b690a81c61
Model: fpadovani/rus-cyrl-100mb-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": 7.637994861602783,
|
|
"epoch": 0.0004369483527047103,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.5197,
|
|
"mean_token_accuracy": 0.0836352527141571,
|
|
"num_tokens": 10478.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.623341083526611,
|
|
"epoch": 0.0008738967054094206,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.5301,
|
|
"mean_token_accuracy": 0.08603608533740044,
|
|
"num_tokens": 21152.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.645789051055909,
|
|
"epoch": 0.0013108450581141308,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.552,
|
|
"mean_token_accuracy": 0.08498126044869422,
|
|
"num_tokens": 31246.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.679685497283936,
|
|
"epoch": 0.0017477934108188413,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.5895,
|
|
"mean_token_accuracy": 0.07903653383255005,
|
|
"num_tokens": 41934.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.792749309539795,
|
|
"epoch": 0.0021847417635235517,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.5444,
|
|
"mean_token_accuracy": 0.08353051990270614,
|
|
"num_tokens": 52830.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.786162900924682,
|
|
"epoch": 0.0026216901162282617,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.5,
|
|
"mean_token_accuracy": 0.08886836394667626,
|
|
"num_tokens": 62706.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.815877103805542,
|
|
"epoch": 0.003058638468932972,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.5486,
|
|
"mean_token_accuracy": 0.08427426405251026,
|
|
"num_tokens": 72619.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.870150184631347,
|
|
"epoch": 0.0034955868216376825,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.5448,
|
|
"mean_token_accuracy": 0.08383063822984696,
|
|
"num_tokens": 82903.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.800839138031006,
|
|
"epoch": 0.003932535174342393,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.5341,
|
|
"mean_token_accuracy": 0.09498083963990211,
|
|
"num_tokens": 94243.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.756237649917603,
|
|
"epoch": 0.004369483527047103,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.4765,
|
|
"mean_token_accuracy": 0.08740946426987647,
|
|
"num_tokens": 103618.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.747218179702759,
|
|
"epoch": 0.004806431879751813,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.5363,
|
|
"mean_token_accuracy": 0.08639938347041606,
|
|
"num_tokens": 112180.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.8047871589660645,
|
|
"epoch": 0.005243380232456523,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.5337,
|
|
"mean_token_accuracy": 0.08548481613397599,
|
|
"num_tokens": 122462.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.848284912109375,
|
|
"epoch": 0.005680328585161234,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.5602,
|
|
"mean_token_accuracy": 0.08545567914843559,
|
|
"num_tokens": 132741.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.7641541957855225,
|
|
"epoch": 0.006117276937865944,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.3675,
|
|
"mean_token_accuracy": 0.09678877294063568,
|
|
"num_tokens": 142973.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.738112068176269,
|
|
"epoch": 0.006554225290570655,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.5937,
|
|
"mean_token_accuracy": 0.08664538338780403,
|
|
"num_tokens": 153199.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.7370462894439695,
|
|
"epoch": 0.006991173643275365,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.4445,
|
|
"mean_token_accuracy": 0.09458591938018798,
|
|
"num_tokens": 163079.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.807093095779419,
|
|
"epoch": 0.0074281219959800755,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.4872,
|
|
"mean_token_accuracy": 0.08863211423158646,
|
|
"num_tokens": 173308.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.725804328918457,
|
|
"epoch": 0.007865070348684786,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.5445,
|
|
"mean_token_accuracy": 0.09568502977490426,
|
|
"num_tokens": 183856.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.763433265686035,
|
|
"epoch": 0.008302018701389496,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.4676,
|
|
"mean_token_accuracy": 0.08726829290390015,
|
|
"num_tokens": 193368.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.7914244651794435,
|
|
"epoch": 0.008738967054094207,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.5028,
|
|
"mean_token_accuracy": 0.08547773025929928,
|
|
"num_tokens": 202686.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.707356786727905,
|
|
"epoch": 0.009175915406798917,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.4556,
|
|
"mean_token_accuracy": 0.08999297693371773,
|
|
"num_tokens": 213237.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.722362422943116,
|
|
"epoch": 0.009612863759503626,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.4589,
|
|
"mean_token_accuracy": 0.09247651025652885,
|
|
"num_tokens": 222406.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.7970898151397705,
|
|
"epoch": 0.010049812112208336,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.5187,
|
|
"mean_token_accuracy": 0.0885585032403469,
|
|
"num_tokens": 232139.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.722547149658203,
|
|
"epoch": 0.010486760464913047,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.4757,
|
|
"mean_token_accuracy": 0.08926801681518555,
|
|
"num_tokens": 242438.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.695586252212524,
|
|
"epoch": 0.010923708817617757,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.4684,
|
|
"mean_token_accuracy": 0.08990140855312348,
|
|
"num_tokens": 253082.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.861955642700195,
|
|
"epoch": 0.011360657170322468,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.4714,
|
|
"mean_token_accuracy": 0.09366248250007629,
|
|
"num_tokens": 264067.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.758950090408325,
|
|
"epoch": 0.011797605523027178,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.4561,
|
|
"mean_token_accuracy": 0.08862813860177994,
|
|
"num_tokens": 274571.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.681786012649536,
|
|
"epoch": 0.012234553875731888,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.4413,
|
|
"mean_token_accuracy": 0.09196381121873856,
|
|
"num_tokens": 284561.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.749648571014404,
|
|
"epoch": 0.012671502228436599,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.3464,
|
|
"mean_token_accuracy": 0.09177442193031311,
|
|
"num_tokens": 295366.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.664951229095459,
|
|
"epoch": 0.01310845058114131,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.5296,
|
|
"mean_token_accuracy": 0.08601538985967636,
|
|
"num_tokens": 305423.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.767955684661866,
|
|
"epoch": 0.01354539893384602,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.4251,
|
|
"mean_token_accuracy": 0.08934596404433251,
|
|
"num_tokens": 315182.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.662592172622681,
|
|
"epoch": 0.01398234728655073,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.459,
|
|
"mean_token_accuracy": 0.08355334773659706,
|
|
"num_tokens": 324780.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.84730715751648,
|
|
"epoch": 0.01441929563925544,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.5123,
|
|
"mean_token_accuracy": 0.0899798959493637,
|
|
"num_tokens": 335104.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.775908184051514,
|
|
"epoch": 0.014856243991960151,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.4946,
|
|
"mean_token_accuracy": 0.08976865485310555,
|
|
"num_tokens": 345073.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.828866195678711,
|
|
"epoch": 0.015293192344664861,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.4994,
|
|
"mean_token_accuracy": 0.08743183836340904,
|
|
"num_tokens": 354342.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.731208658218383,
|
|
"epoch": 0.015730140697369572,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.4269,
|
|
"mean_token_accuracy": 0.08921334892511368,
|
|
"num_tokens": 364441.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.805326890945435,
|
|
"epoch": 0.01616708905007428,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.4345,
|
|
"mean_token_accuracy": 0.08910228461027145,
|
|
"num_tokens": 373918.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.738444805145264,
|
|
"epoch": 0.016604037402778993,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.5209,
|
|
"mean_token_accuracy": 0.08797775506973267,
|
|
"num_tokens": 383273.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.697931146621704,
|
|
"epoch": 0.0170409857554837,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.357,
|
|
"mean_token_accuracy": 0.09655481651425361,
|
|
"num_tokens": 393262.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.8257646560668945,
|
|
"epoch": 0.017477934108188414,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.4976,
|
|
"mean_token_accuracy": 0.08942469507455826,
|
|
"num_tokens": 402389.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.703541660308838,
|
|
"epoch": 0.017914882460893122,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4401,
|
|
"mean_token_accuracy": 0.09125433415174485,
|
|
"num_tokens": 412997.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.828316783905029,
|
|
"epoch": 0.018351830813597834,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4592,
|
|
"mean_token_accuracy": 0.0881546139717102,
|
|
"num_tokens": 422222.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.572913932800293,
|
|
"epoch": 0.018788779166302543,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.4023,
|
|
"mean_token_accuracy": 0.09697630628943443,
|
|
"num_tokens": 432539.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.832680416107178,
|
|
"epoch": 0.019225727519007252,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.4286,
|
|
"mean_token_accuracy": 0.09254593029618263,
|
|
"num_tokens": 442311.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.6697183609008786,
|
|
"epoch": 0.019662675871711964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3919,
|
|
"mean_token_accuracy": 0.0872996911406517,
|
|
"num_tokens": 452727.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.759046792984009,
|
|
"epoch": 0.020099624224416673,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.4466,
|
|
"mean_token_accuracy": 0.09114575162529945,
|
|
"num_tokens": 462461.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.685237169265747,
|
|
"epoch": 0.020536572577121385,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.4258,
|
|
"mean_token_accuracy": 0.08979431167244911,
|
|
"num_tokens": 472362.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.747664165496826,
|
|
"epoch": 0.020973520929826094,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.4573,
|
|
"mean_token_accuracy": 0.08877176120877266,
|
|
"num_tokens": 482718.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.68355770111084,
|
|
"epoch": 0.021410469282530806,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.3976,
|
|
"mean_token_accuracy": 0.09123231843113899,
|
|
"num_tokens": 492947.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.7995494365692135,
|
|
"epoch": 0.021847417635235514,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.4648,
|
|
"mean_token_accuracy": 0.08322979286313056,
|
|
"num_tokens": 502957.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.740732431411743,
|
|
"epoch": 0.022284365987940227,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4177,
|
|
"mean_token_accuracy": 0.08514684960246086,
|
|
"num_tokens": 513220.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.732230281829834,
|
|
"epoch": 0.022721314340644935,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.3827,
|
|
"mean_token_accuracy": 0.08738726824522018,
|
|
"num_tokens": 523217.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.6845520496368405,
|
|
"epoch": 0.023158262693349647,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.4167,
|
|
"mean_token_accuracy": 0.0847338579595089,
|
|
"num_tokens": 533789.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.76469612121582,
|
|
"epoch": 0.023595211046054356,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.3767,
|
|
"mean_token_accuracy": 0.09299462959170342,
|
|
"num_tokens": 544146.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.644073247909546,
|
|
"epoch": 0.02403215939875907,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.4063,
|
|
"mean_token_accuracy": 0.09182784631848336,
|
|
"num_tokens": 554215.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.711794137954712,
|
|
"epoch": 0.024469107751463777,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.4101,
|
|
"mean_token_accuracy": 0.08731252029538154,
|
|
"num_tokens": 564587.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.801581239700317,
|
|
"epoch": 0.024906056104168486,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.4581,
|
|
"mean_token_accuracy": 0.08540895506739617,
|
|
"num_tokens": 574819.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.712231540679932,
|
|
"epoch": 0.025343004456873198,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.3978,
|
|
"mean_token_accuracy": 0.08907487243413925,
|
|
"num_tokens": 585178.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.57398829460144,
|
|
"epoch": 0.025779952809577907,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.3785,
|
|
"mean_token_accuracy": 0.09169624000787735,
|
|
"num_tokens": 595086.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.753789281845092,
|
|
"epoch": 0.02621690116228262,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.4015,
|
|
"mean_token_accuracy": 0.08911786824464799,
|
|
"num_tokens": 604942.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.740912914276123,
|
|
"epoch": 0.026653849514987327,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.365,
|
|
"mean_token_accuracy": 0.09200693666934967,
|
|
"num_tokens": 616082.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.668862152099609,
|
|
"epoch": 0.02709079786769204,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.4392,
|
|
"mean_token_accuracy": 0.0856046225875616,
|
|
"num_tokens": 626375.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.629800462722779,
|
|
"epoch": 0.027527746220396748,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.3741,
|
|
"mean_token_accuracy": 0.0859305128455162,
|
|
"num_tokens": 637563.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.764728212356568,
|
|
"epoch": 0.02796469457310146,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.3935,
|
|
"mean_token_accuracy": 0.09147773832082748,
|
|
"num_tokens": 647256.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.690927219390869,
|
|
"epoch": 0.02840164292580617,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.4189,
|
|
"mean_token_accuracy": 0.0867665283381939,
|
|
"num_tokens": 657247.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.781694221496582,
|
|
"epoch": 0.02883859127851088,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.3252,
|
|
"mean_token_accuracy": 0.08868500515818596,
|
|
"num_tokens": 667613.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.653351449966431,
|
|
"epoch": 0.02927553963121559,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.3939,
|
|
"mean_token_accuracy": 0.09035046473145485,
|
|
"num_tokens": 678048.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.669305658340454,
|
|
"epoch": 0.029712487983920302,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.3691,
|
|
"mean_token_accuracy": 0.09391902461647987,
|
|
"num_tokens": 688468.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.645442485809326,
|
|
"epoch": 0.03014943633662501,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.3628,
|
|
"mean_token_accuracy": 0.09365171119570732,
|
|
"num_tokens": 699809.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.640151834487915,
|
|
"epoch": 0.030586384689329723,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.3112,
|
|
"mean_token_accuracy": 0.0941974550485611,
|
|
"num_tokens": 709227.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.659973907470703,
|
|
"epoch": 0.03102333304203443,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.4041,
|
|
"mean_token_accuracy": 0.08795862942934037,
|
|
"num_tokens": 720178.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.749969959259033,
|
|
"epoch": 0.031460281394739144,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.3598,
|
|
"mean_token_accuracy": 0.0944575697183609,
|
|
"num_tokens": 730514.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.634895277023316,
|
|
"epoch": 0.03189722974744385,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.4221,
|
|
"mean_token_accuracy": 0.09183157607913017,
|
|
"num_tokens": 741345.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.632371330261231,
|
|
"epoch": 0.03233417810014856,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.3275,
|
|
"mean_token_accuracy": 0.09244873151183128,
|
|
"num_tokens": 751163.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.697724151611328,
|
|
"epoch": 0.03277112645285327,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.3143,
|
|
"mean_token_accuracy": 0.08760180100798606,
|
|
"num_tokens": 762090.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.604908990859985,
|
|
"epoch": 0.033208074805557986,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.299,
|
|
"mean_token_accuracy": 0.09711357578635216,
|
|
"num_tokens": 772049.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.570729303359985,
|
|
"epoch": 0.03364502315826269,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.2903,
|
|
"mean_token_accuracy": 0.0953090362250805,
|
|
"num_tokens": 781280.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.673049736022949,
|
|
"epoch": 0.0340819715109674,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.3234,
|
|
"mean_token_accuracy": 0.09910958260297775,
|
|
"num_tokens": 791642.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.579310750961303,
|
|
"epoch": 0.034518919863672115,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.3467,
|
|
"mean_token_accuracy": 0.09289622604846955,
|
|
"num_tokens": 801224.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.6497889995574955,
|
|
"epoch": 0.03495586821637683,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.2947,
|
|
"mean_token_accuracy": 0.092826696485281,
|
|
"num_tokens": 810727.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.73345537185669,
|
|
"epoch": 0.03539281656908153,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.3824,
|
|
"mean_token_accuracy": 0.08923227414488792,
|
|
"num_tokens": 819943.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.517602396011353,
|
|
"epoch": 0.035829764921786245,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.2848,
|
|
"mean_token_accuracy": 0.09139850735664368,
|
|
"num_tokens": 829474.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.638075828552246,
|
|
"epoch": 0.03626671327449096,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.2934,
|
|
"mean_token_accuracy": 0.0908023789525032,
|
|
"num_tokens": 839288.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.616179609298706,
|
|
"epoch": 0.03670366162719567,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.2845,
|
|
"mean_token_accuracy": 0.09343387261033058,
|
|
"num_tokens": 850064.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.491023874282837,
|
|
"epoch": 0.037140609979900374,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.2923,
|
|
"mean_token_accuracy": 0.09214133247733117,
|
|
"num_tokens": 860732.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.562995529174804,
|
|
"epoch": 0.037577558332605086,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.2648,
|
|
"mean_token_accuracy": 0.09335138648748398,
|
|
"num_tokens": 870076.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.482726287841797,
|
|
"epoch": 0.0380145066853098,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.1828,
|
|
"mean_token_accuracy": 0.09552065506577492,
|
|
"num_tokens": 880201.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.537555170059204,
|
|
"epoch": 0.038451455038014504,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.2454,
|
|
"mean_token_accuracy": 0.09459976553916931,
|
|
"num_tokens": 890344.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.510470342636109,
|
|
"epoch": 0.038888403390719216,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.2468,
|
|
"mean_token_accuracy": 0.09458372145891189,
|
|
"num_tokens": 900443.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.594428253173828,
|
|
"epoch": 0.03932535174342393,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.2734,
|
|
"mean_token_accuracy": 0.09156661406159401,
|
|
"num_tokens": 910284.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.5778489112854,
|
|
"epoch": 0.03976230009612864,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.3465,
|
|
"mean_token_accuracy": 0.09012126699090003,
|
|
"num_tokens": 920986.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.58350772857666,
|
|
"epoch": 0.040199248448833345,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.2518,
|
|
"mean_token_accuracy": 0.09617682099342346,
|
|
"num_tokens": 930481.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.555335330963135,
|
|
"epoch": 0.04063619680153806,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.2733,
|
|
"mean_token_accuracy": 0.09550615251064301,
|
|
"num_tokens": 940554.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.51325364112854,
|
|
"epoch": 0.04107314515424277,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.2389,
|
|
"mean_token_accuracy": 0.09795199707150459,
|
|
"num_tokens": 950005.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.518522882461548,
|
|
"epoch": 0.04151009350694748,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.2443,
|
|
"mean_token_accuracy": 0.0910925917327404,
|
|
"num_tokens": 959414.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.530915355682373,
|
|
"epoch": 0.04194704185965219,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.259,
|
|
"mean_token_accuracy": 0.09173793643712998,
|
|
"num_tokens": 969352.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.570693063735962,
|
|
"epoch": 0.0423839902123569,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.2917,
|
|
"mean_token_accuracy": 0.08883628323674202,
|
|
"num_tokens": 980294.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.439288902282715,
|
|
"epoch": 0.04282093856506161,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.1819,
|
|
"mean_token_accuracy": 0.09918189346790314,
|
|
"num_tokens": 990453.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.474934530258179,
|
|
"epoch": 0.04325788691776632,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.1861,
|
|
"mean_token_accuracy": 0.10081736147403716,
|
|
"num_tokens": 1000509.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.503030824661255,
|
|
"epoch": 0.04369483527047103,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.3407,
|
|
"mean_token_accuracy": 0.08743650615215301,
|
|
"num_tokens": 1011747.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.507284879684448,
|
|
"epoch": 0.04413178362317574,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.2963,
|
|
"mean_token_accuracy": 0.086452054977417,
|
|
"num_tokens": 1021511.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.546348524093628,
|
|
"epoch": 0.04456873197588045,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.302,
|
|
"mean_token_accuracy": 0.08823695406317711,
|
|
"num_tokens": 1032116.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.467855310440063,
|
|
"epoch": 0.04500568032858516,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.1938,
|
|
"mean_token_accuracy": 0.09948761016130447,
|
|
"num_tokens": 1041356.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.516360902786255,
|
|
"epoch": 0.04544262868128987,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.2624,
|
|
"mean_token_accuracy": 0.09001169204711915,
|
|
"num_tokens": 1051314.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.522716856002807,
|
|
"epoch": 0.04587957703399458,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.2206,
|
|
"mean_token_accuracy": 0.09518473073840142,
|
|
"num_tokens": 1060857.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.510475397109985,
|
|
"epoch": 0.046316525386699295,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.2541,
|
|
"mean_token_accuracy": 0.095691280066967,
|
|
"num_tokens": 1071744.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.459283924102783,
|
|
"epoch": 0.046753473739404,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.2165,
|
|
"mean_token_accuracy": 0.09503942206501961,
|
|
"num_tokens": 1080777.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.485194826126099,
|
|
"epoch": 0.04719042209210871,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.2191,
|
|
"mean_token_accuracy": 0.09791651666164398,
|
|
"num_tokens": 1090951.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.405230283737183,
|
|
"epoch": 0.047627370444813424,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.1784,
|
|
"mean_token_accuracy": 0.09603556096553803,
|
|
"num_tokens": 1101667.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.466827440261841,
|
|
"epoch": 0.04806431879751814,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.3023,
|
|
"mean_token_accuracy": 0.08709683492779732,
|
|
"num_tokens": 1112652.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.492521619796753,
|
|
"epoch": 0.04850126715022284,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.232,
|
|
"mean_token_accuracy": 0.09334004074335098,
|
|
"num_tokens": 1122518.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.511386775970459,
|
|
"epoch": 0.048938215502927554,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.2466,
|
|
"mean_token_accuracy": 0.09488805904984474,
|
|
"num_tokens": 1132867.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.544691753387451,
|
|
"epoch": 0.049375163855632266,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.33,
|
|
"mean_token_accuracy": 0.08940334022045135,
|
|
"num_tokens": 1142524.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.499535369873047,
|
|
"epoch": 0.04981211220833697,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.1969,
|
|
"mean_token_accuracy": 0.1014377273619175,
|
|
"num_tokens": 1152983.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.482742214202881,
|
|
"epoch": 0.050249060561041684,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.2659,
|
|
"mean_token_accuracy": 0.09228436276316643,
|
|
"num_tokens": 1164271.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.432041788101197,
|
|
"epoch": 0.050686008913746396,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.1369,
|
|
"mean_token_accuracy": 0.0982656441628933,
|
|
"num_tokens": 1173567.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.360566711425781,
|
|
"epoch": 0.05112295726645111,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.194,
|
|
"mean_token_accuracy": 0.09685536473989487,
|
|
"num_tokens": 1183619.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.399991750717163,
|
|
"epoch": 0.05155990561915581,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.1451,
|
|
"mean_token_accuracy": 0.09111583679914474,
|
|
"num_tokens": 1193922.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.478466176986695,
|
|
"epoch": 0.051996853971860525,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.2197,
|
|
"mean_token_accuracy": 0.09398753717541694,
|
|
"num_tokens": 1203665.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.44222354888916,
|
|
"epoch": 0.05243380232456524,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.23,
|
|
"mean_token_accuracy": 0.09689271599054336,
|
|
"num_tokens": 1214119.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.460528373718262,
|
|
"epoch": 0.05287075067726995,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.2427,
|
|
"mean_token_accuracy": 0.09010300114750862,
|
|
"num_tokens": 1225275.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.30951566696167,
|
|
"epoch": 0.053307699029974655,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.1342,
|
|
"mean_token_accuracy": 0.09279084131121636,
|
|
"num_tokens": 1235199.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.454565858840942,
|
|
"epoch": 0.05374464738267937,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.1556,
|
|
"mean_token_accuracy": 0.0968701608479023,
|
|
"num_tokens": 1245648.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.305359888076782,
|
|
"epoch": 0.05418159573538408,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.1208,
|
|
"mean_token_accuracy": 0.10165121629834176,
|
|
"num_tokens": 1254793.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.404820203781128,
|
|
"epoch": 0.05461854408808879,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.1588,
|
|
"mean_token_accuracy": 0.0971425749361515,
|
|
"num_tokens": 1264429.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.337283086776734,
|
|
"epoch": 0.055055492440793496,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.1419,
|
|
"mean_token_accuracy": 0.0944690503180027,
|
|
"num_tokens": 1274449.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.475021743774414,
|
|
"epoch": 0.05549244079349821,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.2603,
|
|
"mean_token_accuracy": 0.09432755038142204,
|
|
"num_tokens": 1284987.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.418339729309082,
|
|
"epoch": 0.05592938914620292,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.2474,
|
|
"mean_token_accuracy": 0.08950235322117805,
|
|
"num_tokens": 1295984.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.26748685836792,
|
|
"epoch": 0.056366337498907626,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.1544,
|
|
"mean_token_accuracy": 0.09836009740829468,
|
|
"num_tokens": 1305738.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.405171012878418,
|
|
"epoch": 0.05680328585161234,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.0997,
|
|
"mean_token_accuracy": 0.09074313640594482,
|
|
"num_tokens": 1315691.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.292159748077393,
|
|
"epoch": 0.05724023420431705,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.1171,
|
|
"mean_token_accuracy": 0.10072707086801529,
|
|
"num_tokens": 1326195.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.338443660736084,
|
|
"epoch": 0.05767718255702176,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.1405,
|
|
"mean_token_accuracy": 0.09912769198417663,
|
|
"num_tokens": 1336916.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.30134425163269,
|
|
"epoch": 0.05811413090972647,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.1773,
|
|
"mean_token_accuracy": 0.09219239056110382,
|
|
"num_tokens": 1347386.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.414137363433838,
|
|
"epoch": 0.05855107926243118,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.1208,
|
|
"mean_token_accuracy": 0.09784709438681602,
|
|
"num_tokens": 1357959.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.263702297210694,
|
|
"epoch": 0.05898802761513589,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.1354,
|
|
"mean_token_accuracy": 0.09500606879591941,
|
|
"num_tokens": 1368135.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.372778415679932,
|
|
"epoch": 0.059424975967840604,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.1653,
|
|
"mean_token_accuracy": 0.0939582608640194,
|
|
"num_tokens": 1378702.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.19251708984375,
|
|
"epoch": 0.05986192432054531,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.0456,
|
|
"mean_token_accuracy": 0.09847457632422447,
|
|
"num_tokens": 1387902.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.3456488132476805,
|
|
"epoch": 0.06029887267325002,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.0601,
|
|
"mean_token_accuracy": 0.10286817029118538,
|
|
"num_tokens": 1397288.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.266854667663575,
|
|
"epoch": 0.060735821025954734,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.0971,
|
|
"mean_token_accuracy": 0.10038763061165809,
|
|
"num_tokens": 1407416.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.384059572219849,
|
|
"epoch": 0.061172769378659446,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.1717,
|
|
"mean_token_accuracy": 0.09187826812267304,
|
|
"num_tokens": 1417733.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.187748289108276,
|
|
"epoch": 0.06160971773136415,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.0684,
|
|
"mean_token_accuracy": 0.09974993579089642,
|
|
"num_tokens": 1426723.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.310714626312256,
|
|
"epoch": 0.06204666608406886,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.1289,
|
|
"mean_token_accuracy": 0.0992344006896019,
|
|
"num_tokens": 1437290.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.245534753799438,
|
|
"epoch": 0.062483614436773575,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.0715,
|
|
"mean_token_accuracy": 0.09555437043309212,
|
|
"num_tokens": 1446756.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.302251720428467,
|
|
"epoch": 0.06292056278947829,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.1289,
|
|
"mean_token_accuracy": 0.09620894640684127,
|
|
"num_tokens": 1457074.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.223730421066284,
|
|
"epoch": 0.06335751114218299,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.2065,
|
|
"mean_token_accuracy": 0.08963397517800331,
|
|
"num_tokens": 1467785.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.307017707824707,
|
|
"epoch": 0.0637944594948877,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.0911,
|
|
"mean_token_accuracy": 0.09854559674859047,
|
|
"num_tokens": 1477532.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.1604907512664795,
|
|
"epoch": 0.06423140784759242,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.0269,
|
|
"mean_token_accuracy": 0.10236552879214286,
|
|
"num_tokens": 1487102.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.2588645935058596,
|
|
"epoch": 0.06466835620029712,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.1184,
|
|
"mean_token_accuracy": 0.0926779955625534,
|
|
"num_tokens": 1497459.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.252214527130127,
|
|
"epoch": 0.06510530455300184,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.1014,
|
|
"mean_token_accuracy": 0.09459270238876342,
|
|
"num_tokens": 1508756.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.249363708496094,
|
|
"epoch": 0.06554225290570655,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.021,
|
|
"mean_token_accuracy": 0.10529743134975433,
|
|
"num_tokens": 1518735.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.237057495117187,
|
|
"epoch": 0.06597920125841125,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.0688,
|
|
"mean_token_accuracy": 0.09851523265242576,
|
|
"num_tokens": 1528632.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.1528160572052,
|
|
"epoch": 0.06641614961111597,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.0595,
|
|
"mean_token_accuracy": 0.09594285860657692,
|
|
"num_tokens": 1538180.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.243620729446411,
|
|
"epoch": 0.06685309796382068,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.0977,
|
|
"mean_token_accuracy": 0.0974743902683258,
|
|
"num_tokens": 1547788.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.187331247329712,
|
|
"epoch": 0.06729004631652538,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.017,
|
|
"mean_token_accuracy": 0.100215582549572,
|
|
"num_tokens": 1558008.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.164813470840454,
|
|
"epoch": 0.0677269946692301,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.081,
|
|
"mean_token_accuracy": 0.09390448704361916,
|
|
"num_tokens": 1567728.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.256727600097657,
|
|
"epoch": 0.0681639430219348,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.0475,
|
|
"mean_token_accuracy": 0.09773643538355828,
|
|
"num_tokens": 1578488.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.129490995407105,
|
|
"epoch": 0.06860089137463951,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.0126,
|
|
"mean_token_accuracy": 0.10168901681900025,
|
|
"num_tokens": 1588070.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.209209394454956,
|
|
"epoch": 0.06903783972734423,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.0928,
|
|
"mean_token_accuracy": 0.09427050650119781,
|
|
"num_tokens": 1598572.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.211539697647095,
|
|
"epoch": 0.06947478808004894,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.0894,
|
|
"mean_token_accuracy": 0.09861121252179146,
|
|
"num_tokens": 1607982.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.200946855545044,
|
|
"epoch": 0.06991173643275365,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.1132,
|
|
"mean_token_accuracy": 0.09658989906311036,
|
|
"num_tokens": 1618785.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.177917003631592,
|
|
"epoch": 0.07034868478545836,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.0225,
|
|
"mean_token_accuracy": 0.09970952942967415,
|
|
"num_tokens": 1627988.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.200639438629151,
|
|
"epoch": 0.07078563313816306,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.1263,
|
|
"mean_token_accuracy": 0.09254502132534981,
|
|
"num_tokens": 1638024.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.2738360404968265,
|
|
"epoch": 0.07122258149086778,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.11,
|
|
"mean_token_accuracy": 0.09046216607093811,
|
|
"num_tokens": 1649215.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.09494981765747,
|
|
"epoch": 0.07165952984357249,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.0047,
|
|
"mean_token_accuracy": 0.09915160611271859,
|
|
"num_tokens": 1659198.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.139633274078369,
|
|
"epoch": 0.0720964781962772,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.0459,
|
|
"mean_token_accuracy": 0.0924466960132122,
|
|
"num_tokens": 1668972.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.046590662002563,
|
|
"epoch": 0.07253342654898191,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.0373,
|
|
"mean_token_accuracy": 0.0979261752218008,
|
|
"num_tokens": 1679807.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.146584796905517,
|
|
"epoch": 0.07297037490168662,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.0786,
|
|
"mean_token_accuracy": 0.09333261549472809,
|
|
"num_tokens": 1690567.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.060258579254151,
|
|
"epoch": 0.07340732325439134,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.9708,
|
|
"mean_token_accuracy": 0.10236304700374603,
|
|
"num_tokens": 1700939.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.0893957138061525,
|
|
"epoch": 0.07384427160709604,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.038,
|
|
"mean_token_accuracy": 0.10244481042027473,
|
|
"num_tokens": 1711181.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.2199750423431395,
|
|
"epoch": 0.07428121995980075,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.0547,
|
|
"mean_token_accuracy": 0.09390221312642097,
|
|
"num_tokens": 1721392.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.097149181365967,
|
|
"epoch": 0.07471816831250547,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.9883,
|
|
"mean_token_accuracy": 0.1020311638712883,
|
|
"num_tokens": 1731942.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.16186032295227,
|
|
"epoch": 0.07515511666521017,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.0872,
|
|
"mean_token_accuracy": 0.09683374986052513,
|
|
"num_tokens": 1743409.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.026008224487304,
|
|
"epoch": 0.07559206501791488,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.9834,
|
|
"mean_token_accuracy": 0.10218272209167481,
|
|
"num_tokens": 1753425.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.078909397125244,
|
|
"epoch": 0.0760290133706196,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.0062,
|
|
"mean_token_accuracy": 0.09942305907607078,
|
|
"num_tokens": 1762722.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.281267595291138,
|
|
"epoch": 0.0764659617233243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.0547,
|
|
"mean_token_accuracy": 0.09092987477779388,
|
|
"num_tokens": 1771895.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.075471496582031,
|
|
"epoch": 0.07690291007602901,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.9906,
|
|
"mean_token_accuracy": 0.10108151286840439,
|
|
"num_tokens": 1782175.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.135920286178589,
|
|
"epoch": 0.07733985842873373,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.0323,
|
|
"mean_token_accuracy": 0.09571060985326767,
|
|
"num_tokens": 1792409.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.1416253566741945,
|
|
"epoch": 0.07777680678143843,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.0772,
|
|
"mean_token_accuracy": 0.09155471846461297,
|
|
"num_tokens": 1802721.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.018156719207764,
|
|
"epoch": 0.07821375513414315,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.9152,
|
|
"mean_token_accuracy": 0.1009690523147583,
|
|
"num_tokens": 1812064.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.185165739059448,
|
|
"epoch": 0.07865070348684786,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.0243,
|
|
"mean_token_accuracy": 0.0946855939924717,
|
|
"num_tokens": 1822284.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.019971942901611,
|
|
"epoch": 0.07908765183955256,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.9408,
|
|
"mean_token_accuracy": 0.10249921903014184,
|
|
"num_tokens": 1832150.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.135112857818603,
|
|
"epoch": 0.07952460019225728,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.0546,
|
|
"mean_token_accuracy": 0.09617897793650627,
|
|
"num_tokens": 1842870.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.019263792037964,
|
|
"epoch": 0.07996154854496199,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.8767,
|
|
"mean_token_accuracy": 0.10999749973416328,
|
|
"num_tokens": 1852771.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.987358617782593,
|
|
"epoch": 0.08039849689766669,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.0028,
|
|
"mean_token_accuracy": 0.09920822754502297,
|
|
"num_tokens": 1863095.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.018406534194947,
|
|
"epoch": 0.08083544525037141,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.0192,
|
|
"mean_token_accuracy": 0.10134783908724784,
|
|
"num_tokens": 1873060.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.069212102890015,
|
|
"epoch": 0.08127239360307612,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.9396,
|
|
"mean_token_accuracy": 0.10620549395680427,
|
|
"num_tokens": 1882574.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.033281898498535,
|
|
"epoch": 0.08170934195578082,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.0066,
|
|
"mean_token_accuracy": 0.10208514109253883,
|
|
"num_tokens": 1892227.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.052687931060791,
|
|
"epoch": 0.08214629030848554,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.0234,
|
|
"mean_token_accuracy": 0.09568553268909455,
|
|
"num_tokens": 1902868.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.065501070022583,
|
|
"epoch": 0.08258323866119024,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.9832,
|
|
"mean_token_accuracy": 0.09660054594278336,
|
|
"num_tokens": 1912781.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.0425121784210205,
|
|
"epoch": 0.08302018701389496,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.9728,
|
|
"mean_token_accuracy": 0.10843080580234528,
|
|
"num_tokens": 1923638.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.016868972778321,
|
|
"epoch": 0.08345713536659967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.9288,
|
|
"mean_token_accuracy": 0.10849572941660882,
|
|
"num_tokens": 1933498.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.000980377197266,
|
|
"epoch": 0.08389408371930437,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.9509,
|
|
"mean_token_accuracy": 0.10340929329395294,
|
|
"num_tokens": 1943798.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.054853391647339,
|
|
"epoch": 0.0843310320720091,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.9966,
|
|
"mean_token_accuracy": 0.0966202974319458,
|
|
"num_tokens": 1954235.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.01042628288269,
|
|
"epoch": 0.0847679804247138,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.9834,
|
|
"mean_token_accuracy": 0.09832858666777611,
|
|
"num_tokens": 1964421.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.955400609970093,
|
|
"epoch": 0.0852049287774185,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.976,
|
|
"mean_token_accuracy": 0.10213669240474701,
|
|
"num_tokens": 1975862.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.061838102340698,
|
|
"epoch": 0.08564187713012322,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.9598,
|
|
"mean_token_accuracy": 0.09855997413396836,
|
|
"num_tokens": 1985758.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.923084402084351,
|
|
"epoch": 0.08607882548282793,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.9431,
|
|
"mean_token_accuracy": 0.09963723346590996,
|
|
"num_tokens": 1996904.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.119592952728271,
|
|
"epoch": 0.08651577383553263,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.023,
|
|
"mean_token_accuracy": 0.0975315362215042,
|
|
"num_tokens": 2006114.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.007775974273682,
|
|
"epoch": 0.08695272218823735,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.9555,
|
|
"mean_token_accuracy": 0.10550742074847222,
|
|
"num_tokens": 2016349.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.926405000686645,
|
|
"epoch": 0.08738967054094206,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.9055,
|
|
"mean_token_accuracy": 0.09952122941613198,
|
|
"num_tokens": 2026701.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.909988212585449,
|
|
"epoch": 0.08782661889364678,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999999986190023,
|
|
"loss": 6.8942,
|
|
"mean_token_accuracy": 0.10107116997241974,
|
|
"num_tokens": 2036950.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.06274824142456,
|
|
"epoch": 0.08826356724635148,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999999930086991,
|
|
"loss": 6.9046,
|
|
"mean_token_accuracy": 0.10389338061213493,
|
|
"num_tokens": 2047655.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.927995491027832,
|
|
"epoch": 0.08870051559905619,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499999983082778,
|
|
"loss": 6.8846,
|
|
"mean_token_accuracy": 0.10662774741649628,
|
|
"num_tokens": 2056800.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.8703173160552975,
|
|
"epoch": 0.0891374639517609,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999999688412394,
|
|
"loss": 6.9257,
|
|
"mean_token_accuracy": 0.10540272071957588,
|
|
"num_tokens": 2066862.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.05763463973999,
|
|
"epoch": 0.08957441230446561,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999502840836,
|
|
"loss": 6.9449,
|
|
"mean_token_accuracy": 0.1028741791844368,
|
|
"num_tokens": 2076585.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.949811029434204,
|
|
"epoch": 0.09001136065717032,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999999274113107,
|
|
"loss": 7.0015,
|
|
"mean_token_accuracy": 0.09622879326343536,
|
|
"num_tokens": 2087768.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.970440816879273,
|
|
"epoch": 0.09044830900987504,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999002229214,
|
|
"loss": 6.912,
|
|
"mean_token_accuracy": 0.1016117550432682,
|
|
"num_tokens": 2097027.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.010776376724243,
|
|
"epoch": 0.09088525736257974,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999998687189161,
|
|
"loss": 6.8502,
|
|
"mean_token_accuracy": 0.11224842295050622,
|
|
"num_tokens": 2107055.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.8836586475372314,
|
|
"epoch": 0.09132220571528446,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999998328992954,
|
|
"loss": 6.7809,
|
|
"mean_token_accuracy": 0.10591298639774323,
|
|
"num_tokens": 2116771.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.847192192077637,
|
|
"epoch": 0.09175915406798917,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049999979276406,
|
|
"loss": 6.9104,
|
|
"mean_token_accuracy": 0.1076812945306301,
|
|
"num_tokens": 2126881.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.95491886138916,
|
|
"epoch": 0.09219610242069387,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999997483132108,
|
|
"loss": 6.8986,
|
|
"mean_token_accuracy": 0.10368494689464569,
|
|
"num_tokens": 2136964.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.9707235336303714,
|
|
"epoch": 0.09263305077339859,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999996995467483,
|
|
"loss": 6.9526,
|
|
"mean_token_accuracy": 0.10105137750506402,
|
|
"num_tokens": 2147263.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.893505430221557,
|
|
"epoch": 0.0930699991261033,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999996464646738,
|
|
"loss": 6.9698,
|
|
"mean_token_accuracy": 0.09723725020885468,
|
|
"num_tokens": 2157474.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.928754138946533,
|
|
"epoch": 0.093506947478808,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999995890669882,
|
|
"loss": 6.8968,
|
|
"mean_token_accuracy": 0.10273590087890624,
|
|
"num_tokens": 2167701.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.855544805526733,
|
|
"epoch": 0.09394389583151272,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999995273536925,
|
|
"loss": 6.8695,
|
|
"mean_token_accuracy": 0.10916284620761871,
|
|
"num_tokens": 2178581.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.926065063476562,
|
|
"epoch": 0.09438084418421742,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499999461324788,
|
|
"loss": 6.8665,
|
|
"mean_token_accuracy": 0.10301437005400657,
|
|
"num_tokens": 2189529.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.931471347808838,
|
|
"epoch": 0.09481779253692213,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999993909802759,
|
|
"loss": 6.9188,
|
|
"mean_token_accuracy": 0.10070269852876663,
|
|
"num_tokens": 2199805.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.864389324188233,
|
|
"epoch": 0.09525474088962685,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999993163201577,
|
|
"loss": 6.867,
|
|
"mean_token_accuracy": 0.10666536092758179,
|
|
"num_tokens": 2210108.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.986412286758423,
|
|
"epoch": 0.09569168924233155,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999992373444347,
|
|
"loss": 6.8837,
|
|
"mean_token_accuracy": 0.10290357768535614,
|
|
"num_tokens": 2220325.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.831525468826294,
|
|
"epoch": 0.09612863759503627,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999991540531084,
|
|
"loss": 6.8743,
|
|
"mean_token_accuracy": 0.10060080140829086,
|
|
"num_tokens": 2230521.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.026464128494263,
|
|
"epoch": 0.09656558594774098,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999990664461804,
|
|
"loss": 6.9131,
|
|
"mean_token_accuracy": 0.0995321400463581,
|
|
"num_tokens": 2240372.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.830053663253784,
|
|
"epoch": 0.09700253430044568,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999989745236524,
|
|
"loss": 6.8651,
|
|
"mean_token_accuracy": 0.11102000325918197,
|
|
"num_tokens": 2250522.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.86471962928772,
|
|
"epoch": 0.0974394826531504,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999988782855261,
|
|
"loss": 6.8068,
|
|
"mean_token_accuracy": 0.10345931202173234,
|
|
"num_tokens": 2260142.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.8818775653839115,
|
|
"epoch": 0.09787643100585511,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999987777318035,
|
|
"loss": 6.8529,
|
|
"mean_token_accuracy": 0.10523375123739243,
|
|
"num_tokens": 2270372.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.768800354003906,
|
|
"epoch": 0.09831337935855981,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999986728624865,
|
|
"loss": 6.7754,
|
|
"mean_token_accuracy": 0.11057863682508469,
|
|
"num_tokens": 2280517.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.968469667434692,
|
|
"epoch": 0.09875032771126453,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499998563677577,
|
|
"loss": 6.8773,
|
|
"mean_token_accuracy": 0.10483333468437195,
|
|
"num_tokens": 2290778.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.8761578559875485,
|
|
"epoch": 0.09918727606396924,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999984501770771,
|
|
"loss": 6.928,
|
|
"mean_token_accuracy": 0.0982240878045559,
|
|
"num_tokens": 2301692.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.879663705825806,
|
|
"epoch": 0.09962422441667394,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999983323609891,
|
|
"loss": 6.8015,
|
|
"mean_token_accuracy": 0.10966127961874009,
|
|
"num_tokens": 2312759.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.873649406433105,
|
|
"epoch": 0.10006117276937866,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999982102293153,
|
|
"loss": 6.7811,
|
|
"mean_token_accuracy": 0.10762107968330384,
|
|
"num_tokens": 2322016.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.836494588851929,
|
|
"epoch": 0.10049812112208337,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999980837820578,
|
|
"loss": 6.7932,
|
|
"mean_token_accuracy": 0.11270353570580482,
|
|
"num_tokens": 2332476.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.899167490005493,
|
|
"epoch": 0.10093506947478809,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999979530192192,
|
|
"loss": 6.8019,
|
|
"mean_token_accuracy": 0.10367468595504761,
|
|
"num_tokens": 2342914.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.799224042892456,
|
|
"epoch": 0.10137201782749279,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999978179408019,
|
|
"loss": 6.8876,
|
|
"mean_token_accuracy": 0.10129361897706986,
|
|
"num_tokens": 2353381.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.881389856338501,
|
|
"epoch": 0.1018089661801975,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999976785468085,
|
|
"loss": 6.8543,
|
|
"mean_token_accuracy": 0.10723742172122001,
|
|
"num_tokens": 2364207.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.8175615787506105,
|
|
"epoch": 0.10224591453290222,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999975348372418,
|
|
"loss": 6.768,
|
|
"mean_token_accuracy": 0.10937329679727555,
|
|
"num_tokens": 2374985.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.797830724716187,
|
|
"epoch": 0.10268286288560692,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999973868121044,
|
|
"loss": 6.8479,
|
|
"mean_token_accuracy": 0.1104587584733963,
|
|
"num_tokens": 2385684.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.961680555343628,
|
|
"epoch": 0.10311981123831163,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999972344713994,
|
|
"loss": 6.7834,
|
|
"mean_token_accuracy": 0.10461923331022263,
|
|
"num_tokens": 2395177.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.685928773880005,
|
|
"epoch": 0.10355675959101635,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999970778151295,
|
|
"loss": 6.8172,
|
|
"mean_token_accuracy": 0.11517063304781913,
|
|
"num_tokens": 2405154.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.829747676849365,
|
|
"epoch": 0.10399370794372105,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999969168432976,
|
|
"loss": 6.8064,
|
|
"mean_token_accuracy": 0.10844132006168365,
|
|
"num_tokens": 2415818.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.826361274719238,
|
|
"epoch": 0.10443065629642576,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999967515559071,
|
|
"loss": 6.7788,
|
|
"mean_token_accuracy": 0.10787174105644226,
|
|
"num_tokens": 2425072.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.7768299102783205,
|
|
"epoch": 0.10486760464913047,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499996581952961,
|
|
"loss": 6.8137,
|
|
"mean_token_accuracy": 0.11103299036622047,
|
|
"num_tokens": 2435055.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.840562725067139,
|
|
"epoch": 0.10530455300183518,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999964080344625,
|
|
"loss": 6.7297,
|
|
"mean_token_accuracy": 0.1094184011220932,
|
|
"num_tokens": 2444434.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.745257711410522,
|
|
"epoch": 0.1057415013545399,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999962298004151,
|
|
"loss": 6.7444,
|
|
"mean_token_accuracy": 0.10750698521733285,
|
|
"num_tokens": 2453860.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.85921721458435,
|
|
"epoch": 0.1061784497072446,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 6.8699,
|
|
"mean_token_accuracy": 0.1019215852022171,
|
|
"num_tokens": 2464235.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.823530101776123,
|
|
"epoch": 0.10661539805994931,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999958603856869,
|
|
"loss": 6.7813,
|
|
"mean_token_accuracy": 0.10817842781543732,
|
|
"num_tokens": 2474561.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.743971061706543,
|
|
"epoch": 0.10705234641265403,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999956692050132,
|
|
"loss": 6.763,
|
|
"mean_token_accuracy": 0.11355147212743759,
|
|
"num_tokens": 2484574.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.859746837615967,
|
|
"epoch": 0.10748929476535873,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999954737088048,
|
|
"loss": 6.7401,
|
|
"mean_token_accuracy": 0.11617439091205597,
|
|
"num_tokens": 2494146.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.72626371383667,
|
|
"epoch": 0.10792624311806344,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999952738970652,
|
|
"loss": 6.8298,
|
|
"mean_token_accuracy": 0.10861490145325661,
|
|
"num_tokens": 2504157.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.863236904144287,
|
|
"epoch": 0.10836319147076816,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999950697697983,
|
|
"loss": 6.7584,
|
|
"mean_token_accuracy": 0.1099944420158863,
|
|
"num_tokens": 2512979.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.742759895324707,
|
|
"epoch": 0.10880013982347286,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999948613270081,
|
|
"loss": 6.8293,
|
|
"mean_token_accuracy": 0.10701432153582573,
|
|
"num_tokens": 2523202.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.795160913467408,
|
|
"epoch": 0.10923708817617758,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999946485686987,
|
|
"loss": 6.7757,
|
|
"mean_token_accuracy": 0.1092297151684761,
|
|
"num_tokens": 2532790.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.7600242614746096,
|
|
"epoch": 0.10967403652888229,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499994431494874,
|
|
"loss": 6.7616,
|
|
"mean_token_accuracy": 0.10790274366736412,
|
|
"num_tokens": 2542337.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.730962944030762,
|
|
"epoch": 0.11011098488158699,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999942101055381,
|
|
"loss": 6.6937,
|
|
"mean_token_accuracy": 0.11463424563407898,
|
|
"num_tokens": 2552762.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.775425910949707,
|
|
"epoch": 0.11054793323429171,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999939844006955,
|
|
"loss": 6.7362,
|
|
"mean_token_accuracy": 0.11280569657683373,
|
|
"num_tokens": 2563261.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.780911922454834,
|
|
"epoch": 0.11098488158699642,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999937543803503,
|
|
"loss": 6.7208,
|
|
"mean_token_accuracy": 0.11466270163655282,
|
|
"num_tokens": 2573089.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.763316488265991,
|
|
"epoch": 0.11142182993970112,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499993520044507,
|
|
"loss": 6.8021,
|
|
"mean_token_accuracy": 0.10308952704071998,
|
|
"num_tokens": 2584358.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.851671457290649,
|
|
"epoch": 0.11185877829240584,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999932813931702,
|
|
"loss": 6.7804,
|
|
"mean_token_accuracy": 0.11292212307453156,
|
|
"num_tokens": 2594981.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.707735347747803,
|
|
"epoch": 0.11229572664511055,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999930384263441,
|
|
"loss": 6.7698,
|
|
"mean_token_accuracy": 0.1120561957359314,
|
|
"num_tokens": 2603508.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.87262110710144,
|
|
"epoch": 0.11273267499781525,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499992791144034,
|
|
"loss": 6.7188,
|
|
"mean_token_accuracy": 0.11393993496894836,
|
|
"num_tokens": 2613666.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.819432783126831,
|
|
"epoch": 0.11316962335051997,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999925395462439,
|
|
"loss": 6.8095,
|
|
"mean_token_accuracy": 0.10437591895461082,
|
|
"num_tokens": 2624441.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.761607503890991,
|
|
"epoch": 0.11360657170322468,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999922836329793,
|
|
"loss": 6.7573,
|
|
"mean_token_accuracy": 0.11246527284383774,
|
|
"num_tokens": 2635261.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.718364334106445,
|
|
"epoch": 0.1140435200559294,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999920234042446,
|
|
"loss": 6.7283,
|
|
"mean_token_accuracy": 0.11169910728931427,
|
|
"num_tokens": 2645493.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.7557297706604,
|
|
"epoch": 0.1144804684086341,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999917588600451,
|
|
"loss": 6.6748,
|
|
"mean_token_accuracy": 0.11324728205800057,
|
|
"num_tokens": 2655430.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.731936120986939,
|
|
"epoch": 0.1149174167613388,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999914900003857,
|
|
"loss": 6.7619,
|
|
"mean_token_accuracy": 0.1131984330713749,
|
|
"num_tokens": 2665675.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.8105064868927006,
|
|
"epoch": 0.11535436511404352,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999912168252717,
|
|
"loss": 6.7183,
|
|
"mean_token_accuracy": 0.10891555175185204,
|
|
"num_tokens": 2675962.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.6981361389160154,
|
|
"epoch": 0.11579131346674823,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999909393347083,
|
|
"loss": 6.7696,
|
|
"mean_token_accuracy": 0.11046200320124626,
|
|
"num_tokens": 2687015.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.805249977111816,
|
|
"epoch": 0.11622826181945294,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999906575287006,
|
|
"loss": 6.8003,
|
|
"mean_token_accuracy": 0.10271921083331108,
|
|
"num_tokens": 2698065.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.699923133850097,
|
|
"epoch": 0.11666521017215765,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999903714072544,
|
|
"loss": 6.6888,
|
|
"mean_token_accuracy": 0.1208715133368969,
|
|
"num_tokens": 2709046.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.805598878860474,
|
|
"epoch": 0.11710215852486236,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999900809703749,
|
|
"loss": 6.7648,
|
|
"mean_token_accuracy": 0.1078792616724968,
|
|
"num_tokens": 2719705.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.71959080696106,
|
|
"epoch": 0.11753910687756706,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004999897862180678,
|
|
"loss": 6.639,
|
|
"mean_token_accuracy": 0.1174460805952549,
|
|
"num_tokens": 2729556.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.650531578063965,
|
|
"epoch": 0.11797605523027178,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999894871503386,
|
|
"loss": 6.7566,
|
|
"mean_token_accuracy": 0.11257789805531501,
|
|
"num_tokens": 2741144.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.823479223251343,
|
|
"epoch": 0.11841300358297649,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999891837671932,
|
|
"loss": 6.6674,
|
|
"mean_token_accuracy": 0.11613549664616585,
|
|
"num_tokens": 2751384.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.634953927993775,
|
|
"epoch": 0.11884995193568121,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999888760686375,
|
|
"loss": 6.6928,
|
|
"mean_token_accuracy": 0.11121985912322999,
|
|
"num_tokens": 2761044.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.683824157714843,
|
|
"epoch": 0.11928690028838591,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499988564054677,
|
|
"loss": 6.6573,
|
|
"mean_token_accuracy": 0.11309800446033477,
|
|
"num_tokens": 2770946.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.737067604064942,
|
|
"epoch": 0.11972384864109062,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999882477253182,
|
|
"loss": 6.7161,
|
|
"mean_token_accuracy": 0.10762240588665009,
|
|
"num_tokens": 2781247.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.665458488464355,
|
|
"epoch": 0.12016079699379534,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999879270805667,
|
|
"loss": 6.5612,
|
|
"mean_token_accuracy": 0.12452048733830452,
|
|
"num_tokens": 2792078.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.6383239269256595,
|
|
"epoch": 0.12059774534650004,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999876021204291,
|
|
"loss": 6.6665,
|
|
"mean_token_accuracy": 0.11566043272614479,
|
|
"num_tokens": 2802458.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.732123756408692,
|
|
"epoch": 0.12103469369920475,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999872728449112,
|
|
"loss": 6.7962,
|
|
"mean_token_accuracy": 0.10792736932635308,
|
|
"num_tokens": 2813352.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.750059413909912,
|
|
"epoch": 0.12147164205190947,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999869392540195,
|
|
"loss": 6.692,
|
|
"mean_token_accuracy": 0.10860167518258095,
|
|
"num_tokens": 2822954.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.739627456665039,
|
|
"epoch": 0.12190859040461417,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999866013477605,
|
|
"loss": 6.712,
|
|
"mean_token_accuracy": 0.11105184629559517,
|
|
"num_tokens": 2833375.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.681881904602051,
|
|
"epoch": 0.12234553875731889,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999862591261407,
|
|
"loss": 6.654,
|
|
"mean_token_accuracy": 0.11549825221300125,
|
|
"num_tokens": 2843103.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.7078999996185305,
|
|
"epoch": 0.1227824871100236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999859125891664,
|
|
"loss": 6.72,
|
|
"mean_token_accuracy": 0.11280344799160957,
|
|
"num_tokens": 2853801.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.723126173019409,
|
|
"epoch": 0.1232194354627283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999855617368445,
|
|
"loss": 6.712,
|
|
"mean_token_accuracy": 0.1107217937707901,
|
|
"num_tokens": 2863851.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.639747476577758,
|
|
"epoch": 0.12365638381543302,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999852065691816,
|
|
"loss": 6.6556,
|
|
"mean_token_accuracy": 0.1157209224998951,
|
|
"num_tokens": 2875073.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.819645643234253,
|
|
"epoch": 0.12409333216813773,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999848470861846,
|
|
"loss": 6.6923,
|
|
"mean_token_accuracy": 0.11399516686797143,
|
|
"num_tokens": 2885676.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.66095814704895,
|
|
"epoch": 0.12453028052084243,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999844832878602,
|
|
"loss": 6.6744,
|
|
"mean_token_accuracy": 0.11909589692950248,
|
|
"num_tokens": 2896663.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.682529258728027,
|
|
"epoch": 0.12496722887354715,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999841151742156,
|
|
"loss": 6.6855,
|
|
"mean_token_accuracy": 0.11644814759492875,
|
|
"num_tokens": 2907555.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.654642724990845,
|
|
"epoch": 0.12540417722625186,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999837427452578,
|
|
"loss": 6.6823,
|
|
"mean_token_accuracy": 0.11288027614355087,
|
|
"num_tokens": 2917173.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.634070777893067,
|
|
"epoch": 0.12584112557895658,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499983366000994,
|
|
"loss": 6.6819,
|
|
"mean_token_accuracy": 0.11158063933253289,
|
|
"num_tokens": 2928268.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.777620124816894,
|
|
"epoch": 0.12627807393166127,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999829849414312,
|
|
"loss": 6.6361,
|
|
"mean_token_accuracy": 0.1173455186188221,
|
|
"num_tokens": 2938203.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.595511102676392,
|
|
"epoch": 0.12671502228436599,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499982599566577,
|
|
"loss": 6.666,
|
|
"mean_token_accuracy": 0.1175123281776905,
|
|
"num_tokens": 2948094.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.724627923965454,
|
|
"epoch": 0.1271519706370707,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999822098764385,
|
|
"loss": 6.6761,
|
|
"mean_token_accuracy": 0.1126259833574295,
|
|
"num_tokens": 2957865.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.633754539489746,
|
|
"epoch": 0.1275889189897754,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999818158710234,
|
|
"loss": 6.582,
|
|
"mean_token_accuracy": 0.11640499681234359,
|
|
"num_tokens": 2967880.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.671688032150269,
|
|
"epoch": 0.12802586734248012,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999814175503392,
|
|
"loss": 6.6542,
|
|
"mean_token_accuracy": 0.11618517264723778,
|
|
"num_tokens": 2979537.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.653942728042603,
|
|
"epoch": 0.12846281569518483,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999810149143935,
|
|
"loss": 6.6421,
|
|
"mean_token_accuracy": 0.11047034710645676,
|
|
"num_tokens": 2989700.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.558183765411377,
|
|
"epoch": 0.12889976404788953,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499980607963194,
|
|
"loss": 6.6535,
|
|
"mean_token_accuracy": 0.11763448640704155,
|
|
"num_tokens": 2999141.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.711502933502198,
|
|
"epoch": 0.12933671240059424,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999801966967486,
|
|
"loss": 6.5868,
|
|
"mean_token_accuracy": 0.11921618357300759,
|
|
"num_tokens": 3008259.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.674244356155396,
|
|
"epoch": 0.12977366075329896,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999797811150652,
|
|
"loss": 6.648,
|
|
"mean_token_accuracy": 0.10815014466643333,
|
|
"num_tokens": 3018281.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.719975137710572,
|
|
"epoch": 0.13021060910600368,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999793612181516,
|
|
"loss": 6.6448,
|
|
"mean_token_accuracy": 0.11819751039147378,
|
|
"num_tokens": 3029062.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.508638143539429,
|
|
"epoch": 0.13064755745870837,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999789370060161,
|
|
"loss": 6.6111,
|
|
"mean_token_accuracy": 0.11788376942276954,
|
|
"num_tokens": 3038142.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.793538331985474,
|
|
"epoch": 0.1310845058114131,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999785084786667,
|
|
"loss": 6.7071,
|
|
"mean_token_accuracy": 0.10659723281860352,
|
|
"num_tokens": 3049123.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.612226247787476,
|
|
"epoch": 0.1315214541641178,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999780756361114,
|
|
"loss": 6.619,
|
|
"mean_token_accuracy": 0.11126089543104171,
|
|
"num_tokens": 3059031.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.67326545715332,
|
|
"epoch": 0.1319584025168225,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999776384783589,
|
|
"loss": 6.6532,
|
|
"mean_token_accuracy": 0.11633370667696,
|
|
"num_tokens": 3068830.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.579953718185425,
|
|
"epoch": 0.13239535086952722,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999771970054174,
|
|
"loss": 6.6592,
|
|
"mean_token_accuracy": 0.1143224373459816,
|
|
"num_tokens": 3080124.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.664220142364502,
|
|
"epoch": 0.13283229922223194,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999767512172953,
|
|
"loss": 6.6545,
|
|
"mean_token_accuracy": 0.10695429295301437,
|
|
"num_tokens": 3089607.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.688190889358521,
|
|
"epoch": 0.13326924757493663,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999763011140013,
|
|
"loss": 6.7211,
|
|
"mean_token_accuracy": 0.10691676661372185,
|
|
"num_tokens": 3099363.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.751109886169433,
|
|
"epoch": 0.13370619592764135,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999758466955439,
|
|
"loss": 6.6214,
|
|
"mean_token_accuracy": 0.11871336251497269,
|
|
"num_tokens": 3109552.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.567575359344483,
|
|
"epoch": 0.13414314428034607,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999753879619319,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.1198199823498726,
|
|
"num_tokens": 3119536.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.637157773971557,
|
|
"epoch": 0.13458009263305076,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999749249131741,
|
|
"loss": 6.6466,
|
|
"mean_token_accuracy": 0.11405760124325752,
|
|
"num_tokens": 3130552.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.744642210006714,
|
|
"epoch": 0.13501704098575548,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999744575492793,
|
|
"loss": 6.5619,
|
|
"mean_token_accuracy": 0.11781792342662811,
|
|
"num_tokens": 3140723.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.585478115081787,
|
|
"epoch": 0.1354539893384602,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999739858702567,
|
|
"loss": 6.6016,
|
|
"mean_token_accuracy": 0.11881603077054023,
|
|
"num_tokens": 3151031.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.587906789779663,
|
|
"epoch": 0.1358909376911649,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499973509876115,
|
|
"loss": 6.6036,
|
|
"mean_token_accuracy": 0.11454507485032081,
|
|
"num_tokens": 3161373.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.673034143447876,
|
|
"epoch": 0.1363278860438696,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999730295668634,
|
|
"loss": 6.6232,
|
|
"mean_token_accuracy": 0.11494075879454613,
|
|
"num_tokens": 3171094.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.599486541748047,
|
|
"epoch": 0.13676483439657433,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999725449425114,
|
|
"loss": 6.5751,
|
|
"mean_token_accuracy": 0.11703467667102814,
|
|
"num_tokens": 3181646.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.574843311309815,
|
|
"epoch": 0.13720178274927902,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499972056003068,
|
|
"loss": 6.5467,
|
|
"mean_token_accuracy": 0.12450342401862144,
|
|
"num_tokens": 3190727.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.643044805526733,
|
|
"epoch": 0.13763873110198374,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999715627485426,
|
|
"loss": 6.6619,
|
|
"mean_token_accuracy": 0.10692948997020721,
|
|
"num_tokens": 3200316.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.6441529273986815,
|
|
"epoch": 0.13807567945468846,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499971065178945,
|
|
"loss": 6.5991,
|
|
"mean_token_accuracy": 0.11431368961930274,
|
|
"num_tokens": 3211830.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.572905778884888,
|
|
"epoch": 0.13851262780739318,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999705632942843,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.11557646915316581,
|
|
"num_tokens": 3222711.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.611633920669556,
|
|
"epoch": 0.13894957616009787,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999700570945704,
|
|
"loss": 6.5282,
|
|
"mean_token_accuracy": 0.12471159398555756,
|
|
"num_tokens": 3232810.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.591669034957886,
|
|
"epoch": 0.1393865245128026,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999695465798128,
|
|
"loss": 6.6326,
|
|
"mean_token_accuracy": 0.11323555037379265,
|
|
"num_tokens": 3243366.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.661644554138183,
|
|
"epoch": 0.1398234728655073,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999690317500215,
|
|
"loss": 6.6116,
|
|
"mean_token_accuracy": 0.11405737772583961,
|
|
"num_tokens": 3254000.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.700826120376587,
|
|
"epoch": 0.140260421218212,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999685126052063,
|
|
"loss": 6.642,
|
|
"mean_token_accuracy": 0.11356792375445365,
|
|
"num_tokens": 3263601.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.5335101127624515,
|
|
"epoch": 0.14069736957091672,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999679891453772,
|
|
"loss": 6.6709,
|
|
"mean_token_accuracy": 0.1109616331756115,
|
|
"num_tokens": 3273243.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.65966911315918,
|
|
"epoch": 0.14113431792362144,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499967461370544,
|
|
"loss": 6.6082,
|
|
"mean_token_accuracy": 0.11456717923283577,
|
|
"num_tokens": 3284208.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.625819253921509,
|
|
"epoch": 0.14157126627632613,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999669292807172,
|
|
"loss": 6.5819,
|
|
"mean_token_accuracy": 0.11917855739593505,
|
|
"num_tokens": 3294216.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.636405372619629,
|
|
"epoch": 0.14200821462903085,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999663928759066,
|
|
"loss": 6.6316,
|
|
"mean_token_accuracy": 0.11559324115514755,
|
|
"num_tokens": 3304576.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.641275072097779,
|
|
"epoch": 0.14244516298173557,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999658521561229,
|
|
"loss": 6.5962,
|
|
"mean_token_accuracy": 0.11600318327546119,
|
|
"num_tokens": 3314214.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.633429431915284,
|
|
"epoch": 0.14288211133444026,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999653071213763,
|
|
"loss": 6.6071,
|
|
"mean_token_accuracy": 0.1085868775844574,
|
|
"num_tokens": 3325527.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.5328723907470705,
|
|
"epoch": 0.14331905968714498,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999647577716771,
|
|
"loss": 6.5292,
|
|
"mean_token_accuracy": 0.12012957409024239,
|
|
"num_tokens": 3334511.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.605924606323242,
|
|
"epoch": 0.1437560080398497,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999642041070361,
|
|
"loss": 6.5238,
|
|
"mean_token_accuracy": 0.1242619700729847,
|
|
"num_tokens": 3343922.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.595180988311768,
|
|
"epoch": 0.1441929563925544,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999636461274637,
|
|
"loss": 6.5324,
|
|
"mean_token_accuracy": 0.11857725381851196,
|
|
"num_tokens": 3353895.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.566598129272461,
|
|
"epoch": 0.1446299047452591,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999630838329706,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.1127896174788475,
|
|
"num_tokens": 3364637.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.610513353347779,
|
|
"epoch": 0.14506685309796383,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999625172235679,
|
|
"loss": 6.5719,
|
|
"mean_token_accuracy": 0.11518365815281868,
|
|
"num_tokens": 3374308.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.5965320587158205,
|
|
"epoch": 0.14550380145066852,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499961946299266,
|
|
"loss": 6.5453,
|
|
"mean_token_accuracy": 0.11517407447099685,
|
|
"num_tokens": 3383637.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.590162563323974,
|
|
"epoch": 0.14594074980337324,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999613710600763,
|
|
"loss": 6.6251,
|
|
"mean_token_accuracy": 0.11774841398000717,
|
|
"num_tokens": 3394150.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.680703973770141,
|
|
"epoch": 0.14637769815607796,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999607915060094,
|
|
"loss": 6.5903,
|
|
"mean_token_accuracy": 0.11480792313814163,
|
|
"num_tokens": 3404445.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.5011927604675295,
|
|
"epoch": 0.14681464650878268,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999602076370768,
|
|
"loss": 6.4964,
|
|
"mean_token_accuracy": 0.12533730790019035,
|
|
"num_tokens": 3415183.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.560801219940186,
|
|
"epoch": 0.14725159486148737,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999596194532895,
|
|
"loss": 6.4879,
|
|
"mean_token_accuracy": 0.1252271644771099,
|
|
"num_tokens": 3424824.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.547294235229492,
|
|
"epoch": 0.1476885432141921,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999590269546588,
|
|
"loss": 6.6166,
|
|
"mean_token_accuracy": 0.11056721806526185,
|
|
"num_tokens": 3434789.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.4686205863952635,
|
|
"epoch": 0.1481254915668968,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999584301411961,
|
|
"loss": 6.495,
|
|
"mean_token_accuracy": 0.13793878480792046,
|
|
"num_tokens": 3445810.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.66889123916626,
|
|
"epoch": 0.1485624399196015,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999578290129129,
|
|
"loss": 6.6183,
|
|
"mean_token_accuracy": 0.11348513811826706,
|
|
"num_tokens": 3455510.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.594088411331176,
|
|
"epoch": 0.14899938827230622,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999572235698206,
|
|
"loss": 6.5905,
|
|
"mean_token_accuracy": 0.11757459565997123,
|
|
"num_tokens": 3465785.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.552883243560791,
|
|
"epoch": 0.14943633662501093,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999566138119308,
|
|
"loss": 6.652,
|
|
"mean_token_accuracy": 0.11335393786430359,
|
|
"num_tokens": 3477568.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.600546979904175,
|
|
"epoch": 0.14987328497771563,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999559997392554,
|
|
"loss": 6.4769,
|
|
"mean_token_accuracy": 0.13354343175888062,
|
|
"num_tokens": 3487703.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.499100685119629,
|
|
"epoch": 0.15031023333042035,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999553813518061,
|
|
"loss": 6.5618,
|
|
"mean_token_accuracy": 0.11586256697773933,
|
|
"num_tokens": 3497757.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.590635681152344,
|
|
"epoch": 0.15074718168312506,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999547586495946,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.1161200724542141,
|
|
"num_tokens": 3507594.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.565278720855713,
|
|
"epoch": 0.15118413003582976,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999541316326329,
|
|
"loss": 6.5941,
|
|
"mean_token_accuracy": 0.11325425505638123,
|
|
"num_tokens": 3517889.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.582718229293823,
|
|
"epoch": 0.15162107838853447,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999535003009332,
|
|
"loss": 6.5919,
|
|
"mean_token_accuracy": 0.1146755650639534,
|
|
"num_tokens": 3528158.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.656514263153076,
|
|
"epoch": 0.1520580267412392,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999528646545074,
|
|
"loss": 6.5854,
|
|
"mean_token_accuracy": 0.12044015303254127,
|
|
"num_tokens": 3539099.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.604732513427734,
|
|
"epoch": 0.15249497509394389,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999522246933678,
|
|
"loss": 6.5961,
|
|
"mean_token_accuracy": 0.1175947681069374,
|
|
"num_tokens": 3549819.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.599875211715698,
|
|
"epoch": 0.1529319234466486,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 6.596,
|
|
"mean_token_accuracy": 0.11611012145876884,
|
|
"num_tokens": 3560022.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.581331825256347,
|
|
"epoch": 0.15336887179935332,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999509318269964,
|
|
"loss": 6.5371,
|
|
"mean_token_accuracy": 0.11462760418653488,
|
|
"num_tokens": 3569681.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.580878448486328,
|
|
"epoch": 0.15380582015205801,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999502789217894,
|
|
"loss": 6.6168,
|
|
"mean_token_accuracy": 0.11628764718770981,
|
|
"num_tokens": 3580731.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.541976404190064,
|
|
"epoch": 0.15424276850476273,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999496217019181,
|
|
"loss": 6.5798,
|
|
"mean_token_accuracy": 0.11936882063746453,
|
|
"num_tokens": 3590482.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.561248731613159,
|
|
"epoch": 0.15467971685746745,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999489601673952,
|
|
"loss": 6.5756,
|
|
"mean_token_accuracy": 0.11308965906500816,
|
|
"num_tokens": 3600988.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.729976606369019,
|
|
"epoch": 0.15511666521017214,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999482943182334,
|
|
"loss": 6.6527,
|
|
"mean_token_accuracy": 0.11284584775567055,
|
|
"num_tokens": 3611226.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.494902324676514,
|
|
"epoch": 0.15555361356287686,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999476241544454,
|
|
"loss": 6.5584,
|
|
"mean_token_accuracy": 0.11853229030966758,
|
|
"num_tokens": 3621324.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.614112901687622,
|
|
"epoch": 0.15599056191558158,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999469496760441,
|
|
"loss": 6.4845,
|
|
"mean_token_accuracy": 0.11637181118130684,
|
|
"num_tokens": 3631650.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.576256132125854,
|
|
"epoch": 0.1564275102682863,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999462708830425,
|
|
"loss": 6.5023,
|
|
"mean_token_accuracy": 0.1310523718595505,
|
|
"num_tokens": 3641173.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.535652542114258,
|
|
"epoch": 0.156864458620991,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999455877754535,
|
|
"loss": 6.5203,
|
|
"mean_token_accuracy": 0.11737008094787597,
|
|
"num_tokens": 3651846.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.526522207260132,
|
|
"epoch": 0.1573014069736957,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999449003532903,
|
|
"loss": 6.5324,
|
|
"mean_token_accuracy": 0.11961890906095504,
|
|
"num_tokens": 3661174.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.528283977508545,
|
|
"epoch": 0.15773835532640043,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999442086165661,
|
|
"loss": 6.487,
|
|
"mean_token_accuracy": 0.11840147376060486,
|
|
"num_tokens": 3671042.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.552019643783569,
|
|
"epoch": 0.15817530367910512,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000499943512565294,
|
|
"loss": 6.4648,
|
|
"mean_token_accuracy": 0.11766612604260444,
|
|
"num_tokens": 3681206.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.509097480773926,
|
|
"epoch": 0.15861225203180984,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999428121994874,
|
|
"loss": 6.5826,
|
|
"mean_token_accuracy": 0.11521901562809944,
|
|
"num_tokens": 3691748.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.594895744323731,
|
|
"epoch": 0.15904920038451456,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999421075191599,
|
|
"loss": 6.4523,
|
|
"mean_token_accuracy": 0.1187455803155899,
|
|
"num_tokens": 3701730.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.495048093795776,
|
|
"epoch": 0.15948614873721925,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999413985243249,
|
|
"loss": 6.5631,
|
|
"mean_token_accuracy": 0.11405811235308647,
|
|
"num_tokens": 3712525.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.652899694442749,
|
|
"epoch": 0.15992309708992397,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499940685214996,
|
|
"loss": 6.5304,
|
|
"mean_token_accuracy": 0.12245537713170052,
|
|
"num_tokens": 3722016.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.5295939445495605,
|
|
"epoch": 0.1603600454426287,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999399675911869,
|
|
"loss": 6.4453,
|
|
"mean_token_accuracy": 0.11833713129162789,
|
|
"num_tokens": 3731299.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.487839317321777,
|
|
"epoch": 0.16079699379533338,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999392456529113,
|
|
"loss": 6.5011,
|
|
"mean_token_accuracy": 0.1233910709619522,
|
|
"num_tokens": 3740922.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.48659315109253,
|
|
"epoch": 0.1612339421480381,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999385194001831,
|
|
"loss": 6.4982,
|
|
"mean_token_accuracy": 0.12182619720697403,
|
|
"num_tokens": 3750339.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.537278699874878,
|
|
"epoch": 0.16167089050074282,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999377888330164,
|
|
"loss": 6.4728,
|
|
"mean_token_accuracy": 0.12529798746109008,
|
|
"num_tokens": 3761379.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.524621915817261,
|
|
"epoch": 0.1621078388534475,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999370539514249,
|
|
"loss": 6.5474,
|
|
"mean_token_accuracy": 0.11859968900680543,
|
|
"num_tokens": 3771649.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.492616367340088,
|
|
"epoch": 0.16254478720615223,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999363147554229,
|
|
"loss": 6.4554,
|
|
"mean_token_accuracy": 0.12341330200433731,
|
|
"num_tokens": 3782393.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.598450231552124,
|
|
"epoch": 0.16298173555885695,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999355712450244,
|
|
"loss": 6.5257,
|
|
"mean_token_accuracy": 0.1240497075021267,
|
|
"num_tokens": 3792849.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.5042177677154545,
|
|
"epoch": 0.16341868391156164,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999348234202438,
|
|
"loss": 6.4764,
|
|
"mean_token_accuracy": 0.12349856197834015,
|
|
"num_tokens": 3803848.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.288655757904053,
|
|
"epoch": 0.16385563226426636,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999340712810956,
|
|
"loss": 6.4098,
|
|
"mean_token_accuracy": 0.13501542136073114,
|
|
"num_tokens": 3814704.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.517355871200562,
|
|
"epoch": 0.16429258061697108,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999333148275939,
|
|
"loss": 6.5381,
|
|
"mean_token_accuracy": 0.11455504298210144,
|
|
"num_tokens": 3824955.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.5474401950836185,
|
|
"epoch": 0.1647295289696758,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999325540597535,
|
|
"loss": 6.5202,
|
|
"mean_token_accuracy": 0.12205357849597931,
|
|
"num_tokens": 3836540.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.465744876861573,
|
|
"epoch": 0.1651664773223805,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999317889775887,
|
|
"loss": 6.4075,
|
|
"mean_token_accuracy": 0.1288439191877842,
|
|
"num_tokens": 3846472.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.521185493469238,
|
|
"epoch": 0.1656034256750852,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999310195811143,
|
|
"loss": 6.5135,
|
|
"mean_token_accuracy": 0.11601202338933944,
|
|
"num_tokens": 3857187.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.53255524635315,
|
|
"epoch": 0.16604037402778993,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999302458703451,
|
|
"loss": 6.4815,
|
|
"mean_token_accuracy": 0.12292045503854751,
|
|
"num_tokens": 3866259.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.447905969619751,
|
|
"epoch": 0.16647732238049462,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499929467845296,
|
|
"loss": 6.5408,
|
|
"mean_token_accuracy": 0.11351652964949607,
|
|
"num_tokens": 3876869.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.610359334945679,
|
|
"epoch": 0.16691427073319934,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999286855059818,
|
|
"loss": 6.5203,
|
|
"mean_token_accuracy": 0.12371717020869255,
|
|
"num_tokens": 3888278.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.551647138595581,
|
|
"epoch": 0.16735121908590406,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004999278988524177,
|
|
"loss": 6.5777,
|
|
"mean_token_accuracy": 0.11743155568838119,
|
|
"num_tokens": 3898648.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.493818187713623,
|
|
"epoch": 0.16778816743860875,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999271078846184,
|
|
"loss": 6.4898,
|
|
"mean_token_accuracy": 0.120925023406744,
|
|
"num_tokens": 3908282.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.4657470226287845,
|
|
"epoch": 0.16822511579131347,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999263126025994,
|
|
"loss": 6.4982,
|
|
"mean_token_accuracy": 0.11906409412622451,
|
|
"num_tokens": 3918333.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.558496046066284,
|
|
"epoch": 0.1686620641440182,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999255130063759,
|
|
"loss": 6.4876,
|
|
"mean_token_accuracy": 0.12188828215003014,
|
|
"num_tokens": 3927403.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.521365690231323,
|
|
"epoch": 0.16909901249672288,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999247090959633,
|
|
"loss": 6.5066,
|
|
"mean_token_accuracy": 0.12119645178318024,
|
|
"num_tokens": 3937352.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.453633642196655,
|
|
"epoch": 0.1695359608494276,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999239008713767,
|
|
"loss": 6.3406,
|
|
"mean_token_accuracy": 0.12555457800626754,
|
|
"num_tokens": 3947164.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.530312156677246,
|
|
"epoch": 0.16997290920213232,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999230883326319,
|
|
"loss": 6.5191,
|
|
"mean_token_accuracy": 0.11990117952227593,
|
|
"num_tokens": 3956887.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.510148668289185,
|
|
"epoch": 0.170409857554837,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999222714797445,
|
|
"loss": 6.4802,
|
|
"mean_token_accuracy": 0.118320432305336,
|
|
"num_tokens": 3966542.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.5808569431304935,
|
|
"epoch": 0.17084680590754173,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049992145031273,
|
|
"loss": 6.4445,
|
|
"mean_token_accuracy": 0.1298608437180519,
|
|
"num_tokens": 3976127.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.371415281295777,
|
|
"epoch": 0.17128375426024645,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999206248316043,
|
|
"loss": 6.4302,
|
|
"mean_token_accuracy": 0.12315708696842194,
|
|
"num_tokens": 3987371.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.443069648742676,
|
|
"epoch": 0.17172070261295114,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499919795036383,
|
|
"loss": 6.4361,
|
|
"mean_token_accuracy": 0.12713590562343596,
|
|
"num_tokens": 3997924.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.529845285415649,
|
|
"epoch": 0.17215765096565586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999189609270823,
|
|
"loss": 6.5188,
|
|
"mean_token_accuracy": 0.12592333555221558,
|
|
"num_tokens": 4009150.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.494536066055298,
|
|
"epoch": 0.17259459931836058,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000499918122503718,
|
|
"loss": 6.5196,
|
|
"mean_token_accuracy": 0.12174422815442085,
|
|
"num_tokens": 4018899.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.504218292236328,
|
|
"epoch": 0.17303154767106527,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999172797663064,
|
|
"loss": 6.4728,
|
|
"mean_token_accuracy": 0.11927963867783546,
|
|
"num_tokens": 4028652.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.526062726974487,
|
|
"epoch": 0.17346849602376999,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999164327148634,
|
|
"loss": 6.5272,
|
|
"mean_token_accuracy": 0.12078682556748391,
|
|
"num_tokens": 4039819.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.509147644042969,
|
|
"epoch": 0.1739054443764747,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999155813494053,
|
|
"loss": 6.4176,
|
|
"mean_token_accuracy": 0.12781703993678092,
|
|
"num_tokens": 4050029.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.421483421325684,
|
|
"epoch": 0.17434239272917942,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999147256699487,
|
|
"loss": 6.4811,
|
|
"mean_token_accuracy": 0.12011851966381074,
|
|
"num_tokens": 4060497.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.563172960281372,
|
|
"epoch": 0.17477934108188412,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999138656765096,
|
|
"loss": 6.4376,
|
|
"mean_token_accuracy": 0.12605830207467078,
|
|
"num_tokens": 4071477.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.576144123077393,
|
|
"epoch": 0.17521628943458883,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999130013691049,
|
|
"loss": 6.5454,
|
|
"mean_token_accuracy": 0.11874540522694588,
|
|
"num_tokens": 4081869.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.570287227630615,
|
|
"epoch": 0.17565323778729355,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999121327477509,
|
|
"loss": 6.5252,
|
|
"mean_token_accuracy": 0.12263748943805694,
|
|
"num_tokens": 4092797.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.444070291519165,
|
|
"epoch": 0.17609018613999824,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999112598124642,
|
|
"loss": 6.4571,
|
|
"mean_token_accuracy": 0.11857560724020004,
|
|
"num_tokens": 4103688.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.4113997459411625,
|
|
"epoch": 0.17652713449270296,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999103825632618,
|
|
"loss": 6.4368,
|
|
"mean_token_accuracy": 0.12056360468268394,
|
|
"num_tokens": 4114037.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.5229727268219,
|
|
"epoch": 0.17696408284540768,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999095010001605,
|
|
"loss": 6.4223,
|
|
"mean_token_accuracy": 0.12138459011912346,
|
|
"num_tokens": 4124164.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.470005750656128,
|
|
"epoch": 0.17740103119811237,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499908615123177,
|
|
"loss": 6.5271,
|
|
"mean_token_accuracy": 0.11661396995186805,
|
|
"num_tokens": 4134225.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.5835813045501705,
|
|
"epoch": 0.1778379795508171,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999077249323284,
|
|
"loss": 6.5804,
|
|
"mean_token_accuracy": 0.1160724326968193,
|
|
"num_tokens": 4145962.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.540454864501953,
|
|
"epoch": 0.1782749279035218,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999068304276319,
|
|
"loss": 6.4559,
|
|
"mean_token_accuracy": 0.11698207259178162,
|
|
"num_tokens": 4156572.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.494862699508667,
|
|
"epoch": 0.1787118762562265,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999059316091045,
|
|
"loss": 6.5379,
|
|
"mean_token_accuracy": 0.117926075309515,
|
|
"num_tokens": 4166960.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.504702520370484,
|
|
"epoch": 0.17914882460893122,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999050284767634,
|
|
"loss": 6.4799,
|
|
"mean_token_accuracy": 0.1223859153687954,
|
|
"num_tokens": 4177833.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.444409275054932,
|
|
"epoch": 0.17958577296163594,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999041210306261,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.12724354416131972,
|
|
"num_tokens": 4187858.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.524564933776856,
|
|
"epoch": 0.18002272131434063,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999032092707098,
|
|
"loss": 6.5382,
|
|
"mean_token_accuracy": 0.11748412624001503,
|
|
"num_tokens": 4198207.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.572392845153809,
|
|
"epoch": 0.18045966966704535,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999022931970323,
|
|
"loss": 6.4191,
|
|
"mean_token_accuracy": 0.1241879142820835,
|
|
"num_tokens": 4207594.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.38447756767273,
|
|
"epoch": 0.18089661801975007,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999013728096107,
|
|
"loss": 6.4312,
|
|
"mean_token_accuracy": 0.125095746666193,
|
|
"num_tokens": 4217334.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.526350355148315,
|
|
"epoch": 0.18133356637245476,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499900448108463,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.12915206849575042,
|
|
"num_tokens": 4226407.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.489539337158203,
|
|
"epoch": 0.18177051472515948,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000499899519093607,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.12649197205901147,
|
|
"num_tokens": 4237818.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.521691370010376,
|
|
"epoch": 0.1822074630778642,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004998985857650603,
|
|
"loss": 6.4944,
|
|
"mean_token_accuracy": 0.11592372059822083,
|
|
"num_tokens": 4247783.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.413587856292724,
|
|
"epoch": 0.18264441143056892,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998976481228409,
|
|
"loss": 6.4355,
|
|
"mean_token_accuracy": 0.1198279656469822,
|
|
"num_tokens": 4258049.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.4406171321868895,
|
|
"epoch": 0.1830813597832736,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998967061669668,
|
|
"loss": 6.4463,
|
|
"mean_token_accuracy": 0.11746001914143563,
|
|
"num_tokens": 4269357.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.498240995407104,
|
|
"epoch": 0.18351830813597833,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998957598974559,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.12721729502081872,
|
|
"num_tokens": 4279576.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.463101100921631,
|
|
"epoch": 0.18395525648868305,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004998948093143266,
|
|
"loss": 6.4257,
|
|
"mean_token_accuracy": 0.12523012161254882,
|
|
"num_tokens": 4289761.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.442949867248535,
|
|
"epoch": 0.18439220484138774,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000499893854417597,
|
|
"loss": 6.3533,
|
|
"mean_token_accuracy": 0.12625055760145187,
|
|
"num_tokens": 4299231.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.447075605392456,
|
|
"epoch": 0.18482915319409246,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998928952072854,
|
|
"loss": 6.5121,
|
|
"mean_token_accuracy": 0.11597891449928284,
|
|
"num_tokens": 4308687.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.5224504470825195,
|
|
"epoch": 0.18526610154679718,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998919316834102,
|
|
"loss": 6.4698,
|
|
"mean_token_accuracy": 0.11885222047567368,
|
|
"num_tokens": 4318183.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.467560958862305,
|
|
"epoch": 0.18570304989950187,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00049989096384599,
|
|
"loss": 6.5139,
|
|
"mean_token_accuracy": 0.12279015704989434,
|
|
"num_tokens": 4328482.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.529058790206909,
|
|
"epoch": 0.1861399982522066,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004998899916950431,
|
|
"loss": 6.3821,
|
|
"mean_token_accuracy": 0.1252948209643364,
|
|
"num_tokens": 4339313.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.460389947891235,
|
|
"epoch": 0.1865769466049113,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998890152305885,
|
|
"loss": 6.4944,
|
|
"mean_token_accuracy": 0.12029476463794708,
|
|
"num_tokens": 4350299.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.528489065170288,
|
|
"epoch": 0.187013894957616,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998880344526447,
|
|
"loss": 6.4391,
|
|
"mean_token_accuracy": 0.12706440985202788,
|
|
"num_tokens": 4361424.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.482869291305542,
|
|
"epoch": 0.18745084331032072,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998870493612306,
|
|
"loss": 6.407,
|
|
"mean_token_accuracy": 0.12022507637739181,
|
|
"num_tokens": 4371480.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.387491750717163,
|
|
"epoch": 0.18788779166302544,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998860599563649,
|
|
"loss": 6.4422,
|
|
"mean_token_accuracy": 0.12101913392543792,
|
|
"num_tokens": 4381951.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.489475870132447,
|
|
"epoch": 0.18832474001573013,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004998850662380668,
|
|
"loss": 6.5016,
|
|
"mean_token_accuracy": 0.1167457014322281,
|
|
"num_tokens": 4392290.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.4344056129455565,
|
|
"epoch": 0.18876168836843485,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004998840682063553,
|
|
"loss": 6.2632,
|
|
"mean_token_accuracy": 0.135141958296299,
|
|
"num_tokens": 4403350.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.418215799331665,
|
|
"epoch": 0.18919863672113957,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998830658612496,
|
|
"loss": 6.4718,
|
|
"mean_token_accuracy": 0.11757678985595703,
|
|
"num_tokens": 4413171.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.456563186645508,
|
|
"epoch": 0.18963558507384426,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998820592027688,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.1265949308872223,
|
|
"num_tokens": 4424371.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.361171054840088,
|
|
"epoch": 0.19007253342654898,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998810482309322,
|
|
"loss": 6.3929,
|
|
"mean_token_accuracy": 0.11713957265019417,
|
|
"num_tokens": 4434040.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.585212564468383,
|
|
"epoch": 0.1905094817792537,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998800329457595,
|
|
"loss": 6.4795,
|
|
"mean_token_accuracy": 0.11658665388822556,
|
|
"num_tokens": 4444663.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.493283939361572,
|
|
"epoch": 0.1909464301319584,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998790133472697,
|
|
"loss": 6.4233,
|
|
"mean_token_accuracy": 0.11703696846961975,
|
|
"num_tokens": 4454733.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.449396371841431,
|
|
"epoch": 0.1913833784846631,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998779894354827,
|
|
"loss": 6.409,
|
|
"mean_token_accuracy": 0.12359335049986839,
|
|
"num_tokens": 4464286.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.488334655761719,
|
|
"epoch": 0.19182032683736783,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499876961210418,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.13071504160761832,
|
|
"num_tokens": 4475005.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.437582492828369,
|
|
"epoch": 0.19225727519007255,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998759286720953,
|
|
"loss": 6.3682,
|
|
"mean_token_accuracy": 0.12397781834006309,
|
|
"num_tokens": 4484606.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.396815586090088,
|
|
"epoch": 0.19269422354277724,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998748918205345,
|
|
"loss": 6.4733,
|
|
"mean_token_accuracy": 0.11907115429639817,
|
|
"num_tokens": 4494930.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.471502208709717,
|
|
"epoch": 0.19313117189548196,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004998738506557554,
|
|
"loss": 6.4905,
|
|
"mean_token_accuracy": 0.11480139791965485,
|
|
"num_tokens": 4505304.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.591741514205933,
|
|
"epoch": 0.19356812024818668,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499872805177778,
|
|
"loss": 6.4211,
|
|
"mean_token_accuracy": 0.12898224964737892,
|
|
"num_tokens": 4514333.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.402223110198975,
|
|
"epoch": 0.19400506860089137,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998717553866225,
|
|
"loss": 6.4659,
|
|
"mean_token_accuracy": 0.1265234135091305,
|
|
"num_tokens": 4525175.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.485518169403076,
|
|
"epoch": 0.1944420169535961,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998707012823087,
|
|
"loss": 6.3523,
|
|
"mean_token_accuracy": 0.12841272950172425,
|
|
"num_tokens": 4534212.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.408768939971924,
|
|
"epoch": 0.1948789653063008,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998696428648573,
|
|
"loss": 6.5188,
|
|
"mean_token_accuracy": 0.12075343132019042,
|
|
"num_tokens": 4545141.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.482947492599488,
|
|
"epoch": 0.1953159136590055,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998685801342881,
|
|
"loss": 6.3669,
|
|
"mean_token_accuracy": 0.1291575625538826,
|
|
"num_tokens": 4554410.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.375760126113891,
|
|
"epoch": 0.19575286201171022,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998675130906217,
|
|
"loss": 6.3699,
|
|
"mean_token_accuracy": 0.12993818074464797,
|
|
"num_tokens": 4564397.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.3663304328918455,
|
|
"epoch": 0.19618981036441493,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998664417338787,
|
|
"loss": 6.3751,
|
|
"mean_token_accuracy": 0.12797396183013915,
|
|
"num_tokens": 4573986.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.509523153305054,
|
|
"epoch": 0.19662675871711963,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004998653660640794,
|
|
"loss": 6.3699,
|
|
"mean_token_accuracy": 0.13107719346880914,
|
|
"num_tokens": 4583449.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.419308996200561,
|
|
"epoch": 0.19706370706982435,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004998642860812447,
|
|
"loss": 6.4144,
|
|
"mean_token_accuracy": 0.12404663264751434,
|
|
"num_tokens": 4593637.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.3758574485778805,
|
|
"epoch": 0.19750065542252906,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004998632017853951,
|
|
"loss": 6.4012,
|
|
"mean_token_accuracy": 0.12606620118021966,
|
|
"num_tokens": 4603865.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.584481143951416,
|
|
"epoch": 0.19793760377523376,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004998621131765514,
|
|
"loss": 6.4357,
|
|
"mean_token_accuracy": 0.12628217190504074,
|
|
"num_tokens": 4613502.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.38882474899292,
|
|
"epoch": 0.19837455212793847,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998610202547345,
|
|
"loss": 6.3999,
|
|
"mean_token_accuracy": 0.12597004026174546,
|
|
"num_tokens": 4623163.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.471518421173096,
|
|
"epoch": 0.1988115004806432,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998599230199654,
|
|
"loss": 6.4193,
|
|
"mean_token_accuracy": 0.13149505183100701,
|
|
"num_tokens": 4632850.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.44390549659729,
|
|
"epoch": 0.19924844883334789,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004998588214722653,
|
|
"loss": 6.413,
|
|
"mean_token_accuracy": 0.12612975835800172,
|
|
"num_tokens": 4642858.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.517856550216675,
|
|
"epoch": 0.1996853971860526,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 6.444,
|
|
"mean_token_accuracy": 0.12016589418053628,
|
|
"num_tokens": 4653083.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.466843843460083,
|
|
"epoch": 0.20012234553875732,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998566054381561,
|
|
"loss": 6.4486,
|
|
"mean_token_accuracy": 0.11985157281160355,
|
|
"num_tokens": 4663353.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.445455694198609,
|
|
"epoch": 0.20055929389146204,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004998554909517895,
|
|
"loss": 6.3183,
|
|
"mean_token_accuracy": 0.12755734249949455,
|
|
"num_tokens": 4673878.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.427143669128418,
|
|
"epoch": 0.20099624224416673,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004998543721525769,
|
|
"loss": 6.3877,
|
|
"mean_token_accuracy": 0.12570685148239136,
|
|
"num_tokens": 4683661.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.355686902999878,
|
|
"epoch": 0.20143319059687145,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004998532490405397,
|
|
"loss": 6.445,
|
|
"mean_token_accuracy": 0.12695046067237853,
|
|
"num_tokens": 4693817.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.415957927703857,
|
|
"epoch": 0.20187013894957617,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998521216156991,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.1261789694428444,
|
|
"num_tokens": 4703550.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.463042449951172,
|
|
"epoch": 0.20230708730228086,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998509898780771,
|
|
"loss": 6.4915,
|
|
"mean_token_accuracy": 0.1210303895175457,
|
|
"num_tokens": 4714872.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.400016498565674,
|
|
"epoch": 0.20274403565498558,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998498538276954,
|
|
"loss": 6.3665,
|
|
"mean_token_accuracy": 0.12931155189871787,
|
|
"num_tokens": 4725745.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.441245460510254,
|
|
"epoch": 0.2031809840076903,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004998487134645755,
|
|
"loss": 6.4628,
|
|
"mean_token_accuracy": 0.12229650542140007,
|
|
"num_tokens": 4735560.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.49150595664978,
|
|
"epoch": 0.203617932360395,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004998475687887396,
|
|
"loss": 6.44,
|
|
"mean_token_accuracy": 0.1181219644844532,
|
|
"num_tokens": 4746304.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.52930097579956,
|
|
"epoch": 0.2040548807130997,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998464198002095,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.12358200997114181,
|
|
"num_tokens": 4756200.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.371595859527588,
|
|
"epoch": 0.20449182906580443,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998452664990072,
|
|
"loss": 6.4228,
|
|
"mean_token_accuracy": 0.12109901309013367,
|
|
"num_tokens": 4766249.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.5394433498382565,
|
|
"epoch": 0.20492877741850912,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998441088851548,
|
|
"loss": 6.4503,
|
|
"mean_token_accuracy": 0.11931437700986862,
|
|
"num_tokens": 4776510.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.455130910873413,
|
|
"epoch": 0.20536572577121384,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998429469586748,
|
|
"loss": 6.4275,
|
|
"mean_token_accuracy": 0.12399638965725898,
|
|
"num_tokens": 4786798.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.386494255065918,
|
|
"epoch": 0.20580267412391856,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000499841780719589,
|
|
"loss": 6.3515,
|
|
"mean_token_accuracy": 0.12153764739632607,
|
|
"num_tokens": 4796001.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.400313091278076,
|
|
"epoch": 0.20623962247662325,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004998406101679202,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.13208253532648087,
|
|
"num_tokens": 4807634.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.462019729614258,
|
|
"epoch": 0.20667657082932797,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004998394353036906,
|
|
"loss": 6.3527,
|
|
"mean_token_accuracy": 0.1344490632414818,
|
|
"num_tokens": 4817840.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.37156572341919,
|
|
"epoch": 0.2071135191820327,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998382561269229,
|
|
"loss": 6.3228,
|
|
"mean_token_accuracy": 0.1289958320558071,
|
|
"num_tokens": 4827186.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.284419775009155,
|
|
"epoch": 0.20755046753473738,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998370726376395,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.12209030091762543,
|
|
"num_tokens": 4837140.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.49763560295105,
|
|
"epoch": 0.2079874158874421,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004998358848358634,
|
|
"loss": 6.3981,
|
|
"mean_token_accuracy": 0.12760360389947892,
|
|
"num_tokens": 4846907.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.359625816345215,
|
|
"epoch": 0.20842436424014682,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000499834692721617,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.12730940505862237,
|
|
"num_tokens": 4856165.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.4935239315032955,
|
|
"epoch": 0.2088613125928515,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998334962949237,
|
|
"loss": 6.2773,
|
|
"mean_token_accuracy": 0.13658949360251427,
|
|
"num_tokens": 4865308.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.358750247955323,
|
|
"epoch": 0.20929826094555623,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004998322955558059,
|
|
"loss": 6.3561,
|
|
"mean_token_accuracy": 0.13445974960923196,
|
|
"num_tokens": 4876286.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.389959907531738,
|
|
"epoch": 0.20973520929826095,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998310905042869,
|
|
"loss": 6.3916,
|
|
"mean_token_accuracy": 0.12824709340929985,
|
|
"num_tokens": 4887227.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.459248208999634,
|
|
"epoch": 0.21017215765096567,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998298811403898,
|
|
"loss": 6.4181,
|
|
"mean_token_accuracy": 0.1229472927749157,
|
|
"num_tokens": 4896994.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.416028738021851,
|
|
"epoch": 0.21060910600367036,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998286674641378,
|
|
"loss": 6.3954,
|
|
"mean_token_accuracy": 0.1258566915988922,
|
|
"num_tokens": 4907623.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.339293336868286,
|
|
"epoch": 0.21104605435637508,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499827449475554,
|
|
"loss": 6.3075,
|
|
"mean_token_accuracy": 0.12986938655376434,
|
|
"num_tokens": 4917040.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.543447732925415,
|
|
"epoch": 0.2114830027090798,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499826227174662,
|
|
"loss": 6.4469,
|
|
"mean_token_accuracy": 0.12280156686902047,
|
|
"num_tokens": 4928390.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.359825563430786,
|
|
"epoch": 0.2119199510617845,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998250005614852,
|
|
"loss": 6.4135,
|
|
"mean_token_accuracy": 0.12152730897068978,
|
|
"num_tokens": 4939040.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.393878936767578,
|
|
"epoch": 0.2123568994144892,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499823769636047,
|
|
"loss": 6.4349,
|
|
"mean_token_accuracy": 0.12271395474672317,
|
|
"num_tokens": 4949915.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.448448228836059,
|
|
"epoch": 0.21279384776719393,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998225343983712,
|
|
"loss": 6.3378,
|
|
"mean_token_accuracy": 0.12833459079265594,
|
|
"num_tokens": 4960127.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.440428781509399,
|
|
"epoch": 0.21323079611989862,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998212948484814,
|
|
"loss": 6.3871,
|
|
"mean_token_accuracy": 0.12280435562133789,
|
|
"num_tokens": 4970152.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.411177682876587,
|
|
"epoch": 0.21366774447260334,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998200509864012,
|
|
"loss": 6.3458,
|
|
"mean_token_accuracy": 0.12693380266427995,
|
|
"num_tokens": 4979745.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.479267740249634,
|
|
"epoch": 0.21410469282530806,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998188028121547,
|
|
"loss": 6.3747,
|
|
"mean_token_accuracy": 0.13292665034532547,
|
|
"num_tokens": 4989924.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.365407466888428,
|
|
"epoch": 0.21454164117801275,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998175503257658,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.13266007974743843,
|
|
"num_tokens": 4999698.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.399653434753418,
|
|
"epoch": 0.21497858953071747,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998162935272585,
|
|
"loss": 6.433,
|
|
"mean_token_accuracy": 0.12551234066486358,
|
|
"num_tokens": 5010625.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.387683725357055,
|
|
"epoch": 0.2154155378834222,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998150324166568,
|
|
"loss": 6.3143,
|
|
"mean_token_accuracy": 0.13393508419394493,
|
|
"num_tokens": 5019740.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.487478494644165,
|
|
"epoch": 0.21585248623612688,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499813766993985,
|
|
"loss": 6.4293,
|
|
"mean_token_accuracy": 0.12056878060102463,
|
|
"num_tokens": 5030601.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.497150993347168,
|
|
"epoch": 0.2162894345888316,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998124972592674,
|
|
"loss": 6.3906,
|
|
"mean_token_accuracy": 0.1267626941204071,
|
|
"num_tokens": 5040567.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.3080087184906,
|
|
"epoch": 0.21672638294153632,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004998112232125283,
|
|
"loss": 6.2682,
|
|
"mean_token_accuracy": 0.13081765845417975,
|
|
"num_tokens": 5049512.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.32685604095459,
|
|
"epoch": 0.217163331294241,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499809944853792,
|
|
"loss": 6.4609,
|
|
"mean_token_accuracy": 0.12319278120994567,
|
|
"num_tokens": 5060986.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.42396092414856,
|
|
"epoch": 0.21760027964694573,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004998086621830833,
|
|
"loss": 6.3755,
|
|
"mean_token_accuracy": 0.12850141301751136,
|
|
"num_tokens": 5071492.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.4019676685333256,
|
|
"epoch": 0.21803722799965045,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998073752004267,
|
|
"loss": 6.4115,
|
|
"mean_token_accuracy": 0.12014096081256867,
|
|
"num_tokens": 5081722.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.498205232620239,
|
|
"epoch": 0.21847417635235516,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004998060839058467,
|
|
"loss": 6.3881,
|
|
"mean_token_accuracy": 0.12541978657245637,
|
|
"num_tokens": 5091906.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.3498509407043455,
|
|
"epoch": 0.21891112470505986,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004998047882993683,
|
|
"loss": 6.3482,
|
|
"mean_token_accuracy": 0.12800950780510903,
|
|
"num_tokens": 5102025.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.381645059585571,
|
|
"epoch": 0.21934807305776458,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998034883810162,
|
|
"loss": 6.3475,
|
|
"mean_token_accuracy": 0.12698294296860696,
|
|
"num_tokens": 5112354.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.373659706115722,
|
|
"epoch": 0.2197850214104693,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998021841508155,
|
|
"loss": 6.289,
|
|
"mean_token_accuracy": 0.13288134709000587,
|
|
"num_tokens": 5121695.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.395002651214599,
|
|
"epoch": 0.22022196976317399,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004998008756087911,
|
|
"loss": 6.4074,
|
|
"mean_token_accuracy": 0.1230700857937336,
|
|
"num_tokens": 5132561.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.474684524536133,
|
|
"epoch": 0.2206589181158787,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000499799562754968,
|
|
"loss": 6.4335,
|
|
"mean_token_accuracy": 0.12292742729187012,
|
|
"num_tokens": 5141981.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.371050119400024,
|
|
"epoch": 0.22109586646858342,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004997982455893716,
|
|
"loss": 6.3251,
|
|
"mean_token_accuracy": 0.1293874688446522,
|
|
"num_tokens": 5151550.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.47653021812439,
|
|
"epoch": 0.22153281482128812,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004997969241120271,
|
|
"loss": 6.3947,
|
|
"mean_token_accuracy": 0.1197041004896164,
|
|
"num_tokens": 5161679.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.365097761154175,
|
|
"epoch": 0.22196976317399283,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997955983229597,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.1268290475010872,
|
|
"num_tokens": 5171575.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.401581716537476,
|
|
"epoch": 0.22240671152669755,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000499794268222195,
|
|
"loss": 6.2896,
|
|
"mean_token_accuracy": 0.13048343136906623,
|
|
"num_tokens": 5180152.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.347995901107788,
|
|
"epoch": 0.22284365987940224,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004997929338097583,
|
|
"loss": 6.362,
|
|
"mean_token_accuracy": 0.12662460505962372,
|
|
"num_tokens": 5190518.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.484149408340454,
|
|
"epoch": 0.22328060823210696,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004997915950856755,
|
|
"loss": 6.3986,
|
|
"mean_token_accuracy": 0.12541723176836966,
|
|
"num_tokens": 5201729.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.404265975952148,
|
|
"epoch": 0.22371755658481168,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997902520499721,
|
|
"loss": 6.4016,
|
|
"mean_token_accuracy": 0.12332973778247833,
|
|
"num_tokens": 5211940.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.325415325164795,
|
|
"epoch": 0.22415450493751637,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997889047026738,
|
|
"loss": 6.3135,
|
|
"mean_token_accuracy": 0.1277544841170311,
|
|
"num_tokens": 5221028.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.368482255935669,
|
|
"epoch": 0.2245914532902211,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004997875530438066,
|
|
"loss": 6.3189,
|
|
"mean_token_accuracy": 0.13291172459721565,
|
|
"num_tokens": 5230498.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.430984592437744,
|
|
"epoch": 0.2250284016429258,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997861970733963,
|
|
"loss": 6.3663,
|
|
"mean_token_accuracy": 0.1215190939605236,
|
|
"num_tokens": 5240112.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.458737134933472,
|
|
"epoch": 0.2254653499956305,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499784836791469,
|
|
"loss": 6.3192,
|
|
"mean_token_accuracy": 0.12820565402507783,
|
|
"num_tokens": 5249201.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.335276365280151,
|
|
"epoch": 0.22590229834833522,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004997834721980507,
|
|
"loss": 6.331,
|
|
"mean_token_accuracy": 0.12517586797475816,
|
|
"num_tokens": 5258541.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.543854236602783,
|
|
"epoch": 0.22633924670103994,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004997821032931676,
|
|
"loss": 6.4331,
|
|
"mean_token_accuracy": 0.12591790556907653,
|
|
"num_tokens": 5268524.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.359928607940674,
|
|
"epoch": 0.22677619505374463,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499780730076846,
|
|
"loss": 6.3493,
|
|
"mean_token_accuracy": 0.12371724024415016,
|
|
"num_tokens": 5280702.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.4017528057098385,
|
|
"epoch": 0.22721314340644935,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997793525491122,
|
|
"loss": 6.3274,
|
|
"mean_token_accuracy": 0.12179224193096161,
|
|
"num_tokens": 5291214.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.364180421829223,
|
|
"epoch": 0.22765009175915407,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004997779707099926,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.1345026545226574,
|
|
"num_tokens": 5300729.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.363022375106811,
|
|
"epoch": 0.2280870401118588,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997765845595138,
|
|
"loss": 6.441,
|
|
"mean_token_accuracy": 0.12474732324481011,
|
|
"num_tokens": 5310551.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.430810880661011,
|
|
"epoch": 0.22852398846456348,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997751940977024,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.13267467617988588,
|
|
"num_tokens": 5320038.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.3052386283874515,
|
|
"epoch": 0.2289609368172682,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997737993245848,
|
|
"loss": 6.3353,
|
|
"mean_token_accuracy": 0.129467436671257,
|
|
"num_tokens": 5329753.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.376943922042846,
|
|
"epoch": 0.22939788516997292,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004997724002401881,
|
|
"loss": 6.3323,
|
|
"mean_token_accuracy": 0.1261540874838829,
|
|
"num_tokens": 5340546.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.386794996261597,
|
|
"epoch": 0.2298348335226776,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004997709968445391,
|
|
"loss": 6.4117,
|
|
"mean_token_accuracy": 0.12256940975785255,
|
|
"num_tokens": 5352097.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.436126089096069,
|
|
"epoch": 0.23027178187538233,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004997695891376644,
|
|
"loss": 6.3473,
|
|
"mean_token_accuracy": 0.12921667471528053,
|
|
"num_tokens": 5361646.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.376198720932007,
|
|
"epoch": 0.23070873022808705,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004997681771195912,
|
|
"loss": 6.3273,
|
|
"mean_token_accuracy": 0.12919537127017974,
|
|
"num_tokens": 5371695.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.378803825378418,
|
|
"epoch": 0.23114567858079174,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004997667607903466,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.12181895822286606,
|
|
"num_tokens": 5381978.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.467701435089111,
|
|
"epoch": 0.23158262693349646,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997653401499578,
|
|
"loss": 6.4007,
|
|
"mean_token_accuracy": 0.12531357929110526,
|
|
"num_tokens": 5391891.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.402388381958008,
|
|
"epoch": 0.23201957528620118,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499763915198452,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.12459794357419014,
|
|
"num_tokens": 5403172.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.378549528121948,
|
|
"epoch": 0.23245652363890587,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004997624859358565,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.1256065085530281,
|
|
"num_tokens": 5413130.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.3742975234985355,
|
|
"epoch": 0.2328934719916106,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004997610523621988,
|
|
"loss": 6.3917,
|
|
"mean_token_accuracy": 0.12258691787719726,
|
|
"num_tokens": 5423510.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.373180770874024,
|
|
"epoch": 0.2333304203443153,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004997596144775063,
|
|
"loss": 6.2241,
|
|
"mean_token_accuracy": 0.13480209782719613,
|
|
"num_tokens": 5433707.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.2156439304351805,
|
|
"epoch": 0.23376736869702,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997581722818067,
|
|
"loss": 6.3541,
|
|
"mean_token_accuracy": 0.12960029989480973,
|
|
"num_tokens": 5444381.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.525657272338867,
|
|
"epoch": 0.23420431704972472,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997567257751275,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.12946442216634751,
|
|
"num_tokens": 5453905.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.361790466308594,
|
|
"epoch": 0.23464126540242944,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004997552749574965,
|
|
"loss": 6.3146,
|
|
"mean_token_accuracy": 0.12517919018864632,
|
|
"num_tokens": 5464839.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.367331504821777,
|
|
"epoch": 0.23507821375513413,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004997538198289416,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.12339176088571549,
|
|
"num_tokens": 5475459.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.353179883956909,
|
|
"epoch": 0.23551516210783885,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004997523603894907,
|
|
"loss": 6.3649,
|
|
"mean_token_accuracy": 0.12877027690410614,
|
|
"num_tokens": 5484886.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.352494192123413,
|
|
"epoch": 0.23595211046054357,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004997508966391717,
|
|
"loss": 6.355,
|
|
"mean_token_accuracy": 0.1291891060769558,
|
|
"num_tokens": 5494803.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.36141185760498,
|
|
"epoch": 0.2363890588132483,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997494285780129,
|
|
"loss": 6.3053,
|
|
"mean_token_accuracy": 0.12495973929762841,
|
|
"num_tokens": 5504997.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.327673482894897,
|
|
"epoch": 0.23682600716595298,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997479562060421,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.13582547903060913,
|
|
"num_tokens": 5514492.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.405963373184204,
|
|
"epoch": 0.2372629555186577,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997464795232877,
|
|
"loss": 6.3269,
|
|
"mean_token_accuracy": 0.12349909618496895,
|
|
"num_tokens": 5524419.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.358639526367187,
|
|
"epoch": 0.23769990387136242,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997449985297782,
|
|
"loss": 6.3633,
|
|
"mean_token_accuracy": 0.12754026502370835,
|
|
"num_tokens": 5534289.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.355934572219849,
|
|
"epoch": 0.2381368522240671,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004997435132255418,
|
|
"loss": 6.2981,
|
|
"mean_token_accuracy": 0.12902715429663658,
|
|
"num_tokens": 5543034.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.414120054244995,
|
|
"epoch": 0.23857380057677183,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997420236106071,
|
|
"loss": 6.3655,
|
|
"mean_token_accuracy": 0.12629004567861557,
|
|
"num_tokens": 5553291.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.336919546127319,
|
|
"epoch": 0.23901074892947655,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004997405296850026,
|
|
"loss": 6.3536,
|
|
"mean_token_accuracy": 0.13027266338467597,
|
|
"num_tokens": 5563772.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.426336717605591,
|
|
"epoch": 0.23944769728218124,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997390314487569,
|
|
"loss": 6.3971,
|
|
"mean_token_accuracy": 0.12313945814967156,
|
|
"num_tokens": 5574348.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.372211456298828,
|
|
"epoch": 0.23988464563488596,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997375289018989,
|
|
"loss": 6.242,
|
|
"mean_token_accuracy": 0.12484033331274987,
|
|
"num_tokens": 5583491.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.295545482635498,
|
|
"epoch": 0.24032159398759068,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004997360220444574,
|
|
"loss": 6.3951,
|
|
"mean_token_accuracy": 0.12214951664209366,
|
|
"num_tokens": 5594273.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.42808051109314,
|
|
"epoch": 0.24075854234029537,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004997345108764611,
|
|
"loss": 6.2957,
|
|
"mean_token_accuracy": 0.12530528381466866,
|
|
"num_tokens": 5604529.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.33855619430542,
|
|
"epoch": 0.2411954906930001,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004997329953979391,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.13347954750061036,
|
|
"num_tokens": 5614036.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.406115388870239,
|
|
"epoch": 0.2416324390457048,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004997314756089206,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.1278097912669182,
|
|
"num_tokens": 5624036.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.385963106155396,
|
|
"epoch": 0.2420693873984095,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004997299515094347,
|
|
"loss": 6.3345,
|
|
"mean_token_accuracy": 0.13025815337896346,
|
|
"num_tokens": 5633987.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.340337467193604,
|
|
"epoch": 0.24250633575111422,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004997284230995105,
|
|
"loss": 6.2052,
|
|
"mean_token_accuracy": 0.13974855989217758,
|
|
"num_tokens": 5643905.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.351865005493164,
|
|
"epoch": 0.24294328410381894,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004997268903791773,
|
|
"loss": 6.4087,
|
|
"mean_token_accuracy": 0.12293170467019081,
|
|
"num_tokens": 5654922.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.3397914409637455,
|
|
"epoch": 0.24338023245652363,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997253533484647,
|
|
"loss": 6.2413,
|
|
"mean_token_accuracy": 0.13280420899391174,
|
|
"num_tokens": 5664407.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.353033638000488,
|
|
"epoch": 0.24381718080922835,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004997238120074021,
|
|
"loss": 6.3079,
|
|
"mean_token_accuracy": 0.13058429807424546,
|
|
"num_tokens": 5674524.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.383109712600708,
|
|
"epoch": 0.24425412916193306,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004997222663560188,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.12487837448716163,
|
|
"num_tokens": 5684691.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.3418395042419435,
|
|
"epoch": 0.24469107751463778,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004997207163943449,
|
|
"loss": 6.2672,
|
|
"mean_token_accuracy": 0.12925235480070113,
|
|
"num_tokens": 5693683.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.346609592437744,
|
|
"epoch": 0.24512802586734248,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004997191621224098,
|
|
"loss": 6.3505,
|
|
"mean_token_accuracy": 0.12702021300792693,
|
|
"num_tokens": 5704394.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.343639373779297,
|
|
"epoch": 0.2455649742200472,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004997176035402435,
|
|
"loss": 6.2929,
|
|
"mean_token_accuracy": 0.13152689412236213,
|
|
"num_tokens": 5715480.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.425011825561524,
|
|
"epoch": 0.2460019225727519,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004997160406478758,
|
|
"loss": 6.2805,
|
|
"mean_token_accuracy": 0.13279203623533248,
|
|
"num_tokens": 5725973.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.252740144729614,
|
|
"epoch": 0.2464388709254566,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 6.2817,
|
|
"mean_token_accuracy": 0.13347256407141686,
|
|
"num_tokens": 5735798.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.413337850570679,
|
|
"epoch": 0.24687581927816132,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997129019326562,
|
|
"loss": 6.3644,
|
|
"mean_token_accuracy": 0.12277695909142494,
|
|
"num_tokens": 5746623.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.432828378677368,
|
|
"epoch": 0.24731276763086604,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004997113261098645,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.1289552219212055,
|
|
"num_tokens": 5756526.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.36118860244751,
|
|
"epoch": 0.24774971598357073,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004997097459769919,
|
|
"loss": 6.3125,
|
|
"mean_token_accuracy": 0.13007271513342858,
|
|
"num_tokens": 5766670.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.405504179000855,
|
|
"epoch": 0.24818666433627545,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004997081615340685,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.12305036559700966,
|
|
"num_tokens": 5776473.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.457984447479248,
|
|
"epoch": 0.24862361268898017,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004997065727811249,
|
|
"loss": 6.3868,
|
|
"mean_token_accuracy": 0.12714115232229234,
|
|
"num_tokens": 5787059.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.364512252807617,
|
|
"epoch": 0.24906056104168486,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004997049797181915,
|
|
"loss": 6.3791,
|
|
"mean_token_accuracy": 0.1261816143989563,
|
|
"num_tokens": 5797367.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.3602512836456295,
|
|
"epoch": 0.24949750939438958,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004997033823452988,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.12893701419234277,
|
|
"num_tokens": 5806704.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.357887887954712,
|
|
"epoch": 0.2499344577470943,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004997017806624774,
|
|
"loss": 6.3511,
|
|
"mean_token_accuracy": 0.13046250268816947,
|
|
"num_tokens": 5817797.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.452028465270996,
|
|
"epoch": 0.250371406099799,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004997001746697582,
|
|
"loss": 6.378,
|
|
"mean_token_accuracy": 0.1331723690032959,
|
|
"num_tokens": 5829270.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.366587162017822,
|
|
"epoch": 0.2508083544525037,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004996985643671719,
|
|
"loss": 6.3137,
|
|
"mean_token_accuracy": 0.1306256264448166,
|
|
"num_tokens": 5839214.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.356428956985473,
|
|
"epoch": 0.2512453028052084,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004996969497547495,
|
|
"loss": 6.2981,
|
|
"mean_token_accuracy": 0.1351346492767334,
|
|
"num_tokens": 5848171.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.351561784744263,
|
|
"epoch": 0.25168225115791315,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996953308325217,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.13406590819358827,
|
|
"num_tokens": 5858399.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.331246757507325,
|
|
"epoch": 0.25211919951061784,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004996937076005198,
|
|
"loss": 6.2302,
|
|
"mean_token_accuracy": 0.13163061663508416,
|
|
"num_tokens": 5868212.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.3308275699615475,
|
|
"epoch": 0.25255614786332253,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004996920800587749,
|
|
"loss": 6.2959,
|
|
"mean_token_accuracy": 0.13326340839266776,
|
|
"num_tokens": 5877883.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.429145336151123,
|
|
"epoch": 0.2529930962160273,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004996904482073181,
|
|
"loss": 6.3208,
|
|
"mean_token_accuracy": 0.12892481535673142,
|
|
"num_tokens": 5887090.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.335492897033691,
|
|
"epoch": 0.25343004456873197,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996888120461808,
|
|
"loss": 6.3525,
|
|
"mean_token_accuracy": 0.12223572880029679,
|
|
"num_tokens": 5897491.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.407157039642334,
|
|
"epoch": 0.25386699292143666,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004996871715753943,
|
|
"loss": 6.3709,
|
|
"mean_token_accuracy": 0.12866056635975837,
|
|
"num_tokens": 5908494.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.483530569076538,
|
|
"epoch": 0.2543039412741414,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00049968552679499,
|
|
"loss": 6.4113,
|
|
"mean_token_accuracy": 0.11444444879889488,
|
|
"num_tokens": 5919708.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.394390058517456,
|
|
"epoch": 0.2547408896268461,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004996838777049998,
|
|
"loss": 6.2742,
|
|
"mean_token_accuracy": 0.1324307791888714,
|
|
"num_tokens": 5930122.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.266551733016968,
|
|
"epoch": 0.2551778379795508,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499682224305455,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.1286554180085659,
|
|
"num_tokens": 5940033.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.341103506088257,
|
|
"epoch": 0.25561478633225554,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004996805665963874,
|
|
"loss": 6.2955,
|
|
"mean_token_accuracy": 0.12507626488804818,
|
|
"num_tokens": 5949335.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.422477149963379,
|
|
"epoch": 0.25605173468496023,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004996789045778287,
|
|
"loss": 6.3136,
|
|
"mean_token_accuracy": 0.13033667132258414,
|
|
"num_tokens": 5959299.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.385528469085694,
|
|
"epoch": 0.2564886830376649,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004996772382498111,
|
|
"loss": 6.2879,
|
|
"mean_token_accuracy": 0.12810725048184396,
|
|
"num_tokens": 5970114.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.352691411972046,
|
|
"epoch": 0.25692563139036967,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996755676123662,
|
|
"loss": 6.3671,
|
|
"mean_token_accuracy": 0.12160494327545165,
|
|
"num_tokens": 5979630.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.448770380020141,
|
|
"epoch": 0.25736257974307436,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004996738926655262,
|
|
"loss": 6.3475,
|
|
"mean_token_accuracy": 0.12364518791437148,
|
|
"num_tokens": 5990190.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.390782070159912,
|
|
"epoch": 0.25779952809577905,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004996722134093231,
|
|
"loss": 6.3783,
|
|
"mean_token_accuracy": 0.12294622734189034,
|
|
"num_tokens": 6000706.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.32075514793396,
|
|
"epoch": 0.2582364764484838,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004996705298437894,
|
|
"loss": 6.3407,
|
|
"mean_token_accuracy": 0.1283108413219452,
|
|
"num_tokens": 6011274.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.437451887130737,
|
|
"epoch": 0.2586734248011885,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004996688419689572,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.13058432415127755,
|
|
"num_tokens": 6021481.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.3496260166168215,
|
|
"epoch": 0.25911037315389324,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004996671497848589,
|
|
"loss": 6.3367,
|
|
"mean_token_accuracy": 0.12986429557204246,
|
|
"num_tokens": 6032091.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.342704248428345,
|
|
"epoch": 0.25954732150659793,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004996654532915269,
|
|
"loss": 6.3442,
|
|
"mean_token_accuracy": 0.12034625858068466,
|
|
"num_tokens": 6043371.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.40626015663147,
|
|
"epoch": 0.2599842698593026,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004996637524889937,
|
|
"loss": 6.2854,
|
|
"mean_token_accuracy": 0.1287955202162266,
|
|
"num_tokens": 6052812.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.317795324325561,
|
|
"epoch": 0.26042121821200737,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004996620473772921,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.13428313955664634,
|
|
"num_tokens": 6064033.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.403295278549194,
|
|
"epoch": 0.26085816656471206,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004996603379564546,
|
|
"loss": 6.4065,
|
|
"mean_token_accuracy": 0.12221458777785302,
|
|
"num_tokens": 6075837.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.480539703369141,
|
|
"epoch": 0.26129511491741675,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004996586242265142,
|
|
"loss": 6.3028,
|
|
"mean_token_accuracy": 0.13012727349996567,
|
|
"num_tokens": 6085514.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.413984298706055,
|
|
"epoch": 0.2617320632701215,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004996569061875036,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.1320499710738659,
|
|
"num_tokens": 6094992.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.2930519580841064,
|
|
"epoch": 0.2621690116228262,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004996551838394559,
|
|
"loss": 6.2941,
|
|
"mean_token_accuracy": 0.12757463231682778,
|
|
"num_tokens": 6104841.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2621690116228262,
|
|
"eval_entropy": 6.144934864984054,
|
|
"eval_loss": 6.327561855316162,
|
|
"eval_mean_token_accuracy": 0.1354727728229144,
|
|
"eval_num_tokens": 6104841.0,
|
|
"eval_runtime": 27.9402,
|
|
"eval_samples_per_second": 1324.76,
|
|
"eval_steps_per_second": 165.604,
|
|
"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": 9147482929152000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|