52705b6d40
Model: fpadovani/rus-cyrl-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2621690116228262,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.897289562225342,
|
|
"epoch": 0.0004369483527047103,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.6042,
|
|
"mean_token_accuracy": 0.08350983113050461,
|
|
"num_tokens": 10478.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.906166076660156,
|
|
"epoch": 0.0008738967054094206,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.6188,
|
|
"mean_token_accuracy": 0.08587298914790154,
|
|
"num_tokens": 21152.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.886682033538818,
|
|
"epoch": 0.0013108450581141308,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.6304,
|
|
"mean_token_accuracy": 0.08478806018829346,
|
|
"num_tokens": 31246.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.918443632125855,
|
|
"epoch": 0.0017477934108188413,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.6787,
|
|
"mean_token_accuracy": 0.07867336831986904,
|
|
"num_tokens": 41934.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.970422983169556,
|
|
"epoch": 0.0021847417635235517,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.6469,
|
|
"mean_token_accuracy": 0.08144963085651398,
|
|
"num_tokens": 52830.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.949476909637451,
|
|
"epoch": 0.0026216901162282617,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.5996,
|
|
"mean_token_accuracy": 0.08676403239369393,
|
|
"num_tokens": 62706.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.977545309066772,
|
|
"epoch": 0.003058638468932972,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.6506,
|
|
"mean_token_accuracy": 0.086336649954319,
|
|
"num_tokens": 72619.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 8.052342128753661,
|
|
"epoch": 0.0034955868216376825,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.6618,
|
|
"mean_token_accuracy": 0.08166376948356628,
|
|
"num_tokens": 82903.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 8.004082489013673,
|
|
"epoch": 0.003932535174342393,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.6376,
|
|
"mean_token_accuracy": 0.09148860350251198,
|
|
"num_tokens": 94243.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.982316017150879,
|
|
"epoch": 0.004369483527047103,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.5827,
|
|
"mean_token_accuracy": 0.08447664603590965,
|
|
"num_tokens": 103618.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.994159317016601,
|
|
"epoch": 0.004806431879751813,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.6458,
|
|
"mean_token_accuracy": 0.0843130737543106,
|
|
"num_tokens": 112180.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.965240716934204,
|
|
"epoch": 0.005243380232456523,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.6378,
|
|
"mean_token_accuracy": 0.0797391913831234,
|
|
"num_tokens": 122462.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.984555625915528,
|
|
"epoch": 0.005680328585161234,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.675,
|
|
"mean_token_accuracy": 0.07956810221076012,
|
|
"num_tokens": 132741.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 8.007879114151,
|
|
"epoch": 0.006117276937865944,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.4766,
|
|
"mean_token_accuracy": 0.09351350888609886,
|
|
"num_tokens": 142973.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 8.00863881111145,
|
|
"epoch": 0.006554225290570655,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.7046,
|
|
"mean_token_accuracy": 0.08399961739778519,
|
|
"num_tokens": 153199.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.956274366378784,
|
|
"epoch": 0.006991173643275365,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.5526,
|
|
"mean_token_accuracy": 0.08937041833996773,
|
|
"num_tokens": 163079.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.965800809860229,
|
|
"epoch": 0.0074281219959800755,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.5914,
|
|
"mean_token_accuracy": 0.08658739626407623,
|
|
"num_tokens": 173308.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.9384160995483395,
|
|
"epoch": 0.007865070348684786,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.6535,
|
|
"mean_token_accuracy": 0.09069974273443222,
|
|
"num_tokens": 183856.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.94856538772583,
|
|
"epoch": 0.008302018701389496,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.5749,
|
|
"mean_token_accuracy": 0.08630532398819923,
|
|
"num_tokens": 193368.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.945826864242553,
|
|
"epoch": 0.008738967054094207,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.5981,
|
|
"mean_token_accuracy": 0.08861325606703759,
|
|
"num_tokens": 202686.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.925296783447266,
|
|
"epoch": 0.009175915406798917,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.5568,
|
|
"mean_token_accuracy": 0.09273463487625122,
|
|
"num_tokens": 213237.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.953626537322998,
|
|
"epoch": 0.009612863759503626,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.5719,
|
|
"mean_token_accuracy": 0.08897444158792496,
|
|
"num_tokens": 222406.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.976461410522461,
|
|
"epoch": 0.010049812112208336,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.6179,
|
|
"mean_token_accuracy": 0.08532986417412758,
|
|
"num_tokens": 232139.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.922226190567017,
|
|
"epoch": 0.010486760464913047,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.5876,
|
|
"mean_token_accuracy": 0.08453975692391395,
|
|
"num_tokens": 242438.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.840370607376099,
|
|
"epoch": 0.010923708817617757,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.589,
|
|
"mean_token_accuracy": 0.08821919411420823,
|
|
"num_tokens": 253082.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.940424108505249,
|
|
"epoch": 0.011360657170322468,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.5948,
|
|
"mean_token_accuracy": 0.0919061541557312,
|
|
"num_tokens": 264067.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 8.062803173065186,
|
|
"epoch": 0.011797605523027178,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.5772,
|
|
"mean_token_accuracy": 0.08630142137408256,
|
|
"num_tokens": 274571.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.8331855773925785,
|
|
"epoch": 0.012234553875731888,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.5644,
|
|
"mean_token_accuracy": 0.09022602662444115,
|
|
"num_tokens": 284561.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.9677777767181395,
|
|
"epoch": 0.012671502228436599,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.4588,
|
|
"mean_token_accuracy": 0.08896260559558869,
|
|
"num_tokens": 295366.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.901757526397705,
|
|
"epoch": 0.01310845058114131,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.6533,
|
|
"mean_token_accuracy": 0.08677535206079483,
|
|
"num_tokens": 305423.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.8698560237884525,
|
|
"epoch": 0.01354539893384602,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.5374,
|
|
"mean_token_accuracy": 0.09062277376651764,
|
|
"num_tokens": 315182.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.939631605148316,
|
|
"epoch": 0.01398234728655073,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.5551,
|
|
"mean_token_accuracy": 0.08309731036424636,
|
|
"num_tokens": 324780.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.941270208358764,
|
|
"epoch": 0.01441929563925544,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.617,
|
|
"mean_token_accuracy": 0.08777398616075516,
|
|
"num_tokens": 335104.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.986670398712159,
|
|
"epoch": 0.014856243991960151,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.6081,
|
|
"mean_token_accuracy": 0.0891649942845106,
|
|
"num_tokens": 345073.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.023071241378783,
|
|
"epoch": 0.015293192344664861,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6144,
|
|
"mean_token_accuracy": 0.08408513441681861,
|
|
"num_tokens": 354342.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.945475244522095,
|
|
"epoch": 0.015730140697369572,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.5353,
|
|
"mean_token_accuracy": 0.09062551632523537,
|
|
"num_tokens": 364441.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.928923225402832,
|
|
"epoch": 0.01616708905007428,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5542,
|
|
"mean_token_accuracy": 0.08356907293200493,
|
|
"num_tokens": 373918.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.914482545852661,
|
|
"epoch": 0.016604037402778993,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.6305,
|
|
"mean_token_accuracy": 0.08665620759129525,
|
|
"num_tokens": 383273.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.877908754348755,
|
|
"epoch": 0.0170409857554837,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.4795,
|
|
"mean_token_accuracy": 0.09727039858698845,
|
|
"num_tokens": 393262.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.961901712417602,
|
|
"epoch": 0.017477934108188414,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.6166,
|
|
"mean_token_accuracy": 0.08374508917331695,
|
|
"num_tokens": 402389.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.935757064819336,
|
|
"epoch": 0.017914882460893122,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.5619,
|
|
"mean_token_accuracy": 0.0888036273419857,
|
|
"num_tokens": 412997.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.9856915950775145,
|
|
"epoch": 0.018351830813597834,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.5661,
|
|
"mean_token_accuracy": 0.08725668415427208,
|
|
"num_tokens": 422222.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.811623525619507,
|
|
"epoch": 0.018788779166302543,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.5068,
|
|
"mean_token_accuracy": 0.09225667044520378,
|
|
"num_tokens": 432539.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.9459527969360355,
|
|
"epoch": 0.019225727519007252,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.5453,
|
|
"mean_token_accuracy": 0.08999547138810157,
|
|
"num_tokens": 442311.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.893007898330689,
|
|
"epoch": 0.019662675871711964,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.5167,
|
|
"mean_token_accuracy": 0.08521599024534225,
|
|
"num_tokens": 452727.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.965888023376465,
|
|
"epoch": 0.020099624224416673,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.5489,
|
|
"mean_token_accuracy": 0.0897920735180378,
|
|
"num_tokens": 462461.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.924414014816284,
|
|
"epoch": 0.020536572577121385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.5427,
|
|
"mean_token_accuracy": 0.0894696906208992,
|
|
"num_tokens": 472362.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.880691957473755,
|
|
"epoch": 0.020973520929826094,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.5639,
|
|
"mean_token_accuracy": 0.08265788778662682,
|
|
"num_tokens": 482718.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.892111539840698,
|
|
"epoch": 0.021410469282530806,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.5248,
|
|
"mean_token_accuracy": 0.08400834277272225,
|
|
"num_tokens": 492947.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.998752784729004,
|
|
"epoch": 0.021847417635235514,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.5869,
|
|
"mean_token_accuracy": 0.08245678767561912,
|
|
"num_tokens": 502957.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.905310440063476,
|
|
"epoch": 0.022284365987940227,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.5414,
|
|
"mean_token_accuracy": 0.08397668749094009,
|
|
"num_tokens": 513220.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.939359521865844,
|
|
"epoch": 0.022721314340644935,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.5046,
|
|
"mean_token_accuracy": 0.0867614358663559,
|
|
"num_tokens": 523217.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.874382209777832,
|
|
"epoch": 0.023158262693349647,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.5321,
|
|
"mean_token_accuracy": 0.08652917370200157,
|
|
"num_tokens": 533789.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.985016393661499,
|
|
"epoch": 0.023595211046054356,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.4971,
|
|
"mean_token_accuracy": 0.09434628114104271,
|
|
"num_tokens": 544146.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.840573167800903,
|
|
"epoch": 0.02403215939875907,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.5389,
|
|
"mean_token_accuracy": 0.0874963328242302,
|
|
"num_tokens": 554215.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.910647535324097,
|
|
"epoch": 0.024469107751463777,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.524,
|
|
"mean_token_accuracy": 0.08785401061177253,
|
|
"num_tokens": 564587.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.014890098571778,
|
|
"epoch": 0.024906056104168486,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.5682,
|
|
"mean_token_accuracy": 0.08573365658521652,
|
|
"num_tokens": 574819.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.8606682300567625,
|
|
"epoch": 0.025343004456873198,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.5076,
|
|
"mean_token_accuracy": 0.08299032188951969,
|
|
"num_tokens": 585178.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.878801870346069,
|
|
"epoch": 0.025779952809577907,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.4975,
|
|
"mean_token_accuracy": 0.08870302848517894,
|
|
"num_tokens": 595086.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.8693853378295895,
|
|
"epoch": 0.02621690116228262,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.5201,
|
|
"mean_token_accuracy": 0.08878342881798744,
|
|
"num_tokens": 604942.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.927869176864624,
|
|
"epoch": 0.026653849514987327,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.4803,
|
|
"mean_token_accuracy": 0.0899667464196682,
|
|
"num_tokens": 616082.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.873331737518311,
|
|
"epoch": 0.02709079786769204,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.5467,
|
|
"mean_token_accuracy": 0.08932502046227456,
|
|
"num_tokens": 626375.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.859624433517456,
|
|
"epoch": 0.027527746220396748,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.4942,
|
|
"mean_token_accuracy": 0.08501280173659324,
|
|
"num_tokens": 637563.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.986823797225952,
|
|
"epoch": 0.02796469457310146,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.5055,
|
|
"mean_token_accuracy": 0.09258699566125869,
|
|
"num_tokens": 647256.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.865791273117066,
|
|
"epoch": 0.02840164292580617,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.5538,
|
|
"mean_token_accuracy": 0.08355396911501885,
|
|
"num_tokens": 657247.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.960019207000732,
|
|
"epoch": 0.02883859127851088,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.4561,
|
|
"mean_token_accuracy": 0.08626900538802147,
|
|
"num_tokens": 667613.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.887899160385132,
|
|
"epoch": 0.02927553963121559,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.5092,
|
|
"mean_token_accuracy": 0.08869680538773536,
|
|
"num_tokens": 678048.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.926455736160278,
|
|
"epoch": 0.029712487983920302,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.4952,
|
|
"mean_token_accuracy": 0.09030729234218597,
|
|
"num_tokens": 688468.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.849487924575806,
|
|
"epoch": 0.03014943633662501,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.4801,
|
|
"mean_token_accuracy": 0.08931280449032783,
|
|
"num_tokens": 699809.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.818565845489502,
|
|
"epoch": 0.030586384689329723,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.4455,
|
|
"mean_token_accuracy": 0.09213222786784173,
|
|
"num_tokens": 709227.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.93096079826355,
|
|
"epoch": 0.03102333304203443,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.5295,
|
|
"mean_token_accuracy": 0.08403203263878822,
|
|
"num_tokens": 720178.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.879321956634522,
|
|
"epoch": 0.031460281394739144,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.4737,
|
|
"mean_token_accuracy": 0.09429880529642105,
|
|
"num_tokens": 730514.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.884739542007447,
|
|
"epoch": 0.03189722974744385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.5358,
|
|
"mean_token_accuracy": 0.08618768155574799,
|
|
"num_tokens": 741345.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.859089326858521,
|
|
"epoch": 0.03233417810014856,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.4394,
|
|
"mean_token_accuracy": 0.0918248526751995,
|
|
"num_tokens": 751163.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.865943956375122,
|
|
"epoch": 0.03277112645285327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.4387,
|
|
"mean_token_accuracy": 0.08565517961978912,
|
|
"num_tokens": 762090.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.882615852355957,
|
|
"epoch": 0.033208074805557986,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.4199,
|
|
"mean_token_accuracy": 0.09661138281226159,
|
|
"num_tokens": 772049.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.8357421875,
|
|
"epoch": 0.03364502315826269,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.3948,
|
|
"mean_token_accuracy": 0.09582874178886414,
|
|
"num_tokens": 781280.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.847851085662842,
|
|
"epoch": 0.0340819715109674,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.4399,
|
|
"mean_token_accuracy": 0.10038882195949554,
|
|
"num_tokens": 791642.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.808693170547485,
|
|
"epoch": 0.034518919863672115,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.461,
|
|
"mean_token_accuracy": 0.08796226382255554,
|
|
"num_tokens": 801224.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.909064292907715,
|
|
"epoch": 0.03495586821637683,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.4035,
|
|
"mean_token_accuracy": 0.09300346970558167,
|
|
"num_tokens": 810727.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.90141282081604,
|
|
"epoch": 0.03539281656908153,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.4981,
|
|
"mean_token_accuracy": 0.08850462436676025,
|
|
"num_tokens": 819943.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.751878356933593,
|
|
"epoch": 0.035829764921786245,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.4123,
|
|
"mean_token_accuracy": 0.08893894106149673,
|
|
"num_tokens": 829474.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.881792497634888,
|
|
"epoch": 0.03626671327449096,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.3957,
|
|
"mean_token_accuracy": 0.09066153168678284,
|
|
"num_tokens": 839288.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.823987722396851,
|
|
"epoch": 0.03670366162719567,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.3985,
|
|
"mean_token_accuracy": 0.09359202459454537,
|
|
"num_tokens": 850064.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.700559186935425,
|
|
"epoch": 0.037140609979900374,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.4049,
|
|
"mean_token_accuracy": 0.08930439800024033,
|
|
"num_tokens": 860732.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.845630502700805,
|
|
"epoch": 0.037577558332605086,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.3843,
|
|
"mean_token_accuracy": 0.09245424419641494,
|
|
"num_tokens": 870076.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.678752708435058,
|
|
"epoch": 0.0380145066853098,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.2926,
|
|
"mean_token_accuracy": 0.09747275933623314,
|
|
"num_tokens": 880201.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.746017980575561,
|
|
"epoch": 0.038451455038014504,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.365,
|
|
"mean_token_accuracy": 0.09477003365755081,
|
|
"num_tokens": 890344.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.766406536102295,
|
|
"epoch": 0.038888403390719216,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.3579,
|
|
"mean_token_accuracy": 0.09475301504135132,
|
|
"num_tokens": 900443.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.832936811447143,
|
|
"epoch": 0.03932535174342393,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.3912,
|
|
"mean_token_accuracy": 0.093039420992136,
|
|
"num_tokens": 910284.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.858904647827148,
|
|
"epoch": 0.03976230009612864,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.4642,
|
|
"mean_token_accuracy": 0.09033563137054443,
|
|
"num_tokens": 920986.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.757792663574219,
|
|
"epoch": 0.040199248448833345,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.3627,
|
|
"mean_token_accuracy": 0.09344023391604424,
|
|
"num_tokens": 930481.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.816108894348145,
|
|
"epoch": 0.04063619680153806,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.3938,
|
|
"mean_token_accuracy": 0.09392273649573327,
|
|
"num_tokens": 940554.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.7882520198822025,
|
|
"epoch": 0.04107314515424277,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.3473,
|
|
"mean_token_accuracy": 0.09586822837591172,
|
|
"num_tokens": 950005.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.681087589263916,
|
|
"epoch": 0.04151009350694748,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.3382,
|
|
"mean_token_accuracy": 0.09327205643057823,
|
|
"num_tokens": 959414.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.797640085220337,
|
|
"epoch": 0.04194704185965219,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.3684,
|
|
"mean_token_accuracy": 0.08881603106856346,
|
|
"num_tokens": 969352.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.834505796432495,
|
|
"epoch": 0.0423839902123569,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.4022,
|
|
"mean_token_accuracy": 0.09166060984134675,
|
|
"num_tokens": 980294.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.640561914443969,
|
|
"epoch": 0.04282093856506161,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.2872,
|
|
"mean_token_accuracy": 0.09981269985437394,
|
|
"num_tokens": 990453.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.763474369049073,
|
|
"epoch": 0.04325788691776632,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.2957,
|
|
"mean_token_accuracy": 0.09954148381948472,
|
|
"num_tokens": 1000509.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.786115121841431,
|
|
"epoch": 0.04369483527047103,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.4391,
|
|
"mean_token_accuracy": 0.08776586875319481,
|
|
"num_tokens": 1011747.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.71697096824646,
|
|
"epoch": 0.04413178362317574,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.3987,
|
|
"mean_token_accuracy": 0.08907804265618324,
|
|
"num_tokens": 1021511.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.781257009506225,
|
|
"epoch": 0.04456873197588045,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.3892,
|
|
"mean_token_accuracy": 0.08882547542452812,
|
|
"num_tokens": 1032116.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.699050712585449,
|
|
"epoch": 0.04500568032858516,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.2936,
|
|
"mean_token_accuracy": 0.0988588310778141,
|
|
"num_tokens": 1041356.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.724139022827148,
|
|
"epoch": 0.04544262868128987,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.3613,
|
|
"mean_token_accuracy": 0.09164860397577286,
|
|
"num_tokens": 1051314.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.725086450576782,
|
|
"epoch": 0.04587957703399458,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.3286,
|
|
"mean_token_accuracy": 0.09037298560142518,
|
|
"num_tokens": 1060857.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.730894708633423,
|
|
"epoch": 0.046316525386699295,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.3401,
|
|
"mean_token_accuracy": 0.09307361096143722,
|
|
"num_tokens": 1071744.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.750498676300049,
|
|
"epoch": 0.046753473739404,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.3204,
|
|
"mean_token_accuracy": 0.0946407824754715,
|
|
"num_tokens": 1080777.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.702250289916992,
|
|
"epoch": 0.04719042209210871,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.3129,
|
|
"mean_token_accuracy": 0.09728860557079315,
|
|
"num_tokens": 1090951.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.662070989608765,
|
|
"epoch": 0.047627370444813424,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.2726,
|
|
"mean_token_accuracy": 0.09608129486441612,
|
|
"num_tokens": 1101667.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.711210823059082,
|
|
"epoch": 0.04806431879751814,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.3992,
|
|
"mean_token_accuracy": 0.08903621137142181,
|
|
"num_tokens": 1112652.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.703273153305053,
|
|
"epoch": 0.04850126715022284,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.337,
|
|
"mean_token_accuracy": 0.09509981796145439,
|
|
"num_tokens": 1122518.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.7245645999908445,
|
|
"epoch": 0.048938215502927554,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.345,
|
|
"mean_token_accuracy": 0.09325287640094757,
|
|
"num_tokens": 1132867.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.777069234848023,
|
|
"epoch": 0.049375163855632266,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.4122,
|
|
"mean_token_accuracy": 0.08977549225091934,
|
|
"num_tokens": 1142524.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.790037679672241,
|
|
"epoch": 0.04981211220833697,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.2861,
|
|
"mean_token_accuracy": 0.10011612400412559,
|
|
"num_tokens": 1152983.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.716982364654541,
|
|
"epoch": 0.050249060561041684,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.3616,
|
|
"mean_token_accuracy": 0.09314811900258065,
|
|
"num_tokens": 1164271.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.647295999526977,
|
|
"epoch": 0.050686008913746396,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.2216,
|
|
"mean_token_accuracy": 0.09704305902123452,
|
|
"num_tokens": 1173567.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.612508869171142,
|
|
"epoch": 0.05112295726645111,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.2779,
|
|
"mean_token_accuracy": 0.10037864819169044,
|
|
"num_tokens": 1183619.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.655305528640747,
|
|
"epoch": 0.05155990561915581,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.233,
|
|
"mean_token_accuracy": 0.09470883682370186,
|
|
"num_tokens": 1193922.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.737557649612427,
|
|
"epoch": 0.051996853971860525,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.3201,
|
|
"mean_token_accuracy": 0.09405622780323028,
|
|
"num_tokens": 1203665.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.673120069503784,
|
|
"epoch": 0.05243380232456524,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.317,
|
|
"mean_token_accuracy": 0.09930261299014091,
|
|
"num_tokens": 1214119.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.711197757720948,
|
|
"epoch": 0.05287075067726995,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.3359,
|
|
"mean_token_accuracy": 0.08920879289507866,
|
|
"num_tokens": 1225275.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.587856864929199,
|
|
"epoch": 0.053307699029974655,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.2069,
|
|
"mean_token_accuracy": 0.09227376878261566,
|
|
"num_tokens": 1235199.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.658899211883545,
|
|
"epoch": 0.05374464738267937,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.2368,
|
|
"mean_token_accuracy": 0.09821678847074508,
|
|
"num_tokens": 1245648.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.546068382263184,
|
|
"epoch": 0.05418159573538408,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.2031,
|
|
"mean_token_accuracy": 0.10184830203652381,
|
|
"num_tokens": 1254793.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.690952110290527,
|
|
"epoch": 0.05461854408808879,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.2577,
|
|
"mean_token_accuracy": 0.09762314632534981,
|
|
"num_tokens": 1264429.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.53085880279541,
|
|
"epoch": 0.055055492440793496,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.2252,
|
|
"mean_token_accuracy": 0.09289011359214783,
|
|
"num_tokens": 1274449.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.681129884719849,
|
|
"epoch": 0.05549244079349821,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.3249,
|
|
"mean_token_accuracy": 0.09160538911819457,
|
|
"num_tokens": 1284987.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.6850756168365475,
|
|
"epoch": 0.05592938914620292,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.321,
|
|
"mean_token_accuracy": 0.08939207196235657,
|
|
"num_tokens": 1295984.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.543700742721557,
|
|
"epoch": 0.056366337498907626,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.2222,
|
|
"mean_token_accuracy": 0.09924623519182205,
|
|
"num_tokens": 1305738.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.613607883453369,
|
|
"epoch": 0.05680328585161234,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.1722,
|
|
"mean_token_accuracy": 0.09349776208400726,
|
|
"num_tokens": 1315691.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.554134130477905,
|
|
"epoch": 0.05724023420431705,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.1896,
|
|
"mean_token_accuracy": 0.10020266026258469,
|
|
"num_tokens": 1326195.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.56112003326416,
|
|
"epoch": 0.05767718255702176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.2129,
|
|
"mean_token_accuracy": 0.09725727662444114,
|
|
"num_tokens": 1336916.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.603675413131714,
|
|
"epoch": 0.05811413090972647,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.247,
|
|
"mean_token_accuracy": 0.09576455503702164,
|
|
"num_tokens": 1347386.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.609761524200439,
|
|
"epoch": 0.05855107926243118,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.196,
|
|
"mean_token_accuracy": 0.09891333803534508,
|
|
"num_tokens": 1357959.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.543549108505249,
|
|
"epoch": 0.05898802761513589,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.2173,
|
|
"mean_token_accuracy": 0.09141774773597718,
|
|
"num_tokens": 1368135.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.643839502334595,
|
|
"epoch": 0.059424975967840604,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.2466,
|
|
"mean_token_accuracy": 0.09271192476153374,
|
|
"num_tokens": 1378702.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.408550214767456,
|
|
"epoch": 0.05986192432054531,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.1268,
|
|
"mean_token_accuracy": 0.1002315916121006,
|
|
"num_tokens": 1387902.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.598399209976196,
|
|
"epoch": 0.06029887267325002,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.1424,
|
|
"mean_token_accuracy": 0.10513755530118943,
|
|
"num_tokens": 1397288.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.5331981658935545,
|
|
"epoch": 0.060735821025954734,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.1805,
|
|
"mean_token_accuracy": 0.1005538746714592,
|
|
"num_tokens": 1407416.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.626793670654297,
|
|
"epoch": 0.061172769378659446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.2406,
|
|
"mean_token_accuracy": 0.09300423189997672,
|
|
"num_tokens": 1417733.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.463755989074707,
|
|
"epoch": 0.06160971773136415,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.1325,
|
|
"mean_token_accuracy": 0.09881449341773987,
|
|
"num_tokens": 1426723.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.4767341136932375,
|
|
"epoch": 0.06204666608406886,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.1811,
|
|
"mean_token_accuracy": 0.09799282476305962,
|
|
"num_tokens": 1437290.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.5843759059906,
|
|
"epoch": 0.062483614436773575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.1317,
|
|
"mean_token_accuracy": 0.10022315308451653,
|
|
"num_tokens": 1446756.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.491819620132446,
|
|
"epoch": 0.06292056278947829,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.1987,
|
|
"mean_token_accuracy": 0.09563518688082695,
|
|
"num_tokens": 1457074.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.548601818084717,
|
|
"epoch": 0.06335751114218299,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.2557,
|
|
"mean_token_accuracy": 0.09054888933897018,
|
|
"num_tokens": 1467785.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.486869239807129,
|
|
"epoch": 0.0637944594948877,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.1532,
|
|
"mean_token_accuracy": 0.09929404258728028,
|
|
"num_tokens": 1477532.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.470096015930176,
|
|
"epoch": 0.06423140784759242,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.0877,
|
|
"mean_token_accuracy": 0.10287476405501365,
|
|
"num_tokens": 1487102.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.446895885467529,
|
|
"epoch": 0.06466835620029712,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.1666,
|
|
"mean_token_accuracy": 0.09422165304422378,
|
|
"num_tokens": 1497459.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.516766309738159,
|
|
"epoch": 0.06510530455300184,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.168,
|
|
"mean_token_accuracy": 0.09273407310247421,
|
|
"num_tokens": 1508756.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.497219371795654,
|
|
"epoch": 0.06554225290570655,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.0858,
|
|
"mean_token_accuracy": 0.10392189174890518,
|
|
"num_tokens": 1518735.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.503822278976441,
|
|
"epoch": 0.06597920125841125,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.1207,
|
|
"mean_token_accuracy": 0.09711763262748718,
|
|
"num_tokens": 1528632.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.355689430236817,
|
|
"epoch": 0.06641614961111597,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.1008,
|
|
"mean_token_accuracy": 0.09904444217681885,
|
|
"num_tokens": 1538180.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.512228107452392,
|
|
"epoch": 0.06685309796382068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.1416,
|
|
"mean_token_accuracy": 0.09793454185128211,
|
|
"num_tokens": 1547788.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.426608943939209,
|
|
"epoch": 0.06729004631652538,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.0757,
|
|
"mean_token_accuracy": 0.10199111700057983,
|
|
"num_tokens": 1558008.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.404742813110351,
|
|
"epoch": 0.0677269946692301,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.1458,
|
|
"mean_token_accuracy": 0.09649223536252975,
|
|
"num_tokens": 1567728.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.468697881698608,
|
|
"epoch": 0.0681639430219348,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.104,
|
|
"mean_token_accuracy": 0.09830691069364547,
|
|
"num_tokens": 1578488.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.433673858642578,
|
|
"epoch": 0.06860089137463951,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.071,
|
|
"mean_token_accuracy": 0.1033280424773693,
|
|
"num_tokens": 1588070.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.444263696670532,
|
|
"epoch": 0.06903783972734423,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.1528,
|
|
"mean_token_accuracy": 0.09422910511493683,
|
|
"num_tokens": 1598572.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.519211387634277,
|
|
"epoch": 0.06947478808004894,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.1589,
|
|
"mean_token_accuracy": 0.09713958278298378,
|
|
"num_tokens": 1607982.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.391828441619873,
|
|
"epoch": 0.06991173643275365,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.1658,
|
|
"mean_token_accuracy": 0.0995835930109024,
|
|
"num_tokens": 1618785.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.510007715225219,
|
|
"epoch": 0.07034868478545836,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.0834,
|
|
"mean_token_accuracy": 0.09890709817409515,
|
|
"num_tokens": 1627988.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.354162311553955,
|
|
"epoch": 0.07078563313816306,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.1707,
|
|
"mean_token_accuracy": 0.09317449629306793,
|
|
"num_tokens": 1638024.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.494234275817871,
|
|
"epoch": 0.07122258149086778,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.1515,
|
|
"mean_token_accuracy": 0.09472875967621804,
|
|
"num_tokens": 1649215.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.336769390106201,
|
|
"epoch": 0.07165952984357249,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.0398,
|
|
"mean_token_accuracy": 0.10013310313224792,
|
|
"num_tokens": 1659198.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.461428451538086,
|
|
"epoch": 0.0720964781962772,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.0921,
|
|
"mean_token_accuracy": 0.09403431341052056,
|
|
"num_tokens": 1668972.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.293336820602417,
|
|
"epoch": 0.07253342654898191,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.0585,
|
|
"mean_token_accuracy": 0.10309704616665841,
|
|
"num_tokens": 1679807.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.416385793685913,
|
|
"epoch": 0.07297037490168662,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.125,
|
|
"mean_token_accuracy": 0.09676878824830056,
|
|
"num_tokens": 1690567.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.312589406967163,
|
|
"epoch": 0.07340732325439134,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.0125,
|
|
"mean_token_accuracy": 0.10345098450779915,
|
|
"num_tokens": 1700939.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.2877274513244625,
|
|
"epoch": 0.07384427160709604,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.0795,
|
|
"mean_token_accuracy": 0.1037543036043644,
|
|
"num_tokens": 1711181.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.450462198257446,
|
|
"epoch": 0.07428121995980075,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.094,
|
|
"mean_token_accuracy": 0.09376272410154343,
|
|
"num_tokens": 1721392.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.326985836029053,
|
|
"epoch": 0.07471816831250547,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.0237,
|
|
"mean_token_accuracy": 0.10064763948321342,
|
|
"num_tokens": 1731942.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.383999919891357,
|
|
"epoch": 0.07515511666521017,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.1221,
|
|
"mean_token_accuracy": 0.09718978181481361,
|
|
"num_tokens": 1743409.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.321899366378784,
|
|
"epoch": 0.07559206501791488,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.0248,
|
|
"mean_token_accuracy": 0.10485066547989845,
|
|
"num_tokens": 1753425.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.311501312255859,
|
|
"epoch": 0.0760290133706196,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.0481,
|
|
"mean_token_accuracy": 0.09691131561994552,
|
|
"num_tokens": 1762722.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.587531995773316,
|
|
"epoch": 0.0764659617233243,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.1176,
|
|
"mean_token_accuracy": 0.09000161141157151,
|
|
"num_tokens": 1771895.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.24350414276123,
|
|
"epoch": 0.07690291007602901,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.0263,
|
|
"mean_token_accuracy": 0.10476705506443977,
|
|
"num_tokens": 1782175.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.367937660217285,
|
|
"epoch": 0.07733985842873373,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.0853,
|
|
"mean_token_accuracy": 0.09626216888427734,
|
|
"num_tokens": 1792409.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.413240146636963,
|
|
"epoch": 0.07777680678143843,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.1215,
|
|
"mean_token_accuracy": 0.093594279140234,
|
|
"num_tokens": 1802721.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.249949169158936,
|
|
"epoch": 0.07821375513414315,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.9593,
|
|
"mean_token_accuracy": 0.0994382567703724,
|
|
"num_tokens": 1812064.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.423052549362183,
|
|
"epoch": 0.07865070348684786,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.0682,
|
|
"mean_token_accuracy": 0.09718895554542542,
|
|
"num_tokens": 1822284.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.293412828445435,
|
|
"epoch": 0.07908765183955256,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.9757,
|
|
"mean_token_accuracy": 0.10433312505483627,
|
|
"num_tokens": 1832150.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.383054161071778,
|
|
"epoch": 0.07952460019225728,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.0895,
|
|
"mean_token_accuracy": 0.09755966365337372,
|
|
"num_tokens": 1842870.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.263940238952637,
|
|
"epoch": 0.07996154854496199,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.9138,
|
|
"mean_token_accuracy": 0.10788114890456199,
|
|
"num_tokens": 1852771.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.258758020401001,
|
|
"epoch": 0.08039849689766669,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.0202,
|
|
"mean_token_accuracy": 0.10123156458139419,
|
|
"num_tokens": 1863095.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.30932240486145,
|
|
"epoch": 0.08083544525037141,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.0345,
|
|
"mean_token_accuracy": 0.10289572551846504,
|
|
"num_tokens": 1873060.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.286193132400513,
|
|
"epoch": 0.08127239360307612,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.9689,
|
|
"mean_token_accuracy": 0.10647596344351769,
|
|
"num_tokens": 1882574.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.255521631240844,
|
|
"epoch": 0.08170934195578082,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.0261,
|
|
"mean_token_accuracy": 0.10283842384815216,
|
|
"num_tokens": 1892227.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.333770799636841,
|
|
"epoch": 0.08214629030848554,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.0544,
|
|
"mean_token_accuracy": 0.09969500303268433,
|
|
"num_tokens": 1902868.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.258380460739136,
|
|
"epoch": 0.08258323866119024,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.0208,
|
|
"mean_token_accuracy": 0.09542301744222641,
|
|
"num_tokens": 1912781.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.288229084014892,
|
|
"epoch": 0.08302018701389496,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.0122,
|
|
"mean_token_accuracy": 0.10442236512899399,
|
|
"num_tokens": 1923638.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.2728832244873045,
|
|
"epoch": 0.08345713536659967,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.9727,
|
|
"mean_token_accuracy": 0.1044746495783329,
|
|
"num_tokens": 1933498.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.165169334411621,
|
|
"epoch": 0.08389408371930437,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.9808,
|
|
"mean_token_accuracy": 0.10142417028546333,
|
|
"num_tokens": 1943798.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.275189161300659,
|
|
"epoch": 0.0843310320720091,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.0178,
|
|
"mean_token_accuracy": 0.1035747729241848,
|
|
"num_tokens": 1954235.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.269236516952515,
|
|
"epoch": 0.0847679804247138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.0173,
|
|
"mean_token_accuracy": 0.09617507830262184,
|
|
"num_tokens": 1964421.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.1920867443084715,
|
|
"epoch": 0.0852049287774185,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.9847,
|
|
"mean_token_accuracy": 0.105922382324934,
|
|
"num_tokens": 1975862.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.282237482070923,
|
|
"epoch": 0.08564187713012322,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.9777,
|
|
"mean_token_accuracy": 0.10412709340453148,
|
|
"num_tokens": 1985758.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.226387071609497,
|
|
"epoch": 0.08607882548282793,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.9644,
|
|
"mean_token_accuracy": 0.1005631759762764,
|
|
"num_tokens": 1996904.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.325346755981445,
|
|
"epoch": 0.08651577383553263,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.0478,
|
|
"mean_token_accuracy": 0.1003109060227871,
|
|
"num_tokens": 2006114.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.19905686378479,
|
|
"epoch": 0.08695272218823735,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.9881,
|
|
"mean_token_accuracy": 0.10641124993562698,
|
|
"num_tokens": 2016349.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.211451530456543,
|
|
"epoch": 0.08738967054094206,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.9353,
|
|
"mean_token_accuracy": 0.10676476284861565,
|
|
"num_tokens": 2026701.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.1555695056915285,
|
|
"epoch": 0.08782661889364678,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999999986190023,
|
|
"loss": 6.9266,
|
|
"mean_token_accuracy": 0.10275837779045105,
|
|
"num_tokens": 2036950.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.262877178192139,
|
|
"epoch": 0.08826356724635148,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999999930086991,
|
|
"loss": 6.9397,
|
|
"mean_token_accuracy": 0.10614437088370324,
|
|
"num_tokens": 2047655.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.181167459487915,
|
|
"epoch": 0.08870051559905619,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499999983082778,
|
|
"loss": 6.9041,
|
|
"mean_token_accuracy": 0.10694134309887886,
|
|
"num_tokens": 2056800.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.162737894058227,
|
|
"epoch": 0.0891374639517609,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999688412394,
|
|
"loss": 6.9414,
|
|
"mean_token_accuracy": 0.10635368078947068,
|
|
"num_tokens": 2066862.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.205184698104858,
|
|
"epoch": 0.08957441230446561,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999502840836,
|
|
"loss": 6.9621,
|
|
"mean_token_accuracy": 0.10661176219582558,
|
|
"num_tokens": 2076585.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.230246829986572,
|
|
"epoch": 0.09001136065717032,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999999274113107,
|
|
"loss": 7.0242,
|
|
"mean_token_accuracy": 0.0967386618256569,
|
|
"num_tokens": 2087768.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.244874048233032,
|
|
"epoch": 0.09044830900987504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999002229214,
|
|
"loss": 6.9319,
|
|
"mean_token_accuracy": 0.10978882536292076,
|
|
"num_tokens": 2097027.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.1607935428619385,
|
|
"epoch": 0.09088525736257974,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999998687189161,
|
|
"loss": 6.8632,
|
|
"mean_token_accuracy": 0.1147397093474865,
|
|
"num_tokens": 2107055.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.114990091323852,
|
|
"epoch": 0.09132220571528446,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999998328992954,
|
|
"loss": 6.8043,
|
|
"mean_token_accuracy": 0.10847252830863,
|
|
"num_tokens": 2116771.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.116586971282959,
|
|
"epoch": 0.09175915406798917,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049999979276406,
|
|
"loss": 6.9405,
|
|
"mean_token_accuracy": 0.10683408454060554,
|
|
"num_tokens": 2126881.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.139071369171143,
|
|
"epoch": 0.09219610242069387,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999997483132108,
|
|
"loss": 6.9056,
|
|
"mean_token_accuracy": 0.10297400355339051,
|
|
"num_tokens": 2136964.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.256573295593261,
|
|
"epoch": 0.09263305077339859,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999996995467483,
|
|
"loss": 6.9573,
|
|
"mean_token_accuracy": 0.10562608242034913,
|
|
"num_tokens": 2147263.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.122767400741577,
|
|
"epoch": 0.0930699991261033,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999996464646738,
|
|
"loss": 6.9787,
|
|
"mean_token_accuracy": 0.10480033457279206,
|
|
"num_tokens": 2157474.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.128157997131348,
|
|
"epoch": 0.093506947478808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999995890669882,
|
|
"loss": 6.9069,
|
|
"mean_token_accuracy": 0.10734480768442153,
|
|
"num_tokens": 2167701.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.108348178863525,
|
|
"epoch": 0.09394389583151272,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999995273536925,
|
|
"loss": 6.8695,
|
|
"mean_token_accuracy": 0.10862331837415695,
|
|
"num_tokens": 2178581.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.111027956008911,
|
|
"epoch": 0.09438084418421742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499999461324788,
|
|
"loss": 6.8725,
|
|
"mean_token_accuracy": 0.10809326171875,
|
|
"num_tokens": 2189529.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.156719923019409,
|
|
"epoch": 0.09481779253692213,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993909802759,
|
|
"loss": 6.9364,
|
|
"mean_token_accuracy": 0.10107551366090775,
|
|
"num_tokens": 2199805.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.0858289241790775,
|
|
"epoch": 0.09525474088962685,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999993163201577,
|
|
"loss": 6.8985,
|
|
"mean_token_accuracy": 0.10579909533262252,
|
|
"num_tokens": 2210108.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.26385760307312,
|
|
"epoch": 0.09569168924233155,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999992373444347,
|
|
"loss": 6.8966,
|
|
"mean_token_accuracy": 0.10724986046552658,
|
|
"num_tokens": 2220325.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.044133472442627,
|
|
"epoch": 0.09612863759503627,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999991540531084,
|
|
"loss": 6.8976,
|
|
"mean_token_accuracy": 0.1008307620882988,
|
|
"num_tokens": 2230521.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.1802715301513675,
|
|
"epoch": 0.09656558594774098,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999990664461804,
|
|
"loss": 6.933,
|
|
"mean_token_accuracy": 0.10014933347702026,
|
|
"num_tokens": 2240372.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.06400728225708,
|
|
"epoch": 0.09700253430044568,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999989745236524,
|
|
"loss": 6.8761,
|
|
"mean_token_accuracy": 0.11035806387662887,
|
|
"num_tokens": 2250522.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.090740442276001,
|
|
"epoch": 0.0974394826531504,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999988782855261,
|
|
"loss": 6.8382,
|
|
"mean_token_accuracy": 0.10595676749944687,
|
|
"num_tokens": 2260142.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.09924898147583,
|
|
"epoch": 0.09787643100585511,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999987777318035,
|
|
"loss": 6.852,
|
|
"mean_token_accuracy": 0.10673597902059555,
|
|
"num_tokens": 2270372.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.989193630218506,
|
|
"epoch": 0.09831337935855981,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999986728624865,
|
|
"loss": 6.7996,
|
|
"mean_token_accuracy": 0.11145754531025887,
|
|
"num_tokens": 2280517.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.1385228633880615,
|
|
"epoch": 0.09875032771126453,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499998563677577,
|
|
"loss": 6.8951,
|
|
"mean_token_accuracy": 0.10448078438639641,
|
|
"num_tokens": 2290778.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.123292922973633,
|
|
"epoch": 0.09918727606396924,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999984501770771,
|
|
"loss": 6.9369,
|
|
"mean_token_accuracy": 0.10169804915785789,
|
|
"num_tokens": 2301692.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.095804166793823,
|
|
"epoch": 0.09962422441667394,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004999983323609891,
|
|
"loss": 6.8209,
|
|
"mean_token_accuracy": 0.10772261098027229,
|
|
"num_tokens": 2312759.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.069378757476807,
|
|
"epoch": 0.10006117276937866,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999982102293153,
|
|
"loss": 6.8021,
|
|
"mean_token_accuracy": 0.10774984061717988,
|
|
"num_tokens": 2322016.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.055843925476074,
|
|
"epoch": 0.10049812112208337,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999980837820578,
|
|
"loss": 6.8062,
|
|
"mean_token_accuracy": 0.11227297484874725,
|
|
"num_tokens": 2332476.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.105614280700683,
|
|
"epoch": 0.10093506947478809,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999979530192192,
|
|
"loss": 6.8314,
|
|
"mean_token_accuracy": 0.10820274353027344,
|
|
"num_tokens": 2342914.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.032117033004761,
|
|
"epoch": 0.10137201782749279,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999978179408019,
|
|
"loss": 6.8902,
|
|
"mean_token_accuracy": 0.10032764598727226,
|
|
"num_tokens": 2353381.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.120272445678711,
|
|
"epoch": 0.1018089661801975,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999976785468085,
|
|
"loss": 6.8674,
|
|
"mean_token_accuracy": 0.10994301959872246,
|
|
"num_tokens": 2364207.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.9931823253631595,
|
|
"epoch": 0.10224591453290222,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999975348372418,
|
|
"loss": 6.7968,
|
|
"mean_token_accuracy": 0.11197755932807922,
|
|
"num_tokens": 2374985.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.06548662185669,
|
|
"epoch": 0.10268286288560692,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999973868121044,
|
|
"loss": 6.8752,
|
|
"mean_token_accuracy": 0.10842390954494477,
|
|
"num_tokens": 2385684.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.193864440917968,
|
|
"epoch": 0.10311981123831163,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999972344713994,
|
|
"loss": 6.7953,
|
|
"mean_token_accuracy": 0.10968969836831093,
|
|
"num_tokens": 2395177.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.892039108276367,
|
|
"epoch": 0.10355675959101635,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999970778151295,
|
|
"loss": 6.8292,
|
|
"mean_token_accuracy": 0.1131418652832508,
|
|
"num_tokens": 2405154.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.109063673019409,
|
|
"epoch": 0.10399370794372105,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999969168432976,
|
|
"loss": 6.8128,
|
|
"mean_token_accuracy": 0.10942742675542831,
|
|
"num_tokens": 2415818.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.981149959564209,
|
|
"epoch": 0.10443065629642576,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999967515559071,
|
|
"loss": 6.7937,
|
|
"mean_token_accuracy": 0.10865649655461311,
|
|
"num_tokens": 2425072.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.053072881698609,
|
|
"epoch": 0.10486760464913047,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499996581952961,
|
|
"loss": 6.8427,
|
|
"mean_token_accuracy": 0.11198535412549973,
|
|
"num_tokens": 2435055.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.097857189178467,
|
|
"epoch": 0.10530455300183518,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999964080344625,
|
|
"loss": 6.7474,
|
|
"mean_token_accuracy": 0.11387341618537902,
|
|
"num_tokens": 2444434.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.945683431625366,
|
|
"epoch": 0.1057415013545399,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999962298004151,
|
|
"loss": 6.7673,
|
|
"mean_token_accuracy": 0.10980340838432312,
|
|
"num_tokens": 2453860.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.091061687469482,
|
|
"epoch": 0.1061784497072446,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 6.8713,
|
|
"mean_token_accuracy": 0.10719245076179504,
|
|
"num_tokens": 2464235.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.024345874786377,
|
|
"epoch": 0.10661539805994931,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999958603856869,
|
|
"loss": 6.8067,
|
|
"mean_token_accuracy": 0.1112932026386261,
|
|
"num_tokens": 2474561.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.958724117279052,
|
|
"epoch": 0.10705234641265403,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999956692050132,
|
|
"loss": 6.7833,
|
|
"mean_token_accuracy": 0.11405704021453858,
|
|
"num_tokens": 2484574.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.0886390209198,
|
|
"epoch": 0.10748929476535873,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999954737088048,
|
|
"loss": 6.7501,
|
|
"mean_token_accuracy": 0.11529114991426467,
|
|
"num_tokens": 2494146.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.948289823532105,
|
|
"epoch": 0.10792624311806344,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999952738970652,
|
|
"loss": 6.8264,
|
|
"mean_token_accuracy": 0.11386599391698837,
|
|
"num_tokens": 2504157.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.057093334197998,
|
|
"epoch": 0.10836319147076816,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999950697697983,
|
|
"loss": 6.7766,
|
|
"mean_token_accuracy": 0.1121026560664177,
|
|
"num_tokens": 2512979.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.975002336502075,
|
|
"epoch": 0.10880013982347286,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999948613270081,
|
|
"loss": 6.8346,
|
|
"mean_token_accuracy": 0.10475755855441093,
|
|
"num_tokens": 2523202.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.0157585620880125,
|
|
"epoch": 0.10923708817617758,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999946485686987,
|
|
"loss": 6.7808,
|
|
"mean_token_accuracy": 0.11152637600898743,
|
|
"num_tokens": 2532790.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.999054861068726,
|
|
"epoch": 0.10967403652888229,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499994431494874,
|
|
"loss": 6.7737,
|
|
"mean_token_accuracy": 0.1105453684926033,
|
|
"num_tokens": 2542337.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.91253628730774,
|
|
"epoch": 0.11011098488158699,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999942101055381,
|
|
"loss": 6.7273,
|
|
"mean_token_accuracy": 0.11472218930721283,
|
|
"num_tokens": 2552762.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.998731660842895,
|
|
"epoch": 0.11054793323429171,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999939844006955,
|
|
"loss": 6.7637,
|
|
"mean_token_accuracy": 0.11208643317222595,
|
|
"num_tokens": 2563261.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.025073385238647,
|
|
"epoch": 0.11098488158699642,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999937543803503,
|
|
"loss": 6.7246,
|
|
"mean_token_accuracy": 0.11664522662758828,
|
|
"num_tokens": 2573089.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.890957021713257,
|
|
"epoch": 0.11142182993970112,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499993520044507,
|
|
"loss": 6.8066,
|
|
"mean_token_accuracy": 0.10803473964333535,
|
|
"num_tokens": 2584358.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.083640241622925,
|
|
"epoch": 0.11185877829240584,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999932813931702,
|
|
"loss": 6.7817,
|
|
"mean_token_accuracy": 0.11540437862277031,
|
|
"num_tokens": 2594981.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.970252609252929,
|
|
"epoch": 0.11229572664511055,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999930384263441,
|
|
"loss": 6.7769,
|
|
"mean_token_accuracy": 0.1091542400419712,
|
|
"num_tokens": 2603508.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.003110408782959,
|
|
"epoch": 0.11273267499781525,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499992791144034,
|
|
"loss": 6.747,
|
|
"mean_token_accuracy": 0.11488912031054496,
|
|
"num_tokens": 2613666.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.111478185653686,
|
|
"epoch": 0.11316962335051997,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999925395462439,
|
|
"loss": 6.8063,
|
|
"mean_token_accuracy": 0.10856303349137306,
|
|
"num_tokens": 2624441.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.943297529220581,
|
|
"epoch": 0.11360657170322468,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999922836329793,
|
|
"loss": 6.7665,
|
|
"mean_token_accuracy": 0.10978462025523186,
|
|
"num_tokens": 2635261.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.897740364074707,
|
|
"epoch": 0.1140435200559294,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999920234042446,
|
|
"loss": 6.7374,
|
|
"mean_token_accuracy": 0.11765253841876984,
|
|
"num_tokens": 2645493.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.958786058425903,
|
|
"epoch": 0.1144804684086341,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999917588600451,
|
|
"loss": 6.7047,
|
|
"mean_token_accuracy": 0.11853755936026573,
|
|
"num_tokens": 2655430.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.939574718475342,
|
|
"epoch": 0.1149174167613388,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999914900003857,
|
|
"loss": 6.7597,
|
|
"mean_token_accuracy": 0.11579839065670967,
|
|
"num_tokens": 2665675.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.983940458297729,
|
|
"epoch": 0.11535436511404352,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999912168252717,
|
|
"loss": 6.7285,
|
|
"mean_token_accuracy": 0.11347154676914215,
|
|
"num_tokens": 2675962.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.963703870773315,
|
|
"epoch": 0.11579131346674823,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999909393347083,
|
|
"loss": 6.766,
|
|
"mean_token_accuracy": 0.11305825337767601,
|
|
"num_tokens": 2687015.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.978190517425537,
|
|
"epoch": 0.11622826181945294,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999906575287006,
|
|
"loss": 6.7953,
|
|
"mean_token_accuracy": 0.10686544924974442,
|
|
"num_tokens": 2698065.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.9220874309539795,
|
|
"epoch": 0.11666521017215765,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999903714072544,
|
|
"loss": 6.6976,
|
|
"mean_token_accuracy": 0.1245916247367859,
|
|
"num_tokens": 2709046.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.0129210472106935,
|
|
"epoch": 0.11710215852486236,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999900809703749,
|
|
"loss": 6.7733,
|
|
"mean_token_accuracy": 0.11275611147284507,
|
|
"num_tokens": 2719705.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.906162214279175,
|
|
"epoch": 0.11753910687756706,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004999897862180678,
|
|
"loss": 6.636,
|
|
"mean_token_accuracy": 0.1237392172217369,
|
|
"num_tokens": 2729556.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.873116540908813,
|
|
"epoch": 0.11797605523027178,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999894871503386,
|
|
"loss": 6.7608,
|
|
"mean_token_accuracy": 0.1130751185119152,
|
|
"num_tokens": 2741144.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.004008674621582,
|
|
"epoch": 0.11841300358297649,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999891837671932,
|
|
"loss": 6.6835,
|
|
"mean_token_accuracy": 0.11774843856692314,
|
|
"num_tokens": 2751384.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.905232238769531,
|
|
"epoch": 0.11884995193568121,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999888760686375,
|
|
"loss": 6.6982,
|
|
"mean_token_accuracy": 0.10932691991329194,
|
|
"num_tokens": 2761044.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.811592769622803,
|
|
"epoch": 0.11928690028838591,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499988564054677,
|
|
"loss": 6.665,
|
|
"mean_token_accuracy": 0.1154528170824051,
|
|
"num_tokens": 2770946.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.016284084320068,
|
|
"epoch": 0.11972384864109062,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999882477253182,
|
|
"loss": 6.7196,
|
|
"mean_token_accuracy": 0.109063258767128,
|
|
"num_tokens": 2781247.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.83001856803894,
|
|
"epoch": 0.12016079699379534,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999879270805667,
|
|
"loss": 6.5671,
|
|
"mean_token_accuracy": 0.1252991333603859,
|
|
"num_tokens": 2792078.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.864751482009888,
|
|
"epoch": 0.12059774534650004,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999876021204291,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.11526466608047485,
|
|
"num_tokens": 2802458.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.941031503677368,
|
|
"epoch": 0.12103469369920475,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999872728449112,
|
|
"loss": 6.8076,
|
|
"mean_token_accuracy": 0.11191245838999749,
|
|
"num_tokens": 2813352.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.937870597839355,
|
|
"epoch": 0.12147164205190947,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999869392540195,
|
|
"loss": 6.6947,
|
|
"mean_token_accuracy": 0.11170903369784355,
|
|
"num_tokens": 2822954.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.951033449172973,
|
|
"epoch": 0.12190859040461417,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999866013477605,
|
|
"loss": 6.727,
|
|
"mean_token_accuracy": 0.11035996600985527,
|
|
"num_tokens": 2833375.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.83228759765625,
|
|
"epoch": 0.12234553875731889,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999862591261407,
|
|
"loss": 6.6502,
|
|
"mean_token_accuracy": 0.11303703859448433,
|
|
"num_tokens": 2843103.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.9420592308044435,
|
|
"epoch": 0.1227824871100236,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999859125891664,
|
|
"loss": 6.732,
|
|
"mean_token_accuracy": 0.11628735661506653,
|
|
"num_tokens": 2853801.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.89582667350769,
|
|
"epoch": 0.1232194354627283,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999855617368445,
|
|
"loss": 6.7202,
|
|
"mean_token_accuracy": 0.10793796628713608,
|
|
"num_tokens": 2863851.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.8485987186431885,
|
|
"epoch": 0.12365638381543302,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999852065691816,
|
|
"loss": 6.656,
|
|
"mean_token_accuracy": 0.11803558021783829,
|
|
"num_tokens": 2875073.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.966313171386719,
|
|
"epoch": 0.12409333216813773,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999848470861846,
|
|
"loss": 6.6892,
|
|
"mean_token_accuracy": 0.11483604982495307,
|
|
"num_tokens": 2885676.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.886367988586426,
|
|
"epoch": 0.12453028052084243,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999844832878602,
|
|
"loss": 6.6692,
|
|
"mean_token_accuracy": 0.12404601722955703,
|
|
"num_tokens": 2896663.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.865903234481811,
|
|
"epoch": 0.12496722887354715,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999841151742156,
|
|
"loss": 6.6836,
|
|
"mean_token_accuracy": 0.11751426309347153,
|
|
"num_tokens": 2907555.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.834966945648193,
|
|
"epoch": 0.12540417722625186,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999837427452578,
|
|
"loss": 6.6711,
|
|
"mean_token_accuracy": 0.1152021735906601,
|
|
"num_tokens": 2917173.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.887197113037109,
|
|
"epoch": 0.12584112557895658,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499983366000994,
|
|
"loss": 6.6828,
|
|
"mean_token_accuracy": 0.11685618609189988,
|
|
"num_tokens": 2928268.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.919593954086304,
|
|
"epoch": 0.12627807393166127,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999829849414312,
|
|
"loss": 6.6339,
|
|
"mean_token_accuracy": 0.12221134454011917,
|
|
"num_tokens": 2938203.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.8582720279693605,
|
|
"epoch": 0.12671502228436599,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499982599566577,
|
|
"loss": 6.6622,
|
|
"mean_token_accuracy": 0.12187671884894372,
|
|
"num_tokens": 2948094.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.868987035751343,
|
|
"epoch": 0.1271519706370707,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999822098764385,
|
|
"loss": 6.6657,
|
|
"mean_token_accuracy": 0.11611272245645524,
|
|
"num_tokens": 2957865.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.846604824066162,
|
|
"epoch": 0.1275889189897754,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999818158710234,
|
|
"loss": 6.5737,
|
|
"mean_token_accuracy": 0.12412638366222381,
|
|
"num_tokens": 2967880.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.874258327484131,
|
|
"epoch": 0.12802586734248012,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999814175503392,
|
|
"loss": 6.6387,
|
|
"mean_token_accuracy": 0.11633199378848076,
|
|
"num_tokens": 2979537.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.812403917312622,
|
|
"epoch": 0.12846281569518483,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999810149143935,
|
|
"loss": 6.6275,
|
|
"mean_token_accuracy": 0.11614747941493989,
|
|
"num_tokens": 2989700.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.771956157684326,
|
|
"epoch": 0.12889976404788953,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499980607963194,
|
|
"loss": 6.639,
|
|
"mean_token_accuracy": 0.11743173152208328,
|
|
"num_tokens": 2999141.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.867529582977295,
|
|
"epoch": 0.12933671240059424,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999801966967486,
|
|
"loss": 6.593,
|
|
"mean_token_accuracy": 0.12583683878183366,
|
|
"num_tokens": 3008259.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.905298471450806,
|
|
"epoch": 0.12977366075329896,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999797811150652,
|
|
"loss": 6.634,
|
|
"mean_token_accuracy": 0.11574389562010765,
|
|
"num_tokens": 3018281.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.850580358505249,
|
|
"epoch": 0.13021060910600368,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999793612181516,
|
|
"loss": 6.6416,
|
|
"mean_token_accuracy": 0.12190348654985428,
|
|
"num_tokens": 3029062.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.823162078857422,
|
|
"epoch": 0.13064755745870837,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999789370060161,
|
|
"loss": 6.6053,
|
|
"mean_token_accuracy": 0.12013282999396324,
|
|
"num_tokens": 3038142.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.878135681152344,
|
|
"epoch": 0.1310845058114131,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999785084786667,
|
|
"loss": 6.7104,
|
|
"mean_token_accuracy": 0.10974604934453965,
|
|
"num_tokens": 3049123.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.827748155593872,
|
|
"epoch": 0.1315214541641178,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999780756361114,
|
|
"loss": 6.6109,
|
|
"mean_token_accuracy": 0.11498570144176483,
|
|
"num_tokens": 3059031.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.89024248123169,
|
|
"epoch": 0.1319584025168225,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999776384783589,
|
|
"loss": 6.6644,
|
|
"mean_token_accuracy": 0.11741800382733344,
|
|
"num_tokens": 3068830.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.721803903579712,
|
|
"epoch": 0.13239535086952722,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999771970054174,
|
|
"loss": 6.6362,
|
|
"mean_token_accuracy": 0.11696416139602661,
|
|
"num_tokens": 3080124.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.899826955795288,
|
|
"epoch": 0.13283229922223194,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999767512172953,
|
|
"loss": 6.638,
|
|
"mean_token_accuracy": 0.11275093853473664,
|
|
"num_tokens": 3089607.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.817293930053711,
|
|
"epoch": 0.13326924757493663,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999763011140013,
|
|
"loss": 6.7252,
|
|
"mean_token_accuracy": 0.10601238310337066,
|
|
"num_tokens": 3099363.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.935261344909668,
|
|
"epoch": 0.13370619592764135,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999758466955439,
|
|
"loss": 6.6219,
|
|
"mean_token_accuracy": 0.1220114767551422,
|
|
"num_tokens": 3109552.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.773904275894165,
|
|
"epoch": 0.13414314428034607,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999753879619319,
|
|
"loss": 6.6,
|
|
"mean_token_accuracy": 0.12055370435118676,
|
|
"num_tokens": 3119536.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.843937015533447,
|
|
"epoch": 0.13458009263305076,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999749249131741,
|
|
"loss": 6.6517,
|
|
"mean_token_accuracy": 0.1186549685895443,
|
|
"num_tokens": 3130552.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.893322515487671,
|
|
"epoch": 0.13501704098575548,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999744575492793,
|
|
"loss": 6.5489,
|
|
"mean_token_accuracy": 0.11952240914106368,
|
|
"num_tokens": 3140723.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.793356323242188,
|
|
"epoch": 0.1354539893384602,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999739858702567,
|
|
"loss": 6.5877,
|
|
"mean_token_accuracy": 0.12382742390036583,
|
|
"num_tokens": 3151031.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.760280799865723,
|
|
"epoch": 0.1358909376911649,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499973509876115,
|
|
"loss": 6.5922,
|
|
"mean_token_accuracy": 0.12205319106578827,
|
|
"num_tokens": 3161373.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.842703056335449,
|
|
"epoch": 0.1363278860438696,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999730295668634,
|
|
"loss": 6.6059,
|
|
"mean_token_accuracy": 0.11810858622193336,
|
|
"num_tokens": 3171094.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.792533588409424,
|
|
"epoch": 0.13676483439657433,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999725449425114,
|
|
"loss": 6.5583,
|
|
"mean_token_accuracy": 0.1213751420378685,
|
|
"num_tokens": 3181646.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.758139514923096,
|
|
"epoch": 0.13720178274927902,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499972056003068,
|
|
"loss": 6.5366,
|
|
"mean_token_accuracy": 0.12806674242019653,
|
|
"num_tokens": 3190727.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.871710777282715,
|
|
"epoch": 0.13763873110198374,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999715627485426,
|
|
"loss": 6.6295,
|
|
"mean_token_accuracy": 0.11181031242012977,
|
|
"num_tokens": 3200316.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.744039487838745,
|
|
"epoch": 0.13807567945468846,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499971065178945,
|
|
"loss": 6.5833,
|
|
"mean_token_accuracy": 0.11728300899267197,
|
|
"num_tokens": 3211830.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.80518102645874,
|
|
"epoch": 0.13851262780739318,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999705632942843,
|
|
"loss": 6.6093,
|
|
"mean_token_accuracy": 0.11741095557808875,
|
|
"num_tokens": 3222711.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.751020383834839,
|
|
"epoch": 0.13894957616009787,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999700570945704,
|
|
"loss": 6.5137,
|
|
"mean_token_accuracy": 0.13087992370128632,
|
|
"num_tokens": 3232810.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.756484413146973,
|
|
"epoch": 0.1393865245128026,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999695465798128,
|
|
"loss": 6.593,
|
|
"mean_token_accuracy": 0.12206040173768998,
|
|
"num_tokens": 3243366.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.843332004547119,
|
|
"epoch": 0.1398234728655073,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999690317500215,
|
|
"loss": 6.5984,
|
|
"mean_token_accuracy": 0.12029016464948654,
|
|
"num_tokens": 3254000.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.8639579772949215,
|
|
"epoch": 0.140260421218212,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999685126052063,
|
|
"loss": 6.6187,
|
|
"mean_token_accuracy": 0.11791635006666183,
|
|
"num_tokens": 3263601.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.737782335281372,
|
|
"epoch": 0.14069736957091672,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999679891453772,
|
|
"loss": 6.6507,
|
|
"mean_token_accuracy": 0.11550768241286277,
|
|
"num_tokens": 3273243.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.825797033309937,
|
|
"epoch": 0.14113431792362144,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499967461370544,
|
|
"loss": 6.5905,
|
|
"mean_token_accuracy": 0.11994630172848701,
|
|
"num_tokens": 3284208.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.765414667129517,
|
|
"epoch": 0.14157126627632613,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999669292807172,
|
|
"loss": 6.5572,
|
|
"mean_token_accuracy": 0.12147776633501053,
|
|
"num_tokens": 3294216.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.838953018188477,
|
|
"epoch": 0.14200821462903085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999663928759066,
|
|
"loss": 6.6214,
|
|
"mean_token_accuracy": 0.11713840439915657,
|
|
"num_tokens": 3304576.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.773513078689575,
|
|
"epoch": 0.14244516298173557,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999658521561229,
|
|
"loss": 6.6058,
|
|
"mean_token_accuracy": 0.11238482668995857,
|
|
"num_tokens": 3314214.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.8341858863830565,
|
|
"epoch": 0.14288211133444026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999653071213763,
|
|
"loss": 6.6128,
|
|
"mean_token_accuracy": 0.11472874283790588,
|
|
"num_tokens": 3325527.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.689016628265381,
|
|
"epoch": 0.14331905968714498,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999647577716771,
|
|
"loss": 6.5222,
|
|
"mean_token_accuracy": 0.12063723728060723,
|
|
"num_tokens": 3334511.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.802826976776123,
|
|
"epoch": 0.1437560080398497,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999642041070361,
|
|
"loss": 6.5073,
|
|
"mean_token_accuracy": 0.12565877586603164,
|
|
"num_tokens": 3343922.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.721828937530518,
|
|
"epoch": 0.1441929563925544,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999636461274637,
|
|
"loss": 6.5278,
|
|
"mean_token_accuracy": 0.11740849018096924,
|
|
"num_tokens": 3353895.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.7812549591064455,
|
|
"epoch": 0.1446299047452591,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999630838329706,
|
|
"loss": 6.6036,
|
|
"mean_token_accuracy": 0.11610466390848159,
|
|
"num_tokens": 3364637.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.796862030029297,
|
|
"epoch": 0.14506685309796383,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999625172235679,
|
|
"loss": 6.5517,
|
|
"mean_token_accuracy": 0.11584209352731704,
|
|
"num_tokens": 3374308.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.753171968460083,
|
|
"epoch": 0.14550380145066852,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499961946299266,
|
|
"loss": 6.5295,
|
|
"mean_token_accuracy": 0.12038384228944779,
|
|
"num_tokens": 3383637.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.769080781936646,
|
|
"epoch": 0.14594074980337324,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999613710600763,
|
|
"loss": 6.6257,
|
|
"mean_token_accuracy": 0.11186694428324699,
|
|
"num_tokens": 3394150.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.839853715896607,
|
|
"epoch": 0.14637769815607796,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999607915060094,
|
|
"loss": 6.5858,
|
|
"mean_token_accuracy": 0.11677002832293511,
|
|
"num_tokens": 3404445.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.678188371658325,
|
|
"epoch": 0.14681464650878268,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999602076370768,
|
|
"loss": 6.4738,
|
|
"mean_token_accuracy": 0.1292397640645504,
|
|
"num_tokens": 3415183.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.721586894989014,
|
|
"epoch": 0.14725159486148737,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999596194532895,
|
|
"loss": 6.4685,
|
|
"mean_token_accuracy": 0.12550642862915992,
|
|
"num_tokens": 3424824.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.744260597229004,
|
|
"epoch": 0.1476885432141921,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999590269546588,
|
|
"loss": 6.5775,
|
|
"mean_token_accuracy": 0.11547422781586647,
|
|
"num_tokens": 3434789.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.6185546875,
|
|
"epoch": 0.1481254915668968,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999584301411961,
|
|
"loss": 6.4484,
|
|
"mean_token_accuracy": 0.14269705563783647,
|
|
"num_tokens": 3445810.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.805194997787476,
|
|
"epoch": 0.1485624399196015,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999578290129129,
|
|
"loss": 6.5926,
|
|
"mean_token_accuracy": 0.11843555644154549,
|
|
"num_tokens": 3455510.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.758487224578857,
|
|
"epoch": 0.14899938827230622,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999572235698206,
|
|
"loss": 6.5666,
|
|
"mean_token_accuracy": 0.11734471693634987,
|
|
"num_tokens": 3465785.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.741208553314209,
|
|
"epoch": 0.14943633662501093,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999566138119308,
|
|
"loss": 6.6292,
|
|
"mean_token_accuracy": 0.11335316821932792,
|
|
"num_tokens": 3477568.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.705219745635986,
|
|
"epoch": 0.14987328497771563,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999559997392554,
|
|
"loss": 6.4506,
|
|
"mean_token_accuracy": 0.14270611405372619,
|
|
"num_tokens": 3487703.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.711113119125367,
|
|
"epoch": 0.15031023333042035,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999553813518061,
|
|
"loss": 6.5284,
|
|
"mean_token_accuracy": 0.11559826582670212,
|
|
"num_tokens": 3497757.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.668199300765991,
|
|
"epoch": 0.15074718168312506,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999547586495946,
|
|
"loss": 6.4834,
|
|
"mean_token_accuracy": 0.12288279235363006,
|
|
"num_tokens": 3507594.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.773939371109009,
|
|
"epoch": 0.15118413003582976,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999541316326329,
|
|
"loss": 6.5773,
|
|
"mean_token_accuracy": 0.1167720839381218,
|
|
"num_tokens": 3517889.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.674737501144409,
|
|
"epoch": 0.15162107838853447,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999535003009332,
|
|
"loss": 6.5629,
|
|
"mean_token_accuracy": 0.12246896028518676,
|
|
"num_tokens": 3528158.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.775814867019653,
|
|
"epoch": 0.1520580267412392,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999528646545074,
|
|
"loss": 6.5627,
|
|
"mean_token_accuracy": 0.1212423361837864,
|
|
"num_tokens": 3539099.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.744331502914429,
|
|
"epoch": 0.15249497509394389,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999522246933678,
|
|
"loss": 6.5672,
|
|
"mean_token_accuracy": 0.11636029034852982,
|
|
"num_tokens": 3549819.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.822514200210572,
|
|
"epoch": 0.1529319234466486,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 6.582,
|
|
"mean_token_accuracy": 0.11982138305902482,
|
|
"num_tokens": 3560022.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.689289999008179,
|
|
"epoch": 0.15336887179935332,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999509318269964,
|
|
"loss": 6.5051,
|
|
"mean_token_accuracy": 0.120124302059412,
|
|
"num_tokens": 3569681.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.7860630512237545,
|
|
"epoch": 0.15380582015205801,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999502789217894,
|
|
"loss": 6.5971,
|
|
"mean_token_accuracy": 0.12079088762402534,
|
|
"num_tokens": 3580731.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.683336973190308,
|
|
"epoch": 0.15424276850476273,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999496217019181,
|
|
"loss": 6.5719,
|
|
"mean_token_accuracy": 0.12470733895897865,
|
|
"num_tokens": 3590482.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.740330457687378,
|
|
"epoch": 0.15467971685746745,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999489601673952,
|
|
"loss": 6.55,
|
|
"mean_token_accuracy": 0.11436792835593224,
|
|
"num_tokens": 3600988.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.879163455963135,
|
|
"epoch": 0.15511666521017214,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999482943182334,
|
|
"loss": 6.6141,
|
|
"mean_token_accuracy": 0.11543426737189293,
|
|
"num_tokens": 3611226.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.648011779785156,
|
|
"epoch": 0.15555361356287686,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999476241544454,
|
|
"loss": 6.5402,
|
|
"mean_token_accuracy": 0.12013219818472862,
|
|
"num_tokens": 3621324.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.7309770584106445,
|
|
"epoch": 0.15599056191558158,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999469496760441,
|
|
"loss": 6.4611,
|
|
"mean_token_accuracy": 0.12005406022071838,
|
|
"num_tokens": 3631650.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.717350196838379,
|
|
"epoch": 0.1564275102682863,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999462708830425,
|
|
"loss": 6.4712,
|
|
"mean_token_accuracy": 0.13633796572685242,
|
|
"num_tokens": 3641173.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.669033765792847,
|
|
"epoch": 0.156864458620991,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999455877754535,
|
|
"loss": 6.4952,
|
|
"mean_token_accuracy": 0.12263205051422119,
|
|
"num_tokens": 3651846.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.672937488555908,
|
|
"epoch": 0.1573014069736957,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999449003532903,
|
|
"loss": 6.4924,
|
|
"mean_token_accuracy": 0.12233219742774963,
|
|
"num_tokens": 3661174.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.715725040435791,
|
|
"epoch": 0.15773835532640043,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999442086165661,
|
|
"loss": 6.4768,
|
|
"mean_token_accuracy": 0.1226891666650772,
|
|
"num_tokens": 3671042.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.707070398330688,
|
|
"epoch": 0.15817530367910512,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499943512565294,
|
|
"loss": 6.456,
|
|
"mean_token_accuracy": 0.11890220195055008,
|
|
"num_tokens": 3681206.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.718597173690796,
|
|
"epoch": 0.15861225203180984,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999428121994874,
|
|
"loss": 6.5416,
|
|
"mean_token_accuracy": 0.12524761259555817,
|
|
"num_tokens": 3691748.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.644932508468628,
|
|
"epoch": 0.15904920038451456,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999421075191599,
|
|
"loss": 6.4351,
|
|
"mean_token_accuracy": 0.12655914798378945,
|
|
"num_tokens": 3701730.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.7265056610107425,
|
|
"epoch": 0.15948614873721925,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999413985243249,
|
|
"loss": 6.5473,
|
|
"mean_token_accuracy": 0.12333036363124847,
|
|
"num_tokens": 3712525.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.780407094955445,
|
|
"epoch": 0.15992309708992397,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499940685214996,
|
|
"loss": 6.5108,
|
|
"mean_token_accuracy": 0.12247696071863175,
|
|
"num_tokens": 3722016.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.7228175640106205,
|
|
"epoch": 0.1603600454426287,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999399675911869,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.128486368060112,
|
|
"num_tokens": 3731299.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.601348638534546,
|
|
"epoch": 0.16079699379533338,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999392456529113,
|
|
"loss": 6.4831,
|
|
"mean_token_accuracy": 0.12748103588819504,
|
|
"num_tokens": 3740922.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.624817132949829,
|
|
"epoch": 0.1612339421480381,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999385194001831,
|
|
"loss": 6.4599,
|
|
"mean_token_accuracy": 0.12713200226426125,
|
|
"num_tokens": 3750339.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.703272294998169,
|
|
"epoch": 0.16167089050074282,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999377888330164,
|
|
"loss": 6.4525,
|
|
"mean_token_accuracy": 0.12768443152308465,
|
|
"num_tokens": 3761379.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.649005270004272,
|
|
"epoch": 0.1621078388534475,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999370539514249,
|
|
"loss": 6.5191,
|
|
"mean_token_accuracy": 0.12053906321525573,
|
|
"num_tokens": 3771649.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.601364612579346,
|
|
"epoch": 0.16254478720615223,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999363147554229,
|
|
"loss": 6.4493,
|
|
"mean_token_accuracy": 0.12944458052515984,
|
|
"num_tokens": 3782393.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.721639108657837,
|
|
"epoch": 0.16298173555885695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999355712450244,
|
|
"loss": 6.5061,
|
|
"mean_token_accuracy": 0.12632624581456184,
|
|
"num_tokens": 3792849.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.676987981796264,
|
|
"epoch": 0.16341868391156164,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999348234202438,
|
|
"loss": 6.4481,
|
|
"mean_token_accuracy": 0.1284789800643921,
|
|
"num_tokens": 3803848.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.551715660095215,
|
|
"epoch": 0.16385563226426636,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999340712810956,
|
|
"loss": 6.3909,
|
|
"mean_token_accuracy": 0.13192431330680848,
|
|
"num_tokens": 3814704.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.705342388153076,
|
|
"epoch": 0.16429258061697108,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999333148275939,
|
|
"loss": 6.5028,
|
|
"mean_token_accuracy": 0.11970377936959267,
|
|
"num_tokens": 3824955.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.683031272888184,
|
|
"epoch": 0.1647295289696758,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999325540597535,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.12891870439052583,
|
|
"num_tokens": 3836540.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.583834505081176,
|
|
"epoch": 0.1651664773223805,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999317889775887,
|
|
"loss": 6.3804,
|
|
"mean_token_accuracy": 0.1364469476044178,
|
|
"num_tokens": 3846472.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.688028192520141,
|
|
"epoch": 0.1656034256750852,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999310195811143,
|
|
"loss": 6.482,
|
|
"mean_token_accuracy": 0.12633047848939896,
|
|
"num_tokens": 3857187.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.714043521881104,
|
|
"epoch": 0.16604037402778993,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999302458703451,
|
|
"loss": 6.4456,
|
|
"mean_token_accuracy": 0.13051569014787673,
|
|
"num_tokens": 3866259.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.573014926910401,
|
|
"epoch": 0.16647732238049462,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499929467845296,
|
|
"loss": 6.5043,
|
|
"mean_token_accuracy": 0.11940461099147796,
|
|
"num_tokens": 3876869.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.7059375762939455,
|
|
"epoch": 0.16691427073319934,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999286855059818,
|
|
"loss": 6.4832,
|
|
"mean_token_accuracy": 0.12376384809613228,
|
|
"num_tokens": 3888278.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.709025764465332,
|
|
"epoch": 0.16735121908590406,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999278988524177,
|
|
"loss": 6.5398,
|
|
"mean_token_accuracy": 0.12542197927832605,
|
|
"num_tokens": 3898648.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.6800124168396,
|
|
"epoch": 0.16778816743860875,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999271078846184,
|
|
"loss": 6.4707,
|
|
"mean_token_accuracy": 0.12389178350567817,
|
|
"num_tokens": 3908282.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.5305383682250975,
|
|
"epoch": 0.16822511579131347,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999263126025994,
|
|
"loss": 6.4439,
|
|
"mean_token_accuracy": 0.1258118435740471,
|
|
"num_tokens": 3918333.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.743747615814209,
|
|
"epoch": 0.1686620641440182,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999255130063759,
|
|
"loss": 6.451,
|
|
"mean_token_accuracy": 0.12649790495634078,
|
|
"num_tokens": 3927403.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.643372011184693,
|
|
"epoch": 0.16909901249672288,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999247090959633,
|
|
"loss": 6.4763,
|
|
"mean_token_accuracy": 0.1255256250500679,
|
|
"num_tokens": 3937352.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.593483400344849,
|
|
"epoch": 0.1695359608494276,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999239008713767,
|
|
"loss": 6.302,
|
|
"mean_token_accuracy": 0.13238156586885452,
|
|
"num_tokens": 3947164.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.632910919189453,
|
|
"epoch": 0.16997290920213232,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999230883326319,
|
|
"loss": 6.4789,
|
|
"mean_token_accuracy": 0.12670883610844613,
|
|
"num_tokens": 3956887.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.690495347976684,
|
|
"epoch": 0.170409857554837,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999222714797445,
|
|
"loss": 6.4517,
|
|
"mean_token_accuracy": 0.125770603120327,
|
|
"num_tokens": 3966542.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.6743687152862545,
|
|
"epoch": 0.17084680590754173,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049992145031273,
|
|
"loss": 6.4149,
|
|
"mean_token_accuracy": 0.13651399984955787,
|
|
"num_tokens": 3976127.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.539837646484375,
|
|
"epoch": 0.17128375426024645,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999206248316043,
|
|
"loss": 6.3808,
|
|
"mean_token_accuracy": 0.129552910476923,
|
|
"num_tokens": 3987371.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.5061633586883545,
|
|
"epoch": 0.17172070261295114,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499919795036383,
|
|
"loss": 6.3923,
|
|
"mean_token_accuracy": 0.13139066472649574,
|
|
"num_tokens": 3997924.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.676038503646851,
|
|
"epoch": 0.17215765096565586,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999189609270823,
|
|
"loss": 6.4851,
|
|
"mean_token_accuracy": 0.12391790822148323,
|
|
"num_tokens": 4009150.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.673120498657227,
|
|
"epoch": 0.17259459931836058,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499918122503718,
|
|
"loss": 6.4923,
|
|
"mean_token_accuracy": 0.1261556513607502,
|
|
"num_tokens": 4018899.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.587709045410156,
|
|
"epoch": 0.17303154767106527,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999172797663064,
|
|
"loss": 6.4382,
|
|
"mean_token_accuracy": 0.12643140107393264,
|
|
"num_tokens": 4028652.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.630083847045898,
|
|
"epoch": 0.17346849602376999,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999164327148634,
|
|
"loss": 6.4762,
|
|
"mean_token_accuracy": 0.12422962710261345,
|
|
"num_tokens": 4039819.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.656488132476807,
|
|
"epoch": 0.1739054443764747,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999155813494053,
|
|
"loss": 6.3795,
|
|
"mean_token_accuracy": 0.13175911754369735,
|
|
"num_tokens": 4050029.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.498795366287231,
|
|
"epoch": 0.17434239272917942,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999147256699487,
|
|
"loss": 6.4081,
|
|
"mean_token_accuracy": 0.13507219925522804,
|
|
"num_tokens": 4060497.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.6314342498779295,
|
|
"epoch": 0.17477934108188412,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999138656765096,
|
|
"loss": 6.3982,
|
|
"mean_token_accuracy": 0.13177526667714118,
|
|
"num_tokens": 4071477.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.677942276000977,
|
|
"epoch": 0.17521628943458883,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999130013691049,
|
|
"loss": 6.5053,
|
|
"mean_token_accuracy": 0.12303248420357704,
|
|
"num_tokens": 4081869.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.6382654190063475,
|
|
"epoch": 0.17565323778729355,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999121327477509,
|
|
"loss": 6.4715,
|
|
"mean_token_accuracy": 0.1286171071231365,
|
|
"num_tokens": 4092797.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.596001386642456,
|
|
"epoch": 0.17609018613999824,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999112598124642,
|
|
"loss": 6.4183,
|
|
"mean_token_accuracy": 0.12707913890480996,
|
|
"num_tokens": 4103688.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.670361614227295,
|
|
"epoch": 0.17652713449270296,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999103825632618,
|
|
"loss": 6.3977,
|
|
"mean_token_accuracy": 0.12762655541300774,
|
|
"num_tokens": 4114037.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.578020477294922,
|
|
"epoch": 0.17696408284540768,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999095010001605,
|
|
"loss": 6.3639,
|
|
"mean_token_accuracy": 0.1284645155072212,
|
|
"num_tokens": 4124164.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.659268522262574,
|
|
"epoch": 0.17740103119811237,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499908615123177,
|
|
"loss": 6.4891,
|
|
"mean_token_accuracy": 0.12261471077799797,
|
|
"num_tokens": 4134225.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.626478099822998,
|
|
"epoch": 0.1778379795508171,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999077249323284,
|
|
"loss": 6.5314,
|
|
"mean_token_accuracy": 0.12370351999998093,
|
|
"num_tokens": 4145962.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.630055475234985,
|
|
"epoch": 0.1782749279035218,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999068304276319,
|
|
"loss": 6.4111,
|
|
"mean_token_accuracy": 0.12499069198966026,
|
|
"num_tokens": 4156572.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.6319256782531735,
|
|
"epoch": 0.1787118762562265,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999059316091045,
|
|
"loss": 6.4848,
|
|
"mean_token_accuracy": 0.12434430345892906,
|
|
"num_tokens": 4166960.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.6504209518432615,
|
|
"epoch": 0.17914882460893122,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999050284767634,
|
|
"loss": 6.4215,
|
|
"mean_token_accuracy": 0.12848171815276146,
|
|
"num_tokens": 4177833.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.527290678024292,
|
|
"epoch": 0.17958577296163594,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999041210306261,
|
|
"loss": 6.349,
|
|
"mean_token_accuracy": 0.13348185643553734,
|
|
"num_tokens": 4187858.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.70694146156311,
|
|
"epoch": 0.18002272131434063,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999032092707098,
|
|
"loss": 6.4954,
|
|
"mean_token_accuracy": 0.12123825252056122,
|
|
"num_tokens": 4198207.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.589783763885498,
|
|
"epoch": 0.18045966966704535,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999022931970323,
|
|
"loss": 6.3684,
|
|
"mean_token_accuracy": 0.13207549452781678,
|
|
"num_tokens": 4207594.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.5987868309021,
|
|
"epoch": 0.18089661801975007,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999013728096107,
|
|
"loss": 6.3884,
|
|
"mean_token_accuracy": 0.1320921741425991,
|
|
"num_tokens": 4217334.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.566110038757325,
|
|
"epoch": 0.18133356637245476,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499900448108463,
|
|
"loss": 6.3573,
|
|
"mean_token_accuracy": 0.13278961703181266,
|
|
"num_tokens": 4226407.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.574927711486817,
|
|
"epoch": 0.18177051472515948,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499899519093607,
|
|
"loss": 6.3179,
|
|
"mean_token_accuracy": 0.13256798908114434,
|
|
"num_tokens": 4237818.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.590792036056518,
|
|
"epoch": 0.1822074630778642,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998985857650603,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.12269085347652435,
|
|
"num_tokens": 4247783.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.530824613571167,
|
|
"epoch": 0.18264441143056892,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998976481228409,
|
|
"loss": 6.3893,
|
|
"mean_token_accuracy": 0.127620892226696,
|
|
"num_tokens": 4258049.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.59817476272583,
|
|
"epoch": 0.1830813597832736,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998967061669668,
|
|
"loss": 6.3786,
|
|
"mean_token_accuracy": 0.12377788498997688,
|
|
"num_tokens": 4269357.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.52078332901001,
|
|
"epoch": 0.18351830813597833,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998957598974559,
|
|
"loss": 6.2953,
|
|
"mean_token_accuracy": 0.14164591878652572,
|
|
"num_tokens": 4279576.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.556330728530884,
|
|
"epoch": 0.18395525648868305,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998948093143266,
|
|
"loss": 6.3485,
|
|
"mean_token_accuracy": 0.1299436144530773,
|
|
"num_tokens": 4289761.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.555707740783691,
|
|
"epoch": 0.18439220484138774,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499893854417597,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.13434590697288512,
|
|
"num_tokens": 4299231.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.549562931060791,
|
|
"epoch": 0.18482915319409246,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998928952072854,
|
|
"loss": 6.4692,
|
|
"mean_token_accuracy": 0.12588368579745293,
|
|
"num_tokens": 4308687.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.6162632465362545,
|
|
"epoch": 0.18526610154679718,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998919316834102,
|
|
"loss": 6.4108,
|
|
"mean_token_accuracy": 0.12744370847940445,
|
|
"num_tokens": 4318183.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.607033395767212,
|
|
"epoch": 0.18570304989950187,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049989096384599,
|
|
"loss": 6.4688,
|
|
"mean_token_accuracy": 0.12834835201501846,
|
|
"num_tokens": 4328482.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.611848211288452,
|
|
"epoch": 0.1861399982522066,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998899916950431,
|
|
"loss": 6.327,
|
|
"mean_token_accuracy": 0.12936775758862495,
|
|
"num_tokens": 4339313.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.535123682022094,
|
|
"epoch": 0.1865769466049113,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998890152305885,
|
|
"loss": 6.448,
|
|
"mean_token_accuracy": 0.12641657814383506,
|
|
"num_tokens": 4350299.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.666938543319702,
|
|
"epoch": 0.187013894957616,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998880344526447,
|
|
"loss": 6.3671,
|
|
"mean_token_accuracy": 0.13759638294577597,
|
|
"num_tokens": 4361424.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.489548110961914,
|
|
"epoch": 0.18745084331032072,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998870493612306,
|
|
"loss": 6.3444,
|
|
"mean_token_accuracy": 0.13067372441291808,
|
|
"num_tokens": 4371480.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.4931432723999025,
|
|
"epoch": 0.18788779166302544,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998860599563649,
|
|
"loss": 6.3826,
|
|
"mean_token_accuracy": 0.1308943137526512,
|
|
"num_tokens": 4381951.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.611650037765503,
|
|
"epoch": 0.18832474001573013,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998850662380668,
|
|
"loss": 6.4303,
|
|
"mean_token_accuracy": 0.12348892539739609,
|
|
"num_tokens": 4392290.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.502107381820679,
|
|
"epoch": 0.18876168836843485,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998840682063553,
|
|
"loss": 6.2015,
|
|
"mean_token_accuracy": 0.1464900940656662,
|
|
"num_tokens": 4403350.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.535247755050659,
|
|
"epoch": 0.18919863672113957,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998830658612496,
|
|
"loss": 6.3957,
|
|
"mean_token_accuracy": 0.13261518627405167,
|
|
"num_tokens": 4413171.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.483105993270874,
|
|
"epoch": 0.18963558507384426,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998820592027688,
|
|
"loss": 6.3331,
|
|
"mean_token_accuracy": 0.13156379163265228,
|
|
"num_tokens": 4424371.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.603164386749268,
|
|
"epoch": 0.19007253342654898,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998810482309322,
|
|
"loss": 6.3293,
|
|
"mean_token_accuracy": 0.1259684681892395,
|
|
"num_tokens": 4434040.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.611560964584351,
|
|
"epoch": 0.1905094817792537,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998800329457595,
|
|
"loss": 6.4017,
|
|
"mean_token_accuracy": 0.12301709577441215,
|
|
"num_tokens": 4444663.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.527074813842773,
|
|
"epoch": 0.1909464301319584,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998790133472697,
|
|
"loss": 6.3604,
|
|
"mean_token_accuracy": 0.12777338102459906,
|
|
"num_tokens": 4454733.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.54938063621521,
|
|
"epoch": 0.1913833784846631,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998779894354827,
|
|
"loss": 6.3562,
|
|
"mean_token_accuracy": 0.13192371279001236,
|
|
"num_tokens": 4464286.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.550158071517944,
|
|
"epoch": 0.19182032683736783,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499876961210418,
|
|
"loss": 6.3274,
|
|
"mean_token_accuracy": 0.13941287770867347,
|
|
"num_tokens": 4475005.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.516703271865845,
|
|
"epoch": 0.19225727519007255,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998759286720953,
|
|
"loss": 6.2863,
|
|
"mean_token_accuracy": 0.1340303435921669,
|
|
"num_tokens": 4484606.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.484053611755371,
|
|
"epoch": 0.19269422354277724,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998748918205345,
|
|
"loss": 6.4027,
|
|
"mean_token_accuracy": 0.12878716513514518,
|
|
"num_tokens": 4494930.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.576354551315307,
|
|
"epoch": 0.19313117189548196,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998738506557554,
|
|
"loss": 6.4254,
|
|
"mean_token_accuracy": 0.12400433123111725,
|
|
"num_tokens": 4505304.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.619117164611817,
|
|
"epoch": 0.19356812024818668,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499872805177778,
|
|
"loss": 6.3368,
|
|
"mean_token_accuracy": 0.1325274594128132,
|
|
"num_tokens": 4514333.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.427423667907715,
|
|
"epoch": 0.19400506860089137,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998717553866225,
|
|
"loss": 6.3963,
|
|
"mean_token_accuracy": 0.1355910688638687,
|
|
"num_tokens": 4525175.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.591354560852051,
|
|
"epoch": 0.1944420169535961,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998707012823087,
|
|
"loss": 6.2709,
|
|
"mean_token_accuracy": 0.13448979929089547,
|
|
"num_tokens": 4534212.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.457765913009643,
|
|
"epoch": 0.1948789653063008,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998696428648573,
|
|
"loss": 6.4433,
|
|
"mean_token_accuracy": 0.1265091545879841,
|
|
"num_tokens": 4545141.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.59932131767273,
|
|
"epoch": 0.1953159136590055,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998685801342881,
|
|
"loss": 6.3016,
|
|
"mean_token_accuracy": 0.1358583614230156,
|
|
"num_tokens": 4554410.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.4797813415527346,
|
|
"epoch": 0.19575286201171022,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998675130906217,
|
|
"loss": 6.3079,
|
|
"mean_token_accuracy": 0.13782036304473877,
|
|
"num_tokens": 4564397.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.455375337600708,
|
|
"epoch": 0.19618981036441493,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998664417338787,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.13762991055846213,
|
|
"num_tokens": 4573986.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.545703554153443,
|
|
"epoch": 0.19662675871711963,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998653660640794,
|
|
"loss": 6.2973,
|
|
"mean_token_accuracy": 0.13973189294338226,
|
|
"num_tokens": 4583449.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.559102153778076,
|
|
"epoch": 0.19706370706982435,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998642860812447,
|
|
"loss": 6.3459,
|
|
"mean_token_accuracy": 0.12769658789038657,
|
|
"num_tokens": 4593637.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.478931617736817,
|
|
"epoch": 0.19750065542252906,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998632017853951,
|
|
"loss": 6.3123,
|
|
"mean_token_accuracy": 0.13895439505577087,
|
|
"num_tokens": 4603865.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.565149307250977,
|
|
"epoch": 0.19793760377523376,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998621131765514,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.13697974607348443,
|
|
"num_tokens": 4613502.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.505105781555176,
|
|
"epoch": 0.19837455212793847,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998610202547345,
|
|
"loss": 6.3232,
|
|
"mean_token_accuracy": 0.13375489190220832,
|
|
"num_tokens": 4623163.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.5777122497558596,
|
|
"epoch": 0.1988115004806432,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998599230199654,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.13985270708799363,
|
|
"num_tokens": 4632850.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.4656078815460205,
|
|
"epoch": 0.19924844883334789,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998588214722653,
|
|
"loss": 6.3446,
|
|
"mean_token_accuracy": 0.1339777112007141,
|
|
"num_tokens": 4642858.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.614597415924072,
|
|
"epoch": 0.1996853971860526,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.12828925773501396,
|
|
"num_tokens": 4653083.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.54793062210083,
|
|
"epoch": 0.20012234553875732,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998566054381561,
|
|
"loss": 6.3764,
|
|
"mean_token_accuracy": 0.13061879575252533,
|
|
"num_tokens": 4663353.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.474935913085938,
|
|
"epoch": 0.20055929389146204,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004998554909517895,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.13771099895238875,
|
|
"num_tokens": 4673878.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.482282829284668,
|
|
"epoch": 0.20099624224416673,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998543721525769,
|
|
"loss": 6.3145,
|
|
"mean_token_accuracy": 0.13249781727790833,
|
|
"num_tokens": 4683661.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.474229240417481,
|
|
"epoch": 0.20143319059687145,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998532490405397,
|
|
"loss": 6.3564,
|
|
"mean_token_accuracy": 0.1330401547253132,
|
|
"num_tokens": 4693817.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.484963512420654,
|
|
"epoch": 0.20187013894957617,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998521216156991,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.13420451059937477,
|
|
"num_tokens": 4703550.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.518954229354859,
|
|
"epoch": 0.20230708730228086,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998509898780771,
|
|
"loss": 6.4029,
|
|
"mean_token_accuracy": 0.12855391204357147,
|
|
"num_tokens": 4714872.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.501462841033936,
|
|
"epoch": 0.20274403565498558,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998498538276954,
|
|
"loss": 6.29,
|
|
"mean_token_accuracy": 0.13525153920054436,
|
|
"num_tokens": 4725745.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.45821533203125,
|
|
"epoch": 0.2031809840076903,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998487134645755,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.13093238174915314,
|
|
"num_tokens": 4735560.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.549660491943359,
|
|
"epoch": 0.203617932360395,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998475687887396,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.12788162082433702,
|
|
"num_tokens": 4746304.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.57174506187439,
|
|
"epoch": 0.2040548807130997,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998464198002095,
|
|
"loss": 6.3098,
|
|
"mean_token_accuracy": 0.13458219319581985,
|
|
"num_tokens": 4756200.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.5113461971282955,
|
|
"epoch": 0.20449182906580443,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998452664990072,
|
|
"loss": 6.3378,
|
|
"mean_token_accuracy": 0.12682230174541473,
|
|
"num_tokens": 4766249.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.55569429397583,
|
|
"epoch": 0.20492877741850912,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998441088851548,
|
|
"loss": 6.3573,
|
|
"mean_token_accuracy": 0.13034775629639625,
|
|
"num_tokens": 4776510.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.524681043624878,
|
|
"epoch": 0.20536572577121384,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998429469586748,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.13234503641724588,
|
|
"num_tokens": 4786798.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.471218490600586,
|
|
"epoch": 0.20580267412391856,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499841780719589,
|
|
"loss": 6.27,
|
|
"mean_token_accuracy": 0.12901424914598464,
|
|
"num_tokens": 4796001.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.446377468109131,
|
|
"epoch": 0.20623962247662325,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998406101679202,
|
|
"loss": 6.2392,
|
|
"mean_token_accuracy": 0.13897980153560638,
|
|
"num_tokens": 4807634.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.482134389877319,
|
|
"epoch": 0.20667657082932797,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998394353036906,
|
|
"loss": 6.2602,
|
|
"mean_token_accuracy": 0.14035317897796631,
|
|
"num_tokens": 4817840.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.448006582260132,
|
|
"epoch": 0.2071135191820327,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998382561269229,
|
|
"loss": 6.2297,
|
|
"mean_token_accuracy": 0.13662357553839682,
|
|
"num_tokens": 4827186.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.418888902664184,
|
|
"epoch": 0.20755046753473738,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998370726376395,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.12804412618279457,
|
|
"num_tokens": 4837140.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.525313377380371,
|
|
"epoch": 0.2079874158874421,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998358848358634,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.13363988548517228,
|
|
"num_tokens": 4846907.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.421245479583741,
|
|
"epoch": 0.20842436424014682,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499834692721617,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.13632143288850784,
|
|
"num_tokens": 4856165.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.532106208801269,
|
|
"epoch": 0.2088613125928515,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998334962949237,
|
|
"loss": 6.1893,
|
|
"mean_token_accuracy": 0.14790109992027284,
|
|
"num_tokens": 4865308.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.363882780075073,
|
|
"epoch": 0.20929826094555623,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998322955558059,
|
|
"loss": 6.2627,
|
|
"mean_token_accuracy": 0.14519340097904204,
|
|
"num_tokens": 4876286.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.495657873153687,
|
|
"epoch": 0.20973520929826095,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998310905042869,
|
|
"loss": 6.2851,
|
|
"mean_token_accuracy": 0.13914690390229226,
|
|
"num_tokens": 4887227.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.47929368019104,
|
|
"epoch": 0.21017215765096567,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998298811403898,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.13582812398672103,
|
|
"num_tokens": 4896994.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.486909008026123,
|
|
"epoch": 0.21060910600367036,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998286674641378,
|
|
"loss": 6.3204,
|
|
"mean_token_accuracy": 0.13193437755107879,
|
|
"num_tokens": 4907623.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.420040416717529,
|
|
"epoch": 0.21104605435637508,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499827449475554,
|
|
"loss": 6.213,
|
|
"mean_token_accuracy": 0.1360305741429329,
|
|
"num_tokens": 4917040.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.561966419219971,
|
|
"epoch": 0.2114830027090798,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499826227174662,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.13053651601076127,
|
|
"num_tokens": 4928390.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.418824338912964,
|
|
"epoch": 0.2119199510617845,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998250005614852,
|
|
"loss": 6.3213,
|
|
"mean_token_accuracy": 0.13254272788763047,
|
|
"num_tokens": 4939040.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.432943868637085,
|
|
"epoch": 0.2123568994144892,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499823769636047,
|
|
"loss": 6.3587,
|
|
"mean_token_accuracy": 0.13161036968231202,
|
|
"num_tokens": 4949915.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.4896979331970215,
|
|
"epoch": 0.21279384776719393,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998225343983712,
|
|
"loss": 6.2475,
|
|
"mean_token_accuracy": 0.13825453370809554,
|
|
"num_tokens": 4960127.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.534148836135865,
|
|
"epoch": 0.21323079611989862,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998212948484814,
|
|
"loss": 6.3152,
|
|
"mean_token_accuracy": 0.13082096055150033,
|
|
"num_tokens": 4970152.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.409393072128296,
|
|
"epoch": 0.21366774447260334,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998200509864012,
|
|
"loss": 6.2538,
|
|
"mean_token_accuracy": 0.13555221557617186,
|
|
"num_tokens": 4979745.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.533963584899903,
|
|
"epoch": 0.21410469282530806,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998188028121547,
|
|
"loss": 6.276,
|
|
"mean_token_accuracy": 0.1419918142259121,
|
|
"num_tokens": 4989924.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.393548154830933,
|
|
"epoch": 0.21454164117801275,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998175503257658,
|
|
"loss": 6.2304,
|
|
"mean_token_accuracy": 0.14116282463073732,
|
|
"num_tokens": 4999698.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.470434617996216,
|
|
"epoch": 0.21497858953071747,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998162935272585,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.13296620473265647,
|
|
"num_tokens": 5010625.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.392181825637818,
|
|
"epoch": 0.2154155378834222,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998150324166568,
|
|
"loss": 6.2241,
|
|
"mean_token_accuracy": 0.14569925218820573,
|
|
"num_tokens": 5019740.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.5314465999603275,
|
|
"epoch": 0.21585248623612688,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499813766993985,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.13134812116622924,
|
|
"num_tokens": 5030601.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.560648441314697,
|
|
"epoch": 0.2162894345888316,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998124972592674,
|
|
"loss": 6.2817,
|
|
"mean_token_accuracy": 0.1379701852798462,
|
|
"num_tokens": 5040567.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.4075439453125,
|
|
"epoch": 0.21672638294153632,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998112232125283,
|
|
"loss": 6.1694,
|
|
"mean_token_accuracy": 0.140249789506197,
|
|
"num_tokens": 5049512.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.388670444488525,
|
|
"epoch": 0.217163331294241,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499809944853792,
|
|
"loss": 6.359,
|
|
"mean_token_accuracy": 0.12962737679481506,
|
|
"num_tokens": 5060986.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.469041967391968,
|
|
"epoch": 0.21760027964694573,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998086621830833,
|
|
"loss": 6.2681,
|
|
"mean_token_accuracy": 0.14133114963769913,
|
|
"num_tokens": 5071492.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.473101425170898,
|
|
"epoch": 0.21803722799965045,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998073752004267,
|
|
"loss": 6.2934,
|
|
"mean_token_accuracy": 0.13215823620557784,
|
|
"num_tokens": 5081722.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.478217506408692,
|
|
"epoch": 0.21847417635235516,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998060839058467,
|
|
"loss": 6.2577,
|
|
"mean_token_accuracy": 0.13338202238082886,
|
|
"num_tokens": 5091906.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.408456039428711,
|
|
"epoch": 0.21891112470505986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998047882993683,
|
|
"loss": 6.2437,
|
|
"mean_token_accuracy": 0.1377291664481163,
|
|
"num_tokens": 5102025.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.419159936904907,
|
|
"epoch": 0.21934807305776458,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998034883810162,
|
|
"loss": 6.2568,
|
|
"mean_token_accuracy": 0.13685641512274743,
|
|
"num_tokens": 5112354.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.460919380187988,
|
|
"epoch": 0.2197850214104693,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998021841508155,
|
|
"loss": 6.1919,
|
|
"mean_token_accuracy": 0.14290908649563788,
|
|
"num_tokens": 5121695.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.459331607818603,
|
|
"epoch": 0.22022196976317399,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998008756087911,
|
|
"loss": 6.3082,
|
|
"mean_token_accuracy": 0.1325561910867691,
|
|
"num_tokens": 5132561.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.490088653564453,
|
|
"epoch": 0.2206589181158787,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499799562754968,
|
|
"loss": 6.3357,
|
|
"mean_token_accuracy": 0.1301969990134239,
|
|
"num_tokens": 5141981.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.422775936126709,
|
|
"epoch": 0.22109586646858342,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997982455893716,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.13869994953274728,
|
|
"num_tokens": 5151550.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.518757390975952,
|
|
"epoch": 0.22153281482128812,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997969241120271,
|
|
"loss": 6.271,
|
|
"mean_token_accuracy": 0.1292865790426731,
|
|
"num_tokens": 5161679.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.383720397949219,
|
|
"epoch": 0.22196976317399283,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997955983229597,
|
|
"loss": 6.3304,
|
|
"mean_token_accuracy": 0.13600479513406755,
|
|
"num_tokens": 5171575.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.425492429733277,
|
|
"epoch": 0.22240671152669755,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499794268222195,
|
|
"loss": 6.1906,
|
|
"mean_token_accuracy": 0.1381123498082161,
|
|
"num_tokens": 5180152.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.384013509750366,
|
|
"epoch": 0.22284365987940224,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997929338097583,
|
|
"loss": 6.2734,
|
|
"mean_token_accuracy": 0.133567613363266,
|
|
"num_tokens": 5190518.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.496050786972046,
|
|
"epoch": 0.22328060823210696,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997915950856755,
|
|
"loss": 6.3065,
|
|
"mean_token_accuracy": 0.12552305087447166,
|
|
"num_tokens": 5201729.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.451396703720093,
|
|
"epoch": 0.22371755658481168,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997902520499721,
|
|
"loss": 6.2854,
|
|
"mean_token_accuracy": 0.1372365988790989,
|
|
"num_tokens": 5211940.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.411359596252441,
|
|
"epoch": 0.22415450493751637,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997889047026738,
|
|
"loss": 6.2217,
|
|
"mean_token_accuracy": 0.1385316163301468,
|
|
"num_tokens": 5221028.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.40747299194336,
|
|
"epoch": 0.2245914532902211,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997875530438066,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.1430547997355461,
|
|
"num_tokens": 5230498.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.414899444580078,
|
|
"epoch": 0.2250284016429258,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997861970733963,
|
|
"loss": 6.2426,
|
|
"mean_token_accuracy": 0.1374136283993721,
|
|
"num_tokens": 5240112.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.420394611358643,
|
|
"epoch": 0.2254653499956305,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499784836791469,
|
|
"loss": 6.213,
|
|
"mean_token_accuracy": 0.14016053378582,
|
|
"num_tokens": 5249201.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.429572916030883,
|
|
"epoch": 0.22590229834833522,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997834721980507,
|
|
"loss": 6.2215,
|
|
"mean_token_accuracy": 0.13842421472072602,
|
|
"num_tokens": 5258541.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.5185013771057125,
|
|
"epoch": 0.22633924670103994,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004997821032931676,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.1385103665292263,
|
|
"num_tokens": 5268524.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.363296604156494,
|
|
"epoch": 0.22677619505374463,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499780730076846,
|
|
"loss": 6.2425,
|
|
"mean_token_accuracy": 0.14057053327560426,
|
|
"num_tokens": 5280702.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.452259969711304,
|
|
"epoch": 0.22721314340644935,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997793525491122,
|
|
"loss": 6.2208,
|
|
"mean_token_accuracy": 0.1316538669168949,
|
|
"num_tokens": 5291214.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.3743082046508786,
|
|
"epoch": 0.22765009175915407,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997779707099926,
|
|
"loss": 6.1768,
|
|
"mean_token_accuracy": 0.14723527133464814,
|
|
"num_tokens": 5300729.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.421396255493164,
|
|
"epoch": 0.2280870401118588,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997765845595138,
|
|
"loss": 6.3155,
|
|
"mean_token_accuracy": 0.13397107347846032,
|
|
"num_tokens": 5310551.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.42731294631958,
|
|
"epoch": 0.22852398846456348,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997751940977024,
|
|
"loss": 6.185,
|
|
"mean_token_accuracy": 0.14047921672463418,
|
|
"num_tokens": 5320038.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.375219440460205,
|
|
"epoch": 0.2289609368172682,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997737993245848,
|
|
"loss": 6.2425,
|
|
"mean_token_accuracy": 0.137275530397892,
|
|
"num_tokens": 5329753.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.359013986587525,
|
|
"epoch": 0.22939788516997292,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997724002401881,
|
|
"loss": 6.2234,
|
|
"mean_token_accuracy": 0.14074066802859306,
|
|
"num_tokens": 5340546.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.377727031707764,
|
|
"epoch": 0.2298348335226776,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997709968445391,
|
|
"loss": 6.2944,
|
|
"mean_token_accuracy": 0.1307218536734581,
|
|
"num_tokens": 5352097.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.516751003265381,
|
|
"epoch": 0.23027178187538233,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997695891376644,
|
|
"loss": 6.2301,
|
|
"mean_token_accuracy": 0.13981532603502272,
|
|
"num_tokens": 5361646.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.378463172912598,
|
|
"epoch": 0.23070873022808705,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997681771195912,
|
|
"loss": 6.2131,
|
|
"mean_token_accuracy": 0.14355284944176674,
|
|
"num_tokens": 5371695.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.387977123260498,
|
|
"epoch": 0.23114567858079174,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997667607903466,
|
|
"loss": 6.2837,
|
|
"mean_token_accuracy": 0.13416371122002602,
|
|
"num_tokens": 5381978.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.501465606689453,
|
|
"epoch": 0.23158262693349646,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997653401499578,
|
|
"loss": 6.286,
|
|
"mean_token_accuracy": 0.14000471904873849,
|
|
"num_tokens": 5391891.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.419810676574707,
|
|
"epoch": 0.23201957528620118,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499763915198452,
|
|
"loss": 6.2509,
|
|
"mean_token_accuracy": 0.13402704000473023,
|
|
"num_tokens": 5403172.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.39618444442749,
|
|
"epoch": 0.23245652363890587,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997624859358565,
|
|
"loss": 6.2691,
|
|
"mean_token_accuracy": 0.13881371021270753,
|
|
"num_tokens": 5413130.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.355148601531982,
|
|
"epoch": 0.2328934719916106,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997610523621988,
|
|
"loss": 6.2918,
|
|
"mean_token_accuracy": 0.13786400184035302,
|
|
"num_tokens": 5423510.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.4528110980987545,
|
|
"epoch": 0.2333304203443153,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997596144775063,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.1457971803843975,
|
|
"num_tokens": 5433707.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.2398120880126955,
|
|
"epoch": 0.23376736869702,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997581722818067,
|
|
"loss": 6.2262,
|
|
"mean_token_accuracy": 0.1393609881401062,
|
|
"num_tokens": 5444381.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.543811321258545,
|
|
"epoch": 0.23420431704972472,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997567257751275,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.1374103344976902,
|
|
"num_tokens": 5453905.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.345109462738037,
|
|
"epoch": 0.23464126540242944,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997552749574965,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.13802675306797027,
|
|
"num_tokens": 5464839.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.386873865127564,
|
|
"epoch": 0.23507821375513413,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997538198289416,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.13631488382816315,
|
|
"num_tokens": 5475459.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.363434362411499,
|
|
"epoch": 0.23551516210783885,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997523603894907,
|
|
"loss": 6.2474,
|
|
"mean_token_accuracy": 0.14079780876636505,
|
|
"num_tokens": 5484886.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.415025997161865,
|
|
"epoch": 0.23595211046054357,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997508966391717,
|
|
"loss": 6.2246,
|
|
"mean_token_accuracy": 0.1376207336783409,
|
|
"num_tokens": 5494803.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.335872220993042,
|
|
"epoch": 0.2363890588132483,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997494285780129,
|
|
"loss": 6.1795,
|
|
"mean_token_accuracy": 0.13543259873986244,
|
|
"num_tokens": 5504997.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.385657262802124,
|
|
"epoch": 0.23682600716595298,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997479562060421,
|
|
"loss": 6.1725,
|
|
"mean_token_accuracy": 0.14626708552241324,
|
|
"num_tokens": 5514492.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.409390449523926,
|
|
"epoch": 0.2372629555186577,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997464795232877,
|
|
"loss": 6.2201,
|
|
"mean_token_accuracy": 0.13575974926352502,
|
|
"num_tokens": 5524419.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.417884826660156,
|
|
"epoch": 0.23769990387136242,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997449985297782,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.13905856385827065,
|
|
"num_tokens": 5534289.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.332362174987793,
|
|
"epoch": 0.2381368522240671,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997435132255418,
|
|
"loss": 6.1802,
|
|
"mean_token_accuracy": 0.1442882761359215,
|
|
"num_tokens": 5543034.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.458979845046997,
|
|
"epoch": 0.23857380057677183,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997420236106071,
|
|
"loss": 6.2378,
|
|
"mean_token_accuracy": 0.1366375796496868,
|
|
"num_tokens": 5553291.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.407902002334595,
|
|
"epoch": 0.23901074892947655,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997405296850026,
|
|
"loss": 6.2287,
|
|
"mean_token_accuracy": 0.13833343163132666,
|
|
"num_tokens": 5563772.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.36975212097168,
|
|
"epoch": 0.23944769728218124,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997390314487569,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.13527763187885283,
|
|
"num_tokens": 5574348.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.397701358795166,
|
|
"epoch": 0.23988464563488596,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997375289018989,
|
|
"loss": 6.12,
|
|
"mean_token_accuracy": 0.13704326897859573,
|
|
"num_tokens": 5583491.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.280293273925781,
|
|
"epoch": 0.24032159398759068,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997360220444574,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.13119822591543198,
|
|
"num_tokens": 5594273.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.4317409038543705,
|
|
"epoch": 0.24075854234029537,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997345108764611,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.1414405457675457,
|
|
"num_tokens": 5604529.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.3399059772491455,
|
|
"epoch": 0.2411954906930001,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997329953979391,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.1501401461660862,
|
|
"num_tokens": 5614036.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.434519290924072,
|
|
"epoch": 0.2416324390457048,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997314756089206,
|
|
"loss": 6.2155,
|
|
"mean_token_accuracy": 0.1381111390888691,
|
|
"num_tokens": 5624036.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.3883912563323975,
|
|
"epoch": 0.2420693873984095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997299515094347,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.14164475947618485,
|
|
"num_tokens": 5633987.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.329027700424194,
|
|
"epoch": 0.24250633575111422,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997284230995105,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.15508053749799727,
|
|
"num_tokens": 5643905.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.36656379699707,
|
|
"epoch": 0.24294328410381894,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997268903791773,
|
|
"loss": 6.2894,
|
|
"mean_token_accuracy": 0.13616579845547677,
|
|
"num_tokens": 5654922.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.366892242431641,
|
|
"epoch": 0.24338023245652363,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997253533484647,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.14602213948965073,
|
|
"num_tokens": 5664407.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.357431697845459,
|
|
"epoch": 0.24381718080922835,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997238120074021,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.13616643026471137,
|
|
"num_tokens": 5674524.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.405643796920776,
|
|
"epoch": 0.24425412916193306,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997222663560188,
|
|
"loss": 6.228,
|
|
"mean_token_accuracy": 0.13521140292286873,
|
|
"num_tokens": 5684691.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.368612289428711,
|
|
"epoch": 0.24469107751463778,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997207163943449,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.1438075728714466,
|
|
"num_tokens": 5693683.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.34757628440857,
|
|
"epoch": 0.24512802586734248,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997191621224098,
|
|
"loss": 6.2258,
|
|
"mean_token_accuracy": 0.13985715731978415,
|
|
"num_tokens": 5704394.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.330892181396484,
|
|
"epoch": 0.2455649742200472,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997176035402435,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.14314275234937668,
|
|
"num_tokens": 5715480.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.420187997817993,
|
|
"epoch": 0.2460019225727519,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997160406478758,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.1458885796368122,
|
|
"num_tokens": 5725973.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.216833543777466,
|
|
"epoch": 0.2464388709254566,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 6.1469,
|
|
"mean_token_accuracy": 0.14866761416196822,
|
|
"num_tokens": 5735798.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.44745454788208,
|
|
"epoch": 0.24687581927816132,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997129019326562,
|
|
"loss": 6.2351,
|
|
"mean_token_accuracy": 0.13342514783143997,
|
|
"num_tokens": 5746623.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.438055801391601,
|
|
"epoch": 0.24731276763086604,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997113261098645,
|
|
"loss": 6.179,
|
|
"mean_token_accuracy": 0.14569296687841415,
|
|
"num_tokens": 5756526.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.3516847610473635,
|
|
"epoch": 0.24774971598357073,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997097459769919,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.14307619631290436,
|
|
"num_tokens": 5766670.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.425496816635132,
|
|
"epoch": 0.24818666433627545,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997081615340685,
|
|
"loss": 6.2188,
|
|
"mean_token_accuracy": 0.1372871719300747,
|
|
"num_tokens": 5776473.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.430360794067383,
|
|
"epoch": 0.24862361268898017,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997065727811249,
|
|
"loss": 6.2628,
|
|
"mean_token_accuracy": 0.13984661772847176,
|
|
"num_tokens": 5787059.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.357260465621948,
|
|
"epoch": 0.24906056104168486,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997049797181915,
|
|
"loss": 6.2442,
|
|
"mean_token_accuracy": 0.13402743339538575,
|
|
"num_tokens": 5797367.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.306977415084839,
|
|
"epoch": 0.24949750939438958,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997033823452988,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.1462322786450386,
|
|
"num_tokens": 5806704.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.339516878128052,
|
|
"epoch": 0.2499344577470943,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997017806624774,
|
|
"loss": 6.2057,
|
|
"mean_token_accuracy": 0.1426796108484268,
|
|
"num_tokens": 5817797.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.462503385543823,
|
|
"epoch": 0.250371406099799,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997001746697582,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.14381124824285507,
|
|
"num_tokens": 5829270.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.333521842956543,
|
|
"epoch": 0.2508083544525037,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996985643671719,
|
|
"loss": 6.1819,
|
|
"mean_token_accuracy": 0.1438910335302353,
|
|
"num_tokens": 5839214.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.331501054763794,
|
|
"epoch": 0.2512453028052084,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996969497547495,
|
|
"loss": 6.1694,
|
|
"mean_token_accuracy": 0.13977854549884797,
|
|
"num_tokens": 5848171.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.337689781188965,
|
|
"epoch": 0.25168225115791315,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996953308325217,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.14665822237730025,
|
|
"num_tokens": 5858399.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.259796857833862,
|
|
"epoch": 0.25211919951061784,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996937076005198,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.1473238319158554,
|
|
"num_tokens": 5868212.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.379367685317993,
|
|
"epoch": 0.25255614786332253,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996920800587749,
|
|
"loss": 6.1579,
|
|
"mean_token_accuracy": 0.1477441743016243,
|
|
"num_tokens": 5877883.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.401600027084351,
|
|
"epoch": 0.2529930962160273,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996904482073181,
|
|
"loss": 6.1745,
|
|
"mean_token_accuracy": 0.1420045681297779,
|
|
"num_tokens": 5887090.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.228640031814575,
|
|
"epoch": 0.25343004456873197,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996888120461808,
|
|
"loss": 6.2163,
|
|
"mean_token_accuracy": 0.13503760173916818,
|
|
"num_tokens": 5897491.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.423250532150268,
|
|
"epoch": 0.25386699292143666,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996871715753943,
|
|
"loss": 6.2207,
|
|
"mean_token_accuracy": 0.14232490286231042,
|
|
"num_tokens": 5908494.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.44255633354187,
|
|
"epoch": 0.2543039412741414,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049968552679499,
|
|
"loss": 6.2737,
|
|
"mean_token_accuracy": 0.12691745460033416,
|
|
"num_tokens": 5919708.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.353352165222168,
|
|
"epoch": 0.2547408896268461,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996838777049998,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.14446713924407958,
|
|
"num_tokens": 5930122.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.272373819351197,
|
|
"epoch": 0.2551778379795508,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499682224305455,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.13961574882268907,
|
|
"num_tokens": 5940033.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.319667816162109,
|
|
"epoch": 0.25561478633225554,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996805665963874,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.141078320145607,
|
|
"num_tokens": 5949335.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.390504455566406,
|
|
"epoch": 0.25605173468496023,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996789045778287,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.14173810854554175,
|
|
"num_tokens": 5959299.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.357183980941772,
|
|
"epoch": 0.2564886830376649,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996772382498111,
|
|
"loss": 6.1365,
|
|
"mean_token_accuracy": 0.13954563736915587,
|
|
"num_tokens": 5970114.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.311671018600464,
|
|
"epoch": 0.25692563139036967,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996755676123662,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.1331164039671421,
|
|
"num_tokens": 5979630.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.456780195236206,
|
|
"epoch": 0.25736257974307436,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996738926655262,
|
|
"loss": 6.2217,
|
|
"mean_token_accuracy": 0.13437832593917848,
|
|
"num_tokens": 5990190.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.370059871673584,
|
|
"epoch": 0.25779952809577905,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996722134093231,
|
|
"loss": 6.2331,
|
|
"mean_token_accuracy": 0.13279297351837158,
|
|
"num_tokens": 6000706.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.242281103134156,
|
|
"epoch": 0.2582364764484838,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996705298437894,
|
|
"loss": 6.2095,
|
|
"mean_token_accuracy": 0.14207181483507156,
|
|
"num_tokens": 6011274.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.422606420516968,
|
|
"epoch": 0.2586734248011885,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996688419689572,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.14407445564866067,
|
|
"num_tokens": 6021481.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.295702743530273,
|
|
"epoch": 0.25911037315389324,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996671497848589,
|
|
"loss": 6.2045,
|
|
"mean_token_accuracy": 0.14156209751963617,
|
|
"num_tokens": 6032091.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.362182235717773,
|
|
"epoch": 0.25954732150659793,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996654532915269,
|
|
"loss": 6.1971,
|
|
"mean_token_accuracy": 0.13414182811975478,
|
|
"num_tokens": 6043371.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.409013032913208,
|
|
"epoch": 0.2599842698593026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996637524889937,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.1435550257563591,
|
|
"num_tokens": 6052812.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.265077257156372,
|
|
"epoch": 0.26042121821200737,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996620473772921,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.14507505744695665,
|
|
"num_tokens": 6064033.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.355175495147705,
|
|
"epoch": 0.26085816656471206,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996603379564546,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.13743579238653184,
|
|
"num_tokens": 6075837.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.47666974067688,
|
|
"epoch": 0.26129511491741675,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996586242265142,
|
|
"loss": 6.1525,
|
|
"mean_token_accuracy": 0.14620224833488465,
|
|
"num_tokens": 6085514.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.294611263275146,
|
|
"epoch": 0.2617320632701215,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996569061875036,
|
|
"loss": 6.0654,
|
|
"mean_token_accuracy": 0.1461657240986824,
|
|
"num_tokens": 6094992.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.339985752105713,
|
|
"epoch": 0.2621690116228262,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996551838394559,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.14486877620220184,
|
|
"num_tokens": 6104841.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2621690116228262,
|
|
"eval_entropy": 6.096288530878612,
|
|
"eval_loss": 6.168129920959473,
|
|
"eval_mean_token_accuracy": 0.14990296079035464,
|
|
"eval_num_tokens": 6104841.0,
|
|
"eval_runtime": 21.503,
|
|
"eval_samples_per_second": 1721.34,
|
|
"eval_steps_per_second": 215.179,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"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": 1356222751211520.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|