18068 lines
494 KiB
JSON
18068 lines
494 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.7865070348684785,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 2.7321829853184e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|