79febb3511
Model: fpadovani/jpn-jpan-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed455 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": 0.3462204270051933,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 3.7323212385177613,
|
|
"epoch": 0.0005770340450086555,
|
|
"grad_norm": 34.0,
|
|
"learning_rate": 2e-06,
|
|
"loss": 13.6143,
|
|
"mean_token_accuracy": 0.042970035597682,
|
|
"num_tokens": 13337.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 3.6967998266220095,
|
|
"epoch": 0.001154068090017311,
|
|
"grad_norm": 32.5,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 13.5571,
|
|
"mean_token_accuracy": 0.04257573280483484,
|
|
"num_tokens": 26339.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.161470651626587,
|
|
"epoch": 0.0017311021350259665,
|
|
"grad_norm": 32.5,
|
|
"learning_rate": 7e-06,
|
|
"loss": 13.2735,
|
|
"mean_token_accuracy": 0.030668590404093265,
|
|
"num_tokens": 39118.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.517871713638305,
|
|
"epoch": 0.002308136180034622,
|
|
"grad_norm": 36.25,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 12.3718,
|
|
"mean_token_accuracy": 0.020669543370604514,
|
|
"num_tokens": 51367.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 9.014927005767822,
|
|
"epoch": 0.0028851702250432777,
|
|
"grad_norm": 14.375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 11.0046,
|
|
"mean_token_accuracy": 0.017831112071871758,
|
|
"num_tokens": 64639.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.463701057434083,
|
|
"epoch": 0.003462204270051933,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.5931,
|
|
"mean_token_accuracy": 0.01491671558469534,
|
|
"num_tokens": 76244.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.491576671600342,
|
|
"epoch": 0.004039238315060588,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3479,
|
|
"mean_token_accuracy": 0.02280671913176775,
|
|
"num_tokens": 88490.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.193946361541748,
|
|
"epoch": 0.004616272360069244,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.0133,
|
|
"mean_token_accuracy": 0.048479363694787024,
|
|
"num_tokens": 102022.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.412507057189941,
|
|
"epoch": 0.0051933064050779,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.8157,
|
|
"mean_token_accuracy": 0.06318248882889747,
|
|
"num_tokens": 114442.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.123257160186768,
|
|
"epoch": 0.005770340450086555,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.7698,
|
|
"mean_token_accuracy": 0.06782412566244603,
|
|
"num_tokens": 128044.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.276771545410156,
|
|
"epoch": 0.006347374495095211,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.7272,
|
|
"mean_token_accuracy": 0.062359335273504256,
|
|
"num_tokens": 141818.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.322304344177246,
|
|
"epoch": 0.006924408540103866,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.5725,
|
|
"mean_token_accuracy": 0.06548289433121682,
|
|
"num_tokens": 155109.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.235727787017822,
|
|
"epoch": 0.0075014425851125215,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.5017,
|
|
"mean_token_accuracy": 0.07019429132342339,
|
|
"num_tokens": 167036.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.236877536773681,
|
|
"epoch": 0.008078476630121177,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.5416,
|
|
"mean_token_accuracy": 0.0642974752932787,
|
|
"num_tokens": 181398.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.093268299102784,
|
|
"epoch": 0.008655510675129832,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.3665,
|
|
"mean_token_accuracy": 0.07238649874925614,
|
|
"num_tokens": 193242.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.19960355758667,
|
|
"epoch": 0.009232544720138488,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.3623,
|
|
"mean_token_accuracy": 0.07175844348967075,
|
|
"num_tokens": 206744.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.094919395446777,
|
|
"epoch": 0.009809578765147143,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.2726,
|
|
"mean_token_accuracy": 0.07449138984084129,
|
|
"num_tokens": 219120.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.15459098815918,
|
|
"epoch": 0.0103866128101558,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.2401,
|
|
"mean_token_accuracy": 0.07340459935367108,
|
|
"num_tokens": 231942.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 9.965401363372802,
|
|
"epoch": 0.010963646855164455,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.1966,
|
|
"mean_token_accuracy": 0.07440538741648198,
|
|
"num_tokens": 244786.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.01766061782837,
|
|
"epoch": 0.01154068090017311,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.036,
|
|
"mean_token_accuracy": 0.08044340573251248,
|
|
"num_tokens": 257503.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 9.868921279907227,
|
|
"epoch": 0.012117714945181766,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.9711,
|
|
"mean_token_accuracy": 0.08332463353872299,
|
|
"num_tokens": 270330.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 9.76955509185791,
|
|
"epoch": 0.012694748990190421,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.0165,
|
|
"mean_token_accuracy": 0.08288254365324974,
|
|
"num_tokens": 283866.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.99423532485962,
|
|
"epoch": 0.013271783035199077,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9324,
|
|
"mean_token_accuracy": 0.07315073981881141,
|
|
"num_tokens": 296715.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.858692646026611,
|
|
"epoch": 0.013848817080207732,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8353,
|
|
"mean_token_accuracy": 0.07335402593016624,
|
|
"num_tokens": 309268.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.587060260772706,
|
|
"epoch": 0.014425851125216388,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7874,
|
|
"mean_token_accuracy": 0.08877900540828705,
|
|
"num_tokens": 322471.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.701264572143554,
|
|
"epoch": 0.015002885170225043,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.7586,
|
|
"mean_token_accuracy": 0.0769478652626276,
|
|
"num_tokens": 335728.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.516640281677246,
|
|
"epoch": 0.015579919215233698,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.6412,
|
|
"mean_token_accuracy": 0.07981666177511215,
|
|
"num_tokens": 347861.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.311244106292724,
|
|
"epoch": 0.016156953260242354,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.6347,
|
|
"mean_token_accuracy": 0.08614776656031609,
|
|
"num_tokens": 360275.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.333715534210205,
|
|
"epoch": 0.01673398730525101,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.571,
|
|
"mean_token_accuracy": 0.07833859249949456,
|
|
"num_tokens": 373948.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.198777198791504,
|
|
"epoch": 0.017311021350259664,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.5338,
|
|
"mean_token_accuracy": 0.07528047934174538,
|
|
"num_tokens": 386267.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.142632865905762,
|
|
"epoch": 0.01788805539526832,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.466,
|
|
"mean_token_accuracy": 0.07569638900458812,
|
|
"num_tokens": 398595.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.001069831848145,
|
|
"epoch": 0.018465089440276975,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.4415,
|
|
"mean_token_accuracy": 0.07843919023871422,
|
|
"num_tokens": 410626.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.904146099090577,
|
|
"epoch": 0.019042123485285632,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.4353,
|
|
"mean_token_accuracy": 0.0845392294228077,
|
|
"num_tokens": 423176.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.805705642700195,
|
|
"epoch": 0.019619157530294286,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.393,
|
|
"mean_token_accuracy": 0.08622003495693206,
|
|
"num_tokens": 435997.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.710006427764892,
|
|
"epoch": 0.020196191575302943,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.3767,
|
|
"mean_token_accuracy": 0.0884266272187233,
|
|
"num_tokens": 449295.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.714795589447021,
|
|
"epoch": 0.0207732256203116,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.4022,
|
|
"mean_token_accuracy": 0.08629754856228829,
|
|
"num_tokens": 463983.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.6787428855896,
|
|
"epoch": 0.021350259665320254,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.4184,
|
|
"mean_token_accuracy": 0.08215429335832596,
|
|
"num_tokens": 476849.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.687536239624023,
|
|
"epoch": 0.02192729371032891,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.3669,
|
|
"mean_token_accuracy": 0.0866314373910427,
|
|
"num_tokens": 489120.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.578043460845947,
|
|
"epoch": 0.022504327755337564,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.2956,
|
|
"mean_token_accuracy": 0.08582662940025329,
|
|
"num_tokens": 501085.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.653344535827637,
|
|
"epoch": 0.02308136180034622,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.363,
|
|
"mean_token_accuracy": 0.08150185570120812,
|
|
"num_tokens": 513207.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.69477891921997,
|
|
"epoch": 0.023658395845354875,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.2959,
|
|
"mean_token_accuracy": 0.08695114329457283,
|
|
"num_tokens": 524809.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.637209606170654,
|
|
"epoch": 0.024235429890363532,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.333,
|
|
"mean_token_accuracy": 0.08224210143089294,
|
|
"num_tokens": 538950.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.533492851257325,
|
|
"epoch": 0.024812463935372186,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.3069,
|
|
"mean_token_accuracy": 0.09452523067593574,
|
|
"num_tokens": 551199.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.584404468536377,
|
|
"epoch": 0.025389497980380843,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.2458,
|
|
"mean_token_accuracy": 0.09130036383867264,
|
|
"num_tokens": 563202.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.542673492431641,
|
|
"epoch": 0.025966532025389497,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.2308,
|
|
"mean_token_accuracy": 0.09193311482667924,
|
|
"num_tokens": 576716.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.472547721862792,
|
|
"epoch": 0.026543566070398154,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.2372,
|
|
"mean_token_accuracy": 0.09359257072210311,
|
|
"num_tokens": 588413.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.6172194480896,
|
|
"epoch": 0.027120600115406807,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.2871,
|
|
"mean_token_accuracy": 0.08904579505324364,
|
|
"num_tokens": 602052.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.518135070800781,
|
|
"epoch": 0.027697634160415464,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.2266,
|
|
"mean_token_accuracy": 0.09081303253769875,
|
|
"num_tokens": 614508.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.339745807647706,
|
|
"epoch": 0.02827466820542412,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.2549,
|
|
"mean_token_accuracy": 0.09370925053954124,
|
|
"num_tokens": 628758.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.498612117767333,
|
|
"epoch": 0.028851702250432775,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.1684,
|
|
"mean_token_accuracy": 0.09330120757222175,
|
|
"num_tokens": 641046.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.45691146850586,
|
|
"epoch": 0.029428736295441432,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.1807,
|
|
"mean_token_accuracy": 0.09563048109412194,
|
|
"num_tokens": 653910.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.430898475646973,
|
|
"epoch": 0.030005770340450086,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.1546,
|
|
"mean_token_accuracy": 0.10104967132210732,
|
|
"num_tokens": 665862.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.375243663787842,
|
|
"epoch": 0.030582804385458743,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.1507,
|
|
"mean_token_accuracy": 0.10190046802163125,
|
|
"num_tokens": 678854.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.442987442016602,
|
|
"epoch": 0.031159838430467397,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.153,
|
|
"mean_token_accuracy": 0.0963923156261444,
|
|
"num_tokens": 690188.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.430098915100098,
|
|
"epoch": 0.031736872475476054,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.1145,
|
|
"mean_token_accuracy": 0.10212414339184761,
|
|
"num_tokens": 702041.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.371403026580811,
|
|
"epoch": 0.03231390652048471,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.1336,
|
|
"mean_token_accuracy": 0.104609215259552,
|
|
"num_tokens": 714109.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.367766094207763,
|
|
"epoch": 0.03289094056549336,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.1545,
|
|
"mean_token_accuracy": 0.09640730917453766,
|
|
"num_tokens": 726120.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.413183784484863,
|
|
"epoch": 0.03346797461050202,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.1028,
|
|
"mean_token_accuracy": 0.1032490886747837,
|
|
"num_tokens": 737868.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.353041744232177,
|
|
"epoch": 0.034045008655510675,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.193,
|
|
"mean_token_accuracy": 0.10336777493357659,
|
|
"num_tokens": 751829.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.405898094177246,
|
|
"epoch": 0.03462204270051933,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.1197,
|
|
"mean_token_accuracy": 0.10570979490876198,
|
|
"num_tokens": 764457.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.260132122039796,
|
|
"epoch": 0.03519907674552799,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.1569,
|
|
"mean_token_accuracy": 0.10863806083798408,
|
|
"num_tokens": 776887.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.448872661590576,
|
|
"epoch": 0.03577611079053664,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.1229,
|
|
"mean_token_accuracy": 0.10281555876135826,
|
|
"num_tokens": 789001.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.287611865997315,
|
|
"epoch": 0.0363531448355453,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.1195,
|
|
"mean_token_accuracy": 0.1042421966791153,
|
|
"num_tokens": 802719.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.269627094268799,
|
|
"epoch": 0.03693017888055395,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.0398,
|
|
"mean_token_accuracy": 0.10676939561963081,
|
|
"num_tokens": 815064.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.33767261505127,
|
|
"epoch": 0.03750721292556261,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.0822,
|
|
"mean_token_accuracy": 0.11563392803072929,
|
|
"num_tokens": 827778.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.284006214141845,
|
|
"epoch": 0.038084246970571264,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.0403,
|
|
"mean_token_accuracy": 0.10939318239688874,
|
|
"num_tokens": 840691.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.257933616638184,
|
|
"epoch": 0.03866128101557992,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.0932,
|
|
"mean_token_accuracy": 0.0974455177783966,
|
|
"num_tokens": 852818.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.325709438323974,
|
|
"epoch": 0.03923831506058857,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.0914,
|
|
"mean_token_accuracy": 0.11402691900730133,
|
|
"num_tokens": 866854.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.225966930389404,
|
|
"epoch": 0.03981534910559723,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.0414,
|
|
"mean_token_accuracy": 0.10918436199426651,
|
|
"num_tokens": 879234.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.31819543838501,
|
|
"epoch": 0.040392383150605886,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.9951,
|
|
"mean_token_accuracy": 0.10175195261836052,
|
|
"num_tokens": 890927.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.258775520324708,
|
|
"epoch": 0.04096941719561454,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.0307,
|
|
"mean_token_accuracy": 0.11141346469521522,
|
|
"num_tokens": 902965.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.264652919769286,
|
|
"epoch": 0.0415464512406232,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.9938,
|
|
"mean_token_accuracy": 0.11707152500748634,
|
|
"num_tokens": 916384.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.206478118896484,
|
|
"epoch": 0.042123485285631854,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.8976,
|
|
"mean_token_accuracy": 0.12026941180229186,
|
|
"num_tokens": 928618.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.14428939819336,
|
|
"epoch": 0.04270051933064051,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.0097,
|
|
"mean_token_accuracy": 0.10829245820641517,
|
|
"num_tokens": 940087.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.182055187225341,
|
|
"epoch": 0.04327755337564916,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.9847,
|
|
"mean_token_accuracy": 0.11593637242913246,
|
|
"num_tokens": 953322.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.304078960418702,
|
|
"epoch": 0.04385458742065782,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.0352,
|
|
"mean_token_accuracy": 0.11048125922679901,
|
|
"num_tokens": 965815.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.090431594848633,
|
|
"epoch": 0.044431621465666475,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.9867,
|
|
"mean_token_accuracy": 0.11254308521747589,
|
|
"num_tokens": 978731.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.222192001342773,
|
|
"epoch": 0.04500865551067513,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.8833,
|
|
"mean_token_accuracy": 0.11793898567557334,
|
|
"num_tokens": 989505.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.180580139160156,
|
|
"epoch": 0.04558568955568378,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.0039,
|
|
"mean_token_accuracy": 0.11668088957667351,
|
|
"num_tokens": 1001888.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.087317895889282,
|
|
"epoch": 0.04616272360069244,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.9376,
|
|
"mean_token_accuracy": 0.12477797642350197,
|
|
"num_tokens": 1015362.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.24937629699707,
|
|
"epoch": 0.0467397576457011,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.0003,
|
|
"mean_token_accuracy": 0.11018196940422058,
|
|
"num_tokens": 1028700.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.146645069122314,
|
|
"epoch": 0.04731679169070975,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.0355,
|
|
"mean_token_accuracy": 0.1107394464313984,
|
|
"num_tokens": 1040766.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.195110607147218,
|
|
"epoch": 0.04789382573571841,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.8899,
|
|
"mean_token_accuracy": 0.11536648571491241,
|
|
"num_tokens": 1054321.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.083704519271851,
|
|
"epoch": 0.048470859780727064,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.9538,
|
|
"mean_token_accuracy": 0.11945511400699615,
|
|
"num_tokens": 1065410.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.268659496307373,
|
|
"epoch": 0.04904789382573572,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.9799,
|
|
"mean_token_accuracy": 0.10876310393214225,
|
|
"num_tokens": 1077369.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.160646915435791,
|
|
"epoch": 0.04962492787074437,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.9156,
|
|
"mean_token_accuracy": 0.11709627509117126,
|
|
"num_tokens": 1089065.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.05447473526001,
|
|
"epoch": 0.05020196191575303,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.8324,
|
|
"mean_token_accuracy": 0.12342519015073776,
|
|
"num_tokens": 1101285.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.127099323272706,
|
|
"epoch": 0.050778995960761686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.8574,
|
|
"mean_token_accuracy": 0.11566452980041504,
|
|
"num_tokens": 1114001.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.098159694671631,
|
|
"epoch": 0.05135603000577034,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.931,
|
|
"mean_token_accuracy": 0.11353125795722008,
|
|
"num_tokens": 1126751.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.043973064422607,
|
|
"epoch": 0.05193306405077899,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.9191,
|
|
"mean_token_accuracy": 0.1132647417485714,
|
|
"num_tokens": 1140737.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.041358852386475,
|
|
"epoch": 0.052510098095787654,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.8619,
|
|
"mean_token_accuracy": 0.1132751502096653,
|
|
"num_tokens": 1152569.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.193452262878418,
|
|
"epoch": 0.05308713214079631,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.8861,
|
|
"mean_token_accuracy": 0.11552667319774627,
|
|
"num_tokens": 1166163.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.04149374961853,
|
|
"epoch": 0.05366416618580496,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.8398,
|
|
"mean_token_accuracy": 0.11528105437755584,
|
|
"num_tokens": 1177647.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.003826427459718,
|
|
"epoch": 0.054241200230813615,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.8806,
|
|
"mean_token_accuracy": 0.11894029006361961,
|
|
"num_tokens": 1190884.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.122087001800537,
|
|
"epoch": 0.054818234275822275,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.9046,
|
|
"mean_token_accuracy": 0.11480232924222947,
|
|
"num_tokens": 1203276.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.040111637115478,
|
|
"epoch": 0.05539526832083093,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.7945,
|
|
"mean_token_accuracy": 0.12931760177016258,
|
|
"num_tokens": 1216001.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.027564573287965,
|
|
"epoch": 0.05597230236583958,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.9184,
|
|
"mean_token_accuracy": 0.1165414072573185,
|
|
"num_tokens": 1228724.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.061245822906494,
|
|
"epoch": 0.05654933641084824,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.9177,
|
|
"mean_token_accuracy": 0.12267720922827721,
|
|
"num_tokens": 1242731.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.968474864959717,
|
|
"epoch": 0.0571263704558569,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.8711,
|
|
"mean_token_accuracy": 0.11604229137301444,
|
|
"num_tokens": 1255275.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.032691955566406,
|
|
"epoch": 0.05770340450086555,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.8464,
|
|
"mean_token_accuracy": 0.12695102244615555,
|
|
"num_tokens": 1267719.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.0850115776062,
|
|
"epoch": 0.058280438545874204,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.8315,
|
|
"mean_token_accuracy": 0.11815451011061669,
|
|
"num_tokens": 1279960.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.9902856826782225,
|
|
"epoch": 0.058857472590882864,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.8152,
|
|
"mean_token_accuracy": 0.1192896917462349,
|
|
"num_tokens": 1292570.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.022426271438599,
|
|
"epoch": 0.05943450663589152,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.8112,
|
|
"mean_token_accuracy": 0.11861110255122184,
|
|
"num_tokens": 1305548.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.9653082370758055,
|
|
"epoch": 0.06001154068090017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.7512,
|
|
"mean_token_accuracy": 0.12333761304616928,
|
|
"num_tokens": 1318904.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.999736309051514,
|
|
"epoch": 0.060588574725908825,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.8275,
|
|
"mean_token_accuracy": 0.11803121715784073,
|
|
"num_tokens": 1332841.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.946177673339844,
|
|
"epoch": 0.061165608770917486,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.828,
|
|
"mean_token_accuracy": 0.11700976938009262,
|
|
"num_tokens": 1345708.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.01097912788391,
|
|
"epoch": 0.06174264281592614,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.7805,
|
|
"mean_token_accuracy": 0.12158992290496826,
|
|
"num_tokens": 1358611.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.956462049484253,
|
|
"epoch": 0.06231967686093479,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.8431,
|
|
"mean_token_accuracy": 0.1208947941660881,
|
|
"num_tokens": 1372753.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.846506118774414,
|
|
"epoch": 0.06289671090594345,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.7475,
|
|
"mean_token_accuracy": 0.13231490254402162,
|
|
"num_tokens": 1383811.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.998351097106934,
|
|
"epoch": 0.06347374495095211,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.8154,
|
|
"mean_token_accuracy": 0.12150197923183441,
|
|
"num_tokens": 1395228.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.844149923324585,
|
|
"epoch": 0.06405077899596076,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.8298,
|
|
"mean_token_accuracy": 0.11782822757959366,
|
|
"num_tokens": 1408869.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.925115871429443,
|
|
"epoch": 0.06462781304096941,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.7363,
|
|
"mean_token_accuracy": 0.126988285779953,
|
|
"num_tokens": 1420926.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.919132804870605,
|
|
"epoch": 0.06520484708597807,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.7324,
|
|
"mean_token_accuracy": 0.1244761623442173,
|
|
"num_tokens": 1432435.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.929744482040405,
|
|
"epoch": 0.06578188113098672,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.8638,
|
|
"mean_token_accuracy": 0.11697117760777473,
|
|
"num_tokens": 1444716.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.861667013168335,
|
|
"epoch": 0.06635891517599539,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.7398,
|
|
"mean_token_accuracy": 0.12333890348672867,
|
|
"num_tokens": 1458129.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.875370264053345,
|
|
"epoch": 0.06693594922100404,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.7118,
|
|
"mean_token_accuracy": 0.1261540025472641,
|
|
"num_tokens": 1472076.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.806885862350464,
|
|
"epoch": 0.0675129832660127,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.7086,
|
|
"mean_token_accuracy": 0.1355113133788109,
|
|
"num_tokens": 1486026.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.809766578674316,
|
|
"epoch": 0.06809001731102135,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.704,
|
|
"mean_token_accuracy": 0.13341286033391953,
|
|
"num_tokens": 1498735.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.84214186668396,
|
|
"epoch": 0.06866705135603,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.6793,
|
|
"mean_token_accuracy": 0.12912188470363617,
|
|
"num_tokens": 1510755.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.897479295730591,
|
|
"epoch": 0.06924408540103866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.7216,
|
|
"mean_token_accuracy": 0.12750375717878343,
|
|
"num_tokens": 1522386.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.845736980438232,
|
|
"epoch": 0.06982111944604731,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.742,
|
|
"mean_token_accuracy": 0.12660543844103814,
|
|
"num_tokens": 1534757.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.81597785949707,
|
|
"epoch": 0.07039815349105598,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.724,
|
|
"mean_token_accuracy": 0.12527383714914322,
|
|
"num_tokens": 1547684.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.850346899032592,
|
|
"epoch": 0.07097518753606463,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.7303,
|
|
"mean_token_accuracy": 0.11933122873306275,
|
|
"num_tokens": 1560583.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.878012609481812,
|
|
"epoch": 0.07155222158107329,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.7424,
|
|
"mean_token_accuracy": 0.12126323059201241,
|
|
"num_tokens": 1573174.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.815459823608398,
|
|
"epoch": 0.07212925562608194,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.7149,
|
|
"mean_token_accuracy": 0.12385709285736084,
|
|
"num_tokens": 1585746.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.842224073410034,
|
|
"epoch": 0.0727062896710906,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.695,
|
|
"mean_token_accuracy": 0.11776623651385307,
|
|
"num_tokens": 1598538.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.825200510025025,
|
|
"epoch": 0.07328332371609925,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.674,
|
|
"mean_token_accuracy": 0.1275767132639885,
|
|
"num_tokens": 1612598.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.780414009094239,
|
|
"epoch": 0.0738603577611079,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.6161,
|
|
"mean_token_accuracy": 0.13024978637695311,
|
|
"num_tokens": 1624418.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.701315689086914,
|
|
"epoch": 0.07443739180611655,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.7056,
|
|
"mean_token_accuracy": 0.13014591559767724,
|
|
"num_tokens": 1637512.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.68240270614624,
|
|
"epoch": 0.07501442585112522,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.6419,
|
|
"mean_token_accuracy": 0.1289619944989681,
|
|
"num_tokens": 1650413.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.799037647247315,
|
|
"epoch": 0.07559145989613388,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.6123,
|
|
"mean_token_accuracy": 0.13126565814018248,
|
|
"num_tokens": 1662225.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.818531084060669,
|
|
"epoch": 0.07616849394114253,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.6901,
|
|
"mean_token_accuracy": 0.12705290466547012,
|
|
"num_tokens": 1674458.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.750899171829223,
|
|
"epoch": 0.07674552798615118,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.701,
|
|
"mean_token_accuracy": 0.12313887178897857,
|
|
"num_tokens": 1686366.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.7861656665802,
|
|
"epoch": 0.07732256203115984,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.6882,
|
|
"mean_token_accuracy": 0.12421951442956924,
|
|
"num_tokens": 1699654.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.768671703338623,
|
|
"epoch": 0.07789959607616849,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.6462,
|
|
"mean_token_accuracy": 0.12908095195889474,
|
|
"num_tokens": 1711923.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.797735977172851,
|
|
"epoch": 0.07847663012117714,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.6328,
|
|
"mean_token_accuracy": 0.12395294979214669,
|
|
"num_tokens": 1723413.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.680013036727905,
|
|
"epoch": 0.07905366416618581,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.6006,
|
|
"mean_token_accuracy": 0.13139746859669685,
|
|
"num_tokens": 1735975.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.710196876525879,
|
|
"epoch": 0.07963069821119446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.6149,
|
|
"mean_token_accuracy": 0.1285354495048523,
|
|
"num_tokens": 1748563.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.633371353149414,
|
|
"epoch": 0.08020773225620312,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.6288,
|
|
"mean_token_accuracy": 0.12319590821862221,
|
|
"num_tokens": 1762914.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.7966938495635985,
|
|
"epoch": 0.08078476630121177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.5953,
|
|
"mean_token_accuracy": 0.13221077919006347,
|
|
"num_tokens": 1776084.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.640158843994141,
|
|
"epoch": 0.08136180034622043,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.5445,
|
|
"mean_token_accuracy": 0.1401802346110344,
|
|
"num_tokens": 1789316.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.714691829681397,
|
|
"epoch": 0.08193883439122908,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.637,
|
|
"mean_token_accuracy": 0.1277747370302677,
|
|
"num_tokens": 1801576.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.588133955001831,
|
|
"epoch": 0.08251586843623773,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.5861,
|
|
"mean_token_accuracy": 0.13175102695822716,
|
|
"num_tokens": 1814039.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.677944850921631,
|
|
"epoch": 0.0830929024812464,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.53,
|
|
"mean_token_accuracy": 0.131522336602211,
|
|
"num_tokens": 1825193.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.593373250961304,
|
|
"epoch": 0.08366993652625505,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.6051,
|
|
"mean_token_accuracy": 0.12541260421276093,
|
|
"num_tokens": 1837983.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.725003337860107,
|
|
"epoch": 0.08424697057126371,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.5148,
|
|
"mean_token_accuracy": 0.13810623735189437,
|
|
"num_tokens": 1849830.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.61106128692627,
|
|
"epoch": 0.08482400461627236,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.5923,
|
|
"mean_token_accuracy": 0.12345706224441529,
|
|
"num_tokens": 1862577.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.646603107452393,
|
|
"epoch": 0.08540103866128101,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.603,
|
|
"mean_token_accuracy": 0.13642554581165314,
|
|
"num_tokens": 1874888.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.624688339233399,
|
|
"epoch": 0.08597807270628967,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.5309,
|
|
"mean_token_accuracy": 0.1350684270262718,
|
|
"num_tokens": 1888400.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.609202241897583,
|
|
"epoch": 0.08655510675129832,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.6054,
|
|
"mean_token_accuracy": 0.12247811630368233,
|
|
"num_tokens": 1900961.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.590191173553467,
|
|
"epoch": 0.08713214079630698,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.5243,
|
|
"mean_token_accuracy": 0.13634067475795747,
|
|
"num_tokens": 1913410.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.664303922653199,
|
|
"epoch": 0.08770917484131564,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.5827,
|
|
"mean_token_accuracy": 0.12373366355895996,
|
|
"num_tokens": 1926602.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.6440318584442135,
|
|
"epoch": 0.0882862088863243,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.5379,
|
|
"mean_token_accuracy": 0.12371056452393532,
|
|
"num_tokens": 1938904.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.585968399047852,
|
|
"epoch": 0.08886324293133295,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.577,
|
|
"mean_token_accuracy": 0.12310778871178626,
|
|
"num_tokens": 1952827.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.638195276260376,
|
|
"epoch": 0.0894402769763416,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.548,
|
|
"mean_token_accuracy": 0.13129694759845734,
|
|
"num_tokens": 1965182.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.510479879379273,
|
|
"epoch": 0.09001731102135026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.5029,
|
|
"mean_token_accuracy": 0.12708307728171347,
|
|
"num_tokens": 1976953.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.737362003326416,
|
|
"epoch": 0.09059434506635891,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.6022,
|
|
"mean_token_accuracy": 0.12702567875385284,
|
|
"num_tokens": 1990019.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.611118268966675,
|
|
"epoch": 0.09117137911136756,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.5488,
|
|
"mean_token_accuracy": 0.1295396715402603,
|
|
"num_tokens": 2002976.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.59055905342102,
|
|
"epoch": 0.09174841315637623,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.5906,
|
|
"mean_token_accuracy": 0.1250334121286869,
|
|
"num_tokens": 2017368.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.517406940460205,
|
|
"epoch": 0.09232544720138489,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.4334,
|
|
"mean_token_accuracy": 0.13203005865216255,
|
|
"num_tokens": 2029838.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.63545331954956,
|
|
"epoch": 0.09290248124639354,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.5516,
|
|
"mean_token_accuracy": 0.12461932525038719,
|
|
"num_tokens": 2042085.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.604149198532104,
|
|
"epoch": 0.0934795152914022,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.5652,
|
|
"mean_token_accuracy": 0.12991983070969582,
|
|
"num_tokens": 2053268.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.614420986175537,
|
|
"epoch": 0.09405654933641085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.5398,
|
|
"mean_token_accuracy": 0.12179678082466125,
|
|
"num_tokens": 2066621.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.462197637557983,
|
|
"epoch": 0.0946335833814195,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.4241,
|
|
"mean_token_accuracy": 0.13013325929641723,
|
|
"num_tokens": 2079590.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.571118640899658,
|
|
"epoch": 0.09521061742642815,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.5334,
|
|
"mean_token_accuracy": 0.12693382874131204,
|
|
"num_tokens": 2091729.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.510286808013916,
|
|
"epoch": 0.09578765147143682,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.4885,
|
|
"mean_token_accuracy": 0.13465983644127846,
|
|
"num_tokens": 2104254.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.585655641555786,
|
|
"epoch": 0.09636468551644548,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.5596,
|
|
"mean_token_accuracy": 0.12383549585938454,
|
|
"num_tokens": 2116327.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.621681976318359,
|
|
"epoch": 0.09694171956145413,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.5559,
|
|
"mean_token_accuracy": 0.1234694242477417,
|
|
"num_tokens": 2129153.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.49256067276001,
|
|
"epoch": 0.09751875360646278,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.508,
|
|
"mean_token_accuracy": 0.136223391443491,
|
|
"num_tokens": 2141705.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.467943477630615,
|
|
"epoch": 0.09809578765147144,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.4178,
|
|
"mean_token_accuracy": 0.1418270103633404,
|
|
"num_tokens": 2153760.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.600914192199707,
|
|
"epoch": 0.09867282169648009,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5065,
|
|
"mean_token_accuracy": 0.13413666784763337,
|
|
"num_tokens": 2168206.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.570523405075074,
|
|
"epoch": 0.09924985574148874,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.5117,
|
|
"mean_token_accuracy": 0.13071473613381385,
|
|
"num_tokens": 2180779.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.412028741836548,
|
|
"epoch": 0.0998268897864974,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.4373,
|
|
"mean_token_accuracy": 0.13453905433416366,
|
|
"num_tokens": 2194075.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.537879610061646,
|
|
"epoch": 0.10040392383150606,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.4232,
|
|
"mean_token_accuracy": 0.13529622703790664,
|
|
"num_tokens": 2206424.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.555378055572509,
|
|
"epoch": 0.10098095787651472,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.4432,
|
|
"mean_token_accuracy": 0.1277135990560055,
|
|
"num_tokens": 2218550.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.4310328483581545,
|
|
"epoch": 0.10155799192152337,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.4761,
|
|
"mean_token_accuracy": 0.1309943303465843,
|
|
"num_tokens": 2231857.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.488246202468872,
|
|
"epoch": 0.10213502596653203,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.4876,
|
|
"mean_token_accuracy": 0.13225487917661666,
|
|
"num_tokens": 2244057.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.613044691085816,
|
|
"epoch": 0.10271206001154068,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.5175,
|
|
"mean_token_accuracy": 0.12458534613251686,
|
|
"num_tokens": 2257361.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.529584169387817,
|
|
"epoch": 0.10328909405654933,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.4967,
|
|
"mean_token_accuracy": 0.12664385214447976,
|
|
"num_tokens": 2269599.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.492797708511352,
|
|
"epoch": 0.10386612810155799,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.5168,
|
|
"mean_token_accuracy": 0.12740001678466797,
|
|
"num_tokens": 2282791.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.53049669265747,
|
|
"epoch": 0.10444316214656665,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.4807,
|
|
"mean_token_accuracy": 0.13134395331144333,
|
|
"num_tokens": 2295336.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.494025135040284,
|
|
"epoch": 0.10502019619157531,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.4828,
|
|
"mean_token_accuracy": 0.12917752116918563,
|
|
"num_tokens": 2308813.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.475014638900757,
|
|
"epoch": 0.10559723023658396,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.4671,
|
|
"mean_token_accuracy": 0.12653358280658722,
|
|
"num_tokens": 2321374.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.4855108737945555,
|
|
"epoch": 0.10617426428159261,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.4787,
|
|
"mean_token_accuracy": 0.12270581796765327,
|
|
"num_tokens": 2333698.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.527695846557617,
|
|
"epoch": 0.10675129832660127,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.4649,
|
|
"mean_token_accuracy": 0.13576419949531554,
|
|
"num_tokens": 2346557.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.328889083862305,
|
|
"epoch": 0.10732833237160992,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.3053,
|
|
"mean_token_accuracy": 0.1375327415764332,
|
|
"num_tokens": 2360003.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.464563989639283,
|
|
"epoch": 0.10790536641661858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.3543,
|
|
"mean_token_accuracy": 0.13607896789908408,
|
|
"num_tokens": 2372765.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.372702598571777,
|
|
"epoch": 0.10848240046162723,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.3561,
|
|
"mean_token_accuracy": 0.13873768970370293,
|
|
"num_tokens": 2385154.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.381151580810547,
|
|
"epoch": 0.1090594345066359,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.3805,
|
|
"mean_token_accuracy": 0.13930853679776192,
|
|
"num_tokens": 2397264.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.4766237258911135,
|
|
"epoch": 0.10963646855164455,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.4843,
|
|
"mean_token_accuracy": 0.13500367030501365,
|
|
"num_tokens": 2408652.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.411814785003662,
|
|
"epoch": 0.1102135025966532,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.4289,
|
|
"mean_token_accuracy": 0.12838349416851996,
|
|
"num_tokens": 2421683.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.380972909927368,
|
|
"epoch": 0.11079053664166186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.3453,
|
|
"mean_token_accuracy": 0.1313640892505646,
|
|
"num_tokens": 2434622.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.420246410369873,
|
|
"epoch": 0.11136757068667051,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.3595,
|
|
"mean_token_accuracy": 0.14137982428073884,
|
|
"num_tokens": 2448157.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.482502222061157,
|
|
"epoch": 0.11194460473167916,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.4034,
|
|
"mean_token_accuracy": 0.1286494918167591,
|
|
"num_tokens": 2460284.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.2979847431182865,
|
|
"epoch": 0.11252163877668782,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.4166,
|
|
"mean_token_accuracy": 0.13066136166453363,
|
|
"num_tokens": 2473031.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.43588399887085,
|
|
"epoch": 0.11309867282169649,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.429,
|
|
"mean_token_accuracy": 0.1351068213582039,
|
|
"num_tokens": 2486870.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.407749509811401,
|
|
"epoch": 0.11367570686670514,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.3198,
|
|
"mean_token_accuracy": 0.1358391098678112,
|
|
"num_tokens": 2498921.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.458673715591431,
|
|
"epoch": 0.1142527409117138,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.3969,
|
|
"mean_token_accuracy": 0.13049472868442535,
|
|
"num_tokens": 2511122.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.389868688583374,
|
|
"epoch": 0.11482977495672245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.4051,
|
|
"mean_token_accuracy": 0.1294924721121788,
|
|
"num_tokens": 2523726.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.3466997146606445,
|
|
"epoch": 0.1154068090017311,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.3137,
|
|
"mean_token_accuracy": 0.13630730137228966,
|
|
"num_tokens": 2536192.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.343966245651245,
|
|
"epoch": 0.11598384304673975,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999999975783157,
|
|
"loss": 7.3879,
|
|
"mean_token_accuracy": 0.13277141600847245,
|
|
"num_tokens": 2550200.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.345440340042114,
|
|
"epoch": 0.11656087709174841,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999999877402236,
|
|
"loss": 7.3285,
|
|
"mean_token_accuracy": 0.137277489900589,
|
|
"num_tokens": 2564045.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.331404352188111,
|
|
"epoch": 0.11713791113675708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999703343686,
|
|
"loss": 7.3359,
|
|
"mean_token_accuracy": 0.13079950734972953,
|
|
"num_tokens": 2576210.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.2891435623168945,
|
|
"epoch": 0.11771494518176573,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999999453607515,
|
|
"loss": 7.3348,
|
|
"mean_token_accuracy": 0.13124105408787728,
|
|
"num_tokens": 2589325.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.409384393692017,
|
|
"epoch": 0.11829197922677438,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999128193729,
|
|
"loss": 7.4309,
|
|
"mean_token_accuracy": 0.13288950622081758,
|
|
"num_tokens": 2601522.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.3894264698028564,
|
|
"epoch": 0.11886901327178304,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499999872710234,
|
|
"loss": 7.3974,
|
|
"mean_token_accuracy": 0.1278626799583435,
|
|
"num_tokens": 2615364.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.375164937973023,
|
|
"epoch": 0.11944604731679169,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999998250333361,
|
|
"loss": 7.3142,
|
|
"mean_token_accuracy": 0.1343100145459175,
|
|
"num_tokens": 2628528.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.282582569122314,
|
|
"epoch": 0.12002308136180034,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499999769788681,
|
|
"loss": 7.3058,
|
|
"mean_token_accuracy": 0.1310929149389267,
|
|
"num_tokens": 2641877.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.369835758209229,
|
|
"epoch": 0.120600115406809,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999997069762703,
|
|
"loss": 7.3171,
|
|
"mean_token_accuracy": 0.13292421400547028,
|
|
"num_tokens": 2655419.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.171972227096558,
|
|
"epoch": 0.12117714945181765,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999996365961062,
|
|
"loss": 7.2777,
|
|
"mean_token_accuracy": 0.13511810302734376,
|
|
"num_tokens": 2667551.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.34223484992981,
|
|
"epoch": 0.12175418349682632,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999995586481912,
|
|
"loss": 7.3047,
|
|
"mean_token_accuracy": 0.13582876622676848,
|
|
"num_tokens": 2679948.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.260743761062622,
|
|
"epoch": 0.12233121754183497,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999994731325276,
|
|
"loss": 7.3492,
|
|
"mean_token_accuracy": 0.1337125964462757,
|
|
"num_tokens": 2691501.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.260812520980835,
|
|
"epoch": 0.12290825158684363,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993800491187,
|
|
"loss": 7.2664,
|
|
"mean_token_accuracy": 0.13844716772437096,
|
|
"num_tokens": 2702689.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.332363796234131,
|
|
"epoch": 0.12348528563185228,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999992793979672,
|
|
"loss": 7.2764,
|
|
"mean_token_accuracy": 0.13439239487051963,
|
|
"num_tokens": 2715023.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.202269220352173,
|
|
"epoch": 0.12406231967686093,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999991711790769,
|
|
"loss": 7.2274,
|
|
"mean_token_accuracy": 0.13450795337557792,
|
|
"num_tokens": 2729517.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.301486778259277,
|
|
"epoch": 0.12463935372186959,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999990553924511,
|
|
"loss": 7.3108,
|
|
"mean_token_accuracy": 0.13219440579414368,
|
|
"num_tokens": 2740984.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.299670457839966,
|
|
"epoch": 0.12521638776687824,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999989320380939,
|
|
"loss": 7.252,
|
|
"mean_token_accuracy": 0.13629381954669953,
|
|
"num_tokens": 2752943.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.296296072006226,
|
|
"epoch": 0.1257934218118869,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999988011160094,
|
|
"loss": 7.3008,
|
|
"mean_token_accuracy": 0.13499366268515586,
|
|
"num_tokens": 2765613.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.2634941101074215,
|
|
"epoch": 0.12637045585689555,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499998662626202,
|
|
"loss": 7.2476,
|
|
"mean_token_accuracy": 0.13409144133329393,
|
|
"num_tokens": 2776820.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.248972606658936,
|
|
"epoch": 0.12694748990190421,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999985165686764,
|
|
"loss": 7.2846,
|
|
"mean_token_accuracy": 0.13224128484725953,
|
|
"num_tokens": 2788981.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.163676500320435,
|
|
"epoch": 0.12752452394691285,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004999983629434373,
|
|
"loss": 7.1433,
|
|
"mean_token_accuracy": 0.14286725521087645,
|
|
"num_tokens": 2801975.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.309284687042236,
|
|
"epoch": 0.12810155799192152,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999982017504901,
|
|
"loss": 7.2511,
|
|
"mean_token_accuracy": 0.12998932003974914,
|
|
"num_tokens": 2814708.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.249689722061158,
|
|
"epoch": 0.1286785920369302,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999980329898401,
|
|
"loss": 7.2684,
|
|
"mean_token_accuracy": 0.13964115902781488,
|
|
"num_tokens": 2827903.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.2154786586761475,
|
|
"epoch": 0.12925562608193883,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499997856661493,
|
|
"loss": 7.2893,
|
|
"mean_token_accuracy": 0.1352258048951626,
|
|
"num_tokens": 2841077.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.290196561813355,
|
|
"epoch": 0.1298326601269475,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499997672765455,
|
|
"loss": 7.2744,
|
|
"mean_token_accuracy": 0.13311855792999266,
|
|
"num_tokens": 2853235.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.231596946716309,
|
|
"epoch": 0.13040969417195614,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999974813017318,
|
|
"loss": 7.2546,
|
|
"mean_token_accuracy": 0.1340233527123928,
|
|
"num_tokens": 2864937.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.187311124801636,
|
|
"epoch": 0.1309867282169648,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999972822703301,
|
|
"loss": 7.1922,
|
|
"mean_token_accuracy": 0.148747056722641,
|
|
"num_tokens": 2877791.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.157298278808594,
|
|
"epoch": 0.13156376226197344,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999970756712567,
|
|
"loss": 7.1925,
|
|
"mean_token_accuracy": 0.13003327026963235,
|
|
"num_tokens": 2889897.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.245456647872925,
|
|
"epoch": 0.1321407963069821,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999968615045183,
|
|
"loss": 7.2011,
|
|
"mean_token_accuracy": 0.13551229760050773,
|
|
"num_tokens": 2902806.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.156963729858399,
|
|
"epoch": 0.13271783035199078,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999966397701222,
|
|
"loss": 7.109,
|
|
"mean_token_accuracy": 0.14400240257382393,
|
|
"num_tokens": 2915703.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.207495975494385,
|
|
"epoch": 0.13329486439699942,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999964104680759,
|
|
"loss": 7.316,
|
|
"mean_token_accuracy": 0.12647873908281326,
|
|
"num_tokens": 2928171.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.237271070480347,
|
|
"epoch": 0.13387189844200809,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999961735983871,
|
|
"loss": 7.1198,
|
|
"mean_token_accuracy": 0.14833424836397172,
|
|
"num_tokens": 2939909.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.277281904220581,
|
|
"epoch": 0.13444893248701673,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999959291610639,
|
|
"loss": 7.2618,
|
|
"mean_token_accuracy": 0.13249962106347085,
|
|
"num_tokens": 2951510.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.115877532958985,
|
|
"epoch": 0.1350259665320254,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999956771561143,
|
|
"loss": 7.1946,
|
|
"mean_token_accuracy": 0.13074965700507163,
|
|
"num_tokens": 2963326.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.202230167388916,
|
|
"epoch": 0.13560300057703403,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999954175835469,
|
|
"loss": 7.2159,
|
|
"mean_token_accuracy": 0.14419033750891685,
|
|
"num_tokens": 2976226.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.2409210205078125,
|
|
"epoch": 0.1361800346220427,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999951504433703,
|
|
"loss": 7.2179,
|
|
"mean_token_accuracy": 0.13466040119528772,
|
|
"num_tokens": 2988180.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.1283531665802,
|
|
"epoch": 0.13675706866705137,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999948757355935,
|
|
"loss": 7.1966,
|
|
"mean_token_accuracy": 0.1367337226867676,
|
|
"num_tokens": 3000215.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.235973787307739,
|
|
"epoch": 0.13733410271206,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499994593460226,
|
|
"loss": 7.2033,
|
|
"mean_token_accuracy": 0.13479142561554908,
|
|
"num_tokens": 3012516.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.171559572219849,
|
|
"epoch": 0.13791113675706868,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999943036172771,
|
|
"loss": 7.1937,
|
|
"mean_token_accuracy": 0.13718242719769477,
|
|
"num_tokens": 3024786.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.207344961166382,
|
|
"epoch": 0.13848817080207732,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999940062067565,
|
|
"loss": 7.1336,
|
|
"mean_token_accuracy": 0.14108351469039918,
|
|
"num_tokens": 3037179.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.102613258361816,
|
|
"epoch": 0.13906520484708598,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999937012286742,
|
|
"loss": 7.2248,
|
|
"mean_token_accuracy": 0.13997655510902404,
|
|
"num_tokens": 3049443.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.126314640045166,
|
|
"epoch": 0.13964223889209462,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999933886830405,
|
|
"loss": 7.1425,
|
|
"mean_token_accuracy": 0.13395074158906936,
|
|
"num_tokens": 3061857.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.17795877456665,
|
|
"epoch": 0.1402192729371033,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499993068569866,
|
|
"loss": 7.1606,
|
|
"mean_token_accuracy": 0.14002601727843283,
|
|
"num_tokens": 3075185.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.182628631591797,
|
|
"epoch": 0.14079630698211196,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999927408891614,
|
|
"loss": 7.1809,
|
|
"mean_token_accuracy": 0.1401163399219513,
|
|
"num_tokens": 3087645.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.178424263000489,
|
|
"epoch": 0.1413733410271206,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999924056409378,
|
|
"loss": 7.1728,
|
|
"mean_token_accuracy": 0.13846464678645135,
|
|
"num_tokens": 3101185.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.171338224411011,
|
|
"epoch": 0.14195037507212926,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999920628252063,
|
|
"loss": 7.1424,
|
|
"mean_token_accuracy": 0.1404540069401264,
|
|
"num_tokens": 3113694.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.138214826583862,
|
|
"epoch": 0.1425274091171379,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999917124419785,
|
|
"loss": 7.2063,
|
|
"mean_token_accuracy": 0.13672061413526534,
|
|
"num_tokens": 3128225.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.167185831069946,
|
|
"epoch": 0.14310444316214657,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999913544912664,
|
|
"loss": 7.1181,
|
|
"mean_token_accuracy": 0.14096531718969346,
|
|
"num_tokens": 3140118.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.1235737800598145,
|
|
"epoch": 0.1436814772071552,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999909889730817,
|
|
"loss": 7.1932,
|
|
"mean_token_accuracy": 0.13819051831960677,
|
|
"num_tokens": 3153479.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.166897106170654,
|
|
"epoch": 0.14425851125216388,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999906158874368,
|
|
"loss": 7.2083,
|
|
"mean_token_accuracy": 0.1376192092895508,
|
|
"num_tokens": 3167062.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.201770496368408,
|
|
"epoch": 0.14483554529717255,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999902352343444,
|
|
"loss": 7.1495,
|
|
"mean_token_accuracy": 0.13775450959801674,
|
|
"num_tokens": 3179061.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.051590633392334,
|
|
"epoch": 0.1454125793421812,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999898470138171,
|
|
"loss": 7.0898,
|
|
"mean_token_accuracy": 0.13835083171725274,
|
|
"num_tokens": 3191333.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.196379327774048,
|
|
"epoch": 0.14598961338718985,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999894512258681,
|
|
"loss": 7.2138,
|
|
"mean_token_accuracy": 0.13437894061207772,
|
|
"num_tokens": 3204487.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.099405574798584,
|
|
"epoch": 0.1465666474321985,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999890478705107,
|
|
"loss": 7.1498,
|
|
"mean_token_accuracy": 0.13982188031077386,
|
|
"num_tokens": 3216733.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.126603460311889,
|
|
"epoch": 0.14714368147720716,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999886369477585,
|
|
"loss": 7.1008,
|
|
"mean_token_accuracy": 0.14624265134334563,
|
|
"num_tokens": 3229605.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.108373546600342,
|
|
"epoch": 0.1477207155222158,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999882184576251,
|
|
"loss": 7.1291,
|
|
"mean_token_accuracy": 0.14253087043762208,
|
|
"num_tokens": 3241023.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.071506214141846,
|
|
"epoch": 0.14829774956722447,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999877924001248,
|
|
"loss": 7.1085,
|
|
"mean_token_accuracy": 0.140438162535429,
|
|
"num_tokens": 3252435.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.088503217697143,
|
|
"epoch": 0.1488747836122331,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999873587752718,
|
|
"loss": 7.1087,
|
|
"mean_token_accuracy": 0.14706358760595323,
|
|
"num_tokens": 3265663.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.13412880897522,
|
|
"epoch": 0.14945181765724178,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999869175830808,
|
|
"loss": 7.1706,
|
|
"mean_token_accuracy": 0.13438717648386955,
|
|
"num_tokens": 3278309.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.13091197013855,
|
|
"epoch": 0.15002885170225044,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999864688235666,
|
|
"loss": 7.1685,
|
|
"mean_token_accuracy": 0.13528112545609475,
|
|
"num_tokens": 3290899.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.147723531723022,
|
|
"epoch": 0.15060588574725908,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999860124967442,
|
|
"loss": 7.1177,
|
|
"mean_token_accuracy": 0.1383133314549923,
|
|
"num_tokens": 3304383.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.104861927032471,
|
|
"epoch": 0.15118291979226775,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999855486026291,
|
|
"loss": 7.1012,
|
|
"mean_token_accuracy": 0.13756937012076378,
|
|
"num_tokens": 3316310.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.1159440040588375,
|
|
"epoch": 0.1517599538372764,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999850771412369,
|
|
"loss": 7.2206,
|
|
"mean_token_accuracy": 0.1360413908958435,
|
|
"num_tokens": 3330018.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.2038905143737795,
|
|
"epoch": 0.15233698788228506,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999845981125832,
|
|
"loss": 7.2703,
|
|
"mean_token_accuracy": 0.13766002431511878,
|
|
"num_tokens": 3343134.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.998542404174804,
|
|
"epoch": 0.1529140219272937,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999841115166844,
|
|
"loss": 7.0589,
|
|
"mean_token_accuracy": 0.14428165778517724,
|
|
"num_tokens": 3356262.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.208941078186035,
|
|
"epoch": 0.15349105597230236,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999836173535568,
|
|
"loss": 7.2169,
|
|
"mean_token_accuracy": 0.1266804538667202,
|
|
"num_tokens": 3369672.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.099120426177978,
|
|
"epoch": 0.15406809001731103,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999831156232169,
|
|
"loss": 7.1171,
|
|
"mean_token_accuracy": 0.14152806103229523,
|
|
"num_tokens": 3381677.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.098885917663575,
|
|
"epoch": 0.15464512406231967,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999826063256818,
|
|
"loss": 7.0637,
|
|
"mean_token_accuracy": 0.14230246171355249,
|
|
"num_tokens": 3394662.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.04814887046814,
|
|
"epoch": 0.15522215810732834,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999820894609683,
|
|
"loss": 7.0554,
|
|
"mean_token_accuracy": 0.1400335341691971,
|
|
"num_tokens": 3407286.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.218550014495849,
|
|
"epoch": 0.15579919215233698,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999815650290941,
|
|
"loss": 7.1649,
|
|
"mean_token_accuracy": 0.13119087666273116,
|
|
"num_tokens": 3419478.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.062303972244263,
|
|
"epoch": 0.15637622619734565,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999810330300766,
|
|
"loss": 7.1215,
|
|
"mean_token_accuracy": 0.13765157833695413,
|
|
"num_tokens": 3433188.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.134823131561279,
|
|
"epoch": 0.1569532602423543,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499980493463934,
|
|
"loss": 7.055,
|
|
"mean_token_accuracy": 0.13748886287212372,
|
|
"num_tokens": 3445806.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.075977420806884,
|
|
"epoch": 0.15753029428736295,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999799463306841,
|
|
"loss": 7.1166,
|
|
"mean_token_accuracy": 0.1390516623854637,
|
|
"num_tokens": 3458931.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.105384302139282,
|
|
"epoch": 0.15810732833237162,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999793916303455,
|
|
"loss": 7.1395,
|
|
"mean_token_accuracy": 0.13716089800000192,
|
|
"num_tokens": 3471338.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.144868850708008,
|
|
"epoch": 0.15868436237738026,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999788293629368,
|
|
"loss": 7.1956,
|
|
"mean_token_accuracy": 0.13625281676650047,
|
|
"num_tokens": 3484865.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.1175049304962155,
|
|
"epoch": 0.15926139642238893,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499978259528477,
|
|
"loss": 7.027,
|
|
"mean_token_accuracy": 0.14556030482053756,
|
|
"num_tokens": 3496676.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.959357500076294,
|
|
"epoch": 0.15983843046739757,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999776821269852,
|
|
"loss": 7.0128,
|
|
"mean_token_accuracy": 0.14267347529530525,
|
|
"num_tokens": 3508748.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.115108299255371,
|
|
"epoch": 0.16041546451240624,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999770971584807,
|
|
"loss": 7.1525,
|
|
"mean_token_accuracy": 0.13423006609082222,
|
|
"num_tokens": 3521490.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.066515588760376,
|
|
"epoch": 0.16099249855741488,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999765046229834,
|
|
"loss": 7.1036,
|
|
"mean_token_accuracy": 0.13900410309433936,
|
|
"num_tokens": 3534092.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.138736629486084,
|
|
"epoch": 0.16156953260242354,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499975904520513,
|
|
"loss": 7.0817,
|
|
"mean_token_accuracy": 0.13845248967409135,
|
|
"num_tokens": 3546583.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.003001499176025,
|
|
"epoch": 0.1621465666474322,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049997529685109,
|
|
"loss": 7.062,
|
|
"mean_token_accuracy": 0.13950492888689042,
|
|
"num_tokens": 3559409.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.0664629459381105,
|
|
"epoch": 0.16272360069244085,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999746816147344,
|
|
"loss": 7.0779,
|
|
"mean_token_accuracy": 0.1423931375145912,
|
|
"num_tokens": 3572362.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.987629556655884,
|
|
"epoch": 0.16330063473744952,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999740588114673,
|
|
"loss": 7.0577,
|
|
"mean_token_accuracy": 0.1511901132762432,
|
|
"num_tokens": 3585505.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.129745292663574,
|
|
"epoch": 0.16387766878245816,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999734284413095,
|
|
"loss": 7.089,
|
|
"mean_token_accuracy": 0.14135312885046006,
|
|
"num_tokens": 3597322.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.032627248764038,
|
|
"epoch": 0.16445470282746683,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499972790504282,
|
|
"loss": 7.08,
|
|
"mean_token_accuracy": 0.13861621245741845,
|
|
"num_tokens": 3609941.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.072962760925293,
|
|
"epoch": 0.16503173687247547,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999721450004067,
|
|
"loss": 7.1308,
|
|
"mean_token_accuracy": 0.1348639465868473,
|
|
"num_tokens": 3621751.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.07695050239563,
|
|
"epoch": 0.16560877091748413,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999714919297049,
|
|
"loss": 7.0637,
|
|
"mean_token_accuracy": 0.13544038236141204,
|
|
"num_tokens": 3633070.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.08627667427063,
|
|
"epoch": 0.1661858049624928,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999708312921987,
|
|
"loss": 7.062,
|
|
"mean_token_accuracy": 0.1404960945248604,
|
|
"num_tokens": 3646730.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.044391202926636,
|
|
"epoch": 0.16676283900750144,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999701630879103,
|
|
"loss": 7.0817,
|
|
"mean_token_accuracy": 0.13194262310862542,
|
|
"num_tokens": 3659976.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.109149980545044,
|
|
"epoch": 0.1673398730525101,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999694873168623,
|
|
"loss": 7.0424,
|
|
"mean_token_accuracy": 0.13931129574775697,
|
|
"num_tokens": 3672607.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.845404720306396,
|
|
"epoch": 0.16791690709751875,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999688039790773,
|
|
"loss": 6.9822,
|
|
"mean_token_accuracy": 0.1478599414229393,
|
|
"num_tokens": 3686338.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.102566385269165,
|
|
"epoch": 0.16849394114252741,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999681130745784,
|
|
"loss": 6.9808,
|
|
"mean_token_accuracy": 0.14532144814729692,
|
|
"num_tokens": 3698986.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.975255870819092,
|
|
"epoch": 0.16907097518753605,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999674146033888,
|
|
"loss": 7.0262,
|
|
"mean_token_accuracy": 0.14121559485793114,
|
|
"num_tokens": 3712453.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.975798940658569,
|
|
"epoch": 0.16964800923254472,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999667085655318,
|
|
"loss": 7.0204,
|
|
"mean_token_accuracy": 0.13978162109851838,
|
|
"num_tokens": 3724769.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.082622957229614,
|
|
"epoch": 0.1702250432775534,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999659949610313,
|
|
"loss": 7.0893,
|
|
"mean_token_accuracy": 0.1329570822417736,
|
|
"num_tokens": 3738052.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.094326066970825,
|
|
"epoch": 0.17080207732256203,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999652737899114,
|
|
"loss": 7.069,
|
|
"mean_token_accuracy": 0.1364828757941723,
|
|
"num_tokens": 3751279.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.166085195541382,
|
|
"epoch": 0.1713791113675707,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999645450521963,
|
|
"loss": 7.103,
|
|
"mean_token_accuracy": 0.13400057479739189,
|
|
"num_tokens": 3764688.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.996908283233642,
|
|
"epoch": 0.17195614541257934,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999638087479104,
|
|
"loss": 7.0783,
|
|
"mean_token_accuracy": 0.13772108033299446,
|
|
"num_tokens": 3776892.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.068263149261474,
|
|
"epoch": 0.172533179457588,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999630648770786,
|
|
"loss": 6.9956,
|
|
"mean_token_accuracy": 0.14322299733757973,
|
|
"num_tokens": 3789287.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.010704708099365,
|
|
"epoch": 0.17311021350259664,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999623134397257,
|
|
"loss": 6.9804,
|
|
"mean_token_accuracy": 0.14074287414550782,
|
|
"num_tokens": 3801467.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.005624055862427,
|
|
"epoch": 0.1736872475476053,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999615544358774,
|
|
"loss": 7.0687,
|
|
"mean_token_accuracy": 0.1379397466778755,
|
|
"num_tokens": 3814641.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.096045875549317,
|
|
"epoch": 0.17426428159261395,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999607878655587,
|
|
"loss": 7.1202,
|
|
"mean_token_accuracy": 0.1285720944404602,
|
|
"num_tokens": 3827187.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.925661325454712,
|
|
"epoch": 0.17484131563762262,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999600137287958,
|
|
"loss": 6.9458,
|
|
"mean_token_accuracy": 0.14802878797054292,
|
|
"num_tokens": 3839832.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.925600910186768,
|
|
"epoch": 0.17541834968263129,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999592320256146,
|
|
"loss": 6.9369,
|
|
"mean_token_accuracy": 0.14163559377193452,
|
|
"num_tokens": 3852026.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.0402978420257565,
|
|
"epoch": 0.17599538372763993,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999584427560412,
|
|
"loss": 6.9887,
|
|
"mean_token_accuracy": 0.14230965897440911,
|
|
"num_tokens": 3864481.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.93634524345398,
|
|
"epoch": 0.1765724177726486,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999576459201024,
|
|
"loss": 6.9934,
|
|
"mean_token_accuracy": 0.13747925013303758,
|
|
"num_tokens": 3876896.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.970355272293091,
|
|
"epoch": 0.17714945181765723,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499956841517825,
|
|
"loss": 6.9343,
|
|
"mean_token_accuracy": 0.14277037978172302,
|
|
"num_tokens": 3890230.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.0250482082366945,
|
|
"epoch": 0.1777264858626659,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499956029549236,
|
|
"loss": 7.0565,
|
|
"mean_token_accuracy": 0.13747095838189125,
|
|
"num_tokens": 3903138.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.930648469924927,
|
|
"epoch": 0.17830351990767454,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999552100143625,
|
|
"loss": 6.9767,
|
|
"mean_token_accuracy": 0.14407200664281844,
|
|
"num_tokens": 3915709.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.993716144561768,
|
|
"epoch": 0.1788805539526832,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999543829132324,
|
|
"loss": 7.0377,
|
|
"mean_token_accuracy": 0.14300602152943612,
|
|
"num_tokens": 3929265.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.9691534519195555,
|
|
"epoch": 0.17945758799769188,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999535482458734,
|
|
"loss": 7.0303,
|
|
"mean_token_accuracy": 0.14471401274204254,
|
|
"num_tokens": 3940416.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.017536211013794,
|
|
"epoch": 0.18003462204270052,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999527060123135,
|
|
"loss": 7.0353,
|
|
"mean_token_accuracy": 0.13983824625611305,
|
|
"num_tokens": 3952999.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.961780738830567,
|
|
"epoch": 0.18061165608770918,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999518562125811,
|
|
"loss": 7.0434,
|
|
"mean_token_accuracy": 0.1446625217795372,
|
|
"num_tokens": 3966852.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.034871435165405,
|
|
"epoch": 0.18118869013271782,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999509988467047,
|
|
"loss": 6.9454,
|
|
"mean_token_accuracy": 0.1454066276550293,
|
|
"num_tokens": 3978242.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.999048185348511,
|
|
"epoch": 0.1817657241777265,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999501339147132,
|
|
"loss": 7.0631,
|
|
"mean_token_accuracy": 0.1318775437772274,
|
|
"num_tokens": 3993122.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.070727872848511,
|
|
"epoch": 0.18234275822273513,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999492614166357,
|
|
"loss": 6.9982,
|
|
"mean_token_accuracy": 0.13728258460760118,
|
|
"num_tokens": 4005230.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.8208441734313965,
|
|
"epoch": 0.1829197922677438,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999483813525014,
|
|
"loss": 6.9562,
|
|
"mean_token_accuracy": 0.1456133134663105,
|
|
"num_tokens": 4017413.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.0011646270751955,
|
|
"epoch": 0.18349682631275246,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999474937223403,
|
|
"loss": 6.9658,
|
|
"mean_token_accuracy": 0.13678978830575944,
|
|
"num_tokens": 4029679.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.959320497512818,
|
|
"epoch": 0.1840738603577611,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999465985261818,
|
|
"loss": 6.9334,
|
|
"mean_token_accuracy": 0.13753121122717857,
|
|
"num_tokens": 4041857.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.92169075012207,
|
|
"epoch": 0.18465089440276977,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999456957640562,
|
|
"loss": 7.0058,
|
|
"mean_token_accuracy": 0.13973769545555115,
|
|
"num_tokens": 4054743.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.9015570163726805,
|
|
"epoch": 0.1852279284477784,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999447854359939,
|
|
"loss": 6.9409,
|
|
"mean_token_accuracy": 0.14501563981175422,
|
|
"num_tokens": 4067554.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.993334484100342,
|
|
"epoch": 0.18580496249278708,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999438675420255,
|
|
"loss": 6.9275,
|
|
"mean_token_accuracy": 0.1423199862241745,
|
|
"num_tokens": 4079912.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.959068775177002,
|
|
"epoch": 0.18638199653779572,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999429420821818,
|
|
"loss": 7.0423,
|
|
"mean_token_accuracy": 0.13619612157344818,
|
|
"num_tokens": 4093217.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.929660987854004,
|
|
"epoch": 0.1869590305828044,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499942009056494,
|
|
"loss": 6.9966,
|
|
"mean_token_accuracy": 0.13814261704683303,
|
|
"num_tokens": 4104328.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.034404706954956,
|
|
"epoch": 0.18753606462781305,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999410684649935,
|
|
"loss": 6.9616,
|
|
"mean_token_accuracy": 0.13907690942287446,
|
|
"num_tokens": 4116711.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.979753398895264,
|
|
"epoch": 0.1881130986728217,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999401203077119,
|
|
"loss": 6.9733,
|
|
"mean_token_accuracy": 0.14133966118097305,
|
|
"num_tokens": 4129066.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.9114867687225345,
|
|
"epoch": 0.18869013271783036,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499939164584681,
|
|
"loss": 6.8953,
|
|
"mean_token_accuracy": 0.14570464044809342,
|
|
"num_tokens": 4141312.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.891939115524292,
|
|
"epoch": 0.189267166762839,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999382012959331,
|
|
"loss": 6.9311,
|
|
"mean_token_accuracy": 0.14414507225155831,
|
|
"num_tokens": 4154687.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.044634866714477,
|
|
"epoch": 0.18984420080784767,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999372304415005,
|
|
"loss": 7.0448,
|
|
"mean_token_accuracy": 0.13355328813195227,
|
|
"num_tokens": 4168401.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.9447554588317875,
|
|
"epoch": 0.1904212348528563,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999362520214159,
|
|
"loss": 6.949,
|
|
"mean_token_accuracy": 0.14309759065508842,
|
|
"num_tokens": 4180707.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.960445737838745,
|
|
"epoch": 0.19099826889786498,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999352660357122,
|
|
"loss": 6.8926,
|
|
"mean_token_accuracy": 0.145469331741333,
|
|
"num_tokens": 4192939.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.897533369064331,
|
|
"epoch": 0.19157530294287364,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999342724844226,
|
|
"loss": 6.9289,
|
|
"mean_token_accuracy": 0.14193087741732596,
|
|
"num_tokens": 4206277.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.960471534729004,
|
|
"epoch": 0.19215233698788228,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999332713675804,
|
|
"loss": 6.9495,
|
|
"mean_token_accuracy": 0.1454074963927269,
|
|
"num_tokens": 4218672.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.909567642211914,
|
|
"epoch": 0.19272937103289095,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999322626852193,
|
|
"loss": 6.9078,
|
|
"mean_token_accuracy": 0.15034415572881699,
|
|
"num_tokens": 4229002.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.856534433364868,
|
|
"epoch": 0.1933064050778996,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999312464373734,
|
|
"loss": 6.822,
|
|
"mean_token_accuracy": 0.15208742171525955,
|
|
"num_tokens": 4241986.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.847362995147705,
|
|
"epoch": 0.19388343912290826,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999302226240767,
|
|
"loss": 6.9334,
|
|
"mean_token_accuracy": 0.14470148533582688,
|
|
"num_tokens": 4254670.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.94252290725708,
|
|
"epoch": 0.1944604731679169,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999291912453637,
|
|
"loss": 6.9721,
|
|
"mean_token_accuracy": 0.14320756793022155,
|
|
"num_tokens": 4267561.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.993172025680542,
|
|
"epoch": 0.19503750721292556,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999281523012691,
|
|
"loss": 6.8919,
|
|
"mean_token_accuracy": 0.14741230085492135,
|
|
"num_tokens": 4280145.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.8782483577728275,
|
|
"epoch": 0.1956145412579342,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999271057918278,
|
|
"loss": 6.9383,
|
|
"mean_token_accuracy": 0.1460707038640976,
|
|
"num_tokens": 4294089.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.885042476654053,
|
|
"epoch": 0.19619157530294287,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999260517170751,
|
|
"loss": 6.8834,
|
|
"mean_token_accuracy": 0.14247703105211257,
|
|
"num_tokens": 4305926.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.926484394073486,
|
|
"epoch": 0.19676860934795154,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999249900770463,
|
|
"loss": 6.9204,
|
|
"mean_token_accuracy": 0.1449449948966503,
|
|
"num_tokens": 4319319.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.942605447769165,
|
|
"epoch": 0.19734564339296018,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999239208717772,
|
|
"loss": 6.9145,
|
|
"mean_token_accuracy": 0.14836193472146988,
|
|
"num_tokens": 4331650.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.88254075050354,
|
|
"epoch": 0.19792267743796885,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999228441013037,
|
|
"loss": 6.9039,
|
|
"mean_token_accuracy": 0.14810601770877838,
|
|
"num_tokens": 4344289.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.884267568588257,
|
|
"epoch": 0.1984997114829775,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499921759765662,
|
|
"loss": 6.8864,
|
|
"mean_token_accuracy": 0.14529623389244078,
|
|
"num_tokens": 4357316.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.860304594039917,
|
|
"epoch": 0.19907674552798615,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999206678648888,
|
|
"loss": 6.8982,
|
|
"mean_token_accuracy": 0.1503975972533226,
|
|
"num_tokens": 4369383.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.8668560028076175,
|
|
"epoch": 0.1996537795729948,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999195683990206,
|
|
"loss": 6.9096,
|
|
"mean_token_accuracy": 0.1409059315919876,
|
|
"num_tokens": 4383509.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.973160696029663,
|
|
"epoch": 0.20023081361800346,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999184613680945,
|
|
"loss": 6.8692,
|
|
"mean_token_accuracy": 0.14564202576875687,
|
|
"num_tokens": 4395105.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.832128429412842,
|
|
"epoch": 0.20080784766301213,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999173467721476,
|
|
"loss": 6.872,
|
|
"mean_token_accuracy": 0.15373900681734085,
|
|
"num_tokens": 4407473.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.00480284690857,
|
|
"epoch": 0.20138488170802077,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999162246112175,
|
|
"loss": 6.9639,
|
|
"mean_token_accuracy": 0.13571243211627007,
|
|
"num_tokens": 4420186.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.829422235488892,
|
|
"epoch": 0.20196191575302944,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999150948853419,
|
|
"loss": 6.8759,
|
|
"mean_token_accuracy": 0.14562891870737077,
|
|
"num_tokens": 4432944.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.9459367275238035,
|
|
"epoch": 0.20253894979803808,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999139575945587,
|
|
"loss": 6.9292,
|
|
"mean_token_accuracy": 0.14216466695070268,
|
|
"num_tokens": 4445784.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.793893766403198,
|
|
"epoch": 0.20311598384304674,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999128127389065,
|
|
"loss": 6.8261,
|
|
"mean_token_accuracy": 0.14876734018325805,
|
|
"num_tokens": 4458338.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.883917713165284,
|
|
"epoch": 0.20369301788805538,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999116603184233,
|
|
"loss": 6.8566,
|
|
"mean_token_accuracy": 0.14208449944853782,
|
|
"num_tokens": 4471058.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.897007083892822,
|
|
"epoch": 0.20427005193306405,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004999105003331482,
|
|
"loss": 6.8803,
|
|
"mean_token_accuracy": 0.14604100286960603,
|
|
"num_tokens": 4485561.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.783369731903076,
|
|
"epoch": 0.20484708597807272,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999093327831202,
|
|
"loss": 6.899,
|
|
"mean_token_accuracy": 0.14240699410438537,
|
|
"num_tokens": 4497865.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.795016145706176,
|
|
"epoch": 0.20542412002308136,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999081576683784,
|
|
"loss": 6.7786,
|
|
"mean_token_accuracy": 0.1580390974879265,
|
|
"num_tokens": 4510291.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.883041477203369,
|
|
"epoch": 0.20600115406809003,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999069749889626,
|
|
"loss": 6.857,
|
|
"mean_token_accuracy": 0.1457240477204323,
|
|
"num_tokens": 4521855.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.8854797840118405,
|
|
"epoch": 0.20657818811309867,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999057847449123,
|
|
"loss": 6.971,
|
|
"mean_token_accuracy": 0.14121209233999252,
|
|
"num_tokens": 4534123.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.984848356246948,
|
|
"epoch": 0.20715522215810733,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999045869362678,
|
|
"loss": 6.9267,
|
|
"mean_token_accuracy": 0.13553888350725174,
|
|
"num_tokens": 4547298.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.798803997039795,
|
|
"epoch": 0.20773225620311597,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499903381563069,
|
|
"loss": 6.8454,
|
|
"mean_token_accuracy": 0.14686679393053054,
|
|
"num_tokens": 4560945.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.964410018920899,
|
|
"epoch": 0.20830929024812464,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999021686253568,
|
|
"loss": 6.9114,
|
|
"mean_token_accuracy": 0.14516634494066238,
|
|
"num_tokens": 4572696.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.751922273635865,
|
|
"epoch": 0.2088863242931333,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999009481231719,
|
|
"loss": 6.8756,
|
|
"mean_token_accuracy": 0.14628861993551254,
|
|
"num_tokens": 4585670.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.973953628540039,
|
|
"epoch": 0.20946335833814195,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998997200565553,
|
|
"loss": 6.8579,
|
|
"mean_token_accuracy": 0.1476499393582344,
|
|
"num_tokens": 4597694.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.862924671173095,
|
|
"epoch": 0.21004039238315061,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998984844255483,
|
|
"loss": 6.8584,
|
|
"mean_token_accuracy": 0.145158788561821,
|
|
"num_tokens": 4609924.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.824046230316162,
|
|
"epoch": 0.21061742642815925,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998972412301925,
|
|
"loss": 6.8614,
|
|
"mean_token_accuracy": 0.14629337787628174,
|
|
"num_tokens": 4621668.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.91977014541626,
|
|
"epoch": 0.21119446047316792,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004998959904705297,
|
|
"loss": 6.925,
|
|
"mean_token_accuracy": 0.14481958076357843,
|
|
"num_tokens": 4635970.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.877291536331176,
|
|
"epoch": 0.21177149451817656,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998947321466021,
|
|
"loss": 6.9056,
|
|
"mean_token_accuracy": 0.14075979888439177,
|
|
"num_tokens": 4649557.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.868559741973877,
|
|
"epoch": 0.21234852856318523,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998934662584518,
|
|
"loss": 6.8864,
|
|
"mean_token_accuracy": 0.1476551428437233,
|
|
"num_tokens": 4662572.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.886713933944702,
|
|
"epoch": 0.2129255626081939,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998921928061214,
|
|
"loss": 6.8409,
|
|
"mean_token_accuracy": 0.13886594846844674,
|
|
"num_tokens": 4674783.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.78210129737854,
|
|
"epoch": 0.21350259665320254,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998909117896539,
|
|
"loss": 6.8551,
|
|
"mean_token_accuracy": 0.150478532910347,
|
|
"num_tokens": 4687543.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.975531578063965,
|
|
"epoch": 0.2140796306982112,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998896232090922,
|
|
"loss": 6.8099,
|
|
"mean_token_accuracy": 0.14673146605491638,
|
|
"num_tokens": 4700225.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.6987810134887695,
|
|
"epoch": 0.21465666474321984,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998883270644798,
|
|
"loss": 6.8708,
|
|
"mean_token_accuracy": 0.14261882826685907,
|
|
"num_tokens": 4712950.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.979980373382569,
|
|
"epoch": 0.2152336987882285,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998870233558602,
|
|
"loss": 6.9684,
|
|
"mean_token_accuracy": 0.14130085632205008,
|
|
"num_tokens": 4725563.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.872949504852295,
|
|
"epoch": 0.21581073283323715,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998857120832774,
|
|
"loss": 6.8768,
|
|
"mean_token_accuracy": 0.14834909737110138,
|
|
"num_tokens": 4739057.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.829817581176758,
|
|
"epoch": 0.21638776687824582,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998843932467751,
|
|
"loss": 6.8336,
|
|
"mean_token_accuracy": 0.15014879405498505,
|
|
"num_tokens": 4752782.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.834365272521973,
|
|
"epoch": 0.21696480092325446,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998830668463982,
|
|
"loss": 6.7885,
|
|
"mean_token_accuracy": 0.1466831497848034,
|
|
"num_tokens": 4765740.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.809153747558594,
|
|
"epoch": 0.21754183496826313,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998817328821909,
|
|
"loss": 6.8593,
|
|
"mean_token_accuracy": 0.1415070801973343,
|
|
"num_tokens": 4778711.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.89850492477417,
|
|
"epoch": 0.2181188690132718,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998803913541983,
|
|
"loss": 6.8493,
|
|
"mean_token_accuracy": 0.143658284842968,
|
|
"num_tokens": 4791402.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.818964958190918,
|
|
"epoch": 0.21869590305828043,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998790422624654,
|
|
"loss": 6.8456,
|
|
"mean_token_accuracy": 0.1407043866813183,
|
|
"num_tokens": 4804256.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.819336557388306,
|
|
"epoch": 0.2192729371032891,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998776856070376,
|
|
"loss": 6.789,
|
|
"mean_token_accuracy": 0.14376113265752793,
|
|
"num_tokens": 4817424.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.805288505554199,
|
|
"epoch": 0.21984997114829774,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998763213879606,
|
|
"loss": 6.8274,
|
|
"mean_token_accuracy": 0.1412200078368187,
|
|
"num_tokens": 4829222.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.7459861755371096,
|
|
"epoch": 0.2204270051933064,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998749496052803,
|
|
"loss": 6.8126,
|
|
"mean_token_accuracy": 0.14899692088365554,
|
|
"num_tokens": 4844011.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.881348991394043,
|
|
"epoch": 0.22100403923831505,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998735702590426,
|
|
"loss": 6.8511,
|
|
"mean_token_accuracy": 0.1448480397462845,
|
|
"num_tokens": 4857116.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.781710624694824,
|
|
"epoch": 0.22158107328332372,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998721833492942,
|
|
"loss": 6.7721,
|
|
"mean_token_accuracy": 0.15325645804405214,
|
|
"num_tokens": 4867680.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.845559120178223,
|
|
"epoch": 0.22215810732833238,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998707888760816,
|
|
"loss": 6.8473,
|
|
"mean_token_accuracy": 0.1444242402911186,
|
|
"num_tokens": 4880553.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.795937204360962,
|
|
"epoch": 0.22273514137334102,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998693868394516,
|
|
"loss": 6.8314,
|
|
"mean_token_accuracy": 0.14200094863772392,
|
|
"num_tokens": 4893706.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.812420654296875,
|
|
"epoch": 0.2233121754183497,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998679772394516,
|
|
"loss": 6.884,
|
|
"mean_token_accuracy": 0.14432224184274672,
|
|
"num_tokens": 4906016.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.793758773803711,
|
|
"epoch": 0.22388920946335833,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998665600761289,
|
|
"loss": 6.7693,
|
|
"mean_token_accuracy": 0.15037692189216614,
|
|
"num_tokens": 4918628.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.891831541061402,
|
|
"epoch": 0.224466243508367,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499865135349531,
|
|
"loss": 6.85,
|
|
"mean_token_accuracy": 0.1410201907157898,
|
|
"num_tokens": 4930525.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.862972545623779,
|
|
"epoch": 0.22504327755337564,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998637030597061,
|
|
"loss": 6.8579,
|
|
"mean_token_accuracy": 0.14448119103908538,
|
|
"num_tokens": 4942510.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.852001047134399,
|
|
"epoch": 0.2256203115983843,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998622632067022,
|
|
"loss": 6.8322,
|
|
"mean_token_accuracy": 0.142857813090086,
|
|
"num_tokens": 4954865.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.849268865585327,
|
|
"epoch": 0.22619734564339297,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998608157905678,
|
|
"loss": 6.9068,
|
|
"mean_token_accuracy": 0.13810089901089667,
|
|
"num_tokens": 4968078.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.828215026855469,
|
|
"epoch": 0.2267743796884016,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998593608113515,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.14653953462839125,
|
|
"num_tokens": 4980273.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.837485408782959,
|
|
"epoch": 0.22735141373341028,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998578982691024,
|
|
"loss": 6.8295,
|
|
"mean_token_accuracy": 0.1414664812386036,
|
|
"num_tokens": 4992372.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.791807365417481,
|
|
"epoch": 0.22792844777841892,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998564281638694,
|
|
"loss": 6.8131,
|
|
"mean_token_accuracy": 0.14089381247758864,
|
|
"num_tokens": 5004766.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.786174869537353,
|
|
"epoch": 0.2285054818234276,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998549504957023,
|
|
"loss": 6.7601,
|
|
"mean_token_accuracy": 0.14380791336297988,
|
|
"num_tokens": 5017007.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.821545076370239,
|
|
"epoch": 0.22908251586843623,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998534652646506,
|
|
"loss": 6.8221,
|
|
"mean_token_accuracy": 0.14419303238391876,
|
|
"num_tokens": 5029506.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.815482902526855,
|
|
"epoch": 0.2296595499134449,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998519724707642,
|
|
"loss": 6.8091,
|
|
"mean_token_accuracy": 0.1457746997475624,
|
|
"num_tokens": 5042209.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.8471766948699955,
|
|
"epoch": 0.23023658395845356,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998504721140934,
|
|
"loss": 6.8541,
|
|
"mean_token_accuracy": 0.1391491897404194,
|
|
"num_tokens": 5056026.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.837068510055542,
|
|
"epoch": 0.2308136180034622,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998489641946887,
|
|
"loss": 6.8116,
|
|
"mean_token_accuracy": 0.14428771734237672,
|
|
"num_tokens": 5068194.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.664884614944458,
|
|
"epoch": 0.23139065204847087,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998474487126009,
|
|
"loss": 6.7351,
|
|
"mean_token_accuracy": 0.1473590686917305,
|
|
"num_tokens": 5080468.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.884929609298706,
|
|
"epoch": 0.2319676860934795,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998459256678806,
|
|
"loss": 6.9369,
|
|
"mean_token_accuracy": 0.1359821602702141,
|
|
"num_tokens": 5093104.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.826117992401123,
|
|
"epoch": 0.23254472013848818,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998443950605796,
|
|
"loss": 6.7957,
|
|
"mean_token_accuracy": 0.14508781284093858,
|
|
"num_tokens": 5105710.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.905029249191284,
|
|
"epoch": 0.23312175418349682,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998428568907488,
|
|
"loss": 6.8745,
|
|
"mean_token_accuracy": 0.14229415580630303,
|
|
"num_tokens": 5118946.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.728935241699219,
|
|
"epoch": 0.23369878822850548,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998413111584403,
|
|
"loss": 6.7202,
|
|
"mean_token_accuracy": 0.15764200091362,
|
|
"num_tokens": 5132567.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.694896554946899,
|
|
"epoch": 0.23427582227351415,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998397578637059,
|
|
"loss": 6.7779,
|
|
"mean_token_accuracy": 0.15084137320518493,
|
|
"num_tokens": 5145669.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.758299112319946,
|
|
"epoch": 0.2348528563185228,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499838197006598,
|
|
"loss": 6.7169,
|
|
"mean_token_accuracy": 0.1479812353849411,
|
|
"num_tokens": 5157753.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.72536416053772,
|
|
"epoch": 0.23542989036353146,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499836628587169,
|
|
"loss": 6.738,
|
|
"mean_token_accuracy": 0.1493836060166359,
|
|
"num_tokens": 5170167.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.763384819030762,
|
|
"epoch": 0.2360069244085401,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998350526054716,
|
|
"loss": 6.7365,
|
|
"mean_token_accuracy": 0.14397142082452774,
|
|
"num_tokens": 5182143.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.825057792663574,
|
|
"epoch": 0.23658395845354876,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998334690615591,
|
|
"loss": 6.7837,
|
|
"mean_token_accuracy": 0.1431373730301857,
|
|
"num_tokens": 5195586.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.68499903678894,
|
|
"epoch": 0.2371609924985574,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998318779554844,
|
|
"loss": 6.7554,
|
|
"mean_token_accuracy": 0.14732947051525117,
|
|
"num_tokens": 5207774.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.71256422996521,
|
|
"epoch": 0.23773802654356607,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998302792873012,
|
|
"loss": 6.7794,
|
|
"mean_token_accuracy": 0.14680352061986923,
|
|
"num_tokens": 5219330.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.830109930038452,
|
|
"epoch": 0.23831506058857474,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998286730570631,
|
|
"loss": 6.8465,
|
|
"mean_token_accuracy": 0.1373237304389477,
|
|
"num_tokens": 5233817.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.789051580429077,
|
|
"epoch": 0.23889209463358338,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998270592648245,
|
|
"loss": 6.8371,
|
|
"mean_token_accuracy": 0.14460220336914062,
|
|
"num_tokens": 5246483.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.836073017120361,
|
|
"epoch": 0.23946912867859205,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998254379106394,
|
|
"loss": 6.829,
|
|
"mean_token_accuracy": 0.14329571947455405,
|
|
"num_tokens": 5258695.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.749055814743042,
|
|
"epoch": 0.2400461627236007,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998238089945622,
|
|
"loss": 6.7726,
|
|
"mean_token_accuracy": 0.14508575648069383,
|
|
"num_tokens": 5271355.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.937589025497436,
|
|
"epoch": 0.24062319676860935,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998221725166479,
|
|
"loss": 6.8964,
|
|
"mean_token_accuracy": 0.1389458566904068,
|
|
"num_tokens": 5284905.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.719331741333008,
|
|
"epoch": 0.241200230813618,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998205284769516,
|
|
"loss": 6.8109,
|
|
"mean_token_accuracy": 0.14349860548973084,
|
|
"num_tokens": 5298266.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.828605842590332,
|
|
"epoch": 0.24177726485862666,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998188768755285,
|
|
"loss": 6.8694,
|
|
"mean_token_accuracy": 0.1355933129787445,
|
|
"num_tokens": 5311148.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.83973069190979,
|
|
"epoch": 0.2423542989036353,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998172177124341,
|
|
"loss": 6.7748,
|
|
"mean_token_accuracy": 0.14382925629615784,
|
|
"num_tokens": 5322638.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.663211250305176,
|
|
"epoch": 0.24293133294864397,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998155509877242,
|
|
"loss": 6.6548,
|
|
"mean_token_accuracy": 0.15735870003700256,
|
|
"num_tokens": 5336116.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.7159160614013675,
|
|
"epoch": 0.24350836699365264,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499813876701455,
|
|
"loss": 6.7707,
|
|
"mean_token_accuracy": 0.14908685460686683,
|
|
"num_tokens": 5347561.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.844922876358032,
|
|
"epoch": 0.24408540103866128,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998121948536828,
|
|
"loss": 6.8154,
|
|
"mean_token_accuracy": 0.14128955006599425,
|
|
"num_tokens": 5360055.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.773591470718384,
|
|
"epoch": 0.24466243508366994,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998105054444639,
|
|
"loss": 6.7771,
|
|
"mean_token_accuracy": 0.15177889317274093,
|
|
"num_tokens": 5372722.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.782438707351685,
|
|
"epoch": 0.24523946912867858,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998088084738555,
|
|
"loss": 6.7404,
|
|
"mean_token_accuracy": 0.14531630873680115,
|
|
"num_tokens": 5385586.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.681029987335205,
|
|
"epoch": 0.24581650317368725,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998071039419144,
|
|
"loss": 6.7641,
|
|
"mean_token_accuracy": 0.14682294577360153,
|
|
"num_tokens": 5399266.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.774657392501831,
|
|
"epoch": 0.2463935372186959,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499805391848698,
|
|
"loss": 6.7644,
|
|
"mean_token_accuracy": 0.14703176617622377,
|
|
"num_tokens": 5412093.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.70880913734436,
|
|
"epoch": 0.24697057126370456,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499803672194264,
|
|
"loss": 6.7833,
|
|
"mean_token_accuracy": 0.1430216610431671,
|
|
"num_tokens": 5425181.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.749992370605469,
|
|
"epoch": 0.24754760530871323,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998019449786701,
|
|
"loss": 6.6795,
|
|
"mean_token_accuracy": 0.15330939292907714,
|
|
"num_tokens": 5437392.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.751720428466797,
|
|
"epoch": 0.24812463935372187,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998002102019744,
|
|
"loss": 6.7483,
|
|
"mean_token_accuracy": 0.15037278309464455,
|
|
"num_tokens": 5449455.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.753234720230102,
|
|
"epoch": 0.24870167339873053,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997984678642354,
|
|
"loss": 6.7739,
|
|
"mean_token_accuracy": 0.14836794808506965,
|
|
"num_tokens": 5463095.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.702136754989624,
|
|
"epoch": 0.24927870744373917,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997967179655115,
|
|
"loss": 6.7224,
|
|
"mean_token_accuracy": 0.15014025568962097,
|
|
"num_tokens": 5474440.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.758479595184326,
|
|
"epoch": 0.24985574148874784,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997949605058617,
|
|
"loss": 6.7367,
|
|
"mean_token_accuracy": 0.15418562889099122,
|
|
"num_tokens": 5487365.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.72683892250061,
|
|
"epoch": 0.2504327755337565,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997931954853451,
|
|
"loss": 6.8064,
|
|
"mean_token_accuracy": 0.14088582396507263,
|
|
"num_tokens": 5502356.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.764380550384521,
|
|
"epoch": 0.2510098095787651,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499791422904021,
|
|
"loss": 6.8133,
|
|
"mean_token_accuracy": 0.14515454694628716,
|
|
"num_tokens": 5514504.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.811923265457153,
|
|
"epoch": 0.2515868436237738,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997896427619491,
|
|
"loss": 6.8184,
|
|
"mean_token_accuracy": 0.14146610125899314,
|
|
"num_tokens": 5526415.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.721636390686035,
|
|
"epoch": 0.25216387766878245,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997878550591892,
|
|
"loss": 6.6809,
|
|
"mean_token_accuracy": 0.14960418790578842,
|
|
"num_tokens": 5538484.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.822943162918091,
|
|
"epoch": 0.2527409117137911,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997860597958013,
|
|
"loss": 6.7458,
|
|
"mean_token_accuracy": 0.15074630677700043,
|
|
"num_tokens": 5551315.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.600991916656494,
|
|
"epoch": 0.2533179457587998,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997842569718461,
|
|
"loss": 6.6448,
|
|
"mean_token_accuracy": 0.14987451508641242,
|
|
"num_tokens": 5564179.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.7274760723114015,
|
|
"epoch": 0.25389497980380843,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499782446587384,
|
|
"loss": 6.7716,
|
|
"mean_token_accuracy": 0.13751927390694618,
|
|
"num_tokens": 5577060.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.6231166362762455,
|
|
"epoch": 0.25447201384881707,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499780628642476,
|
|
"loss": 6.5854,
|
|
"mean_token_accuracy": 0.16829559057950974,
|
|
"num_tokens": 5589170.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.710141897201538,
|
|
"epoch": 0.2550490478938257,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997788031371834,
|
|
"loss": 6.7737,
|
|
"mean_token_accuracy": 0.14554792270064354,
|
|
"num_tokens": 5601747.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.7795628070831295,
|
|
"epoch": 0.2556260819388344,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997769700715672,
|
|
"loss": 6.7876,
|
|
"mean_token_accuracy": 0.13844683319330214,
|
|
"num_tokens": 5614308.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.6915586471557615,
|
|
"epoch": 0.25620311598384304,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997751294456892,
|
|
"loss": 6.7544,
|
|
"mean_token_accuracy": 0.14007925242185593,
|
|
"num_tokens": 5626351.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.810964775085449,
|
|
"epoch": 0.2567801500288517,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997732812596114,
|
|
"loss": 6.7285,
|
|
"mean_token_accuracy": 0.15032831579446793,
|
|
"num_tokens": 5638339.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.73750147819519,
|
|
"epoch": 0.2573571840738604,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997714255133961,
|
|
"loss": 6.7858,
|
|
"mean_token_accuracy": 0.14408532232046128,
|
|
"num_tokens": 5651210.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.72407546043396,
|
|
"epoch": 0.257934218118869,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997695622071054,
|
|
"loss": 6.7764,
|
|
"mean_token_accuracy": 0.148297780752182,
|
|
"num_tokens": 5664150.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.773475217819214,
|
|
"epoch": 0.25851125216387766,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997676913408021,
|
|
"loss": 6.6947,
|
|
"mean_token_accuracy": 0.15271911919116973,
|
|
"num_tokens": 5676009.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.8198034286499025,
|
|
"epoch": 0.2590882862088863,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997658129145493,
|
|
"loss": 6.8775,
|
|
"mean_token_accuracy": 0.14045544862747192,
|
|
"num_tokens": 5688557.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.7614494323730465,
|
|
"epoch": 0.259665320253895,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997639269284099,
|
|
"loss": 6.8247,
|
|
"mean_token_accuracy": 0.14492859840393066,
|
|
"num_tokens": 5702032.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.77425799369812,
|
|
"epoch": 0.26024235429890363,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997620333824476,
|
|
"loss": 6.6499,
|
|
"mean_token_accuracy": 0.1555098697543144,
|
|
"num_tokens": 5714623.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.668704319000244,
|
|
"epoch": 0.2608193883439123,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997601322767258,
|
|
"loss": 6.6668,
|
|
"mean_token_accuracy": 0.1488153889775276,
|
|
"num_tokens": 5727415.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.739748096466064,
|
|
"epoch": 0.26139642238892097,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997582236113087,
|
|
"loss": 6.7189,
|
|
"mean_token_accuracy": 0.14608575105667115,
|
|
"num_tokens": 5740129.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.70829586982727,
|
|
"epoch": 0.2619734564339296,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997563073862603,
|
|
"loss": 6.6847,
|
|
"mean_token_accuracy": 0.15272213518619537,
|
|
"num_tokens": 5752469.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.702632331848145,
|
|
"epoch": 0.26255049047893825,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997543836016453,
|
|
"loss": 6.782,
|
|
"mean_token_accuracy": 0.15359314829111098,
|
|
"num_tokens": 5765408.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.852825546264649,
|
|
"epoch": 0.2631275245239469,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997524522575281,
|
|
"loss": 6.712,
|
|
"mean_token_accuracy": 0.14011794328689575,
|
|
"num_tokens": 5777450.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.71787576675415,
|
|
"epoch": 0.2637045585689556,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997505133539738,
|
|
"loss": 6.7499,
|
|
"mean_token_accuracy": 0.14179244339466096,
|
|
"num_tokens": 5790435.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.795726108551025,
|
|
"epoch": 0.2642815926139642,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997485668910476,
|
|
"loss": 6.7392,
|
|
"mean_token_accuracy": 0.14688139259815217,
|
|
"num_tokens": 5803517.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.632097005844116,
|
|
"epoch": 0.26485862665897286,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997466128688151,
|
|
"loss": 6.6931,
|
|
"mean_token_accuracy": 0.1566813513636589,
|
|
"num_tokens": 5815802.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.698785448074341,
|
|
"epoch": 0.26543566070398156,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499744651287342,
|
|
"loss": 6.72,
|
|
"mean_token_accuracy": 0.14845843315124513,
|
|
"num_tokens": 5827807.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.728725481033325,
|
|
"epoch": 0.2660126947489902,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499742682146694,
|
|
"loss": 6.7315,
|
|
"mean_token_accuracy": 0.1497019961476326,
|
|
"num_tokens": 5840759.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.780129289627075,
|
|
"epoch": 0.26658972879399884,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997407054469377,
|
|
"loss": 6.7611,
|
|
"mean_token_accuracy": 0.14581131488084792,
|
|
"num_tokens": 5853117.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.565095138549805,
|
|
"epoch": 0.2671667628390075,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997387211881392,
|
|
"loss": 6.6753,
|
|
"mean_token_accuracy": 0.1566202774643898,
|
|
"num_tokens": 5866717.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.743575382232666,
|
|
"epoch": 0.26774379688401617,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997367293703656,
|
|
"loss": 6.7424,
|
|
"mean_token_accuracy": 0.14907404631376267,
|
|
"num_tokens": 5879017.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.713337516784668,
|
|
"epoch": 0.2683208309290248,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997347299936837,
|
|
"loss": 6.7133,
|
|
"mean_token_accuracy": 0.14949267506599426,
|
|
"num_tokens": 5891481.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.698743152618408,
|
|
"epoch": 0.26889786497403345,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997327230581608,
|
|
"loss": 6.7359,
|
|
"mean_token_accuracy": 0.14829655289649962,
|
|
"num_tokens": 5903389.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.676599073410034,
|
|
"epoch": 0.26947489901904215,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997307085638644,
|
|
"loss": 6.629,
|
|
"mean_token_accuracy": 0.14779743552207947,
|
|
"num_tokens": 5916084.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.671857261657715,
|
|
"epoch": 0.2700519330640508,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997286865108621,
|
|
"loss": 6.6841,
|
|
"mean_token_accuracy": 0.15207995921373368,
|
|
"num_tokens": 5927797.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.579140996932983,
|
|
"epoch": 0.2706289671090594,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997266568992222,
|
|
"loss": 6.609,
|
|
"mean_token_accuracy": 0.15099724531173705,
|
|
"num_tokens": 5941886.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.694521522521972,
|
|
"epoch": 0.27120600115406807,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997246197290128,
|
|
"loss": 6.7122,
|
|
"mean_token_accuracy": 0.15124790519475936,
|
|
"num_tokens": 5953655.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.872830104827881,
|
|
"epoch": 0.27178303519907676,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997225750003024,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.14656617790460585,
|
|
"num_tokens": 5967818.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.621160650253296,
|
|
"epoch": 0.2723600692440854,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997205227131599,
|
|
"loss": 6.6683,
|
|
"mean_token_accuracy": 0.15280671566724777,
|
|
"num_tokens": 5980742.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.720431566238403,
|
|
"epoch": 0.27293710328909404,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997184628676542,
|
|
"loss": 6.6961,
|
|
"mean_token_accuracy": 0.14359625577926635,
|
|
"num_tokens": 5993263.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.768740940093994,
|
|
"epoch": 0.27351413733410274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997163954638546,
|
|
"loss": 6.7821,
|
|
"mean_token_accuracy": 0.13767419382929802,
|
|
"num_tokens": 6007820.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.749808263778687,
|
|
"epoch": 0.2740911713791114,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997143205018306,
|
|
"loss": 6.7393,
|
|
"mean_token_accuracy": 0.14474162012338637,
|
|
"num_tokens": 6020665.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.737027406692505,
|
|
"epoch": 0.27466820542412,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997122379816523,
|
|
"loss": 6.6633,
|
|
"mean_token_accuracy": 0.15110542327165605,
|
|
"num_tokens": 6032847.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.652834367752075,
|
|
"epoch": 0.27524523946912866,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997101479033893,
|
|
"loss": 6.7217,
|
|
"mean_token_accuracy": 0.14369864910840988,
|
|
"num_tokens": 6045291.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.695873260498047,
|
|
"epoch": 0.27582227351413735,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997080502671122,
|
|
"loss": 6.6998,
|
|
"mean_token_accuracy": 0.1474764734506607,
|
|
"num_tokens": 6057872.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.653308582305908,
|
|
"epoch": 0.276399307559146,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997059450728913,
|
|
"loss": 6.6736,
|
|
"mean_token_accuracy": 0.1510896533727646,
|
|
"num_tokens": 6070252.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.759108924865723,
|
|
"epoch": 0.27697634160415463,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997038323207977,
|
|
"loss": 6.7658,
|
|
"mean_token_accuracy": 0.14066046848893166,
|
|
"num_tokens": 6083728.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.719287300109864,
|
|
"epoch": 0.2775533756491633,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997017120109022,
|
|
"loss": 6.7103,
|
|
"mean_token_accuracy": 0.14144404977560043,
|
|
"num_tokens": 6097140.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.596685552597046,
|
|
"epoch": 0.27813040969417197,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996995841432762,
|
|
"loss": 6.6862,
|
|
"mean_token_accuracy": 0.14334119111299515,
|
|
"num_tokens": 6109518.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.788815879821778,
|
|
"epoch": 0.2787074437391806,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996974487179915,
|
|
"loss": 6.6762,
|
|
"mean_token_accuracy": 0.1471431717276573,
|
|
"num_tokens": 6122160.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.597071027755737,
|
|
"epoch": 0.27928447778418924,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996953057351195,
|
|
"loss": 6.7212,
|
|
"mean_token_accuracy": 0.1476117990911007,
|
|
"num_tokens": 6134638.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.760407972335815,
|
|
"epoch": 0.27986151182919794,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996931551947327,
|
|
"loss": 6.7589,
|
|
"mean_token_accuracy": 0.14486420899629593,
|
|
"num_tokens": 6147142.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.794008064270019,
|
|
"epoch": 0.2804385458742066,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996909970969031,
|
|
"loss": 6.744,
|
|
"mean_token_accuracy": 0.1503509297966957,
|
|
"num_tokens": 6159137.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.6532281875610355,
|
|
"epoch": 0.2810155799192152,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996888314417034,
|
|
"loss": 6.7328,
|
|
"mean_token_accuracy": 0.14441587403416634,
|
|
"num_tokens": 6171663.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.826012897491455,
|
|
"epoch": 0.2815926139642239,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996866582292067,
|
|
"loss": 6.7408,
|
|
"mean_token_accuracy": 0.14965420067310334,
|
|
"num_tokens": 6184282.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.679483222961426,
|
|
"epoch": 0.28216964800923255,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996844774594856,
|
|
"loss": 6.7343,
|
|
"mean_token_accuracy": 0.14577517807483673,
|
|
"num_tokens": 6197243.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.663284683227539,
|
|
"epoch": 0.2827466820542412,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996822891326138,
|
|
"loss": 6.6567,
|
|
"mean_token_accuracy": 0.1508615292608738,
|
|
"num_tokens": 6209061.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.653768301010132,
|
|
"epoch": 0.28332371609924983,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996800932486648,
|
|
"loss": 6.6216,
|
|
"mean_token_accuracy": 0.15076174587011337,
|
|
"num_tokens": 6223497.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.671743392944336,
|
|
"epoch": 0.28390075014425853,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996778898077126,
|
|
"loss": 6.6509,
|
|
"mean_token_accuracy": 0.15512303858995438,
|
|
"num_tokens": 6236395.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.668979549407959,
|
|
"epoch": 0.28447778418926717,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996756788098309,
|
|
"loss": 6.6199,
|
|
"mean_token_accuracy": 0.15135869532823562,
|
|
"num_tokens": 6248700.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.690337991714477,
|
|
"epoch": 0.2850548182342758,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996734602550945,
|
|
"loss": 6.6867,
|
|
"mean_token_accuracy": 0.14691711217164993,
|
|
"num_tokens": 6262728.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.60182819366455,
|
|
"epoch": 0.2856318522792845,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996712341435779,
|
|
"loss": 6.6504,
|
|
"mean_token_accuracy": 0.14799974262714385,
|
|
"num_tokens": 6276007.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.800230884552002,
|
|
"epoch": 0.28620888632429314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996690004753559,
|
|
"loss": 6.7706,
|
|
"mean_token_accuracy": 0.14552113711833953,
|
|
"num_tokens": 6289033.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.621489667892456,
|
|
"epoch": 0.2867859203693018,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996667592505037,
|
|
"loss": 6.7187,
|
|
"mean_token_accuracy": 0.139874604344368,
|
|
"num_tokens": 6300994.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.712352705001831,
|
|
"epoch": 0.2873629544143104,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996645104690967,
|
|
"loss": 6.6761,
|
|
"mean_token_accuracy": 0.14659769386053084,
|
|
"num_tokens": 6313447.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.69777102470398,
|
|
"epoch": 0.2879399884593191,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996622541312103,
|
|
"loss": 6.6714,
|
|
"mean_token_accuracy": 0.1478801764547825,
|
|
"num_tokens": 6326622.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.648268127441407,
|
|
"epoch": 0.28851702250432776,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996599902369207,
|
|
"loss": 6.6896,
|
|
"mean_token_accuracy": 0.14757568538188934,
|
|
"num_tokens": 6339286.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.6651811599731445,
|
|
"epoch": 0.2890940565493364,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996577187863039,
|
|
"loss": 6.6847,
|
|
"mean_token_accuracy": 0.14420827105641365,
|
|
"num_tokens": 6351869.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.638708543777466,
|
|
"epoch": 0.2896710905943451,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996554397794364,
|
|
"loss": 6.6235,
|
|
"mean_token_accuracy": 0.15295252203941345,
|
|
"num_tokens": 6363974.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.6614098072052,
|
|
"epoch": 0.29024812463935373,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996531532163947,
|
|
"loss": 6.6232,
|
|
"mean_token_accuracy": 0.15056563541293144,
|
|
"num_tokens": 6376569.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.636733722686768,
|
|
"epoch": 0.2908251586843624,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996508590972558,
|
|
"loss": 6.6341,
|
|
"mean_token_accuracy": 0.1568033814430237,
|
|
"num_tokens": 6388830.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.627635335922241,
|
|
"epoch": 0.291402192729371,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996485574220969,
|
|
"loss": 6.6377,
|
|
"mean_token_accuracy": 0.1470814898610115,
|
|
"num_tokens": 6401542.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.600588321685791,
|
|
"epoch": 0.2919792267743797,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996462481909953,
|
|
"loss": 6.6167,
|
|
"mean_token_accuracy": 0.15283410847187043,
|
|
"num_tokens": 6414123.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.704501485824585,
|
|
"epoch": 0.29255626081938835,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996439314040287,
|
|
"loss": 6.6938,
|
|
"mean_token_accuracy": 0.14676552414894103,
|
|
"num_tokens": 6427269.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.631581497192383,
|
|
"epoch": 0.293133294864397,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499641607061275,
|
|
"loss": 6.7408,
|
|
"mean_token_accuracy": 0.14724025428295134,
|
|
"num_tokens": 6442296.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.733328866958618,
|
|
"epoch": 0.2937103289094057,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996392751628126,
|
|
"loss": 6.7476,
|
|
"mean_token_accuracy": 0.14128965958952905,
|
|
"num_tokens": 6456954.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.6841991424560545,
|
|
"epoch": 0.2942873629544143,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996369357087196,
|
|
"loss": 6.7437,
|
|
"mean_token_accuracy": 0.14420021548867226,
|
|
"num_tokens": 6470139.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.810974264144898,
|
|
"epoch": 0.29486439699942296,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499634588699075,
|
|
"loss": 6.6532,
|
|
"mean_token_accuracy": 0.15219533294439316,
|
|
"num_tokens": 6483106.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.595229625701904,
|
|
"epoch": 0.2954414310444316,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996322341339575,
|
|
"loss": 6.6908,
|
|
"mean_token_accuracy": 0.1466153398156166,
|
|
"num_tokens": 6495921.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.637534332275391,
|
|
"epoch": 0.2960184650894403,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996298720134465,
|
|
"loss": 6.5823,
|
|
"mean_token_accuracy": 0.1488182932138443,
|
|
"num_tokens": 6508408.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.580471229553223,
|
|
"epoch": 0.29659549913444894,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996275023376213,
|
|
"loss": 6.6766,
|
|
"mean_token_accuracy": 0.1433579817414284,
|
|
"num_tokens": 6522081.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.743631982803345,
|
|
"epoch": 0.2971725331794576,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996251251065615,
|
|
"loss": 6.6524,
|
|
"mean_token_accuracy": 0.14642552882432938,
|
|
"num_tokens": 6535065.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.65220079421997,
|
|
"epoch": 0.2977495672244662,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996227403203473,
|
|
"loss": 6.6288,
|
|
"mean_token_accuracy": 0.15091437101364136,
|
|
"num_tokens": 6547972.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.619907283782959,
|
|
"epoch": 0.2983266012694749,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004996203479790589,
|
|
"loss": 6.5948,
|
|
"mean_token_accuracy": 0.1509481832385063,
|
|
"num_tokens": 6559935.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.593966054916382,
|
|
"epoch": 0.29890363531448355,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996179480827764,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.15155731663107871,
|
|
"num_tokens": 6572373.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.682660484313965,
|
|
"epoch": 0.2994806693594922,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499615540631581,
|
|
"loss": 6.677,
|
|
"mean_token_accuracy": 0.14595670402050018,
|
|
"num_tokens": 6585846.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.691784238815307,
|
|
"epoch": 0.3000577034045009,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996131256255534,
|
|
"loss": 6.7495,
|
|
"mean_token_accuracy": 0.14251318722963333,
|
|
"num_tokens": 6600387.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.625003719329834,
|
|
"epoch": 0.3006347374495095,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996107030647749,
|
|
"loss": 6.667,
|
|
"mean_token_accuracy": 0.14578246474266052,
|
|
"num_tokens": 6613142.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.596926593780518,
|
|
"epoch": 0.30121177149451817,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996082729493269,
|
|
"loss": 6.5739,
|
|
"mean_token_accuracy": 0.15168050229549407,
|
|
"num_tokens": 6626273.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.659254646301269,
|
|
"epoch": 0.3017888055395268,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004996058352792913,
|
|
"loss": 6.6539,
|
|
"mean_token_accuracy": 0.14640988335013388,
|
|
"num_tokens": 6639831.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.739427900314331,
|
|
"epoch": 0.3023658395845355,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049960339005475,
|
|
"loss": 6.7259,
|
|
"mean_token_accuracy": 0.1433930814266205,
|
|
"num_tokens": 6652776.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.713594102859497,
|
|
"epoch": 0.30294287362954414,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996009372757852,
|
|
"loss": 6.6827,
|
|
"mean_token_accuracy": 0.14745238050818443,
|
|
"num_tokens": 6665465.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.552315902709961,
|
|
"epoch": 0.3035199076745528,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995984769424795,
|
|
"loss": 6.5667,
|
|
"mean_token_accuracy": 0.1607323855161667,
|
|
"num_tokens": 6677472.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.593226766586303,
|
|
"epoch": 0.3040969417195615,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995960090549155,
|
|
"loss": 6.5878,
|
|
"mean_token_accuracy": 0.1506764367222786,
|
|
"num_tokens": 6689145.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.589013576507568,
|
|
"epoch": 0.3046739757645701,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995935336131764,
|
|
"loss": 6.5832,
|
|
"mean_token_accuracy": 0.15121154189109803,
|
|
"num_tokens": 6701520.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.666328239440918,
|
|
"epoch": 0.30525100980957875,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995910506173452,
|
|
"loss": 6.6851,
|
|
"mean_token_accuracy": 0.14975427985191345,
|
|
"num_tokens": 6715615.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.676078271865845,
|
|
"epoch": 0.3058280438545874,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995885600675059,
|
|
"loss": 6.6783,
|
|
"mean_token_accuracy": 0.14618042930960656,
|
|
"num_tokens": 6728772.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.670553731918335,
|
|
"epoch": 0.3064050778995961,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995860619637415,
|
|
"loss": 6.637,
|
|
"mean_token_accuracy": 0.14901359081268312,
|
|
"num_tokens": 6741454.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.599151611328125,
|
|
"epoch": 0.30698211194460473,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995835563061367,
|
|
"loss": 6.6555,
|
|
"mean_token_accuracy": 0.1510484904050827,
|
|
"num_tokens": 6753983.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.74462776184082,
|
|
"epoch": 0.30755914598961337,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995810430947756,
|
|
"loss": 6.699,
|
|
"mean_token_accuracy": 0.1489512011408806,
|
|
"num_tokens": 6767377.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.649488878250122,
|
|
"epoch": 0.30813618003462206,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995785223297426,
|
|
"loss": 6.6467,
|
|
"mean_token_accuracy": 0.15547565817832948,
|
|
"num_tokens": 6779220.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.671740865707397,
|
|
"epoch": 0.3087132140796307,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995759940111225,
|
|
"loss": 6.626,
|
|
"mean_token_accuracy": 0.15176912397146225,
|
|
"num_tokens": 6792202.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.538708877563477,
|
|
"epoch": 0.30929024812463934,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995734581390005,
|
|
"loss": 6.623,
|
|
"mean_token_accuracy": 0.15197737216949464,
|
|
"num_tokens": 6804988.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.68460521697998,
|
|
"epoch": 0.309867282169648,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995709147134617,
|
|
"loss": 6.6537,
|
|
"mean_token_accuracy": 0.1486986458301544,
|
|
"num_tokens": 6817311.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.667502927780151,
|
|
"epoch": 0.3104443162146567,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995683637345919,
|
|
"loss": 6.6367,
|
|
"mean_token_accuracy": 0.14956765994429588,
|
|
"num_tokens": 6829875.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.645153999328613,
|
|
"epoch": 0.3110213502596653,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004995658052024765,
|
|
"loss": 6.6112,
|
|
"mean_token_accuracy": 0.155751770734787,
|
|
"num_tokens": 6843080.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.594676733016968,
|
|
"epoch": 0.31159838430467396,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995632391172019,
|
|
"loss": 6.5964,
|
|
"mean_token_accuracy": 0.15243575125932693,
|
|
"num_tokens": 6857202.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.682533931732178,
|
|
"epoch": 0.31217541834968265,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995606654788543,
|
|
"loss": 6.7016,
|
|
"mean_token_accuracy": 0.1450270637869835,
|
|
"num_tokens": 6870801.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.654961776733399,
|
|
"epoch": 0.3127524523946913,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995580842875202,
|
|
"loss": 6.6479,
|
|
"mean_token_accuracy": 0.1479589194059372,
|
|
"num_tokens": 6883084.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.708399629592895,
|
|
"epoch": 0.31332948643969993,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995554955432866,
|
|
"loss": 6.6756,
|
|
"mean_token_accuracy": 0.1470663696527481,
|
|
"num_tokens": 6895309.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.572336673736572,
|
|
"epoch": 0.3139065204847086,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995528992462404,
|
|
"loss": 6.6248,
|
|
"mean_token_accuracy": 0.15860298946499823,
|
|
"num_tokens": 6907646.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.6901154041290285,
|
|
"epoch": 0.31448355452971727,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499550295396469,
|
|
"loss": 6.6142,
|
|
"mean_token_accuracy": 0.15778794139623642,
|
|
"num_tokens": 6919769.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.4766926765441895,
|
|
"epoch": 0.3150605885747259,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995476839940598,
|
|
"loss": 6.6201,
|
|
"mean_token_accuracy": 0.15026881247758866,
|
|
"num_tokens": 6933348.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.714725732803345,
|
|
"epoch": 0.31563762261973455,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499545065039101,
|
|
"loss": 6.6743,
|
|
"mean_token_accuracy": 0.14582089185714722,
|
|
"num_tokens": 6945105.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.545088768005371,
|
|
"epoch": 0.31621465666474324,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995424385316803,
|
|
"loss": 6.6618,
|
|
"mean_token_accuracy": 0.1445609971880913,
|
|
"num_tokens": 6958009.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.6502604484558105,
|
|
"epoch": 0.3167916907097519,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995398044718863,
|
|
"loss": 6.5485,
|
|
"mean_token_accuracy": 0.15240858346223832,
|
|
"num_tokens": 6970156.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.583297348022461,
|
|
"epoch": 0.3173687247547605,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995371628598074,
|
|
"loss": 6.6473,
|
|
"mean_token_accuracy": 0.151313416659832,
|
|
"num_tokens": 6983431.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.705528640747071,
|
|
"epoch": 0.31794575879976916,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995345136955328,
|
|
"loss": 6.6931,
|
|
"mean_token_accuracy": 0.14359337761998175,
|
|
"num_tokens": 6997470.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.686682987213135,
|
|
"epoch": 0.31852279284477786,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995318569791512,
|
|
"loss": 6.6505,
|
|
"mean_token_accuracy": 0.15525564998388292,
|
|
"num_tokens": 7010337.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.64365782737732,
|
|
"epoch": 0.3190998268897865,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995291927107522,
|
|
"loss": 6.6628,
|
|
"mean_token_accuracy": 0.14557797089219093,
|
|
"num_tokens": 7023950.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.638036775588989,
|
|
"epoch": 0.31967686093479514,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995265208904252,
|
|
"loss": 6.622,
|
|
"mean_token_accuracy": 0.15690350979566575,
|
|
"num_tokens": 7036409.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.616341543197632,
|
|
"epoch": 0.32025389497980383,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995238415182603,
|
|
"loss": 6.6326,
|
|
"mean_token_accuracy": 0.14718683063983917,
|
|
"num_tokens": 7049409.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.688148880004883,
|
|
"epoch": 0.3208309290248125,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995211545943476,
|
|
"loss": 6.6907,
|
|
"mean_token_accuracy": 0.14982038736343384,
|
|
"num_tokens": 7062120.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.680778884887696,
|
|
"epoch": 0.3214079630698211,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995184601187772,
|
|
"loss": 6.668,
|
|
"mean_token_accuracy": 0.14194481670856476,
|
|
"num_tokens": 7073150.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.626657867431641,
|
|
"epoch": 0.32198499711482975,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049951575809164,
|
|
"loss": 6.6001,
|
|
"mean_token_accuracy": 0.142817410081625,
|
|
"num_tokens": 7085927.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.64122838973999,
|
|
"epoch": 0.32256203115983845,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995130485130269,
|
|
"loss": 6.6837,
|
|
"mean_token_accuracy": 0.14988088607788086,
|
|
"num_tokens": 7097607.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.641415691375732,
|
|
"epoch": 0.3231390652048471,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995103313830289,
|
|
"loss": 6.5998,
|
|
"mean_token_accuracy": 0.15160279124975204,
|
|
"num_tokens": 7109771.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.694540548324585,
|
|
"epoch": 0.3237160992498557,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995076067017373,
|
|
"loss": 6.6737,
|
|
"mean_token_accuracy": 0.14511681348085403,
|
|
"num_tokens": 7122757.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.624036026000977,
|
|
"epoch": 0.3242931332948644,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995048744692439,
|
|
"loss": 6.6436,
|
|
"mean_token_accuracy": 0.1493765577673912,
|
|
"num_tokens": 7135516.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.639794206619262,
|
|
"epoch": 0.32487016733987306,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995021346856405,
|
|
"loss": 6.7264,
|
|
"mean_token_accuracy": 0.14374846667051316,
|
|
"num_tokens": 7149125.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.706334114074707,
|
|
"epoch": 0.3254472013848817,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994993873510196,
|
|
"loss": 6.6653,
|
|
"mean_token_accuracy": 0.14253946542739868,
|
|
"num_tokens": 7160723.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.645235395431518,
|
|
"epoch": 0.32602423542989034,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994966324654731,
|
|
"loss": 6.6433,
|
|
"mean_token_accuracy": 0.144842017441988,
|
|
"num_tokens": 7174551.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.650976371765137,
|
|
"epoch": 0.32660126947489904,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499493870029094,
|
|
"loss": 6.6189,
|
|
"mean_token_accuracy": 0.14779492169618608,
|
|
"num_tokens": 7186764.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.611865520477295,
|
|
"epoch": 0.3271783035199077,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994911000419749,
|
|
"loss": 6.6143,
|
|
"mean_token_accuracy": 0.15066873282194138,
|
|
"num_tokens": 7199645.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.6020160675048825,
|
|
"epoch": 0.3277553375649163,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994883225042093,
|
|
"loss": 6.54,
|
|
"mean_token_accuracy": 0.1572998732328415,
|
|
"num_tokens": 7212579.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.586337566375732,
|
|
"epoch": 0.328332371609925,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994855374158905,
|
|
"loss": 6.571,
|
|
"mean_token_accuracy": 0.15372254252433776,
|
|
"num_tokens": 7225139.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.710922813415527,
|
|
"epoch": 0.32890940565493365,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499482744777112,
|
|
"loss": 6.7311,
|
|
"mean_token_accuracy": 0.14069035798311233,
|
|
"num_tokens": 7239220.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.675474834442139,
|
|
"epoch": 0.3294864396999423,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499479944587968,
|
|
"loss": 6.7533,
|
|
"mean_token_accuracy": 0.1474220335483551,
|
|
"num_tokens": 7252613.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.580682802200317,
|
|
"epoch": 0.33006347374495093,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994771368485526,
|
|
"loss": 6.5772,
|
|
"mean_token_accuracy": 0.15456188917160035,
|
|
"num_tokens": 7263658.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.643721866607666,
|
|
"epoch": 0.3306405077899596,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994743215589602,
|
|
"loss": 6.6064,
|
|
"mean_token_accuracy": 0.1567901760339737,
|
|
"num_tokens": 7275782.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.544418811798096,
|
|
"epoch": 0.33121754183496827,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994714987192854,
|
|
"loss": 6.6359,
|
|
"mean_token_accuracy": 0.15609208047389983,
|
|
"num_tokens": 7288536.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.609630966186524,
|
|
"epoch": 0.3317945758799769,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994686683296234,
|
|
"loss": 6.6019,
|
|
"mean_token_accuracy": 0.15594898611307145,
|
|
"num_tokens": 7300480.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.634557008743286,
|
|
"epoch": 0.3323716099249856,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994658303900691,
|
|
"loss": 6.6475,
|
|
"mean_token_accuracy": 0.15181711912155152,
|
|
"num_tokens": 7313168.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.5809680938720705,
|
|
"epoch": 0.33294864396999424,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994629849007182,
|
|
"loss": 6.6147,
|
|
"mean_token_accuracy": 0.15636203438043594,
|
|
"num_tokens": 7327347.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.733543872833252,
|
|
"epoch": 0.3335256780150029,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994601318616663,
|
|
"loss": 6.6466,
|
|
"mean_token_accuracy": 0.1510158471763134,
|
|
"num_tokens": 7339955.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.584178400039673,
|
|
"epoch": 0.3341027120600115,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994572712730092,
|
|
"loss": 6.6188,
|
|
"mean_token_accuracy": 0.14996251463890076,
|
|
"num_tokens": 7353586.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.593496084213257,
|
|
"epoch": 0.3346797461050202,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994544031348434,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.14958511143922806,
|
|
"num_tokens": 7365802.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.634331750869751,
|
|
"epoch": 0.33525678015002885,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994515274472653,
|
|
"loss": 6.5569,
|
|
"mean_token_accuracy": 0.14671666771173478,
|
|
"num_tokens": 7377864.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.52061505317688,
|
|
"epoch": 0.3358338141950375,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994486442103715,
|
|
"loss": 6.5051,
|
|
"mean_token_accuracy": 0.1553037017583847,
|
|
"num_tokens": 7389921.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.606663084030151,
|
|
"epoch": 0.3364108482400462,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499445753424259,
|
|
"loss": 6.585,
|
|
"mean_token_accuracy": 0.14963840320706367,
|
|
"num_tokens": 7402765.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.612658452987671,
|
|
"epoch": 0.33698788228505483,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994428550890251,
|
|
"loss": 6.588,
|
|
"mean_token_accuracy": 0.14756084382534027,
|
|
"num_tokens": 7416330.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.546629619598389,
|
|
"epoch": 0.33756491633006347,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994399492047672,
|
|
"loss": 6.5569,
|
|
"mean_token_accuracy": 0.1625090643763542,
|
|
"num_tokens": 7428701.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.616139030456543,
|
|
"epoch": 0.3381419503750721,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994370357715832,
|
|
"loss": 6.5609,
|
|
"mean_token_accuracy": 0.1539958417415619,
|
|
"num_tokens": 7440687.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.554273843765259,
|
|
"epoch": 0.3387189844200808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499434114789571,
|
|
"loss": 6.65,
|
|
"mean_token_accuracy": 0.14359127953648568,
|
|
"num_tokens": 7454448.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.695260524749756,
|
|
"epoch": 0.33929601846508944,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994311862588286,
|
|
"loss": 6.5699,
|
|
"mean_token_accuracy": 0.15439818054437637,
|
|
"num_tokens": 7466722.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.530065727233887,
|
|
"epoch": 0.3398730525100981,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994282501794551,
|
|
"loss": 6.5843,
|
|
"mean_token_accuracy": 0.15763369649648667,
|
|
"num_tokens": 7478574.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.518723726272583,
|
|
"epoch": 0.3404500865551068,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994253065515486,
|
|
"loss": 6.4807,
|
|
"mean_token_accuracy": 0.15764836221933365,
|
|
"num_tokens": 7490424.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.633134555816651,
|
|
"epoch": 0.3410271206001154,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994223553752084,
|
|
"loss": 6.6256,
|
|
"mean_token_accuracy": 0.15402503609657286,
|
|
"num_tokens": 7502832.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.511202335357666,
|
|
"epoch": 0.34160415464512406,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994193966505339,
|
|
"loss": 6.5529,
|
|
"mean_token_accuracy": 0.15395866483449935,
|
|
"num_tokens": 7514151.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.612486219406128,
|
|
"epoch": 0.3421811886901327,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994164303776244,
|
|
"loss": 6.5929,
|
|
"mean_token_accuracy": 0.1546282023191452,
|
|
"num_tokens": 7526877.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.601590824127197,
|
|
"epoch": 0.3427582227351414,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994134565565797,
|
|
"loss": 6.556,
|
|
"mean_token_accuracy": 0.15401398837566377,
|
|
"num_tokens": 7538858.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.674258995056152,
|
|
"epoch": 0.34333525678015003,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994104751875,
|
|
"loss": 6.5985,
|
|
"mean_token_accuracy": 0.15456424802541732,
|
|
"num_tokens": 7550804.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.490966129302978,
|
|
"epoch": 0.3439122908251587,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994074862704854,
|
|
"loss": 6.5304,
|
|
"mean_token_accuracy": 0.15696495920419692,
|
|
"num_tokens": 7562269.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.60324239730835,
|
|
"epoch": 0.3444893248701673,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994044898056363,
|
|
"loss": 6.6167,
|
|
"mean_token_accuracy": 0.14663480520248412,
|
|
"num_tokens": 7573695.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.655906391143799,
|
|
"epoch": 0.345066358915176,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994014857930538,
|
|
"loss": 6.6318,
|
|
"mean_token_accuracy": 0.15162624269723893,
|
|
"num_tokens": 7585943.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.56010856628418,
|
|
"epoch": 0.34564339296018465,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993984742328387,
|
|
"loss": 6.6145,
|
|
"mean_token_accuracy": 0.1463395446538925,
|
|
"num_tokens": 7598326.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.628453969955444,
|
|
"epoch": 0.3462204270051933,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993954551250925,
|
|
"loss": 6.6109,
|
|
"mean_token_accuracy": 0.14573243409395217,
|
|
"num_tokens": 7609950.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3462204270051933,
|
|
"eval_entropy": 6.495445118866964,
|
|
"eval_loss": 6.647010326385498,
|
|
"eval_mean_token_accuracy": 0.15230962459314673,
|
|
"eval_num_tokens": 7609950.0,
|
|
"eval_runtime": 22.9056,
|
|
"eval_samples_per_second": 1228.347,
|
|
"eval_steps_per_second": 153.543,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 86650,
|
|
"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": 1.126483024896e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|