9201ce1da6
Model: fpadovani/nld-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.27213352685050796,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.294069576263428,
|
|
"epoch": 0.00045355587808418,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.8082,
|
|
"mean_token_accuracy": 0.10324694961309433,
|
|
"num_tokens": 10827.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.281773281097412,
|
|
"epoch": 0.00090711175616836,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.82,
|
|
"mean_token_accuracy": 0.09896889626979828,
|
|
"num_tokens": 21025.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.273117637634277,
|
|
"epoch": 0.00136066763425254,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.7665,
|
|
"mean_token_accuracy": 0.10093757957220077,
|
|
"num_tokens": 31678.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.247605180740356,
|
|
"epoch": 0.00181422351233672,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.7109,
|
|
"mean_token_accuracy": 0.11424258798360824,
|
|
"num_tokens": 41025.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.302770519256592,
|
|
"epoch": 0.0022677793904208998,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.8182,
|
|
"mean_token_accuracy": 0.10542535930871963,
|
|
"num_tokens": 51270.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.143268346786499,
|
|
"epoch": 0.00272133526850508,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.7184,
|
|
"mean_token_accuracy": 0.09942657127976418,
|
|
"num_tokens": 62142.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.138898038864136,
|
|
"epoch": 0.00317489114658926,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.8522,
|
|
"mean_token_accuracy": 0.1027273491024971,
|
|
"num_tokens": 72709.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.083880186080933,
|
|
"epoch": 0.00362844702467344,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.691,
|
|
"mean_token_accuracy": 0.1096431165933609,
|
|
"num_tokens": 82313.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.065870761871338,
|
|
"epoch": 0.00408200290275762,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.709,
|
|
"mean_token_accuracy": 0.11063554510474205,
|
|
"num_tokens": 92450.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.089556646347046,
|
|
"epoch": 0.0045355587808417995,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.7247,
|
|
"mean_token_accuracy": 0.09662125557661057,
|
|
"num_tokens": 103978.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.111036014556885,
|
|
"epoch": 0.00498911465892598,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.6995,
|
|
"mean_token_accuracy": 0.11020737215876579,
|
|
"num_tokens": 114134.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.1653160572052,
|
|
"epoch": 0.00544267053701016,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.8947,
|
|
"mean_token_accuracy": 0.09984557479619979,
|
|
"num_tokens": 125037.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.146482801437378,
|
|
"epoch": 0.00589622641509434,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.7116,
|
|
"mean_token_accuracy": 0.11133431643247604,
|
|
"num_tokens": 134721.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.114493370056152,
|
|
"epoch": 0.00634978229317852,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.6489,
|
|
"mean_token_accuracy": 0.10958910807967186,
|
|
"num_tokens": 144448.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.126422929763794,
|
|
"epoch": 0.006803338171262699,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.7058,
|
|
"mean_token_accuracy": 0.10741295143961907,
|
|
"num_tokens": 154343.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.110815334320068,
|
|
"epoch": 0.00725689404934688,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.7713,
|
|
"mean_token_accuracy": 0.10833674892783166,
|
|
"num_tokens": 165650.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.209178161621094,
|
|
"epoch": 0.007710449927431059,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.9573,
|
|
"mean_token_accuracy": 0.10000077486038209,
|
|
"num_tokens": 177098.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.122071313858032,
|
|
"epoch": 0.00816400580551524,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.6834,
|
|
"mean_token_accuracy": 0.11381161436438561,
|
|
"num_tokens": 187903.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.1197929859161375,
|
|
"epoch": 0.00861756168359942,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.7278,
|
|
"mean_token_accuracy": 0.10795715600252151,
|
|
"num_tokens": 198077.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.142152261734009,
|
|
"epoch": 0.009071117561683599,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.8489,
|
|
"mean_token_accuracy": 0.10571764856576919,
|
|
"num_tokens": 208641.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.104328584671021,
|
|
"epoch": 0.009524673439767779,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.114326973259449,
|
|
"num_tokens": 218398.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.09408917427063,
|
|
"epoch": 0.00997822931785196,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.6445,
|
|
"mean_token_accuracy": 0.10643699690699578,
|
|
"num_tokens": 229059.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.079065132141113,
|
|
"epoch": 0.01043178519593614,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.7188,
|
|
"mean_token_accuracy": 0.10808592811226844,
|
|
"num_tokens": 239775.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.048356246948242,
|
|
"epoch": 0.01088534107402032,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.604,
|
|
"mean_token_accuracy": 0.10746061727404595,
|
|
"num_tokens": 249954.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.094142627716065,
|
|
"epoch": 0.011338896952104499,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.7139,
|
|
"mean_token_accuracy": 0.1050918959081173,
|
|
"num_tokens": 260056.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.079626655578613,
|
|
"epoch": 0.01179245283018868,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.6984,
|
|
"mean_token_accuracy": 0.1138601079583168,
|
|
"num_tokens": 269904.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.136023092269897,
|
|
"epoch": 0.01224600870827286,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.6975,
|
|
"mean_token_accuracy": 0.10696214884519577,
|
|
"num_tokens": 280900.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.108730602264404,
|
|
"epoch": 0.01269956458635704,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.7283,
|
|
"mean_token_accuracy": 0.1071628138422966,
|
|
"num_tokens": 290844.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.061822891235352,
|
|
"epoch": 0.013153120464441219,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.7121,
|
|
"mean_token_accuracy": 0.10810653567314148,
|
|
"num_tokens": 301345.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.080287647247315,
|
|
"epoch": 0.013606676342525399,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.7084,
|
|
"mean_token_accuracy": 0.10700314119458199,
|
|
"num_tokens": 312681.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.125663185119629,
|
|
"epoch": 0.01406023222060958,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.6748,
|
|
"mean_token_accuracy": 0.10948033705353737,
|
|
"num_tokens": 323492.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.086132001876831,
|
|
"epoch": 0.01451378809869376,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.7303,
|
|
"mean_token_accuracy": 0.10884013846516609,
|
|
"num_tokens": 334521.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.097598886489868,
|
|
"epoch": 0.014967343976777939,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.7547,
|
|
"mean_token_accuracy": 0.11234977021813393,
|
|
"num_tokens": 345468.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.158268976211548,
|
|
"epoch": 0.015420899854862119,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.6848,
|
|
"mean_token_accuracy": 0.11324930489063263,
|
|
"num_tokens": 355911.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.074994707107544,
|
|
"epoch": 0.0158744557329463,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.7033,
|
|
"mean_token_accuracy": 0.10836530178785324,
|
|
"num_tokens": 367537.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.234744691848755,
|
|
"epoch": 0.01632801161103048,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.8874,
|
|
"mean_token_accuracy": 0.10362846553325653,
|
|
"num_tokens": 377918.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.165385055541992,
|
|
"epoch": 0.01678156748911466,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.7471,
|
|
"mean_token_accuracy": 0.10905997231602668,
|
|
"num_tokens": 388461.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.085760498046875,
|
|
"epoch": 0.01723512336719884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.7294,
|
|
"mean_token_accuracy": 0.1090123176574707,
|
|
"num_tokens": 399771.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.09751558303833,
|
|
"epoch": 0.01768867924528302,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.6457,
|
|
"mean_token_accuracy": 0.11132576763629913,
|
|
"num_tokens": 410254.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.104769086837768,
|
|
"epoch": 0.018142235123367198,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.6448,
|
|
"mean_token_accuracy": 0.10658138245344162,
|
|
"num_tokens": 419792.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.064562034606934,
|
|
"epoch": 0.018595791001451378,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.6915,
|
|
"mean_token_accuracy": 0.11256536692380906,
|
|
"num_tokens": 429264.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.033247804641723,
|
|
"epoch": 0.019049346879535557,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.6445,
|
|
"mean_token_accuracy": 0.11356118023395538,
|
|
"num_tokens": 439624.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.0533287525177,
|
|
"epoch": 0.01950290275761974,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.6641,
|
|
"mean_token_accuracy": 0.10742003992199897,
|
|
"num_tokens": 449556.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.127027368545532,
|
|
"epoch": 0.01995645863570392,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.6976,
|
|
"mean_token_accuracy": 0.1103837251663208,
|
|
"num_tokens": 460243.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.084058809280395,
|
|
"epoch": 0.0204100145137881,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.7234,
|
|
"mean_token_accuracy": 0.10724443346261978,
|
|
"num_tokens": 469767.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.108950233459472,
|
|
"epoch": 0.02086357039187228,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.6963,
|
|
"mean_token_accuracy": 0.1088191345334053,
|
|
"num_tokens": 480329.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.037991762161255,
|
|
"epoch": 0.02131712626995646,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.6476,
|
|
"mean_token_accuracy": 0.10804546251893044,
|
|
"num_tokens": 490096.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.215046215057373,
|
|
"epoch": 0.02177068214804064,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.6471,
|
|
"mean_token_accuracy": 0.10496766492724419,
|
|
"num_tokens": 501231.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.999786281585694,
|
|
"epoch": 0.022224238026124818,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.6219,
|
|
"mean_token_accuracy": 0.11307241767644882,
|
|
"num_tokens": 510722.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.085280036926269,
|
|
"epoch": 0.022677793904208998,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.6711,
|
|
"mean_token_accuracy": 0.10972743034362793,
|
|
"num_tokens": 521452.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.075028562545777,
|
|
"epoch": 0.023131349782293177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.6852,
|
|
"mean_token_accuracy": 0.10879904478788376,
|
|
"num_tokens": 532397.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.080456399917603,
|
|
"epoch": 0.02358490566037736,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.6625,
|
|
"mean_token_accuracy": 0.10898046344518661,
|
|
"num_tokens": 542271.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.04259991645813,
|
|
"epoch": 0.02403846153846154,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.6673,
|
|
"mean_token_accuracy": 0.11369868144392967,
|
|
"num_tokens": 552411.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.1117438793182375,
|
|
"epoch": 0.02449201741654572,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.6571,
|
|
"mean_token_accuracy": 0.11307868435978889,
|
|
"num_tokens": 561518.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.074210357666016,
|
|
"epoch": 0.0249455732946299,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.7211,
|
|
"mean_token_accuracy": 0.11085665598511696,
|
|
"num_tokens": 571361.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.007254123687744,
|
|
"epoch": 0.02539912917271408,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.615,
|
|
"mean_token_accuracy": 0.11170280948281289,
|
|
"num_tokens": 580926.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.089535856246949,
|
|
"epoch": 0.025852685050798258,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.7083,
|
|
"mean_token_accuracy": 0.10579465702176094,
|
|
"num_tokens": 592282.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.124145221710205,
|
|
"epoch": 0.026306240928882438,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.7235,
|
|
"mean_token_accuracy": 0.10901360288262367,
|
|
"num_tokens": 602767.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.125961971282959,
|
|
"epoch": 0.026759796806966617,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.6398,
|
|
"mean_token_accuracy": 0.11005486473441124,
|
|
"num_tokens": 612763.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.99384126663208,
|
|
"epoch": 0.027213352685050797,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.6203,
|
|
"mean_token_accuracy": 0.11310217007994652,
|
|
"num_tokens": 622796.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.990754795074463,
|
|
"epoch": 0.027666908563134977,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.5983,
|
|
"mean_token_accuracy": 0.1153037615120411,
|
|
"num_tokens": 633136.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.018349838256836,
|
|
"epoch": 0.02812046444121916,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.6196,
|
|
"mean_token_accuracy": 0.11451629996299743,
|
|
"num_tokens": 643347.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.088607692718506,
|
|
"epoch": 0.02857402031930334,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.6067,
|
|
"mean_token_accuracy": 0.1193146750330925,
|
|
"num_tokens": 653096.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.883705759048462,
|
|
"epoch": 0.02902757619738752,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.6439,
|
|
"mean_token_accuracy": 0.1120058111846447,
|
|
"num_tokens": 663557.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.102012681961059,
|
|
"epoch": 0.0294811320754717,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.7247,
|
|
"mean_token_accuracy": 0.1098653145134449,
|
|
"num_tokens": 674395.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.06192626953125,
|
|
"epoch": 0.029934687953555878,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.6559,
|
|
"mean_token_accuracy": 0.1131248153746128,
|
|
"num_tokens": 684776.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.036684370040893,
|
|
"epoch": 0.030388243831640058,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.6097,
|
|
"mean_token_accuracy": 0.11125744804739952,
|
|
"num_tokens": 694886.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.014414644241333,
|
|
"epoch": 0.030841799709724237,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.6881,
|
|
"mean_token_accuracy": 0.11227559223771096,
|
|
"num_tokens": 705426.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.103907060623169,
|
|
"epoch": 0.03129535558780842,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.10788564383983612,
|
|
"num_tokens": 716271.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.0990581035614015,
|
|
"epoch": 0.0317489114658926,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.672,
|
|
"mean_token_accuracy": 0.1117681197822094,
|
|
"num_tokens": 726875.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.9609973430633545,
|
|
"epoch": 0.032202467343976776,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.6149,
|
|
"mean_token_accuracy": 0.11049453616142273,
|
|
"num_tokens": 737825.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.027775573730469,
|
|
"epoch": 0.03265602322206096,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.5764,
|
|
"mean_token_accuracy": 0.11501729264855384,
|
|
"num_tokens": 747424.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.032524490356446,
|
|
"epoch": 0.033109579100145135,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.6177,
|
|
"mean_token_accuracy": 0.11091509833931923,
|
|
"num_tokens": 757649.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.0149918556213375,
|
|
"epoch": 0.03356313497822932,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.6171,
|
|
"mean_token_accuracy": 0.11376268118619919,
|
|
"num_tokens": 768556.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.010801887512207,
|
|
"epoch": 0.034016690856313495,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.607,
|
|
"mean_token_accuracy": 0.1097978562116623,
|
|
"num_tokens": 778331.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.967943716049194,
|
|
"epoch": 0.03447024673439768,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.6039,
|
|
"mean_token_accuracy": 0.1124206118285656,
|
|
"num_tokens": 788065.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.05260066986084,
|
|
"epoch": 0.03492380261248186,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.6727,
|
|
"mean_token_accuracy": 0.11531179398298264,
|
|
"num_tokens": 798912.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.010505723953247,
|
|
"epoch": 0.03537735849056604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.5932,
|
|
"mean_token_accuracy": 0.11802476570010186,
|
|
"num_tokens": 809580.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.041739130020142,
|
|
"epoch": 0.03583091436865022,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.698,
|
|
"mean_token_accuracy": 0.11100108623504638,
|
|
"num_tokens": 820207.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.895339822769165,
|
|
"epoch": 0.036284470246734396,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.5155,
|
|
"mean_token_accuracy": 0.11325377970933914,
|
|
"num_tokens": 831038.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.01606822013855,
|
|
"epoch": 0.03673802612481858,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.619,
|
|
"mean_token_accuracy": 0.11496082544326783,
|
|
"num_tokens": 842144.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.006781196594238,
|
|
"epoch": 0.037191582002902755,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.6274,
|
|
"mean_token_accuracy": 0.11621586382389068,
|
|
"num_tokens": 851315.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.954495906829834,
|
|
"epoch": 0.03764513788098694,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.6407,
|
|
"mean_token_accuracy": 0.11225903108716011,
|
|
"num_tokens": 861233.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.989374589920044,
|
|
"epoch": 0.038098693759071114,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.6035,
|
|
"mean_token_accuracy": 0.11319806352257729,
|
|
"num_tokens": 871131.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.961730718612671,
|
|
"epoch": 0.0385522496371553,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6019,
|
|
"mean_token_accuracy": 0.10756484866142273,
|
|
"num_tokens": 882195.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.033092260360718,
|
|
"epoch": 0.03900580551523948,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.5797,
|
|
"mean_token_accuracy": 0.11503332033753395,
|
|
"num_tokens": 891806.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.988789701461792,
|
|
"epoch": 0.03945936139332366,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.6323,
|
|
"mean_token_accuracy": 0.10891624465584755,
|
|
"num_tokens": 901350.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.0045853614807125,
|
|
"epoch": 0.03991291727140784,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.5539,
|
|
"mean_token_accuracy": 0.11177553907036782,
|
|
"num_tokens": 912061.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.900162267684936,
|
|
"epoch": 0.040366473149492016,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.5201,
|
|
"mean_token_accuracy": 0.11248114556074143,
|
|
"num_tokens": 922220.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.956882047653198,
|
|
"epoch": 0.0408200290275762,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.5593,
|
|
"mean_token_accuracy": 0.11303049996495247,
|
|
"num_tokens": 932319.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.911965465545654,
|
|
"epoch": 0.041273584905660375,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.58,
|
|
"mean_token_accuracy": 0.11454110518097878,
|
|
"num_tokens": 943254.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.996125650405884,
|
|
"epoch": 0.04172714078374456,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.6029,
|
|
"mean_token_accuracy": 0.10846876502037048,
|
|
"num_tokens": 953921.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.936468839645386,
|
|
"epoch": 0.042180696661828734,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.526,
|
|
"mean_token_accuracy": 0.11692283749580383,
|
|
"num_tokens": 963832.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.945839929580688,
|
|
"epoch": 0.04263425253991292,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.6208,
|
|
"mean_token_accuracy": 0.10841431692242623,
|
|
"num_tokens": 974066.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.90062198638916,
|
|
"epoch": 0.0430878084179971,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.616,
|
|
"mean_token_accuracy": 0.11435005068778992,
|
|
"num_tokens": 984402.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.956665706634522,
|
|
"epoch": 0.04354136429608128,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.5122,
|
|
"mean_token_accuracy": 0.11360828503966332,
|
|
"num_tokens": 993555.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.95721468925476,
|
|
"epoch": 0.04399492017416546,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.5271,
|
|
"mean_token_accuracy": 0.12218032553791999,
|
|
"num_tokens": 1002920.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.885728740692139,
|
|
"epoch": 0.044448476052249636,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.608,
|
|
"mean_token_accuracy": 0.10632575079798698,
|
|
"num_tokens": 1013611.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.892173099517822,
|
|
"epoch": 0.04490203193033382,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.4836,
|
|
"mean_token_accuracy": 0.11247801780700684,
|
|
"num_tokens": 1024121.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.059810018539428,
|
|
"epoch": 0.045355587808417995,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7215,
|
|
"mean_token_accuracy": 0.1127111479640007,
|
|
"num_tokens": 1033845.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.917029905319214,
|
|
"epoch": 0.04580914368650218,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.5315,
|
|
"mean_token_accuracy": 0.11300075054168701,
|
|
"num_tokens": 1044642.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.874821615219116,
|
|
"epoch": 0.046262699564586354,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6032,
|
|
"mean_token_accuracy": 0.10996716171503067,
|
|
"num_tokens": 1054728.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.894815063476562,
|
|
"epoch": 0.04671625544267054,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.10969225391745567,
|
|
"num_tokens": 1065743.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.828075170516968,
|
|
"epoch": 0.04716981132075472,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.4864,
|
|
"mean_token_accuracy": 0.11496817469596862,
|
|
"num_tokens": 1076798.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.936053895950318,
|
|
"epoch": 0.047623367198838897,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6064,
|
|
"mean_token_accuracy": 0.11198530569672585,
|
|
"num_tokens": 1087445.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.88051404953003,
|
|
"epoch": 0.04807692307692308,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.5258,
|
|
"mean_token_accuracy": 0.11618097051978112,
|
|
"num_tokens": 1098379.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.968464517593384,
|
|
"epoch": 0.048530478955007256,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6118,
|
|
"mean_token_accuracy": 0.11241324171423912,
|
|
"num_tokens": 1108016.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.838916206359864,
|
|
"epoch": 0.04898403483309144,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.4859,
|
|
"mean_token_accuracy": 0.1130056694149971,
|
|
"num_tokens": 1117887.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.830152797698974,
|
|
"epoch": 0.049437590711175615,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.4995,
|
|
"mean_token_accuracy": 0.106851976364851,
|
|
"num_tokens": 1128497.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.847278594970703,
|
|
"epoch": 0.0498911465892598,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.11530316844582558,
|
|
"num_tokens": 1138168.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.883500242233277,
|
|
"epoch": 0.050344702467343974,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5128,
|
|
"mean_token_accuracy": 0.11332335695624352,
|
|
"num_tokens": 1148357.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.851631021499633,
|
|
"epoch": 0.05079825834542816,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5414,
|
|
"mean_token_accuracy": 0.11176767796278,
|
|
"num_tokens": 1159964.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.893160057067871,
|
|
"epoch": 0.05125181422351233,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5865,
|
|
"mean_token_accuracy": 0.11133491396903991,
|
|
"num_tokens": 1170683.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.922141647338867,
|
|
"epoch": 0.051705370101596516,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.552,
|
|
"mean_token_accuracy": 0.11003944724798202,
|
|
"num_tokens": 1181680.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.8009681224823,
|
|
"epoch": 0.0521589259796807,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.4299,
|
|
"mean_token_accuracy": 0.11521938815712929,
|
|
"num_tokens": 1191619.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.7351405143737795,
|
|
"epoch": 0.052612481857764876,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.4436,
|
|
"mean_token_accuracy": 0.1167814739048481,
|
|
"num_tokens": 1202264.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.800995492935181,
|
|
"epoch": 0.05306603773584906,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.4535,
|
|
"mean_token_accuracy": 0.11420593708753586,
|
|
"num_tokens": 1212119.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.896333932876587,
|
|
"epoch": 0.053519593613933235,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5814,
|
|
"mean_token_accuracy": 0.11330544948577881,
|
|
"num_tokens": 1222317.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.882574033737183,
|
|
"epoch": 0.05397314949201742,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5286,
|
|
"mean_token_accuracy": 0.11739532127976418,
|
|
"num_tokens": 1232914.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.691092920303345,
|
|
"epoch": 0.054426705370101594,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.3838,
|
|
"mean_token_accuracy": 0.11833471432328224,
|
|
"num_tokens": 1244214.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.853950929641724,
|
|
"epoch": 0.05488026124818578,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4824,
|
|
"mean_token_accuracy": 0.11780562847852707,
|
|
"num_tokens": 1254626.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.790469121932984,
|
|
"epoch": 0.05533381712626995,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5719,
|
|
"mean_token_accuracy": 0.11432634964585305,
|
|
"num_tokens": 1265461.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.8617181301116945,
|
|
"epoch": 0.055787373004354136,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.4572,
|
|
"mean_token_accuracy": 0.1158202901482582,
|
|
"num_tokens": 1275810.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.72202844619751,
|
|
"epoch": 0.05624092888243832,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4716,
|
|
"mean_token_accuracy": 0.1191383220255375,
|
|
"num_tokens": 1285170.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.832190465927124,
|
|
"epoch": 0.056694484760522496,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.4065,
|
|
"mean_token_accuracy": 0.11602196991443633,
|
|
"num_tokens": 1295460.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.798471832275391,
|
|
"epoch": 0.05714804063860668,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5401,
|
|
"mean_token_accuracy": 0.11370082646608352,
|
|
"num_tokens": 1306656.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.835934972763061,
|
|
"epoch": 0.057601596516690855,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5059,
|
|
"mean_token_accuracy": 0.11711395084857941,
|
|
"num_tokens": 1318019.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.653035640716553,
|
|
"epoch": 0.05805515239477504,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.4287,
|
|
"mean_token_accuracy": 0.11944135650992393,
|
|
"num_tokens": 1328120.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.86923885345459,
|
|
"epoch": 0.058508708272859214,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.527,
|
|
"mean_token_accuracy": 0.11324021890759468,
|
|
"num_tokens": 1338354.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.790145397186279,
|
|
"epoch": 0.0589622641509434,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4831,
|
|
"mean_token_accuracy": 0.11808143481612206,
|
|
"num_tokens": 1348666.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.80904107093811,
|
|
"epoch": 0.05941582002902757,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5404,
|
|
"mean_token_accuracy": 0.1175168700516224,
|
|
"num_tokens": 1359713.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.7852167129516605,
|
|
"epoch": 0.059869375907111756,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.12213529795408248,
|
|
"num_tokens": 1369507.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.834307098388672,
|
|
"epoch": 0.06032293178519594,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5583,
|
|
"mean_token_accuracy": 0.11135573908686638,
|
|
"num_tokens": 1380726.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.805551242828369,
|
|
"epoch": 0.060776487663280115,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4852,
|
|
"mean_token_accuracy": 0.11822790279984474,
|
|
"num_tokens": 1391423.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.7903587341308596,
|
|
"epoch": 0.0612300435413643,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4651,
|
|
"mean_token_accuracy": 0.1208954781293869,
|
|
"num_tokens": 1402492.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.778665447235108,
|
|
"epoch": 0.061683599419448475,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5073,
|
|
"mean_token_accuracy": 0.11749565601348877,
|
|
"num_tokens": 1412497.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.856817674636841,
|
|
"epoch": 0.06213715529753266,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4803,
|
|
"mean_token_accuracy": 0.1222834125161171,
|
|
"num_tokens": 1423214.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.691046953201294,
|
|
"epoch": 0.06259071117561683,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4779,
|
|
"mean_token_accuracy": 0.1166260376572609,
|
|
"num_tokens": 1434044.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.79459776878357,
|
|
"epoch": 0.06304426705370102,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4429,
|
|
"mean_token_accuracy": 0.11843409463763237,
|
|
"num_tokens": 1444387.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.704948234558105,
|
|
"epoch": 0.0634978229317852,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3861,
|
|
"mean_token_accuracy": 0.11568867340683937,
|
|
"num_tokens": 1455157.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.735180950164795,
|
|
"epoch": 0.06395137880986937,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.477,
|
|
"mean_token_accuracy": 0.12313677221536637,
|
|
"num_tokens": 1466145.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.7879307746887205,
|
|
"epoch": 0.06440493468795355,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4737,
|
|
"mean_token_accuracy": 0.1173794686794281,
|
|
"num_tokens": 1476713.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.802341651916504,
|
|
"epoch": 0.06485849056603774,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.482,
|
|
"mean_token_accuracy": 0.12098045200109482,
|
|
"num_tokens": 1486908.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.710763883590698,
|
|
"epoch": 0.06531204644412192,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4084,
|
|
"mean_token_accuracy": 0.1253804959356785,
|
|
"num_tokens": 1498185.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.715804719924927,
|
|
"epoch": 0.0657656023222061,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4454,
|
|
"mean_token_accuracy": 0.11805666983127594,
|
|
"num_tokens": 1508376.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.765777683258056,
|
|
"epoch": 0.06621915820029027,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5331,
|
|
"mean_token_accuracy": 0.11824854388833046,
|
|
"num_tokens": 1519953.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.677792072296143,
|
|
"epoch": 0.06667271407837445,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4204,
|
|
"mean_token_accuracy": 0.11954097524285316,
|
|
"num_tokens": 1529793.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.716114711761475,
|
|
"epoch": 0.06712626995645864,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4162,
|
|
"mean_token_accuracy": 0.12043775469064713,
|
|
"num_tokens": 1540859.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.67792387008667,
|
|
"epoch": 0.06757982583454282,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3369,
|
|
"mean_token_accuracy": 0.127581225335598,
|
|
"num_tokens": 1549783.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.635021018981933,
|
|
"epoch": 0.06803338171262699,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4073,
|
|
"mean_token_accuracy": 0.12199747264385223,
|
|
"num_tokens": 1560522.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.677228021621704,
|
|
"epoch": 0.06848693759071117,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3805,
|
|
"mean_token_accuracy": 0.12109958082437515,
|
|
"num_tokens": 1570668.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.705593681335449,
|
|
"epoch": 0.06894049346879536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4978,
|
|
"mean_token_accuracy": 0.1242837056517601,
|
|
"num_tokens": 1581523.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.739868640899658,
|
|
"epoch": 0.06939404934687954,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4013,
|
|
"mean_token_accuracy": 0.1199745386838913,
|
|
"num_tokens": 1591356.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.6305756092071535,
|
|
"epoch": 0.06984760522496372,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3821,
|
|
"mean_token_accuracy": 0.12265411987900735,
|
|
"num_tokens": 1601779.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.71905837059021,
|
|
"epoch": 0.07030116110304789,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3932,
|
|
"mean_token_accuracy": 0.12244714498519897,
|
|
"num_tokens": 1611995.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.672496271133423,
|
|
"epoch": 0.07075471698113207,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4211,
|
|
"mean_token_accuracy": 0.1178926706314087,
|
|
"num_tokens": 1621834.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.678148460388184,
|
|
"epoch": 0.07120827285921626,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4579,
|
|
"mean_token_accuracy": 0.11523651331663132,
|
|
"num_tokens": 1632881.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.615700531005859,
|
|
"epoch": 0.07166182873730044,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.4437,
|
|
"mean_token_accuracy": 0.11981857419013978,
|
|
"num_tokens": 1642870.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.719856405258179,
|
|
"epoch": 0.07211538461538461,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3202,
|
|
"mean_token_accuracy": 0.12486634775996208,
|
|
"num_tokens": 1653390.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.682466459274292,
|
|
"epoch": 0.07256894049346879,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.446,
|
|
"mean_token_accuracy": 0.12393867447972298,
|
|
"num_tokens": 1663382.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.698669910430908,
|
|
"epoch": 0.07302249637155298,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.449,
|
|
"mean_token_accuracy": 0.1184344507753849,
|
|
"num_tokens": 1673601.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.570560455322266,
|
|
"epoch": 0.07347605224963716,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3681,
|
|
"mean_token_accuracy": 0.126424128562212,
|
|
"num_tokens": 1683565.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.632832860946655,
|
|
"epoch": 0.07392960812772134,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.3367,
|
|
"mean_token_accuracy": 0.12308898121118546,
|
|
"num_tokens": 1693636.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.7626114845275875,
|
|
"epoch": 0.07438316400580551,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.4517,
|
|
"mean_token_accuracy": 0.11969177201390266,
|
|
"num_tokens": 1703415.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.699670362472534,
|
|
"epoch": 0.0748367198838897,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4305,
|
|
"mean_token_accuracy": 0.12528733313083648,
|
|
"num_tokens": 1713579.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.586101007461548,
|
|
"epoch": 0.07529027576197388,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4246,
|
|
"mean_token_accuracy": 0.11557562425732612,
|
|
"num_tokens": 1724583.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.649460124969482,
|
|
"epoch": 0.07574383164005806,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.349,
|
|
"mean_token_accuracy": 0.12887958213686942,
|
|
"num_tokens": 1735293.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.688171482086181,
|
|
"epoch": 0.07619738751814223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.366,
|
|
"mean_token_accuracy": 0.123409453779459,
|
|
"num_tokens": 1745623.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.583874368667603,
|
|
"epoch": 0.07665094339622641,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4085,
|
|
"mean_token_accuracy": 0.12038984745740891,
|
|
"num_tokens": 1755713.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.691501235961914,
|
|
"epoch": 0.0771044992743106,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.3932,
|
|
"mean_token_accuracy": 0.12171499505639076,
|
|
"num_tokens": 1765264.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.6751635551452635,
|
|
"epoch": 0.07755805515239478,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4043,
|
|
"mean_token_accuracy": 0.12203977331519127,
|
|
"num_tokens": 1775769.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.57877140045166,
|
|
"epoch": 0.07801161103047896,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3398,
|
|
"mean_token_accuracy": 0.12160504087805749,
|
|
"num_tokens": 1786245.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.531408166885376,
|
|
"epoch": 0.07846516690856313,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.3694,
|
|
"mean_token_accuracy": 0.1285658784210682,
|
|
"num_tokens": 1796040.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.592545700073242,
|
|
"epoch": 0.07891872278664731,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.12193747386336326,
|
|
"num_tokens": 1806007.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.7914567470550535,
|
|
"epoch": 0.0793722786647315,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4675,
|
|
"mean_token_accuracy": 0.11332392543554307,
|
|
"num_tokens": 1816935.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.508628511428833,
|
|
"epoch": 0.07982583454281568,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.1232911117374897,
|
|
"num_tokens": 1827419.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.673329305648804,
|
|
"epoch": 0.08027939042089985,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.4276,
|
|
"mean_token_accuracy": 0.11844546273350716,
|
|
"num_tokens": 1837933.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.630283260345459,
|
|
"epoch": 0.08073294629898403,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4793,
|
|
"mean_token_accuracy": 0.12463728785514831,
|
|
"num_tokens": 1848551.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.692006587982178,
|
|
"epoch": 0.08118650217706821,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.11869508177042007,
|
|
"num_tokens": 1858380.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.5042383670806885,
|
|
"epoch": 0.0816400580551524,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2822,
|
|
"mean_token_accuracy": 0.12670984119176865,
|
|
"num_tokens": 1868291.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.616396141052246,
|
|
"epoch": 0.08209361393323658,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.386,
|
|
"mean_token_accuracy": 0.12300045192241668,
|
|
"num_tokens": 1879219.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.637605619430542,
|
|
"epoch": 0.08254716981132075,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3695,
|
|
"mean_token_accuracy": 0.12218734100461007,
|
|
"num_tokens": 1889809.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.52483057975769,
|
|
"epoch": 0.08300072568940493,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3383,
|
|
"mean_token_accuracy": 0.12149963527917862,
|
|
"num_tokens": 1899986.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.640835094451904,
|
|
"epoch": 0.08345428156748912,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3212,
|
|
"mean_token_accuracy": 0.12286782488226891,
|
|
"num_tokens": 1909314.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.6047581195831295,
|
|
"epoch": 0.0839078374455733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.3726,
|
|
"mean_token_accuracy": 0.12332175076007842,
|
|
"num_tokens": 1918443.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.563626766204834,
|
|
"epoch": 0.08436139332365747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.316,
|
|
"mean_token_accuracy": 0.12443615049123764,
|
|
"num_tokens": 1928683.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.458373975753784,
|
|
"epoch": 0.08481494920174165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.233,
|
|
"mean_token_accuracy": 0.12297066450119018,
|
|
"num_tokens": 1938293.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.509970378875733,
|
|
"epoch": 0.08526850507982583,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.12207101732492447,
|
|
"num_tokens": 1948233.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.600475120544433,
|
|
"epoch": 0.08572206095791002,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.12516278997063637,
|
|
"num_tokens": 1958611.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.593886280059815,
|
|
"epoch": 0.0861756168359942,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.4088,
|
|
"mean_token_accuracy": 0.1253935366868973,
|
|
"num_tokens": 1968957.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.540861320495606,
|
|
"epoch": 0.08662917271407837,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2584,
|
|
"mean_token_accuracy": 0.12826553955674172,
|
|
"num_tokens": 1978503.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.460687065124512,
|
|
"epoch": 0.08708272859216255,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.12641479223966598,
|
|
"num_tokens": 1988458.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.554324579238892,
|
|
"epoch": 0.08753628447024674,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3931,
|
|
"mean_token_accuracy": 0.12135342583060264,
|
|
"num_tokens": 1999984.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.4496111392974855,
|
|
"epoch": 0.08798984034833092,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2431,
|
|
"mean_token_accuracy": 0.13175339475274087,
|
|
"num_tokens": 2010645.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.600621032714844,
|
|
"epoch": 0.08844339622641509,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.36,
|
|
"mean_token_accuracy": 0.12460424080491066,
|
|
"num_tokens": 2020196.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.53763222694397,
|
|
"epoch": 0.08889695210449927,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.12676869034767152,
|
|
"num_tokens": 2030101.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.473430156707764,
|
|
"epoch": 0.08935050798258345,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.1231530986726284,
|
|
"num_tokens": 2040454.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.448872709274292,
|
|
"epoch": 0.08980406386066764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.12086713090538978,
|
|
"num_tokens": 2050378.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.557286500930786,
|
|
"epoch": 0.09025761973875182,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.12634406611323357,
|
|
"num_tokens": 2060282.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.511825323104858,
|
|
"epoch": 0.09071117561683599,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3212,
|
|
"mean_token_accuracy": 0.12492988184094429,
|
|
"num_tokens": 2070563.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.540437269210815,
|
|
"epoch": 0.09116473149492017,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999985110217,
|
|
"loss": 6.3931,
|
|
"mean_token_accuracy": 0.12742957547307016,
|
|
"num_tokens": 2080153.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.470778942108154,
|
|
"epoch": 0.09161828737300436,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999999924620471,
|
|
"loss": 6.236,
|
|
"mean_token_accuracy": 0.12746582329273223,
|
|
"num_tokens": 2090590.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.5432836532592775,
|
|
"epoch": 0.09207184325108854,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999999817600155,
|
|
"loss": 6.318,
|
|
"mean_token_accuracy": 0.11900549307465554,
|
|
"num_tokens": 2101945.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.5527753829956055,
|
|
"epoch": 0.09252539912917271,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999664049268,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.12768215388059617,
|
|
"num_tokens": 2112514.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.417323160171509,
|
|
"epoch": 0.09297895500725689,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999463967816,
|
|
"loss": 6.2586,
|
|
"mean_token_accuracy": 0.12710441127419472,
|
|
"num_tokens": 2122296.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.639082574844361,
|
|
"epoch": 0.09343251088534107,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049999992173558,
|
|
"loss": 6.4053,
|
|
"mean_token_accuracy": 0.11305732280015945,
|
|
"num_tokens": 2134512.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.5072770595550535,
|
|
"epoch": 0.09388606676342526,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999998924213228,
|
|
"loss": 6.3261,
|
|
"mean_token_accuracy": 0.12832158356904982,
|
|
"num_tokens": 2143934.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.44057936668396,
|
|
"epoch": 0.09433962264150944,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999998584540105,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.12571750357747077,
|
|
"num_tokens": 2155730.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.528116464614868,
|
|
"epoch": 0.09479317851959361,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999998198336437,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.12236737087368965,
|
|
"num_tokens": 2166422.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.461041498184204,
|
|
"epoch": 0.09524673439767779,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999997765602233,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.12111935913562774,
|
|
"num_tokens": 2177842.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.55608811378479,
|
|
"epoch": 0.09570029027576198,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999997286337502,
|
|
"loss": 6.425,
|
|
"mean_token_accuracy": 0.12338349744677543,
|
|
"num_tokens": 2188614.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.552207946777344,
|
|
"epoch": 0.09615384615384616,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999996760542254,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.12883713990449905,
|
|
"num_tokens": 2197886.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.3705360889434814,
|
|
"epoch": 0.09660740203193033,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049999961882165,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.12635389864444732,
|
|
"num_tokens": 2209930.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.534476470947266,
|
|
"epoch": 0.09706095791001451,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999995569360251,
|
|
"loss": 6.2868,
|
|
"mean_token_accuracy": 0.12291447669267655,
|
|
"num_tokens": 2219767.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.428853178024292,
|
|
"epoch": 0.0975145137880987,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499999490397352,
|
|
"loss": 6.2117,
|
|
"mean_token_accuracy": 0.1293780729174614,
|
|
"num_tokens": 2230082.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.476440477371216,
|
|
"epoch": 0.09796806966618288,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999994192056321,
|
|
"loss": 6.2369,
|
|
"mean_token_accuracy": 0.13364363461732864,
|
|
"num_tokens": 2240066.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.405725526809692,
|
|
"epoch": 0.09842162554426705,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999993433608669,
|
|
"loss": 6.2701,
|
|
"mean_token_accuracy": 0.12502679005265235,
|
|
"num_tokens": 2250732.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.442107105255127,
|
|
"epoch": 0.09887518142235123,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999992628630579,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.12542710900306703,
|
|
"num_tokens": 2261452.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.452964830398559,
|
|
"epoch": 0.09932873730043541,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999991777122069,
|
|
"loss": 6.2658,
|
|
"mean_token_accuracy": 0.1284552037715912,
|
|
"num_tokens": 2271929.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.414393424987793,
|
|
"epoch": 0.0997822931785196,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999990879083156,
|
|
"loss": 6.2473,
|
|
"mean_token_accuracy": 0.12654093131422997,
|
|
"num_tokens": 2282987.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.367011642456054,
|
|
"epoch": 0.10023584905660378,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999989934513857,
|
|
"loss": 6.2291,
|
|
"mean_token_accuracy": 0.13299606069922448,
|
|
"num_tokens": 2292796.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.531451177597046,
|
|
"epoch": 0.10068940493468795,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999988943414193,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.127064548432827,
|
|
"num_tokens": 2303057.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.33807897567749,
|
|
"epoch": 0.10114296081277213,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999987905784184,
|
|
"loss": 6.2576,
|
|
"mean_token_accuracy": 0.1281444862484932,
|
|
"num_tokens": 2314168.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.440323400497436,
|
|
"epoch": 0.10159651669085631,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999986821623853,
|
|
"loss": 6.2274,
|
|
"mean_token_accuracy": 0.12680768072605134,
|
|
"num_tokens": 2325241.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.514708232879639,
|
|
"epoch": 0.1020500725689405,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999985690933219,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.12574926167726516,
|
|
"num_tokens": 2334866.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.322805023193359,
|
|
"epoch": 0.10250362844702467,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999984513712311,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.12497551888227462,
|
|
"num_tokens": 2345422.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.5371935844421385,
|
|
"epoch": 0.10295718432510885,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999983289961146,
|
|
"loss": 6.2772,
|
|
"mean_token_accuracy": 0.12496376484632492,
|
|
"num_tokens": 2356285.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.343741798400879,
|
|
"epoch": 0.10341074020319303,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999982019679755,
|
|
"loss": 6.174,
|
|
"mean_token_accuracy": 0.13649375587701798,
|
|
"num_tokens": 2366861.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.431583738327026,
|
|
"epoch": 0.10386429608127722,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999980702868164,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.13263476118445397,
|
|
"num_tokens": 2376851.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.428322172164917,
|
|
"epoch": 0.1043178519593614,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999979339526396,
|
|
"loss": 6.2835,
|
|
"mean_token_accuracy": 0.13185692876577376,
|
|
"num_tokens": 2386857.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.469877624511719,
|
|
"epoch": 0.10477140783744557,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999977929654484,
|
|
"loss": 6.2088,
|
|
"mean_token_accuracy": 0.13108245208859443,
|
|
"num_tokens": 2397035.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.404506397247315,
|
|
"epoch": 0.10522496371552975,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999976473252453,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.1281719334423542,
|
|
"num_tokens": 2408177.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.543879461288452,
|
|
"epoch": 0.10567851959361393,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999974970320338,
|
|
"loss": 6.2436,
|
|
"mean_token_accuracy": 0.12375756427645683,
|
|
"num_tokens": 2418445.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.355627489089966,
|
|
"epoch": 0.10613207547169812,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999973420858165,
|
|
"loss": 6.2404,
|
|
"mean_token_accuracy": 0.1271333783864975,
|
|
"num_tokens": 2428990.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.4137852668762205,
|
|
"epoch": 0.10658563134978229,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999971824865968,
|
|
"loss": 6.268,
|
|
"mean_token_accuracy": 0.12645680457353592,
|
|
"num_tokens": 2439643.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.5276916980743405,
|
|
"epoch": 0.10703918722786647,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999970182343782,
|
|
"loss": 6.311,
|
|
"mean_token_accuracy": 0.12705472484230995,
|
|
"num_tokens": 2450691.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.504130935668945,
|
|
"epoch": 0.10749274310595065,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999968493291638,
|
|
"loss": 6.2423,
|
|
"mean_token_accuracy": 0.12769789844751359,
|
|
"num_tokens": 2460706.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.226739454269409,
|
|
"epoch": 0.10794629898403484,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999966757709573,
|
|
"loss": 6.1367,
|
|
"mean_token_accuracy": 0.13683899343013764,
|
|
"num_tokens": 2470947.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.458954811096191,
|
|
"epoch": 0.10839985486211902,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999964975597622,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.13537428453564643,
|
|
"num_tokens": 2481132.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.338390970230103,
|
|
"epoch": 0.10885341074020319,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999963146955821,
|
|
"loss": 6.138,
|
|
"mean_token_accuracy": 0.1305425487458706,
|
|
"num_tokens": 2491701.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.297045183181763,
|
|
"epoch": 0.10930696661828737,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499996127178421,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.12452783957123756,
|
|
"num_tokens": 2502360.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.401448202133179,
|
|
"epoch": 0.10976052249637155,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999959350082825,
|
|
"loss": 6.1111,
|
|
"mean_token_accuracy": 0.1346064828336239,
|
|
"num_tokens": 2512140.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.388574886322021,
|
|
"epoch": 0.11021407837445574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999957381851709,
|
|
"loss": 6.2384,
|
|
"mean_token_accuracy": 0.1266896404325962,
|
|
"num_tokens": 2522721.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.324961376190186,
|
|
"epoch": 0.1106676342525399,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999955367090901,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.13158604130148888,
|
|
"num_tokens": 2531786.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.4173516750335695,
|
|
"epoch": 0.11112119013062409,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999953305800441,
|
|
"loss": 6.2082,
|
|
"mean_token_accuracy": 0.12343020662665367,
|
|
"num_tokens": 2542895.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.308479452133179,
|
|
"epoch": 0.11157474600870827,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999951197980374,
|
|
"loss": 6.2113,
|
|
"mean_token_accuracy": 0.12858483716845512,
|
|
"num_tokens": 2554120.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.494872283935547,
|
|
"epoch": 0.11202830188679246,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999949043630744,
|
|
"loss": 6.2613,
|
|
"mean_token_accuracy": 0.126002337038517,
|
|
"num_tokens": 2563935.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.2588221549987795,
|
|
"epoch": 0.11248185776487664,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999946842751593,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.13200209736824037,
|
|
"num_tokens": 2574465.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.344051551818848,
|
|
"epoch": 0.11293541364296081,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999944595342968,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.13319186195731164,
|
|
"num_tokens": 2584694.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.293050384521484,
|
|
"epoch": 0.11338896952104499,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999942301404916,
|
|
"loss": 6.0892,
|
|
"mean_token_accuracy": 0.13468018174171448,
|
|
"num_tokens": 2594540.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.27103443145752,
|
|
"epoch": 0.11384252539912917,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999939960937484,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.13721646815538407,
|
|
"num_tokens": 2604896.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.413160896301269,
|
|
"epoch": 0.11429608127721336,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999937573940721,
|
|
"loss": 6.1974,
|
|
"mean_token_accuracy": 0.14260305911302568,
|
|
"num_tokens": 2614143.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.228365230560303,
|
|
"epoch": 0.11474963715529753,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999935140414674,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.13245780095458032,
|
|
"num_tokens": 2623999.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.427315664291382,
|
|
"epoch": 0.11520319303338171,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999932660359395,
|
|
"loss": 6.3045,
|
|
"mean_token_accuracy": 0.1259209007024765,
|
|
"num_tokens": 2636208.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.353607034683227,
|
|
"epoch": 0.11565674891146589,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999930133774936,
|
|
"loss": 6.1813,
|
|
"mean_token_accuracy": 0.13700075224041938,
|
|
"num_tokens": 2645854.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.392856884002685,
|
|
"epoch": 0.11611030478955008,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999927560661348,
|
|
"loss": 6.1641,
|
|
"mean_token_accuracy": 0.13880657628178597,
|
|
"num_tokens": 2655877.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.396235799789428,
|
|
"epoch": 0.11656386066763426,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999924941018685,
|
|
"loss": 6.1871,
|
|
"mean_token_accuracy": 0.1347483940422535,
|
|
"num_tokens": 2666157.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.304231357574463,
|
|
"epoch": 0.11701741654571843,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999922274847,
|
|
"loss": 6.1112,
|
|
"mean_token_accuracy": 0.13436754122376443,
|
|
"num_tokens": 2676647.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.259562253952026,
|
|
"epoch": 0.11747097242380261,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499991956214635,
|
|
"loss": 6.1475,
|
|
"mean_token_accuracy": 0.14410557746887206,
|
|
"num_tokens": 2686417.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.3692951679229735,
|
|
"epoch": 0.1179245283018868,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499991680291679,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.12797631248831748,
|
|
"num_tokens": 2697540.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.3081450939178465,
|
|
"epoch": 0.11837808417997098,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999913997158378,
|
|
"loss": 6.1925,
|
|
"mean_token_accuracy": 0.12314079701900482,
|
|
"num_tokens": 2709397.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.354034662246704,
|
|
"epoch": 0.11883164005805515,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999911144871169,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.12890623807907103,
|
|
"num_tokens": 2720430.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.274476385116577,
|
|
"epoch": 0.11928519593613933,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999908246055226,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.128923050314188,
|
|
"num_tokens": 2730648.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.303538846969604,
|
|
"epoch": 0.11973875181422351,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999905300710607,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.13420135006308556,
|
|
"num_tokens": 2739979.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.31509165763855,
|
|
"epoch": 0.1201923076923077,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999902308837373,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.12678968757390977,
|
|
"num_tokens": 2750329.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.295187377929688,
|
|
"epoch": 0.12064586357039188,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999899270435584,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.14072596430778503,
|
|
"num_tokens": 2760535.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.30014271736145,
|
|
"epoch": 0.12109941944847605,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999896185505307,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.133646260201931,
|
|
"num_tokens": 2770470.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.295889663696289,
|
|
"epoch": 0.12155297532656023,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999893054046603,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.13114681392908095,
|
|
"num_tokens": 2781506.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.219323301315308,
|
|
"epoch": 0.12200653120464441,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999889876059537,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.14254361912608146,
|
|
"num_tokens": 2791245.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.264402437210083,
|
|
"epoch": 0.1224600870827286,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999886651544176,
|
|
"loss": 6.0352,
|
|
"mean_token_accuracy": 0.13747782483696938,
|
|
"num_tokens": 2801680.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.328179216384887,
|
|
"epoch": 0.12291364296081277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999883380500584,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.13885134533047677,
|
|
"num_tokens": 2812805.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.274612092971802,
|
|
"epoch": 0.12336719883889695,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999880062928831,
|
|
"loss": 6.1525,
|
|
"mean_token_accuracy": 0.13258814290165902,
|
|
"num_tokens": 2822834.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.32262659072876,
|
|
"epoch": 0.12382075471698113,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999876698828985,
|
|
"loss": 6.093,
|
|
"mean_token_accuracy": 0.1388528026640415,
|
|
"num_tokens": 2832312.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.264431667327881,
|
|
"epoch": 0.12427431059506532,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999873288201116,
|
|
"loss": 6.1074,
|
|
"mean_token_accuracy": 0.14017656743526458,
|
|
"num_tokens": 2842998.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.334399604797364,
|
|
"epoch": 0.1247278664731495,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004999869831045294,
|
|
"loss": 6.1358,
|
|
"mean_token_accuracy": 0.13416288197040557,
|
|
"num_tokens": 2854218.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.257809448242187,
|
|
"epoch": 0.12518142235123367,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999866327361589,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.14412764012813567,
|
|
"num_tokens": 2864484.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.278401279449463,
|
|
"epoch": 0.12563497822931785,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999862777150077,
|
|
"loss": 6.1335,
|
|
"mean_token_accuracy": 0.13539522439241408,
|
|
"num_tokens": 2873800.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.327728033065796,
|
|
"epoch": 0.12608853410740203,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999859180410829,
|
|
"loss": 6.1425,
|
|
"mean_token_accuracy": 0.13279536589980126,
|
|
"num_tokens": 2884247.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.269402170181275,
|
|
"epoch": 0.12654208998548622,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999855537143919,
|
|
"loss": 6.0613,
|
|
"mean_token_accuracy": 0.13359882831573486,
|
|
"num_tokens": 2894739.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.197747993469238,
|
|
"epoch": 0.1269956458635704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999851847349425,
|
|
"loss": 6.0982,
|
|
"mean_token_accuracy": 0.13437446355819702,
|
|
"num_tokens": 2904376.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.377307605743408,
|
|
"epoch": 0.12744920174165458,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999848111027419,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.12998344823718072,
|
|
"num_tokens": 2914304.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.292350578308105,
|
|
"epoch": 0.12790275761973874,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999844328177983,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.14133364632725715,
|
|
"num_tokens": 2924400.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.371039295196534,
|
|
"epoch": 0.12835631349782292,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999840498801191,
|
|
"loss": 6.274,
|
|
"mean_token_accuracy": 0.13513783514499664,
|
|
"num_tokens": 2935040.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.21938738822937,
|
|
"epoch": 0.1288098693759071,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999836622897126,
|
|
"loss": 6.0552,
|
|
"mean_token_accuracy": 0.13850467056035995,
|
|
"num_tokens": 2945536.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.202126550674438,
|
|
"epoch": 0.1292634252539913,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999832700465865,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.13881825804710388,
|
|
"num_tokens": 2954969.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.261548900604248,
|
|
"epoch": 0.12971698113207547,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999828731507491,
|
|
"loss": 6.1059,
|
|
"mean_token_accuracy": 0.13205914497375487,
|
|
"num_tokens": 2966218.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.315013360977173,
|
|
"epoch": 0.13017053701015965,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999824716022085,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.12892259508371354,
|
|
"num_tokens": 2976640.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.221342897415161,
|
|
"epoch": 0.13062409288824384,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999820654009731,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.13740533366799354,
|
|
"num_tokens": 2985883.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.278382968902588,
|
|
"epoch": 0.13107764876632802,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999816545470513,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.12974392548203467,
|
|
"num_tokens": 2996695.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.26499662399292,
|
|
"epoch": 0.1315312046444122,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999812390404514,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.13423352390527726,
|
|
"num_tokens": 3007500.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.136911249160766,
|
|
"epoch": 0.13198476052249636,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999808188811823,
|
|
"loss": 5.9549,
|
|
"mean_token_accuracy": 0.13566315323114395,
|
|
"num_tokens": 3017299.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.368114423751831,
|
|
"epoch": 0.13243831640058054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999803940692524,
|
|
"loss": 6.239,
|
|
"mean_token_accuracy": 0.12817587703466415,
|
|
"num_tokens": 3028389.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.223598575592041,
|
|
"epoch": 0.13289187227866472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999799646046707,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.13951559141278266,
|
|
"num_tokens": 3038883.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.345055007934571,
|
|
"epoch": 0.1333454281567489,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999795304874461,
|
|
"loss": 6.1808,
|
|
"mean_token_accuracy": 0.13515384122729301,
|
|
"num_tokens": 3049904.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.184125995635986,
|
|
"epoch": 0.1337989840348331,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999790917175873,
|
|
"loss": 6.0163,
|
|
"mean_token_accuracy": 0.13716932758688927,
|
|
"num_tokens": 3059788.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.27112979888916,
|
|
"epoch": 0.13425253991291727,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999786482951036,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.1407728001475334,
|
|
"num_tokens": 3070413.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.198488378524781,
|
|
"epoch": 0.13470609579100146,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999782002200041,
|
|
"loss": 6.1247,
|
|
"mean_token_accuracy": 0.13304170593619347,
|
|
"num_tokens": 3081093.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.299404525756836,
|
|
"epoch": 0.13515965166908564,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999777474922982,
|
|
"loss": 6.0758,
|
|
"mean_token_accuracy": 0.13359509408473969,
|
|
"num_tokens": 3090594.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.272291612625122,
|
|
"epoch": 0.13561320754716982,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999772901119951,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.1321714386343956,
|
|
"num_tokens": 3101061.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.250188732147217,
|
|
"epoch": 0.13606676342525398,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999768280791043,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.13871695548295976,
|
|
"num_tokens": 3111715.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.187767601013183,
|
|
"epoch": 0.13652031930333816,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999763613936352,
|
|
"loss": 6.0033,
|
|
"mean_token_accuracy": 0.14132409542798996,
|
|
"num_tokens": 3121378.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.173904228210449,
|
|
"epoch": 0.13697387518142234,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999758900555979,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.142991504073143,
|
|
"num_tokens": 3131229.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.184138822555542,
|
|
"epoch": 0.13742743105950653,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999754140650017,
|
|
"loss": 6.033,
|
|
"mean_token_accuracy": 0.1338609889149666,
|
|
"num_tokens": 3140859.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.279017591476441,
|
|
"epoch": 0.1378809869375907,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999749334218567,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.13679298311471938,
|
|
"num_tokens": 3151692.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.150258111953735,
|
|
"epoch": 0.1383345428156749,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999744481261726,
|
|
"loss": 6.1035,
|
|
"mean_token_accuracy": 0.13335202634334564,
|
|
"num_tokens": 3161879.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.205261278152466,
|
|
"epoch": 0.13878809869375908,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999739581779597,
|
|
"loss": 5.9614,
|
|
"mean_token_accuracy": 0.1442497506737709,
|
|
"num_tokens": 3171282.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.204788684844971,
|
|
"epoch": 0.13924165457184326,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499973463577228,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.14128000661730766,
|
|
"num_tokens": 3181398.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.210041856765747,
|
|
"epoch": 0.13969521044992744,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999729643239877,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.1372975580394268,
|
|
"num_tokens": 3191431.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.246035623550415,
|
|
"epoch": 0.1401487663280116,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999724604182492,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.1305283486843109,
|
|
"num_tokens": 3202147.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.317409181594849,
|
|
"epoch": 0.14060232220609578,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999719518600229,
|
|
"loss": 6.0187,
|
|
"mean_token_accuracy": 0.14262037947773934,
|
|
"num_tokens": 3212428.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.198874998092651,
|
|
"epoch": 0.14105587808417996,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999714386493192,
|
|
"loss": 6.0638,
|
|
"mean_token_accuracy": 0.1392004132270813,
|
|
"num_tokens": 3222099.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.23433141708374,
|
|
"epoch": 0.14150943396226415,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999709207861489,
|
|
"loss": 6.0113,
|
|
"mean_token_accuracy": 0.1394033081829548,
|
|
"num_tokens": 3232079.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.08824315071106,
|
|
"epoch": 0.14196298984034833,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999703982705227,
|
|
"loss": 5.928,
|
|
"mean_token_accuracy": 0.14834348112344742,
|
|
"num_tokens": 3241762.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.164975643157959,
|
|
"epoch": 0.1424165457184325,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999698711024513,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.1406618483364582,
|
|
"num_tokens": 3252571.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.212284135818481,
|
|
"epoch": 0.1428701015965167,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999693392819456,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.13540706485509874,
|
|
"num_tokens": 3263542.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.246869134902954,
|
|
"epoch": 0.14332365747460088,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999688028090166,
|
|
"loss": 6.1386,
|
|
"mean_token_accuracy": 0.13631665483117103,
|
|
"num_tokens": 3273295.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.328453207015992,
|
|
"epoch": 0.14377721335268506,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999682616836755,
|
|
"loss": 6.1427,
|
|
"mean_token_accuracy": 0.13787241727113725,
|
|
"num_tokens": 3283605.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.191803979873657,
|
|
"epoch": 0.14423076923076922,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999677159059334,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.14498581141233444,
|
|
"num_tokens": 3293837.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.072175979614258,
|
|
"epoch": 0.1446843251088534,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999671654758016,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.14269243702292442,
|
|
"num_tokens": 3304131.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.235024261474609,
|
|
"epoch": 0.14513788098693758,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999666103932915,
|
|
"loss": 6.0234,
|
|
"mean_token_accuracy": 0.13487293496727942,
|
|
"num_tokens": 3313543.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.185160875320435,
|
|
"epoch": 0.14559143686502177,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999660506584145,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.13741163462400435,
|
|
"num_tokens": 3324487.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.239445686340332,
|
|
"epoch": 0.14604499274310595,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999654862711823,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.137547168135643,
|
|
"num_tokens": 3335094.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.134017467498779,
|
|
"epoch": 0.14649854862119013,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999649172316065,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.13992214426398278,
|
|
"num_tokens": 3344252.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.197755432128906,
|
|
"epoch": 0.14695210449927432,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499964343539699,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.13646679371595383,
|
|
"num_tokens": 3354265.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.2219359397888185,
|
|
"epoch": 0.1474056603773585,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999637651954714,
|
|
"loss": 6.125,
|
|
"mean_token_accuracy": 0.1394253857433796,
|
|
"num_tokens": 3364616.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.27594027519226,
|
|
"epoch": 0.14785921625544268,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999631821989358,
|
|
"loss": 6.0927,
|
|
"mean_token_accuracy": 0.14138601943850518,
|
|
"num_tokens": 3373650.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.101440382003784,
|
|
"epoch": 0.14831277213352684,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999625945501043,
|
|
"loss": 5.9886,
|
|
"mean_token_accuracy": 0.1461173690855503,
|
|
"num_tokens": 3384590.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.26271767616272,
|
|
"epoch": 0.14876632801161102,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499962002248989,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.13982762396335602,
|
|
"num_tokens": 3395616.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.153381443023681,
|
|
"epoch": 0.1492198838896952,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999614052956024,
|
|
"loss": 6.0239,
|
|
"mean_token_accuracy": 0.13940254971385002,
|
|
"num_tokens": 3405810.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.254888677597046,
|
|
"epoch": 0.1496734397677794,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999608036899563,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.1363350972533226,
|
|
"num_tokens": 3415932.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.151538419723511,
|
|
"epoch": 0.15012699564586357,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999601974320636,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.14114982038736343,
|
|
"num_tokens": 3425626.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.121203470230102,
|
|
"epoch": 0.15058055152394775,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999595865219367,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.13342469930648804,
|
|
"num_tokens": 3434837.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.156308937072754,
|
|
"epoch": 0.15103410740203194,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999589709595881,
|
|
"loss": 6.0332,
|
|
"mean_token_accuracy": 0.14258277863264085,
|
|
"num_tokens": 3445238.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.166830587387085,
|
|
"epoch": 0.15148766328011612,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999583507450308,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.1305796168744564,
|
|
"num_tokens": 3456738.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.070332002639771,
|
|
"epoch": 0.1519412191582003,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999577258782774,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.13995402976870536,
|
|
"num_tokens": 3466296.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.266418838500977,
|
|
"epoch": 0.15239477503628446,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499957096359341,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.13597871735692024,
|
|
"num_tokens": 3476989.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.111058521270752,
|
|
"epoch": 0.15284833091436864,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999564621882343,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.141887167096138,
|
|
"num_tokens": 3487050.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.225695085525513,
|
|
"epoch": 0.15330188679245282,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999558233649708,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.1312915213406086,
|
|
"num_tokens": 3497777.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.17779574394226,
|
|
"epoch": 0.153755442670537,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999551798895636,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.13619913384318352,
|
|
"num_tokens": 3509066.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.141854095458984,
|
|
"epoch": 0.1542089985486212,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999545317620258,
|
|
"loss": 5.9776,
|
|
"mean_token_accuracy": 0.1392234146595001,
|
|
"num_tokens": 3519567.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.124539947509765,
|
|
"epoch": 0.15466255442670537,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999538789823711,
|
|
"loss": 6.0076,
|
|
"mean_token_accuracy": 0.1419394336640835,
|
|
"num_tokens": 3529402.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.27455096244812,
|
|
"epoch": 0.15511611030478956,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999532215506127,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.14713949486613273,
|
|
"num_tokens": 3539805.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.072864151000976,
|
|
"epoch": 0.15556966618287374,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999525594667645,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.14898346215486527,
|
|
"num_tokens": 3550477.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.0882893085479735,
|
|
"epoch": 0.15602322206095792,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049995189273084,
|
|
"loss": 5.9843,
|
|
"mean_token_accuracy": 0.1400413043797016,
|
|
"num_tokens": 3560729.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.1748028755187985,
|
|
"epoch": 0.15647677793904208,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499951221342853,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.1325826108455658,
|
|
"num_tokens": 3571538.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.174065685272216,
|
|
"epoch": 0.15693033381712626,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999505453028174,
|
|
"loss": 6.0644,
|
|
"mean_token_accuracy": 0.13689751103520392,
|
|
"num_tokens": 3583128.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.2016395092010494,
|
|
"epoch": 0.15738388969521044,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999498646107472,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.1429124280810356,
|
|
"num_tokens": 3594358.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.129647302627563,
|
|
"epoch": 0.15783744557329463,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999491792666566,
|
|
"loss": 5.9292,
|
|
"mean_token_accuracy": 0.14557284563779832,
|
|
"num_tokens": 3604345.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.089707612991333,
|
|
"epoch": 0.1582910014513788,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999484892705597,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.1409473091363907,
|
|
"num_tokens": 3616129.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.162917709350586,
|
|
"epoch": 0.158744557329463,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999477946224705,
|
|
"loss": 6.0177,
|
|
"mean_token_accuracy": 0.14049824178218842,
|
|
"num_tokens": 3627458.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.149751949310303,
|
|
"epoch": 0.15919811320754718,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999470953224037,
|
|
"loss": 5.9031,
|
|
"mean_token_accuracy": 0.1436824843287468,
|
|
"num_tokens": 3636047.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.0508606910705565,
|
|
"epoch": 0.15965166908563136,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999463913703735,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.1433118313550949,
|
|
"num_tokens": 3646930.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.124081325531006,
|
|
"epoch": 0.16010522496371554,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999456827663948,
|
|
"loss": 5.9919,
|
|
"mean_token_accuracy": 0.1459735155105591,
|
|
"num_tokens": 3657279.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.052764081954956,
|
|
"epoch": 0.1605587808417997,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499944969510482,
|
|
"loss": 5.9001,
|
|
"mean_token_accuracy": 0.13991431295871734,
|
|
"num_tokens": 3667070.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.181622266769409,
|
|
"epoch": 0.16101233671988388,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999442516026498,
|
|
"loss": 5.9141,
|
|
"mean_token_accuracy": 0.14285601824522018,
|
|
"num_tokens": 3677560.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.027710103988648,
|
|
"epoch": 0.16146589259796806,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999435290429133,
|
|
"loss": 5.8862,
|
|
"mean_token_accuracy": 0.14947912245988845,
|
|
"num_tokens": 3686701.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.117189884185791,
|
|
"epoch": 0.16191944847605225,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999428018312872,
|
|
"loss": 5.9719,
|
|
"mean_token_accuracy": 0.14543041959404945,
|
|
"num_tokens": 3696338.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.091988801956177,
|
|
"epoch": 0.16237300435413643,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999420699677867,
|
|
"loss": 5.9492,
|
|
"mean_token_accuracy": 0.1432087704539299,
|
|
"num_tokens": 3705752.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.203689908981323,
|
|
"epoch": 0.1628265602322206,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999413334524269,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.13643145337700843,
|
|
"num_tokens": 3716225.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.111277675628662,
|
|
"epoch": 0.1632801161103048,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999405922852229,
|
|
"loss": 5.9098,
|
|
"mean_token_accuracy": 0.14482017382979392,
|
|
"num_tokens": 3726593.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.028970766067505,
|
|
"epoch": 0.16373367198838898,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999398464661901,
|
|
"loss": 5.9708,
|
|
"mean_token_accuracy": 0.13964075967669487,
|
|
"num_tokens": 3737563.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.246074914932251,
|
|
"epoch": 0.16418722786647316,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999390959953441,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.14332932382822036,
|
|
"num_tokens": 3747752.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.053060626983642,
|
|
"epoch": 0.16464078374455732,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999383408727002,
|
|
"loss": 5.9539,
|
|
"mean_token_accuracy": 0.14173785969614983,
|
|
"num_tokens": 3758795.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.167564058303833,
|
|
"epoch": 0.1650943396226415,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999375810982741,
|
|
"loss": 5.9315,
|
|
"mean_token_accuracy": 0.14446532130241393,
|
|
"num_tokens": 3768690.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.0776159286499025,
|
|
"epoch": 0.16554789550072568,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999368166720815,
|
|
"loss": 6.014,
|
|
"mean_token_accuracy": 0.14304881766438485,
|
|
"num_tokens": 3779018.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.147589683532715,
|
|
"epoch": 0.16600145137880987,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999360475941382,
|
|
"loss": 5.9118,
|
|
"mean_token_accuracy": 0.14721195623278618,
|
|
"num_tokens": 3788985.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.131836366653443,
|
|
"epoch": 0.16645500725689405,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049993527386446,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.1322140447795391,
|
|
"num_tokens": 3800787.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.089927768707275,
|
|
"epoch": 0.16690856313497823,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999344954830633,
|
|
"loss": 5.9208,
|
|
"mean_token_accuracy": 0.1421339437365532,
|
|
"num_tokens": 3811381.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.0987998962402346,
|
|
"epoch": 0.16736211901306242,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999337124499638,
|
|
"loss": 6.0339,
|
|
"mean_token_accuracy": 0.14644376039505005,
|
|
"num_tokens": 3822055.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.147271633148193,
|
|
"epoch": 0.1678156748911466,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999329247651777,
|
|
"loss": 5.9932,
|
|
"mean_token_accuracy": 0.1378726117312908,
|
|
"num_tokens": 3831900.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.1165355205535885,
|
|
"epoch": 0.16826923076923078,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999321324287213,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.14189887940883636,
|
|
"num_tokens": 3842702.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.1751471042633055,
|
|
"epoch": 0.16872278664731494,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999313354406114,
|
|
"loss": 5.9187,
|
|
"mean_token_accuracy": 0.1416791319847107,
|
|
"num_tokens": 3852690.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.9985252857208256,
|
|
"epoch": 0.16917634252539912,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499930533800864,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.1507345899939537,
|
|
"num_tokens": 3863040.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.10200867652893,
|
|
"epoch": 0.1696298984034833,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999297275094958,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.14036339968442918,
|
|
"num_tokens": 3873613.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.999226474761963,
|
|
"epoch": 0.1700834542815675,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999289165665235,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.14994008243083953,
|
|
"num_tokens": 3883936.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.995340251922608,
|
|
"epoch": 0.17053701015965167,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999281009719639,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.15587486177682877,
|
|
"num_tokens": 3893788.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.001563358306885,
|
|
"epoch": 0.17099056603773585,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999272807258339,
|
|
"loss": 5.8376,
|
|
"mean_token_accuracy": 0.15261975079774856,
|
|
"num_tokens": 3903434.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.05434021949768,
|
|
"epoch": 0.17144412191582004,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999264558281504,
|
|
"loss": 5.8409,
|
|
"mean_token_accuracy": 0.1521665245294571,
|
|
"num_tokens": 3913476.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.971798706054687,
|
|
"epoch": 0.17189767779390422,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999256262789305,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.151979461312294,
|
|
"num_tokens": 3923301.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.028662157058716,
|
|
"epoch": 0.1723512336719884,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999247920781913,
|
|
"loss": 5.9603,
|
|
"mean_token_accuracy": 0.14160882011055947,
|
|
"num_tokens": 3933335.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.160859155654907,
|
|
"epoch": 0.17280478955007256,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999239532259502,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.1399615041911602,
|
|
"num_tokens": 3944171.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.11788387298584,
|
|
"epoch": 0.17325834542815674,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999231097222244,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.14640697762370108,
|
|
"num_tokens": 3954160.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.125342941284179,
|
|
"epoch": 0.17371190130624092,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999222615670312,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.15440410375595093,
|
|
"num_tokens": 3964110.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.047020721435547,
|
|
"epoch": 0.1741654571843251,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999214087603885,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.14503437876701356,
|
|
"num_tokens": 3974293.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.03211555480957,
|
|
"epoch": 0.1746190130624093,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999205513023135,
|
|
"loss": 5.8896,
|
|
"mean_token_accuracy": 0.14775249734520912,
|
|
"num_tokens": 3984346.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.992477941513061,
|
|
"epoch": 0.17507256894049347,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999196891928245,
|
|
"loss": 5.8312,
|
|
"mean_token_accuracy": 0.15544059574604036,
|
|
"num_tokens": 3992897.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.042530679702759,
|
|
"epoch": 0.17552612481857766,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999188224319388,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.15182426571846008,
|
|
"num_tokens": 4002575.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.01702356338501,
|
|
"epoch": 0.17597968069666184,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999179510196746,
|
|
"loss": 5.9547,
|
|
"mean_token_accuracy": 0.1407930850982666,
|
|
"num_tokens": 4013752.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.041807699203491,
|
|
"epoch": 0.17643323657474602,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999170749560498,
|
|
"loss": 5.833,
|
|
"mean_token_accuracy": 0.1515166938304901,
|
|
"num_tokens": 4023718.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.038792991638184,
|
|
"epoch": 0.17688679245283018,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999161942410827,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.13799159675836564,
|
|
"num_tokens": 4034210.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.134712362289429,
|
|
"epoch": 0.17734034833091436,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999153088747913,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.14558120667934418,
|
|
"num_tokens": 4044868.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.951734399795532,
|
|
"epoch": 0.17779390420899854,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499914418857194,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.14710975885391236,
|
|
"num_tokens": 4055049.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.109003973007202,
|
|
"epoch": 0.17824746008708273,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999135241883092,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.14337438270449637,
|
|
"num_tokens": 4065889.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.076221990585327,
|
|
"epoch": 0.1787010159651669,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999126248681555,
|
|
"loss": 5.9986,
|
|
"mean_token_accuracy": 0.14153247475624084,
|
|
"num_tokens": 4077288.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.059194612503052,
|
|
"epoch": 0.1791545718432511,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999117208967513,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.14241613298654557,
|
|
"num_tokens": 4087402.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.074989175796508,
|
|
"epoch": 0.17960812772133528,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999108122741154,
|
|
"loss": 5.9911,
|
|
"mean_token_accuracy": 0.1394512176513672,
|
|
"num_tokens": 4098150.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.997276258468628,
|
|
"epoch": 0.18006168359941946,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999098990002666,
|
|
"loss": 5.8489,
|
|
"mean_token_accuracy": 0.14526972770690919,
|
|
"num_tokens": 4108134.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.0917863845825195,
|
|
"epoch": 0.18051523947750364,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999089810752237,
|
|
"loss": 5.988,
|
|
"mean_token_accuracy": 0.1419826477766037,
|
|
"num_tokens": 4118251.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.037380886077881,
|
|
"epoch": 0.1809687953555878,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499908058499006,
|
|
"loss": 5.8256,
|
|
"mean_token_accuracy": 0.1488537833094597,
|
|
"num_tokens": 4129228.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.989283561706543,
|
|
"epoch": 0.18142235123367198,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999071312716321,
|
|
"loss": 5.8905,
|
|
"mean_token_accuracy": 0.15052457451820372,
|
|
"num_tokens": 4139391.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.038852834701538,
|
|
"epoch": 0.18187590711175616,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999061993931215,
|
|
"loss": 5.8198,
|
|
"mean_token_accuracy": 0.15358539968729018,
|
|
"num_tokens": 4148891.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.235394716262817,
|
|
"epoch": 0.18232946298984035,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999052628634934,
|
|
"loss": 6.1728,
|
|
"mean_token_accuracy": 0.14022321105003357,
|
|
"num_tokens": 4159551.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.079950952529908,
|
|
"epoch": 0.18278301886792453,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999043216827671,
|
|
"loss": 5.9696,
|
|
"mean_token_accuracy": 0.14237845912575722,
|
|
"num_tokens": 4170055.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.993285369873047,
|
|
"epoch": 0.1832365747460087,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999033758509621,
|
|
"loss": 5.8201,
|
|
"mean_token_accuracy": 0.14752258732914925,
|
|
"num_tokens": 4180767.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.0369898796081545,
|
|
"epoch": 0.1836901306240929,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499902425368098,
|
|
"loss": 5.9485,
|
|
"mean_token_accuracy": 0.14603547155857086,
|
|
"num_tokens": 4190654.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.0134642124176025,
|
|
"epoch": 0.18414368650217708,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999014702341944,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.1434512048959732,
|
|
"num_tokens": 4200753.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.070598554611206,
|
|
"epoch": 0.18459724238026126,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999005104492712,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.14099996089935302,
|
|
"num_tokens": 4210994.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.0680242538452145,
|
|
"epoch": 0.18505079825834542,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998995460133481,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.14143144562840462,
|
|
"num_tokens": 4220883.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.077210140228272,
|
|
"epoch": 0.1855043541364296,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998985769264451,
|
|
"loss": 5.9245,
|
|
"mean_token_accuracy": 0.13767858743667602,
|
|
"num_tokens": 4231269.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.974451160430908,
|
|
"epoch": 0.18595791001451378,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998976031885821,
|
|
"loss": 5.93,
|
|
"mean_token_accuracy": 0.1419460207223892,
|
|
"num_tokens": 4241559.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.0086987018585205,
|
|
"epoch": 0.18641146589259797,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998966247997794,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.14645475745201111,
|
|
"num_tokens": 4250870.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.967829656600952,
|
|
"epoch": 0.18686502177068215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998956417600572,
|
|
"loss": 5.7746,
|
|
"mean_token_accuracy": 0.15297217816114425,
|
|
"num_tokens": 4260848.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.986316537857055,
|
|
"epoch": 0.18731857764876633,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998946540694358,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.15208268463611602,
|
|
"num_tokens": 4270973.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.132760667800904,
|
|
"epoch": 0.18777213352685052,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998936617279357,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.14554873257875442,
|
|
"num_tokens": 4281211.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.941362285614014,
|
|
"epoch": 0.1882256894049347,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998926647355773,
|
|
"loss": 5.8306,
|
|
"mean_token_accuracy": 0.150546196103096,
|
|
"num_tokens": 4291425.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.098439311981201,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998916630923813,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.14438463374972343,
|
|
"num_tokens": 4301079.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.045752716064453,
|
|
"epoch": 0.18913280116110304,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998906567983685,
|
|
"loss": 5.9215,
|
|
"mean_token_accuracy": 0.1422693431377411,
|
|
"num_tokens": 4312374.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.030663347244262,
|
|
"epoch": 0.18958635703918722,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998896458535595,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.15475437194108962,
|
|
"num_tokens": 4322810.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.984178876876831,
|
|
"epoch": 0.1900399129172714,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998886302579752,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.14914876371622085,
|
|
"num_tokens": 4332082.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.012246084213257,
|
|
"epoch": 0.19049346879535559,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499887610011637,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.1479165866971016,
|
|
"num_tokens": 4342632.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.986341905593872,
|
|
"epoch": 0.19094702467343977,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998865851145656,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.14595670849084855,
|
|
"num_tokens": 4353544.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.9498518943786625,
|
|
"epoch": 0.19140058055152395,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998855555667822,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.1430116519331932,
|
|
"num_tokens": 4363636.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.076320600509644,
|
|
"epoch": 0.19185413642960814,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998845213683084,
|
|
"loss": 5.831,
|
|
"mean_token_accuracy": 0.1475878320634365,
|
|
"num_tokens": 4373672.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.910988473892212,
|
|
"epoch": 0.19230769230769232,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998834825191652,
|
|
"loss": 5.8096,
|
|
"mean_token_accuracy": 0.14788725823163987,
|
|
"num_tokens": 4383199.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.013854932785034,
|
|
"epoch": 0.1927612481857765,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998824390193743,
|
|
"loss": 5.886,
|
|
"mean_token_accuracy": 0.1449464038014412,
|
|
"num_tokens": 4394446.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.0993109226226805,
|
|
"epoch": 0.19321480406386066,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998813908689573,
|
|
"loss": 5.9237,
|
|
"mean_token_accuracy": 0.14512224718928338,
|
|
"num_tokens": 4405882.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.93023910522461,
|
|
"epoch": 0.19366835994194484,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998803380679359,
|
|
"loss": 5.7867,
|
|
"mean_token_accuracy": 0.1542275607585907,
|
|
"num_tokens": 4415280.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.99576849937439,
|
|
"epoch": 0.19412191582002902,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998792806163317,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.1401658058166504,
|
|
"num_tokens": 4425755.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.925059509277344,
|
|
"epoch": 0.1945754716981132,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998782185141667,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.14792224615812302,
|
|
"num_tokens": 4436259.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.045332574844361,
|
|
"epoch": 0.1950290275761974,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998771517614629,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.14263954162597656,
|
|
"num_tokens": 4446423.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.00939302444458,
|
|
"epoch": 0.19548258345428157,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998760803582422,
|
|
"loss": 5.8288,
|
|
"mean_token_accuracy": 0.15420894026756288,
|
|
"num_tokens": 4456678.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.945328330993652,
|
|
"epoch": 0.19593613933236576,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998750043045269,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.15192546397447587,
|
|
"num_tokens": 4467031.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.024298143386841,
|
|
"epoch": 0.19638969521044994,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998739236003392,
|
|
"loss": 5.9066,
|
|
"mean_token_accuracy": 0.14100065529346467,
|
|
"num_tokens": 4477771.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.0035483837127686,
|
|
"epoch": 0.1968432510885341,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998728382457014,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.1434047520160675,
|
|
"num_tokens": 4488426.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.103923177719116,
|
|
"epoch": 0.19729680696661828,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998717482406362,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.14213445484638215,
|
|
"num_tokens": 4499735.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.009974479675293,
|
|
"epoch": 0.19775036284470246,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998706535851657,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.14943975061178208,
|
|
"num_tokens": 4509500.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.964470767974854,
|
|
"epoch": 0.19820391872278664,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998695542793129,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.14806249961256981,
|
|
"num_tokens": 4520431.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.013790941238403,
|
|
"epoch": 0.19865747460087083,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998684503231003,
|
|
"loss": 5.9367,
|
|
"mean_token_accuracy": 0.1468561165034771,
|
|
"num_tokens": 4532294.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.979345083236694,
|
|
"epoch": 0.199111030478955,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499867341716551,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.1456448383629322,
|
|
"num_tokens": 4542488.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.9495869159698485,
|
|
"epoch": 0.1995645863570392,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998662284596878,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.14156620278954507,
|
|
"num_tokens": 4552933.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.036973190307617,
|
|
"epoch": 0.20001814223512338,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998651105525335,
|
|
"loss": 5.7937,
|
|
"mean_token_accuracy": 0.15192690938711167,
|
|
"num_tokens": 4562373.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.927747917175293,
|
|
"epoch": 0.20047169811320756,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998639879951115,
|
|
"loss": 5.9131,
|
|
"mean_token_accuracy": 0.14802779853343964,
|
|
"num_tokens": 4572715.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.064771509170532,
|
|
"epoch": 0.2009252539912917,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499862860787445,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.14533086642622947,
|
|
"num_tokens": 4582782.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.980919456481933,
|
|
"epoch": 0.2013788098693759,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998617289295571,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.13982278481125832,
|
|
"num_tokens": 4594108.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.0538468837738035,
|
|
"epoch": 0.20183236574746008,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998605924214714,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.1460525505244732,
|
|
"num_tokens": 4604732.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.000491809844971,
|
|
"epoch": 0.20228592162554426,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998594512632114,
|
|
"loss": 5.9955,
|
|
"mean_token_accuracy": 0.13708511143922805,
|
|
"num_tokens": 4614998.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.970520877838135,
|
|
"epoch": 0.20273947750362845,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998583054548006,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.1484377056360245,
|
|
"num_tokens": 4624665.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.00954236984253,
|
|
"epoch": 0.20319303338171263,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998571549962628,
|
|
"loss": 5.8101,
|
|
"mean_token_accuracy": 0.15187345445156097,
|
|
"num_tokens": 4633731.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.991653680801392,
|
|
"epoch": 0.2036465892597968,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998559998876216,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.14615286365151406,
|
|
"num_tokens": 4643421.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.987816905975341,
|
|
"epoch": 0.204100145137881,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998548401289012,
|
|
"loss": 5.9151,
|
|
"mean_token_accuracy": 0.14586994647979737,
|
|
"num_tokens": 4653795.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.008340549468994,
|
|
"epoch": 0.20455370101596518,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998536757201253,
|
|
"loss": 5.8858,
|
|
"mean_token_accuracy": 0.1444897711277008,
|
|
"num_tokens": 4664840.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.039184617996216,
|
|
"epoch": 0.20500725689404933,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998525066613181,
|
|
"loss": 5.8979,
|
|
"mean_token_accuracy": 0.15061988234519957,
|
|
"num_tokens": 4675508.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.932389974594116,
|
|
"epoch": 0.20546081277213352,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998513329525038,
|
|
"loss": 5.8199,
|
|
"mean_token_accuracy": 0.15319341719150542,
|
|
"num_tokens": 4685995.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.023037481307983,
|
|
"epoch": 0.2059143686502177,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998501545937066,
|
|
"loss": 5.8348,
|
|
"mean_token_accuracy": 0.14633184522390366,
|
|
"num_tokens": 4696659.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.960624837875367,
|
|
"epoch": 0.20636792452830188,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499848971584951,
|
|
"loss": 5.8072,
|
|
"mean_token_accuracy": 0.15713879466056824,
|
|
"num_tokens": 4706438.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.881855773925781,
|
|
"epoch": 0.20682148040638607,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998477839262611,
|
|
"loss": 5.8119,
|
|
"mean_token_accuracy": 0.15000793784856797,
|
|
"num_tokens": 4716402.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.990855503082275,
|
|
"epoch": 0.20727503628447025,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499846591617662,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.14913058578968047,
|
|
"num_tokens": 4728488.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.952394151687622,
|
|
"epoch": 0.20772859216255443,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998453946591779,
|
|
"loss": 5.9189,
|
|
"mean_token_accuracy": 0.1516925185918808,
|
|
"num_tokens": 4738693.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.991802835464478,
|
|
"epoch": 0.20818214804063861,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998441930508339,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.15066843181848527,
|
|
"num_tokens": 4748895.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.047665977478028,
|
|
"epoch": 0.2086357039187228,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998429867926547,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.14194059297442435,
|
|
"num_tokens": 4760135.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.035406303405762,
|
|
"epoch": 0.20908925979680695,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998417758846651,
|
|
"loss": 5.9523,
|
|
"mean_token_accuracy": 0.15069413632154466,
|
|
"num_tokens": 4769935.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.0572274684906,
|
|
"epoch": 0.20954281567489114,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998405603268903,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.14732977300882338,
|
|
"num_tokens": 4779520.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.93422679901123,
|
|
"epoch": 0.20999637155297532,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998393401193554,
|
|
"loss": 5.8067,
|
|
"mean_token_accuracy": 0.1515841841697693,
|
|
"num_tokens": 4791256.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.881869649887085,
|
|
"epoch": 0.2104499274310595,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998381152620857,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.15506275743246078,
|
|
"num_tokens": 4801334.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.885318040847778,
|
|
"epoch": 0.21090348330914369,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998368857551067,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.1555730938911438,
|
|
"num_tokens": 4811361.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.969886207580567,
|
|
"epoch": 0.21135703918722787,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998356515984433,
|
|
"loss": 5.807,
|
|
"mean_token_accuracy": 0.15263233184814454,
|
|
"num_tokens": 4821190.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.9508056640625,
|
|
"epoch": 0.21181059506531205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998344127921213,
|
|
"loss": 5.8241,
|
|
"mean_token_accuracy": 0.1541541337966919,
|
|
"num_tokens": 4830694.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.928486108779907,
|
|
"epoch": 0.21226415094339623,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998331693361666,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.1508532479405403,
|
|
"num_tokens": 4841344.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.951602220535278,
|
|
"epoch": 0.21271770682148042,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998319212306046,
|
|
"loss": 5.8021,
|
|
"mean_token_accuracy": 0.14895136952400206,
|
|
"num_tokens": 4851161.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.9326536655426025,
|
|
"epoch": 0.21317126269956457,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499830668475461,
|
|
"loss": 5.7841,
|
|
"mean_token_accuracy": 0.14950372502207757,
|
|
"num_tokens": 4860740.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.928380012512207,
|
|
"epoch": 0.21362481857764876,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499829411070762,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.15025952607393264,
|
|
"num_tokens": 4871733.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.940114498138428,
|
|
"epoch": 0.21407837445573294,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998281490165335,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.14290931671857834,
|
|
"num_tokens": 4883617.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.0039795398712155,
|
|
"epoch": 0.21453193033381712,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998268823128016,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.14657811671495438,
|
|
"num_tokens": 4894519.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.913796472549438,
|
|
"epoch": 0.2149854862119013,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998256109595923,
|
|
"loss": 5.7663,
|
|
"mean_token_accuracy": 0.15133122503757476,
|
|
"num_tokens": 4904965.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.905171871185303,
|
|
"epoch": 0.2154390420899855,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998243349569323,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.16264960318803787,
|
|
"num_tokens": 4914618.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.793045377731323,
|
|
"epoch": 0.21589259796806967,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998230543048477,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.15822856724262238,
|
|
"num_tokens": 4924341.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.860754489898682,
|
|
"epoch": 0.21634615384615385,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499821769003365,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.15276679992675782,
|
|
"num_tokens": 4934231.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.90138463973999,
|
|
"epoch": 0.21679970972423804,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998204790525109,
|
|
"loss": 5.7442,
|
|
"mean_token_accuracy": 0.15233908742666244,
|
|
"num_tokens": 4944303.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.892811250686646,
|
|
"epoch": 0.2172532656023222,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998191844523119,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.15439640134572982,
|
|
"num_tokens": 4954571.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.912092924118042,
|
|
"epoch": 0.21770682148040638,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499817885202795,
|
|
"loss": 5.7943,
|
|
"mean_token_accuracy": 0.15238530337810516,
|
|
"num_tokens": 4964418.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.960055160522461,
|
|
"epoch": 0.21816037735849056,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998165813039869,
|
|
"loss": 5.7833,
|
|
"mean_token_accuracy": 0.1479422241449356,
|
|
"num_tokens": 4975036.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.970535087585449,
|
|
"epoch": 0.21861393323657474,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998152727559145,
|
|
"loss": 5.8868,
|
|
"mean_token_accuracy": 0.14599555134773254,
|
|
"num_tokens": 4985272.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.004713773727417,
|
|
"epoch": 0.21906748911465893,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499813959558605,
|
|
"loss": 5.812,
|
|
"mean_token_accuracy": 0.15417784452438354,
|
|
"num_tokens": 4995187.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.99905571937561,
|
|
"epoch": 0.2195210449927431,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998126417120856,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.1530926562845707,
|
|
"num_tokens": 5005013.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.994871044158936,
|
|
"epoch": 0.2199746008708273,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998113192163835,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.14475401639938354,
|
|
"num_tokens": 5016789.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.921261167526245,
|
|
"epoch": 0.22042815674891147,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499809992071526,
|
|
"loss": 5.828,
|
|
"mean_token_accuracy": 0.1518557384610176,
|
|
"num_tokens": 5026913.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.9377799987792965,
|
|
"epoch": 0.22088171262699566,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998086602775406,
|
|
"loss": 5.9104,
|
|
"mean_token_accuracy": 0.14928861260414122,
|
|
"num_tokens": 5037501.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.983516836166382,
|
|
"epoch": 0.2213352685050798,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998073238344547,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.15100034326314926,
|
|
"num_tokens": 5048478.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.903777933120727,
|
|
"epoch": 0.221788824383164,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998059827422962,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.14812486618757248,
|
|
"num_tokens": 5059118.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.963100814819336,
|
|
"epoch": 0.22224238026124818,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998046370010926,
|
|
"loss": 5.7848,
|
|
"mean_token_accuracy": 0.15494603514671326,
|
|
"num_tokens": 5070180.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.880324077606201,
|
|
"epoch": 0.22269593613933236,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998032866108718,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.1510962054133415,
|
|
"num_tokens": 5079912.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.994835710525512,
|
|
"epoch": 0.22314949201741655,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998019315716618,
|
|
"loss": 5.8732,
|
|
"mean_token_accuracy": 0.15168511420488356,
|
|
"num_tokens": 5090549.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.909025812149048,
|
|
"epoch": 0.22360304789550073,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998005718834905,
|
|
"loss": 5.7193,
|
|
"mean_token_accuracy": 0.1588350161910057,
|
|
"num_tokens": 5100880.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.910657835006714,
|
|
"epoch": 0.2240566037735849,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997992075463862,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.14884106069803238,
|
|
"num_tokens": 5111796.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.975823974609375,
|
|
"epoch": 0.2245101596516691,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997978385603769,
|
|
"loss": 5.8232,
|
|
"mean_token_accuracy": 0.15248575657606125,
|
|
"num_tokens": 5123468.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.874198150634766,
|
|
"epoch": 0.22496371552975328,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997964649254911,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.15882757753133775,
|
|
"num_tokens": 5132925.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.932957172393799,
|
|
"epoch": 0.22541727140783743,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997950866417572,
|
|
"loss": 5.8278,
|
|
"mean_token_accuracy": 0.14813223630189895,
|
|
"num_tokens": 5143445.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.961171960830688,
|
|
"epoch": 0.22587082728592162,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997937037092034,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.14807531088590623,
|
|
"num_tokens": 5153176.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.9957068920135494,
|
|
"epoch": 0.2263243831640058,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997923161278587,
|
|
"loss": 5.7973,
|
|
"mean_token_accuracy": 0.15407470166683196,
|
|
"num_tokens": 5162765.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.935280895233154,
|
|
"epoch": 0.22677793904208998,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997909238977514,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.15373046398162843,
|
|
"num_tokens": 5173390.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.851876974105835,
|
|
"epoch": 0.22723149492017417,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997895270189108,
|
|
"loss": 5.7455,
|
|
"mean_token_accuracy": 0.15115862116217613,
|
|
"num_tokens": 5184212.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.847887372970581,
|
|
"epoch": 0.22768505079825835,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997881254913653,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.15100416243076326,
|
|
"num_tokens": 5194311.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.867375993728638,
|
|
"epoch": 0.22813860667634253,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997867193151441,
|
|
"loss": 5.7339,
|
|
"mean_token_accuracy": 0.15452023446559907,
|
|
"num_tokens": 5204708.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.844597864151001,
|
|
"epoch": 0.22859216255442671,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997853084902763,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.15443815141916276,
|
|
"num_tokens": 5214566.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.916435194015503,
|
|
"epoch": 0.2290457184325109,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997838930167911,
|
|
"loss": 5.7463,
|
|
"mean_token_accuracy": 0.15494998544454575,
|
|
"num_tokens": 5224762.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.9442017555236815,
|
|
"epoch": 0.22949927431059505,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997824728947176,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.15142686367034913,
|
|
"num_tokens": 5235146.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.965577602386475,
|
|
"epoch": 0.22995283018867924,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997810481240853,
|
|
"loss": 5.786,
|
|
"mean_token_accuracy": 0.1514734596014023,
|
|
"num_tokens": 5243867.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.83701639175415,
|
|
"epoch": 0.23040638606676342,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997796187049238,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.153061743080616,
|
|
"num_tokens": 5254279.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.0492133617401125,
|
|
"epoch": 0.2308599419448476,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997781846372623,
|
|
"loss": 5.7978,
|
|
"mean_token_accuracy": 0.1522805020213127,
|
|
"num_tokens": 5264769.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.893232774734497,
|
|
"epoch": 0.23131349782293179,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997767459211307,
|
|
"loss": 5.7644,
|
|
"mean_token_accuracy": 0.14629466086626053,
|
|
"num_tokens": 5274291.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.868297386169433,
|
|
"epoch": 0.23176705370101597,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997753025565587,
|
|
"loss": 5.695,
|
|
"mean_token_accuracy": 0.15659698024392127,
|
|
"num_tokens": 5284366.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.889286661148072,
|
|
"epoch": 0.23222060957910015,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997738545435763,
|
|
"loss": 5.8173,
|
|
"mean_token_accuracy": 0.15293926745653152,
|
|
"num_tokens": 5294494.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.899365377426148,
|
|
"epoch": 0.23267416545718433,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997724018822133,
|
|
"loss": 5.813,
|
|
"mean_token_accuracy": 0.15529518127441405,
|
|
"num_tokens": 5305606.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.90656361579895,
|
|
"epoch": 0.23312772133526852,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997709445724996,
|
|
"loss": 5.8101,
|
|
"mean_token_accuracy": 0.1502317950129509,
|
|
"num_tokens": 5315677.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.9617547512054445,
|
|
"epoch": 0.23358127721335267,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997694826144656,
|
|
"loss": 5.866,
|
|
"mean_token_accuracy": 0.14772987067699433,
|
|
"num_tokens": 5326453.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.8899938583374025,
|
|
"epoch": 0.23403483309143686,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997680160081414,
|
|
"loss": 5.7592,
|
|
"mean_token_accuracy": 0.1525429829955101,
|
|
"num_tokens": 5337591.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.914120006561279,
|
|
"epoch": 0.23448838896952104,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997665447535573,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.1570722669363022,
|
|
"num_tokens": 5349400.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.9674485206604,
|
|
"epoch": 0.23494194484760522,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997650688507438,
|
|
"loss": 5.7325,
|
|
"mean_token_accuracy": 0.15442833602428435,
|
|
"num_tokens": 5359984.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.855543184280395,
|
|
"epoch": 0.2353955007256894,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997635882997314,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.16013004034757614,
|
|
"num_tokens": 5369254.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.920786714553833,
|
|
"epoch": 0.2358490566037736,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997621031005507,
|
|
"loss": 5.755,
|
|
"mean_token_accuracy": 0.15076399594545364,
|
|
"num_tokens": 5379648.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.818716669082642,
|
|
"epoch": 0.23630261248185777,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997606132532325,
|
|
"loss": 5.7028,
|
|
"mean_token_accuracy": 0.16014982685446738,
|
|
"num_tokens": 5390321.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.850492286682129,
|
|
"epoch": 0.23675616835994195,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997591187578075,
|
|
"loss": 5.7541,
|
|
"mean_token_accuracy": 0.1600041940808296,
|
|
"num_tokens": 5401078.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.8976398468017575,
|
|
"epoch": 0.23720972423802614,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997576196143067,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.16146167367696762,
|
|
"num_tokens": 5411977.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.871705007553101,
|
|
"epoch": 0.2376632801161103,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499756115822761,
|
|
"loss": 5.7102,
|
|
"mean_token_accuracy": 0.15028589516878127,
|
|
"num_tokens": 5422967.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.950361585617065,
|
|
"epoch": 0.23811683599419448,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997546073832015,
|
|
"loss": 5.7474,
|
|
"mean_token_accuracy": 0.16250978112220765,
|
|
"num_tokens": 5432260.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.842865753173828,
|
|
"epoch": 0.23857039187227866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997530942956595,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.15647428780794143,
|
|
"num_tokens": 5441706.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.885302925109864,
|
|
"epoch": 0.23902394775036284,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997515765601662,
|
|
"loss": 5.7294,
|
|
"mean_token_accuracy": 0.1620200365781784,
|
|
"num_tokens": 5452397.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.802298927307129,
|
|
"epoch": 0.23947750362844702,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997500541767531,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.1544307217001915,
|
|
"num_tokens": 5463762.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.895985698699951,
|
|
"epoch": 0.2399310595065312,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997485271454516,
|
|
"loss": 5.7718,
|
|
"mean_token_accuracy": 0.14597637057304383,
|
|
"num_tokens": 5474622.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.872747230529785,
|
|
"epoch": 0.2403846153846154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997469954662933,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.15389883369207383,
|
|
"num_tokens": 5484697.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.795325708389282,
|
|
"epoch": 0.24083817126269957,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997454591393097,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.15505960136651992,
|
|
"num_tokens": 5496433.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.929238319396973,
|
|
"epoch": 0.24129172714078376,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997439181645329,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.14926385432481765,
|
|
"num_tokens": 5507917.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.066269302368164,
|
|
"epoch": 0.2417452830188679,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997423725419945,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.15168920159339905,
|
|
"num_tokens": 5519159.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.896298265457153,
|
|
"epoch": 0.2421988388969521,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997408222717267,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.15869408696889878,
|
|
"num_tokens": 5529180.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.829392433166504,
|
|
"epoch": 0.24265239477503628,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997392673537612,
|
|
"loss": 5.7138,
|
|
"mean_token_accuracy": 0.1638789251446724,
|
|
"num_tokens": 5539363.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.891768503189087,
|
|
"epoch": 0.24310595065312046,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997377077881306,
|
|
"loss": 5.8155,
|
|
"mean_token_accuracy": 0.15023489147424698,
|
|
"num_tokens": 5549841.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.889240789413452,
|
|
"epoch": 0.24355950653120464,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997361435748668,
|
|
"loss": 5.6947,
|
|
"mean_token_accuracy": 0.16268197000026702,
|
|
"num_tokens": 5560299.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.9125152111053465,
|
|
"epoch": 0.24401306240928883,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997345747140024,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.15359243452548982,
|
|
"num_tokens": 5571081.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.8776861190795895,
|
|
"epoch": 0.244466618287373,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997330012055695,
|
|
"loss": 5.7108,
|
|
"mean_token_accuracy": 0.15765073597431184,
|
|
"num_tokens": 5581389.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.861866426467896,
|
|
"epoch": 0.2449201741654572,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997314230496011,
|
|
"loss": 5.754,
|
|
"mean_token_accuracy": 0.1500275418162346,
|
|
"num_tokens": 5592347.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.839778137207031,
|
|
"epoch": 0.24537373004354138,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997298402461296,
|
|
"loss": 5.7228,
|
|
"mean_token_accuracy": 0.15842826217412947,
|
|
"num_tokens": 5603411.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.9260224342346195,
|
|
"epoch": 0.24582728592162553,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997282527951876,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.15986051708459853,
|
|
"num_tokens": 5614615.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.790437936782837,
|
|
"epoch": 0.24628084179970972,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997266606968081,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.1561066210269928,
|
|
"num_tokens": 5624582.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.811624383926391,
|
|
"epoch": 0.2467343976777939,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997250639510241,
|
|
"loss": 5.7,
|
|
"mean_token_accuracy": 0.15437885671854018,
|
|
"num_tokens": 5634310.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.889466571807861,
|
|
"epoch": 0.24718795355587808,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997234625578684,
|
|
"loss": 5.7947,
|
|
"mean_token_accuracy": 0.14918309599161148,
|
|
"num_tokens": 5644018.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.858435821533203,
|
|
"epoch": 0.24764150943396226,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997218565173742,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.15628414005041122,
|
|
"num_tokens": 5653592.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.904895401000976,
|
|
"epoch": 0.24809506531204645,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997202458295748,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.15781814455986024,
|
|
"num_tokens": 5662812.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.902950763702393,
|
|
"epoch": 0.24854862119013063,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997186304945034,
|
|
"loss": 5.7511,
|
|
"mean_token_accuracy": 0.15532326996326445,
|
|
"num_tokens": 5672939.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.827338409423828,
|
|
"epoch": 0.24900217706821481,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997170105121935,
|
|
"loss": 5.7313,
|
|
"mean_token_accuracy": 0.15588268786668777,
|
|
"num_tokens": 5683350.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.919451379776001,
|
|
"epoch": 0.249455732946299,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997153858826786,
|
|
"loss": 5.816,
|
|
"mean_token_accuracy": 0.14666671603918074,
|
|
"num_tokens": 5694516.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.843132162094117,
|
|
"epoch": 0.24990928882438315,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997137566059922,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.15954998284578323,
|
|
"num_tokens": 5705443.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.838101053237915,
|
|
"epoch": 0.25036284470246734,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997121226821681,
|
|
"loss": 5.742,
|
|
"mean_token_accuracy": 0.15265777483582496,
|
|
"num_tokens": 5715933.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.910187196731568,
|
|
"epoch": 0.25081640058055155,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049971048411124,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.1447537824511528,
|
|
"num_tokens": 5726630.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.9618613719940186,
|
|
"epoch": 0.2512699564586357,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997088408932418,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.15529899746179582,
|
|
"num_tokens": 5736890.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.754767274856567,
|
|
"epoch": 0.25172351233671986,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997071930282076,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.16765589267015457,
|
|
"num_tokens": 5747042.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.836727952957153,
|
|
"epoch": 0.25217706821480407,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997055405161712,
|
|
"loss": 5.7737,
|
|
"mean_token_accuracy": 0.15657578855752946,
|
|
"num_tokens": 5757367.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.892507696151734,
|
|
"epoch": 0.2526306240928882,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997038833571671,
|
|
"loss": 5.8198,
|
|
"mean_token_accuracy": 0.15040036141872407,
|
|
"num_tokens": 5769557.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.882242345809937,
|
|
"epoch": 0.25308417997097243,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997022215512295,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.162361441552639,
|
|
"num_tokens": 5780615.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.901854085922241,
|
|
"epoch": 0.2535377358490566,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997005550983925,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.1581372618675232,
|
|
"num_tokens": 5791271.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.816129541397094,
|
|
"epoch": 0.2539912917271408,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499698883998691,
|
|
"loss": 5.6376,
|
|
"mean_token_accuracy": 0.15995124131441116,
|
|
"num_tokens": 5801117.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.778412342071533,
|
|
"epoch": 0.25444484760522496,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996972082521591,
|
|
"loss": 5.6657,
|
|
"mean_token_accuracy": 0.16171006560325624,
|
|
"num_tokens": 5811696.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.8469995021820065,
|
|
"epoch": 0.25489840348330917,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996955278588319,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.16263554394245147,
|
|
"num_tokens": 5822207.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.802956390380859,
|
|
"epoch": 0.2553519593613933,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996938428187437,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.1667325183749199,
|
|
"num_tokens": 5831927.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.801891422271728,
|
|
"epoch": 0.2558055152394775,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996921531319297,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.15510134547948837,
|
|
"num_tokens": 5842093.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.818565034866333,
|
|
"epoch": 0.2562590711175617,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996904587984246,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.16608070433139802,
|
|
"num_tokens": 5850551.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.797169351577759,
|
|
"epoch": 0.25671262699564584,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996887598182636,
|
|
"loss": 5.6412,
|
|
"mean_token_accuracy": 0.1570335805416107,
|
|
"num_tokens": 5860651.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.70640926361084,
|
|
"epoch": 0.25716618287373005,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996870561914819,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.1594139203429222,
|
|
"num_tokens": 5871500.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.810226488113403,
|
|
"epoch": 0.2576197387518142,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996853479181145,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.15245891511440277,
|
|
"num_tokens": 5881523.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.9306385040283205,
|
|
"epoch": 0.2580732946298984,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996836349981969,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.1541695550084114,
|
|
"num_tokens": 5891162.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.793090677261352,
|
|
"epoch": 0.2585268505079826,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996819174317645,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.15518372505903244,
|
|
"num_tokens": 5901818.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.8290753841400145,
|
|
"epoch": 0.2589804063860668,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996801952188528,
|
|
"loss": 5.7439,
|
|
"mean_token_accuracy": 0.15479833632707596,
|
|
"num_tokens": 5913889.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.848030471801758,
|
|
"epoch": 0.25943396226415094,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996784683594973,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.16026207208633422,
|
|
"num_tokens": 5923429.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.953624963760376,
|
|
"epoch": 0.2598875181422351,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996767368537338,
|
|
"loss": 5.7536,
|
|
"mean_token_accuracy": 0.15464293360710143,
|
|
"num_tokens": 5933847.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.797641706466675,
|
|
"epoch": 0.2603410740203193,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996750007015983,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.15784441232681273,
|
|
"num_tokens": 5943874.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.836393356323242,
|
|
"epoch": 0.26079462989840346,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996732599031264,
|
|
"loss": 5.6901,
|
|
"mean_token_accuracy": 0.15797710716724395,
|
|
"num_tokens": 5953653.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.831515836715698,
|
|
"epoch": 0.2612481857764877,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996715144583543,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.16178645938634872,
|
|
"num_tokens": 5964039.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.8883569717407225,
|
|
"epoch": 0.26170174165457183,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499669764367318,
|
|
"loss": 5.7538,
|
|
"mean_token_accuracy": 0.15600325912237167,
|
|
"num_tokens": 5974083.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.775406360626221,
|
|
"epoch": 0.26215529753265604,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996680096300537,
|
|
"loss": 5.711,
|
|
"mean_token_accuracy": 0.15503483414649963,
|
|
"num_tokens": 5984629.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.7855353355407715,
|
|
"epoch": 0.2626088534107402,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996662502465978,
|
|
"loss": 5.6067,
|
|
"mean_token_accuracy": 0.1710730493068695,
|
|
"num_tokens": 5994295.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.8054187297821045,
|
|
"epoch": 0.2630624092888244,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996644862169864,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.15672381818294526,
|
|
"num_tokens": 6004156.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.815729665756225,
|
|
"epoch": 0.26351596516690856,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996627175412563,
|
|
"loss": 5.7391,
|
|
"mean_token_accuracy": 0.16197800040245056,
|
|
"num_tokens": 6014188.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.904583549499511,
|
|
"epoch": 0.2639695210449927,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499660944219444,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.15212338119745256,
|
|
"num_tokens": 6024879.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.926459264755249,
|
|
"epoch": 0.2644230769230769,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996591662515861,
|
|
"loss": 5.8701,
|
|
"mean_token_accuracy": 0.15266856625676156,
|
|
"num_tokens": 6036374.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.832221269607544,
|
|
"epoch": 0.2648766328011611,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996573836377193,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.15986677557229995,
|
|
"num_tokens": 6046432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.8731166362762455,
|
|
"epoch": 0.2653301886792453,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996555963778806,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.15033943355083465,
|
|
"num_tokens": 6056864.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.9467894554138185,
|
|
"epoch": 0.26578374455732945,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499653804472107,
|
|
"loss": 5.7396,
|
|
"mean_token_accuracy": 0.1595652773976326,
|
|
"num_tokens": 6067294.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.863904571533203,
|
|
"epoch": 0.26623730043541366,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996520079204353,
|
|
"loss": 5.741,
|
|
"mean_token_accuracy": 0.15215880274772645,
|
|
"num_tokens": 6077587.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.880077457427978,
|
|
"epoch": 0.2666908563134978,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499650206722903,
|
|
"loss": 5.6892,
|
|
"mean_token_accuracy": 0.1558769851922989,
|
|
"num_tokens": 6089306.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.7567362785339355,
|
|
"epoch": 0.267144412191582,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996484008795471,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.15309089198708534,
|
|
"num_tokens": 6099651.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.811124467849732,
|
|
"epoch": 0.2675979680696662,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499646590390405,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.1572161540389061,
|
|
"num_tokens": 6110063.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.807859134674072,
|
|
"epoch": 0.26805152394775034,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996447752555142,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.15904018133878708,
|
|
"num_tokens": 6120031.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.8083930015563965,
|
|
"epoch": 0.26850507982583455,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996429554749122,
|
|
"loss": 5.7183,
|
|
"mean_token_accuracy": 0.15861095041036605,
|
|
"num_tokens": 6131274.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.888201808929443,
|
|
"epoch": 0.2689586357039187,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996411310486367,
|
|
"loss": 5.7658,
|
|
"mean_token_accuracy": 0.15850751847028732,
|
|
"num_tokens": 6140878.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.859344720840454,
|
|
"epoch": 0.2694121915820029,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996393019767253,
|
|
"loss": 5.7646,
|
|
"mean_token_accuracy": 0.1520871713757515,
|
|
"num_tokens": 6152229.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.737780809402466,
|
|
"epoch": 0.26986574746008707,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996374682592158,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.15743956118822097,
|
|
"num_tokens": 6162311.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.8878035068511965,
|
|
"epoch": 0.2703193033381713,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996356298961463,
|
|
"loss": 5.7654,
|
|
"mean_token_accuracy": 0.15596626251935958,
|
|
"num_tokens": 6172806.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.860615348815918,
|
|
"epoch": 0.27077285921625543,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996337868875549,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.1540456607937813,
|
|
"num_tokens": 6183479.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.865048408508301,
|
|
"epoch": 0.27122641509433965,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996319392334792,
|
|
"loss": 5.7043,
|
|
"mean_token_accuracy": 0.15600668787956237,
|
|
"num_tokens": 6194201.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.800745820999145,
|
|
"epoch": 0.2716799709724238,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499630086933958,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.1544359117746353,
|
|
"num_tokens": 6204774.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.796499633789063,
|
|
"epoch": 0.27213352685050796,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996282299890292,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.15237775593996047,
|
|
"num_tokens": 6215056.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.27213352685050796,
|
|
"eval_entropy": 5.64969411068912,
|
|
"eval_loss": 5.721183776855469,
|
|
"eval_mean_token_accuracy": 0.16399123540223992,
|
|
"eval_num_tokens": 6215056.0,
|
|
"eval_runtime": 20.9259,
|
|
"eval_samples_per_second": 1689.772,
|
|
"eval_steps_per_second": 211.221,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 110230,
|
|
"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": 1338598636093440.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|