loss": 5.8926,
|
|
"mean_token_accuracy": 0.15063771679997445,
|
|
"num_tokens": 25666184.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 6.219676780700683,
|
|
"epoch": 1.1076640741064405,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004883392910744528,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.15376341938972474,
|
|
"num_tokens": 25675571.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 6.211104822158814,
|
|
"epoch": 1.1081010224591452,
|
|
"grad_norm": 5.78125,
|
|
"learning_rate": 0.0004883293875987245,
|
|
"loss": 5.9353,
|
|
"mean_token_accuracy": 0.1464277945458889,
|
|
"num_tokens": 25685485.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 6.087258625030517,
|
|
"epoch": 1.1085379708118501,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004883194800312268,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.15398255437612535,
|
|
"num_tokens": 25695278.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 6.1708001613616945,
|
|
"epoch": 1.1089749191645548,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004883095683721497,
|
|
"loss": 5.9207,
|
|
"mean_token_accuracy": 0.15454749017953873,
|
|
"num_tokens": 25704410.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 6.186515378952026,
|
|
"epoch": 1.1094118675172595,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004882996526216833,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.14819520488381385,
|
|
"num_tokens": 25715027.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 6.228687143325805,
|
|
"epoch": 1.1098488158699642,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004882897327800178,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.1518068417906761,
|
|
"num_tokens": 25723992.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 6.212923622131347,
|
|
"epoch": 1.110285764222669,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004882798088473435,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.1467521905899048,
|
|
"num_tokens": 25733791.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 6.159442901611328,
|
|
"epoch": 1.1107227125753736,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048826988082385065,
|
|
"loss": 5.9207,
|
|
"mean_token_accuracy": 0.14514946714043617,
|
|
"num_tokens": 25743258.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 6.160631990432739,
|
|
"epoch": 1.1111596609280783,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048825994870972976,
|
|
"loss": 5.9438,
|
|
"mean_token_accuracy": 0.14972086474299431,
|
|
"num_tokens": 25753183.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 6.220805501937866,
|
|
"epoch": 1.111596609280783,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.00048825001250517124,
|
|
"loss": 5.9722,
|
|
"mean_token_accuracy": 0.14766730591654778,
|
|
"num_tokens": 25763308.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 6.199866914749146,
|
|
"epoch": 1.1120335576334877,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004882400722103658,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.1589813455939293,
|
|
"num_tokens": 25774269.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 6.055586147308349,
|
|
"epoch": 1.1124705059861923,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.000488230127825504,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.15525724738836288,
|
|
"num_tokens": 25785194.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 6.151578140258789,
|
|
"epoch": 1.112907454338897,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048822017935077673,
|
|
"loss": 5.8963,
|
|
"mean_token_accuracy": 0.15453674048185348,
|
|
"num_tokens": 25793927.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 6.212102222442627,
|
|
"epoch": 1.113344402691602,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004882102267863746,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.14770420044660568,
|
|
"num_tokens": 25805395.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 6.214001703262329,
|
|
"epoch": 1.1137813510443066,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048820027013248864,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.1472778335213661,
|
|
"num_tokens": 25816594.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 6.243660402297974,
|
|
"epoch": 1.1142182993970113,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048819030938930974,
|
|
"loss": 5.8968,
|
|
"mean_token_accuracy": 0.15108416527509688,
|
|
"num_tokens": 25825943.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 6.138241147994995,
|
|
"epoch": 1.114655247749716,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000488180344557029,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.15438546389341354,
|
|
"num_tokens": 25835928.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 6.1140360832214355,
|
|
"epoch": 1.1150921961024207,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004881703756358376,
|
|
"loss": 5.9289,
|
|
"mean_token_accuracy": 0.14904947578907013,
|
|
"num_tokens": 25847363.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 6.161057662963867,
|
|
"epoch": 1.1155291444551254,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004881604026259266,
|
|
"loss": 5.9381,
|
|
"mean_token_accuracy": 0.1508537843823433,
|
|
"num_tokens": 25857246.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 6.285070276260376,
|
|
"epoch": 1.11596609280783,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00048815042552748745,
|
|
"loss": 5.952,
|
|
"mean_token_accuracy": 0.1469726085662842,
|
|
"num_tokens": 25866615.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 6.225005435943603,
|
|
"epoch": 1.1164030411605348,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004881404443407115,
|
|
"loss": 6.0025,
|
|
"mean_token_accuracy": 0.14359909892082215,
|
|
"num_tokens": 25876698.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 6.239930868148804,
|
|
"epoch": 1.1168399895132395,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00048813045906579,
|
|
"loss": 5.9767,
|
|
"mean_token_accuracy": 0.1381794475018978,
|
|
"num_tokens": 25888029.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 6.168526124954224,
|
|
"epoch": 1.1172769378659442,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048812046970291473,
|
|
"loss": 6.0075,
|
|
"mean_token_accuracy": 0.14545436352491378,
|
|
"num_tokens": 25897472.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 6.277098894119263,
|
|
"epoch": 1.1177138862186489,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004881104762522772,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.14485169649124147,
|
|
"num_tokens": 25908025.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 6.309070301055908,
|
|
"epoch": 1.1181508345713538,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000488100478714069,
|
|
"loss": 5.949,
|
|
"mean_token_accuracy": 0.1473851904273033,
|
|
"num_tokens": 25919110.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 6.157921648025512,
|
|
"epoch": 1.1185877829240585,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.00048809047708848194,
|
|
"loss": 5.8712,
|
|
"mean_token_accuracy": 0.15649706423282622,
|
|
"num_tokens": 25928322.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 6.076091861724853,
|
|
"epoch": 1.1190247312767632,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048808047137570795,
|
|
"loss": 5.8379,
|
|
"mean_token_accuracy": 0.14862755611538886,
|
|
"num_tokens": 25937347.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 6.091773843765258,
|
|
"epoch": 1.1194616796294679,
|
|
"grad_norm": 5.5,
|
|
"learning_rate": 0.0004880704615759388,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.15211082249879837,
|
|
"num_tokens": 25948408.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 6.198835706710815,
|
|
"epoch": 1.1198986279821725,
|
|
"grad_norm": 5.9375,
|
|
"learning_rate": 0.00048806044768936655,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.14384416937828065,
|
|
"num_tokens": 25958249.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 6.22984299659729,
|
|
"epoch": 1.1203355763348772,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004880504297161833,
|
|
"loss": 5.9729,
|
|
"mean_token_accuracy": 0.1435294672846794,
|
|
"num_tokens": 25968849.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 6.186871814727783,
|
|
"epoch": 1.120772524687582,
|
|
"grad_norm": 8.1875,
|
|
"learning_rate": 0.00048804040765658115,
|
|
"loss": 5.9722,
|
|
"mean_token_accuracy": 0.149842718988657,
|
|
"num_tokens": 25978787.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 6.126379680633545,
|
|
"epoch": 1.1212094730402866,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048803038151075227,
|
|
"loss": 5.9149,
|
|
"mean_token_accuracy": 0.15154345333576202,
|
|
"num_tokens": 25988619.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 6.208881092071533,
|
|
"epoch": 1.1216464213929913,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004880203512788892,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.1463656470179558,
|
|
"num_tokens": 25999080.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 6.21388988494873,
|
|
"epoch": 1.122083369745696,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048801031696118406,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.1544377714395523,
|
|
"num_tokens": 26010329.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 6.149548673629761,
|
|
"epoch": 1.1225203180984007,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004880002785578295,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.14981589317321778,
|
|
"num_tokens": 26019147.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 6.128245210647583,
|
|
"epoch": 1.1229572664511054,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000487990236069018,
|
|
"loss": 5.9103,
|
|
"mean_token_accuracy": 0.1495534211397171,
|
|
"num_tokens": 26029212.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 6.188356161117554,
|
|
"epoch": 1.12339421480381,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048798018949494214,
|
|
"loss": 5.7797,
|
|
"mean_token_accuracy": 0.1502614289522171,
|
|
"num_tokens": 26038059.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 6.195520257949829,
|
|
"epoch": 1.123831163156515,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004879701388357946,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.139035477489233,
|
|
"num_tokens": 26048076.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 6.141154003143311,
|
|
"epoch": 1.1242681115092197,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004879600840917683,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.14810874313116074,
|
|
"num_tokens": 26059006.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 6.15558557510376,
|
|
"epoch": 1.1247050598619244,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004879500252630559,
|
|
"loss": 5.8715,
|
|
"mean_token_accuracy": 0.1544817343354225,
|
|
"num_tokens": 26069275.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 6.182112789154052,
|
|
"epoch": 1.125142008214629,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004879399623498504,
|
|
"loss": 5.8542,
|
|
"mean_token_accuracy": 0.15223054438829423,
|
|
"num_tokens": 26078869.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 6.172968101501465,
|
|
"epoch": 1.1255789565673338,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.000487929895352345,
|
|
"loss": 5.8624,
|
|
"mean_token_accuracy": 0.14759116023778915,
|
|
"num_tokens": 26088544.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 6.0676685810089115,
|
|
"epoch": 1.1260159049200384,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004879198242707325,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.1578221946954727,
|
|
"num_tokens": 26097503.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 6.253616619110107,
|
|
"epoch": 1.1264528532727431,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048790974910520627,
|
|
"loss": 5.9791,
|
|
"mean_token_accuracy": 0.1464863285422325,
|
|
"num_tokens": 26107228.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 6.182883834838867,
|
|
"epoch": 1.1268898016254478,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.00048789966985595946,
|
|
"loss": 5.9061,
|
|
"mean_token_accuracy": 0.15523041635751725,
|
|
"num_tokens": 26117633.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 6.113433408737182,
|
|
"epoch": 1.1273267499781525,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004878895865231854,
|
|
"loss": 5.9354,
|
|
"mean_token_accuracy": 0.14570484161376954,
|
|
"num_tokens": 26127781.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 6.192937850952148,
|
|
"epoch": 1.1277636983308572,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004878794991070776,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.15598804056644439,
|
|
"num_tokens": 26137675.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 6.211550092697143,
|
|
"epoch": 1.128200646683562,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048786940760782937,
|
|
"loss": 6.0002,
|
|
"mean_token_accuracy": 0.14600116685032843,
|
|
"num_tokens": 26148572.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 6.159525442123413,
|
|
"epoch": 1.1286375950362668,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048785931202563443,
|
|
"loss": 5.9757,
|
|
"mean_token_accuracy": 0.15151511877775192,
|
|
"num_tokens": 26159261.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 6.161359024047852,
|
|
"epoch": 1.1290745433889715,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004878492123606863,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.14990262165665627,
|
|
"num_tokens": 26170072.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 6.203384733200073,
|
|
"epoch": 1.1295114917416762,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048783910861317873,
|
|
"loss": 5.8786,
|
|
"mean_token_accuracy": 0.14958043470978738,
|
|
"num_tokens": 26179947.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 6.249737024307251,
|
|
"epoch": 1.129948440094381,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048782900078330556,
|
|
"loss": 5.9246,
|
|
"mean_token_accuracy": 0.14690151065587997,
|
|
"num_tokens": 26189982.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 6.246534252166748,
|
|
"epoch": 1.1303853884470856,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004878188888712606,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.137100001424551,
|
|
"num_tokens": 26200832.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 6.14182710647583,
|
|
"epoch": 1.1308223367997903,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004878087728772379,
|
|
"loss": 5.9764,
|
|
"mean_token_accuracy": 0.14586392045021057,
|
|
"num_tokens": 26211506.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 6.121871566772461,
|
|
"epoch": 1.131259285152495,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004877986528014314,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.14971708208322526,
|
|
"num_tokens": 26222045.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 6.124219799041748,
|
|
"epoch": 1.1316962335051997,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004877885286440353,
|
|
"loss": 5.8293,
|
|
"mean_token_accuracy": 0.15299318581819535,
|
|
"num_tokens": 26231411.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 6.176163387298584,
|
|
"epoch": 1.1321331818579043,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048777840040524365,
|
|
"loss": 5.9419,
|
|
"mean_token_accuracy": 0.14727454632520676,
|
|
"num_tokens": 26241491.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 6.1419812679290775,
|
|
"epoch": 1.132570130210609,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048776826808525074,
|
|
"loss": 6.0072,
|
|
"mean_token_accuracy": 0.14592743515968323,
|
|
"num_tokens": 26252037.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 6.187282514572144,
|
|
"epoch": 1.1330070785633137,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048775813168425104,
|
|
"loss": 6.0075,
|
|
"mean_token_accuracy": 0.14510024040937425,
|
|
"num_tokens": 26262310.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 6.220762872695923,
|
|
"epoch": 1.1334440269160186,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048774799120243883,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.1512672409415245,
|
|
"num_tokens": 26273001.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 6.204404687881469,
|
|
"epoch": 1.1338809752687231,
|
|
"grad_norm": 5.625,
|
|
"learning_rate": 0.0004877378466400087,
|
|
"loss": 5.9418,
|
|
"mean_token_accuracy": 0.15215789824724196,
|
|
"num_tokens": 26283500.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 6.102461242675782,
|
|
"epoch": 1.134317923621428,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004877276979971552,
|
|
"loss": 5.8917,
|
|
"mean_token_accuracy": 0.14968496486544608,
|
|
"num_tokens": 26294118.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 6.23026123046875,
|
|
"epoch": 1.1347548719741327,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000487717545274073,
|
|
"loss": 6.0188,
|
|
"mean_token_accuracy": 0.14182747900485992,
|
|
"num_tokens": 26303833.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 6.237927532196045,
|
|
"epoch": 1.1351918203268374,
|
|
"grad_norm": 4.75,
|
|
"learning_rate": 0.00048770738847095683,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.1449764922261238,
|
|
"num_tokens": 26313542.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 6.137920904159546,
|
|
"epoch": 1.135628768679542,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048769722758800144,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.1549493372440338,
|
|
"num_tokens": 26322783.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 6.217292070388794,
|
|
"epoch": 1.1360657170322468,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004876870626254018,
|
|
"loss": 5.9672,
|
|
"mean_token_accuracy": 0.14531565308570862,
|
|
"num_tokens": 26333770.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 6.222366571426392,
|
|
"epoch": 1.1365026653849515,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048767689358335286,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.14643460512161255,
|
|
"num_tokens": 26344435.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 6.131643676757813,
|
|
"epoch": 1.1369396137376562,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 0.0004876667204620497,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.15525186583399772,
|
|
"num_tokens": 26355410.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 6.17512469291687,
|
|
"epoch": 1.1373765620903609,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004876565432616873,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.15009936392307283,
|
|
"num_tokens": 26365785.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 6.234361839294434,
|
|
"epoch": 1.1378135104430656,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048764636198246104,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.1503366306424141,
|
|
"num_tokens": 26375489.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 6.13693790435791,
|
|
"epoch": 1.1382504587957702,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004876361766245661,
|
|
"loss": 5.8935,
|
|
"mean_token_accuracy": 0.1502930074930191,
|
|
"num_tokens": 26385126.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 6.141677713394165,
|
|
"epoch": 1.138687407148475,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004876259871881979,
|
|
"loss": 5.8918,
|
|
"mean_token_accuracy": 0.14507785439491272,
|
|
"num_tokens": 26395314.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 6.177396249771118,
|
|
"epoch": 1.1391243555011799,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004876157936735519,
|
|
"loss": 5.9339,
|
|
"mean_token_accuracy": 0.14458275586366653,
|
|
"num_tokens": 26404660.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 6.194282484054566,
|
|
"epoch": 1.1395613038538845,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048760559608082343,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.15247158706188202,
|
|
"num_tokens": 26415371.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 6.171847629547119,
|
|
"epoch": 1.1399982522065892,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004875953944102084,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.14727843254804612,
|
|
"num_tokens": 26424896.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 6.177714014053345,
|
|
"epoch": 1.140435200559294,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048758518866190214,
|
|
"loss": 5.9013,
|
|
"mean_token_accuracy": 0.15153519809246063,
|
|
"num_tokens": 26434847.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 6.119139719009399,
|
|
"epoch": 1.1408721489119986,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.0004875749788361006,
|
|
"loss": 5.8668,
|
|
"mean_token_accuracy": 0.14892391189932824,
|
|
"num_tokens": 26444138.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 6.175608062744141,
|
|
"epoch": 1.1413090972647033,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004875647649329997,
|
|
"loss": 5.9071,
|
|
"mean_token_accuracy": 0.1447135291993618,
|
|
"num_tokens": 26453549.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 6.201389455795288,
|
|
"epoch": 1.141746045617408,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004875545469527952,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.14497822076082229,
|
|
"num_tokens": 26464386.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 6.16513843536377,
|
|
"epoch": 1.1421829939701127,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000487544324895683,
|
|
"loss": 5.8879,
|
|
"mean_token_accuracy": 0.15028253346681594,
|
|
"num_tokens": 26474146.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 6.158507823944092,
|
|
"epoch": 1.1426199423228174,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00048753409876185934,
|
|
"loss": 5.8559,
|
|
"mean_token_accuracy": 0.15528683811426164,
|
|
"num_tokens": 26484408.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 6.1672851085662845,
|
|
"epoch": 1.143056890675522,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004875238685515203,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.14090832620859145,
|
|
"num_tokens": 26494769.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 6.129169368743897,
|
|
"epoch": 1.1434938390282268,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048751363426486206,
|
|
"loss": 5.9309,
|
|
"mean_token_accuracy": 0.14978424459695816,
|
|
"num_tokens": 26505917.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 6.199118709564209,
|
|
"epoch": 1.1439307873809317,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.000487503395902081,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.13977217376232148,
|
|
"num_tokens": 26516388.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 6.294061899185181,
|
|
"epoch": 1.1443677357336364,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004874931534633735,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.14296025186777114,
|
|
"num_tokens": 26527180.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 6.150160551071167,
|
|
"epoch": 1.144804684086341,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.0004874829069489359,
|
|
"loss": 5.9007,
|
|
"mean_token_accuracy": 0.15269961953163147,
|
|
"num_tokens": 26537705.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 6.115722799301148,
|
|
"epoch": 1.1452416324390458,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048747265635896487,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.13656316250562667,
|
|
"num_tokens": 26548862.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 6.216728019714355,
|
|
"epoch": 1.1456785807917504,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048746240169365683,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.14423804432153703,
|
|
"num_tokens": 26559344.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 6.187315177917481,
|
|
"epoch": 1.1461155291444551,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004874521429532087,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.14793665260076522,
|
|
"num_tokens": 26568439.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 6.192612266540527,
|
|
"epoch": 1.1465524774971598,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048744188013781714,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.1501721516251564,
|
|
"num_tokens": 26578588.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 6.147067213058472,
|
|
"epoch": 1.1469894258498645,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000487431613247679,
|
|
"loss": 5.9471,
|
|
"mean_token_accuracy": 0.1519698679447174,
|
|
"num_tokens": 26588491.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 6.160977935791015,
|
|
"epoch": 1.1474263742025692,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048742134228299116,
|
|
"loss": 5.9643,
|
|
"mean_token_accuracy": 0.14815946519374848,
|
|
"num_tokens": 26598945.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 6.172370958328247,
|
|
"epoch": 1.147863322555274,
|
|
"grad_norm": 5.21875,
|
|
"learning_rate": 0.0004874110672439508,
|
|
"loss": 5.8636,
|
|
"mean_token_accuracy": 0.1555538922548294,
|
|
"num_tokens": 26609842.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 6.2168840885162355,
|
|
"epoch": 1.1483002709079786,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004874007881307547,
|
|
"loss": 5.9902,
|
|
"mean_token_accuracy": 0.1484801799058914,
|
|
"num_tokens": 26620836.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 6.224114036560058,
|
|
"epoch": 1.1487372192606835,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048739050494360026,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.14655357077717782,
|
|
"num_tokens": 26630148.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 6.215399074554443,
|
|
"epoch": 1.149174167613388,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048738021768268463,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.14698300510644913,
|
|
"num_tokens": 26640518.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 6.132278299331665,
|
|
"epoch": 1.149611115966093,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004873699263482052,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.16045882403850556,
|
|
"num_tokens": 26650156.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 6.229346513748169,
|
|
"epoch": 1.1500480643187976,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048735963094035924,
|
|
"loss": 5.9309,
|
|
"mean_token_accuracy": 0.1450416103005409,
|
|
"num_tokens": 26661251.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 6.20313835144043,
|
|
"epoch": 1.1504850126715023,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004873493314593443,
|
|
"loss": 5.9533,
|
|
"mean_token_accuracy": 0.14792988076806068,
|
|
"num_tokens": 26671851.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 6.1452638626098635,
|
|
"epoch": 1.150921961024207,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004873390279053579,
|
|
"loss": 5.9549,
|
|
"mean_token_accuracy": 0.14189176633954048,
|
|
"num_tokens": 26682984.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 6.1874671459198,
|
|
"epoch": 1.1513589093769117,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004873287202785977,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.1542479231953621,
|
|
"num_tokens": 26692706.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 6.203208780288696,
|
|
"epoch": 1.1517958577296163,
|
|
"grad_norm": 7.09375,
|
|
"learning_rate": 0.0004873184085792614,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.14727155715227128,
|
|
"num_tokens": 26702152.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 6.062010002136231,
|
|
"epoch": 1.152232806082321,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048730809280754674,
|
|
"loss": 5.8999,
|
|
"mean_token_accuracy": 0.15685417205095292,
|
|
"num_tokens": 26711404.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 6.177418375015259,
|
|
"epoch": 1.1526697544350257,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004872977729636516,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.152011838555336,
|
|
"num_tokens": 26720776.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 6.210717296600341,
|
|
"epoch": 1.1531067027877304,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00048728744904777394,
|
|
"loss": 5.9283,
|
|
"mean_token_accuracy": 0.14755924940109252,
|
|
"num_tokens": 26730700.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 6.22635588645935,
|
|
"epoch": 1.1535436511404351,
|
|
"grad_norm": 7.8125,
|
|
"learning_rate": 0.00048727712106011185,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.14609125405550002,
|
|
"num_tokens": 26741453.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 6.208837938308716,
|
|
"epoch": 1.1539805994931398,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048726678900086327,
|
|
"loss": 5.9069,
|
|
"mean_token_accuracy": 0.1469104468822479,
|
|
"num_tokens": 26750627.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 6.204519844055175,
|
|
"epoch": 1.1544175478458447,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048725645287022644,
|
|
"loss": 5.9276,
|
|
"mean_token_accuracy": 0.1467217855155468,
|
|
"num_tokens": 26760820.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 6.1821324825286865,
|
|
"epoch": 1.1548544961985494,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004872461126683996,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.1448241375386715,
|
|
"num_tokens": 26771535.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 6.222924375534058,
|
|
"epoch": 1.155291444551254,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004872357683955812,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.15162405669689177,
|
|
"num_tokens": 26782755.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 6.199812126159668,
|
|
"epoch": 1.1557283929039588,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048722542005196954,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.1463736265897751,
|
|
"num_tokens": 26792834.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 6.111869430541992,
|
|
"epoch": 1.1561653412566635,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00048721506763776306,
|
|
"loss": 5.9053,
|
|
"mean_token_accuracy": 0.15205851346254348,
|
|
"num_tokens": 26802865.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 6.121051549911499,
|
|
"epoch": 1.1566022896093682,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004872047111531604,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.14660682380199433,
|
|
"num_tokens": 26813566.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 6.183195304870606,
|
|
"epoch": 1.1570392379620729,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004871943505983602,
|
|
"loss": 5.8854,
|
|
"mean_token_accuracy": 0.15813306868076324,
|
|
"num_tokens": 26823885.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 6.063178014755249,
|
|
"epoch": 1.1574761863147776,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004871839859735612,
|
|
"loss": 5.8253,
|
|
"mean_token_accuracy": 0.1624150589108467,
|
|
"num_tokens": 26833236.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 6.172446298599243,
|
|
"epoch": 1.1579131346674822,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048717361727896203,
|
|
"loss": 5.9686,
|
|
"mean_token_accuracy": 0.1461391344666481,
|
|
"num_tokens": 26842651.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 6.175981140136718,
|
|
"epoch": 1.158350083020187,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00048716324451476183,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.14535028114914894,
|
|
"num_tokens": 26852198.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 6.262139511108399,
|
|
"epoch": 1.1587870313728916,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004871528676811594,
|
|
"loss": 6.0089,
|
|
"mean_token_accuracy": 0.14602211117744446,
|
|
"num_tokens": 26862807.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 6.273232746124267,
|
|
"epoch": 1.1592239797255965,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004871424867783538,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.1396594375371933,
|
|
"num_tokens": 26871992.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 6.196260643005371,
|
|
"epoch": 1.1596609280783012,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.00048713210180654414,
|
|
"loss": 5.8997,
|
|
"mean_token_accuracy": 0.14591027721762656,
|
|
"num_tokens": 26881417.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 6.188068580627442,
|
|
"epoch": 1.160097876431006,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048712171276592964,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.15216402113437652,
|
|
"num_tokens": 26891879.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 6.183082151412964,
|
|
"epoch": 1.1605348247837106,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004871113196567095,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.14431816339492798,
|
|
"num_tokens": 26902729.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 6.152678155899048,
|
|
"epoch": 1.1609717731364153,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00048710092247908316,
|
|
"loss": 5.9107,
|
|
"mean_token_accuracy": 0.15283699035644532,
|
|
"num_tokens": 26914415.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 6.256611728668213,
|
|
"epoch": 1.16140872148912,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.00048709052123324995,
|
|
"loss": 5.9447,
|
|
"mean_token_accuracy": 0.1510358914732933,
|
|
"num_tokens": 26924513.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 6.193924140930176,
|
|
"epoch": 1.1618456698418247,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048708011591940936,
|
|
"loss": 5.8499,
|
|
"mean_token_accuracy": 0.1548793777823448,
|
|
"num_tokens": 26935039.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 6.129718065261841,
|
|
"epoch": 1.1622826181945294,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000487069706537761,
|
|
"loss": 5.838,
|
|
"mean_token_accuracy": 0.15177211165428162,
|
|
"num_tokens": 26945148.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 6.139807987213135,
|
|
"epoch": 1.162719566547234,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004870592930885046,
|
|
"loss": 5.8829,
|
|
"mean_token_accuracy": 0.15055215656757354,
|
|
"num_tokens": 26955227.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 6.194760179519653,
|
|
"epoch": 1.1631565148999388,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048704887557183993,
|
|
"loss": 5.8557,
|
|
"mean_token_accuracy": 0.14913835525512695,
|
|
"num_tokens": 26964389.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 6.2291806697845455,
|
|
"epoch": 1.1635934632526435,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00048703845398796665,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.1489256888628006,
|
|
"num_tokens": 26974695.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 6.227977085113525,
|
|
"epoch": 1.1640304116053484,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048702802833708466,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.15597414076328278,
|
|
"num_tokens": 26984851.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 6.236116600036621,
|
|
"epoch": 1.1644673599580528,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048701759861939403,
|
|
"loss": 5.9481,
|
|
"mean_token_accuracy": 0.14879257455468178,
|
|
"num_tokens": 26995967.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 6.125051069259643,
|
|
"epoch": 1.1649043083107578,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.00048700716483509476,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.15883732140064238,
|
|
"num_tokens": 27006469.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 6.1943573474884035,
|
|
"epoch": 1.1653412566634624,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.000486996726984387,
|
|
"loss": 5.9676,
|
|
"mean_token_accuracy": 0.14819352924823762,
|
|
"num_tokens": 27016419.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 6.263797998428345,
|
|
"epoch": 1.1657782050161671,
|
|
"grad_norm": 4.84375,
|
|
"learning_rate": 0.0004869862850674709,
|
|
"loss": 5.9365,
|
|
"mean_token_accuracy": 0.1433882534503937,
|
|
"num_tokens": 27026322.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 6.152531290054322,
|
|
"epoch": 1.1662151533688718,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048697583908454675,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.14920396804809571,
|
|
"num_tokens": 27036518.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 6.203283405303955,
|
|
"epoch": 1.1666521017215765,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000486965389035815,
|
|
"loss": 5.9558,
|
|
"mean_token_accuracy": 0.1449318841099739,
|
|
"num_tokens": 27048035.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 6.19470181465149,
|
|
"epoch": 1.1670890500742812,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00048695493492147596,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.14441130608320235,
|
|
"num_tokens": 27058507.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 6.133526134490967,
|
|
"epoch": 1.167525998426986,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.00048694447674173025,
|
|
"loss": 5.9015,
|
|
"mean_token_accuracy": 0.1514151781797409,
|
|
"num_tokens": 27068350.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 6.128726005554199,
|
|
"epoch": 1.1679629467796906,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004869340144967784,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.15001028180122375,
|
|
"num_tokens": 27077840.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 6.146130847930908,
|
|
"epoch": 1.1683998951323953,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.00048692354818682113,
|
|
"loss": 5.8649,
|
|
"mean_token_accuracy": 0.15206778347492217,
|
|
"num_tokens": 27087687.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 6.208657455444336,
|
|
"epoch": 1.1688368434851,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004869130778120591,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.1396991528570652,
|
|
"num_tokens": 27099057.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 6.197882795333863,
|
|
"epoch": 1.1692737918378047,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004869026033726933,
|
|
"loss": 5.9813,
|
|
"mean_token_accuracy": 0.1465886875987053,
|
|
"num_tokens": 27109617.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 6.235219240188599,
|
|
"epoch": 1.1697107401905096,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004868921248689244,
|
|
"loss": 5.9435,
|
|
"mean_token_accuracy": 0.14212179258465768,
|
|
"num_tokens": 27119456.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 6.155871772766114,
|
|
"epoch": 1.1701476885432143,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004868816423009535,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.1531216859817505,
|
|
"num_tokens": 27129333.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 6.150876522064209,
|
|
"epoch": 1.170584636895919,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004868711556689818,
|
|
"loss": 5.9022,
|
|
"mean_token_accuracy": 0.14866817519068717,
|
|
"num_tokens": 27139205.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 6.224974918365478,
|
|
"epoch": 1.1710215852486237,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048686066497321027,
|
|
"loss": 5.9259,
|
|
"mean_token_accuracy": 0.15095333755016327,
|
|
"num_tokens": 27148530.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 6.277073955535888,
|
|
"epoch": 1.1714585336013283,
|
|
"grad_norm": 6.5625,
|
|
"learning_rate": 0.00048685017021384014,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.14719715267419814,
|
|
"num_tokens": 27159000.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 6.230797481536865,
|
|
"epoch": 1.171895481954033,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00048683967139107276,
|
|
"loss": 5.9327,
|
|
"mean_token_accuracy": 0.14801158457994462,
|
|
"num_tokens": 27169035.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 6.1944574356079105,
|
|
"epoch": 1.1723324303067377,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004868291685051095,
|
|
"loss": 5.9278,
|
|
"mean_token_accuracy": 0.14793018102645875,
|
|
"num_tokens": 27179809.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 6.174774408340454,
|
|
"epoch": 1.1727693786594424,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004868186615561518,
|
|
"loss": 5.9309,
|
|
"mean_token_accuracy": 0.1465114802122116,
|
|
"num_tokens": 27190445.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 6.214708614349365,
|
|
"epoch": 1.173206327012147,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048680815054440114,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.14549873024225235,
|
|
"num_tokens": 27201097.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 6.180704498291016,
|
|
"epoch": 1.1736432753648518,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048679763547005925,
|
|
"loss": 5.8619,
|
|
"mean_token_accuracy": 0.15421843975782396,
|
|
"num_tokens": 27210181.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 6.140958547592163,
|
|
"epoch": 1.1740802237175565,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004867871163333276,
|
|
"loss": 5.9087,
|
|
"mean_token_accuracy": 0.14630078971385957,
|
|
"num_tokens": 27219869.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 6.179342031478882,
|
|
"epoch": 1.1745171720702614,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004867765931344082,
|
|
"loss": 5.9312,
|
|
"mean_token_accuracy": 0.15077333003282548,
|
|
"num_tokens": 27229730.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 6.194200658798218,
|
|
"epoch": 1.174954120422966,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004867660658735027,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.15319260582327843,
|
|
"num_tokens": 27239534.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 6.176281595230103,
|
|
"epoch": 1.1753910687756708,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004867555345508131,
|
|
"loss": 5.9652,
|
|
"mean_token_accuracy": 0.14543908312916756,
|
|
"num_tokens": 27249017.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 6.242269849777221,
|
|
"epoch": 1.1758280171283755,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004867449991665414,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.14285536855459213,
|
|
"num_tokens": 27261135.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 6.231696653366089,
|
|
"epoch": 1.1762649654810802,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004867344597208897,
|
|
"loss": 5.9102,
|
|
"mean_token_accuracy": 0.1442875511944294,
|
|
"num_tokens": 27270763.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 6.1746025562286375,
|
|
"epoch": 1.1767019138337849,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004867239162140601,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.14871663004159927,
|
|
"num_tokens": 27280115.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 6.155801773071289,
|
|
"epoch": 1.1771388621864896,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004867133686462548,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.14929405450820923,
|
|
"num_tokens": 27290162.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 6.1686280250549315,
|
|
"epoch": 1.1775758105391942,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.00048670281701767616,
|
|
"loss": 5.8689,
|
|
"mean_token_accuracy": 0.1549352988600731,
|
|
"num_tokens": 27300467.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 6.157352781295776,
|
|
"epoch": 1.178012758891899,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004866922613285266,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.14707837551832198,
|
|
"num_tokens": 27310524.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 6.187600374221802,
|
|
"epoch": 1.1784497072446036,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004866817015790085,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.1510642573237419,
|
|
"num_tokens": 27320861.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 6.2566859245300295,
|
|
"epoch": 1.1788866555973083,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.00048667113776932453,
|
|
"loss": 5.9566,
|
|
"mean_token_accuracy": 0.1472768247127533,
|
|
"num_tokens": 27331771.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 6.187179136276245,
|
|
"epoch": 1.1793236039500132,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004866605698996772,
|
|
"loss": 5.9401,
|
|
"mean_token_accuracy": 0.1475620873272419,
|
|
"num_tokens": 27341449.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 6.1723979949951175,
|
|
"epoch": 1.1797605523027177,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004866499979702691,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.13973579555749893,
|
|
"num_tokens": 27353127.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 6.197310924530029,
|
|
"epoch": 1.1801975006554226,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004866394219813032,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.15200105756521226,
|
|
"num_tokens": 27362116.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 6.184662580490112,
|
|
"epoch": 1.1806344490081273,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.00048662884193298233,
|
|
"loss": 5.8896,
|
|
"mean_token_accuracy": 0.15370760038495063,
|
|
"num_tokens": 27372204.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 6.152497243881226,
|
|
"epoch": 1.181071397360832,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004866182578255094,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.14656676426529885,
|
|
"num_tokens": 27382963.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 6.13969931602478,
|
|
"epoch": 1.1815083457135367,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048660766965908736,
|
|
"loss": 5.8866,
|
|
"mean_token_accuracy": 0.15366474986076356,
|
|
"num_tokens": 27392426.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 6.129809761047364,
|
|
"epoch": 1.1819452940662414,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004865970774339194,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.15134273767471312,
|
|
"num_tokens": 27402679.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 6.20675106048584,
|
|
"epoch": 1.182382242418946,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048658648115020855,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.14752191081643104,
|
|
"num_tokens": 27412911.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 6.236071634292602,
|
|
"epoch": 1.1828191907716508,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004865758808081581,
|
|
"loss": 5.8992,
|
|
"mean_token_accuracy": 0.1471305325627327,
|
|
"num_tokens": 27423394.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 6.168351316452027,
|
|
"epoch": 1.1832561391243555,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048656527640797144,
|
|
"loss": 5.8875,
|
|
"mean_token_accuracy": 0.15766822248697282,
|
|
"num_tokens": 27433016.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 6.146002244949341,
|
|
"epoch": 1.1836930874770601,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048655466794985194,
|
|
"loss": 5.9066,
|
|
"mean_token_accuracy": 0.14376786053180696,
|
|
"num_tokens": 27442414.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 6.139078283309937,
|
|
"epoch": 1.1841300358297648,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000486544055434003,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.14735411405563353,
|
|
"num_tokens": 27452410.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 6.209070253372192,
|
|
"epoch": 1.1845669841824695,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004865334388606282,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.15575417578220369,
|
|
"num_tokens": 27462196.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 6.22119550704956,
|
|
"epoch": 1.1850039325351744,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048652281822993127,
|
|
"loss": 5.9685,
|
|
"mean_token_accuracy": 0.1431777723133564,
|
|
"num_tokens": 27473934.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 6.19681749343872,
|
|
"epoch": 1.1854408808878791,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.00048651219354211585,
|
|
"loss": 6.0147,
|
|
"mean_token_accuracy": 0.1507688894867897,
|
|
"num_tokens": 27484218.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 6.153265857696534,
|
|
"epoch": 1.1858778292405838,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048650156479738575,
|
|
"loss": 6.0073,
|
|
"mean_token_accuracy": 0.14877953380346298,
|
|
"num_tokens": 27494663.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 6.203997945785522,
|
|
"epoch": 1.1863147775932885,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00048649093199594473,
|
|
"loss": 5.8486,
|
|
"mean_token_accuracy": 0.15308129787445068,
|
|
"num_tokens": 27504233.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 6.185912227630615,
|
|
"epoch": 1.1867517259459932,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004864802951379969,
|
|
"loss": 5.9159,
|
|
"mean_token_accuracy": 0.14943065941333772,
|
|
"num_tokens": 27514032.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 6.176620435714722,
|
|
"epoch": 1.187188674298698,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048646965422374615,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.14695518538355828,
|
|
"num_tokens": 27524659.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 6.179401302337647,
|
|
"epoch": 1.1876256226514026,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004864590092533966,
|
|
"loss": 5.8604,
|
|
"mean_token_accuracy": 0.14711184054613113,
|
|
"num_tokens": 27534003.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 6.138573026657104,
|
|
"epoch": 1.1880625710041073,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004864483602271524,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.14601757675409316,
|
|
"num_tokens": 27543586.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 6.123298597335816,
|
|
"epoch": 1.188499519356812,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000486437707145218,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.15870054811239243,
|
|
"num_tokens": 27554210.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 6.230636405944824,
|
|
"epoch": 1.1889364677095167,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048642705000779754,
|
|
"loss": 5.9765,
|
|
"mean_token_accuracy": 0.14838793352246285,
|
|
"num_tokens": 27565324.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 6.166018772125244,
|
|
"epoch": 1.1893734160622214,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004864163888150955,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.15250848829746247,
|
|
"num_tokens": 27575192.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 6.148905420303345,
|
|
"epoch": 1.1898103644149263,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048640572356731623,
|
|
"loss": 5.9068,
|
|
"mean_token_accuracy": 0.14767027348279954,
|
|
"num_tokens": 27585294.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 6.18740873336792,
|
|
"epoch": 1.190247312767631,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048639505426466447,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.15437621027231216,
|
|
"num_tokens": 27595667.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 6.194943046569824,
|
|
"epoch": 1.1906842611203357,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004863843809073448,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.15669466108083724,
|
|
"num_tokens": 27605816.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 6.0837657928466795,
|
|
"epoch": 1.1911212094730403,
|
|
"grad_norm": 6.90625,
|
|
"learning_rate": 0.000486373703495562,
|
|
"loss": 5.9017,
|
|
"mean_token_accuracy": 0.150448040664196,
|
|
"num_tokens": 27614874.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 6.157348489761352,
|
|
"epoch": 1.191558157825745,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004863630220295207,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.14978635609149932,
|
|
"num_tokens": 27625610.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 6.209554290771484,
|
|
"epoch": 1.1919951061784497,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048635233650942596,
|
|
"loss": 5.9245,
|
|
"mean_token_accuracy": 0.14628103449940683,
|
|
"num_tokens": 27636646.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 6.155116558074951,
|
|
"epoch": 1.1924320545311544,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048634164693548267,
|
|
"loss": 5.9354,
|
|
"mean_token_accuracy": 0.14759790599346162,
|
|
"num_tokens": 27647311.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 6.159931707382202,
|
|
"epoch": 1.192869002883859,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004863309533078957,
|
|
"loss": 5.935,
|
|
"mean_token_accuracy": 0.14424525052309037,
|
|
"num_tokens": 27658347.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 6.1673603534698485,
|
|
"epoch": 1.1933059512365638,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048632025562687047,
|
|
"loss": 5.8853,
|
|
"mean_token_accuracy": 0.15577892661094667,
|
|
"num_tokens": 27669211.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 6.192775058746338,
|
|
"epoch": 1.1937428995892685,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00048630955389261193,
|
|
"loss": 5.8798,
|
|
"mean_token_accuracy": 0.15026595443487167,
|
|
"num_tokens": 27678904.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 6.157775449752807,
|
|
"epoch": 1.1941798479419732,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048629884810532547,
|
|
"loss": 5.8649,
|
|
"mean_token_accuracy": 0.14732719361782073,
|
|
"num_tokens": 27688928.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 6.167954349517823,
|
|
"epoch": 1.1946167962946779,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004862881382652164,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.14584649205207825,
|
|
"num_tokens": 27699855.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 6.195680952072143,
|
|
"epoch": 1.1950537446473826,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004862774243724901,
|
|
"loss": 5.935,
|
|
"mean_token_accuracy": 0.15434314161539078,
|
|
"num_tokens": 27709857.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 6.197531509399414,
|
|
"epoch": 1.1954906930000875,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004862667064273521,
|
|
"loss": 5.9395,
|
|
"mean_token_accuracy": 0.1450137674808502,
|
|
"num_tokens": 27719612.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 6.145286178588867,
|
|
"epoch": 1.1959276413527922,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004862559844300079,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.1506308361887932,
|
|
"num_tokens": 27730052.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 6.152642488479614,
|
|
"epoch": 1.1963645897054969,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004862452583806633,
|
|
"loss": 5.8167,
|
|
"mean_token_accuracy": 0.1600808709859848,
|
|
"num_tokens": 27739980.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 6.171810626983643,
|
|
"epoch": 1.1968015380582016,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.00048623452827952385,
|
|
"loss": 5.9246,
|
|
"mean_token_accuracy": 0.1522218957543373,
|
|
"num_tokens": 27748863.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 6.127953767776489,
|
|
"epoch": 1.1972384864109062,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004862237941267956,
|
|
"loss": 5.89,
|
|
"mean_token_accuracy": 0.15447674840688705,
|
|
"num_tokens": 27758672.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 6.164484596252441,
|
|
"epoch": 1.197675434763611,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004862130559226842,
|
|
"loss": 5.9148,
|
|
"mean_token_accuracy": 0.14712174534797667,
|
|
"num_tokens": 27768195.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 6.153045701980591,
|
|
"epoch": 1.1981123831163156,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004862023136673958,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.15653797835111619,
|
|
"num_tokens": 27778135.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 6.255939865112305,
|
|
"epoch": 1.1985493314690203,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.00048619156736113634,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.14238950833678246,
|
|
"num_tokens": 27788723.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 6.21520037651062,
|
|
"epoch": 1.198986279821725,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004861808170041119,
|
|
"loss": 5.9571,
|
|
"mean_token_accuracy": 0.14887107238173486,
|
|
"num_tokens": 27799060.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 6.1764750480651855,
|
|
"epoch": 1.1994232281744297,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004861700625965287,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.14113897532224656,
|
|
"num_tokens": 27809542.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 6.108205413818359,
|
|
"epoch": 1.1998601765271344,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048615930413859317,
|
|
"loss": 5.9451,
|
|
"mean_token_accuracy": 0.14324765130877495,
|
|
"num_tokens": 27819738.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 6.273303651809693,
|
|
"epoch": 1.2002971248798393,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.00048614854163051143,
|
|
"loss": 5.877,
|
|
"mean_token_accuracy": 0.1496002718806267,
|
|
"num_tokens": 27829052.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 6.236565160751343,
|
|
"epoch": 1.200734073232544,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004861377750724901,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.15066418796777725,
|
|
"num_tokens": 27839277.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 6.149129629135132,
|
|
"epoch": 1.2011710215852487,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004861270044647356,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.1499796360731125,
|
|
"num_tokens": 27848550.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 6.093921709060669,
|
|
"epoch": 1.2016079699379534,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048611622980745446,
|
|
"loss": 5.952,
|
|
"mean_token_accuracy": 0.1432810753583908,
|
|
"num_tokens": 27858546.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 6.213047790527344,
|
|
"epoch": 1.202044918290658,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 0.00048610545110085347,
|
|
"loss": 5.9667,
|
|
"mean_token_accuracy": 0.1422676384449005,
|
|
"num_tokens": 27869192.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 6.250215244293213,
|
|
"epoch": 1.2024818666433628,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004860946683451393,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.15389849692583085,
|
|
"num_tokens": 27878534.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 6.122016906738281,
|
|
"epoch": 1.2029188149960675,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048608388154051875,
|
|
"loss": 5.852,
|
|
"mean_token_accuracy": 0.1557212255895138,
|
|
"num_tokens": 27888074.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 6.118573999404907,
|
|
"epoch": 1.2033557633487721,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048607309068719875,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.14594862833619118,
|
|
"num_tokens": 27898210.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 6.130645847320556,
|
|
"epoch": 1.2037927117014768,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004860622957853863,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.15255392268300055,
|
|
"num_tokens": 27907472.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 6.132734966278076,
|
|
"epoch": 1.2042296600541815,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004860514968352885,
|
|
"loss": 5.926,
|
|
"mean_token_accuracy": 0.15163296610116958,
|
|
"num_tokens": 27917265.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 6.158398628234863,
|
|
"epoch": 1.2046666084068862,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048604069383711225,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.15847632437944412,
|
|
"num_tokens": 27926883.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 6.217565965652466,
|
|
"epoch": 1.2051035567595911,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.00048602988679106497,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.14781321734189987,
|
|
"num_tokens": 27937167.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 6.21237154006958,
|
|
"epoch": 1.2055405051122958,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004860190756973539,
|
|
"loss": 5.8773,
|
|
"mean_token_accuracy": 0.15900922194123268,
|
|
"num_tokens": 27947422.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 6.213820266723633,
|
|
"epoch": 1.2059774534650005,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048600826055618634,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.15147775411605835,
|
|
"num_tokens": 27958407.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 6.177189016342163,
|
|
"epoch": 1.2064144018177052,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00048599744136776986,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.15412741899490356,
|
|
"num_tokens": 27968277.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 6.1591204643249515,
|
|
"epoch": 1.20685135017041,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048598661813231177,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.15879237949848174,
|
|
"num_tokens": 27978116.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 6.143211412429809,
|
|
"epoch": 1.2072882985231146,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048597579085001984,
|
|
"loss": 5.8447,
|
|
"mean_token_accuracy": 0.15078818202018737,
|
|
"num_tokens": 27988383.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 6.095460319519043,
|
|
"epoch": 1.2077252468758193,
|
|
"grad_norm": 5.875,
|
|
"learning_rate": 0.00048596495952110176,
|
|
"loss": 5.8608,
|
|
"mean_token_accuracy": 0.15658497512340547,
|
|
"num_tokens": 27999118.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 6.140877056121826,
|
|
"epoch": 1.208162195228524,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004859541241457651,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.15611317455768586,
|
|
"num_tokens": 28008849.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 6.238790130615234,
|
|
"epoch": 1.2085991435812287,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004859432847242179,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.14997541755437852,
|
|
"num_tokens": 28019063.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 6.172117805480957,
|
|
"epoch": 1.2090360919339334,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.00048593244125666793,
|
|
"loss": 5.8229,
|
|
"mean_token_accuracy": 0.15812181681394577,
|
|
"num_tokens": 28028333.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 6.1784388542175295,
|
|
"epoch": 1.209473040286638,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004859215937433232,
|
|
"loss": 5.9117,
|
|
"mean_token_accuracy": 0.1518342137336731,
|
|
"num_tokens": 28037704.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 6.186066818237305,
|
|
"epoch": 1.2099099886393427,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004859107421843918,
|
|
"loss": 5.928,
|
|
"mean_token_accuracy": 0.15025399029254913,
|
|
"num_tokens": 28047157.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 6.176485013961792,
|
|
"epoch": 1.2103469369920474,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048589988658008184,
|
|
"loss": 5.8577,
|
|
"mean_token_accuracy": 0.15271882265806197,
|
|
"num_tokens": 28057582.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 6.161338520050049,
|
|
"epoch": 1.2107838853447523,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048588902693060156,
|
|
"loss": 5.921,
|
|
"mean_token_accuracy": 0.1398226022720337,
|
|
"num_tokens": 28067458.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 6.277706146240234,
|
|
"epoch": 1.211220833697457,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004858781632361592,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.15111400932073593,
|
|
"num_tokens": 28078967.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 6.1715000629425045,
|
|
"epoch": 1.2116577820501617,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004858672954969632,
|
|
"loss": 5.8585,
|
|
"mean_token_accuracy": 0.1534536749124527,
|
|
"num_tokens": 28088498.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 6.064240789413452,
|
|
"epoch": 1.2120947304028664,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048585642371322196,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.14823956340551375,
|
|
"num_tokens": 28098884.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 6.179372549057007,
|
|
"epoch": 1.212531678755571,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004858455478851441,
|
|
"loss": 5.8704,
|
|
"mean_token_accuracy": 0.15619773864746095,
|
|
"num_tokens": 28109629.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 6.195692491531372,
|
|
"epoch": 1.2129686271082758,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000485834668012938,
|
|
"loss": 5.8296,
|
|
"mean_token_accuracy": 0.15061113387346267,
|
|
"num_tokens": 28118555.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 6.197376346588134,
|
|
"epoch": 1.2134055754609805,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004858237840968127,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.14522878602147102,
|
|
"num_tokens": 28129028.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 6.117794990539551,
|
|
"epoch": 1.2138425238136852,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00048581289613697654,
|
|
"loss": 5.9193,
|
|
"mean_token_accuracy": 0.14912183135747908,
|
|
"num_tokens": 28139188.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 6.159627056121826,
|
|
"epoch": 1.2142794721663899,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048580200413363866,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.15412092655897142,
|
|
"num_tokens": 28148199.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 6.163512134552002,
|
|
"epoch": 1.2147164205190946,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004857911080870079,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.15558690428733826,
|
|
"num_tokens": 28157811.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 6.101589059829712,
|
|
"epoch": 1.2151533688717993,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048578020799729327,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.15734661221504212,
|
|
"num_tokens": 28168644.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 6.158587074279785,
|
|
"epoch": 1.2155903172245042,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004857693038647037,
|
|
"loss": 5.9259,
|
|
"mean_token_accuracy": 0.14993413537740707,
|
|
"num_tokens": 28179846.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 6.212523889541626,
|
|
"epoch": 1.2160272655772089,
|
|
"grad_norm": 6.34375,
|
|
"learning_rate": 0.0004857583956894485,
|
|
"loss": 5.8776,
|
|
"mean_token_accuracy": 0.15534001141786574,
|
|
"num_tokens": 28189400.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 6.139555788040161,
|
|
"epoch": 1.2164642139299136,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004857474834717368,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.14881992489099502,
|
|
"num_tokens": 28199695.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 6.1129858016967775,
|
|
"epoch": 1.2169011622826182,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00048573656721177805,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.15997774451971053,
|
|
"num_tokens": 28209977.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 6.212561178207397,
|
|
"epoch": 1.217338110635323,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004857256469097814,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.15285259187221528,
|
|
"num_tokens": 28220619.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 6.156783628463745,
|
|
"epoch": 1.2177750589880276,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004857147225659564,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.15748235881328582,
|
|
"num_tokens": 28230065.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 6.115792846679687,
|
|
"epoch": 1.2182120073407323,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048570379418051273,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.15798841714859008,
|
|
"num_tokens": 28239307.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 6.199590015411377,
|
|
"epoch": 1.218648955693437,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004856928617536598,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.15174517184495925,
|
|
"num_tokens": 28249421.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 6.088633441925049,
|
|
"epoch": 1.2190859040461417,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004856819252856073,
|
|
"loss": 5.8415,
|
|
"mean_token_accuracy": 0.15172751992940903,
|
|
"num_tokens": 28258125.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 6.005021095275879,
|
|
"epoch": 1.2195228523988464,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00048567098477656526,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.1543092504143715,
|
|
"num_tokens": 28268897.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 6.118499994277954,
|
|
"epoch": 1.219959800751551,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004856600402267432,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.15268064066767692,
|
|
"num_tokens": 28278506.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 6.2342699527740475,
|
|
"epoch": 1.220396749104256,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004856490916363513,
|
|
"loss": 5.8577,
|
|
"mean_token_accuracy": 0.15139369666576385,
|
|
"num_tokens": 28287905.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 6.190746784210205,
|
|
"epoch": 1.2208336974569605,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004856381390055994,
|
|
"loss": 5.9371,
|
|
"mean_token_accuracy": 0.1514703616499901,
|
|
"num_tokens": 28297123.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 6.140774345397949,
|
|
"epoch": 1.2212706458096654,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048562718233469756,
|
|
"loss": 5.9523,
|
|
"mean_token_accuracy": 0.14569918811321259,
|
|
"num_tokens": 28306621.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 6.2415910243988035,
|
|
"epoch": 1.22170759416237,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048561622162385606,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.1411128021776676,
|
|
"num_tokens": 28318369.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 6.2192271709442135,
|
|
"epoch": 1.2221445425150748,
|
|
"grad_norm": 6.09375,
|
|
"learning_rate": 0.00048560525687328497,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.14681155383586883,
|
|
"num_tokens": 28328817.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 6.235672283172607,
|
|
"epoch": 1.2225814908677795,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.00048559428808319483,
|
|
"loss": 5.9738,
|
|
"mean_token_accuracy": 0.14341663420200348,
|
|
"num_tokens": 28339448.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 6.175102710723877,
|
|
"epoch": 1.2230184392204841,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004855833152537958,
|
|
"loss": 5.8812,
|
|
"mean_token_accuracy": 0.15200393050909042,
|
|
"num_tokens": 28349243.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 6.1426825523376465,
|
|
"epoch": 1.2234553875731888,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004855723383852985,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.15116727948188782,
|
|
"num_tokens": 28359392.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 6.176077270507813,
|
|
"epoch": 1.2238923359258935,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004855613574779134,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.15116518288850783,
|
|
"num_tokens": 28369160.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 6.183259916305542,
|
|
"epoch": 1.2243292842785982,
|
|
"grad_norm": 5.34375,
|
|
"learning_rate": 0.00048555037253185114,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.15362579822540284,
|
|
"num_tokens": 28379107.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 6.18773832321167,
|
|
"epoch": 1.224766232631303,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048553938354732243,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.14881558418273927,
|
|
"num_tokens": 28388956.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 6.153997135162354,
|
|
"epoch": 1.2252031809840076,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.00048552839052453794,
|
|
"loss": 5.8899,
|
|
"mean_token_accuracy": 0.14805519729852676,
|
|
"num_tokens": 28398925.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 6.20629563331604,
|
|
"epoch": 1.2256401293367123,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048551739346370864,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.13878847360610963,
|
|
"num_tokens": 28408714.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 6.247835731506347,
|
|
"epoch": 1.2260770776894172,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004855063923650455,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.15068021565675735,
|
|
"num_tokens": 28419408.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 6.126561450958252,
|
|
"epoch": 1.226514026042122,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004854953872287593,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.1522832691669464,
|
|
"num_tokens": 28430044.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 6.119768047332764,
|
|
"epoch": 1.2269509743948266,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.0004854843780550614,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.15552353262901306,
|
|
"num_tokens": 28440100.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 6.137379693984985,
|
|
"epoch": 1.2273879227475313,
|
|
"grad_norm": 4.75,
|
|
"learning_rate": 0.0004854733648441628,
|
|
"loss": 5.848,
|
|
"mean_token_accuracy": 0.1561823680996895,
|
|
"num_tokens": 28449497.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 6.177059316635132,
|
|
"epoch": 1.227824871100236,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.00048546234759627477,
|
|
"loss": 5.8933,
|
|
"mean_token_accuracy": 0.15604597926139832,
|
|
"num_tokens": 28459789.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 6.245036840438843,
|
|
"epoch": 1.2282618194529407,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00048545132631160856,
|
|
"loss": 5.957,
|
|
"mean_token_accuracy": 0.1454416736960411,
|
|
"num_tokens": 28471728.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 6.240487480163575,
|
|
"epoch": 1.2286987678056454,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00048544030099037576,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.15105270743370056,
|
|
"num_tokens": 28481876.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 6.210722970962524,
|
|
"epoch": 1.22913571615835,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048542927163278766,
|
|
"loss": 5.9094,
|
|
"mean_token_accuracy": 0.150232669711113,
|
|
"num_tokens": 28491800.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 6.079072761535644,
|
|
"epoch": 1.2295726645110547,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004854182382390559,
|
|
"loss": 5.8662,
|
|
"mean_token_accuracy": 0.1539934977889061,
|
|
"num_tokens": 28502033.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 6.143470764160156,
|
|
"epoch": 1.2300096128637594,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.000485407200809392,
|
|
"loss": 5.937,
|
|
"mean_token_accuracy": 0.14482716843485832,
|
|
"num_tokens": 28511921.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 6.253262233734131,
|
|
"epoch": 1.2304465612164641,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.0004853961593440078,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.15441647917032242,
|
|
"num_tokens": 28521449.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 6.197099256515503,
|
|
"epoch": 1.230883509569169,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000485385113843115,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.15310391336679458,
|
|
"num_tokens": 28532088.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 6.2283447265625,
|
|
"epoch": 1.2313204579218737,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004853740643069255,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.14941720366477967,
|
|
"num_tokens": 28541835.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 6.197736835479736,
|
|
"epoch": 1.2317574062745784,
|
|
"grad_norm": 5.6875,
|
|
"learning_rate": 0.00048536301073565113,
|
|
"loss": 5.9061,
|
|
"mean_token_accuracy": 0.14509299993515015,
|
|
"num_tokens": 28551601.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 6.148233699798584,
|
|
"epoch": 1.232194354627283,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004853519531295041,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.1543732464313507,
|
|
"num_tokens": 28561012.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 6.177007007598877,
|
|
"epoch": 1.2326313029799878,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004853408914886963,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.1462666854262352,
|
|
"num_tokens": 28571431.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 6.159669589996338,
|
|
"epoch": 1.2330682513326925,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.00048532982581344004,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.15932746529579161,
|
|
"num_tokens": 28581185.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 6.150724983215332,
|
|
"epoch": 1.2335051996853972,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004853187561039475,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.15079872608184813,
|
|
"num_tokens": 28591164.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 6.100163269042969,
|
|
"epoch": 1.2339421480381019,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048530768236043094,
|
|
"loss": 5.7967,
|
|
"mean_token_accuracy": 0.1576806828379631,
|
|
"num_tokens": 28600931.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 6.145612096786499,
|
|
"epoch": 1.2343790963908066,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004852966045831029,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.14835426062345505,
|
|
"num_tokens": 28611908.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 6.226451396942139,
|
|
"epoch": 1.2348160447435113,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004852855227721758,
|
|
"loss": 5.9716,
|
|
"mean_token_accuracy": 0.14340434670448304,
|
|
"num_tokens": 28622106.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 6.262969732284546,
|
|
"epoch": 1.235252993096216,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.00048527443692786217,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.14171316847205162,
|
|
"num_tokens": 28632634.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 6.206275415420532,
|
|
"epoch": 1.2356899414489209,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004852633470503746,
|
|
"loss": 5.9305,
|
|
"mean_token_accuracy": 0.14711518213152885,
|
|
"num_tokens": 28642936.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 6.25238356590271,
|
|
"epoch": 1.2361268898016253,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048525225313992594,
|
|
"loss": 5.8888,
|
|
"mean_token_accuracy": 0.15033729523420333,
|
|
"num_tokens": 28653539.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 6.1946642875671385,
|
|
"epoch": 1.2365638381543302,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004852411551967289,
|
|
"loss": 5.9603,
|
|
"mean_token_accuracy": 0.14472445994615554,
|
|
"num_tokens": 28664212.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 6.2647181987762455,
|
|
"epoch": 1.237000786507035,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048523005322099626,
|
|
"loss": 5.9567,
|
|
"mean_token_accuracy": 0.14432160556316376,
|
|
"num_tokens": 28676028.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 6.234403800964356,
|
|
"epoch": 1.2374377348597396,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.00048521894721294115,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.14716139659285546,
|
|
"num_tokens": 28685370.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 6.154047298431396,
|
|
"epoch": 1.2378746832124443,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048520783717277645,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.1565360024571419,
|
|
"num_tokens": 28695300.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 6.1391188621521,
|
|
"epoch": 1.238311631565149,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048519672310071523,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.15393647998571397,
|
|
"num_tokens": 28705485.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 6.192353963851929,
|
|
"epoch": 1.2387485799178537,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00048518560499697066,
|
|
"loss": 5.9153,
|
|
"mean_token_accuracy": 0.14622731655836105,
|
|
"num_tokens": 28715407.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 6.211352300643921,
|
|
"epoch": 1.2391855282705584,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.00048517448286175617,
|
|
"loss": 5.9353,
|
|
"mean_token_accuracy": 0.15140830874443054,
|
|
"num_tokens": 28725283.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 6.13202428817749,
|
|
"epoch": 1.239622476623263,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.00048516335669528495,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.15868661999702455,
|
|
"num_tokens": 28736131.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 6.110800886154175,
|
|
"epoch": 1.2400594249759678,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004851522264977704,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.15677210539579392,
|
|
"num_tokens": 28745446.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 6.157938051223755,
|
|
"epoch": 1.2404963733286725,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000485141092269426,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.15657073333859445,
|
|
"num_tokens": 28754639.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 6.164085483551025,
|
|
"epoch": 1.2409333216813772,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004851299540104654,
|
|
"loss": 5.9198,
|
|
"mean_token_accuracy": 0.15186750441789626,
|
|
"num_tokens": 28764397.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 6.126307487487793,
|
|
"epoch": 1.241370270034082,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.00048511881172110216,
|
|
"loss": 5.8665,
|
|
"mean_token_accuracy": 0.15348217338323594,
|
|
"num_tokens": 28773680.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 6.2114870071411135,
|
|
"epoch": 1.2418072183867868,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048510766540154997,
|
|
"loss": 5.938,
|
|
"mean_token_accuracy": 0.1543569818139076,
|
|
"num_tokens": 28784034.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 6.178019046783447,
|
|
"epoch": 1.2422441667394915,
|
|
"grad_norm": 9.6875,
|
|
"learning_rate": 0.00048509651505202275,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.14725581854581832,
|
|
"num_tokens": 28794487.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 6.205572175979614,
|
|
"epoch": 1.2426811150921961,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004850853606727342,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.1567555233836174,
|
|
"num_tokens": 28803942.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 6.22735013961792,
|
|
"epoch": 1.2431180634449008,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004850742022638984,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.14974181205034257,
|
|
"num_tokens": 28814498.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 6.124869060516358,
|
|
"epoch": 1.2435550117976055,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048506303982572924,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.15606651157140733,
|
|
"num_tokens": 28824513.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 6.208728075027466,
|
|
"epoch": 1.2439919601503102,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.000485051873358441,
|
|
"loss": 5.9939,
|
|
"mean_token_accuracy": 0.13807140439748763,
|
|
"num_tokens": 28835643.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 6.300460147857666,
|
|
"epoch": 1.244428908503015,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004850407028622477,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.1439963012933731,
|
|
"num_tokens": 28845615.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 6.223985242843628,
|
|
"epoch": 1.2448658568557196,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048502952833736365,
|
|
"loss": 5.8938,
|
|
"mean_token_accuracy": 0.1521884098649025,
|
|
"num_tokens": 28856152.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 6.114186573028564,
|
|
"epoch": 1.2453028052084243,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048501834978400323,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.1594656988978386,
|
|
"num_tokens": 28866926.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 6.1715654850006105,
|
|
"epoch": 1.245739753561129,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004850071672023809,
|
|
"loss": 5.9053,
|
|
"mean_token_accuracy": 0.14316325187683104,
|
|
"num_tokens": 28877188.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 6.161950588226318,
|
|
"epoch": 1.246176701913834,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048499598059271087,
|
|
"loss": 5.9003,
|
|
"mean_token_accuracy": 0.15031933039426804,
|
|
"num_tokens": 28887710.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 6.179935646057129,
|
|
"epoch": 1.2466136502665386,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.000484984789955208,
|
|
"loss": 5.9564,
|
|
"mean_token_accuracy": 0.14734355956315995,
|
|
"num_tokens": 28897064.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 6.162792730331421,
|
|
"epoch": 1.2470505986192433,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048497359529008684,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.14970822632312775,
|
|
"num_tokens": 28907103.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 6.175220203399658,
|
|
"epoch": 1.247487546971948,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004849623965975621,
|
|
"loss": 5.9142,
|
|
"mean_token_accuracy": 0.15144832134246827,
|
|
"num_tokens": 28916851.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 6.184738969802856,
|
|
"epoch": 1.2479244953246527,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004849511938778485,
|
|
"loss": 5.939,
|
|
"mean_token_accuracy": 0.14545366317033767,
|
|
"num_tokens": 28926638.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 6.281378841400146,
|
|
"epoch": 1.2483614436773574,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048493998713116103,
|
|
"loss": 5.9008,
|
|
"mean_token_accuracy": 0.1458335377275944,
|
|
"num_tokens": 28936764.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 6.153763341903686,
|
|
"epoch": 1.248798392030062,
|
|
"grad_norm": 6.28125,
|
|
"learning_rate": 0.00048492877635771464,
|
|
"loss": 5.9097,
|
|
"mean_token_accuracy": 0.14964258149266244,
|
|
"num_tokens": 28946494.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 6.078196859359741,
|
|
"epoch": 1.2492353403827667,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048491756155772433,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.1571328654885292,
|
|
"num_tokens": 28955626.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 6.212883758544922,
|
|
"epoch": 1.2496722887354714,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048490634273140517,
|
|
"loss": 5.9133,
|
|
"mean_token_accuracy": 0.1500519648194313,
|
|
"num_tokens": 28966317.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 6.1862303733825685,
|
|
"epoch": 1.2501092370881761,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00048489511987897236,
|
|
"loss": 5.9262,
|
|
"mean_token_accuracy": 0.14952007979154586,
|
|
"num_tokens": 28976063.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 6.153039216995239,
|
|
"epoch": 1.2505461854408808,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004848838930006411,
|
|
"loss": 5.9168,
|
|
"mean_token_accuracy": 0.14818838983774185,
|
|
"num_tokens": 28985789.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 6.097548723220825,
|
|
"epoch": 1.2509831337935857,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004848726620966269,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.14401112347841263,
|
|
"num_tokens": 28996458.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 6.223761940002442,
|
|
"epoch": 1.2514200821462902,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.000484861427167145,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.15155038833618165,
|
|
"num_tokens": 29007641.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 6.279244327545166,
|
|
"epoch": 1.251857030498995,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.00048485018821241104,
|
|
"loss": 5.9027,
|
|
"mean_token_accuracy": 0.14320011883974076,
|
|
"num_tokens": 29017351.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 6.154199171066284,
|
|
"epoch": 1.2522939788516998,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048483894523264045,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.1451245054602623,
|
|
"num_tokens": 29026951.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 6.141295862197876,
|
|
"epoch": 1.2527309272044045,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004848276982280489,
|
|
"loss": 5.9114,
|
|
"mean_token_accuracy": 0.15095143765211105,
|
|
"num_tokens": 29037596.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 6.18510365486145,
|
|
"epoch": 1.2531678755571092,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004848164471988522,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.15030819922685623,
|
|
"num_tokens": 29049010.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 6.204849195480347,
|
|
"epoch": 1.2536048239098139,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048480519214526616,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.15004382357001306,
|
|
"num_tokens": 29059028.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 6.18299822807312,
|
|
"epoch": 1.2540417722625186,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048479393306750647,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.14778466001152993,
|
|
"num_tokens": 29069661.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 6.192969179153442,
|
|
"epoch": 1.2544787206152233,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004847826699657893,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.15246857404708863,
|
|
"num_tokens": 29079971.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 6.177361106872558,
|
|
"epoch": 1.254915668967928,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048477140284033054,
|
|
"loss": 5.9444,
|
|
"mean_token_accuracy": 0.14768177792429923,
|
|
"num_tokens": 29091378.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 6.168608331680298,
|
|
"epoch": 1.2553526173206326,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004847601316913464,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.1504699133336544,
|
|
"num_tokens": 29101516.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 6.149482154846192,
|
|
"epoch": 1.2557895656733375,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000484748856519053,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.14562420397996903,
|
|
"num_tokens": 29112147.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 6.199831819534301,
|
|
"epoch": 1.256226514026042,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004847375773236667,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.1556869275867939,
|
|
"num_tokens": 29122084.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 6.222476291656494,
|
|
"epoch": 1.256663462378747,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004847262941054037,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.1485342875123024,
|
|
"num_tokens": 29131988.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 6.153385162353516,
|
|
"epoch": 1.2571004107314516,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004847150068644805,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.14586437940597535,
|
|
"num_tokens": 29141731.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 6.234918069839478,
|
|
"epoch": 1.2575373590841563,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048470371560111353,
|
|
"loss": 5.9764,
|
|
"mean_token_accuracy": 0.14204879105091095,
|
|
"num_tokens": 29152185.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 6.17518162727356,
|
|
"epoch": 1.257974307436861,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004846924203155194,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.15808162093162537,
|
|
"num_tokens": 29162337.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 6.174739646911621,
|
|
"epoch": 1.2584112557895657,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048468112100791483,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.14998275637626649,
|
|
"num_tokens": 29173246.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 6.193538475036621,
|
|
"epoch": 1.2588482041422704,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004846698176785165,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.15311593413352967,
|
|
"num_tokens": 29183700.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 6.180676078796386,
|
|
"epoch": 1.259285152494975,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004846585103275412,
|
|
"loss": 5.8798,
|
|
"mean_token_accuracy": 0.1494651809334755,
|
|
"num_tokens": 29193686.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 6.096537685394287,
|
|
"epoch": 1.2597221008476798,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048464719895520577,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.15009548962116243,
|
|
"num_tokens": 29203575.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 6.14689998626709,
|
|
"epoch": 1.2601590492003845,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004846358835617273,
|
|
"loss": 5.9124,
|
|
"mean_token_accuracy": 0.14776561483740808,
|
|
"num_tokens": 29213591.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 6.245035982131958,
|
|
"epoch": 1.2605959975530892,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048462456414732257,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.15431948006153107,
|
|
"num_tokens": 29222799.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 6.156334686279297,
|
|
"epoch": 1.2610329459057938,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048461324071220896,
|
|
"loss": 5.8885,
|
|
"mean_token_accuracy": 0.15020613521337509,
|
|
"num_tokens": 29232477.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 6.164317464828491,
|
|
"epoch": 1.2614698942584988,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048460191325660356,
|
|
"loss": 5.8765,
|
|
"mean_token_accuracy": 0.14821490719914437,
|
|
"num_tokens": 29243477.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 6.179251861572266,
|
|
"epoch": 1.2619068426112032,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.00048459058178072366,
|
|
"loss": 5.9527,
|
|
"mean_token_accuracy": 0.14439554736018181,
|
|
"num_tokens": 29253426.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 6.253608751296997,
|
|
"epoch": 1.2623437909639081,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004845792462847866,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.14989247918128967,
|
|
"num_tokens": 29263639.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 6.1858583927154545,
|
|
"epoch": 1.2627807393166128,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048456790676900963,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.14528666511178018,
|
|
"num_tokens": 29273980.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 6.170363903045654,
|
|
"epoch": 1.2632176876693175,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048455656323361055,
|
|
"loss": 5.8503,
|
|
"mean_token_accuracy": 0.15631430894136428,
|
|
"num_tokens": 29283983.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 6.245016288757324,
|
|
"epoch": 1.2636546360220222,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004845452156788067,
|
|
"loss": 5.9828,
|
|
"mean_token_accuracy": 0.1483379125595093,
|
|
"num_tokens": 29294460.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 6.129631805419922,
|
|
"epoch": 1.264091584374727,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004845338641048158,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.14798096418380738,
|
|
"num_tokens": 29305788.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 6.250259923934936,
|
|
"epoch": 1.2645285327274316,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00048452250851185565,
|
|
"loss": 5.9422,
|
|
"mean_token_accuracy": 0.14614320248365403,
|
|
"num_tokens": 29315457.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 6.224140596389771,
|
|
"epoch": 1.2649654810801363,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000484511148900144,
|
|
"loss": 5.8709,
|
|
"mean_token_accuracy": 0.1495636910200119,
|
|
"num_tokens": 29325713.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 6.12435245513916,
|
|
"epoch": 1.265402429432841,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004844997852698987,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.14698525816202163,
|
|
"num_tokens": 29336489.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 6.146484518051148,
|
|
"epoch": 1.2658393777855457,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004844884176213377,
|
|
"loss": 5.8808,
|
|
"mean_token_accuracy": 0.15530710518360138,
|
|
"num_tokens": 29345567.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 6.2139365673065186,
|
|
"epoch": 1.2662763261382506,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048447704595467917,
|
|
"loss": 5.8864,
|
|
"mean_token_accuracy": 0.15221369564533233,
|
|
"num_tokens": 29355890.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 6.194058895111084,
|
|
"epoch": 1.266713274490955,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00048446567027014104,
|
|
"loss": 5.9328,
|
|
"mean_token_accuracy": 0.1531245470046997,
|
|
"num_tokens": 29365948.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 6.153910350799561,
|
|
"epoch": 1.26715022284366,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004844542905679417,
|
|
"loss": 5.8788,
|
|
"mean_token_accuracy": 0.14753377586603164,
|
|
"num_tokens": 29375673.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 6.104307842254639,
|
|
"epoch": 1.2675871711963647,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004844429068482993,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.14662039428949356,
|
|
"num_tokens": 29384567.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 6.120322132110596,
|
|
"epoch": 1.2680241195490694,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048443151911143213,
|
|
"loss": 5.7971,
|
|
"mean_token_accuracy": 0.1598436340689659,
|
|
"num_tokens": 29393747.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 6.15862078666687,
|
|
"epoch": 1.268461067901774,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004844201273575587,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.1484014794230461,
|
|
"num_tokens": 29404095.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 6.155391836166382,
|
|
"epoch": 1.2688980162544787,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048440873158689754,
|
|
"loss": 5.8901,
|
|
"mean_token_accuracy": 0.15144707411527633,
|
|
"num_tokens": 29414450.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 6.144805431365967,
|
|
"epoch": 1.2693349646071834,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004843973317996672,
|
|
"loss": 5.8761,
|
|
"mean_token_accuracy": 0.14961023330688478,
|
|
"num_tokens": 29424054.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 6.23119421005249,
|
|
"epoch": 1.2697719129598881,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004843859279960862,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.14579635262489318,
|
|
"num_tokens": 29434585.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 6.171369028091431,
|
|
"epoch": 1.2702088613125928,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004843745201763735,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.15390822887420655,
|
|
"num_tokens": 29443863.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 6.1620285987854,
|
|
"epoch": 1.2706458096652975,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048436310834074764,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.15127672255039215,
|
|
"num_tokens": 29453851.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 6.121674203872681,
|
|
"epoch": 1.2710827580180022,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004843516924894278,
|
|
"loss": 5.8042,
|
|
"mean_token_accuracy": 0.16123372465372085,
|
|
"num_tokens": 29465152.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 6.130862045288086,
|
|
"epoch": 1.2715197063707069,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00048434027262263274,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.1620439700782299,
|
|
"num_tokens": 29474749.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 6.169938659667968,
|
|
"epoch": 1.2719566547234118,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004843288487405816,
|
|
"loss": 5.8832,
|
|
"mean_token_accuracy": 0.15470795184373856,
|
|
"num_tokens": 29483554.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 6.127190589904785,
|
|
"epoch": 1.2723936030761165,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00048431742084349347,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.1568259835243225,
|
|
"num_tokens": 29493718.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 6.147765874862671,
|
|
"epoch": 1.2728305514288212,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004843059889315874,
|
|
"loss": 5.9602,
|
|
"mean_token_accuracy": 0.14497726261615754,
|
|
"num_tokens": 29504407.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 6.289806747436524,
|
|
"epoch": 1.2732674997815259,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004842945530050829,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.143418525159359,
|
|
"num_tokens": 29514992.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 6.278067493438721,
|
|
"epoch": 1.2737044481342306,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048428311306419913,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.14940451830625534,
|
|
"num_tokens": 29525109.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 6.171770906448364,
|
|
"epoch": 1.2741413964869353,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048427166910915565,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.15071330070495606,
|
|
"num_tokens": 29536131.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 6.155459690093994,
|
|
"epoch": 1.27457834483964,
|
|
"grad_norm": 5.875,
|
|
"learning_rate": 0.0004842602211401719,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.1590773269534111,
|
|
"num_tokens": 29547614.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 6.171518802642822,
|
|
"epoch": 1.2750152931923446,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004842487691574675,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.15063830241560935,
|
|
"num_tokens": 29557499.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 6.212518548965454,
|
|
"epoch": 1.2754522415450493,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048423731316126194,
|
|
"loss": 5.9303,
|
|
"mean_token_accuracy": 0.14245495349168777,
|
|
"num_tokens": 29569909.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 6.2845064163208,
|
|
"epoch": 1.275889189897754,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004842258531517752,
|
|
"loss": 6.0474,
|
|
"mean_token_accuracy": 0.1399131067097187,
|
|
"num_tokens": 29581261.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 6.194215154647827,
|
|
"epoch": 1.2763261382504587,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004842143891292269,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.1560487687587738,
|
|
"num_tokens": 29590604.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 6.134926891326904,
|
|
"epoch": 1.2767630866031636,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00048420292109383704,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.14538030028343202,
|
|
"num_tokens": 29600129.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 6.161518955230713,
|
|
"epoch": 1.277200034955868,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048419144904582545,
|
|
"loss": 5.8293,
|
|
"mean_token_accuracy": 0.15877978950738908,
|
|
"num_tokens": 29609608.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 6.120277404785156,
|
|
"epoch": 1.277636983308573,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048417997298541235,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.15769645273685456,
|
|
"num_tokens": 29618764.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 6.20949501991272,
|
|
"epoch": 1.2780739316612777,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048416849291281765,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.1464912362396717,
|
|
"num_tokens": 29628703.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 6.209291124343872,
|
|
"epoch": 1.2785108800139824,
|
|
"grad_norm": 7.125,
|
|
"learning_rate": 0.00048415700882826167,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.1516139253973961,
|
|
"num_tokens": 29639291.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 6.132389068603516,
|
|
"epoch": 1.278947828366687,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048414552073196477,
|
|
"loss": 5.895,
|
|
"mean_token_accuracy": 0.15139073729515076,
|
|
"num_tokens": 29649058.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 6.1872399806976315,
|
|
"epoch": 1.2793847767193918,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004841340286241471,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.150474514067173,
|
|
"num_tokens": 29658629.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 6.2158318042755125,
|
|
"epoch": 1.2798217250720965,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004841225325050292,
|
|
"loss": 5.9749,
|
|
"mean_token_accuracy": 0.14868110716342925,
|
|
"num_tokens": 29668875.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 6.182331609725952,
|
|
"epoch": 1.2802586734248012,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048411103237483156,
|
|
"loss": 5.9508,
|
|
"mean_token_accuracy": 0.14346095845103263,
|
|
"num_tokens": 29678427.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 6.166947937011718,
|
|
"epoch": 1.2806956217775058,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048409952823377474,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.155053573846817,
|
|
"num_tokens": 29688975.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 6.2332848072052,
|
|
"epoch": 1.2811325701302105,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.00048408802008207937,
|
|
"loss": 5.9506,
|
|
"mean_token_accuracy": 0.14689844325184823,
|
|
"num_tokens": 29699550.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 6.167322015762329,
|
|
"epoch": 1.2815695184829154,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.00048407650791996624,
|
|
"loss": 5.8898,
|
|
"mean_token_accuracy": 0.15218482315540313,
|
|
"num_tokens": 29709597.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 6.196347856521607,
|
|
"epoch": 1.28200646683562,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004840649917476561,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.14479824751615525,
|
|
"num_tokens": 29719250.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 6.226090764999389,
|
|
"epoch": 1.2824434151883248,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048405347156536995,
|
|
"loss": 5.9619,
|
|
"mean_token_accuracy": 0.14350830093026162,
|
|
"num_tokens": 29728809.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 6.182662153244019,
|
|
"epoch": 1.2828803635410295,
|
|
"grad_norm": 9.3125,
|
|
"learning_rate": 0.0004840419473733287,
|
|
"loss": 5.8683,
|
|
"mean_token_accuracy": 0.15773474425077438,
|
|
"num_tokens": 29739240.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 6.257904052734375,
|
|
"epoch": 1.2833173118937342,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00048403041917175323,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.15196478217840195,
|
|
"num_tokens": 29749284.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 6.19420804977417,
|
|
"epoch": 1.283754260246439,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.00048401888696086485,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.1439095050096512,
|
|
"num_tokens": 29758770.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 6.133532524108887,
|
|
"epoch": 1.2841912085991436,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004840073507408847,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.14940415620803832,
|
|
"num_tokens": 29770111.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 6.124604606628418,
|
|
"epoch": 1.2846281569518483,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.000483995810512034,
|
|
"loss": 5.866,
|
|
"mean_token_accuracy": 0.1501758873462677,
|
|
"num_tokens": 29780210.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 6.143610954284668,
|
|
"epoch": 1.285065105304553,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048398426627453423,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.1509410858154297,
|
|
"num_tokens": 29789903.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 6.23986930847168,
|
|
"epoch": 1.2855020536572577,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048397271802860667,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.15100280642509462,
|
|
"num_tokens": 29799377.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 6.223856353759766,
|
|
"epoch": 1.2859390020099624,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004839611657744729,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.15203122347593306,
|
|
"num_tokens": 29809173.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 6.100538730621338,
|
|
"epoch": 1.286375950362667,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.00048394960951235444,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.15066004991531373,
|
|
"num_tokens": 29819475.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 6.101089286804199,
|
|
"epoch": 1.2868128987153717,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.000483938049242473,
|
|
"loss": 5.8497,
|
|
"mean_token_accuracy": 0.14844564348459244,
|
|
"num_tokens": 29829109.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 6.2474274158477785,
|
|
"epoch": 1.2872498470680767,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00048392648496505024,
|
|
"loss": 5.865,
|
|
"mean_token_accuracy": 0.15116432979702948,
|
|
"num_tokens": 29839735.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 6.202255153656006,
|
|
"epoch": 1.2876867954207811,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004839149166803081,
|
|
"loss": 5.8653,
|
|
"mean_token_accuracy": 0.1497869923710823,
|
|
"num_tokens": 29850039.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 6.1789017677307125,
|
|
"epoch": 1.288123743773486,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004839033443884684,
|
|
"loss": 5.8675,
|
|
"mean_token_accuracy": 0.1542421191930771,
|
|
"num_tokens": 29859411.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 6.182638645172119,
|
|
"epoch": 1.2885606921261907,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.0004838917680897531,
|
|
"loss": 5.977,
|
|
"mean_token_accuracy": 0.14336021691560746,
|
|
"num_tokens": 29870426.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 6.197987842559814,
|
|
"epoch": 1.2889976404788954,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048388018778438413,
|
|
"loss": 5.8966,
|
|
"mean_token_accuracy": 0.14952237159013748,
|
|
"num_tokens": 29881992.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 6.1714198112487795,
|
|
"epoch": 1.2894345888316001,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004838686034725838,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.1571191132068634,
|
|
"num_tokens": 29891496.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 6.186280012130737,
|
|
"epoch": 1.2898715371843048,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00048385701515457413,
|
|
"loss": 5.8917,
|
|
"mean_token_accuracy": 0.14586877152323724,
|
|
"num_tokens": 29901529.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 6.172721338272095,
|
|
"epoch": 1.2903084855370095,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.0004838454228305775,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.15179523825645447,
|
|
"num_tokens": 29910773.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 6.1468113422393795,
|
|
"epoch": 1.2907454338897142,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048383382650081633,
|
|
"loss": 5.9087,
|
|
"mean_token_accuracy": 0.14850216880440711,
|
|
"num_tokens": 29919381.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 6.1847312450408936,
|
|
"epoch": 1.2911823822424189,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004838222261655129,
|
|
"loss": 5.9324,
|
|
"mean_token_accuracy": 0.1445184215903282,
|
|
"num_tokens": 29929179.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 6.20357494354248,
|
|
"epoch": 1.2916193305951236,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00048381062182488964,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.15342671424150467,
|
|
"num_tokens": 29938252.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 6.130641937255859,
|
|
"epoch": 1.2920562789478285,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048379901347916926,
|
|
"loss": 5.9049,
|
|
"mean_token_accuracy": 0.15069559663534166,
|
|
"num_tokens": 29947489.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 6.114811038970947,
|
|
"epoch": 1.292493227300533,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048378740112857443,
|
|
"loss": 5.8311,
|
|
"mean_token_accuracy": 0.15836550891399384,
|
|
"num_tokens": 29956788.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 6.205475473403931,
|
|
"epoch": 1.2929301756532379,
|
|
"grad_norm": 6.25,
|
|
"learning_rate": 0.00048377578477332785,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.1439168445765972,
|
|
"num_tokens": 29967161.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 6.186266565322876,
|
|
"epoch": 1.2933671240059426,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004837641644136523,
|
|
"loss": 5.7726,
|
|
"mean_token_accuracy": 0.16408921927213668,
|
|
"num_tokens": 29976739.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 6.1210907936096195,
|
|
"epoch": 1.2938040723586473,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048375254004977074,
|
|
"loss": 5.8829,
|
|
"mean_token_accuracy": 0.15104206800460815,
|
|
"num_tokens": 29986739.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 6.1187256336212155,
|
|
"epoch": 1.294241020711352,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004837409116819061,
|
|
"loss": 5.8638,
|
|
"mean_token_accuracy": 0.1541775420308113,
|
|
"num_tokens": 29996687.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 6.1896298885345455,
|
|
"epoch": 1.2946779690640566,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004837292793102813,
|
|
"loss": 5.9114,
|
|
"mean_token_accuracy": 0.15141934752464295,
|
|
"num_tokens": 30007757.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 6.14250807762146,
|
|
"epoch": 1.2951149174167613,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048371764293511963,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.1616487592458725,
|
|
"num_tokens": 30018129.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 6.200066232681275,
|
|
"epoch": 1.295551865769466,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004837060025566441,
|
|
"loss": 5.8952,
|
|
"mean_token_accuracy": 0.14735157638788224,
|
|
"num_tokens": 30028194.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 6.165783643722534,
|
|
"epoch": 1.2959888141221707,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004836943581750782,
|
|
"loss": 5.9972,
|
|
"mean_token_accuracy": 0.1404227539896965,
|
|
"num_tokens": 30038182.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 6.258273410797119,
|
|
"epoch": 1.2964257624748754,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004836827097906451,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.15336589217185975,
|
|
"num_tokens": 30047848.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 6.2141883850097654,
|
|
"epoch": 1.2968627108275803,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048367105740356825,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.15072886943817138,
|
|
"num_tokens": 30058697.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 6.160948419570923,
|
|
"epoch": 1.2972996591802848,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048365940101407123,
|
|
"loss": 5.8247,
|
|
"mean_token_accuracy": 0.15410750061273576,
|
|
"num_tokens": 30068611.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 6.098754644393921,
|
|
"epoch": 1.2977366075329897,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004836477406223775,
|
|
"loss": 5.8587,
|
|
"mean_token_accuracy": 0.15362597554922103,
|
|
"num_tokens": 30077992.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 6.339209318161011,
|
|
"epoch": 1.2981735558856944,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048363607622871086,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.1438070684671402,
|
|
"num_tokens": 30088940.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 6.261860942840576,
|
|
"epoch": 1.298610504238399,
|
|
"grad_norm": 9.625,
|
|
"learning_rate": 0.00048362440783329485,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.1498449146747589,
|
|
"num_tokens": 30099249.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 6.087208557128906,
|
|
"epoch": 1.2990474525911038,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004836127354363535,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.15286509990692138,
|
|
"num_tokens": 30110548.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 6.082006931304932,
|
|
"epoch": 1.2994844009438085,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048360105903811045,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.1580217644572258,
|
|
"num_tokens": 30120842.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 6.224267482757568,
|
|
"epoch": 1.2999213492965132,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048358937863878984,
|
|
"loss": 5.9568,
|
|
"mean_token_accuracy": 0.14608903005719184,
|
|
"num_tokens": 30130439.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 6.233326101303101,
|
|
"epoch": 1.3003582976492178,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004835776942386157,
|
|
"loss": 5.937,
|
|
"mean_token_accuracy": 0.14689819365739823,
|
|
"num_tokens": 30140976.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 6.159067153930664,
|
|
"epoch": 1.3007952460019225,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.000483566005837812,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.15265558809041976,
|
|
"num_tokens": 30150989.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 6.169952821731568,
|
|
"epoch": 1.3012321943546272,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048355431343660303,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.14985596537590026,
|
|
"num_tokens": 30161605.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 6.190279483795166,
|
|
"epoch": 1.301669142707332,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004835426170352131,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.1517595186829567,
|
|
"num_tokens": 30171361.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 6.1301452159881595,
|
|
"epoch": 1.3021060910600366,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048353091663386655,
|
|
"loss": 5.8008,
|
|
"mean_token_accuracy": 0.15861595720052718,
|
|
"num_tokens": 30180352.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 6.201026821136475,
|
|
"epoch": 1.3025430394127415,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004835192122327877,
|
|
"loss": 5.8525,
|
|
"mean_token_accuracy": 0.15493385791778563,
|
|
"num_tokens": 30190624.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 6.1833131313323975,
|
|
"epoch": 1.302979987765446,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00048350750383220105,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.1573862612247467,
|
|
"num_tokens": 30200203.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 6.120649671554565,
|
|
"epoch": 1.303416936118151,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048349579143233126,
|
|
"loss": 5.8638,
|
|
"mean_token_accuracy": 0.15807482749223709,
|
|
"num_tokens": 30210546.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 6.216634082794189,
|
|
"epoch": 1.3038538844708556,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004834840750334029,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.14518765062093736,
|
|
"num_tokens": 30221316.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 6.279817199707031,
|
|
"epoch": 1.3042908328235603,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004834723546356408,
|
|
"loss": 5.9442,
|
|
"mean_token_accuracy": 0.14440446943044663,
|
|
"num_tokens": 30232580.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 6.15865535736084,
|
|
"epoch": 1.304727781176265,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048346063023926964,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.1546608865261078,
|
|
"num_tokens": 30241976.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 6.127216720581055,
|
|
"epoch": 1.3051647295289697,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048344890184451436,
|
|
"loss": 5.8836,
|
|
"mean_token_accuracy": 0.14819984436035155,
|
|
"num_tokens": 30252723.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 6.210349750518799,
|
|
"epoch": 1.3056016778816744,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048343716945159997,
|
|
"loss": 5.9174,
|
|
"mean_token_accuracy": 0.15172467082738877,
|
|
"num_tokens": 30263125.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 6.158228874206543,
|
|
"epoch": 1.306038626234379,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004834254330607514,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.16196292042732238,
|
|
"num_tokens": 30273113.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 6.129610347747803,
|
|
"epoch": 1.3064755745870837,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004834136926721939,
|
|
"loss": 5.8029,
|
|
"mean_token_accuracy": 0.1589888870716095,
|
|
"num_tokens": 30282550.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 6.12127275466919,
|
|
"epoch": 1.3069125229397884,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048340194828615246,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.14687294214963914,
|
|
"num_tokens": 30293377.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 6.179308366775513,
|
|
"epoch": 1.3073494712924933,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004833901999028525,
|
|
"loss": 5.8712,
|
|
"mean_token_accuracy": 0.15503755509853362,
|
|
"num_tokens": 30303147.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 6.183325147628784,
|
|
"epoch": 1.3077864196451978,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004833784475225192,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.14612608253955842,
|
|
"num_tokens": 30313426.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 6.19778151512146,
|
|
"epoch": 1.3082233679979027,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004833666911453783,
|
|
"loss": 5.9343,
|
|
"mean_token_accuracy": 0.14557006433606148,
|
|
"num_tokens": 30323896.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 6.130338335037232,
|
|
"epoch": 1.3086603163506074,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000483354930771655,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.14434198811650276,
|
|
"num_tokens": 30333523.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 6.204380941390991,
|
|
"epoch": 1.3090972647033121,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048334316640157493,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.15440258681774138,
|
|
"num_tokens": 30344035.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 6.2058931350708,
|
|
"epoch": 1.3095342130560168,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004833313980353637,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.15022298619151114,
|
|
"num_tokens": 30354385.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 6.104279375076294,
|
|
"epoch": 1.3099711614087215,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048331962567324717,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.1413296028971672,
|
|
"num_tokens": 30364941.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 6.1678324222564695,
|
|
"epoch": 1.3104081097614262,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000483307849315451,
|
|
"loss": 5.838,
|
|
"mean_token_accuracy": 0.15294638648629189,
|
|
"num_tokens": 30376160.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 6.274331426620483,
|
|
"epoch": 1.3108450581141309,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048329606896220116,
|
|
"loss": 5.9276,
|
|
"mean_token_accuracy": 0.14750345796346664,
|
|
"num_tokens": 30385018.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.3108450581141309,
|
|
"eval_entropy": 5.9782779657328025,
|
|
"eval_loss": 5.957468032836914,
|
|
"eval_mean_token_accuracy": 0.15653674234963208,
|
|
"eval_num_tokens": 30385018.0,
|
|
"eval_runtime": 28.2657,
|
|
"eval_samples_per_second": 1309.502,
|
|
"eval_steps_per_second": 163.697,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 6.148051929473877,
|
|
"epoch": 1.3112820064668356,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004832842846137236,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.15537035912275315,
|
|
"num_tokens": 30394618.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 6.176465845108032,
|
|
"epoch": 1.3117189548195403,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048327249627024433,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.15127553790807724,
|
|
"num_tokens": 30404081.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 6.134244537353515,
|
|
"epoch": 1.3121559031722452,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004832607039319894,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.14448730796575546,
|
|
"num_tokens": 30413892.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 6.214825677871704,
|
|
"epoch": 1.3125928515249496,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048324890759918513,
|
|
"loss": 5.9509,
|
|
"mean_token_accuracy": 0.14472972452640534,
|
|
"num_tokens": 30424523.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 6.194734239578247,
|
|
"epoch": 1.3130297998776546,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004832371072720576,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.15406875610351561,
|
|
"num_tokens": 30435092.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 6.084768152236938,
|
|
"epoch": 1.3134667482303592,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004832253029508332,
|
|
"loss": 5.8419,
|
|
"mean_token_accuracy": 0.15242524743080138,
|
|
"num_tokens": 30445628.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 6.1286914348602295,
|
|
"epoch": 1.313903696583064,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004832134946357384,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.14976181983947753,
|
|
"num_tokens": 30457433.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 6.206806182861328,
|
|
"epoch": 1.3143406449357686,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004832016823269998,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.15214013457298278,
|
|
"num_tokens": 30467987.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 6.178217506408691,
|
|
"epoch": 1.3147775932884733,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004831898660248437,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.14360788315534592,
|
|
"num_tokens": 30476577.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 6.153936910629272,
|
|
"epoch": 1.315214541641178,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048317804572949697,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.15068671256303787,
|
|
"num_tokens": 30487410.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 6.202679681777954,
|
|
"epoch": 1.3156514899938827,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004831662214411862,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.1465588890016079,
|
|
"num_tokens": 30497778.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 6.178036642074585,
|
|
"epoch": 1.3160884383465874,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004831543931601382,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.15059689432382584,
|
|
"num_tokens": 30507369.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 6.166036605834961,
|
|
"epoch": 1.316525386699292,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.00048314256088657985,
|
|
"loss": 5.9122,
|
|
"mean_token_accuracy": 0.14978303164243698,
|
|
"num_tokens": 30518126.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 6.145087623596192,
|
|
"epoch": 1.3169623350519968,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004831307246207382,
|
|
"loss": 5.8763,
|
|
"mean_token_accuracy": 0.15576560273766518,
|
|
"num_tokens": 30528167.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 6.1718322277069095,
|
|
"epoch": 1.3173992834047015,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048311888436284017,
|
|
"loss": 5.8401,
|
|
"mean_token_accuracy": 0.15360784232616426,
|
|
"num_tokens": 30538111.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 6.129813718795776,
|
|
"epoch": 1.3178362317574064,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004831070401131129,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.1528167486190796,
|
|
"num_tokens": 30547773.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 6.119461917877198,
|
|
"epoch": 1.3182731801101109,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004830951918717834,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.1502302333712578,
|
|
"num_tokens": 30558058.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 6.133006429672241,
|
|
"epoch": 1.3187101284628158,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048308333963907927,
|
|
"loss": 5.8117,
|
|
"mean_token_accuracy": 0.15927943140268325,
|
|
"num_tokens": 30567297.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 6.184013843536377,
|
|
"epoch": 1.3191470768155205,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00048307148341522756,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.15289607793092727,
|
|
"num_tokens": 30578159.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 6.1799774169921875,
|
|
"epoch": 1.3195840251682251,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048305962320045574,
|
|
"loss": 5.9017,
|
|
"mean_token_accuracy": 0.15140537172555923,
|
|
"num_tokens": 30588734.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 6.105605602264404,
|
|
"epoch": 1.3200209735209298,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048304775899499143,
|
|
"loss": 5.8031,
|
|
"mean_token_accuracy": 0.16111132502555847,
|
|
"num_tokens": 30598496.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 6.117049646377564,
|
|
"epoch": 1.3204579218736345,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000483035890799062,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.15213498026132583,
|
|
"num_tokens": 30608330.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 6.183338308334351,
|
|
"epoch": 1.3208948702263392,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004830240186128952,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.15419178307056428,
|
|
"num_tokens": 30618887.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 6.22232494354248,
|
|
"epoch": 1.321331818579044,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048301214243671884,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.15129734724760055,
|
|
"num_tokens": 30629479.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 6.147677993774414,
|
|
"epoch": 1.3217687669317486,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004830002622707604,
|
|
"loss": 5.817,
|
|
"mean_token_accuracy": 0.154408822953701,
|
|
"num_tokens": 30639270.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 6.130454587936401,
|
|
"epoch": 1.3222057152844533,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004829883781152481,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.15437458902597428,
|
|
"num_tokens": 30649156.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 6.149850511550904,
|
|
"epoch": 1.3226426636371582,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048297648997040966,
|
|
"loss": 5.9678,
|
|
"mean_token_accuracy": 0.14519903287291527,
|
|
"num_tokens": 30659919.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 6.226070213317871,
|
|
"epoch": 1.3230796119898627,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048296459783647304,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.15368696600198745,
|
|
"num_tokens": 30670523.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 6.204253149032593,
|
|
"epoch": 1.3235165603425676,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048295270171366665,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.15158659368753433,
|
|
"num_tokens": 30680803.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 6.1911430835723875,
|
|
"epoch": 1.3239535086952723,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048294080160221837,
|
|
"loss": 5.8146,
|
|
"mean_token_accuracy": 0.1503637984395027,
|
|
"num_tokens": 30690401.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 6.188399791717529,
|
|
"epoch": 1.324390457047977,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048292889750235665,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.14866487085819244,
|
|
"num_tokens": 30700779.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 6.187041854858398,
|
|
"epoch": 1.3248274054006817,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00048291698941430955,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.14539026319980622,
|
|
"num_tokens": 30711556.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 6.15223240852356,
|
|
"epoch": 1.3252643537533864,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004829050773383058,
|
|
"loss": 5.7862,
|
|
"mean_token_accuracy": 0.15828098356723785,
|
|
"num_tokens": 30721929.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 6.176116609573365,
|
|
"epoch": 1.325701302106091,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004828931612745737,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.1483965814113617,
|
|
"num_tokens": 30732848.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 6.141019487380982,
|
|
"epoch": 1.3261382504587957,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048288124122334176,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.14580026268959045,
|
|
"num_tokens": 30742628.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 6.191814947128296,
|
|
"epoch": 1.3265751988115004,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004828693171848388,
|
|
"loss": 5.9259,
|
|
"mean_token_accuracy": 0.14872915670275688,
|
|
"num_tokens": 30752866.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 6.157923841476441,
|
|
"epoch": 1.3270121471642051,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004828573891592933,
|
|
"loss": 5.8502,
|
|
"mean_token_accuracy": 0.1581645578145981,
|
|
"num_tokens": 30762861.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 6.089473295211792,
|
|
"epoch": 1.32744909551691,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004828454571469342,
|
|
"loss": 5.9181,
|
|
"mean_token_accuracy": 0.15590844303369522,
|
|
"num_tokens": 30772555.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 6.173651218414307,
|
|
"epoch": 1.3278860438696145,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004828335211479903,
|
|
"loss": 5.8846,
|
|
"mean_token_accuracy": 0.15066574960947038,
|
|
"num_tokens": 30782739.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 6.259365129470825,
|
|
"epoch": 1.3283229922223194,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048282158116269065,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.1502900466322899,
|
|
"num_tokens": 30792600.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 6.158281898498535,
|
|
"epoch": 1.3287599405750241,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004828096371912641,
|
|
"loss": 5.8832,
|
|
"mean_token_accuracy": 0.144914473593235,
|
|
"num_tokens": 30801433.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 6.101165246963501,
|
|
"epoch": 1.3291968889277288,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048279768923393987,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.14661043509840965,
|
|
"num_tokens": 30811277.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 6.1981529712677,
|
|
"epoch": 1.3296338372804335,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048278573729094705,
|
|
"loss": 5.9108,
|
|
"mean_token_accuracy": 0.15046690851449968,
|
|
"num_tokens": 30821120.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 6.171682071685791,
|
|
"epoch": 1.3300707856331382,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048277378136251487,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.15861936211585997,
|
|
"num_tokens": 30831660.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 6.217426538467407,
|
|
"epoch": 1.3305077339858429,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048276182144887274,
|
|
"loss": 5.9028,
|
|
"mean_token_accuracy": 0.14908593744039536,
|
|
"num_tokens": 30842530.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 6.231807518005371,
|
|
"epoch": 1.3309446823385476,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048274985755025003,
|
|
"loss": 5.905,
|
|
"mean_token_accuracy": 0.14666102826595306,
|
|
"num_tokens": 30852954.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 6.13426661491394,
|
|
"epoch": 1.3313816306912523,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048273788966687615,
|
|
"loss": 5.8191,
|
|
"mean_token_accuracy": 0.153940911591053,
|
|
"num_tokens": 30862864.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 6.167418193817139,
|
|
"epoch": 1.331818579043957,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004827259177989807,
|
|
"loss": 5.8957,
|
|
"mean_token_accuracy": 0.14726108610630034,
|
|
"num_tokens": 30873533.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 6.175304317474366,
|
|
"epoch": 1.3322555273966616,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00048271394194679336,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.15829232484102249,
|
|
"num_tokens": 30883564.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 6.18950309753418,
|
|
"epoch": 1.3326924757493663,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004827019621105436,
|
|
"loss": 5.861,
|
|
"mean_token_accuracy": 0.15210068076848984,
|
|
"num_tokens": 30893516.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 6.149360847473145,
|
|
"epoch": 1.3331294241020712,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048268997829046156,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.15454588681459427,
|
|
"num_tokens": 30903104.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 6.150010442733764,
|
|
"epoch": 1.3335663724547757,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048267799048677684,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.15118254125118255,
|
|
"num_tokens": 30912759.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 6.1635654926300045,
|
|
"epoch": 1.3340033208074806,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004826659986997194,
|
|
"loss": 5.8662,
|
|
"mean_token_accuracy": 0.15174566358327865,
|
|
"num_tokens": 30921361.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 6.174410438537597,
|
|
"epoch": 1.3344402691601853,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004826540029295193,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.14787096679210662,
|
|
"num_tokens": 30931006.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 6.157722854614258,
|
|
"epoch": 1.33487721751289,
|
|
"grad_norm": 6.25,
|
|
"learning_rate": 0.00048264200317640665,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.1552622899413109,
|
|
"num_tokens": 30940647.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 6.197625541687012,
|
|
"epoch": 1.3353141658655947,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004826299994406116,
|
|
"loss": 5.9313,
|
|
"mean_token_accuracy": 0.14712630659341813,
|
|
"num_tokens": 30951028.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 6.146320819854736,
|
|
"epoch": 1.3357511142182994,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048261799172236435,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.15156200900673866,
|
|
"num_tokens": 30960726.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 6.188878679275513,
|
|
"epoch": 1.336188062571004,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004826059800218952,
|
|
"loss": 5.9599,
|
|
"mean_token_accuracy": 0.14741793274879456,
|
|
"num_tokens": 30971061.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 6.15547456741333,
|
|
"epoch": 1.3366250109237088,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004825939643394346,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.16355321407318116,
|
|
"num_tokens": 30980518.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 6.189762926101684,
|
|
"epoch": 1.3370619592764135,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.00048258194467521294,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.14899965077638627,
|
|
"num_tokens": 30990759.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 6.232774972915649,
|
|
"epoch": 1.3374989076291182,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048256992102946084,
|
|
"loss": 5.9453,
|
|
"mean_token_accuracy": 0.14278285801410676,
|
|
"num_tokens": 31002218.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 6.13329291343689,
|
|
"epoch": 1.337935855981823,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004825578934024089,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.1570137172937393,
|
|
"num_tokens": 31012434.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 6.19418683052063,
|
|
"epoch": 1.3383728043345275,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048254586179428776,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.14452686607837678,
|
|
"num_tokens": 31022805.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 6.179207801818848,
|
|
"epoch": 1.3388097526872325,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004825338262053283,
|
|
"loss": 5.862,
|
|
"mean_token_accuracy": 0.15455538034439087,
|
|
"num_tokens": 31032563.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 6.09782919883728,
|
|
"epoch": 1.3392467010399371,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004825217866357613,
|
|
"loss": 5.8146,
|
|
"mean_token_accuracy": 0.1602785497903824,
|
|
"num_tokens": 31041445.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 6.1660455703735355,
|
|
"epoch": 1.3396836493926418,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00048250974308581765,
|
|
"loss": 5.8604,
|
|
"mean_token_accuracy": 0.15620155781507492,
|
|
"num_tokens": 31051413.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 6.218658828735352,
|
|
"epoch": 1.3401205977453465,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048249769555572844,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.15629526674747468,
|
|
"num_tokens": 31061822.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 6.133849668502807,
|
|
"epoch": 1.3405575460980512,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048248564404572463,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.15279928594827652,
|
|
"num_tokens": 31071889.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 6.089661073684693,
|
|
"epoch": 1.340994494450756,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048247358855603754,
|
|
"loss": 5.8109,
|
|
"mean_token_accuracy": 0.16055045872926713,
|
|
"num_tokens": 31080933.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 6.156580591201783,
|
|
"epoch": 1.3414314428034606,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004824615290868982,
|
|
"loss": 5.9418,
|
|
"mean_token_accuracy": 0.14569876790046693,
|
|
"num_tokens": 31091349.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 6.312840843200684,
|
|
"epoch": 1.3418683911561653,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004824494656385381,
|
|
"loss": 5.9142,
|
|
"mean_token_accuracy": 0.1483866587281227,
|
|
"num_tokens": 31101485.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 6.1742030620574955,
|
|
"epoch": 1.34230533950887,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.0004824373982111886,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.1494912676513195,
|
|
"num_tokens": 31111965.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 6.140328216552734,
|
|
"epoch": 1.3427422878615747,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.000482425326805081,
|
|
"loss": 5.853,
|
|
"mean_token_accuracy": 0.15451739430427552,
|
|
"num_tokens": 31122284.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 6.207666969299316,
|
|
"epoch": 1.3431792362142794,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.00048241325142044697,
|
|
"loss": 5.8889,
|
|
"mean_token_accuracy": 0.1462631568312645,
|
|
"num_tokens": 31132156.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 6.172466468811035,
|
|
"epoch": 1.3436161845669843,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048240117205751817,
|
|
"loss": 5.812,
|
|
"mean_token_accuracy": 0.15407064855098723,
|
|
"num_tokens": 31141609.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 6.060343790054321,
|
|
"epoch": 1.344053132919689,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004823890887165261,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.14953329041600227,
|
|
"num_tokens": 31153159.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 6.133303213119507,
|
|
"epoch": 1.3444900812723937,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00048237700139770273,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.1543626755475998,
|
|
"num_tokens": 31163330.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 6.2770579814910885,
|
|
"epoch": 1.3449270296250984,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004823649101012797,
|
|
"loss": 5.9351,
|
|
"mean_token_accuracy": 0.15404071658849716,
|
|
"num_tokens": 31173874.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 6.158340740203857,
|
|
"epoch": 1.345363977977803,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004823528148274891,
|
|
"loss": 5.824,
|
|
"mean_token_accuracy": 0.15880247950553894,
|
|
"num_tokens": 31183933.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 6.081319904327392,
|
|
"epoch": 1.3458009263305077,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048234071557656295,
|
|
"loss": 5.8066,
|
|
"mean_token_accuracy": 0.16156378239393235,
|
|
"num_tokens": 31194308.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 6.11509256362915,
|
|
"epoch": 1.3462378746832124,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004823286123487331,
|
|
"loss": 5.8618,
|
|
"mean_token_accuracy": 0.15184128731489183,
|
|
"num_tokens": 31203757.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 6.218196010589599,
|
|
"epoch": 1.3466748230359171,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048231650514423194,
|
|
"loss": 5.945,
|
|
"mean_token_accuracy": 0.14972004294395447,
|
|
"num_tokens": 31213980.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 6.261203813552856,
|
|
"epoch": 1.3471117713886218,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00048230439396329143,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.14936172515153884,
|
|
"num_tokens": 31225034.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 6.133521842956543,
|
|
"epoch": 1.3475487197413265,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00048229227880614413,
|
|
"loss": 5.8927,
|
|
"mean_token_accuracy": 0.14812134951353073,
|
|
"num_tokens": 31236393.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 6.150119924545288,
|
|
"epoch": 1.3479856680940312,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004822801596730222,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.1485971063375473,
|
|
"num_tokens": 31246577.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 6.1682209968566895,
|
|
"epoch": 1.348422616446736,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048226803656415833,
|
|
"loss": 5.8241,
|
|
"mean_token_accuracy": 0.15531778931617737,
|
|
"num_tokens": 31256004.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 6.202504634857178,
|
|
"epoch": 1.3488595647994406,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004822559094797849,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.14537073522806168,
|
|
"num_tokens": 31267294.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 6.152498722076416,
|
|
"epoch": 1.3492965131521455,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00048224377842013443,
|
|
"loss": 5.8217,
|
|
"mean_token_accuracy": 0.16052476167678834,
|
|
"num_tokens": 31276896.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 6.140977430343628,
|
|
"epoch": 1.3497334615048502,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004822316433854397,
|
|
"loss": 5.9065,
|
|
"mean_token_accuracy": 0.15101585239171983,
|
|
"num_tokens": 31287248.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 6.11960883140564,
|
|
"epoch": 1.3501704098575549,
|
|
"grad_norm": 5.78125,
|
|
"learning_rate": 0.00048221950437593353,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.15626996457576753,
|
|
"num_tokens": 31297422.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 6.153040027618408,
|
|
"epoch": 1.3506073582102596,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048220736139184864,
|
|
"loss": 5.9142,
|
|
"mean_token_accuracy": 0.15504897236824036,
|
|
"num_tokens": 31307182.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 6.206346225738526,
|
|
"epoch": 1.3510443065629643,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000482195214433418,
|
|
"loss": 5.9918,
|
|
"mean_token_accuracy": 0.1427098862826824,
|
|
"num_tokens": 31317234.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 6.22294397354126,
|
|
"epoch": 1.351481254915669,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004821830635008746,
|
|
"loss": 5.9764,
|
|
"mean_token_accuracy": 0.14484017714858055,
|
|
"num_tokens": 31328294.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 6.2555149555206295,
|
|
"epoch": 1.3519182032683736,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004821709085944515,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.15396426022052764,
|
|
"num_tokens": 31337250.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 6.183167791366577,
|
|
"epoch": 1.3523551516210783,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004821587497143817,
|
|
"loss": 5.9305,
|
|
"mean_token_accuracy": 0.15111508667469026,
|
|
"num_tokens": 31346900.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 6.159300804138184,
|
|
"epoch": 1.352792099973783,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004821465868608986,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.1471735455095768,
|
|
"num_tokens": 31357233.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 6.18670687675476,
|
|
"epoch": 1.353229048326488,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004821344200342355,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.1530952975153923,
|
|
"num_tokens": 31367043.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 6.1640722274780275,
|
|
"epoch": 1.3536659966791924,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004821222492346256,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.14524135291576384,
|
|
"num_tokens": 31376770.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 6.202436351776123,
|
|
"epoch": 1.3541029450318973,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048211007446230243,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.15482534021139144,
|
|
"num_tokens": 31386056.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 6.1484537601470945,
|
|
"epoch": 1.354539893384602,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048209789571749954,
|
|
"loss": 5.9419,
|
|
"mean_token_accuracy": 0.14602854549884797,
|
|
"num_tokens": 31395129.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 6.220837545394898,
|
|
"epoch": 1.3549768417373067,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048208571300045045,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.14848102629184723,
|
|
"num_tokens": 31404720.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 6.230710124969482,
|
|
"epoch": 1.3554137900900114,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00048207352631138897,
|
|
"loss": 5.8808,
|
|
"mean_token_accuracy": 0.15658908486366271,
|
|
"num_tokens": 31415588.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 6.180061388015747,
|
|
"epoch": 1.355850738442716,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00048206133565054863,
|
|
"loss": 5.9698,
|
|
"mean_token_accuracy": 0.14740943163633347,
|
|
"num_tokens": 31425904.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 6.158311080932617,
|
|
"epoch": 1.3562876867954208,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004820491410181634,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.14886042326688767,
|
|
"num_tokens": 31435282.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 6.227653503417969,
|
|
"epoch": 1.3567246351481255,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048203694241446724,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.14620602056384085,
|
|
"num_tokens": 31445681.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 6.146025085449219,
|
|
"epoch": 1.3571615835008302,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048202473983969396,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.15896469801664354,
|
|
"num_tokens": 31456934.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 6.076095151901245,
|
|
"epoch": 1.3575985318535349,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048201253329407766,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.1567166641354561,
|
|
"num_tokens": 31466692.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 6.108785200119018,
|
|
"epoch": 1.3580354802062395,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004820003227778526,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.14972759932279586,
|
|
"num_tokens": 31477166.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 6.241550159454346,
|
|
"epoch": 1.3584724285589442,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004819881082912528,
|
|
"loss": 5.9007,
|
|
"mean_token_accuracy": 0.14770390912890435,
|
|
"num_tokens": 31486998.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 6.217063617706299,
|
|
"epoch": 1.3589093769116491,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048197588983451265,
|
|
"loss": 5.9147,
|
|
"mean_token_accuracy": 0.1456634059548378,
|
|
"num_tokens": 31496674.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 6.151744365692139,
|
|
"epoch": 1.3593463252643536,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 0.00048196366740786646,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.1474331870675087,
|
|
"num_tokens": 31507412.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 6.1885085105896,
|
|
"epoch": 1.3597832736170585,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048195144101154867,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.14947630912065507,
|
|
"num_tokens": 31517048.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 6.142838001251221,
|
|
"epoch": 1.3602202219697632,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00048193921064579385,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.14596446081995965,
|
|
"num_tokens": 31526353.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 6.214523601531982,
|
|
"epoch": 1.360657170322468,
|
|
"grad_norm": 3.890625,
|
|
"learning_rate": 0.0004819269763108365,
|
|
"loss": 5.9382,
|
|
"mean_token_accuracy": 0.14883836954832078,
|
|
"num_tokens": 31537194.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 6.268964099884033,
|
|
"epoch": 1.3610941186751726,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048191473800691145,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.150735567510128,
|
|
"num_tokens": 31547896.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 6.131948471069336,
|
|
"epoch": 1.3615310670278773,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004819024957342531,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.14850337356328963,
|
|
"num_tokens": 31558750.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 6.130724382400513,
|
|
"epoch": 1.361968015380582,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048189024949309655,
|
|
"loss": 5.8586,
|
|
"mean_token_accuracy": 0.15690528899431228,
|
|
"num_tokens": 31568721.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 6.1273688793182375,
|
|
"epoch": 1.3624049637332867,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004818779992836766,
|
|
"loss": 5.8465,
|
|
"mean_token_accuracy": 0.1506320394575596,
|
|
"num_tokens": 31579907.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 6.243776464462281,
|
|
"epoch": 1.3628419120859914,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048186574510622823,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.15120431780815125,
|
|
"num_tokens": 31590137.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 6.202559566497802,
|
|
"epoch": 1.363278860438696,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048185348696098653,
|
|
"loss": 5.9645,
|
|
"mean_token_accuracy": 0.14439767971634865,
|
|
"num_tokens": 31599969.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 6.144268560409546,
|
|
"epoch": 1.363715808791401,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004818412248481865,
|
|
"loss": 5.9,
|
|
"mean_token_accuracy": 0.1490763917565346,
|
|
"num_tokens": 31609951.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 6.142098474502563,
|
|
"epoch": 1.3641527571441054,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.00048182895876806343,
|
|
"loss": 5.8319,
|
|
"mean_token_accuracy": 0.1605251982808113,
|
|
"num_tokens": 31619214.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 6.203738832473755,
|
|
"epoch": 1.3645897054968104,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004818166887208524,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.15474345684051513,
|
|
"num_tokens": 31629562.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 6.123479223251342,
|
|
"epoch": 1.365026653849515,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004818044147067891,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.1578165262937546,
|
|
"num_tokens": 31639801.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 6.197249507904052,
|
|
"epoch": 1.3654636022022197,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048179213672610866,
|
|
"loss": 5.9213,
|
|
"mean_token_accuracy": 0.14585366025567054,
|
|
"num_tokens": 31650593.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 6.189125061035156,
|
|
"epoch": 1.3659005505549244,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048177985477904675,
|
|
"loss": 5.8872,
|
|
"mean_token_accuracy": 0.1538390077650547,
|
|
"num_tokens": 31660942.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 6.2054060935974125,
|
|
"epoch": 1.3663374989076291,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048176756886583884,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.1442718930542469,
|
|
"num_tokens": 31671105.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 6.199615240097046,
|
|
"epoch": 1.3667744472603338,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004817552789867206,
|
|
"loss": 5.8721,
|
|
"mean_token_accuracy": 0.1513895183801651,
|
|
"num_tokens": 31680696.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 6.077017545700073,
|
|
"epoch": 1.3672113956130385,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048174298514192784,
|
|
"loss": 5.8006,
|
|
"mean_token_accuracy": 0.15794742107391357,
|
|
"num_tokens": 31689755.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 6.0574463367462155,
|
|
"epoch": 1.3676483439657432,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.00048173068733169615,
|
|
"loss": 5.8491,
|
|
"mean_token_accuracy": 0.15717778652906417,
|
|
"num_tokens": 31699614.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 6.192130374908447,
|
|
"epoch": 1.3680852923184479,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004817183855562617,
|
|
"loss": 5.8485,
|
|
"mean_token_accuracy": 0.15516546070575715,
|
|
"num_tokens": 31709106.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 6.214150381088257,
|
|
"epoch": 1.3685222406711528,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048170607981586023,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.1518714964389801,
|
|
"num_tokens": 31719542.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 6.217283868789673,
|
|
"epoch": 1.3689591890238573,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048169377011072784,
|
|
"loss": 5.887,
|
|
"mean_token_accuracy": 0.15334418565034866,
|
|
"num_tokens": 31730477.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 6.132981204986573,
|
|
"epoch": 1.3693961373765622,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004816814564411006,
|
|
"loss": 5.8786,
|
|
"mean_token_accuracy": 0.15643389523029327,
|
|
"num_tokens": 31740269.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 6.173278713226319,
|
|
"epoch": 1.3698330857292669,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004816691388072148,
|
|
"loss": 5.8596,
|
|
"mean_token_accuracy": 0.1569000393152237,
|
|
"num_tokens": 31750153.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 6.2268585681915285,
|
|
"epoch": 1.3702700340819716,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048165681720930653,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.14221562445163727,
|
|
"num_tokens": 31760171.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 6.195370864868164,
|
|
"epoch": 1.3707069824346763,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004816444916476123,
|
|
"loss": 5.9355,
|
|
"mean_token_accuracy": 0.14723035991191863,
|
|
"num_tokens": 31771601.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 6.2029111862182615,
|
|
"epoch": 1.371143930787381,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048163216212236844,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.15174343883991243,
|
|
"num_tokens": 31781423.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 6.125151777267456,
|
|
"epoch": 1.3715808791400856,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004816198286338115,
|
|
"loss": 5.7959,
|
|
"mean_token_accuracy": 0.15884669944643975,
|
|
"num_tokens": 31791025.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 6.069617414474488,
|
|
"epoch": 1.3720178274927903,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00048160749118217783,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.15135340988636017,
|
|
"num_tokens": 31801125.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 6.214752244949341,
|
|
"epoch": 1.372454775845495,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004815951497677043,
|
|
"loss": 5.889,
|
|
"mean_token_accuracy": 0.14464661851525307,
|
|
"num_tokens": 31811100.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 6.267079305648804,
|
|
"epoch": 1.3728917241981997,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004815828043906275,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.14064408764243125,
|
|
"num_tokens": 31821667.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 6.178414678573608,
|
|
"epoch": 1.3733286725509044,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004815704550511843,
|
|
"loss": 5.8316,
|
|
"mean_token_accuracy": 0.15786113291978837,
|
|
"num_tokens": 31831859.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 6.1278722286224365,
|
|
"epoch": 1.373765620903609,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004815581017496115,
|
|
"loss": 5.8342,
|
|
"mean_token_accuracy": 0.15364986658096313,
|
|
"num_tokens": 31842952.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 6.0776642799377445,
|
|
"epoch": 1.374202569256314,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048154574448614607,
|
|
"loss": 5.9285,
|
|
"mean_token_accuracy": 0.15256015807390214,
|
|
"num_tokens": 31852869.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 6.202900838851929,
|
|
"epoch": 1.3746395176090185,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004815333832610251,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.157974199205637,
|
|
"num_tokens": 31862590.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 6.1410387516021725,
|
|
"epoch": 1.3750764659617234,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048152101807448554,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.14932089447975158,
|
|
"num_tokens": 31873071.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 6.168727540969849,
|
|
"epoch": 1.375513414314428,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004815086489267647,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.15680812895298005,
|
|
"num_tokens": 31883325.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 6.200935983657837,
|
|
"epoch": 1.3759503626671328,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048149627581809974,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.15281272530555726,
|
|
"num_tokens": 31893071.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 6.141010189056397,
|
|
"epoch": 1.3763873110198375,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.000481483898748728,
|
|
"loss": 5.8618,
|
|
"mean_token_accuracy": 0.15925009846687316,
|
|
"num_tokens": 31902948.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 6.140580844879151,
|
|
"epoch": 1.3768242593725422,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004814715177188869,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.15180886685848236,
|
|
"num_tokens": 31913425.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 6.158436346054077,
|
|
"epoch": 1.3772612077252468,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004814591327288139,
|
|
"loss": 5.8722,
|
|
"mean_token_accuracy": 0.1527306467294693,
|
|
"num_tokens": 31923608.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 6.113433170318603,
|
|
"epoch": 1.3776981560779515,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00048144674377874656,
|
|
"loss": 5.8151,
|
|
"mean_token_accuracy": 0.15847359746694564,
|
|
"num_tokens": 31932863.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 6.157820081710815,
|
|
"epoch": 1.3781351044306562,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048143435086892244,
|
|
"loss": 5.8862,
|
|
"mean_token_accuracy": 0.14980321377515793,
|
|
"num_tokens": 31942425.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 6.172450399398803,
|
|
"epoch": 1.378572052783361,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004814219539995793,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.15043785572052001,
|
|
"num_tokens": 31952152.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 6.202452230453491,
|
|
"epoch": 1.3790090011360658,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00048140955317095503,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.14953644722700118,
|
|
"num_tokens": 31962224.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 6.17941370010376,
|
|
"epoch": 1.3794459494887703,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004813971483832873,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.16343390345573425,
|
|
"num_tokens": 31971517.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 6.140935802459717,
|
|
"epoch": 1.3798828978414752,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004813847396368141,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.1522977203130722,
|
|
"num_tokens": 31982461.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 6.127985000610352,
|
|
"epoch": 1.38031984619418,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004813723269317734,
|
|
"loss": 5.8314,
|
|
"mean_token_accuracy": 0.15892155915498735,
|
|
"num_tokens": 31992202.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 6.197576189041138,
|
|
"epoch": 1.3807567945468846,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004813599102684034,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.15693169012665747,
|
|
"num_tokens": 32002283.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 6.225122261047363,
|
|
"epoch": 1.3811937428995893,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.00048134748964694227,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.15252324640750886,
|
|
"num_tokens": 32013135.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 6.193136405944824,
|
|
"epoch": 1.381630691252294,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004813350650676281,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.15140448957681657,
|
|
"num_tokens": 32022631.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 6.133950710296631,
|
|
"epoch": 1.3820676396049987,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004813226365306992,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.14851686209440232,
|
|
"num_tokens": 32032216.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 6.141397094726562,
|
|
"epoch": 1.3825045879577034,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048131020403639405,
|
|
"loss": 5.8846,
|
|
"mean_token_accuracy": 0.16149332374334335,
|
|
"num_tokens": 32042382.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 6.180974531173706,
|
|
"epoch": 1.382941536310408,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048129776758495116,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.15454696267843246,
|
|
"num_tokens": 32052592.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 6.103881072998047,
|
|
"epoch": 1.3833784846631128,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004812853271766089,
|
|
"loss": 5.7835,
|
|
"mean_token_accuracy": 0.15395764410495758,
|
|
"num_tokens": 32062260.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 6.156110858917236,
|
|
"epoch": 1.3838154330158177,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.000481272882811606,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.15162370949983597,
|
|
"num_tokens": 32072079.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 6.158740663528443,
|
|
"epoch": 1.3842523813685221,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.00048126043449018115,
|
|
"loss": 5.8899,
|
|
"mean_token_accuracy": 0.15353164523839952,
|
|
"num_tokens": 32082151.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 6.227280569076538,
|
|
"epoch": 1.384689329721227,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000481247982212573,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.1456128641963005,
|
|
"num_tokens": 32091893.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 6.185877513885498,
|
|
"epoch": 1.3851262780739317,
|
|
"grad_norm": 5.15625,
|
|
"learning_rate": 0.00048123552597902053,
|
|
"loss": 5.832,
|
|
"mean_token_accuracy": 0.15836296677589418,
|
|
"num_tokens": 32101550.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 6.039649963378906,
|
|
"epoch": 1.3855632264266364,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048122306578976266,
|
|
"loss": 5.7481,
|
|
"mean_token_accuracy": 0.16527795940637588,
|
|
"num_tokens": 32112278.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 6.148902320861817,
|
|
"epoch": 1.3860001747793411,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048121060164503835,
|
|
"loss": 5.9183,
|
|
"mean_token_accuracy": 0.15111266374588012,
|
|
"num_tokens": 32122284.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 6.235367679595948,
|
|
"epoch": 1.3864371231320458,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004811981335450865,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.1495277166366577,
|
|
"num_tokens": 32131552.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 6.262882804870605,
|
|
"epoch": 1.3868740714847505,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048118566149014653,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.14120246171951295,
|
|
"num_tokens": 32141758.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 6.135331535339356,
|
|
"epoch": 1.3873110198374552,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004811731854804575,
|
|
"loss": 5.8394,
|
|
"mean_token_accuracy": 0.1489864706993103,
|
|
"num_tokens": 32150679.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 6.072045612335205,
|
|
"epoch": 1.3877479681901599,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004811607055162587,
|
|
"loss": 5.8252,
|
|
"mean_token_accuracy": 0.1568121463060379,
|
|
"num_tokens": 32160967.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 6.209223699569702,
|
|
"epoch": 1.3881849165428646,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004811482215977895,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.1478721097111702,
|
|
"num_tokens": 32170516.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 6.191197443008423,
|
|
"epoch": 1.3886218648955693,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048113573372528956,
|
|
"loss": 5.9,
|
|
"mean_token_accuracy": 0.14994119107723236,
|
|
"num_tokens": 32180741.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 6.231997156143189,
|
|
"epoch": 1.389058813248274,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004811232418989981,
|
|
"loss": 5.9283,
|
|
"mean_token_accuracy": 0.15348664447665214,
|
|
"num_tokens": 32190646.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 6.1127461910247805,
|
|
"epoch": 1.3894957616009789,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048111074611915483,
|
|
"loss": 5.861,
|
|
"mean_token_accuracy": 0.15147869288921356,
|
|
"num_tokens": 32201361.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 6.161264371871948,
|
|
"epoch": 1.3899327099536833,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004810982463859996,
|
|
"loss": 5.9823,
|
|
"mean_token_accuracy": 0.13942893147468566,
|
|
"num_tokens": 32211759.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 6.228479719161987,
|
|
"epoch": 1.3903696583063883,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004810857426997719,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.14883668646216391,
|
|
"num_tokens": 32222582.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 6.170031929016114,
|
|
"epoch": 1.390806606659093,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048107323506071167,
|
|
"loss": 5.89,
|
|
"mean_token_accuracy": 0.15693831741809844,
|
|
"num_tokens": 32232936.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 6.172857189178467,
|
|
"epoch": 1.3912435550117976,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048106072346905875,
|
|
"loss": 5.9068,
|
|
"mean_token_accuracy": 0.15017607063055038,
|
|
"num_tokens": 32242392.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 6.227355003356934,
|
|
"epoch": 1.3916805033645023,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048104820792505335,
|
|
"loss": 5.9655,
|
|
"mean_token_accuracy": 0.14521736949682235,
|
|
"num_tokens": 32252385.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 6.209153461456299,
|
|
"epoch": 1.392117451717207,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048103568842893527,
|
|
"loss": 5.9163,
|
|
"mean_token_accuracy": 0.145188207924366,
|
|
"num_tokens": 32263537.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 6.183942461013794,
|
|
"epoch": 1.3925544000699117,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048102316498094467,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.1478283680975437,
|
|
"num_tokens": 32273450.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 6.1553215980529785,
|
|
"epoch": 1.3929913484226164,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048101063758132186,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.1517511449754238,
|
|
"num_tokens": 32283243.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 6.11683611869812,
|
|
"epoch": 1.393428296775321,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004809981062303071,
|
|
"loss": 5.8512,
|
|
"mean_token_accuracy": 0.1503870740532875,
|
|
"num_tokens": 32292458.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 6.18965163230896,
|
|
"epoch": 1.3938652451280258,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048098557092814066,
|
|
"loss": 5.8614,
|
|
"mean_token_accuracy": 0.14753165915608407,
|
|
"num_tokens": 32302574.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 6.1169227123260494,
|
|
"epoch": 1.3943021934807307,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000480973031675063,
|
|
"loss": 5.8437,
|
|
"mean_token_accuracy": 0.15693144202232362,
|
|
"num_tokens": 32312658.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 6.168728446960449,
|
|
"epoch": 1.3947391418334352,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004809604884713148,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.15188750624656677,
|
|
"num_tokens": 32322717.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 6.131944751739502,
|
|
"epoch": 1.39517609018614,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048094794131713645,
|
|
"loss": 5.861,
|
|
"mean_token_accuracy": 0.1567105695605278,
|
|
"num_tokens": 32333316.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 6.188786745071411,
|
|
"epoch": 1.3956130385388448,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004809353902127686,
|
|
"loss": 5.8929,
|
|
"mean_token_accuracy": 0.15127069801092147,
|
|
"num_tokens": 32343857.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 6.116759538650513,
|
|
"epoch": 1.3960499868915495,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048092283515845216,
|
|
"loss": 5.7933,
|
|
"mean_token_accuracy": 0.157977394759655,
|
|
"num_tokens": 32353883.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 6.045762014389038,
|
|
"epoch": 1.3964869352442542,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004809102761544278,
|
|
"loss": 5.7867,
|
|
"mean_token_accuracy": 0.15422953963279723,
|
|
"num_tokens": 32363355.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 6.151582336425781,
|
|
"epoch": 1.3969238835969588,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004808977132009364,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.15060843676328659,
|
|
"num_tokens": 32373066.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 6.129072904586792,
|
|
"epoch": 1.3973608319496635,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000480885146298219,
|
|
"loss": 5.8415,
|
|
"mean_token_accuracy": 0.15550466179847716,
|
|
"num_tokens": 32383720.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 6.18328824043274,
|
|
"epoch": 1.3977977803023682,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004808725754465167,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.14687421619892121,
|
|
"num_tokens": 32393823.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 6.090304279327393,
|
|
"epoch": 1.398234728655073,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048086000064607044,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.16058974340558052,
|
|
"num_tokens": 32404745.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 6.121276426315307,
|
|
"epoch": 1.3986716770077776,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048084742189712147,
|
|
"loss": 5.8583,
|
|
"mean_token_accuracy": 0.1604558691382408,
|
|
"num_tokens": 32415325.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 6.180326843261719,
|
|
"epoch": 1.3991086253604825,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004808348391999112,
|
|
"loss": 5.9299,
|
|
"mean_token_accuracy": 0.14896190762519837,
|
|
"num_tokens": 32425810.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 6.181202220916748,
|
|
"epoch": 1.399545573713187,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004808222525546808,
|
|
"loss": 5.898,
|
|
"mean_token_accuracy": 0.15360227674245835,
|
|
"num_tokens": 32436799.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 6.1136504173278805,
|
|
"epoch": 1.399982522065892,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048080966196167163,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.1552768036723137,
|
|
"num_tokens": 32446409.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 6.143660068511963,
|
|
"epoch": 1.4004194704185966,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004807970674211255,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.1488344267010689,
|
|
"num_tokens": 32456268.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 6.109568881988525,
|
|
"epoch": 1.4008564187713013,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048078446893328364,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.14640575498342515,
|
|
"num_tokens": 32467622.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 6.19821720123291,
|
|
"epoch": 1.401293367124006,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004807718664983879,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.15022818595170975,
|
|
"num_tokens": 32477753.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 6.182455921173096,
|
|
"epoch": 1.4017303154767107,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048075926011667997,
|
|
"loss": 5.8057,
|
|
"mean_token_accuracy": 0.15594885796308516,
|
|
"num_tokens": 32487758.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 6.08267765045166,
|
|
"epoch": 1.4021672638294154,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048074664978840147,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.15419219434261322,
|
|
"num_tokens": 32497725.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 6.134919738769531,
|
|
"epoch": 1.40260421218212,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004807340355137945,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.1592742070555687,
|
|
"num_tokens": 32507515.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 6.138142251968384,
|
|
"epoch": 1.4030411605348247,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.000480721417293101,
|
|
"loss": 5.8096,
|
|
"mean_token_accuracy": 0.15780906230211258,
|
|
"num_tokens": 32516943.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 6.06535496711731,
|
|
"epoch": 1.4034781088875294,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004807087951265628,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.16902215480804444,
|
|
"num_tokens": 32527223.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 6.12424521446228,
|
|
"epoch": 1.4039150572402341,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004806961690144222,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.15572343319654464,
|
|
"num_tokens": 32536668.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 6.160105180740357,
|
|
"epoch": 1.4043520055929388,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004806835389569213,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.15538810044527054,
|
|
"num_tokens": 32546566.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 6.0662766456604,
|
|
"epoch": 1.4047889539456437,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048067090495430235,
|
|
"loss": 5.7922,
|
|
"mean_token_accuracy": 0.1557777628302574,
|
|
"num_tokens": 32555927.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 6.173278856277466,
|
|
"epoch": 1.4052259022983482,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048065826700680763,
|
|
"loss": 5.8285,
|
|
"mean_token_accuracy": 0.1510176494717598,
|
|
"num_tokens": 32566569.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 6.1212835788726805,
|
|
"epoch": 1.4056628506510531,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048064562511467956,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.15893922448158265,
|
|
"num_tokens": 32577076.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 6.1175226211547855,
|
|
"epoch": 1.4060997990037578,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048063297927816067,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.1452830120921135,
|
|
"num_tokens": 32587926.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 6.199253511428833,
|
|
"epoch": 1.4065367473564625,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004806203294974935,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.15250675678253173,
|
|
"num_tokens": 32599012.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 6.211430263519287,
|
|
"epoch": 1.4069736957091672,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048060767577292067,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.15296147912740707,
|
|
"num_tokens": 32609094.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 6.109265851974487,
|
|
"epoch": 1.4074106440618719,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004805950181046849,
|
|
"loss": 5.9055,
|
|
"mean_token_accuracy": 0.1492737740278244,
|
|
"num_tokens": 32620356.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 6.159668636322022,
|
|
"epoch": 1.4078475924145766,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000480582356493029,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.15144226998090743,
|
|
"num_tokens": 32629841.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 6.156450986862183,
|
|
"epoch": 1.4082845407672813,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004805696909381957,
|
|
"loss": 5.9017,
|
|
"mean_token_accuracy": 0.15453390926122665,
|
|
"num_tokens": 32639006.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 6.1538920402526855,
|
|
"epoch": 1.408721489119986,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048055702144042794,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.15112707912921905,
|
|
"num_tokens": 32648419.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 6.151839399337769,
|
|
"epoch": 1.4091584374726907,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004805443479999689,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.1580185577273369,
|
|
"num_tokens": 32658050.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 6.197067975997925,
|
|
"epoch": 1.4095953858253956,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004805316706170615,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.14884357899427414,
|
|
"num_tokens": 32668176.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 6.071049928665161,
|
|
"epoch": 1.4100323341781,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.00048051898929194907,
|
|
"loss": 5.7842,
|
|
"mean_token_accuracy": 0.1572985127568245,
|
|
"num_tokens": 32678517.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 6.122809267044067,
|
|
"epoch": 1.410469282530805,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004805063040248747,
|
|
"loss": 5.8322,
|
|
"mean_token_accuracy": 0.15304223895072938,
|
|
"num_tokens": 32688459.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 6.1579183578491214,
|
|
"epoch": 1.4109062308835096,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004804936148160817,
|
|
"loss": 5.8627,
|
|
"mean_token_accuracy": 0.15743836015462875,
|
|
"num_tokens": 32698481.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 6.121659803390503,
|
|
"epoch": 1.4113431792362143,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004804809216658135,
|
|
"loss": 5.8826,
|
|
"mean_token_accuracy": 0.14823081195354462,
|
|
"num_tokens": 32709031.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 6.130120420455933,
|
|
"epoch": 1.411780127588919,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048046822457431347,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.15891651660203934,
|
|
"num_tokens": 32720293.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 6.1630120277404785,
|
|
"epoch": 1.4122170759416237,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048045552354182536,
|
|
"loss": 5.9028,
|
|
"mean_token_accuracy": 0.15743406265974044,
|
|
"num_tokens": 32730108.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 6.163303184509277,
|
|
"epoch": 1.4126540242943284,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048044281856859255,
|
|
"loss": 5.8795,
|
|
"mean_token_accuracy": 0.15551360696554184,
|
|
"num_tokens": 32740614.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 6.1726726531982425,
|
|
"epoch": 1.413090972647033,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004804301096548589,
|
|
"loss": 5.8176,
|
|
"mean_token_accuracy": 0.15367681086063384,
|
|
"num_tokens": 32751155.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 6.102839374542237,
|
|
"epoch": 1.4135279209997378,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004804173968008681,
|
|
"loss": 5.7854,
|
|
"mean_token_accuracy": 0.15775360763072968,
|
|
"num_tokens": 32761067.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 6.067156505584717,
|
|
"epoch": 1.4139648693524425,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048040468000686395,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.1634780600667,
|
|
"num_tokens": 32771357.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 6.154537391662598,
|
|
"epoch": 1.4144018177051472,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004803919592730904,
|
|
"loss": 5.9657,
|
|
"mean_token_accuracy": 0.15175942927598954,
|
|
"num_tokens": 32781116.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 6.17523889541626,
|
|
"epoch": 1.4148387660578519,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004803792345997915,
|
|
"loss": 5.9262,
|
|
"mean_token_accuracy": 0.14918609112501144,
|
|
"num_tokens": 32791660.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 6.178508949279785,
|
|
"epoch": 1.4152757144105568,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.00048036650598721125,
|
|
"loss": 5.8589,
|
|
"mean_token_accuracy": 0.15216931849718093,
|
|
"num_tokens": 32801413.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 6.168720483779907,
|
|
"epoch": 1.4157126627632615,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048035377343559377,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.15241920799016953,
|
|
"num_tokens": 32811293.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 6.173145055770874,
|
|
"epoch": 1.4161496111159662,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.00048034103694518336,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.15666632652282714,
|
|
"num_tokens": 32821609.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 6.213352060317993,
|
|
"epoch": 1.4165865594686708,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048032829651622425,
|
|
"loss": 5.863,
|
|
"mean_token_accuracy": 0.15040107369422911,
|
|
"num_tokens": 32831219.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 6.163787889480591,
|
|
"epoch": 1.4170235078213755,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048031555214896076,
|
|
"loss": 5.8897,
|
|
"mean_token_accuracy": 0.14951475113630294,
|
|
"num_tokens": 32841085.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 6.106598234176635,
|
|
"epoch": 1.4174604561740802,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004803028038436375,
|
|
"loss": 5.8497,
|
|
"mean_token_accuracy": 0.1578148603439331,
|
|
"num_tokens": 32851592.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 6.174910926818848,
|
|
"epoch": 1.417897404526785,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00048029005160049886,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.15424165725708008,
|
|
"num_tokens": 32862124.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 6.105254411697388,
|
|
"epoch": 1.4183343528794896,
|
|
"grad_norm": 5.375,
|
|
"learning_rate": 0.0004802772954197894,
|
|
"loss": 5.825,
|
|
"mean_token_accuracy": 0.16686519086360932,
|
|
"num_tokens": 32872760.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 6.1387444019317625,
|
|
"epoch": 1.4187713012321943,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048026453530175393,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.15198744982481002,
|
|
"num_tokens": 32883542.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 6.160576486587525,
|
|
"epoch": 1.419208249584899,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.00048025177124663704,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.15290183424949647,
|
|
"num_tokens": 32893922.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 6.176000118255615,
|
|
"epoch": 1.4196451979376037,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00048023900325468367,
|
|
"loss": 5.8765,
|
|
"mean_token_accuracy": 0.15981116741895676,
|
|
"num_tokens": 32903907.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 6.179763984680176,
|
|
"epoch": 1.4200821462903086,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.00048022623132613863,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.15064170509576796,
|
|
"num_tokens": 32914656.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 6.138255262374878,
|
|
"epoch": 1.420519094643013,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000480213455461247,
|
|
"loss": 5.902,
|
|
"mean_token_accuracy": 0.1474309653043747,
|
|
"num_tokens": 32925250.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 6.138006639480591,
|
|
"epoch": 1.420956042995718,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.00048020067566025373,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.15242878198623658,
|
|
"num_tokens": 32935435.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 6.19958004951477,
|
|
"epoch": 1.4213929913484227,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000480187891923404,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.15308659821748732,
|
|
"num_tokens": 32946166.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 6.146883201599121,
|
|
"epoch": 1.4218299397011274,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004801751042509429,
|
|
"loss": 5.8234,
|
|
"mean_token_accuracy": 0.15771649926900863,
|
|
"num_tokens": 32955751.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 6.084358215332031,
|
|
"epoch": 1.422266888053832,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004801623126431159,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.1521984726190567,
|
|
"num_tokens": 32966121.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 6.160526180267334,
|
|
"epoch": 1.4227038364065367,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004801495171001681,
|
|
"loss": 5.8701,
|
|
"mean_token_accuracy": 0.1625432178378105,
|
|
"num_tokens": 32976950.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 6.181528854370117,
|
|
"epoch": 1.4231407847592414,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004801367176223452,
|
|
"loss": 5.8395,
|
|
"mean_token_accuracy": 0.16046028435230256,
|
|
"num_tokens": 32987278.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 6.141334152221679,
|
|
"epoch": 1.4235777331119461,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004801239142098926,
|
|
"loss": 5.9374,
|
|
"mean_token_accuracy": 0.14678418934345244,
|
|
"num_tokens": 32997050.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 6.168014812469482,
|
|
"epoch": 1.4240146814646508,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004801111068630557,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.157503941655159,
|
|
"num_tokens": 33007799.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 6.19782829284668,
|
|
"epoch": 1.4244516298173555,
|
|
"grad_norm": 8.8125,
|
|
"learning_rate": 0.00048009829558208044,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.15878252387046815,
|
|
"num_tokens": 33017476.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 6.101291751861572,
|
|
"epoch": 1.4248885781700604,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048008548036721226,
|
|
"loss": 5.8389,
|
|
"mean_token_accuracy": 0.15810855329036713,
|
|
"num_tokens": 33027617.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 6.143493032455444,
|
|
"epoch": 1.425325526522765,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004800726612186972,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.15185931473970413,
|
|
"num_tokens": 33037257.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 6.13328537940979,
|
|
"epoch": 1.4257624748754698,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004800598381367811,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.1564851865172386,
|
|
"num_tokens": 33047406.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 6.109671020507813,
|
|
"epoch": 1.4261994232281745,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004800470111217096,
|
|
"loss": 5.8809,
|
|
"mean_token_accuracy": 0.161655480414629,
|
|
"num_tokens": 33057975.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 6.200307559967041,
|
|
"epoch": 1.4266363715808792,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048003418017372924,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.14856939017772675,
|
|
"num_tokens": 33068645.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 6.20980920791626,
|
|
"epoch": 1.4270733199335839,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004800213452930857,
|
|
"loss": 5.8856,
|
|
"mean_token_accuracy": 0.1545938655734062,
|
|
"num_tokens": 33079147.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 6.1469982147216795,
|
|
"epoch": 1.4275102682862886,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004800085064800255,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.149704609811306,
|
|
"num_tokens": 33089229.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 6.134866523742676,
|
|
"epoch": 1.4279472166389933,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004799956637347946,
|
|
"loss": 5.852,
|
|
"mean_token_accuracy": 0.15586744323372842,
|
|
"num_tokens": 33099688.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 6.1218828678131105,
|
|
"epoch": 1.428384164991698,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004799828170576395,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.15585654079914094,
|
|
"num_tokens": 33110019.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 6.020287752151489,
|
|
"epoch": 1.4288211133444026,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004799699664488065,
|
|
"loss": 5.7511,
|
|
"mean_token_accuracy": 0.16514252573251725,
|
|
"num_tokens": 33120141.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 6.134222984313965,
|
|
"epoch": 1.4292580616971073,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004799571119085422,
|
|
"loss": 5.8259,
|
|
"mean_token_accuracy": 0.1553936094045639,
|
|
"num_tokens": 33130047.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 6.186822462081909,
|
|
"epoch": 1.429695010049812,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004799442534370931,
|
|
"loss": 5.9241,
|
|
"mean_token_accuracy": 0.1481953263282776,
|
|
"num_tokens": 33141234.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 6.117707538604736,
|
|
"epoch": 1.4301319584025167,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004799313910347057,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.16003192961215973,
|
|
"num_tokens": 33150788.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 6.095549154281616,
|
|
"epoch": 1.4305689067552216,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.000479918524701627,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.15991369783878326,
|
|
"num_tokens": 33160928.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 6.177237462997437,
|
|
"epoch": 1.431005855107926,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047990565443810357,
|
|
"loss": 5.9644,
|
|
"mean_token_accuracy": 0.14254036098718642,
|
|
"num_tokens": 33171333.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 6.048695850372314,
|
|
"epoch": 1.431442803460631,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047989278024438233,
|
|
"loss": 5.7536,
|
|
"mean_token_accuracy": 0.16269160956144332,
|
|
"num_tokens": 33180396.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 6.073717784881592,
|
|
"epoch": 1.4318797518133357,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004798799021207102,
|
|
"loss": 5.8351,
|
|
"mean_token_accuracy": 0.15462781935930253,
|
|
"num_tokens": 33189571.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 6.07733678817749,
|
|
"epoch": 1.4323167001660404,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047986702006733417,
|
|
"loss": 5.7978,
|
|
"mean_token_accuracy": 0.15696240216493607,
|
|
"num_tokens": 33198979.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 6.107527589797973,
|
|
"epoch": 1.432753648518745,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047985413408450136,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.16013509184122085,
|
|
"num_tokens": 33208862.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 6.1095493793487545,
|
|
"epoch": 1.4331905968714498,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004798412441724589,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.14833230525255203,
|
|
"num_tokens": 33218804.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 6.23686408996582,
|
|
"epoch": 1.4336275452241545,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047982835033145413,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.14775953441858292,
|
|
"num_tokens": 33228783.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 6.243742513656616,
|
|
"epoch": 1.4340644935768592,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.00047981545256173415,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.1458210825920105,
|
|
"num_tokens": 33241029.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 6.181990623474121,
|
|
"epoch": 1.4345014419295639,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004798025508635465,
|
|
"loss": 5.9464,
|
|
"mean_token_accuracy": 0.14418817758560182,
|
|
"num_tokens": 33250383.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 6.099666118621826,
|
|
"epoch": 1.4349383902822685,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004797896452371386,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.1675995633006096,
|
|
"num_tokens": 33260424.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 6.167949771881103,
|
|
"epoch": 1.4353753386349735,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047977673568275805,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.14974709004163742,
|
|
"num_tokens": 33270200.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 6.1727800369262695,
|
|
"epoch": 1.435812286987678,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004797638222006524,
|
|
"loss": 5.9702,
|
|
"mean_token_accuracy": 0.1439051777124405,
|
|
"num_tokens": 33279850.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 6.143870735168457,
|
|
"epoch": 1.4362492353403828,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 0.0004797509047910693,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.15714142099022865,
|
|
"num_tokens": 33289053.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 6.18264331817627,
|
|
"epoch": 1.4366861836930875,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.00047973798345425655,
|
|
"loss": 5.853,
|
|
"mean_token_accuracy": 0.15542616695165634,
|
|
"num_tokens": 33298988.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 6.090325212478637,
|
|
"epoch": 1.4371231320457922,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00047972505819046207,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.15734313577413558,
|
|
"num_tokens": 33308683.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 6.0857462882995605,
|
|
"epoch": 1.437560080398497,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004797121289999336,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.14859300330281258,
|
|
"num_tokens": 33319230.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 6.212685823440552,
|
|
"epoch": 1.4379970287512016,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004796991958829193,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.14558419734239578,
|
|
"num_tokens": 33329277.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 6.1804320335388185,
|
|
"epoch": 1.4384339771039063,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004796862588396672,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.1521575629711151,
|
|
"num_tokens": 33338644.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 6.154590892791748,
|
|
"epoch": 1.438870925456611,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047967331787042536,
|
|
"loss": 5.7726,
|
|
"mean_token_accuracy": 0.1656111016869545,
|
|
"num_tokens": 33348996.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 6.159158754348755,
|
|
"epoch": 1.4393078738093157,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00047966037297544195,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.15389342457056046,
|
|
"num_tokens": 33358581.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 6.130748081207275,
|
|
"epoch": 1.4397448221620204,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.00047964742415496553,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.15477489084005355,
|
|
"num_tokens": 33368925.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 6.131583547592163,
|
|
"epoch": 1.4401817705147253,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004796344714092441,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.15620177909731864,
|
|
"num_tokens": 33378918.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 6.107097434997558,
|
|
"epoch": 1.4406187188674298,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004796215147385264,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.15190946012735368,
|
|
"num_tokens": 33389039.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 6.183122301101685,
|
|
"epoch": 1.4410556672201347,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004796085541430608,
|
|
"loss": 5.8142,
|
|
"mean_token_accuracy": 0.16158209294080733,
|
|
"num_tokens": 33398893.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 6.185396146774292,
|
|
"epoch": 1.4414926155728394,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004795955896230959,
|
|
"loss": 5.8967,
|
|
"mean_token_accuracy": 0.15102121606469154,
|
|
"num_tokens": 33408188.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 6.116655921936035,
|
|
"epoch": 1.441929563925544,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047958262117888035,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.15978309661149978,
|
|
"num_tokens": 33418926.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 6.137224912643433,
|
|
"epoch": 1.4423665122782487,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.00047956964881066297,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.15085428953170776,
|
|
"num_tokens": 33429790.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 6.1617601871490475,
|
|
"epoch": 1.4428034606309534,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004795566725186925,
|
|
"loss": 5.8679,
|
|
"mean_token_accuracy": 0.15546119213104248,
|
|
"num_tokens": 33440470.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 6.132394504547119,
|
|
"epoch": 1.4432404089836581,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004795436923032179,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.15429432392120362,
|
|
"num_tokens": 33449875.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 6.145984840393067,
|
|
"epoch": 1.4436773573363628,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004795307081644881,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.1543783277273178,
|
|
"num_tokens": 33458841.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 6.109430551528931,
|
|
"epoch": 1.4441143056890675,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004795177201027521,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.15995844304561616,
|
|
"num_tokens": 33468656.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 6.125645494461059,
|
|
"epoch": 1.4445512540417722,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047950472811825916,
|
|
"loss": 5.8677,
|
|
"mean_token_accuracy": 0.1534265995025635,
|
|
"num_tokens": 33478977.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 6.140962409973144,
|
|
"epoch": 1.444988202394477,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004794917322112583,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.15178718864917756,
|
|
"num_tokens": 33488418.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 6.101782512664795,
|
|
"epoch": 1.4454251507471816,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004794787323819989,
|
|
"loss": 5.8268,
|
|
"mean_token_accuracy": 0.15940861105918885,
|
|
"num_tokens": 33499125.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 6.119931888580322,
|
|
"epoch": 1.4458620990998865,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00047946572863073023,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.1551864489912987,
|
|
"num_tokens": 33508826.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 6.058589887619019,
|
|
"epoch": 1.446299047452591,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00047945272095770174,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.1704589009284973,
|
|
"num_tokens": 33518398.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 6.140607261657715,
|
|
"epoch": 1.4467359958052959,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.000479439709363163,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.15202014595270158,
|
|
"num_tokens": 33528289.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 6.199735116958618,
|
|
"epoch": 1.4471729441580006,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004794266938473635,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.14671660512685775,
|
|
"num_tokens": 33539228.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 6.148595476150513,
|
|
"epoch": 1.4476098925107053,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00047941367441055283,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.15249387919902802,
|
|
"num_tokens": 33551015.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 6.174115991592407,
|
|
"epoch": 1.44804684086341,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047940065105298073,
|
|
"loss": 5.8368,
|
|
"mean_token_accuracy": 0.15895399302244187,
|
|
"num_tokens": 33560374.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 6.054957389831543,
|
|
"epoch": 1.4484837892161146,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004793876237748972,
|
|
"loss": 5.7117,
|
|
"mean_token_accuracy": 0.16946170032024382,
|
|
"num_tokens": 33569916.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 6.032973527908325,
|
|
"epoch": 1.4489207375688193,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004793745925765518,
|
|
"loss": 5.7836,
|
|
"mean_token_accuracy": 0.16140772253274918,
|
|
"num_tokens": 33579930.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 6.098497581481934,
|
|
"epoch": 1.449357685921524,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004793615574581947,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.152655665576458,
|
|
"num_tokens": 33588612.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 6.191740942001343,
|
|
"epoch": 1.4497946342742287,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047934851842007585,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.14861786514520645,
|
|
"num_tokens": 33599253.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 6.181076622009277,
|
|
"epoch": 1.4502315826269334,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004793354754624453,
|
|
"loss": 5.8152,
|
|
"mean_token_accuracy": 0.1626364678144455,
|
|
"num_tokens": 33609484.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 6.172141408920288,
|
|
"epoch": 1.4506685309796383,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004793224285855533,
|
|
"loss": 5.8219,
|
|
"mean_token_accuracy": 0.1544149249792099,
|
|
"num_tokens": 33619660.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 6.133356523513794,
|
|
"epoch": 1.4511054793323428,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047930937778965,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.15033407211303712,
|
|
"num_tokens": 33629505.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 6.140414619445801,
|
|
"epoch": 1.4515424276850477,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004792963230749858,
|
|
"loss": 5.9248,
|
|
"mean_token_accuracy": 0.15426726564764975,
|
|
"num_tokens": 33639680.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 6.164324617385864,
|
|
"epoch": 1.4519793760377524,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047928326444181117,
|
|
"loss": 5.9262,
|
|
"mean_token_accuracy": 0.1457628309726715,
|
|
"num_tokens": 33649200.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 6.167906141281128,
|
|
"epoch": 1.452416324390457,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.00047927020189037634,
|
|
"loss": 5.8441,
|
|
"mean_token_accuracy": 0.1539966955780983,
|
|
"num_tokens": 33658386.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 6.125351095199585,
|
|
"epoch": 1.4528532727431618,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004792571354209321,
|
|
"loss": 5.8061,
|
|
"mean_token_accuracy": 0.156576569378376,
|
|
"num_tokens": 33669139.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 6.141805696487427,
|
|
"epoch": 1.4532902210958665,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004792440650337289,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.15396281853318214,
|
|
"num_tokens": 33679629.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 6.184770774841309,
|
|
"epoch": 1.4537271694485712,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004792309907290175,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.14761248975992203,
|
|
"num_tokens": 33689633.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 6.150835847854614,
|
|
"epoch": 1.4541641178012759,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00047921791250704875,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.15278035700321196,
|
|
"num_tokens": 33699719.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 6.223496007919311,
|
|
"epoch": 1.4546010661539805,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047920483036807346,
|
|
"loss": 5.8938,
|
|
"mean_token_accuracy": 0.1495446264743805,
|
|
"num_tokens": 33709389.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 6.098867893218994,
|
|
"epoch": 1.4550380145066852,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00047919174431234246,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.14994095414876937,
|
|
"num_tokens": 33719063.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 6.185135364532471,
|
|
"epoch": 1.4554749628593902,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004791786543401068,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.144273891299963,
|
|
"num_tokens": 33729798.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 6.22833399772644,
|
|
"epoch": 1.4559119112120946,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004791655604516176,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.1472241647541523,
|
|
"num_tokens": 33740012.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 6.107581281661988,
|
|
"epoch": 1.4563488595647995,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.00047915246264712595,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.158633478730917,
|
|
"num_tokens": 33749478.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 6.059699249267578,
|
|
"epoch": 1.4567858079175042,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.0004791393609268831,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.1739884614944458,
|
|
"num_tokens": 33758935.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 6.125878190994262,
|
|
"epoch": 1.457222756270209,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004791262552911404,
|
|
"loss": 5.8118,
|
|
"mean_token_accuracy": 0.15728891044855117,
|
|
"num_tokens": 33769035.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 6.098521614074707,
|
|
"epoch": 1.4576597046229136,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00047911314574014904,
|
|
"loss": 5.834,
|
|
"mean_token_accuracy": 0.15414561033248902,
|
|
"num_tokens": 33779288.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 6.161070251464844,
|
|
"epoch": 1.4580966529756183,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004791000322741606,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.1579616993665695,
|
|
"num_tokens": 33789138.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 6.193655776977539,
|
|
"epoch": 1.458533601328323,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004790869148934267,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.14765916317701339,
|
|
"num_tokens": 33798649.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 6.007314872741699,
|
|
"epoch": 1.4589705496810277,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047907379359819877,
|
|
"loss": 5.7806,
|
|
"mean_token_accuracy": 0.16793847233057022,
|
|
"num_tokens": 33808742.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 6.1155003070831295,
|
|
"epoch": 1.4594074980337324,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004790606683887286,
|
|
"loss": 5.825,
|
|
"mean_token_accuracy": 0.15763843283057213,
|
|
"num_tokens": 33819507.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 6.193852949142456,
|
|
"epoch": 1.459844446386437,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047904753926526777,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.14575171768665313,
|
|
"num_tokens": 33829722.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 6.109727239608764,
|
|
"epoch": 1.4602813947391418,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004790344062280683,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.15260518491268157,
|
|
"num_tokens": 33839350.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 6.134222173690796,
|
|
"epoch": 1.4607183430918464,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047902126927738196,
|
|
"loss": 5.8518,
|
|
"mean_token_accuracy": 0.15978336334228516,
|
|
"num_tokens": 33849233.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 6.14475736618042,
|
|
"epoch": 1.4611552914445514,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047900812841346086,
|
|
"loss": 5.9247,
|
|
"mean_token_accuracy": 0.14815541505813598,
|
|
"num_tokens": 33859996.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 6.133819532394409,
|
|
"epoch": 1.4615922397972558,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004789949836365569,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.15771810114383697,
|
|
"num_tokens": 33870780.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 6.147455263137817,
|
|
"epoch": 1.4620291881499607,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004789818349469222,
|
|
"loss": 5.8763,
|
|
"mean_token_accuracy": 0.15781297236680986,
|
|
"num_tokens": 33880182.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 6.196677732467651,
|
|
"epoch": 1.4624661365026654,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004789686823448091,
|
|
"loss": 5.893,
|
|
"mean_token_accuracy": 0.15342501997947694,
|
|
"num_tokens": 33889464.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 6.157237815856933,
|
|
"epoch": 1.4629030848553701,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004789555258304698,
|
|
"loss": 5.8395,
|
|
"mean_token_accuracy": 0.15037917494773864,
|
|
"num_tokens": 33899530.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 6.101448488235474,
|
|
"epoch": 1.4633400332080748,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004789423654041566,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.15652785450220108,
|
|
"num_tokens": 33910094.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 6.1704583168029785,
|
|
"epoch": 1.4637769815607795,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047892920106612204,
|
|
"loss": 5.8295,
|
|
"mean_token_accuracy": 0.15678684264421464,
|
|
"num_tokens": 33921181.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 6.175072479248047,
|
|
"epoch": 1.4642139299134842,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004789160328166184,
|
|
"loss": 5.9464,
|
|
"mean_token_accuracy": 0.15273372381925582,
|
|
"num_tokens": 33931567.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 6.192115306854248,
|
|
"epoch": 1.464650878266189,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047890286065589856,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.15326565504074097,
|
|
"num_tokens": 33941513.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 6.104971075057984,
|
|
"epoch": 1.4650878266188936,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047888968458421487,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.1533613994717598,
|
|
"num_tokens": 33953400.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 6.130507564544677,
|
|
"epoch": 1.4655247749715983,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004788765046018204,
|
|
"loss": 5.8997,
|
|
"mean_token_accuracy": 0.14915316104888915,
|
|
"num_tokens": 33964394.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 6.193925952911377,
|
|
"epoch": 1.4659617233243032,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00047886332070896747,
|
|
"loss": 6.0017,
|
|
"mean_token_accuracy": 0.141588294506073,
|
|
"num_tokens": 33975266.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 6.223922300338745,
|
|
"epoch": 1.4663986716770077,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004788501329059094,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.14766502901911735,
|
|
"num_tokens": 33986159.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 6.226293897628784,
|
|
"epoch": 1.4668356200297126,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00047883694119289896,
|
|
"loss": 5.8964,
|
|
"mean_token_accuracy": 0.15321390926837922,
|
|
"num_tokens": 33997792.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 6.183793449401856,
|
|
"epoch": 1.4672725683824173,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047882374557018916,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.155574768781662,
|
|
"num_tokens": 34007945.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 6.199473142623901,
|
|
"epoch": 1.467709516735122,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.00047881054603803307,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.15616601407527925,
|
|
"num_tokens": 34018399.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 6.166972923278808,
|
|
"epoch": 1.4681464650878266,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004787973425966839,
|
|
"loss": 5.9662,
|
|
"mean_token_accuracy": 0.15201805159449577,
|
|
"num_tokens": 34028267.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 6.185429906845092,
|
|
"epoch": 1.4685834134405313,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000478784135246395,
|
|
"loss": 5.9943,
|
|
"mean_token_accuracy": 0.141352641582489,
|
|
"num_tokens": 34037904.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 6.184894752502442,
|
|
"epoch": 1.469020361793236,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004787709239874196,
|
|
"loss": 5.8308,
|
|
"mean_token_accuracy": 0.16382694393396377,
|
|
"num_tokens": 34049203.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 6.192157649993897,
|
|
"epoch": 1.4694573101459407,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000478757708820011,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.1531964898109436,
|
|
"num_tokens": 34059670.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 6.1121491432189945,
|
|
"epoch": 1.4698942584986454,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004787444897444229,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.15862599313259124,
|
|
"num_tokens": 34069730.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 6.19559326171875,
|
|
"epoch": 1.47033120685135,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004787312667609086,
|
|
"loss": 5.865,
|
|
"mean_token_accuracy": 0.153972090780735,
|
|
"num_tokens": 34079315.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 6.145363664627075,
|
|
"epoch": 1.470768155204055,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000478718039869722,
|
|
"loss": 5.8624,
|
|
"mean_token_accuracy": 0.15099019557237625,
|
|
"num_tokens": 34089431.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 6.1299206733703615,
|
|
"epoch": 1.4712051035567595,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047870480907111657,
|
|
"loss": 5.8507,
|
|
"mean_token_accuracy": 0.1506814807653427,
|
|
"num_tokens": 34100120.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 6.155368232727051,
|
|
"epoch": 1.4716420519094644,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004786915743653461,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.15664769858121871,
|
|
"num_tokens": 34110271.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 6.202772951126098,
|
|
"epoch": 1.472079000262169,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00047867833575266456,
|
|
"loss": 5.934,
|
|
"mean_token_accuracy": 0.14555186480283738,
|
|
"num_tokens": 34120240.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 6.192800045013428,
|
|
"epoch": 1.4725159486148738,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.0004786650932333259,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.15328696072101594,
|
|
"num_tokens": 34130813.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 6.159699964523315,
|
|
"epoch": 1.4729528969675785,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004786518468075839,
|
|
"loss": 5.8971,
|
|
"mean_token_accuracy": 0.15006352439522744,
|
|
"num_tokens": 34141169.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 6.1492616653442385,
|
|
"epoch": 1.4733898453202832,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004786385964756928,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.15355351567268372,
|
|
"num_tokens": 34151869.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 6.19665675163269,
|
|
"epoch": 1.4738267936729879,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004786253422379068,
|
|
"loss": 5.9562,
|
|
"mean_token_accuracy": 0.14665970504283904,
|
|
"num_tokens": 34162608.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 6.158228588104248,
|
|
"epoch": 1.4742637420256925,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047861208409448,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.15374520421028137,
|
|
"num_tokens": 34172648.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 6.156950426101685,
|
|
"epoch": 1.4747006903783972,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004785988220456666,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.15451784282922745,
|
|
"num_tokens": 34183603.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 6.212537717819214,
|
|
"epoch": 1.475137638731102,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004785855560917213,
|
|
"loss": 5.901,
|
|
"mean_token_accuracy": 0.14746190309524537,
|
|
"num_tokens": 34193830.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 6.075336360931397,
|
|
"epoch": 1.4755745870838066,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.00047857228623289825,
|
|
"loss": 5.7356,
|
|
"mean_token_accuracy": 0.17408724129199982,
|
|
"num_tokens": 34203074.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 6.114908838272095,
|
|
"epoch": 1.4760115354365113,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047855901246945205,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.14402876049280167,
|
|
"num_tokens": 34212958.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 6.12075777053833,
|
|
"epoch": 1.4764484837892162,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004785457348016374,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.14680899307131767,
|
|
"num_tokens": 34223077.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 6.17345552444458,
|
|
"epoch": 1.4768854321419207,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00047853245322970885,
|
|
"loss": 5.8748,
|
|
"mean_token_accuracy": 0.15817682594060897,
|
|
"num_tokens": 34233386.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 6.197332143783569,
|
|
"epoch": 1.4773223804946256,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004785191677539212,
|
|
"loss": 5.8864,
|
|
"mean_token_accuracy": 0.15587843507528304,
|
|
"num_tokens": 34244488.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 6.134504079818726,
|
|
"epoch": 1.4777593288473303,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00047850587837452936,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.15110252797603607,
|
|
"num_tokens": 34254047.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 6.137491989135742,
|
|
"epoch": 1.478196277200035,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004784925850917881,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.14915971457958221,
|
|
"num_tokens": 34264297.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 6.243809223175049,
|
|
"epoch": 1.4786332255527397,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004784792879059524,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.14868390411138535,
|
|
"num_tokens": 34274945.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 6.139284992218018,
|
|
"epoch": 1.4790701739054444,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047846598681727733,
|
|
"loss": 5.8087,
|
|
"mean_token_accuracy": 0.15301438719034194,
|
|
"num_tokens": 34284914.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 6.06685848236084,
|
|
"epoch": 1.479507122258149,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000478452681826018,
|
|
"loss": 5.8709,
|
|
"mean_token_accuracy": 0.15490325689315795,
|
|
"num_tokens": 34294277.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 6.2253889560699465,
|
|
"epoch": 1.4799440706108538,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047843937293242967,
|
|
"loss": 5.9426,
|
|
"mean_token_accuracy": 0.15257695764303209,
|
|
"num_tokens": 34304865.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 6.0872008323669435,
|
|
"epoch": 1.4803810189635584,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047842606013676753,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.165998575091362,
|
|
"num_tokens": 34315404.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 6.23872013092041,
|
|
"epoch": 1.4808179673162631,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00047841274343928697,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.1495609849691391,
|
|
"num_tokens": 34325448.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 6.1050526142120365,
|
|
"epoch": 1.481254915668968,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004783994228402434,
|
|
"loss": 5.865,
|
|
"mean_token_accuracy": 0.16074959486722945,
|
|
"num_tokens": 34335266.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 6.163719987869262,
|
|
"epoch": 1.4816918640216725,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004783860983398924,
|
|
"loss": 5.8591,
|
|
"mean_token_accuracy": 0.15349616706371308,
|
|
"num_tokens": 34345847.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 6.157124805450439,
|
|
"epoch": 1.4821288123743774,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004783727699384894,
|
|
"loss": 5.8096,
|
|
"mean_token_accuracy": 0.15444130301475525,
|
|
"num_tokens": 34355718.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 6.073325824737549,
|
|
"epoch": 1.4825657607270821,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004783594376362901,
|
|
"loss": 5.8795,
|
|
"mean_token_accuracy": 0.15474819391965866,
|
|
"num_tokens": 34366100.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 6.178067350387574,
|
|
"epoch": 1.4830027090797868,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004783461014335502,
|
|
"loss": 5.9614,
|
|
"mean_token_accuracy": 0.15003640651702882,
|
|
"num_tokens": 34376977.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 6.2077248096466064,
|
|
"epoch": 1.4834396574324915,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004783327613305256,
|
|
"loss": 5.9,
|
|
"mean_token_accuracy": 0.15152034908533096,
|
|
"num_tokens": 34387782.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 6.092386054992676,
|
|
"epoch": 1.4838766057851962,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000478319417327472,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.1603291943669319,
|
|
"num_tokens": 34397321.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 6.114581108093262,
|
|
"epoch": 1.484313554137901,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004783060694246455,
|
|
"loss": 5.899,
|
|
"mean_token_accuracy": 0.1481311537325382,
|
|
"num_tokens": 34407594.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 6.279845666885376,
|
|
"epoch": 1.4847505024906056,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004782927176223021,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.15344629883766175,
|
|
"num_tokens": 34417337.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 6.093864631652832,
|
|
"epoch": 1.4851874508433103,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004782793619206977,
|
|
"loss": 5.7818,
|
|
"mean_token_accuracy": 0.1617438644170761,
|
|
"num_tokens": 34427643.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 6.112289524078369,
|
|
"epoch": 1.485624399196015,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004782660023200887,
|
|
"loss": 5.8903,
|
|
"mean_token_accuracy": 0.15189099535346032,
|
|
"num_tokens": 34437224.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 6.230650997161865,
|
|
"epoch": 1.4860613475487199,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.0004782526388207313,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.14694590047001838,
|
|
"num_tokens": 34447376.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 6.130454730987549,
|
|
"epoch": 1.4864982959014243,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004782392714228818,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.1544419229030609,
|
|
"num_tokens": 34457649.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 6.139226198196411,
|
|
"epoch": 1.4869352442541293,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00047822590012679654,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.157633076608181,
|
|
"num_tokens": 34467437.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 6.196960973739624,
|
|
"epoch": 1.487372192606834,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047821252493273204,
|
|
"loss": 5.8212,
|
|
"mean_token_accuracy": 0.1524882048368454,
|
|
"num_tokens": 34477615.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 6.137586975097657,
|
|
"epoch": 1.4878091409595386,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004781991458409448,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.1533292680978775,
|
|
"num_tokens": 34487619.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 6.155377435684204,
|
|
"epoch": 1.4882460893122433,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00047818576285169154,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.1548856280744076,
|
|
"num_tokens": 34498837.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 6.130313444137573,
|
|
"epoch": 1.488683037664948,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047817237596522885,
|
|
"loss": 5.8574,
|
|
"mean_token_accuracy": 0.15142044201493263,
|
|
"num_tokens": 34508972.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 6.218903732299805,
|
|
"epoch": 1.4891199860176527,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004781589851818135,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.1547143667936325,
|
|
"num_tokens": 34519289.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 6.10342435836792,
|
|
"epoch": 1.4895569343703574,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00047814559050170236,
|
|
"loss": 5.7664,
|
|
"mean_token_accuracy": 0.16532005369663239,
|
|
"num_tokens": 34528384.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 6.074532175064087,
|
|
"epoch": 1.489993882723062,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00047813219192515235,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.14611624032258988,
|
|
"num_tokens": 34537442.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 6.185675048828125,
|
|
"epoch": 1.4904308310757668,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004781187894524205,
|
|
"loss": 5.902,
|
|
"mean_token_accuracy": 0.15343325957655907,
|
|
"num_tokens": 34547960.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 6.139957427978516,
|
|
"epoch": 1.4908677794284715,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047810538308376376,
|
|
"loss": 5.8101,
|
|
"mean_token_accuracy": 0.14967811107635498,
|
|
"num_tokens": 34556730.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 6.061622381210327,
|
|
"epoch": 1.4913047277811762,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004780919728194394,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.1490348219871521,
|
|
"num_tokens": 34566751.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 6.25036654472351,
|
|
"epoch": 1.491741676133881,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00047807855865970454,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.15316146612167358,
|
|
"num_tokens": 34576417.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 6.226842546463013,
|
|
"epoch": 1.4921786244865856,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004780651406048166,
|
|
"loss": 5.9638,
|
|
"mean_token_accuracy": 0.1471695989370346,
|
|
"num_tokens": 34586976.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 6.133858394622803,
|
|
"epoch": 1.4926155728392905,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004780517186550328,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.15699538290500642,
|
|
"num_tokens": 34597374.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 6.116224718093872,
|
|
"epoch": 1.4930525211919952,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004780382928106107,
|
|
"loss": 5.8185,
|
|
"mean_token_accuracy": 0.1594260722398758,
|
|
"num_tokens": 34607586.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 6.1564229965209964,
|
|
"epoch": 1.4934894695446999,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00047802486307180767,
|
|
"loss": 5.9007,
|
|
"mean_token_accuracy": 0.15488080382347108,
|
|
"num_tokens": 34617152.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 6.124329280853272,
|
|
"epoch": 1.4939264178974045,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047801142943888135,
|
|
"loss": 5.8304,
|
|
"mean_token_accuracy": 0.16123347729444504,
|
|
"num_tokens": 34627421.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 6.161361265182495,
|
|
"epoch": 1.4943633662501092,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00047799799191208955,
|
|
"loss": 5.8443,
|
|
"mean_token_accuracy": 0.15437712520360947,
|
|
"num_tokens": 34637687.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 6.192191648483276,
|
|
"epoch": 1.494800314602814,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004779845504916898,
|
|
"loss": 5.901,
|
|
"mean_token_accuracy": 0.1494130253791809,
|
|
"num_tokens": 34647884.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 6.16855640411377,
|
|
"epoch": 1.4952372629555186,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004779711051779401,
|
|
"loss": 5.8809,
|
|
"mean_token_accuracy": 0.1491269662976265,
|
|
"num_tokens": 34658658.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 6.1588623046875,
|
|
"epoch": 1.4956742113082233,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004779576559710982,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.15391636043787002,
|
|
"num_tokens": 34668728.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 6.185825300216675,
|
|
"epoch": 1.496111159660928,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047794420287142203,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.15038785636425017,
|
|
"num_tokens": 34678576.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 6.2679033279418945,
|
|
"epoch": 1.496548108013633,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047793074587916984,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.14634464979171752,
|
|
"num_tokens": 34688920.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 6.149936866760254,
|
|
"epoch": 1.4969850563663374,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047791728499459955,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.15319266617298127,
|
|
"num_tokens": 34699348.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 6.107307958602905,
|
|
"epoch": 1.4974220047190423,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004779038202179694,
|
|
"loss": 5.7727,
|
|
"mean_token_accuracy": 0.1620291978120804,
|
|
"num_tokens": 34708991.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 6.164907312393188,
|
|
"epoch": 1.497858953071747,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047789035154953776,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.14633265882730484,
|
|
"num_tokens": 34720869.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 6.117620849609375,
|
|
"epoch": 1.4982959014244517,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004778768789895627,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.15676439553499222,
|
|
"num_tokens": 34731025.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 6.097006177902221,
|
|
"epoch": 1.4987328497771564,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004778634025383029,
|
|
"loss": 5.8917,
|
|
"mean_token_accuracy": 0.15143688768148422,
|
|
"num_tokens": 34741846.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 6.106971263885498,
|
|
"epoch": 1.499169798129861,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047784992219601673,
|
|
"loss": 5.7706,
|
|
"mean_token_accuracy": 0.17086363434791565,
|
|
"num_tokens": 34753294.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 6.222295331954956,
|
|
"epoch": 1.4996067464825658,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004778364379629627,
|
|
"loss": 5.8604,
|
|
"mean_token_accuracy": 0.15040425434708596,
|
|
"num_tokens": 34763997.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 6.085229969024658,
|
|
"epoch": 1.5000436948352704,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047782294983939955,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.1629262536764145,
|
|
"num_tokens": 34772925.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 6.124052572250366,
|
|
"epoch": 1.5004806431879751,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004778094578255859,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.15400953888893126,
|
|
"num_tokens": 34782608.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 6.089442443847656,
|
|
"epoch": 1.5009175915406798,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004777959619217807,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.16333565413951873,
|
|
"num_tokens": 34792533.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 6.188339281082153,
|
|
"epoch": 1.5013545398933847,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047778246212824263,
|
|
"loss": 5.9562,
|
|
"mean_token_accuracy": 0.14302828162908554,
|
|
"num_tokens": 34803069.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 6.115234422683716,
|
|
"epoch": 1.5017914882460892,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004777689584452306,
|
|
"loss": 5.8841,
|
|
"mean_token_accuracy": 0.15647624284029008,
|
|
"num_tokens": 34811925.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 6.0832971096038815,
|
|
"epoch": 1.5022284365987941,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.0004777554508730038,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.15610338002443314,
|
|
"num_tokens": 34821511.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 6.138559246063233,
|
|
"epoch": 1.5026653849514986,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004777419394118212,
|
|
"loss": 5.9162,
|
|
"mean_token_accuracy": 0.14611384645104408,
|
|
"num_tokens": 34831683.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 6.227632617950439,
|
|
"epoch": 1.5031023333042035,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004777284240619419,
|
|
"loss": 5.8725,
|
|
"mean_token_accuracy": 0.15374660789966582,
|
|
"num_tokens": 34841578.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 6.162811422348023,
|
|
"epoch": 1.5035392816569082,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004777149048236252,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.15482842922210693,
|
|
"num_tokens": 34851959.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 6.082300519943237,
|
|
"epoch": 1.503976230009613,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047770138169713047,
|
|
"loss": 5.9133,
|
|
"mean_token_accuracy": 0.14467027336359023,
|
|
"num_tokens": 34862557.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 6.185537672042846,
|
|
"epoch": 1.5044131783623176,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047768785468271704,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.15043128728866578,
|
|
"num_tokens": 34872394.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 6.207429647445679,
|
|
"epoch": 1.5048501267150223,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047767432378064426,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.1513463541865349,
|
|
"num_tokens": 34881938.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 6.158588123321533,
|
|
"epoch": 1.505287075067727,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047766078899117174,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.1548664763569832,
|
|
"num_tokens": 34892769.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 6.175883531570435,
|
|
"epoch": 1.5057240234204317,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00047764725031455927,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.14331179484724998,
|
|
"num_tokens": 34903643.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 6.148700475692749,
|
|
"epoch": 1.5061609717731366,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004776337077510662,
|
|
"loss": 5.8744,
|
|
"mean_token_accuracy": 0.14294183254241943,
|
|
"num_tokens": 34913558.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 6.175105619430542,
|
|
"epoch": 1.506597920125841,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00047762016130095246,
|
|
"loss": 5.8489,
|
|
"mean_token_accuracy": 0.15276338756084443,
|
|
"num_tokens": 34923653.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 6.118389415740967,
|
|
"epoch": 1.507034868478546,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00047760661096447784,
|
|
"loss": 5.8822,
|
|
"mean_token_accuracy": 0.1490948513150215,
|
|
"num_tokens": 34933381.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 6.124467945098877,
|
|
"epoch": 1.5074718168312504,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004775930567419023,
|
|
"loss": 5.7892,
|
|
"mean_token_accuracy": 0.16079355478286744,
|
|
"num_tokens": 34942486.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 6.147614049911499,
|
|
"epoch": 1.5079087651839553,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004775794986334857,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.14684897810220718,
|
|
"num_tokens": 34952291.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 6.199529218673706,
|
|
"epoch": 1.5083457135366598,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004775659366394883,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.1480625316500664,
|
|
"num_tokens": 34963842.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 6.112629318237305,
|
|
"epoch": 1.5087826618893647,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047755237076016997,
|
|
"loss": 5.8021,
|
|
"mean_token_accuracy": 0.15716639012098313,
|
|
"num_tokens": 34973057.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 6.179137659072876,
|
|
"epoch": 1.5092196102420694,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004775388009957911,
|
|
"loss": 5.9797,
|
|
"mean_token_accuracy": 0.14639114066958428,
|
|
"num_tokens": 34983257.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 6.179181623458862,
|
|
"epoch": 1.509656558594774,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00047752522734661193,
|
|
"loss": 5.8392,
|
|
"mean_token_accuracy": 0.15043409168720245,
|
|
"num_tokens": 34993066.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 6.176004648208618,
|
|
"epoch": 1.5100935069474788,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047751164981289264,
|
|
"loss": 5.8312,
|
|
"mean_token_accuracy": 0.15084033384919165,
|
|
"num_tokens": 35002830.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 6.094789361953735,
|
|
"epoch": 1.5105304553001835,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004774980683948939,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.15349375754594802,
|
|
"num_tokens": 35011837.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 6.1739795207977295,
|
|
"epoch": 1.5109674036528882,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00047748448309287606,
|
|
"loss": 5.8379,
|
|
"mean_token_accuracy": 0.1536051645874977,
|
|
"num_tokens": 35021589.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 6.149427890777588,
|
|
"epoch": 1.5114043520055929,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00047747089390709973,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.15581002384424208,
|
|
"num_tokens": 35032207.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 6.164715242385864,
|
|
"epoch": 1.5118413003582978,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004774573008378256,
|
|
"loss": 5.9344,
|
|
"mean_token_accuracy": 0.14515655487775803,
|
|
"num_tokens": 35042661.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 6.180689668655395,
|
|
"epoch": 1.5122782487110022,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004774437038853143,
|
|
"loss": 5.8917,
|
|
"mean_token_accuracy": 0.15099122375249863,
|
|
"num_tokens": 35053050.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 6.247140979766845,
|
|
"epoch": 1.5127151970637072,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047743010304982674,
|
|
"loss": 5.9282,
|
|
"mean_token_accuracy": 0.14915898814797401,
|
|
"num_tokens": 35064381.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 6.180149269104004,
|
|
"epoch": 1.5131521454164116,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004774164983316237,
|
|
"loss": 5.8037,
|
|
"mean_token_accuracy": 0.15262559577822685,
|
|
"num_tokens": 35074787.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 6.035295391082764,
|
|
"epoch": 1.5135890937691165,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004774028897309662,
|
|
"loss": 5.7895,
|
|
"mean_token_accuracy": 0.1611209601163864,
|
|
"num_tokens": 35085801.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 6.099165201187134,
|
|
"epoch": 1.5140260421218212,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047738927724811514,
|
|
"loss": 5.8925,
|
|
"mean_token_accuracy": 0.15450572967529297,
|
|
"num_tokens": 35096800.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 6.124790954589844,
|
|
"epoch": 1.514462990474526,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004773756608833318,
|
|
"loss": 5.7183,
|
|
"mean_token_accuracy": 0.17593078017234803,
|
|
"num_tokens": 35106735.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 6.081604909896851,
|
|
"epoch": 1.5148999388272306,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047736204063687717,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.15834816694259643,
|
|
"num_tokens": 35116221.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 6.085692739486694,
|
|
"epoch": 1.5153368871799353,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00047734841650901255,
|
|
"loss": 5.7771,
|
|
"mean_token_accuracy": 0.1613197699189186,
|
|
"num_tokens": 35124896.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 6.1304854393005375,
|
|
"epoch": 1.51577383553264,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004773347884999993,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.15470646619796752,
|
|
"num_tokens": 35134576.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 6.128907537460327,
|
|
"epoch": 1.5162107838853447,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004773211566100988,
|
|
"loss": 5.7862,
|
|
"mean_token_accuracy": 0.16112884134054184,
|
|
"num_tokens": 35144210.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 6.079049205780029,
|
|
"epoch": 1.5166477322380496,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004773075208395725,
|
|
"loss": 5.768,
|
|
"mean_token_accuracy": 0.15846778452396393,
|
|
"num_tokens": 35153669.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 6.149544954299927,
|
|
"epoch": 1.517084680590754,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004772938811886818,
|
|
"loss": 5.8897,
|
|
"mean_token_accuracy": 0.1511499747633934,
|
|
"num_tokens": 35163469.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 6.1565367698669435,
|
|
"epoch": 1.517521628943459,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004772802376576887,
|
|
"loss": 5.8992,
|
|
"mean_token_accuracy": 0.15798701643943786,
|
|
"num_tokens": 35173479.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 6.060641765594482,
|
|
"epoch": 1.5179585772961635,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004772665902468545,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.15399756282567978,
|
|
"num_tokens": 35184570.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 6.1313300132751465,
|
|
"epoch": 1.5183955256488684,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004772529389564412,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.15239900052547456,
|
|
"num_tokens": 35193714.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 6.14327483177185,
|
|
"epoch": 1.518832474001573,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004772392837867104,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.1508115939795971,
|
|
"num_tokens": 35203806.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 6.198706197738647,
|
|
"epoch": 1.5192694223542778,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047722562473792433,
|
|
"loss": 5.8987,
|
|
"mean_token_accuracy": 0.15045736208558083,
|
|
"num_tokens": 35213677.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 6.171533823013306,
|
|
"epoch": 1.5197063707069824,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047721196181034465,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.1512599065899849,
|
|
"num_tokens": 35223663.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 6.112890720367432,
|
|
"epoch": 1.5201433190596871,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00047719829500423374,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.15048087984323502,
|
|
"num_tokens": 35234551.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 6.1172607898712155,
|
|
"epoch": 1.5205802674123918,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047718462431985354,
|
|
"loss": 5.8417,
|
|
"mean_token_accuracy": 0.1563853070139885,
|
|
"num_tokens": 35244350.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 6.143025302886963,
|
|
"epoch": 1.5210172157650965,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004771709497574662,
|
|
"loss": 5.7976,
|
|
"mean_token_accuracy": 0.15802988708019255,
|
|
"num_tokens": 35253970.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 6.09180474281311,
|
|
"epoch": 1.5214541641178014,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00047715727131733424,
|
|
"loss": 5.8146,
|
|
"mean_token_accuracy": 0.15859377682209014,
|
|
"num_tokens": 35263316.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 6.159878158569336,
|
|
"epoch": 1.521891112470506,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047714358899971984,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.16033942997455597,
|
|
"num_tokens": 35273407.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 6.13733434677124,
|
|
"epoch": 1.5223280608232108,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004771299028048855,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.14890057668089868,
|
|
"num_tokens": 35284225.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 6.1634420394897464,
|
|
"epoch": 1.5227650091759153,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047711621273309365,
|
|
"loss": 5.773,
|
|
"mean_token_accuracy": 0.15862138643860818,
|
|
"num_tokens": 35294747.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 6.1453797817230225,
|
|
"epoch": 1.5232019575286202,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.000477102518784607,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.15801094472408295,
|
|
"num_tokens": 35304856.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 6.1217848777771,
|
|
"epoch": 1.5236389058813247,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047708882095968817,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.16101155877113343,
|
|
"num_tokens": 35315550.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 6.210644817352295,
|
|
"epoch": 1.5240758542340296,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004770751192585997,
|
|
"loss": 5.9505,
|
|
"mean_token_accuracy": 0.14861477687954902,
|
|
"num_tokens": 35325970.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 6.156119012832642,
|
|
"epoch": 1.5245128025867343,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004770614136816047,
|
|
"loss": 5.8299,
|
|
"mean_token_accuracy": 0.1522540733218193,
|
|
"num_tokens": 35337277.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 6.154503440856933,
|
|
"epoch": 1.524949750939439,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00047704770422896586,
|
|
"loss": 5.8872,
|
|
"mean_token_accuracy": 0.14827334582805635,
|
|
"num_tokens": 35347686.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 6.173165798187256,
|
|
"epoch": 1.5253866992921437,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047703399090094623,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.15608186423778533,
|
|
"num_tokens": 35358727.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 6.060405349731445,
|
|
"epoch": 1.5258236476448483,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004770202736978087,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.15327811241149902,
|
|
"num_tokens": 35369741.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 6.14546570777893,
|
|
"epoch": 1.526260595997553,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004770065526198166,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.15440157651901246,
|
|
"num_tokens": 35380213.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 6.137426805496216,
|
|
"epoch": 1.5266975443502577,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004769928276672328,
|
|
"loss": 5.8682,
|
|
"mean_token_accuracy": 0.15861286073923112,
|
|
"num_tokens": 35389937.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 6.143026542663574,
|
|
"epoch": 1.5271344927029626,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004769790988403208,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.15100124180316926,
|
|
"num_tokens": 35400534.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 6.158385133743286,
|
|
"epoch": 1.5275714410556671,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004769653661393438,
|
|
"loss": 5.8668,
|
|
"mean_token_accuracy": 0.1581027925014496,
|
|
"num_tokens": 35410607.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 6.174805927276611,
|
|
"epoch": 1.528008389408372,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004769516295645654,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.15170571506023406,
|
|
"num_tokens": 35420242.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 6.089843988418579,
|
|
"epoch": 1.5284453377610765,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047693788911624876,
|
|
"loss": 5.8229,
|
|
"mean_token_accuracy": 0.1534021645784378,
|
|
"num_tokens": 35429469.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 6.045228576660156,
|
|
"epoch": 1.5288822861137814,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004769241447946577,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.15693089067935945,
|
|
"num_tokens": 35439656.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 6.152874183654785,
|
|
"epoch": 1.529319234466486,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004769103966000557,
|
|
"loss": 5.7434,
|
|
"mean_token_accuracy": 0.15863042771816255,
|
|
"num_tokens": 35448600.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 6.086853170394898,
|
|
"epoch": 1.5297561828191908,
|
|
"grad_norm": 6.375,
|
|
"learning_rate": 0.0004768966445327065,
|
|
"loss": 5.8423,
|
|
"mean_token_accuracy": 0.15816927403211595,
|
|
"num_tokens": 35458124.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 6.153998327255249,
|
|
"epoch": 1.5301931311718955,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004768828885928738,
|
|
"loss": 5.8,
|
|
"mean_token_accuracy": 0.15543074607849122,
|
|
"num_tokens": 35467616.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 6.070661115646362,
|
|
"epoch": 1.5306300795246002,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004768691287808216,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.15411746948957444,
|
|
"num_tokens": 35478356.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 6.144384384155273,
|
|
"epoch": 1.5310670278773049,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004768553650968137,
|
|
"loss": 5.8968,
|
|
"mean_token_accuracy": 0.15931062623858452,
|
|
"num_tokens": 35490213.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 6.144395160675049,
|
|
"epoch": 1.5315039762300096,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004768415975411142,
|
|
"loss": 5.789,
|
|
"mean_token_accuracy": 0.1629176154732704,
|
|
"num_tokens": 35499982.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 6.12995457649231,
|
|
"epoch": 1.5319409245827145,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047682782611398693,
|
|
"loss": 5.8842,
|
|
"mean_token_accuracy": 0.15302219837903977,
|
|
"num_tokens": 35510572.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 6.234933853149414,
|
|
"epoch": 1.532377872935419,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00047681405081569637,
|
|
"loss": 5.9495,
|
|
"mean_token_accuracy": 0.14548078253865243,
|
|
"num_tokens": 35521560.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 6.217502164840698,
|
|
"epoch": 1.5328148212881239,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047680027164650644,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.14836311414837838,
|
|
"num_tokens": 35530879.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 6.141724014282227,
|
|
"epoch": 1.5332517696408283,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047678648860668163,
|
|
"loss": 5.909,
|
|
"mean_token_accuracy": 0.15604118928313254,
|
|
"num_tokens": 35541210.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 6.14900803565979,
|
|
"epoch": 1.5336887179935332,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047677270169648616,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.1519891694188118,
|
|
"num_tokens": 35550149.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 6.1639406204223635,
|
|
"epoch": 1.534125666346238,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047675891091618464,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.15059865713119508,
|
|
"num_tokens": 35561191.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 6.120050621032715,
|
|
"epoch": 1.5345626146989426,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047674511626604144,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.16110145300626755,
|
|
"num_tokens": 35571636.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 6.10401554107666,
|
|
"epoch": 1.5349995630516473,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004767313177463212,
|
|
"loss": 5.8247,
|
|
"mean_token_accuracy": 0.151840540766716,
|
|
"num_tokens": 35583191.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 6.083314085006714,
|
|
"epoch": 1.535436511404352,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004767175153572885,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.15515257939696311,
|
|
"num_tokens": 35592875.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 6.14441180229187,
|
|
"epoch": 1.5358734597570567,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004767037090992083,
|
|
"loss": 5.782,
|
|
"mean_token_accuracy": 0.158903169631958,
|
|
"num_tokens": 35602158.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 6.100735759735107,
|
|
"epoch": 1.5363104081097614,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047668989897234516,
|
|
"loss": 5.8161,
|
|
"mean_token_accuracy": 0.16153561770915986,
|
|
"num_tokens": 35612077.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 6.130440902709961,
|
|
"epoch": 1.5367473564624663,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047667608497696415,
|
|
"loss": 5.7458,
|
|
"mean_token_accuracy": 0.16635396778583528,
|
|
"num_tokens": 35621856.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 6.076784276962281,
|
|
"epoch": 1.5371843048151708,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.00047666226711333014,
|
|
"loss": 5.8813,
|
|
"mean_token_accuracy": 0.15905992388725282,
|
|
"num_tokens": 35633160.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 6.200541257858276,
|
|
"epoch": 1.5376212531678757,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004766484453817081,
|
|
"loss": 5.8659,
|
|
"mean_token_accuracy": 0.15177130997180938,
|
|
"num_tokens": 35642477.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 6.158634042739868,
|
|
"epoch": 1.5380582015205801,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004766346197823633,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.15790839940309526,
|
|
"num_tokens": 35651938.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 6.116852426528931,
|
|
"epoch": 1.538495149873285,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00047662079031556085,
|
|
"loss": 5.8691,
|
|
"mean_token_accuracy": 0.15003041326999664,
|
|
"num_tokens": 35662881.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 6.122784233093261,
|
|
"epoch": 1.5389320982259895,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004766069569815659,
|
|
"loss": 5.8265,
|
|
"mean_token_accuracy": 0.15284564197063447,
|
|
"num_tokens": 35673436.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 6.138750267028809,
|
|
"epoch": 1.5393690465786944,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.000476593119780644,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.1549277886748314,
|
|
"num_tokens": 35683411.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 6.106433486938476,
|
|
"epoch": 1.5398059949313991,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00047657927871306037,
|
|
"loss": 5.8095,
|
|
"mean_token_accuracy": 0.15640153139829635,
|
|
"num_tokens": 35693806.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 6.098014307022095,
|
|
"epoch": 1.5402429432841038,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004765654337790805,
|
|
"loss": 5.8621,
|
|
"mean_token_accuracy": 0.1564367577433586,
|
|
"num_tokens": 35705015.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 6.186513805389405,
|
|
"epoch": 1.5406798916368085,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004765515849789701,
|
|
"loss": 5.8896,
|
|
"mean_token_accuracy": 0.1558088928461075,
|
|
"num_tokens": 35715668.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 6.206081104278565,
|
|
"epoch": 1.5411168399895132,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00047653773231299455,
|
|
"loss": 5.8467,
|
|
"mean_token_accuracy": 0.156816578656435,
|
|
"num_tokens": 35726381.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 6.152064275741577,
|
|
"epoch": 1.541553788342218,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00047652387578141973,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.1551175206899643,
|
|
"num_tokens": 35736223.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 6.125501394271851,
|
|
"epoch": 1.5419907366949226,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047651001538451146,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.15457146763801574,
|
|
"num_tokens": 35746959.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 6.16798734664917,
|
|
"epoch": 1.5424276850476275,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00047649615112253547,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.1611318990588188,
|
|
"num_tokens": 35756975.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 6.124963617324829,
|
|
"epoch": 1.542864633400332,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.00047648228299575766,
|
|
"loss": 5.8022,
|
|
"mean_token_accuracy": 0.15940418988466262,
|
|
"num_tokens": 35765890.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 6.081785678863525,
|
|
"epoch": 1.5433015817530369,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.00047646841100444415,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.1595257118344307,
|
|
"num_tokens": 35775630.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 6.075564384460449,
|
|
"epoch": 1.5437385301057414,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00047645453514886095,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.15650368481874466,
|
|
"num_tokens": 35786053.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 6.1906568050384525,
|
|
"epoch": 1.5441754784584463,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004764406554292742,
|
|
"loss": 5.8739,
|
|
"mean_token_accuracy": 0.15723182410001754,
|
|
"num_tokens": 35795736.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 6.1809087753295895,
|
|
"epoch": 1.544612426811151,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004764267718459501,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.15416981875896454,
|
|
"num_tokens": 35805887.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 6.0569689750671385,
|
|
"epoch": 1.5450493751638557,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.000476412884399155,
|
|
"loss": 5.8687,
|
|
"mean_token_accuracy": 0.15537567883729936,
|
|
"num_tokens": 35815625.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 6.149646234512329,
|
|
"epoch": 1.5454863235165603,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004763989930891552,
|
|
"loss": 5.8226,
|
|
"mean_token_accuracy": 0.15840071737766265,
|
|
"num_tokens": 35825617.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 6.105234050750733,
|
|
"epoch": 1.545923271869265,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00047638509791621714,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.15119030326604843,
|
|
"num_tokens": 35835538.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 6.166472578048706,
|
|
"epoch": 1.5463602202219697,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00047637119888060747,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.16132533103227614,
|
|
"num_tokens": 35846302.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 6.2242824077606205,
|
|
"epoch": 1.5467971685746744,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047635729598259266,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.14949096739292145,
|
|
"num_tokens": 35857384.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 6.209799814224243,
|
|
"epoch": 1.5472341169273793,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004763433892224394,
|
|
"loss": 5.8718,
|
|
"mean_token_accuracy": 0.14422939270734786,
|
|
"num_tokens": 35867496.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 6.1603435516357425,
|
|
"epoch": 1.5476710652800838,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004763294786004144,
|
|
"loss": 5.8807,
|
|
"mean_token_accuracy": 0.15611384958028793,
|
|
"num_tokens": 35878051.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 6.131881952285767,
|
|
"epoch": 1.5481080136327887,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004763155641167846,
|
|
"loss": 5.8175,
|
|
"mean_token_accuracy": 0.1604203164577484,
|
|
"num_tokens": 35887926.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 6.1118607997894285,
|
|
"epoch": 1.5485449619854932,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047630164577181666,
|
|
"loss": 5.8287,
|
|
"mean_token_accuracy": 0.15149388164281846,
|
|
"num_tokens": 35897982.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 6.113210725784302,
|
|
"epoch": 1.548981910338198,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004762877235657777,
|
|
"loss": 5.8803,
|
|
"mean_token_accuracy": 0.15546282082796098,
|
|
"num_tokens": 35908805.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 6.178672790527344,
|
|
"epoch": 1.5494188586909028,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004762737974989348,
|
|
"loss": 5.7969,
|
|
"mean_token_accuracy": 0.15982719659805297,
|
|
"num_tokens": 35918739.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 6.099252510070801,
|
|
"epoch": 1.5498558070436075,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000476259867571555,
|
|
"loss": 5.8749,
|
|
"mean_token_accuracy": 0.15605874061584474,
|
|
"num_tokens": 35928592.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 6.064162015914917,
|
|
"epoch": 1.5502927553963122,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004762459337839055,
|
|
"loss": 5.8197,
|
|
"mean_token_accuracy": 0.15851555913686752,
|
|
"num_tokens": 35938287.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 6.224677419662475,
|
|
"epoch": 1.5507297037490169,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047623199613625343,
|
|
"loss": 5.8184,
|
|
"mean_token_accuracy": 0.1545197382569313,
|
|
"num_tokens": 35947890.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 6.047910928726196,
|
|
"epoch": 1.5511666521017216,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004762180546288663,
|
|
"loss": 5.792,
|
|
"mean_token_accuracy": 0.16004120260477067,
|
|
"num_tokens": 35956513.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 6.07114953994751,
|
|
"epoch": 1.5516036004544262,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004762041092620114,
|
|
"loss": 5.8501,
|
|
"mean_token_accuracy": 0.159542578458786,
|
|
"num_tokens": 35966837.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 6.207669973373413,
|
|
"epoch": 1.5520405488071312,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047619016003595625,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.14954447597265244,
|
|
"num_tokens": 35977076.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 6.214081525802612,
|
|
"epoch": 1.5524774971598356,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00047617620695096854,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.15590979307889938,
|
|
"num_tokens": 35986862.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 6.175775575637817,
|
|
"epoch": 1.5529144455125405,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00047616225000731566,
|
|
"loss": 5.8807,
|
|
"mean_token_accuracy": 0.14411073699593543,
|
|
"num_tokens": 35997488.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 6.140735149383545,
|
|
"epoch": 1.553351393865245,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004761482892052655,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.14927130043506623,
|
|
"num_tokens": 36008045.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 6.156619215011597,
|
|
"epoch": 1.55378834221795,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00047613432454508565,
|
|
"loss": 5.8232,
|
|
"mean_token_accuracy": 0.15075255781412125,
|
|
"num_tokens": 36017864.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 6.14031400680542,
|
|
"epoch": 1.5542252905706544,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047612035602704407,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.15727190524339676,
|
|
"num_tokens": 36027797.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 6.1969451904296875,
|
|
"epoch": 1.5546622389233593,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047610638365140867,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.1498262345790863,
|
|
"num_tokens": 36037627.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 6.133720731735229,
|
|
"epoch": 1.555099187276064,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047609240741844757,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.14968007132411004,
|
|
"num_tokens": 36046324.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 6.094100475311279,
|
|
"epoch": 1.5555361356287687,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004760784273284286,
|
|
"loss": 5.7899,
|
|
"mean_token_accuracy": 0.16053585708141327,
|
|
"num_tokens": 36056212.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 6.148568534851075,
|
|
"epoch": 1.5559730839814734,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004760644433816201,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.1476304531097412,
|
|
"num_tokens": 36066745.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 6.216650438308716,
|
|
"epoch": 1.556410032334178,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004760504555782902,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.1519563153386116,
|
|
"num_tokens": 36077415.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 6.103620147705078,
|
|
"epoch": 1.5568469806868828,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047603646391870715,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.16240674257278442,
|
|
"num_tokens": 36088381.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 6.0874169826507565,
|
|
"epoch": 1.5572839290395875,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047602246840313945,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.1603674679994583,
|
|
"num_tokens": 36098333.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 6.064192008972168,
|
|
"epoch": 1.5577208773922924,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047600846903185544,
|
|
"loss": 5.8682,
|
|
"mean_token_accuracy": 0.153440423309803,
|
|
"num_tokens": 36107843.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 6.192847871780396,
|
|
"epoch": 1.5581578257449968,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004759944658051237,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.1583794519305229,
|
|
"num_tokens": 36116948.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 6.153967332839966,
|
|
"epoch": 1.5585947740977018,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004759804587232127,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.1532774269580841,
|
|
"num_tokens": 36126808.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 6.127297449111938,
|
|
"epoch": 1.5590317224504062,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047596644778639133,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.14905515313148499,
|
|
"num_tokens": 36136630.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 6.2333721160888675,
|
|
"epoch": 1.5594686708031111,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004759524329949281,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.14976508766412736,
|
|
"num_tokens": 36146422.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 6.185214185714722,
|
|
"epoch": 1.5599056191558158,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004759384143490919,
|
|
"loss": 5.8501,
|
|
"mean_token_accuracy": 0.14938322603702545,
|
|
"num_tokens": 36156169.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 6.116262340545655,
|
|
"epoch": 1.5603425675085205,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004759243918491517,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.1594856485724449,
|
|
"num_tokens": 36165173.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 6.173662376403809,
|
|
"epoch": 1.5607795158612252,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047591036549537633,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.15109619051218032,
|
|
"num_tokens": 36175852.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 6.13984637260437,
|
|
"epoch": 1.56121646421393,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004758963352880348,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.15417944490909577,
|
|
"num_tokens": 36185288.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 6.183798027038574,
|
|
"epoch": 1.5616534125666346,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004758823012273964,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.15622807145118714,
|
|
"num_tokens": 36196374.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 6.1149355411529545,
|
|
"epoch": 1.5620903609193393,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047586826331373025,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.15695322304964066,
|
|
"num_tokens": 36206714.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 6.19454517364502,
|
|
"epoch": 1.5625273092720442,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004758542215473054,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.14614250063896178,
|
|
"num_tokens": 36217891.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 6.176143741607666,
|
|
"epoch": 1.5629642576247487,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004758401759283915,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.15781117528676986,
|
|
"num_tokens": 36226776.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 6.14338641166687,
|
|
"epoch": 1.5634012059774536,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00047582612645725764,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.15400125086307526,
|
|
"num_tokens": 36237362.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 6.109305906295776,
|
|
"epoch": 1.563838154330158,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047581207313417346,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.15746268332004548,
|
|
"num_tokens": 36246264.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 6.191521739959716,
|
|
"epoch": 1.564275102682863,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047579801595940853,
|
|
"loss": 5.8686,
|
|
"mean_token_accuracy": 0.1532348468899727,
|
|
"num_tokens": 36255676.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 6.137023687362671,
|
|
"epoch": 1.5647120510355674,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00047578395493323245,
|
|
"loss": 5.729,
|
|
"mean_token_accuracy": 0.16360267698764802,
|
|
"num_tokens": 36264346.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 6.053152847290039,
|
|
"epoch": 1.5651489993882723,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047576989005591495,
|
|
"loss": 5.8377,
|
|
"mean_token_accuracy": 0.14955184161663054,
|
|
"num_tokens": 36273569.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 6.127921628952026,
|
|
"epoch": 1.565585947740977,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004757558213277257,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.16324147805571557,
|
|
"num_tokens": 36283708.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 6.1554240703582765,
|
|
"epoch": 1.5660228960936817,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047574174874893456,
|
|
"loss": 5.798,
|
|
"mean_token_accuracy": 0.15344853103160858,
|
|
"num_tokens": 36293184.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 6.090034246444702,
|
|
"epoch": 1.5664598444463864,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004757276723198115,
|
|
"loss": 5.8923,
|
|
"mean_token_accuracy": 0.15130351930856706,
|
|
"num_tokens": 36303071.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 6.147397661209107,
|
|
"epoch": 1.566896792799091,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004757135920406266,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.15910038352012634,
|
|
"num_tokens": 36313245.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 6.078237390518188,
|
|
"epoch": 1.567333741151796,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004756995079116498,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.15247970968484878,
|
|
"num_tokens": 36322711.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 6.0533184051513675,
|
|
"epoch": 1.5677706895045005,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00047568541993315124,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.15331623703241348,
|
|
"num_tokens": 36333667.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 6.210267353057861,
|
|
"epoch": 1.5682076378572054,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047567132810540113,
|
|
"loss": 5.9076,
|
|
"mean_token_accuracy": 0.14778622090816498,
|
|
"num_tokens": 36343660.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 6.142909240722656,
|
|
"epoch": 1.5686445862099099,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047565723242866983,
|
|
"loss": 5.9106,
|
|
"mean_token_accuracy": 0.15254026874899865,
|
|
"num_tokens": 36353581.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 6.138402795791626,
|
|
"epoch": 1.5690815345626148,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00047564313290322774,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.15257705599069596,
|
|
"num_tokens": 36363818.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 6.135894870758056,
|
|
"epoch": 1.5695184829153193,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004756290295293451,
|
|
"loss": 5.8455,
|
|
"mean_token_accuracy": 0.15520919114351273,
|
|
"num_tokens": 36373590.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 6.1613812923431395,
|
|
"epoch": 1.5699554312680242,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004756149223072926,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.15242792218923568,
|
|
"num_tokens": 36383556.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 6.152489709854126,
|
|
"epoch": 1.5703923796207289,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004756008112373408,
|
|
"loss": 5.8332,
|
|
"mean_token_accuracy": 0.15248623639345169,
|
|
"num_tokens": 36393194.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 6.120516300201416,
|
|
"epoch": 1.5708293279734336,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004755866963197603,
|
|
"loss": 5.8233,
|
|
"mean_token_accuracy": 0.15515899062156677,
|
|
"num_tokens": 36402962.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 6.1442992210388185,
|
|
"epoch": 1.5712662763261382,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004755725775548219,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.15354258567094803,
|
|
"num_tokens": 36411932.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 6.1702721118927,
|
|
"epoch": 1.571703224678843,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047555845494279633,
|
|
"loss": 5.8074,
|
|
"mean_token_accuracy": 0.16097897440195083,
|
|
"num_tokens": 36421363.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 6.132246685028076,
|
|
"epoch": 1.5721401730315476,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004755443284839545,
|
|
"loss": 5.8221,
|
|
"mean_token_accuracy": 0.1544548377394676,
|
|
"num_tokens": 36431422.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 6.075223112106324,
|
|
"epoch": 1.5725771213842523,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047553019817856736,
|
|
"loss": 5.813,
|
|
"mean_token_accuracy": 0.15758510082960128,
|
|
"num_tokens": 36441004.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 6.225890064239502,
|
|
"epoch": 1.5730140697369572,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047551606402690595,
|
|
"loss": 5.9213,
|
|
"mean_token_accuracy": 0.1466245472431183,
|
|
"num_tokens": 36451474.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.5730140697369572,
|
|
"eval_entropy": 5.992097050988548,
|
|
"eval_loss": 5.897541522979736,
|
|
"eval_mean_token_accuracy": 0.16076978383316498,
|
|
"eval_num_tokens": 36451474.0,
|
|
"eval_runtime": 28.2174,
|
|
"eval_samples_per_second": 1311.744,
|
|
"eval_steps_per_second": 163.977,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 6.158188962936402,
|
|
"epoch": 1.5734510180896617,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004755019260292414,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.155093415081501,
|
|
"num_tokens": 36461341.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 6.103657579421997,
|
|
"epoch": 1.5738879664423666,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004754877841858448,
|
|
"loss": 5.928,
|
|
"mean_token_accuracy": 0.15227026119828224,
|
|
"num_tokens": 36471679.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 6.188374614715576,
|
|
"epoch": 1.574324914795071,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004754736384969875,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.1491597056388855,
|
|
"num_tokens": 36481457.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 6.115581274032593,
|
|
"epoch": 1.574761863147776,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004754594889629407,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.15590354502201081,
|
|
"num_tokens": 36490596.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 6.189972972869873,
|
|
"epoch": 1.5751988115004807,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004754453355839759,
|
|
"loss": 5.907,
|
|
"mean_token_accuracy": 0.1497448593378067,
|
|
"num_tokens": 36501027.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 6.140265607833863,
|
|
"epoch": 1.5756357598531854,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047543117836036446,
|
|
"loss": 5.8032,
|
|
"mean_token_accuracy": 0.15489476919174194,
|
|
"num_tokens": 36512089.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 6.076355457305908,
|
|
"epoch": 1.57607270820589,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047541701729237815,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.15851605236530303,
|
|
"num_tokens": 36522521.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 6.234769821166992,
|
|
"epoch": 1.5765096565585948,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004754028523802883,
|
|
"loss": 5.9214,
|
|
"mean_token_accuracy": 0.14585841074585915,
|
|
"num_tokens": 36533111.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 6.116734504699707,
|
|
"epoch": 1.5769466049112995,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004753886836243668,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.1609452873468399,
|
|
"num_tokens": 36542477.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 6.050258493423462,
|
|
"epoch": 1.5773835532640041,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047537451102488526,
|
|
"loss": 5.8604,
|
|
"mean_token_accuracy": 0.15373194292187692,
|
|
"num_tokens": 36552137.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 6.17083477973938,
|
|
"epoch": 1.577820501616709,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004753603345821157,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.15040013045072556,
|
|
"num_tokens": 36562440.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 6.1897135257720945,
|
|
"epoch": 1.5782574499694135,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047534615429632986,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.15815496444702148,
|
|
"num_tokens": 36571863.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 6.081523466110229,
|
|
"epoch": 1.5786943983221184,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004753319701677999,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.1590537667274475,
|
|
"num_tokens": 36581409.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 6.135543918609619,
|
|
"epoch": 1.579131346674823,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047531778219679773,
|
|
"loss": 5.8387,
|
|
"mean_token_accuracy": 0.1500946596264839,
|
|
"num_tokens": 36592779.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 6.099080991744995,
|
|
"epoch": 1.5795682950275278,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047530359038359547,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.16549460887908934,
|
|
"num_tokens": 36601173.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 6.092098569869995,
|
|
"epoch": 1.5800052433802323,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004752893947284654,
|
|
"loss": 5.8677,
|
|
"mean_token_accuracy": 0.15613431632518768,
|
|
"num_tokens": 36610147.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 6.12001142501831,
|
|
"epoch": 1.5804421917329372,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004752751952316799,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.15582821518182755,
|
|
"num_tokens": 36620093.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 6.163449096679687,
|
|
"epoch": 1.580879140085642,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00047526099189351115,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.15226275324821473,
|
|
"num_tokens": 36631833.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 6.121299171447754,
|
|
"epoch": 1.5813160884383466,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004752467847142316,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.15259799361228943,
|
|
"num_tokens": 36641123.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 6.122568988800049,
|
|
"epoch": 1.5817530367910513,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047523257369411383,
|
|
"loss": 5.8833,
|
|
"mean_token_accuracy": 0.15033481940627097,
|
|
"num_tokens": 36652310.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 6.199804639816284,
|
|
"epoch": 1.582189985143756,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004752183588334303,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.152802512049675,
|
|
"num_tokens": 36662783.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 6.155228853225708,
|
|
"epoch": 1.5826269334964607,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047520414013245383,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.1583334967494011,
|
|
"num_tokens": 36672933.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 6.1429215431213375,
|
|
"epoch": 1.5830638818491654,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004751899175914571,
|
|
"loss": 5.8927,
|
|
"mean_token_accuracy": 0.15098801255226135,
|
|
"num_tokens": 36682570.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 6.102208280563355,
|
|
"epoch": 1.5835008302018703,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004751756912107127,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.16016732454299926,
|
|
"num_tokens": 36693008.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 6.047227907180786,
|
|
"epoch": 1.5839377785545747,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047516146099049376,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.16307833045721054,
|
|
"num_tokens": 36702611.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 6.099211072921753,
|
|
"epoch": 1.5843747269072797,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047514722693107304,
|
|
"loss": 5.8812,
|
|
"mean_token_accuracy": 0.15601153075695037,
|
|
"num_tokens": 36712470.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 6.157591247558594,
|
|
"epoch": 1.5848116752599841,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004751329890327237,
|
|
"loss": 5.8888,
|
|
"mean_token_accuracy": 0.15223745182156562,
|
|
"num_tokens": 36722578.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 6.162668514251709,
|
|
"epoch": 1.585248623612689,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004751187472957187,
|
|
"loss": 5.8746,
|
|
"mean_token_accuracy": 0.15409443974494935,
|
|
"num_tokens": 36732334.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 6.123752069473267,
|
|
"epoch": 1.5856855719653937,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004751045017203313,
|
|
"loss": 5.8885,
|
|
"mean_token_accuracy": 0.15324715673923492,
|
|
"num_tokens": 36742328.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 6.141130352020264,
|
|
"epoch": 1.5861225203180984,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004750902523068347,
|
|
"loss": 5.8926,
|
|
"mean_token_accuracy": 0.15117437094449998,
|
|
"num_tokens": 36754363.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 6.151986789703369,
|
|
"epoch": 1.586559468670803,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004750759990555022,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.14788235649466513,
|
|
"num_tokens": 36765588.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 6.08484959602356,
|
|
"epoch": 1.5869964170235078,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004750617419666072,
|
|
"loss": 5.7995,
|
|
"mean_token_accuracy": 0.15464927703142167,
|
|
"num_tokens": 36774851.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 6.132309865951538,
|
|
"epoch": 1.5874333653762125,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047504748104042324,
|
|
"loss": 5.8627,
|
|
"mean_token_accuracy": 0.15192834734916688,
|
|
"num_tokens": 36785836.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 6.061438465118409,
|
|
"epoch": 1.5878703137289172,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00047503321627722375,
|
|
"loss": 5.797,
|
|
"mean_token_accuracy": 0.16071885600686073,
|
|
"num_tokens": 36795367.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 6.141823673248291,
|
|
"epoch": 1.588307262081622,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047501894767728225,
|
|
"loss": 5.7842,
|
|
"mean_token_accuracy": 0.1577644795179367,
|
|
"num_tokens": 36804294.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 6.135769701004028,
|
|
"epoch": 1.5887442104343266,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00047500467524087266,
|
|
"loss": 5.8456,
|
|
"mean_token_accuracy": 0.1532744884490967,
|
|
"num_tokens": 36813711.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 6.156258630752563,
|
|
"epoch": 1.5891811587870315,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004749903989682685,
|
|
"loss": 5.8345,
|
|
"mean_token_accuracy": 0.1577165961265564,
|
|
"num_tokens": 36824498.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 6.1636247634887695,
|
|
"epoch": 1.589618107139736,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047497611885974366,
|
|
"loss": 5.7983,
|
|
"mean_token_accuracy": 0.16096200197935104,
|
|
"num_tokens": 36833329.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 6.105648612976074,
|
|
"epoch": 1.5900550554924409,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047496183491557215,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.1531764507293701,
|
|
"num_tokens": 36842783.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 6.066834402084351,
|
|
"epoch": 1.5904920038451456,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00047494754713602787,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.15330330207943915,
|
|
"num_tokens": 36852785.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 6.11262698173523,
|
|
"epoch": 1.5909289521978502,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047493325552138484,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.1529523327946663,
|
|
"num_tokens": 36862337.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 6.165375089645385,
|
|
"epoch": 1.591365900550555,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004749189600719172,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.15142595618963242,
|
|
"num_tokens": 36872026.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 6.114049291610717,
|
|
"epoch": 1.5918028489032596,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004749046607878992,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.15473776459693908,
|
|
"num_tokens": 36882520.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 6.075957012176514,
|
|
"epoch": 1.5922397972559643,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047489035766960504,
|
|
"loss": 5.7429,
|
|
"mean_token_accuracy": 0.16983606517314911,
|
|
"num_tokens": 36892630.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 6.19117112159729,
|
|
"epoch": 1.592676745608669,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047487605071730904,
|
|
"loss": 5.8687,
|
|
"mean_token_accuracy": 0.15230597406625748,
|
|
"num_tokens": 36902692.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 6.2098315238952635,
|
|
"epoch": 1.593113693961374,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047486173993128566,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.14443593248724937,
|
|
"num_tokens": 36913581.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 6.11932864189148,
|
|
"epoch": 1.5935506423140784,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004748474253118094,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.15359503030776978,
|
|
"num_tokens": 36924031.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 6.147268056869507,
|
|
"epoch": 1.5939875906667833,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004748331068591548,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.1566885754466057,
|
|
"num_tokens": 36934622.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 6.1849205493927,
|
|
"epoch": 1.5944245390194878,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004748187845735965,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.158174766600132,
|
|
"num_tokens": 36944374.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 6.136397647857666,
|
|
"epoch": 1.5948614873721927,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047480445845540927,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.15433474332094194,
|
|
"num_tokens": 36954371.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 6.053894710540772,
|
|
"epoch": 1.5952984357248972,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00047479012850486777,
|
|
"loss": 5.8279,
|
|
"mean_token_accuracy": 0.1602454349398613,
|
|
"num_tokens": 36964217.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 6.2213554859161375,
|
|
"epoch": 1.595735384077602,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047477579472224687,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.150271500647068,
|
|
"num_tokens": 36974580.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 6.0925116539001465,
|
|
"epoch": 1.5961723324303068,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004747614571078216,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.17123343348503112,
|
|
"num_tokens": 36983434.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 6.057025814056397,
|
|
"epoch": 1.5966092807830115,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004747471156618669,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.1516721248626709,
|
|
"num_tokens": 36993813.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 6.1624181270599365,
|
|
"epoch": 1.5970462291357161,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004747327703846579,
|
|
"loss": 5.8415,
|
|
"mean_token_accuracy": 0.15800213813781738,
|
|
"num_tokens": 37003855.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 6.102229309082031,
|
|
"epoch": 1.5974831774884208,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00047471842127646966,
|
|
"loss": 5.8066,
|
|
"mean_token_accuracy": 0.16011677086353301,
|
|
"num_tokens": 37013660.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 6.042488145828247,
|
|
"epoch": 1.5979201258411255,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047470406833757746,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.1555236518383026,
|
|
"num_tokens": 37023888.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 6.171698427200317,
|
|
"epoch": 1.5983570741938302,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047468971156825656,
|
|
"loss": 5.9277,
|
|
"mean_token_accuracy": 0.14409274607896805,
|
|
"num_tokens": 37034260.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 6.1402528285980225,
|
|
"epoch": 1.5987940225465351,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004746753509687824,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.15345453470945358,
|
|
"num_tokens": 37045300.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 6.163219738006592,
|
|
"epoch": 1.5992309708992396,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004746609865394303,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.16205774247646332,
|
|
"num_tokens": 37054898.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 6.053664112091065,
|
|
"epoch": 1.5996679192519445,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004746466182804759,
|
|
"loss": 5.7697,
|
|
"mean_token_accuracy": 0.156445737183094,
|
|
"num_tokens": 37064519.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 6.072087907791138,
|
|
"epoch": 1.600104867604649,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004746322461921948,
|
|
"loss": 5.8531,
|
|
"mean_token_accuracy": 0.15501998960971833,
|
|
"num_tokens": 37074967.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 6.115574693679809,
|
|
"epoch": 1.600541815957354,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004746178702748626,
|
|
"loss": 5.8371,
|
|
"mean_token_accuracy": 0.1587224781513214,
|
|
"num_tokens": 37084736.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 6.170813703536988,
|
|
"epoch": 1.6009787643100586,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000474603490528755,
|
|
"loss": 5.8044,
|
|
"mean_token_accuracy": 0.16121101081371308,
|
|
"num_tokens": 37094327.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 6.140086221694946,
|
|
"epoch": 1.6014157126627633,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004745891069541479,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.15752982199192048,
|
|
"num_tokens": 37104099.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 6.114892101287841,
|
|
"epoch": 1.601852661015468,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047457471955131714,
|
|
"loss": 5.8892,
|
|
"mean_token_accuracy": 0.14979428946971893,
|
|
"num_tokens": 37115337.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 6.170300102233886,
|
|
"epoch": 1.6022896093681727,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004745603283205387,
|
|
"loss": 5.8199,
|
|
"mean_token_accuracy": 0.15776073485612868,
|
|
"num_tokens": 37125522.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 6.154092025756836,
|
|
"epoch": 1.6027265577208774,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004745459332620885,
|
|
"loss": 5.9082,
|
|
"mean_token_accuracy": 0.15259279161691666,
|
|
"num_tokens": 37135847.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 6.01115345954895,
|
|
"epoch": 1.603163506073582,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004745315343762428,
|
|
"loss": 5.7863,
|
|
"mean_token_accuracy": 0.16372239738702773,
|
|
"num_tokens": 37145714.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 6.101547622680664,
|
|
"epoch": 1.603600454426287,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047451713166327776,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.15872190445661544,
|
|
"num_tokens": 37154921.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 6.17178316116333,
|
|
"epoch": 1.6040374027789914,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047450272512346953,
|
|
"loss": 5.8216,
|
|
"mean_token_accuracy": 0.15789951384067535,
|
|
"num_tokens": 37165303.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 6.102764511108399,
|
|
"epoch": 1.6044743511316963,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047448831475709454,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.15744060277938843,
|
|
"num_tokens": 37175014.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 6.079820156097412,
|
|
"epoch": 1.6049112994844008,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004744739005644291,
|
|
"loss": 5.8088,
|
|
"mean_token_accuracy": 0.16320455074310303,
|
|
"num_tokens": 37185830.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 6.082566165924073,
|
|
"epoch": 1.6053482478371057,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004744594825457498,
|
|
"loss": 5.736,
|
|
"mean_token_accuracy": 0.16083633452653884,
|
|
"num_tokens": 37196264.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 6.16067361831665,
|
|
"epoch": 1.6057851961898104,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00047444506070133305,
|
|
"loss": 5.8702,
|
|
"mean_token_accuracy": 0.15172916948795317,
|
|
"num_tokens": 37206338.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 6.133966636657715,
|
|
"epoch": 1.606222144542515,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004744306350314555,
|
|
"loss": 5.834,
|
|
"mean_token_accuracy": 0.15540405511856079,
|
|
"num_tokens": 37216231.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 6.255458927154541,
|
|
"epoch": 1.6066590928952198,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004744162055363939,
|
|
"loss": 5.9554,
|
|
"mean_token_accuracy": 0.14620960950851442,
|
|
"num_tokens": 37227209.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 6.1480175971984865,
|
|
"epoch": 1.6070960412479245,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000474401772216425,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.1554884910583496,
|
|
"num_tokens": 37238056.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 6.062219905853271,
|
|
"epoch": 1.6075329896006292,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004743873350718257,
|
|
"loss": 5.8097,
|
|
"mean_token_accuracy": 0.15636790841817855,
|
|
"num_tokens": 37247864.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 6.048687553405761,
|
|
"epoch": 1.6079699379533339,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004743728941028727,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.16187262088060378,
|
|
"num_tokens": 37256418.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 6.119430303573608,
|
|
"epoch": 1.6084068863060388,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004743584493098431,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.15558625459671022,
|
|
"num_tokens": 37266540.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 6.188225746154785,
|
|
"epoch": 1.6088438346587433,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047434400069301414,
|
|
"loss": 5.8421,
|
|
"mean_token_accuracy": 0.1538287803530693,
|
|
"num_tokens": 37277011.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 6.105555009841919,
|
|
"epoch": 1.6092807830114482,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004743295482526627,
|
|
"loss": 5.8359,
|
|
"mean_token_accuracy": 0.157236485183239,
|
|
"num_tokens": 37287203.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 6.083509492874145,
|
|
"epoch": 1.6097177313641526,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004743150919890661,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.1586715191602707,
|
|
"num_tokens": 37297293.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 6.166322374343872,
|
|
"epoch": 1.6101546797168576,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00047430063190250155,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.1494002342224121,
|
|
"num_tokens": 37307882.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 6.082572603225708,
|
|
"epoch": 1.610591628069562,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004742861679932464,
|
|
"loss": 5.7658,
|
|
"mean_token_accuracy": 0.16378538608551024,
|
|
"num_tokens": 37317466.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 6.054345893859863,
|
|
"epoch": 1.611028576422267,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047427170026157823,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.15313297808170317,
|
|
"num_tokens": 37327544.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 6.156347465515137,
|
|
"epoch": 1.6114655247749716,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004742572287077744,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.15231260806322097,
|
|
"num_tokens": 37338082.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 6.187852287292481,
|
|
"epoch": 1.6119024731276763,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047424275333211256,
|
|
"loss": 5.8248,
|
|
"mean_token_accuracy": 0.15846317410469055,
|
|
"num_tokens": 37348127.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 6.189578294754028,
|
|
"epoch": 1.612339421480381,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004742282741348702,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.1473035603761673,
|
|
"num_tokens": 37359547.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 6.147730827331543,
|
|
"epoch": 1.6127763698330857,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004742137911163253,
|
|
"loss": 5.9371,
|
|
"mean_token_accuracy": 0.15470682680606843,
|
|
"num_tokens": 37369547.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 6.110079622268676,
|
|
"epoch": 1.6132133181857904,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004741993042767554,
|
|
"loss": 5.9168,
|
|
"mean_token_accuracy": 0.157265368103981,
|
|
"num_tokens": 37380055.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 6.183764362335205,
|
|
"epoch": 1.613650266538495,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047418481361643844,
|
|
"loss": 5.9211,
|
|
"mean_token_accuracy": 0.15204641371965408,
|
|
"num_tokens": 37390179.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 6.236109256744385,
|
|
"epoch": 1.6140872148912,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047417031913565247,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.15373657792806625,
|
|
"num_tokens": 37400663.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 6.129943609237671,
|
|
"epoch": 1.6145241632439045,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004741558208346753,
|
|
"loss": 5.8659,
|
|
"mean_token_accuracy": 0.1560629978775978,
|
|
"num_tokens": 37410988.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 6.199072647094726,
|
|
"epoch": 1.6149611115966094,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047414131871378526,
|
|
"loss": 5.9526,
|
|
"mean_token_accuracy": 0.15012071579694747,
|
|
"num_tokens": 37422092.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 6.131946229934693,
|
|
"epoch": 1.6153980599493138,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004741268127732603,
|
|
"loss": 5.835,
|
|
"mean_token_accuracy": 0.15567414164543153,
|
|
"num_tokens": 37431637.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 6.142140293121338,
|
|
"epoch": 1.6158350083020188,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047411230301337877,
|
|
"loss": 5.9197,
|
|
"mean_token_accuracy": 0.14138541519641876,
|
|
"num_tokens": 37442678.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 6.176050090789795,
|
|
"epoch": 1.6162719566547235,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004740977894344189,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.15359829142689704,
|
|
"num_tokens": 37452324.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 6.142911100387574,
|
|
"epoch": 1.6167089050074281,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004740832720366591,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.1494448497891426,
|
|
"num_tokens": 37462940.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 6.132896661758423,
|
|
"epoch": 1.6171458533601328,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004740687508203779,
|
|
"loss": 5.9082,
|
|
"mean_token_accuracy": 0.15300915539264678,
|
|
"num_tokens": 37474121.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 6.110058116912842,
|
|
"epoch": 1.6175828017128375,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004740542257858536,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.15394898653030395,
|
|
"num_tokens": 37483439.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 6.196117782592774,
|
|
"epoch": 1.6180197500655422,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.00047403969693336507,
|
|
"loss": 5.8701,
|
|
"mean_token_accuracy": 0.15491663068532943,
|
|
"num_tokens": 37493804.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 6.145570993423462,
|
|
"epoch": 1.618456698418247,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004740251642631909,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.15633058845996856,
|
|
"num_tokens": 37504158.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 6.094492197036743,
|
|
"epoch": 1.6188936467709518,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004740106277756097,
|
|
"loss": 5.8435,
|
|
"mean_token_accuracy": 0.15085844844579696,
|
|
"num_tokens": 37515069.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 6.0258582592010494,
|
|
"epoch": 1.6193305951236563,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047399608747090033,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.15899247005581857,
|
|
"num_tokens": 37525486.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 6.142672967910767,
|
|
"epoch": 1.6197675434763612,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047398154334934187,
|
|
"loss": 5.8674,
|
|
"mean_token_accuracy": 0.15258204638957978,
|
|
"num_tokens": 37535616.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 6.094711589813232,
|
|
"epoch": 1.6202044918290657,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047396699541121296,
|
|
"loss": 5.8246,
|
|
"mean_token_accuracy": 0.1578874409198761,
|
|
"num_tokens": 37546084.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 6.058980131149292,
|
|
"epoch": 1.6206414401817706,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004739524436567929,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.1601293243467808,
|
|
"num_tokens": 37555865.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 6.090431213378906,
|
|
"epoch": 1.6210783885344753,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004739378880863608,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.15517839342355727,
|
|
"num_tokens": 37565985.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 6.1478002071380615,
|
|
"epoch": 1.62151533688718,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004739233287001957,
|
|
"loss": 5.9188,
|
|
"mean_token_accuracy": 0.14992354512214662,
|
|
"num_tokens": 37575887.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 6.139444732666016,
|
|
"epoch": 1.6219522852398847,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047390876549857695,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.1608128160238266,
|
|
"num_tokens": 37585346.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 6.144708108901978,
|
|
"epoch": 1.6223892335925894,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047389419848178384,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.1571737825870514,
|
|
"num_tokens": 37595674.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 6.109766626358033,
|
|
"epoch": 1.622826181945294,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047387962765009576,
|
|
"loss": 5.837,
|
|
"mean_token_accuracy": 0.15036114826798438,
|
|
"num_tokens": 37605537.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 6.148508358001709,
|
|
"epoch": 1.6232631302979987,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047386505300379224,
|
|
"loss": 5.8813,
|
|
"mean_token_accuracy": 0.15324413031339645,
|
|
"num_tokens": 37615801.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 6.13037633895874,
|
|
"epoch": 1.6237000786507036,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004738504745431528,
|
|
"loss": 5.7696,
|
|
"mean_token_accuracy": 0.1616264298558235,
|
|
"num_tokens": 37625582.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 6.104911661148071,
|
|
"epoch": 1.6241370270034081,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047383589226845707,
|
|
"loss": 5.8896,
|
|
"mean_token_accuracy": 0.15660351365804673,
|
|
"num_tokens": 37636075.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 6.046101427078247,
|
|
"epoch": 1.624573975356113,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047382130617998477,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.1683705359697342,
|
|
"num_tokens": 37645692.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 6.128520774841308,
|
|
"epoch": 1.6250109237088175,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004738067162780156,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.1556292802095413,
|
|
"num_tokens": 37655035.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 6.148236703872681,
|
|
"epoch": 1.6254478720615224,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004737921225628294,
|
|
"loss": 5.8172,
|
|
"mean_token_accuracy": 0.15634016543626786,
|
|
"num_tokens": 37665829.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 6.067884206771851,
|
|
"epoch": 1.6258848204142269,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00047377752503470613,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.16721004694700242,
|
|
"num_tokens": 37676318.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 6.114659547805786,
|
|
"epoch": 1.6263217687669318,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047376292369392584,
|
|
"loss": 5.8606,
|
|
"mean_token_accuracy": 0.15416946560144423,
|
|
"num_tokens": 37686977.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 6.085484218597412,
|
|
"epoch": 1.6267587171196365,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047374831854076843,
|
|
"loss": 5.8032,
|
|
"mean_token_accuracy": 0.15572132617235185,
|
|
"num_tokens": 37697004.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 6.105016708374023,
|
|
"epoch": 1.6271956654723412,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047373370957551423,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.15412657111883163,
|
|
"num_tokens": 37707613.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 6.154040145874023,
|
|
"epoch": 1.6276326138250459,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004737190967984433,
|
|
"loss": 5.815,
|
|
"mean_token_accuracy": 0.15441539734601975,
|
|
"num_tokens": 37717167.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 6.135318040847778,
|
|
"epoch": 1.6280695621777506,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004737044802098359,
|
|
"loss": 5.915,
|
|
"mean_token_accuracy": 0.14939552247524263,
|
|
"num_tokens": 37727496.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 6.093013715744019,
|
|
"epoch": 1.6285065105304553,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004736898598099725,
|
|
"loss": 5.8211,
|
|
"mean_token_accuracy": 0.1553942784667015,
|
|
"num_tokens": 37736844.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 6.165453815460205,
|
|
"epoch": 1.62894345888316,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047367523559913347,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.15251405388116837,
|
|
"num_tokens": 37746027.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 6.174861478805542,
|
|
"epoch": 1.6293804072358649,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047366060757759933,
|
|
"loss": 5.8098,
|
|
"mean_token_accuracy": 0.15763675719499587,
|
|
"num_tokens": 37756499.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 6.101605224609375,
|
|
"epoch": 1.6298173555885693,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047364597574565064,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.15793321132659913,
|
|
"num_tokens": 37766533.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 6.1170854568481445,
|
|
"epoch": 1.6302543039412742,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000473631340103568,
|
|
"loss": 5.8193,
|
|
"mean_token_accuracy": 0.1622927963733673,
|
|
"num_tokens": 37775937.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 6.122182750701905,
|
|
"epoch": 1.6306912522939787,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00047361670065163225,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.1569531351327896,
|
|
"num_tokens": 37786587.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 6.128579950332641,
|
|
"epoch": 1.6311282006466836,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047360205739012406,
|
|
"loss": 5.8439,
|
|
"mean_token_accuracy": 0.15462930351495743,
|
|
"num_tokens": 37797200.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 6.066535949707031,
|
|
"epoch": 1.6315651489993883,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004735874103193244,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.16094542890787125,
|
|
"num_tokens": 37806652.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 6.137418413162232,
|
|
"epoch": 1.632002097352093,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004735727594395141,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.1501804545521736,
|
|
"num_tokens": 37817057.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 6.117572450637818,
|
|
"epoch": 1.6324390457047977,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00047355810475097423,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.15169511288404464,
|
|
"num_tokens": 37826216.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 6.1833806991577145,
|
|
"epoch": 1.6328759940575024,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047354344625398596,
|
|
"loss": 5.8884,
|
|
"mean_token_accuracy": 0.1534342348575592,
|
|
"num_tokens": 37835834.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 6.10155930519104,
|
|
"epoch": 1.633312942410207,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004735287839488302,
|
|
"loss": 5.8167,
|
|
"mean_token_accuracy": 0.16098785549402236,
|
|
"num_tokens": 37846252.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 6.101823854446411,
|
|
"epoch": 1.6337498907629118,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00047351411783578846,
|
|
"loss": 5.8107,
|
|
"mean_token_accuracy": 0.15409183204174043,
|
|
"num_tokens": 37856020.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 6.188598203659057,
|
|
"epoch": 1.6341868391156167,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004734994479151418,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.15436530858278275,
|
|
"num_tokens": 37866132.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 6.106948757171631,
|
|
"epoch": 1.6346237874683212,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004734847741871718,
|
|
"loss": 5.8997,
|
|
"mean_token_accuracy": 0.15431200116872787,
|
|
"num_tokens": 37876779.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 6.1267928123474125,
|
|
"epoch": 1.635060735821026,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047347009665215983,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.15666446685791016,
|
|
"num_tokens": 37886981.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 6.103256511688232,
|
|
"epoch": 1.6354976841737305,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004734554153103874,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.1629627212882042,
|
|
"num_tokens": 37896974.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 6.1627795696258545,
|
|
"epoch": 1.6359346325264355,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00047344073016213615,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.14571316093206405,
|
|
"num_tokens": 37909020.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 6.198339128494263,
|
|
"epoch": 1.63637158087914,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047342604120768764,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.1588145151734352,
|
|
"num_tokens": 37919417.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 6.1158068656921385,
|
|
"epoch": 1.6368085292318448,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004734113484473237,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.1477796733379364,
|
|
"num_tokens": 37929030.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 6.090813541412354,
|
|
"epoch": 1.6372454775845495,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004733966518813262,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.15683868974447251,
|
|
"num_tokens": 37939157.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 6.121892595291138,
|
|
"epoch": 1.6376824259372542,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047338195150997686,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.15147726386785507,
|
|
"num_tokens": 37950544.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 6.08565993309021,
|
|
"epoch": 1.638119374289959,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00047336724733355786,
|
|
"loss": 5.7644,
|
|
"mean_token_accuracy": 0.16694549173116685,
|
|
"num_tokens": 37960059.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 6.093255233764649,
|
|
"epoch": 1.6385563226426636,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00047335253935235094,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.15961635261774063,
|
|
"num_tokens": 37970669.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 6.077090787887573,
|
|
"epoch": 1.6389932709953685,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00047333782756663853,
|
|
"loss": 5.8211,
|
|
"mean_token_accuracy": 0.1623784527182579,
|
|
"num_tokens": 37980088.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 6.130883264541626,
|
|
"epoch": 1.639430219348073,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047332311197670264,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.15645087212324144,
|
|
"num_tokens": 37989433.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 6.168463802337646,
|
|
"epoch": 1.639867167700778,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00047330839258282544,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.15782661885023117,
|
|
"num_tokens": 37999735.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 6.086714363098144,
|
|
"epoch": 1.6403041160534824,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004732936693852895,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.1667976751923561,
|
|
"num_tokens": 38008515.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 6.1335205078125,
|
|
"epoch": 1.6407410644061873,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047327894238437696,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.15473941415548326,
|
|
"num_tokens": 38018778.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 6.169872426986695,
|
|
"epoch": 1.6411780127588917,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047326421158037045,
|
|
"loss": 5.8763,
|
|
"mean_token_accuracy": 0.15240313559770585,
|
|
"num_tokens": 38029062.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 6.091077470779419,
|
|
"epoch": 1.6416149611115967,
|
|
"grad_norm": 6.03125,
|
|
"learning_rate": 0.00047324947697355253,
|
|
"loss": 5.7618,
|
|
"mean_token_accuracy": 0.16436618864536284,
|
|
"num_tokens": 38039945.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 6.13494725227356,
|
|
"epoch": 1.6420519094643014,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047323473856420573,
|
|
"loss": 5.852,
|
|
"mean_token_accuracy": 0.153858582675457,
|
|
"num_tokens": 38050213.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 6.117273807525635,
|
|
"epoch": 1.642488857817006,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047321999635261276,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.15843318849802018,
|
|
"num_tokens": 38060147.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 6.100334501266479,
|
|
"epoch": 1.6429258061697107,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004732052503390563,
|
|
"loss": 5.8576,
|
|
"mean_token_accuracy": 0.15376311391592026,
|
|
"num_tokens": 38070854.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 6.118924236297607,
|
|
"epoch": 1.6433627545224154,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004731905005238194,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.14683781787753106,
|
|
"num_tokens": 38080998.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 6.145289516448974,
|
|
"epoch": 1.6437997028751201,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047317574690718486,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.15473107993602753,
|
|
"num_tokens": 38091421.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 6.117181921005249,
|
|
"epoch": 1.6442366512278248,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047316098948943557,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.16150670647621154,
|
|
"num_tokens": 38101106.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 6.124206638336181,
|
|
"epoch": 1.6446735995805297,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00047314622827085466,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.15121359154582023,
|
|
"num_tokens": 38111346.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 6.194262552261352,
|
|
"epoch": 1.6451105479332342,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047313146325172534,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.147097672522068,
|
|
"num_tokens": 38121798.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 6.124340009689331,
|
|
"epoch": 1.645547496285939,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004731166944323307,
|
|
"loss": 5.8881,
|
|
"mean_token_accuracy": 0.14912372529506684,
|
|
"num_tokens": 38134145.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 6.161386203765869,
|
|
"epoch": 1.6459844446386436,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047310192181295406,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.15616045147180557,
|
|
"num_tokens": 38144213.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 6.122765636444091,
|
|
"epoch": 1.6464213929913485,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004730871453938788,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.16242776662111283,
|
|
"num_tokens": 38154245.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 6.099372720718383,
|
|
"epoch": 1.6468583413440532,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004730723651753882,
|
|
"loss": 5.8227,
|
|
"mean_token_accuracy": 0.1565498560667038,
|
|
"num_tokens": 38163969.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 6.059172439575195,
|
|
"epoch": 1.6472952896967579,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004730575811577659,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.15794841796159745,
|
|
"num_tokens": 38173586.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 6.0792951583862305,
|
|
"epoch": 1.6477322380494626,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004730427933412954,
|
|
"loss": 5.777,
|
|
"mean_token_accuracy": 0.1548040106892586,
|
|
"num_tokens": 38182702.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 6.07518162727356,
|
|
"epoch": 1.6481691864021673,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004730280017262604,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.16442347913980485,
|
|
"num_tokens": 38191937.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 6.09440131187439,
|
|
"epoch": 1.648606134754872,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004730132063129445,
|
|
"loss": 5.7839,
|
|
"mean_token_accuracy": 0.159683395922184,
|
|
"num_tokens": 38201234.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 6.1160468578338625,
|
|
"epoch": 1.6490430831075766,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00047299840710163157,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.1586320295929909,
|
|
"num_tokens": 38211790.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 6.147962951660157,
|
|
"epoch": 1.6494800314602815,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00047298360409260543,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.15903422236442566,
|
|
"num_tokens": 38221946.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 6.0754194259643555,
|
|
"epoch": 1.649916979812986,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00047296879728615,
|
|
"loss": 5.8554,
|
|
"mean_token_accuracy": 0.15347450822591782,
|
|
"num_tokens": 38232366.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 6.133282041549682,
|
|
"epoch": 1.650353928165691,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047295398668254933,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.1509290099143982,
|
|
"num_tokens": 38242504.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 6.182716655731201,
|
|
"epoch": 1.6507908765183954,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004729391722820875,
|
|
"loss": 5.8571,
|
|
"mean_token_accuracy": 0.15664587765932084,
|
|
"num_tokens": 38251916.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 6.072823715209961,
|
|
"epoch": 1.6512278248711003,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047292435408504855,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.15972300320863725,
|
|
"num_tokens": 38262438.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 6.039656114578247,
|
|
"epoch": 1.6516647732238048,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004729095320917169,
|
|
"loss": 5.7734,
|
|
"mean_token_accuracy": 0.17215760201215743,
|
|
"num_tokens": 38273095.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 6.167916774749756,
|
|
"epoch": 1.6521017215765097,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004728947063023766,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.1562114581465721,
|
|
"num_tokens": 38282827.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 6.219447088241577,
|
|
"epoch": 1.6525386699292144,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004728798767173122,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.15486627519130708,
|
|
"num_tokens": 38292827.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 6.125799322128296,
|
|
"epoch": 1.652975618281919,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00047286504333680804,
|
|
"loss": 5.8488,
|
|
"mean_token_accuracy": 0.1487625904381275,
|
|
"num_tokens": 38302658.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 6.119754648208618,
|
|
"epoch": 1.6534125666346238,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004728502061611488,
|
|
"loss": 5.8125,
|
|
"mean_token_accuracy": 0.15366054475307464,
|
|
"num_tokens": 38312154.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 6.12138671875,
|
|
"epoch": 1.6538495149873285,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047283536519061875,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.1609782636165619,
|
|
"num_tokens": 38321317.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 6.093803071975708,
|
|
"epoch": 1.6542864633400332,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047282052042550276,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.15576285868883133,
|
|
"num_tokens": 38331632.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 6.1320899486541744,
|
|
"epoch": 1.6547234116927378,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047280567186608563,
|
|
"loss": 5.8679,
|
|
"mean_token_accuracy": 0.1505403511226177,
|
|
"num_tokens": 38342072.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 6.211898517608643,
|
|
"epoch": 1.6551603600454428,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000472790819512652,
|
|
"loss": 5.811,
|
|
"mean_token_accuracy": 0.15256388932466508,
|
|
"num_tokens": 38351105.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 6.193249702453613,
|
|
"epoch": 1.6555973083981472,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004727759633654868,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.15076037496328354,
|
|
"num_tokens": 38361521.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 6.070543527603149,
|
|
"epoch": 1.6560342567508521,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004727611034248751,
|
|
"loss": 5.7791,
|
|
"mean_token_accuracy": 0.15336894989013672,
|
|
"num_tokens": 38370720.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 6.0799023628234865,
|
|
"epoch": 1.6564712051035566,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004727462396911017,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.15835435688495636,
|
|
"num_tokens": 38380434.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 6.022542905807495,
|
|
"epoch": 1.6569081534562615,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047273137216445176,
|
|
"loss": 5.7317,
|
|
"mean_token_accuracy": 0.173357991874218,
|
|
"num_tokens": 38390503.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 6.16728367805481,
|
|
"epoch": 1.6573451018089662,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004727165008452106,
|
|
"loss": 5.952,
|
|
"mean_token_accuracy": 0.1479262411594391,
|
|
"num_tokens": 38401757.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 6.112488460540772,
|
|
"epoch": 1.657782050161671,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004727016257336633,
|
|
"loss": 5.8418,
|
|
"mean_token_accuracy": 0.15839479118585587,
|
|
"num_tokens": 38412130.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 6.101836204528809,
|
|
"epoch": 1.6582189985143756,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047268674683009526,
|
|
"loss": 5.8219,
|
|
"mean_token_accuracy": 0.15906714797019958,
|
|
"num_tokens": 38422155.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 6.116298866271973,
|
|
"epoch": 1.6586559468670803,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047267186413479185,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.16271159201860427,
|
|
"num_tokens": 38431621.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 6.178564023971558,
|
|
"epoch": 1.659092895219785,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047265697764803843,
|
|
"loss": 5.9011,
|
|
"mean_token_accuracy": 0.15169056057929992,
|
|
"num_tokens": 38442354.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 6.085093355178833,
|
|
"epoch": 1.6595298435724897,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047264208737012064,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.15349179804325103,
|
|
"num_tokens": 38452932.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 6.094286775588989,
|
|
"epoch": 1.6599667919251946,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004726271933013241,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.1560909390449524,
|
|
"num_tokens": 38464442.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 6.140982151031494,
|
|
"epoch": 1.660403740277899,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00047261229544193434,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.15364985167980194,
|
|
"num_tokens": 38475718.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 6.0793756484985355,
|
|
"epoch": 1.660840688630604,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047259739379223726,
|
|
"loss": 5.8179,
|
|
"mean_token_accuracy": 0.15528008192777634,
|
|
"num_tokens": 38485091.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 6.151020765304565,
|
|
"epoch": 1.6612776369833084,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047258248835251867,
|
|
"loss": 5.8278,
|
|
"mean_token_accuracy": 0.15394909381866456,
|
|
"num_tokens": 38495748.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 6.190218257904053,
|
|
"epoch": 1.6617145853360134,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047256757912306435,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.1539991468191147,
|
|
"num_tokens": 38506152.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 6.156981611251831,
|
|
"epoch": 1.662151533688718,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004725526661041604,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.15531576201319694,
|
|
"num_tokens": 38515722.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 6.083573865890503,
|
|
"epoch": 1.6625884820414227,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004725377492960927,
|
|
"loss": 5.7999,
|
|
"mean_token_accuracy": 0.16602276414632797,
|
|
"num_tokens": 38526270.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 6.136768865585327,
|
|
"epoch": 1.6630254303941274,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004725228286991475,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.15266606360673904,
|
|
"num_tokens": 38537436.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 6.1395446300506595,
|
|
"epoch": 1.6634623787468321,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004725079043136111,
|
|
"loss": 5.8012,
|
|
"mean_token_accuracy": 0.1607723727822304,
|
|
"num_tokens": 38547298.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 6.068498325347901,
|
|
"epoch": 1.6638993270995368,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004724929761397694,
|
|
"loss": 5.8054,
|
|
"mean_token_accuracy": 0.1583385407924652,
|
|
"num_tokens": 38556465.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 6.072360706329346,
|
|
"epoch": 1.6643362754522415,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000472478044177909,
|
|
"loss": 5.8425,
|
|
"mean_token_accuracy": 0.1597535043954849,
|
|
"num_tokens": 38568009.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 6.146525239944458,
|
|
"epoch": 1.6647732238049464,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004724631084283163,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.15977909564971923,
|
|
"num_tokens": 38578778.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 6.0575133800506595,
|
|
"epoch": 1.6652101721576509,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047244816889127763,
|
|
"loss": 5.7483,
|
|
"mean_token_accuracy": 0.1671575352549553,
|
|
"num_tokens": 38588991.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 6.155195903778076,
|
|
"epoch": 1.6656471205103558,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004724332255670797,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.16592033207416534,
|
|
"num_tokens": 38598800.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 6.070187377929687,
|
|
"epoch": 1.6660840688630603,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047241827845600896,
|
|
"loss": 5.8069,
|
|
"mean_token_accuracy": 0.15673100650310517,
|
|
"num_tokens": 38608680.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 6.124496603012085,
|
|
"epoch": 1.6665210172157652,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047240332755835217,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.15894126668572425,
|
|
"num_tokens": 38618402.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 6.26353907585144,
|
|
"epoch": 1.6669579655684696,
|
|
"grad_norm": 5.9375,
|
|
"learning_rate": 0.00047238837287439625,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.15350157767534256,
|
|
"num_tokens": 38628370.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 6.1332025051116945,
|
|
"epoch": 1.6673949139211746,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004723734144044278,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.1663918063044548,
|
|
"num_tokens": 38638138.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 6.117161989212036,
|
|
"epoch": 1.6678318622738793,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047235845214873385,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.15420200526714326,
|
|
"num_tokens": 38649412.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 6.145470809936524,
|
|
"epoch": 1.668268810626584,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047234348610760145,
|
|
"loss": 5.7974,
|
|
"mean_token_accuracy": 0.1533084586262703,
|
|
"num_tokens": 38660048.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 6.105442905426026,
|
|
"epoch": 1.6687057589792886,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004723285162813175,
|
|
"loss": 5.7969,
|
|
"mean_token_accuracy": 0.16411686688661575,
|
|
"num_tokens": 38671246.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 6.117104768753052,
|
|
"epoch": 1.6691427073319933,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004723135426701693,
|
|
"loss": 5.8273,
|
|
"mean_token_accuracy": 0.1577977180480957,
|
|
"num_tokens": 38680880.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 6.044180011749267,
|
|
"epoch": 1.669579655684698,
|
|
"grad_norm": 6.53125,
|
|
"learning_rate": 0.0004722985652744438,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.15735935270786286,
|
|
"num_tokens": 38691440.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 6.119514274597168,
|
|
"epoch": 1.6700166040374027,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047228358409442863,
|
|
"loss": 5.8091,
|
|
"mean_token_accuracy": 0.1662777468562126,
|
|
"num_tokens": 38700846.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 6.238430547714233,
|
|
"epoch": 1.6704535523901076,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047226859913041084,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.16070397943258286,
|
|
"num_tokens": 38712130.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 6.180017757415771,
|
|
"epoch": 1.670890500742812,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00047225361038267795,
|
|
"loss": 5.9067,
|
|
"mean_token_accuracy": 0.15520768612623215,
|
|
"num_tokens": 38722482.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.9815174579620365,
|
|
"epoch": 1.671327449095517,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047223861785151744,
|
|
"loss": 5.7566,
|
|
"mean_token_accuracy": 0.15863682925701142,
|
|
"num_tokens": 38731936.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 6.0875166893005375,
|
|
"epoch": 1.6717643974482215,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004722236215372169,
|
|
"loss": 5.7405,
|
|
"mean_token_accuracy": 0.15893969535827637,
|
|
"num_tokens": 38741444.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 6.21986083984375,
|
|
"epoch": 1.6722013458009264,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000472208621440064,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.14849231764674187,
|
|
"num_tokens": 38751454.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 6.1371866226196286,
|
|
"epoch": 1.672638294153631,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004721936175603463,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.14809708148241044,
|
|
"num_tokens": 38761373.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 6.120560216903686,
|
|
"epoch": 1.6730752425063358,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00047217860989835184,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.16308124959468842,
|
|
"num_tokens": 38772047.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 6.145443487167358,
|
|
"epoch": 1.6735121908590405,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004721635984543682,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.16155510991811753,
|
|
"num_tokens": 38781393.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 6.145397710800171,
|
|
"epoch": 1.6739491392117452,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004721485832286835,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.15633226037025452,
|
|
"num_tokens": 38791104.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 6.039845895767212,
|
|
"epoch": 1.6743860875644498,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004721335642215856,
|
|
"loss": 5.8627,
|
|
"mean_token_accuracy": 0.15498319491744042,
|
|
"num_tokens": 38801855.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 6.044262790679932,
|
|
"epoch": 1.6748230359171545,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004721185414333627,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.16360869854688645,
|
|
"num_tokens": 38811983.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 6.076495170593262,
|
|
"epoch": 1.6752599842698594,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004721035148643029,
|
|
"loss": 5.7706,
|
|
"mean_token_accuracy": 0.15775015950202942,
|
|
"num_tokens": 38821762.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 6.044222021102906,
|
|
"epoch": 1.675696932622564,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004720884845146944,
|
|
"loss": 5.8175,
|
|
"mean_token_accuracy": 0.16202907115221024,
|
|
"num_tokens": 38831840.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 6.102727460861206,
|
|
"epoch": 1.6761338809752688,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00047207345038482545,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.1704510048031807,
|
|
"num_tokens": 38841506.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 6.145182085037232,
|
|
"epoch": 1.6765708293279733,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004720584124749844,
|
|
"loss": 5.8712,
|
|
"mean_token_accuracy": 0.15555896311998368,
|
|
"num_tokens": 38851793.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 6.011753129959106,
|
|
"epoch": 1.6770077776806782,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00047204337078545985,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.16332475394010543,
|
|
"num_tokens": 38861958.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 6.086695909500122,
|
|
"epoch": 1.677444726033383,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004720283253165402,
|
|
"loss": 5.8019,
|
|
"mean_token_accuracy": 0.15991731584072114,
|
|
"num_tokens": 38872181.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 6.173571586608887,
|
|
"epoch": 1.6778816743860876,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047201327606851394,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.15976209789514542,
|
|
"num_tokens": 38882423.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 6.16213698387146,
|
|
"epoch": 1.6783186227387923,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004719982230416699,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.15263132005929947,
|
|
"num_tokens": 38892833.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 6.139116191864014,
|
|
"epoch": 1.678755571091497,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004719831662362967,
|
|
"loss": 5.8888,
|
|
"mean_token_accuracy": 0.15749704241752624,
|
|
"num_tokens": 38904037.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 6.0898291110992435,
|
|
"epoch": 1.6791925194442017,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004719681056526831,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.164544478058815,
|
|
"num_tokens": 38914194.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 6.039488077163696,
|
|
"epoch": 1.6796294677969064,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047195304129111804,
|
|
"loss": 5.8509,
|
|
"mean_token_accuracy": 0.15357363373041152,
|
|
"num_tokens": 38925354.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 6.172190713882446,
|
|
"epoch": 1.6800664161496113,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047193797315189047,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.15298427045345306,
|
|
"num_tokens": 38936170.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 6.172828149795532,
|
|
"epoch": 1.6805033645023157,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004719229012352894,
|
|
"loss": 5.8449,
|
|
"mean_token_accuracy": 0.15547781437635422,
|
|
"num_tokens": 38945316.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 6.130415439605713,
|
|
"epoch": 1.6809403128550207,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047190782554160386,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.15261305794119834,
|
|
"num_tokens": 38955444.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 6.080860996246338,
|
|
"epoch": 1.6813772612077251,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004718927460711231,
|
|
"loss": 5.7725,
|
|
"mean_token_accuracy": 0.16373928785324096,
|
|
"num_tokens": 38965202.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 6.053822183609009,
|
|
"epoch": 1.68181420956043,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047187766282413623,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.15780514031648635,
|
|
"num_tokens": 38975822.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 6.110651063919067,
|
|
"epoch": 1.6822511579131345,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004718625758009327,
|
|
"loss": 5.8095,
|
|
"mean_token_accuracy": 0.16059374213218688,
|
|
"num_tokens": 38985890.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 6.125767564773559,
|
|
"epoch": 1.6826881062658394,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00047184748500180175,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.16184118539094924,
|
|
"num_tokens": 38996374.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 6.08174500465393,
|
|
"epoch": 1.6831250546185441,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004718323904270329,
|
|
"loss": 5.8103,
|
|
"mean_token_accuracy": 0.1581805855035782,
|
|
"num_tokens": 39006371.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 6.079828882217408,
|
|
"epoch": 1.6835620029712488,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004718172920769157,
|
|
"loss": 5.7721,
|
|
"mean_token_accuracy": 0.16084895133972169,
|
|
"num_tokens": 39015514.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 6.096600675582886,
|
|
"epoch": 1.6839989513239535,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004718021899517397,
|
|
"loss": 5.79,
|
|
"mean_token_accuracy": 0.16337790489196777,
|
|
"num_tokens": 39025700.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 6.063145446777344,
|
|
"epoch": 1.6844358996766582,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00047178708405179454,
|
|
"loss": 5.8365,
|
|
"mean_token_accuracy": 0.1638899862766266,
|
|
"num_tokens": 39036157.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 6.153424978256226,
|
|
"epoch": 1.6848728480293629,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047177197437737003,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.15151374638080597,
|
|
"num_tokens": 39046044.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 6.163524580001831,
|
|
"epoch": 1.6853097963820676,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004717568609287559,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.14842982366681098,
|
|
"num_tokens": 39056034.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 6.140909671783447,
|
|
"epoch": 1.6857467447347725,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004717417437062421,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.15855249464511872,
|
|
"num_tokens": 39065687.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 6.110138702392578,
|
|
"epoch": 1.686183693087477,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047172662271011855,
|
|
"loss": 5.8198,
|
|
"mean_token_accuracy": 0.15501875281333924,
|
|
"num_tokens": 39077107.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 6.084283828735352,
|
|
"epoch": 1.6866206414401819,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00047171149794067533,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.15895448625087738,
|
|
"num_tokens": 39087220.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 6.1323915958404545,
|
|
"epoch": 1.6870575897928863,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004716963693982025,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.16237185448408126,
|
|
"num_tokens": 39097706.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 6.125293827056884,
|
|
"epoch": 1.6874945381455912,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004716812370829902,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.1505938410758972,
|
|
"num_tokens": 39108044.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 6.0772223472595215,
|
|
"epoch": 1.687931486498296,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004716661009953287,
|
|
"loss": 5.8118,
|
|
"mean_token_accuracy": 0.1537209965288639,
|
|
"num_tokens": 39116917.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 6.056534147262573,
|
|
"epoch": 1.6883684348510006,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004716509611355084,
|
|
"loss": 5.8115,
|
|
"mean_token_accuracy": 0.16177838891744614,
|
|
"num_tokens": 39126770.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 6.069213485717773,
|
|
"epoch": 1.6888053832037053,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047163581750381956,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.15334124118089676,
|
|
"num_tokens": 39137406.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 6.111293697357178,
|
|
"epoch": 1.68924233155641,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047162067010055275,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.15638425350189208,
|
|
"num_tokens": 39146950.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 6.128775310516358,
|
|
"epoch": 1.6896792799091147,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004716055189259984,
|
|
"loss": 5.7575,
|
|
"mean_token_accuracy": 0.1567702740430832,
|
|
"num_tokens": 39157382.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 6.082703018188477,
|
|
"epoch": 1.6901162282618194,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00047159036398044727,
|
|
"loss": 5.8044,
|
|
"mean_token_accuracy": 0.15351771414279938,
|
|
"num_tokens": 39166641.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 6.073806095123291,
|
|
"epoch": 1.6905531766145243,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004715752052641899,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.15833919048309325,
|
|
"num_tokens": 39176731.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 6.172596979141235,
|
|
"epoch": 1.6909901249672288,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004715600427775171,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.1556394711136818,
|
|
"num_tokens": 39187202.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 6.141682434082031,
|
|
"epoch": 1.6914270733199337,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004715448765207196,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.15623832643032073,
|
|
"num_tokens": 39197302.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 6.161933422088623,
|
|
"epoch": 1.6918640216726382,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004715297064940885,
|
|
"loss": 5.8449,
|
|
"mean_token_accuracy": 0.15721532255411147,
|
|
"num_tokens": 39208382.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 6.108320522308349,
|
|
"epoch": 1.692300970025343,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004715145326979146,
|
|
"loss": 5.7858,
|
|
"mean_token_accuracy": 0.15833992809057235,
|
|
"num_tokens": 39218529.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 6.094034099578858,
|
|
"epoch": 1.6927379183780478,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00047149935513248896,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.15539976805448533,
|
|
"num_tokens": 39228976.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 6.103112697601318,
|
|
"epoch": 1.6931748667307525,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004714841737981028,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.1658128723502159,
|
|
"num_tokens": 39238921.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 6.018022108078003,
|
|
"epoch": 1.6936118150834572,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047146898869504717,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.1520024523139,
|
|
"num_tokens": 39247978.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 6.070518350601196,
|
|
"epoch": 1.6940487634361618,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00047145379982361336,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.16389472037553787,
|
|
"num_tokens": 39257487.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 6.11506609916687,
|
|
"epoch": 1.6944857117888665,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047143860718409285,
|
|
"loss": 5.772,
|
|
"mean_token_accuracy": 0.16077075898647308,
|
|
"num_tokens": 39267819.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 6.141073894500733,
|
|
"epoch": 1.6949226601415712,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047142341077677685,
|
|
"loss": 5.8704,
|
|
"mean_token_accuracy": 0.1514420062303543,
|
|
"num_tokens": 39277673.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 6.106815814971924,
|
|
"epoch": 1.6953596084942761,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004714082106019569,
|
|
"loss": 5.7257,
|
|
"mean_token_accuracy": 0.15973930805921555,
|
|
"num_tokens": 39287340.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 6.112748098373413,
|
|
"epoch": 1.6957965568469806,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004713930066599246,
|
|
"loss": 5.8611,
|
|
"mean_token_accuracy": 0.16122769713401794,
|
|
"num_tokens": 39298277.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 6.123789072036743,
|
|
"epoch": 1.6962335051996855,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00047137779895097145,
|
|
"loss": 5.8217,
|
|
"mean_token_accuracy": 0.15225579738616943,
|
|
"num_tokens": 39307996.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 6.097979784011841,
|
|
"epoch": 1.69667045355239,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047136258747538926,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.15645243972539902,
|
|
"num_tokens": 39317327.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 6.063478755950928,
|
|
"epoch": 1.697107401905095,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004713473722334697,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.16891108006238936,
|
|
"num_tokens": 39326728.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 6.1465741157531735,
|
|
"epoch": 1.6975443502577994,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047133215322550464,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.15052735805511475,
|
|
"num_tokens": 39336606.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 6.161265277862549,
|
|
"epoch": 1.6979812986105043,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004713169304517861,
|
|
"loss": 5.8177,
|
|
"mean_token_accuracy": 0.15517356991767883,
|
|
"num_tokens": 39345622.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 6.162582921981811,
|
|
"epoch": 1.698418246963209,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047130170391260597,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.15732862651348115,
|
|
"num_tokens": 39356868.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 6.071225881576538,
|
|
"epoch": 1.6988551953159137,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004712864736082562,
|
|
"loss": 5.7278,
|
|
"mean_token_accuracy": 0.16240954250097275,
|
|
"num_tokens": 39366866.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 6.0279035568237305,
|
|
"epoch": 1.6992921436686184,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047127123953902907,
|
|
"loss": 5.8019,
|
|
"mean_token_accuracy": 0.1561470329761505,
|
|
"num_tokens": 39377303.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 6.094523334503174,
|
|
"epoch": 1.699729092021323,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004712560017052167,
|
|
"loss": 5.7729,
|
|
"mean_token_accuracy": 0.16477225571870804,
|
|
"num_tokens": 39387191.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 6.0450057029724125,
|
|
"epoch": 1.7001660403740277,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004712407601071114,
|
|
"loss": 5.8029,
|
|
"mean_token_accuracy": 0.1633811041712761,
|
|
"num_tokens": 39397416.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 6.122595977783203,
|
|
"epoch": 1.7006029887267324,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047122551474500555,
|
|
"loss": 5.8209,
|
|
"mean_token_accuracy": 0.15754495412111283,
|
|
"num_tokens": 39407855.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 6.141034698486328,
|
|
"epoch": 1.7010399370794373,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047121026561919137,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.15303106158971785,
|
|
"num_tokens": 39417735.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 6.131769800186158,
|
|
"epoch": 1.7014768854321418,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004711950127299616,
|
|
"loss": 5.8011,
|
|
"mean_token_accuracy": 0.15741673707962037,
|
|
"num_tokens": 39427641.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 6.0494544982910154,
|
|
"epoch": 1.7019138337848467,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004711797560776087,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.1707633838057518,
|
|
"num_tokens": 39437372.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 6.125210428237915,
|
|
"epoch": 1.7023507821375512,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00047116449566242516,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.16120726615190506,
|
|
"num_tokens": 39447800.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 6.1110752582550045,
|
|
"epoch": 1.7027877304902561,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004711492314847038,
|
|
"loss": 5.8512,
|
|
"mean_token_accuracy": 0.1558827742934227,
|
|
"num_tokens": 39457310.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 6.0604277610778805,
|
|
"epoch": 1.7032246788429608,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047113396354473753,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.15217647403478624,
|
|
"num_tokens": 39468579.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 6.14478440284729,
|
|
"epoch": 1.7036616271956655,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000471118691842819,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.15656710267066956,
|
|
"num_tokens": 39479027.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 6.078792572021484,
|
|
"epoch": 1.7040985755483702,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047110341637924126,
|
|
"loss": 5.7844,
|
|
"mean_token_accuracy": 0.1674623131752014,
|
|
"num_tokens": 39488651.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 6.016928243637085,
|
|
"epoch": 1.7045355239010749,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004710881371542972,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.1599768027663231,
|
|
"num_tokens": 39498633.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 6.077724409103394,
|
|
"epoch": 1.7049724722537796,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047107285416827984,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.16976630091667175,
|
|
"num_tokens": 39509351.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 6.059860515594482,
|
|
"epoch": 1.7054094206064843,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004710575674214824,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.17138244360685348,
|
|
"num_tokens": 39519821.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 6.08597354888916,
|
|
"epoch": 1.7058463689591892,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004710422769141982,
|
|
"loss": 5.8304,
|
|
"mean_token_accuracy": 0.1571711540222168,
|
|
"num_tokens": 39530040.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 6.1210408210754395,
|
|
"epoch": 1.7062833173118936,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004710269826467203,
|
|
"loss": 5.8161,
|
|
"mean_token_accuracy": 0.15810015946626663,
|
|
"num_tokens": 39540669.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 6.138817501068115,
|
|
"epoch": 1.7067202656645986,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047101168461934225,
|
|
"loss": 5.8071,
|
|
"mean_token_accuracy": 0.15717188715934755,
|
|
"num_tokens": 39550651.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 6.082176446914673,
|
|
"epoch": 1.707157214017303,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004709963828323573,
|
|
"loss": 5.8054,
|
|
"mean_token_accuracy": 0.14699531793594361,
|
|
"num_tokens": 39561748.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 6.058559131622315,
|
|
"epoch": 1.707594162370008,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004709810772860591,
|
|
"loss": 5.7454,
|
|
"mean_token_accuracy": 0.1647449776530266,
|
|
"num_tokens": 39571328.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 6.062957096099853,
|
|
"epoch": 1.7080311107227124,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000470965767980741,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.16907085478305817,
|
|
"num_tokens": 39581931.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 6.106709575653076,
|
|
"epoch": 1.7084680590754173,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047095045491669696,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.15409351736307145,
|
|
"num_tokens": 39592818.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 6.0509696960449215,
|
|
"epoch": 1.708905007428122,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047093513809422043,
|
|
"loss": 5.8039,
|
|
"mean_token_accuracy": 0.159418548643589,
|
|
"num_tokens": 39602867.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 6.10002760887146,
|
|
"epoch": 1.7093419557808267,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004709198175136053,
|
|
"loss": 5.8111,
|
|
"mean_token_accuracy": 0.15785362124443053,
|
|
"num_tokens": 39613185.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 6.111972522735596,
|
|
"epoch": 1.7097789041335314,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004709044931751454,
|
|
"loss": 5.7734,
|
|
"mean_token_accuracy": 0.16488297283649445,
|
|
"num_tokens": 39623262.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 6.152746105194092,
|
|
"epoch": 1.710215852486236,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004708891650791347,
|
|
"loss": 5.8064,
|
|
"mean_token_accuracy": 0.1590514674782753,
|
|
"num_tokens": 39633184.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 6.069907903671265,
|
|
"epoch": 1.710652800838941,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004708738332258671,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.15927487015724182,
|
|
"num_tokens": 39643778.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 6.024876642227173,
|
|
"epoch": 1.7110897491916455,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004708584976156368,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.16237813532352446,
|
|
"num_tokens": 39653519.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 6.065796899795532,
|
|
"epoch": 1.7115266975443504,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047084315824873793,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.15744800567626954,
|
|
"num_tokens": 39663824.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 6.117559957504272,
|
|
"epoch": 1.7119636458970549,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004708278151254646,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.15706327557563782,
|
|
"num_tokens": 39673631.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 6.20908145904541,
|
|
"epoch": 1.7124005942497598,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004708124682461112,
|
|
"loss": 5.9043,
|
|
"mean_token_accuracy": 0.1504289224743843,
|
|
"num_tokens": 39683118.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 6.143590927124023,
|
|
"epoch": 1.7128375426024642,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.00047079711761097197,
|
|
"loss": 5.8102,
|
|
"mean_token_accuracy": 0.15656877309083939,
|
|
"num_tokens": 39693947.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 6.1515895366668705,
|
|
"epoch": 1.7132744909551691,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004707817632203415,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.15703746378421785,
|
|
"num_tokens": 39703874.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 6.100787544250489,
|
|
"epoch": 1.7137114393078738,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047076640507451425,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.16517805308103561,
|
|
"num_tokens": 39714997.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 6.133305835723877,
|
|
"epoch": 1.7141483876605785,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004707510431737847,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.1590082861483097,
|
|
"num_tokens": 39726042.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 6.072143936157227,
|
|
"epoch": 1.7145853360132832,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004707356775184476,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.15487070977687836,
|
|
"num_tokens": 39736733.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 6.172472286224365,
|
|
"epoch": 1.715022284365988,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004707203081087977,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.14709966480731965,
|
|
"num_tokens": 39746811.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 6.170523166656494,
|
|
"epoch": 1.7154592327186926,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004707049349451297,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.15364097952842712,
|
|
"num_tokens": 39757371.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 6.069514322280884,
|
|
"epoch": 1.7158961810713973,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004706895580277384,
|
|
"loss": 5.7897,
|
|
"mean_token_accuracy": 0.1589108169078827,
|
|
"num_tokens": 39767430.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 6.100810766220093,
|
|
"epoch": 1.7163331294241022,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047067417735691884,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.16221286505460739,
|
|
"num_tokens": 39777270.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 6.0711774826049805,
|
|
"epoch": 1.7167700777768067,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004706587929329662,
|
|
"loss": 5.8088,
|
|
"mean_token_accuracy": 0.16016956865787507,
|
|
"num_tokens": 39787647.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 6.07291316986084,
|
|
"epoch": 1.7172070261295116,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047064340475617527,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.15247760564088822,
|
|
"num_tokens": 39797315.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 6.114043951034546,
|
|
"epoch": 1.717643974482216,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004706280128268413,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.16428982317447663,
|
|
"num_tokens": 39806625.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 6.085983753204346,
|
|
"epoch": 1.718080922834921,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004706126171452596,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.15948590785264968,
|
|
"num_tokens": 39818113.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 6.079538297653198,
|
|
"epoch": 1.7185178711876257,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004705972177117254,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.15430212914943695,
|
|
"num_tokens": 39827897.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 6.110194683074951,
|
|
"epoch": 1.7189548195403304,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047058181452653403,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.17461654245853425,
|
|
"num_tokens": 39837209.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 6.115376710891724,
|
|
"epoch": 1.719391767893035,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000470566407589981,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.16116696149110793,
|
|
"num_tokens": 39848023.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 6.088941621780395,
|
|
"epoch": 1.7198287162457397,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004705509969023618,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.15758197903633117,
|
|
"num_tokens": 39857992.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 6.10357027053833,
|
|
"epoch": 1.7202656645984444,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000470535582463972,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.15936634242534636,
|
|
"num_tokens": 39867927.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 6.083196306228638,
|
|
"epoch": 1.7207026129511491,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004705201642751073,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.16738648116588592,
|
|
"num_tokens": 39877327.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 6.135484075546264,
|
|
"epoch": 1.721139561303854,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047050474233606334,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.15428519546985625,
|
|
"num_tokens": 39887369.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 6.169403553009033,
|
|
"epoch": 1.7215765096565585,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000470489316647136,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.15813133269548416,
|
|
"num_tokens": 39897530.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 6.11139063835144,
|
|
"epoch": 1.7220134580092634,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004704738872086212,
|
|
"loss": 5.7868,
|
|
"mean_token_accuracy": 0.15899520814418794,
|
|
"num_tokens": 39907234.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 6.1176755905151365,
|
|
"epoch": 1.722450406361968,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004704584540208148,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.14965191781520842,
|
|
"num_tokens": 39917940.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 6.061934232711792,
|
|
"epoch": 1.7228873547146728,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004704430170840127,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.17103257924318313,
|
|
"num_tokens": 39927569.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 6.062588214874268,
|
|
"epoch": 1.7233243030673773,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004704275763985113,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.1563766971230507,
|
|
"num_tokens": 39938302.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 6.180183267593383,
|
|
"epoch": 1.7237612514200822,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004704121319646065,
|
|
"loss": 5.7812,
|
|
"mean_token_accuracy": 0.16535097658634185,
|
|
"num_tokens": 39948133.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 6.109431028366089,
|
|
"epoch": 1.7241981997727869,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047039668378259455,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.16346433609724045,
|
|
"num_tokens": 39958924.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 6.093697357177734,
|
|
"epoch": 1.7246351481254916,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047038123185277187,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.1630522519350052,
|
|
"num_tokens": 39968578.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 6.050151920318603,
|
|
"epoch": 1.7250720964781963,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00047036577617543484,
|
|
"loss": 5.75,
|
|
"mean_token_accuracy": 0.16871791779994966,
|
|
"num_tokens": 39978112.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 6.04722638130188,
|
|
"epoch": 1.725509044830901,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.00047035031675087983,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.15301677137613295,
|
|
"num_tokens": 39988071.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 6.165513944625855,
|
|
"epoch": 1.7259459931836056,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004703348535794034,
|
|
"loss": 5.8487,
|
|
"mean_token_accuracy": 0.15659181028604507,
|
|
"num_tokens": 39998112.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 6.10497145652771,
|
|
"epoch": 1.7263829415363103,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047031938666130206,
|
|
"loss": 5.8109,
|
|
"mean_token_accuracy": 0.1588652789592743,
|
|
"num_tokens": 40008869.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 6.133491516113281,
|
|
"epoch": 1.7268198898890152,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004703039159968726,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.16081639528274536,
|
|
"num_tokens": 40018711.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 6.127039194107056,
|
|
"epoch": 1.7272568382417197,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047028844158641166,
|
|
"loss": 5.8113,
|
|
"mean_token_accuracy": 0.1599874258041382,
|
|
"num_tokens": 40029209.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 6.124913072586059,
|
|
"epoch": 1.7276937865944246,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000470272963430216,
|
|
"loss": 5.7925,
|
|
"mean_token_accuracy": 0.15902002155780792,
|
|
"num_tokens": 40039071.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 6.07090311050415,
|
|
"epoch": 1.728130734947129,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004702574815285827,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.16340671926736833,
|
|
"num_tokens": 40049765.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 6.014097356796265,
|
|
"epoch": 1.728567683299834,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004702419958818085,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.16334608048200608,
|
|
"num_tokens": 40060020.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 6.131642818450928,
|
|
"epoch": 1.7290046316525387,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00047022650649019063,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.158540341258049,
|
|
"num_tokens": 40070081.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 6.169640636444091,
|
|
"epoch": 1.7294415800052434,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000470211013354026,
|
|
"loss": 5.8532,
|
|
"mean_token_accuracy": 0.15497546046972274,
|
|
"num_tokens": 40080532.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 6.08638219833374,
|
|
"epoch": 1.729878528357948,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004701955164736118,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.16103439629077912,
|
|
"num_tokens": 40091288.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 6.105102586746216,
|
|
"epoch": 1.7303154767106528,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004701800158492454,
|
|
"loss": 5.7804,
|
|
"mean_token_accuracy": 0.15797901302576065,
|
|
"num_tokens": 40100461.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 6.130492925643921,
|
|
"epoch": 1.7307524250633575,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000470164511481224,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.16075600385665895,
|
|
"num_tokens": 40109627.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 6.056947946548462,
|
|
"epoch": 1.7311893734160622,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000470149003369845,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.1607701726257801,
|
|
"num_tokens": 40119183.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 6.099366903305054,
|
|
"epoch": 1.731626321768767,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004701334915154058,
|
|
"loss": 5.8212,
|
|
"mean_token_accuracy": 0.1572314754128456,
|
|
"num_tokens": 40129569.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 6.15400652885437,
|
|
"epoch": 1.7320632701214715,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047011797591820404,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.161799655854702,
|
|
"num_tokens": 40139618.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 6.015894174575806,
|
|
"epoch": 1.7325002184741765,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047010245657853726,
|
|
"loss": 5.6981,
|
|
"mean_token_accuracy": 0.1670214295387268,
|
|
"num_tokens": 40149349.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 6.086278915405273,
|
|
"epoch": 1.732937166826881,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004700869334967031,
|
|
"loss": 5.8248,
|
|
"mean_token_accuracy": 0.15957651287317276,
|
|
"num_tokens": 40159161.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 6.098497915267944,
|
|
"epoch": 1.7333741151795858,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00047007140667299944,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.15914907604455947,
|
|
"num_tokens": 40169006.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 6.0696619033813475,
|
|
"epoch": 1.7338110635322905,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00047005587610772384,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.15699501782655717,
|
|
"num_tokens": 40179964.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 6.0839104652404785,
|
|
"epoch": 1.7342480118849952,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047004034180117446,
|
|
"loss": 5.8392,
|
|
"mean_token_accuracy": 0.15348096936941147,
|
|
"num_tokens": 40190598.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 6.194391250610352,
|
|
"epoch": 1.7346849602377,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.000470024803753649,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.15980052649974824,
|
|
"num_tokens": 40199537.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 6.089365434646607,
|
|
"epoch": 1.7351219085904046,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004700092619654456,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.1661269783973694,
|
|
"num_tokens": 40209167.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 6.115077066421509,
|
|
"epoch": 1.7355588569431093,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.0004699937164368625,
|
|
"loss": 5.7892,
|
|
"mean_token_accuracy": 0.16164094358682632,
|
|
"num_tokens": 40218738.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 6.13235993385315,
|
|
"epoch": 1.735995805295814,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004699781671681977,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.1674604207277298,
|
|
"num_tokens": 40227897.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 6.098686265945434,
|
|
"epoch": 1.736432753648519,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00046996261415974946,
|
|
"loss": 5.8531,
|
|
"mean_token_accuracy": 0.15154337733983994,
|
|
"num_tokens": 40238870.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 6.06974081993103,
|
|
"epoch": 1.7368697020012234,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00046994705741181615,
|
|
"loss": 5.7654,
|
|
"mean_token_accuracy": 0.1588371604681015,
|
|
"num_tokens": 40247832.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 6.133505582809448,
|
|
"epoch": 1.7373066503539283,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004699314969246961,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.16144887804985047,
|
|
"num_tokens": 40258696.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 6.135479545593261,
|
|
"epoch": 1.7377435987066328,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046991593269868776,
|
|
"loss": 5.7799,
|
|
"mean_token_accuracy": 0.16415976583957673,
|
|
"num_tokens": 40267767.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 6.124272394180298,
|
|
"epoch": 1.7381805470593377,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004699003647340898,
|
|
"loss": 5.8364,
|
|
"mean_token_accuracy": 0.1598043531179428,
|
|
"num_tokens": 40277813.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 6.1051390171051025,
|
|
"epoch": 1.7386174954120421,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00046988479303120066,
|
|
"loss": 5.8418,
|
|
"mean_token_accuracy": 0.16099047660827637,
|
|
"num_tokens": 40289031.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 6.124701452255249,
|
|
"epoch": 1.739054443764747,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046986921759031906,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.1616186574101448,
|
|
"num_tokens": 40299428.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 6.097035360336304,
|
|
"epoch": 1.7394913921174517,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004698536384117438,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.15883323699235916,
|
|
"num_tokens": 40308996.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 6.114970874786377,
|
|
"epoch": 1.7399283404701564,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00046983805549577365,
|
|
"loss": 5.8343,
|
|
"mean_token_accuracy": 0.16042929142713547,
|
|
"num_tokens": 40319753.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 6.181920528411865,
|
|
"epoch": 1.7403652888228611,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004698224688427074,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.14773821085691452,
|
|
"num_tokens": 40330729.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 6.173805475234985,
|
|
"epoch": 1.7408022371755658,
|
|
"grad_norm": 8.0,
|
|
"learning_rate": 0.0004698068784528442,
|
|
"loss": 5.8712,
|
|
"mean_token_accuracy": 0.15089573711156845,
|
|
"num_tokens": 40340246.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 6.140525674819946,
|
|
"epoch": 1.7412391855282705,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000469791284326483,
|
|
"loss": 5.7339,
|
|
"mean_token_accuracy": 0.15793695002794267,
|
|
"num_tokens": 40350099.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 6.124837207794189,
|
|
"epoch": 1.7416761338809752,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00046977568646392284,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.16175366342067718,
|
|
"num_tokens": 40360825.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 6.138683843612671,
|
|
"epoch": 1.74211308223368,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.000469760084865463,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.14274640902876853,
|
|
"num_tokens": 40371025.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 6.1342261791229244,
|
|
"epoch": 1.7425500305863846,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004697444795314027,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.16824313402175903,
|
|
"num_tokens": 40380338.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 6.112724494934082,
|
|
"epoch": 1.7429869789390895,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00046972887046204114,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.1612398386001587,
|
|
"num_tokens": 40391814.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 6.1076788902282715,
|
|
"epoch": 1.743423927291794,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046971325765767793,
|
|
"loss": 5.801,
|
|
"mean_token_accuracy": 0.15103936195373535,
|
|
"num_tokens": 40402013.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 6.149267053604126,
|
|
"epoch": 1.7438608756444989,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00046969764111861234,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.15401173681020736,
|
|
"num_tokens": 40412205.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 6.018934965133667,
|
|
"epoch": 1.7442978239972036,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00046968202084514405,
|
|
"loss": 5.7452,
|
|
"mean_token_accuracy": 0.17005741745233535,
|
|
"num_tokens": 40423212.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 6.087668323516846,
|
|
"epoch": 1.7447347723499083,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004696663968375725,
|
|
"loss": 5.7369,
|
|
"mean_token_accuracy": 0.15847148001194,
|
|
"num_tokens": 40433272.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 6.170419836044312,
|
|
"epoch": 1.745171720702613,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004696507690961975,
|
|
"loss": 5.889,
|
|
"mean_token_accuracy": 0.15732436180114745,
|
|
"num_tokens": 40443931.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 6.11259183883667,
|
|
"epoch": 1.7456086690553176,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004696351376213188,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.16061891317367555,
|
|
"num_tokens": 40453008.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 6.029903888702393,
|
|
"epoch": 1.7460456174080223,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000469619502413236,
|
|
"loss": 5.8557,
|
|
"mean_token_accuracy": 0.15949919819831848,
|
|
"num_tokens": 40463081.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 6.105974817276001,
|
|
"epoch": 1.746482565760727,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004696038634722493,
|
|
"loss": 5.6849,
|
|
"mean_token_accuracy": 0.16437639892101288,
|
|
"num_tokens": 40472390.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 6.113411855697632,
|
|
"epoch": 1.746919514113432,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.00046958822079865855,
|
|
"loss": 5.8554,
|
|
"mean_token_accuracy": 0.1559371531009674,
|
|
"num_tokens": 40483068.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 6.165650415420532,
|
|
"epoch": 1.7473564624661364,
|
|
"grad_norm": 8.625,
|
|
"learning_rate": 0.0004695725743927637,
|
|
"loss": 5.8203,
|
|
"mean_token_accuracy": 0.16495466828346253,
|
|
"num_tokens": 40493125.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 6.093226909637451,
|
|
"epoch": 1.7477934108188413,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00046955692425486496,
|
|
"loss": 5.8068,
|
|
"mean_token_accuracy": 0.1584664985537529,
|
|
"num_tokens": 40502618.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 6.1111351490020756,
|
|
"epoch": 1.7482303591715458,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004695412703852624,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.16017089933156967,
|
|
"num_tokens": 40512878.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 6.048735857009888,
|
|
"epoch": 1.7486673075242507,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004695256127842563,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.15966059416532516,
|
|
"num_tokens": 40521983.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 6.018918180465699,
|
|
"epoch": 1.7491042558769554,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00046950995145214716,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.1607269287109375,
|
|
"num_tokens": 40533126.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 6.080697250366211,
|
|
"epoch": 1.74954120422966,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004694942863892352,
|
|
"loss": 5.7748,
|
|
"mean_token_accuracy": 0.16380762457847595,
|
|
"num_tokens": 40543321.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 6.116272592544556,
|
|
"epoch": 1.7499781525823648,
|
|
"grad_norm": 5.4375,
|
|
"learning_rate": 0.0004694786175958209,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.162904292345047,
|
|
"num_tokens": 40554208.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 6.147489881515503,
|
|
"epoch": 1.7504151009350695,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00046946294507220477,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.15288180112838745,
|
|
"num_tokens": 40563365.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.9902637004852295,
|
|
"epoch": 1.7508520492877742,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004694472688186874,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.16462101489305497,
|
|
"num_tokens": 40573765.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 6.040267848968506,
|
|
"epoch": 1.7512889976404789,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004694315888355697,
|
|
"loss": 5.7955,
|
|
"mean_token_accuracy": 0.16260012239217758,
|
|
"num_tokens": 40583786.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 6.088585710525512,
|
|
"epoch": 1.7517259459931838,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00046941590512315215,
|
|
"loss": 5.8312,
|
|
"mean_token_accuracy": 0.15657771080732347,
|
|
"num_tokens": 40593686.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 6.089376735687256,
|
|
"epoch": 1.7521628943458882,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004694002176817356,
|
|
"loss": 5.7958,
|
|
"mean_token_accuracy": 0.15806715488433837,
|
|
"num_tokens": 40604326.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 6.134919023513794,
|
|
"epoch": 1.7525998426985931,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004693845265116211,
|
|
"loss": 5.7826,
|
|
"mean_token_accuracy": 0.15690571218729019,
|
|
"num_tokens": 40613683.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 6.098470735549927,
|
|
"epoch": 1.7530367910512976,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00046936883161310944,
|
|
"loss": 5.8124,
|
|
"mean_token_accuracy": 0.16023394614458084,
|
|
"num_tokens": 40623675.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 6.1270934581756595,
|
|
"epoch": 1.7534737394040025,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00046935313298650185,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.15611762255430223,
|
|
"num_tokens": 40634006.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 6.041053342819214,
|
|
"epoch": 1.753910687756707,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.00046933743063209927,
|
|
"loss": 5.697,
|
|
"mean_token_accuracy": 0.17064322680234909,
|
|
"num_tokens": 40643175.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 6.15368161201477,
|
|
"epoch": 1.754347636109412,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00046932172455020296,
|
|
"loss": 5.8431,
|
|
"mean_token_accuracy": 0.14859526455402375,
|
|
"num_tokens": 40653447.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 6.164422464370728,
|
|
"epoch": 1.7547845844621166,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004693060147411141,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.1601276680827141,
|
|
"num_tokens": 40663499.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 6.063589191436767,
|
|
"epoch": 1.7552215328148213,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004692903012051341,
|
|
"loss": 5.7773,
|
|
"mean_token_accuracy": 0.16496762931346892,
|
|
"num_tokens": 40672943.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 6.052312898635864,
|
|
"epoch": 1.755658481167526,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004692745839425643,
|
|
"loss": 5.8293,
|
|
"mean_token_accuracy": 0.1603731095790863,
|
|
"num_tokens": 40683659.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 6.176554393768311,
|
|
"epoch": 1.7560954295202307,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004692588629537062,
|
|
"loss": 5.8437,
|
|
"mean_token_accuracy": 0.15700934082269669,
|
|
"num_tokens": 40693829.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 6.1258251667022705,
|
|
"epoch": 1.7565323778729354,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004692431382388613,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.15558656603097915,
|
|
"num_tokens": 40704717.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 6.1134437084197994,
|
|
"epoch": 1.75696932622564,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.00046922740979833135,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.15428268760442734,
|
|
"num_tokens": 40714970.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 6.109387731552124,
|
|
"epoch": 1.757406274578345,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00046921167763241777,
|
|
"loss": 5.7751,
|
|
"mean_token_accuracy": 0.16221875548362732,
|
|
"num_tokens": 40723664.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 6.10299654006958,
|
|
"epoch": 1.7578432229310494,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00046919594174142247,
|
|
"loss": 5.7692,
|
|
"mean_token_accuracy": 0.15864422172307968,
|
|
"num_tokens": 40733735.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 6.117214059829712,
|
|
"epoch": 1.7582801712837544,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00046918020212564725,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.15609552711248398,
|
|
"num_tokens": 40743699.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 6.076550769805908,
|
|
"epoch": 1.7587171196364588,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.000469164458785394,
|
|
"loss": 5.8734,
|
|
"mean_token_accuracy": 0.1531803399324417,
|
|
"num_tokens": 40754553.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 6.1531970500946045,
|
|
"epoch": 1.7591540679891637,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00046914871172096473,
|
|
"loss": 5.832,
|
|
"mean_token_accuracy": 0.15300681218504905,
|
|
"num_tokens": 40764660.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 6.124754905700684,
|
|
"epoch": 1.7595910163418684,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004691329609326614,
|
|
"loss": 5.6663,
|
|
"mean_token_accuracy": 0.17002324759960175,
|
|
"num_tokens": 40774237.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 6.064556074142456,
|
|
"epoch": 1.7600279646945731,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004691172064207862,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.1665944427251816,
|
|
"num_tokens": 40783608.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 6.151745176315307,
|
|
"epoch": 1.7604649130472778,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004691014481856412,
|
|
"loss": 5.8235,
|
|
"mean_token_accuracy": 0.15317616909742354,
|
|
"num_tokens": 40793987.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 6.174080038070679,
|
|
"epoch": 1.7609018613999825,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00046908568622752874,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.1541568398475647,
|
|
"num_tokens": 40805600.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 6.106844186782837,
|
|
"epoch": 1.7613388097526872,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046906992054675115,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.1637753963470459,
|
|
"num_tokens": 40815252.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 6.04176287651062,
|
|
"epoch": 1.7617757581053919,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004690541511436107,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.16401199549436568,
|
|
"num_tokens": 40825945.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 6.106495428085327,
|
|
"epoch": 1.7622127064580968,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004690383780184101,
|
|
"loss": 5.8429,
|
|
"mean_token_accuracy": 0.15902678966522216,
|
|
"num_tokens": 40835811.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 6.141741943359375,
|
|
"epoch": 1.7626496548108013,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00046902260117145163,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.15804900377988815,
|
|
"num_tokens": 40845088.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 6.0984584331512455,
|
|
"epoch": 1.7630866031635062,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000469006820603038,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.157698193192482,
|
|
"num_tokens": 40854703.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 6.179224252700806,
|
|
"epoch": 1.7635235515162107,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00046899103631347196,
|
|
"loss": 5.8021,
|
|
"mean_token_accuracy": 0.15572601705789565,
|
|
"num_tokens": 40865056.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 6.078614711761475,
|
|
"epoch": 1.7639604998689156,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004689752483030561,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.16415783613920212,
|
|
"num_tokens": 40874355.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 6.075523948669433,
|
|
"epoch": 1.7643974482216203,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004689594565720934,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.1595476284623146,
|
|
"num_tokens": 40884329.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 6.078005838394165,
|
|
"epoch": 1.764834396574325,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004689436611208867,
|
|
"loss": 5.7986,
|
|
"mean_token_accuracy": 0.1628919407725334,
|
|
"num_tokens": 40894702.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 6.1492271900177,
|
|
"epoch": 1.7652713449270296,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00046892786194973897,
|
|
"loss": 5.7791,
|
|
"mean_token_accuracy": 0.15836129039525987,
|
|
"num_tokens": 40905467.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 6.12502088546753,
|
|
"epoch": 1.7657082932797343,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004689120590589532,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.15785814374685286,
|
|
"num_tokens": 40915915.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 6.054952096939087,
|
|
"epoch": 1.766145241632439,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004688962524488325,
|
|
"loss": 5.7665,
|
|
"mean_token_accuracy": 0.16187303513288498,
|
|
"num_tokens": 40925941.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 6.108825159072876,
|
|
"epoch": 1.7665821899851437,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004688804421196801,
|
|
"loss": 5.8356,
|
|
"mean_token_accuracy": 0.15991260409355162,
|
|
"num_tokens": 40935831.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 6.034203100204468,
|
|
"epoch": 1.7670191383378486,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00046886462807179926,
|
|
"loss": 5.7838,
|
|
"mean_token_accuracy": 0.16537935733795167,
|
|
"num_tokens": 40945341.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 6.136110496520996,
|
|
"epoch": 1.767456086690553,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004688488103054931,
|
|
"loss": 5.8317,
|
|
"mean_token_accuracy": 0.1633661061525345,
|
|
"num_tokens": 40955759.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 6.170142745971679,
|
|
"epoch": 1.767893035043258,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004688329888210654,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.1559879496693611,
|
|
"num_tokens": 40966184.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 6.114583969116211,
|
|
"epoch": 1.7683299833959625,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004688171636188194,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.16104481220245362,
|
|
"num_tokens": 40975797.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 6.142330169677734,
|
|
"epoch": 1.7687669317486674,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004688013346990585,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.1605291798710823,
|
|
"num_tokens": 40985830.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 6.036077928543091,
|
|
"epoch": 1.7692038801013719,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00046878550206208656,
|
|
"loss": 5.7106,
|
|
"mean_token_accuracy": 0.16255198419094086,
|
|
"num_tokens": 40995692.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 6.117742252349854,
|
|
"epoch": 1.7696408284540768,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004687696657082071,
|
|
"loss": 5.8295,
|
|
"mean_token_accuracy": 0.1577209010720253,
|
|
"num_tokens": 41005506.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 6.119452285766601,
|
|
"epoch": 1.7700777768067815,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00046875382563772396,
|
|
"loss": 5.7293,
|
|
"mean_token_accuracy": 0.16344009190797806,
|
|
"num_tokens": 41014944.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 6.145107364654541,
|
|
"epoch": 1.7705147251594862,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00046873798185094093,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.15175872445106506,
|
|
"num_tokens": 41025424.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 6.010427761077881,
|
|
"epoch": 1.7709516735121908,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004687221343481618,
|
|
"loss": 5.7275,
|
|
"mean_token_accuracy": 0.1676472619175911,
|
|
"num_tokens": 41035817.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 6.0415114402771,
|
|
"epoch": 1.7713886218648955,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046870628312969064,
|
|
"loss": 5.7668,
|
|
"mean_token_accuracy": 0.16444457173347474,
|
|
"num_tokens": 41045730.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 6.190864324569702,
|
|
"epoch": 1.7718255702176002,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004686904281958315,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.146004269272089,
|
|
"num_tokens": 41057921.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 6.196317291259765,
|
|
"epoch": 1.772262518570305,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00046867456954688847,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.16148425191640853,
|
|
"num_tokens": 41068879.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 6.098105239868164,
|
|
"epoch": 1.7726994669230098,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004686587071831657,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.15764899104833602,
|
|
"num_tokens": 41079443.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 6.100146055221558,
|
|
"epoch": 1.7731364152757143,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004686428411049675,
|
|
"loss": 5.8421,
|
|
"mean_token_accuracy": 0.15223202258348464,
|
|
"num_tokens": 41089932.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 6.190094470977783,
|
|
"epoch": 1.7735733636284192,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004686269713125981,
|
|
"loss": 5.8346,
|
|
"mean_token_accuracy": 0.15577563941478728,
|
|
"num_tokens": 41100412.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 6.152592897415161,
|
|
"epoch": 1.7740103119811237,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004686110978063619,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.15591662526130676,
|
|
"num_tokens": 41110830.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 6.08135666847229,
|
|
"epoch": 1.7744472603338286,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004685952205865634,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.15901214629411697,
|
|
"num_tokens": 41120662.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 6.03677077293396,
|
|
"epoch": 1.7748842086865333,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.00046857933965350714,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.16290881484746933,
|
|
"num_tokens": 41130523.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 6.153215599060059,
|
|
"epoch": 1.775321157039238,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004685634550074977,
|
|
"loss": 5.8722,
|
|
"mean_token_accuracy": 0.1608460485935211,
|
|
"num_tokens": 41141659.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 6.190534353256226,
|
|
"epoch": 1.7757581053919427,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004685475666488398,
|
|
"loss": 5.9061,
|
|
"mean_token_accuracy": 0.1462700441479683,
|
|
"num_tokens": 41151038.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 6.113929414749146,
|
|
"epoch": 1.7761950537446474,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00046853167457783815,
|
|
"loss": 5.8543,
|
|
"mean_token_accuracy": 0.16006929129362107,
|
|
"num_tokens": 41161888.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 6.189467811584473,
|
|
"epoch": 1.776632002097352,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004685157787947975,
|
|
"loss": 5.8947,
|
|
"mean_token_accuracy": 0.1520603619515896,
|
|
"num_tokens": 41172722.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 6.119915103912353,
|
|
"epoch": 1.7770689504500568,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004684998793000229,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.16104741841554643,
|
|
"num_tokens": 41181716.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 6.0875872611999515,
|
|
"epoch": 1.7775058988027617,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004684839760938193,
|
|
"loss": 5.849,
|
|
"mean_token_accuracy": 0.15372057110071183,
|
|
"num_tokens": 41192903.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 6.08648681640625,
|
|
"epoch": 1.7779428471554661,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00046846806917649145,
|
|
"loss": 5.8064,
|
|
"mean_token_accuracy": 0.1587863400578499,
|
|
"num_tokens": 41203283.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 6.144145202636719,
|
|
"epoch": 1.778379795508171,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004684521585483447,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.1550808683037758,
|
|
"num_tokens": 41213615.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 6.129676866531372,
|
|
"epoch": 1.7788167438608755,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00046843624420968435,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.1703510418534279,
|
|
"num_tokens": 41222705.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 6.0233738899230955,
|
|
"epoch": 1.7792536922135804,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004684203261608153,
|
|
"loss": 5.7619,
|
|
"mean_token_accuracy": 0.1642073407769203,
|
|
"num_tokens": 41233201.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 6.09271092414856,
|
|
"epoch": 1.7796906405662851,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004684044044020431,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.1556283265352249,
|
|
"num_tokens": 41243088.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 6.176855421066284,
|
|
"epoch": 1.7801275889189898,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004683884789336731,
|
|
"loss": 5.8311,
|
|
"mean_token_accuracy": 0.1534987837076187,
|
|
"num_tokens": 41253009.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 6.109649515151977,
|
|
"epoch": 1.7805645372716945,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046837254975601073,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.16142655462026595,
|
|
"num_tokens": 41262209.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 6.1149022579193115,
|
|
"epoch": 1.7810014856243992,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00046835661686936154,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.16219808012247086,
|
|
"num_tokens": 41272762.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 6.1016394138336185,
|
|
"epoch": 1.7814384339771039,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00046834068027403115,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.1537313625216484,
|
|
"num_tokens": 41284306.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 6.140647554397583,
|
|
"epoch": 1.7818753823298086,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00046832473997032514,
|
|
"loss": 5.8428,
|
|
"mean_token_accuracy": 0.15506634265184402,
|
|
"num_tokens": 41295211.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 6.09630970954895,
|
|
"epoch": 1.7823123306825135,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004683087959585493,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.1630358673632145,
|
|
"num_tokens": 41303773.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 6.034410905838013,
|
|
"epoch": 1.782749279035218,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004682928482390095,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.16355063617229462,
|
|
"num_tokens": 41313536.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 6.161115884780884,
|
|
"epoch": 1.7831862273879229,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046827689681201164,
|
|
"loss": 5.8195,
|
|
"mean_token_accuracy": 0.1601507380604744,
|
|
"num_tokens": 41323831.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 6.147857761383056,
|
|
"epoch": 1.7836231757406273,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004682609416778615,
|
|
"loss": 5.808,
|
|
"mean_token_accuracy": 0.16318029016256333,
|
|
"num_tokens": 41334295.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 6.079022693634033,
|
|
"epoch": 1.7840601240933323,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004682449828368653,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.15694925785064698,
|
|
"num_tokens": 41344672.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 6.1396078109741214,
|
|
"epoch": 1.7844970724460367,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004682290202893291,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.15283788591623307,
|
|
"num_tokens": 41355108.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 6.275498867034912,
|
|
"epoch": 1.7849340207987416,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00046821305403555905,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.1496388629078865,
|
|
"num_tokens": 41366277.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 6.143874597549439,
|
|
"epoch": 1.7853709691514463,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00046819708407586135,
|
|
"loss": 5.7921,
|
|
"mean_token_accuracy": 0.16322183907032012,
|
|
"num_tokens": 41374757.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 6.081591987609864,
|
|
"epoch": 1.785807917504151,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004681811104105423,
|
|
"loss": 5.7979,
|
|
"mean_token_accuracy": 0.16126659363508225,
|
|
"num_tokens": 41384883.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 6.1282867908477785,
|
|
"epoch": 1.7862448658568557,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004681651330399084,
|
|
"loss": 5.8241,
|
|
"mean_token_accuracy": 0.15773673504590988,
|
|
"num_tokens": 41396492.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 6.1116548538208,
|
|
"epoch": 1.7866818142095604,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000468149151964266,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.15950769037008286,
|
|
"num_tokens": 41406217.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 6.08352632522583,
|
|
"epoch": 1.787118762562265,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004681331671839217,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.16734521239995956,
|
|
"num_tokens": 41415895.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 6.1378966808319095,
|
|
"epoch": 1.7875557109149698,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00046811717869918196,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.15817746967077256,
|
|
"num_tokens": 41426021.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 6.145797538757324,
|
|
"epoch": 1.7879926592676747,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004681011865103536,
|
|
"loss": 5.7852,
|
|
"mean_token_accuracy": 0.15867676734924316,
|
|
"num_tokens": 41434656.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 6.0983133792877195,
|
|
"epoch": 1.7884296076203792,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00046808519061774324,
|
|
"loss": 5.8081,
|
|
"mean_token_accuracy": 0.1602679818868637,
|
|
"num_tokens": 41443940.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 6.095771837234497,
|
|
"epoch": 1.788866555973084,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00046806919102165785,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.15755071491003036,
|
|
"num_tokens": 41454907.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 6.12061333656311,
|
|
"epoch": 1.7893035043257886,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004680531877224042,
|
|
"loss": 5.7317,
|
|
"mean_token_accuracy": 0.16473085135221482,
|
|
"num_tokens": 41464248.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 6.107315635681152,
|
|
"epoch": 1.7897404526784935,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004680371807202892,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.16742003262042998,
|
|
"num_tokens": 41475192.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 6.112410163879394,
|
|
"epoch": 1.7901774010311982,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00046802117001561996,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.14819685891270637,
|
|
"num_tokens": 41484753.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 6.100326347351074,
|
|
"epoch": 1.7906143493839028,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046800515560870346,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.14722870737314225,
|
|
"num_tokens": 41495885.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 6.2265296459198,
|
|
"epoch": 1.7910512977366075,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00046798913749984694,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.1564646005630493,
|
|
"num_tokens": 41506330.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 6.090691995620728,
|
|
"epoch": 1.7914882460893122,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004679731156893577,
|
|
"loss": 5.8006,
|
|
"mean_token_accuracy": 0.16281561702489852,
|
|
"num_tokens": 41515850.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 6.097841072082519,
|
|
"epoch": 1.791925194442017,
|
|
"grad_norm": 7.53125,
|
|
"learning_rate": 0.000467957090177543,
|
|
"loss": 5.8068,
|
|
"mean_token_accuracy": 0.16149195283651352,
|
|
"num_tokens": 41525910.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 6.12894926071167,
|
|
"epoch": 1.7923621427947216,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00046794106096471015,
|
|
"loss": 5.7294,
|
|
"mean_token_accuracy": 0.16208693981170655,
|
|
"num_tokens": 41536417.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 6.085343742370606,
|
|
"epoch": 1.7927990911474265,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004679250280511667,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.15372299104928971,
|
|
"num_tokens": 41547215.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 6.101957893371582,
|
|
"epoch": 1.793236039500131,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004679089914372201,
|
|
"loss": 5.8324,
|
|
"mean_token_accuracy": 0.1555679500102997,
|
|
"num_tokens": 41556036.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 6.112474632263184,
|
|
"epoch": 1.793672987852836,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00046789295112317796,
|
|
"loss": 5.8195,
|
|
"mean_token_accuracy": 0.16118495017290116,
|
|
"num_tokens": 41565534.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 6.118927335739135,
|
|
"epoch": 1.7941099362055404,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004678769071093479,
|
|
"loss": 5.7762,
|
|
"mean_token_accuracy": 0.15942887365818023,
|
|
"num_tokens": 41576150.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 6.055995988845825,
|
|
"epoch": 1.7945468845582453,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046786085939603785,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.16656645238399506,
|
|
"num_tokens": 41585248.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 6.102273845672608,
|
|
"epoch": 1.7949838329109498,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004678448079835552,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.15687010139226915,
|
|
"num_tokens": 41595215.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 6.20481424331665,
|
|
"epoch": 1.7954207812636547,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004678287528722083,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.1566680058836937,
|
|
"num_tokens": 41605268.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 6.0769875049591064,
|
|
"epoch": 1.7958577296163594,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004678126940623048,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.16630046516656877,
|
|
"num_tokens": 41614554.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 6.060003280639648,
|
|
"epoch": 1.796294677969064,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00046779663155415287,
|
|
"loss": 5.8423,
|
|
"mean_token_accuracy": 0.16168198585510254,
|
|
"num_tokens": 41624839.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 6.028343343734742,
|
|
"epoch": 1.7967316263217687,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004677805653480604,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.17468472868204116,
|
|
"num_tokens": 41634577.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 6.154319858551025,
|
|
"epoch": 1.7971685746744734,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00046776449544433575,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.15375510305166246,
|
|
"num_tokens": 41645213.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 6.152465438842773,
|
|
"epoch": 1.7976055230271784,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000467748421843287,
|
|
"loss": 5.7128,
|
|
"mean_token_accuracy": 0.16934482455253602,
|
|
"num_tokens": 41655160.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 6.109637594223022,
|
|
"epoch": 1.7980424713798828,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046773234454522265,
|
|
"loss": 5.7927,
|
|
"mean_token_accuracy": 0.15572577118873596,
|
|
"num_tokens": 41665861.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 6.1086390018463135,
|
|
"epoch": 1.7984794197325877,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00046771626355045085,
|
|
"loss": 5.8102,
|
|
"mean_token_accuracy": 0.16062305569648744,
|
|
"num_tokens": 41676699.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 6.127663087844849,
|
|
"epoch": 1.7989163680852922,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004677001788592801,
|
|
"loss": 5.839,
|
|
"mean_token_accuracy": 0.16055029779672622,
|
|
"num_tokens": 41688162.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 6.151435804367066,
|
|
"epoch": 1.7993533164379971,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000467684090472019,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.15665507316589355,
|
|
"num_tokens": 41698088.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 6.134163761138916,
|
|
"epoch": 1.7997902647907016,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004676679983889761,
|
|
"loss": 5.7751,
|
|
"mean_token_accuracy": 0.16672883033752442,
|
|
"num_tokens": 41707446.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 6.117214727401733,
|
|
"epoch": 1.8002272131434065,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00046765190261046,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.15792782604694366,
|
|
"num_tokens": 41716388.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 6.152116441726685,
|
|
"epoch": 1.8006641614961112,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004676358031367795,
|
|
"loss": 5.8478,
|
|
"mean_token_accuracy": 0.161505389213562,
|
|
"num_tokens": 41726328.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 6.130058240890503,
|
|
"epoch": 1.8011011098488159,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00046761969996824326,
|
|
"loss": 5.786,
|
|
"mean_token_accuracy": 0.15552452951669693,
|
|
"num_tokens": 41736128.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 6.059102201461792,
|
|
"epoch": 1.8015380582015206,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004676035931051604,
|
|
"loss": 5.7392,
|
|
"mean_token_accuracy": 0.1600651666522026,
|
|
"num_tokens": 41746316.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 6.154334640502929,
|
|
"epoch": 1.8019750065542253,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.00046758748254783957,
|
|
"loss": 5.7031,
|
|
"mean_token_accuracy": 0.16528104543685912,
|
|
"num_tokens": 41756015.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 6.1261743068695065,
|
|
"epoch": 1.80241195490693,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00046757136829658996,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.16703375279903412,
|
|
"num_tokens": 41766360.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 6.138262987136841,
|
|
"epoch": 1.8028489032596346,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.00046755525035172056,
|
|
"loss": 5.8596,
|
|
"mean_token_accuracy": 0.155458702147007,
|
|
"num_tokens": 41776640.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 6.113243770599365,
|
|
"epoch": 1.8032858516123396,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004675391287135406,
|
|
"loss": 5.8368,
|
|
"mean_token_accuracy": 0.16024687588214875,
|
|
"num_tokens": 41787329.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 6.127006244659424,
|
|
"epoch": 1.803722799965044,
|
|
"grad_norm": 6.3125,
|
|
"learning_rate": 0.00046752300338235924,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.15542975589632987,
|
|
"num_tokens": 41797890.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 6.138513469696045,
|
|
"epoch": 1.804159748317749,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004675068743584858,
|
|
"loss": 5.84,
|
|
"mean_token_accuracy": 0.15307705402374266,
|
|
"num_tokens": 41808845.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 6.190570974349976,
|
|
"epoch": 1.8045966966704534,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004674907416422297,
|
|
"loss": 5.8173,
|
|
"mean_token_accuracy": 0.15928134173154831,
|
|
"num_tokens": 41819499.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 6.091172552108764,
|
|
"epoch": 1.8050336450231583,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004674746052339002,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.15936562418937683,
|
|
"num_tokens": 41827998.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 6.114912319183349,
|
|
"epoch": 1.805470593375863,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00046745846513380704,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.15339112058281898,
|
|
"num_tokens": 41839610.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 6.187399244308471,
|
|
"epoch": 1.8059075417285677,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00046744232134225954,
|
|
"loss": 5.7874,
|
|
"mean_token_accuracy": 0.1547248400747776,
|
|
"num_tokens": 41850111.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 6.133647871017456,
|
|
"epoch": 1.8063444900812724,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004674261738595676,
|
|
"loss": 5.7727,
|
|
"mean_token_accuracy": 0.15688270926475525,
|
|
"num_tokens": 41859843.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 6.102827501296997,
|
|
"epoch": 1.806781438433977,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00046741002268604073,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.1591956213116646,
|
|
"num_tokens": 41868864.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 6.1106727600097654,
|
|
"epoch": 1.8072183867866818,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00046739386782198883,
|
|
"loss": 5.8242,
|
|
"mean_token_accuracy": 0.15824078321456908,
|
|
"num_tokens": 41878274.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 6.124302911758423,
|
|
"epoch": 1.8076553351393865,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00046737770926772175,
|
|
"loss": 5.7774,
|
|
"mean_token_accuracy": 0.15494089871644973,
|
|
"num_tokens": 41888005.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 6.178764772415161,
|
|
"epoch": 1.8080922834920914,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004673615470235494,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.15514364540576936,
|
|
"num_tokens": 41897415.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 6.115621042251587,
|
|
"epoch": 1.8085292318447959,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004673453810897817,
|
|
"loss": 5.7573,
|
|
"mean_token_accuracy": 0.1636564776301384,
|
|
"num_tokens": 41907021.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 6.111355829238891,
|
|
"epoch": 1.8089661801975008,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004673292114667289,
|
|
"loss": 5.8536,
|
|
"mean_token_accuracy": 0.152622027695179,
|
|
"num_tokens": 41918358.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 6.199451732635498,
|
|
"epoch": 1.8094031285502052,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00046731303815470104,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.14563099816441535,
|
|
"num_tokens": 41929311.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 6.1681983947753904,
|
|
"epoch": 1.8098400769029102,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046729686115400826,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.15910544097423554,
|
|
"num_tokens": 41939623.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 6.062235879898071,
|
|
"epoch": 1.8102770252556146,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004672806804649611,
|
|
"loss": 5.79,
|
|
"mean_token_accuracy": 0.16066670417785645,
|
|
"num_tokens": 41949650.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 6.136530256271362,
|
|
"epoch": 1.8107139736083195,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.00046726449608786957,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.15900637358427047,
|
|
"num_tokens": 41960262.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 6.169749546051025,
|
|
"epoch": 1.8111509219610242,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004672483080230443,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.15270697921514512,
|
|
"num_tokens": 41969874.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 6.083888387680053,
|
|
"epoch": 1.811587870313729,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00046723211627079577,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.15930332541465758,
|
|
"num_tokens": 41978810.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 6.055484867095947,
|
|
"epoch": 1.8120248186664336,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004672159208314344,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.15917766243219375,
|
|
"num_tokens": 41988785.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 6.085396146774292,
|
|
"epoch": 1.8124617670191383,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004671997217052711,
|
|
"loss": 5.8294,
|
|
"mean_token_accuracy": 0.16241493076086044,
|
|
"num_tokens": 41998698.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 6.107514905929565,
|
|
"epoch": 1.812898715371843,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004671835188926164,
|
|
"loss": 5.7815,
|
|
"mean_token_accuracy": 0.1644461750984192,
|
|
"num_tokens": 42009082.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 6.1661248207092285,
|
|
"epoch": 1.8133356637245477,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004671673123937811,
|
|
"loss": 5.8053,
|
|
"mean_token_accuracy": 0.156510129570961,
|
|
"num_tokens": 42019960.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 6.071886777877808,
|
|
"epoch": 1.8137726120772526,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000467151102209076,
|
|
"loss": 5.7171,
|
|
"mean_token_accuracy": 0.16496340185403824,
|
|
"num_tokens": 42028799.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 6.058169794082642,
|
|
"epoch": 1.814209560429957,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00046713488833881214,
|
|
"loss": 5.8008,
|
|
"mean_token_accuracy": 0.15486937165260314,
|
|
"num_tokens": 42038967.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 6.094454908370972,
|
|
"epoch": 1.814646508782662,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00046711867078330047,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.16041286438703536,
|
|
"num_tokens": 42049982.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 6.12947187423706,
|
|
"epoch": 1.8150834571353665,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.00046710244954285184,
|
|
"loss": 5.8831,
|
|
"mean_token_accuracy": 0.15631230175495148,
|
|
"num_tokens": 42059835.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 6.086891078948975,
|
|
"epoch": 1.8155204054880714,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046708622461777774,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.16795631349086762,
|
|
"num_tokens": 42069339.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 6.078075170516968,
|
|
"epoch": 1.815957353840776,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004670699960083892,
|
|
"loss": 5.7284,
|
|
"mean_token_accuracy": 0.16038838326931,
|
|
"num_tokens": 42080618.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 6.147924709320068,
|
|
"epoch": 1.8163943021934807,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004670537637149974,
|
|
"loss": 5.8712,
|
|
"mean_token_accuracy": 0.15019579082727433,
|
|
"num_tokens": 42091458.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 6.135207605361939,
|
|
"epoch": 1.8168312505461854,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046703752773791387,
|
|
"loss": 5.8832,
|
|
"mean_token_accuracy": 0.15260590761899948,
|
|
"num_tokens": 42102515.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 6.1127361297607425,
|
|
"epoch": 1.8172681988988901,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004670212880774499,
|
|
"loss": 5.79,
|
|
"mean_token_accuracy": 0.1580725595355034,
|
|
"num_tokens": 42113853.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 6.13453516960144,
|
|
"epoch": 1.8177051472515948,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000467005044733917,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.15106360316276551,
|
|
"num_tokens": 42123101.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 6.1749011993408205,
|
|
"epoch": 1.8181420956042995,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004669887977076267,
|
|
"loss": 5.8111,
|
|
"mean_token_accuracy": 0.15376880913972854,
|
|
"num_tokens": 42133051.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 6.115439319610596,
|
|
"epoch": 1.8185790439570044,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00046697254699889064,
|
|
"loss": 5.8066,
|
|
"mean_token_accuracy": 0.1609758272767067,
|
|
"num_tokens": 42142705.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 6.093760919570923,
|
|
"epoch": 1.819015992309709,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00046695629260802064,
|
|
"loss": 5.7881,
|
|
"mean_token_accuracy": 0.1603650778532028,
|
|
"num_tokens": 42152399.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 6.1325829982757565,
|
|
"epoch": 1.8194529406624138,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004669400345353283,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.15808191448450087,
|
|
"num_tokens": 42162651.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 6.026057291030884,
|
|
"epoch": 1.8198898890151183,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004669237727811255,
|
|
"loss": 5.7018,
|
|
"mean_token_accuracy": 0.16397202312946318,
|
|
"num_tokens": 42172595.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 6.091785955429077,
|
|
"epoch": 1.8203268373678232,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004669075073457242,
|
|
"loss": 5.7844,
|
|
"mean_token_accuracy": 0.1637825071811676,
|
|
"num_tokens": 42182631.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 6.128258085250854,
|
|
"epoch": 1.8207637857205279,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00046689123822943643,
|
|
"loss": 5.7818,
|
|
"mean_token_accuracy": 0.15594326704740524,
|
|
"num_tokens": 42192743.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 6.117905712127685,
|
|
"epoch": 1.8212007340732326,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004668749654325741,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.15570884943008423,
|
|
"num_tokens": 42203090.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 6.155374908447266,
|
|
"epoch": 1.8216376824259373,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004668586889554493,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.15288415253162385,
|
|
"num_tokens": 42213341.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 6.152459764480591,
|
|
"epoch": 1.822074630778642,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004668424087983744,
|
|
"loss": 5.8583,
|
|
"mean_token_accuracy": 0.16066688150167466,
|
|
"num_tokens": 42222862.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 6.159763431549072,
|
|
"epoch": 1.8225115791313466,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00046682612496166156,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.15694592669606208,
|
|
"num_tokens": 42234045.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 6.1904944896698,
|
|
"epoch": 1.8229485274840513,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00046680983744562315,
|
|
"loss": 5.783,
|
|
"mean_token_accuracy": 0.16031327098608017,
|
|
"num_tokens": 42244093.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 6.055976724624633,
|
|
"epoch": 1.8233854758367563,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004667935462505716,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.16109249144792556,
|
|
"num_tokens": 42254865.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 6.09691743850708,
|
|
"epoch": 1.8238224241894607,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046677725137681924,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.1622224047780037,
|
|
"num_tokens": 42264565.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 6.1953661918640135,
|
|
"epoch": 1.8242593725421656,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046676095282467873,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.15550556927919387,
|
|
"num_tokens": 42274289.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 6.1334230422973635,
|
|
"epoch": 1.82469632089487,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004667446505944627,
|
|
"loss": 5.8113,
|
|
"mean_token_accuracy": 0.15679647624492646,
|
|
"num_tokens": 42283855.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.984568786621094,
|
|
"epoch": 1.825133269247575,
|
|
"grad_norm": 5.0625,
|
|
"learning_rate": 0.00046672834468648375,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.16409749537706375,
|
|
"num_tokens": 42294871.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 6.168867206573486,
|
|
"epoch": 1.8255702176002795,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004667120351010547,
|
|
"loss": 5.7963,
|
|
"mean_token_accuracy": 0.16068321764469146,
|
|
"num_tokens": 42305315.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 6.183169364929199,
|
|
"epoch": 1.8260071659529844,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00046669572183848833,
|
|
"loss": 5.7879,
|
|
"mean_token_accuracy": 0.1644870012998581,
|
|
"num_tokens": 42316893.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 6.064131784439087,
|
|
"epoch": 1.826444114305689,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00046667940489909766,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.16768437176942824,
|
|
"num_tokens": 42326784.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 6.046210527420044,
|
|
"epoch": 1.8268810626583938,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00046666308428319547,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.16883353739976883,
|
|
"num_tokens": 42336283.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 6.078384971618652,
|
|
"epoch": 1.8273180110110985,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046664675999109494,
|
|
"loss": 5.7902,
|
|
"mean_token_accuracy": 0.16064900606870652,
|
|
"num_tokens": 42346933.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 6.100211954116821,
|
|
"epoch": 1.8277549593638032,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004666304320231091,
|
|
"loss": 5.8441,
|
|
"mean_token_accuracy": 0.15444888770580292,
|
|
"num_tokens": 42357616.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 6.153164720535278,
|
|
"epoch": 1.8281919077165079,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004666141003795512,
|
|
"loss": 5.8095,
|
|
"mean_token_accuracy": 0.16054720282554627,
|
|
"num_tokens": 42367566.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 6.156742668151855,
|
|
"epoch": 1.8286288560692125,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00046659776506073446,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.16173860877752305,
|
|
"num_tokens": 42377412.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 6.144735383987427,
|
|
"epoch": 1.8290658044219175,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00046658142606697216,
|
|
"loss": 5.7777,
|
|
"mean_token_accuracy": 0.1658511847257614,
|
|
"num_tokens": 42387952.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 6.1396565437316895,
|
|
"epoch": 1.829502752774622,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004665650833985777,
|
|
"loss": 5.8192,
|
|
"mean_token_accuracy": 0.15561270862817764,
|
|
"num_tokens": 42398488.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 6.138120889663696,
|
|
"epoch": 1.8299397011273268,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00046654873705586464,
|
|
"loss": 5.762,
|
|
"mean_token_accuracy": 0.16394922137260437,
|
|
"num_tokens": 42409137.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 6.157368946075439,
|
|
"epoch": 1.8303766494800313,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004665323870391464,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.1497701436281204,
|
|
"num_tokens": 42419867.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 6.118807220458985,
|
|
"epoch": 1.8308135978327362,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004665160333487365,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.15170530527830123,
|
|
"num_tokens": 42429590.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 6.175193643569946,
|
|
"epoch": 1.831250546185441,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004664996759849489,
|
|
"loss": 5.7813,
|
|
"mean_token_accuracy": 0.16057996898889543,
|
|
"num_tokens": 42439777.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 6.063419008255005,
|
|
"epoch": 1.8316874945381456,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004664833149480971,
|
|
"loss": 5.7779,
|
|
"mean_token_accuracy": 0.16476726680994033,
|
|
"num_tokens": 42449843.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 6.064124917984008,
|
|
"epoch": 1.8321244428908503,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046646695023849506,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.17267682552337646,
|
|
"num_tokens": 42459056.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 6.121998119354248,
|
|
"epoch": 1.832561391243555,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00046645058185645644,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.16060147136449815,
|
|
"num_tokens": 42468946.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 6.054912042617798,
|
|
"epoch": 1.8329983395962597,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004664342098022954,
|
|
"loss": 5.7746,
|
|
"mean_token_accuracy": 0.16255973130464554,
|
|
"num_tokens": 42478894.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 6.12795844078064,
|
|
"epoch": 1.8334352879489644,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004664178340763259,
|
|
"loss": 5.7703,
|
|
"mean_token_accuracy": 0.16182252168655395,
|
|
"num_tokens": 42490124.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 6.119140577316284,
|
|
"epoch": 1.8338722363016693,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004664014546788621,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.15724663734436034,
|
|
"num_tokens": 42499554.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 6.027507019042969,
|
|
"epoch": 1.8343091846543738,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.00046638507161021807,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.1705660715699196,
|
|
"num_tokens": 42510364.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 6.135519075393677,
|
|
"epoch": 1.8347461330070787,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00046636868487070804,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.14906709194183348,
|
|
"num_tokens": 42521671.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 6.136737632751465,
|
|
"epoch": 1.8351830813597831,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00046635229446064647,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.1624959036707878,
|
|
"num_tokens": 42532784.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 1.8351830813597831,
|
|
"eval_entropy": 5.872524485929187,
|
|
"eval_loss": 5.83701753616333,
|
|
"eval_mean_token_accuracy": 0.1655561091253135,
|
|
"eval_num_tokens": 42532784.0,
|
|
"eval_runtime": 28.1492,
|
|
"eval_samples_per_second": 1314.921,
|
|
"eval_steps_per_second": 164.374,
|
|
"step": 21000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 114420,
|
|
"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": 6.3680988651264e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|