ffa3d0ff90
Model: fpadovani/dan-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
24079 lines
660 KiB
JSON
24079 lines
660 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.0023387905111927,
|
|
"eval_steps": 3000,
|
|
"global_step": 12000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 6.7180821895599365,
|
|
"epoch": 0.000417641162712997,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.5123,
|
|
"mean_token_accuracy": 0.10666800066828727,
|
|
"num_tokens": 9371.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 6.808059024810791,
|
|
"epoch": 0.000835282325425994,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.5956,
|
|
"mean_token_accuracy": 0.10533942952752114,
|
|
"num_tokens": 18155.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 6.759247636795044,
|
|
"epoch": 0.001252923488138991,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.5801,
|
|
"mean_token_accuracy": 0.10018297508358956,
|
|
"num_tokens": 27776.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 6.797110748291016,
|
|
"epoch": 0.001670564650851988,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.5797,
|
|
"mean_token_accuracy": 0.10600945577025414,
|
|
"num_tokens": 37166.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.759796857833862,
|
|
"epoch": 0.002088205813564985,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.5305,
|
|
"mean_token_accuracy": 0.11286764591932297,
|
|
"num_tokens": 46667.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 6.808503246307373,
|
|
"epoch": 0.002505846976277982,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.5297,
|
|
"mean_token_accuracy": 0.10954836457967758,
|
|
"num_tokens": 55738.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.905849361419678,
|
|
"epoch": 0.002923488138990979,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.6363,
|
|
"mean_token_accuracy": 0.10485906973481178,
|
|
"num_tokens": 65303.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 6.810987138748169,
|
|
"epoch": 0.003341129301703976,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.4128,
|
|
"mean_token_accuracy": 0.11579142212867737,
|
|
"num_tokens": 74876.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 6.819403839111328,
|
|
"epoch": 0.003758770464416973,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.5539,
|
|
"mean_token_accuracy": 0.11837585121393204,
|
|
"num_tokens": 84683.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 6.842317581176758,
|
|
"epoch": 0.00417641162712997,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.5476,
|
|
"mean_token_accuracy": 0.1076658695936203,
|
|
"num_tokens": 94511.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 6.806653213500977,
|
|
"epoch": 0.004594052789842967,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.529,
|
|
"mean_token_accuracy": 0.12048889845609664,
|
|
"num_tokens": 103820.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 6.758758592605591,
|
|
"epoch": 0.005011693952555964,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.5035,
|
|
"mean_token_accuracy": 0.1163383036851883,
|
|
"num_tokens": 112398.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 6.7997699737548825,
|
|
"epoch": 0.005429335115268961,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.119983372092247,
|
|
"num_tokens": 121167.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 6.826302528381348,
|
|
"epoch": 0.005846976277981958,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.4857,
|
|
"mean_token_accuracy": 0.11032287627458573,
|
|
"num_tokens": 129399.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 6.845746660232544,
|
|
"epoch": 0.006264617440694955,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.4687,
|
|
"mean_token_accuracy": 0.1163133703172207,
|
|
"num_tokens": 138512.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 6.800804281234742,
|
|
"epoch": 0.006682258603407952,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.5206,
|
|
"mean_token_accuracy": 0.10875637605786323,
|
|
"num_tokens": 147712.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 6.811766719818115,
|
|
"epoch": 0.007099899766120949,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.4852,
|
|
"mean_token_accuracy": 0.1177453450858593,
|
|
"num_tokens": 156759.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 6.773466730117798,
|
|
"epoch": 0.007517540928833946,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.533,
|
|
"mean_token_accuracy": 0.11238256990909576,
|
|
"num_tokens": 166395.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 6.842059373855591,
|
|
"epoch": 0.007935182091546943,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.4534,
|
|
"mean_token_accuracy": 0.11896919012069702,
|
|
"num_tokens": 174739.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 6.710035228729248,
|
|
"epoch": 0.00835282325425994,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.12140651717782021,
|
|
"num_tokens": 183010.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 6.729191780090332,
|
|
"epoch": 0.008770464416972937,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.5163,
|
|
"mean_token_accuracy": 0.11011387556791305,
|
|
"num_tokens": 192589.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 6.83894910812378,
|
|
"epoch": 0.009188105579685933,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.45,
|
|
"mean_token_accuracy": 0.11901598572731018,
|
|
"num_tokens": 201638.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 6.744243049621582,
|
|
"epoch": 0.00960574674239893,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.12338117063045502,
|
|
"num_tokens": 209862.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 6.756110143661499,
|
|
"epoch": 0.010023387905111928,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.11191049665212631,
|
|
"num_tokens": 218897.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 6.908449125289917,
|
|
"epoch": 0.010441029067824925,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.5859,
|
|
"mean_token_accuracy": 0.11279568374156952,
|
|
"num_tokens": 227682.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 6.8623613834381105,
|
|
"epoch": 0.010858670230537921,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.4542,
|
|
"mean_token_accuracy": 0.11863475143909455,
|
|
"num_tokens": 236170.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 6.790626573562622,
|
|
"epoch": 0.011276311393250919,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.5522,
|
|
"mean_token_accuracy": 0.11070087552070618,
|
|
"num_tokens": 245710.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 6.78648738861084,
|
|
"epoch": 0.011693952555963916,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.5029,
|
|
"mean_token_accuracy": 0.11403205692768097,
|
|
"num_tokens": 254751.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 6.7859738826751705,
|
|
"epoch": 0.012111593718676913,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.433,
|
|
"mean_token_accuracy": 0.1188641369342804,
|
|
"num_tokens": 264210.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 6.8096400737762455,
|
|
"epoch": 0.01252923488138991,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.4861,
|
|
"mean_token_accuracy": 0.12114087268710136,
|
|
"num_tokens": 272944.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 6.791913175582886,
|
|
"epoch": 0.012946876044102907,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.12244183719158172,
|
|
"num_tokens": 281311.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 6.694759273529053,
|
|
"epoch": 0.013364517206815904,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.3769,
|
|
"mean_token_accuracy": 0.12260683327913284,
|
|
"num_tokens": 289701.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 6.748257827758789,
|
|
"epoch": 0.013782158369528901,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.5215,
|
|
"mean_token_accuracy": 0.1143926203250885,
|
|
"num_tokens": 299459.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 6.883009147644043,
|
|
"epoch": 0.014199799532241897,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.5421,
|
|
"mean_token_accuracy": 0.11752694174647331,
|
|
"num_tokens": 309343.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 6.830853223800659,
|
|
"epoch": 0.014617440694954895,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.5302,
|
|
"mean_token_accuracy": 0.11090763658285141,
|
|
"num_tokens": 318840.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 6.675867223739624,
|
|
"epoch": 0.015035081857667892,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.3784,
|
|
"mean_token_accuracy": 0.11448234245181084,
|
|
"num_tokens": 328689.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 6.797796392440796,
|
|
"epoch": 0.01545272302038089,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.4889,
|
|
"mean_token_accuracy": 0.11072958707809448,
|
|
"num_tokens": 338209.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 6.7780595302581785,
|
|
"epoch": 0.015870364183093885,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.417,
|
|
"mean_token_accuracy": 0.11931143030524254,
|
|
"num_tokens": 347270.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 6.799556255340576,
|
|
"epoch": 0.016288005345806884,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.4735,
|
|
"mean_token_accuracy": 0.11163464188575745,
|
|
"num_tokens": 356366.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 6.763126516342163,
|
|
"epoch": 0.01670564650851988,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.11596830189228058,
|
|
"num_tokens": 365980.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 6.702800369262695,
|
|
"epoch": 0.017123287671232876,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.3882,
|
|
"mean_token_accuracy": 0.11993374973535538,
|
|
"num_tokens": 374591.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 6.849011707305908,
|
|
"epoch": 0.017540928833945875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.4294,
|
|
"mean_token_accuracy": 0.11508302688598633,
|
|
"num_tokens": 383250.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 6.693080568313599,
|
|
"epoch": 0.01795856999665887,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.11563051715493203,
|
|
"num_tokens": 391502.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.630117034912109,
|
|
"epoch": 0.018376211159371866,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.11645801290869713,
|
|
"num_tokens": 400225.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 6.8181227684021,
|
|
"epoch": 0.018793852322084866,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.4937,
|
|
"mean_token_accuracy": 0.1128729097545147,
|
|
"num_tokens": 410008.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 6.736743688583374,
|
|
"epoch": 0.01921149348479786,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.4332,
|
|
"mean_token_accuracy": 0.11869536191225052,
|
|
"num_tokens": 418979.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 6.718912887573242,
|
|
"epoch": 0.01962913464751086,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.11591459438204765,
|
|
"num_tokens": 428139.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 6.7471612930297855,
|
|
"epoch": 0.020046775810223856,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.12110752388834953,
|
|
"num_tokens": 437113.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.818037843704223,
|
|
"epoch": 0.020464416972936852,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.6019,
|
|
"mean_token_accuracy": 0.11445037350058555,
|
|
"num_tokens": 446879.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 6.695638751983642,
|
|
"epoch": 0.02088205813564985,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.5041,
|
|
"mean_token_accuracy": 0.11364466175436974,
|
|
"num_tokens": 456362.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 6.799724435806274,
|
|
"epoch": 0.021299699298362847,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.12356706708669662,
|
|
"num_tokens": 464930.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.682189035415649,
|
|
"epoch": 0.021717340461075842,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.469,
|
|
"mean_token_accuracy": 0.11262325197458267,
|
|
"num_tokens": 474303.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 6.784652948379517,
|
|
"epoch": 0.02213498162378884,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.4998,
|
|
"mean_token_accuracy": 0.11313469260931015,
|
|
"num_tokens": 483750.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 6.743142223358154,
|
|
"epoch": 0.022552622786501837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.3944,
|
|
"mean_token_accuracy": 0.1151240773499012,
|
|
"num_tokens": 493325.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 6.729674768447876,
|
|
"epoch": 0.022970263949214833,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.4083,
|
|
"mean_token_accuracy": 0.11122140809893608,
|
|
"num_tokens": 501907.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.695761060714721,
|
|
"epoch": 0.023387905111927832,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.4871,
|
|
"mean_token_accuracy": 0.11502960547804833,
|
|
"num_tokens": 511522.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 6.770887994766236,
|
|
"epoch": 0.023805546274640828,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.4136,
|
|
"mean_token_accuracy": 0.1140117235481739,
|
|
"num_tokens": 521287.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 6.772694158554077,
|
|
"epoch": 0.024223187437353827,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.5268,
|
|
"mean_token_accuracy": 0.10702815651893616,
|
|
"num_tokens": 530631.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.726316118240357,
|
|
"epoch": 0.024640828600066823,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.12561146542429924,
|
|
"num_tokens": 540386.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.716358995437622,
|
|
"epoch": 0.02505846976277982,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.11597420573234558,
|
|
"num_tokens": 550121.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.649577903747558,
|
|
"epoch": 0.025476110925492818,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.3557,
|
|
"mean_token_accuracy": 0.11343038976192474,
|
|
"num_tokens": 559460.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 6.724728441238403,
|
|
"epoch": 0.025893752088205813,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.12006132379174232,
|
|
"num_tokens": 568392.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.653720140457153,
|
|
"epoch": 0.02631139325091881,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.11691968142986298,
|
|
"num_tokens": 578248.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.7646496295928955,
|
|
"epoch": 0.026729034413631808,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.4952,
|
|
"mean_token_accuracy": 0.11188015565276146,
|
|
"num_tokens": 588164.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.729947662353515,
|
|
"epoch": 0.027146675576344804,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.4382,
|
|
"mean_token_accuracy": 0.11248505786061287,
|
|
"num_tokens": 598715.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 6.6656099319458,
|
|
"epoch": 0.027564316739057803,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.3299,
|
|
"mean_token_accuracy": 0.11870421469211578,
|
|
"num_tokens": 606939.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.688929510116577,
|
|
"epoch": 0.0279819579017708,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.4408,
|
|
"mean_token_accuracy": 0.12059589847922325,
|
|
"num_tokens": 615803.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.677912378311158,
|
|
"epoch": 0.028399599064483794,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.3016,
|
|
"mean_token_accuracy": 0.1152017168700695,
|
|
"num_tokens": 624730.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.668429660797119,
|
|
"epoch": 0.028817240227196794,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.11559123620390892,
|
|
"num_tokens": 634082.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 6.710170698165894,
|
|
"epoch": 0.02923488138990979,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.11764291599392891,
|
|
"num_tokens": 643367.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.57072377204895,
|
|
"epoch": 0.029652522552622785,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.12115906029939652,
|
|
"num_tokens": 651861.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.699751520156861,
|
|
"epoch": 0.030070163715335784,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.383,
|
|
"mean_token_accuracy": 0.11497076004743575,
|
|
"num_tokens": 661064.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.6671435832977295,
|
|
"epoch": 0.03048780487804878,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.3574,
|
|
"mean_token_accuracy": 0.12420301362872124,
|
|
"num_tokens": 669299.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.628156757354736,
|
|
"epoch": 0.03090544604076178,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.4516,
|
|
"mean_token_accuracy": 0.11220049262046813,
|
|
"num_tokens": 678631.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.7193104267120365,
|
|
"epoch": 0.03132308720347477,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.1158321812748909,
|
|
"num_tokens": 688511.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.703116130828858,
|
|
"epoch": 0.03174072836618777,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.3797,
|
|
"mean_token_accuracy": 0.11359225586056709,
|
|
"num_tokens": 697956.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.668367481231689,
|
|
"epoch": 0.03215836952890077,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.12736818715929984,
|
|
"num_tokens": 706779.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.554675436019897,
|
|
"epoch": 0.03257601069161377,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.11831648498773575,
|
|
"num_tokens": 715749.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.59646201133728,
|
|
"epoch": 0.03299365185432676,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.2781,
|
|
"mean_token_accuracy": 0.11623693332076072,
|
|
"num_tokens": 724756.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.562495231628418,
|
|
"epoch": 0.03341129301703976,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.3001,
|
|
"mean_token_accuracy": 0.1243792787194252,
|
|
"num_tokens": 733288.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.739299392700195,
|
|
"epoch": 0.03382893417975276,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.4209,
|
|
"mean_token_accuracy": 0.1129365734755993,
|
|
"num_tokens": 741629.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.62856707572937,
|
|
"epoch": 0.03424657534246575,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.3605,
|
|
"mean_token_accuracy": 0.12043223157525063,
|
|
"num_tokens": 751336.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.780359745025635,
|
|
"epoch": 0.03466421650517875,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.4408,
|
|
"mean_token_accuracy": 0.11233260035514832,
|
|
"num_tokens": 759725.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.7300169467926025,
|
|
"epoch": 0.03508185766789175,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.4676,
|
|
"mean_token_accuracy": 0.11555668562650681,
|
|
"num_tokens": 769752.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.61152400970459,
|
|
"epoch": 0.03549949883060474,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.3419,
|
|
"mean_token_accuracy": 0.12118100821971893,
|
|
"num_tokens": 779124.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.572236108779907,
|
|
"epoch": 0.03591713999331774,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.3142,
|
|
"mean_token_accuracy": 0.11852151229977607,
|
|
"num_tokens": 788892.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.499159049987793,
|
|
"epoch": 0.03633478115603074,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.2789,
|
|
"mean_token_accuracy": 0.12280359491705894,
|
|
"num_tokens": 798265.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.5266131401062015,
|
|
"epoch": 0.03675242231874373,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.12434489950537682,
|
|
"num_tokens": 806896.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.646367168426513,
|
|
"epoch": 0.03717006348145673,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.1231755070388317,
|
|
"num_tokens": 815540.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.595507431030273,
|
|
"epoch": 0.03758770464416973,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.11604066267609596,
|
|
"num_tokens": 824555.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.659368467330933,
|
|
"epoch": 0.03800534580688272,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.429,
|
|
"mean_token_accuracy": 0.11681790426373481,
|
|
"num_tokens": 833414.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.521911573410034,
|
|
"epoch": 0.03842298696959572,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.2667,
|
|
"mean_token_accuracy": 0.1260523058474064,
|
|
"num_tokens": 842644.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.635482358932495,
|
|
"epoch": 0.03884062813230872,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.3016,
|
|
"mean_token_accuracy": 0.11958117336034775,
|
|
"num_tokens": 851786.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.533578109741211,
|
|
"epoch": 0.03925826929502172,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.378,
|
|
"mean_token_accuracy": 0.11788101494312286,
|
|
"num_tokens": 861508.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.512241077423096,
|
|
"epoch": 0.03967591045773471,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.24,
|
|
"mean_token_accuracy": 0.1280357524752617,
|
|
"num_tokens": 870433.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.659976148605347,
|
|
"epoch": 0.04009355162044771,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.12422682046890259,
|
|
"num_tokens": 879059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.637609958648682,
|
|
"epoch": 0.04051119278316071,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.3906,
|
|
"mean_token_accuracy": 0.11781356558203697,
|
|
"num_tokens": 888009.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.5305976390838625,
|
|
"epoch": 0.040928833945873704,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.11897468864917755,
|
|
"num_tokens": 897335.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.650092506408692,
|
|
"epoch": 0.0413464751085867,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.12942158281803132,
|
|
"num_tokens": 905802.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.505962324142456,
|
|
"epoch": 0.0417641162712997,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.2894,
|
|
"mean_token_accuracy": 0.1238292008638382,
|
|
"num_tokens": 914836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.481074333190918,
|
|
"epoch": 0.042181757434012694,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.2294,
|
|
"mean_token_accuracy": 0.12505172789096833,
|
|
"num_tokens": 924254.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.538729810714722,
|
|
"epoch": 0.04259939859672569,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.343,
|
|
"mean_token_accuracy": 0.12079363018274307,
|
|
"num_tokens": 933841.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.602547264099121,
|
|
"epoch": 0.04301703975943869,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.3927,
|
|
"mean_token_accuracy": 0.11534046903252601,
|
|
"num_tokens": 943304.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.526961374282837,
|
|
"epoch": 0.043434680922151685,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.12119961977005005,
|
|
"num_tokens": 952915.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.538762998580933,
|
|
"epoch": 0.043852322084864684,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.12450704649090767,
|
|
"num_tokens": 962752.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.56287579536438,
|
|
"epoch": 0.04426996324757768,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.309,
|
|
"mean_token_accuracy": 0.1171677753329277,
|
|
"num_tokens": 971240.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.575090742111206,
|
|
"epoch": 0.044687604410290675,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.3548,
|
|
"mean_token_accuracy": 0.11371841728687286,
|
|
"num_tokens": 981391.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.543639373779297,
|
|
"epoch": 0.045105245573003674,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.12311091870069504,
|
|
"num_tokens": 990551.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.53157148361206,
|
|
"epoch": 0.045522886735716674,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.2798,
|
|
"mean_token_accuracy": 0.12509959563612938,
|
|
"num_tokens": 999593.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.54977445602417,
|
|
"epoch": 0.045940527898429666,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.3563,
|
|
"mean_token_accuracy": 0.11864383593201637,
|
|
"num_tokens": 1008785.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.53155255317688,
|
|
"epoch": 0.046358169061142665,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.12224255055189133,
|
|
"num_tokens": 1016815.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.564304971694947,
|
|
"epoch": 0.046775810223855664,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.2135,
|
|
"mean_token_accuracy": 0.13047643452882768,
|
|
"num_tokens": 1026182.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.417008876800537,
|
|
"epoch": 0.04719345138656866,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.1538,
|
|
"mean_token_accuracy": 0.1273562304675579,
|
|
"num_tokens": 1034032.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.540080308914185,
|
|
"epoch": 0.047611092549281656,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.3695,
|
|
"mean_token_accuracy": 0.12380489185452462,
|
|
"num_tokens": 1043493.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.542786312103272,
|
|
"epoch": 0.048028733711994655,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.12197929993271828,
|
|
"num_tokens": 1052989.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.446332406997681,
|
|
"epoch": 0.048446374874707654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.2418,
|
|
"mean_token_accuracy": 0.12374974638223649,
|
|
"num_tokens": 1061803.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.586713171005249,
|
|
"epoch": 0.048864016037420646,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.12280836850404739,
|
|
"num_tokens": 1071227.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.523447036743164,
|
|
"epoch": 0.049281657200133645,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.3889,
|
|
"mean_token_accuracy": 0.12325869053602219,
|
|
"num_tokens": 1080082.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.480297422409057,
|
|
"epoch": 0.049699298362846644,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.12905326038599013,
|
|
"num_tokens": 1089750.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.378500175476074,
|
|
"epoch": 0.05011693952555964,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.2089,
|
|
"mean_token_accuracy": 0.12159204185009002,
|
|
"num_tokens": 1098691.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.468329238891601,
|
|
"epoch": 0.050534580688272636,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.2107,
|
|
"mean_token_accuracy": 0.1222094714641571,
|
|
"num_tokens": 1107602.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.37498927116394,
|
|
"epoch": 0.050952221850985635,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.1582,
|
|
"mean_token_accuracy": 0.12626441866159438,
|
|
"num_tokens": 1116426.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.563107347488403,
|
|
"epoch": 0.05136986301369863,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.3579,
|
|
"mean_token_accuracy": 0.12089578509330749,
|
|
"num_tokens": 1126221.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.436634206771851,
|
|
"epoch": 0.051787504176411626,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.2162,
|
|
"mean_token_accuracy": 0.13165414333343506,
|
|
"num_tokens": 1135662.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.47764105796814,
|
|
"epoch": 0.052205145339124626,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.1241353303194046,
|
|
"num_tokens": 1143963.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.503053283691406,
|
|
"epoch": 0.05262278650183762,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.2121,
|
|
"mean_token_accuracy": 0.12860342785716056,
|
|
"num_tokens": 1152470.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.398306846618652,
|
|
"epoch": 0.05304042766455062,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.12845860794186592,
|
|
"num_tokens": 1161257.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.530808067321777,
|
|
"epoch": 0.053458068827263616,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.3039,
|
|
"mean_token_accuracy": 0.12109335586428642,
|
|
"num_tokens": 1170969.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.558892440795899,
|
|
"epoch": 0.053875709989976615,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4402,
|
|
"mean_token_accuracy": 0.12084705233573914,
|
|
"num_tokens": 1181127.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.407193994522094,
|
|
"epoch": 0.05429335115268961,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.2425,
|
|
"mean_token_accuracy": 0.12455282807350158,
|
|
"num_tokens": 1190260.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.455674695968628,
|
|
"epoch": 0.05471099231540261,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.316,
|
|
"mean_token_accuracy": 0.12325879707932472,
|
|
"num_tokens": 1200013.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.5374016761779785,
|
|
"epoch": 0.055128633478115606,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.13025743141770363,
|
|
"num_tokens": 1209239.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.347896671295166,
|
|
"epoch": 0.0555462746408286,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.1814,
|
|
"mean_token_accuracy": 0.12614438980817794,
|
|
"num_tokens": 1218552.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.401571559906006,
|
|
"epoch": 0.0559639158035416,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.2656,
|
|
"mean_token_accuracy": 0.12373785302042961,
|
|
"num_tokens": 1227632.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.45081524848938,
|
|
"epoch": 0.056381556966254597,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.2906,
|
|
"mean_token_accuracy": 0.12531701177358628,
|
|
"num_tokens": 1236433.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.433235931396484,
|
|
"epoch": 0.05679919812896759,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.11682864874601365,
|
|
"num_tokens": 1245700.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.424199199676513,
|
|
"epoch": 0.05721683929168059,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.1626,
|
|
"mean_token_accuracy": 0.12845946177840234,
|
|
"num_tokens": 1254206.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.392566871643067,
|
|
"epoch": 0.05763448045439359,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.2238,
|
|
"mean_token_accuracy": 0.12663000896573068,
|
|
"num_tokens": 1263302.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.433683109283447,
|
|
"epoch": 0.05805212161710658,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.261,
|
|
"mean_token_accuracy": 0.12566009759902955,
|
|
"num_tokens": 1272998.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.42986831665039,
|
|
"epoch": 0.05846976277981958,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.2316,
|
|
"mean_token_accuracy": 0.12945592105388642,
|
|
"num_tokens": 1281955.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.384770917892456,
|
|
"epoch": 0.05888740394253258,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.1220188558101654,
|
|
"num_tokens": 1291219.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.439512538909912,
|
|
"epoch": 0.05930504510524557,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.11803281754255295,
|
|
"num_tokens": 1300963.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.434574270248413,
|
|
"epoch": 0.05972268626795857,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.315,
|
|
"mean_token_accuracy": 0.11672014072537422,
|
|
"num_tokens": 1310112.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.382553958892823,
|
|
"epoch": 0.06014032743067157,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.12916786298155786,
|
|
"num_tokens": 1319309.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.326040887832642,
|
|
"epoch": 0.06055796859338457,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.12591121718287468,
|
|
"num_tokens": 1329049.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.351260471343994,
|
|
"epoch": 0.06097560975609756,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.0671,
|
|
"mean_token_accuracy": 0.12919704169034957,
|
|
"num_tokens": 1337770.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.254184007644653,
|
|
"epoch": 0.06139325091881056,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.1822,
|
|
"mean_token_accuracy": 0.1272610329091549,
|
|
"num_tokens": 1346705.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.3455441951751705,
|
|
"epoch": 0.06181089208152356,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.2394,
|
|
"mean_token_accuracy": 0.12634490579366683,
|
|
"num_tokens": 1354860.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.381866407394409,
|
|
"epoch": 0.06222853324423655,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.12138592973351478,
|
|
"num_tokens": 1364140.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.432730674743652,
|
|
"epoch": 0.06264617440694954,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3331,
|
|
"mean_token_accuracy": 0.11733241975307465,
|
|
"num_tokens": 1373645.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.377966737747192,
|
|
"epoch": 0.06306381556966255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2159,
|
|
"mean_token_accuracy": 0.13121263906359673,
|
|
"num_tokens": 1383291.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.239141368865967,
|
|
"epoch": 0.06348145673237554,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.1152,
|
|
"mean_token_accuracy": 0.1310908943414688,
|
|
"num_tokens": 1391172.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.377418088912964,
|
|
"epoch": 0.06389909789508853,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.1472,
|
|
"mean_token_accuracy": 0.12764590457081795,
|
|
"num_tokens": 1400864.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.295232057571411,
|
|
"epoch": 0.06431673905780154,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.12997447326779366,
|
|
"num_tokens": 1410570.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.313883256912232,
|
|
"epoch": 0.06473438022051453,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.1744,
|
|
"mean_token_accuracy": 0.1313069112598896,
|
|
"num_tokens": 1419536.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.338523483276367,
|
|
"epoch": 0.06515202138322754,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.091,
|
|
"mean_token_accuracy": 0.13004501089453696,
|
|
"num_tokens": 1428000.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.260497093200684,
|
|
"epoch": 0.06556966254594053,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2992,
|
|
"mean_token_accuracy": 0.12507489323616028,
|
|
"num_tokens": 1437789.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.270367765426636,
|
|
"epoch": 0.06598730370865352,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.1259957693517208,
|
|
"num_tokens": 1446848.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.279500675201416,
|
|
"epoch": 0.06640494487136653,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.1257844291627407,
|
|
"num_tokens": 1455749.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.253476810455322,
|
|
"epoch": 0.06682258603407952,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.1354301691055298,
|
|
"num_tokens": 1464556.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.333716917037964,
|
|
"epoch": 0.06724022719679251,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.2213,
|
|
"mean_token_accuracy": 0.12829236462712287,
|
|
"num_tokens": 1473617.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.306687116622925,
|
|
"epoch": 0.06765786835950552,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.2385,
|
|
"mean_token_accuracy": 0.12713917568325997,
|
|
"num_tokens": 1483006.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.430218935012817,
|
|
"epoch": 0.06807550952221851,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2582,
|
|
"mean_token_accuracy": 0.1252996154129505,
|
|
"num_tokens": 1493009.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.253592920303345,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.1317764475941658,
|
|
"num_tokens": 1501261.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.3305917263031,
|
|
"epoch": 0.06891079184764451,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.2536,
|
|
"mean_token_accuracy": 0.12618372738361358,
|
|
"num_tokens": 1511623.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.283257102966308,
|
|
"epoch": 0.0693284330103575,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2422,
|
|
"mean_token_accuracy": 0.12288018986582756,
|
|
"num_tokens": 1521741.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.252234697341919,
|
|
"epoch": 0.0697460741730705,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.12901844680309296,
|
|
"num_tokens": 1530988.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.257218217849731,
|
|
"epoch": 0.0701637153357835,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.13119714483618736,
|
|
"num_tokens": 1539415.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.338153076171875,
|
|
"epoch": 0.07058135649849649,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.12688441276550294,
|
|
"num_tokens": 1547969.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.164967966079712,
|
|
"epoch": 0.07099899766120948,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.1340305209159851,
|
|
"num_tokens": 1557526.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.167168045043946,
|
|
"epoch": 0.07141663882392249,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.13036102801561356,
|
|
"num_tokens": 1565982.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.178088760375976,
|
|
"epoch": 0.07183427998663548,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.13804332464933394,
|
|
"num_tokens": 1574492.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.236712503433227,
|
|
"epoch": 0.07225192114934847,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.12888288199901582,
|
|
"num_tokens": 1583726.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.159904909133911,
|
|
"epoch": 0.07266956231206148,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1032,
|
|
"mean_token_accuracy": 0.12467294186353683,
|
|
"num_tokens": 1593780.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.252811336517334,
|
|
"epoch": 0.07308720347477447,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.1311504900455475,
|
|
"num_tokens": 1602746.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.235387468338013,
|
|
"epoch": 0.07350484463748747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.1317,
|
|
"mean_token_accuracy": 0.13153513595461847,
|
|
"num_tokens": 1611767.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.322087335586548,
|
|
"epoch": 0.07392248580020047,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.13359929099678994,
|
|
"num_tokens": 1621568.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.234439277648926,
|
|
"epoch": 0.07434012696291346,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.1362864576280117,
|
|
"num_tokens": 1630650.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.207277011871338,
|
|
"epoch": 0.07475776812562646,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.1565,
|
|
"mean_token_accuracy": 0.1267276994884014,
|
|
"num_tokens": 1640482.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.311604309082031,
|
|
"epoch": 0.07517540928833946,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2126,
|
|
"mean_token_accuracy": 0.1277651831507683,
|
|
"num_tokens": 1649344.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.199459648132324,
|
|
"epoch": 0.07559305045105245,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.13086290359497071,
|
|
"num_tokens": 1658962.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.197014045715332,
|
|
"epoch": 0.07601069161376545,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.12403983399271964,
|
|
"num_tokens": 1668615.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.247787952423096,
|
|
"epoch": 0.07642833277647845,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.1306306391954422,
|
|
"num_tokens": 1679282.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.110937595367432,
|
|
"epoch": 0.07684597393919144,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.1861,
|
|
"mean_token_accuracy": 0.13143347576260567,
|
|
"num_tokens": 1688362.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.203617334365845,
|
|
"epoch": 0.07726361510190444,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.12813379019498825,
|
|
"num_tokens": 1697593.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.284222555160523,
|
|
"epoch": 0.07768125626461744,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.1326735071837902,
|
|
"num_tokens": 1706961.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.214397430419922,
|
|
"epoch": 0.07809889742733044,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.1837,
|
|
"mean_token_accuracy": 0.13653906658291817,
|
|
"num_tokens": 1716222.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.132423162460327,
|
|
"epoch": 0.07851653859004344,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.0741,
|
|
"mean_token_accuracy": 0.12650192454457282,
|
|
"num_tokens": 1726750.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.258601665496826,
|
|
"epoch": 0.07893417975275643,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.12657316625118256,
|
|
"num_tokens": 1736262.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.192229986190796,
|
|
"epoch": 0.07935182091546943,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1729,
|
|
"mean_token_accuracy": 0.13067680075764657,
|
|
"num_tokens": 1745555.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.050552940368652,
|
|
"epoch": 0.07976946207818243,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.0643,
|
|
"mean_token_accuracy": 0.12940090522170067,
|
|
"num_tokens": 1754107.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.305977058410645,
|
|
"epoch": 0.08018710324089542,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.12384195700287819,
|
|
"num_tokens": 1762982.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.171813297271728,
|
|
"epoch": 0.08060474440360842,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.1338811330497265,
|
|
"num_tokens": 1772545.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.244448280334472,
|
|
"epoch": 0.08102238556632142,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.12475204095244408,
|
|
"num_tokens": 1782052.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.1756124019622805,
|
|
"epoch": 0.08144002672903441,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.1337449759244919,
|
|
"num_tokens": 1791682.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.1777324199676515,
|
|
"epoch": 0.08185766789174741,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.13526007980108262,
|
|
"num_tokens": 1800526.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.219584560394287,
|
|
"epoch": 0.08227530905446041,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2113,
|
|
"mean_token_accuracy": 0.1325635403394699,
|
|
"num_tokens": 1810062.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.163633823394775,
|
|
"epoch": 0.0826929502171734,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.13362277597188948,
|
|
"num_tokens": 1818909.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.275831508636474,
|
|
"epoch": 0.0831105913798864,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.13871751874685287,
|
|
"num_tokens": 1827978.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.068942451477051,
|
|
"epoch": 0.0835282325425994,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.1366957776248455,
|
|
"num_tokens": 1837955.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.199518489837646,
|
|
"epoch": 0.0839458737053124,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999999987395534,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.12947369664907454,
|
|
"num_tokens": 1847699.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.2342846393585205,
|
|
"epoch": 0.08436351486802539,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999936189888,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.1308988593518734,
|
|
"num_tokens": 1856490.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.187710952758789,
|
|
"epoch": 0.0847811560307384,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999845595285,
|
|
"loss": 6.1336,
|
|
"mean_token_accuracy": 0.1302417054772377,
|
|
"num_tokens": 1865644.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.139751815795899,
|
|
"epoch": 0.08519879719345139,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004999999715611727,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.13923914581537247,
|
|
"num_tokens": 1874450.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.1254647731781,
|
|
"epoch": 0.08561643835616438,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999546239215,
|
|
"loss": 6.0891,
|
|
"mean_token_accuracy": 0.13145651072263717,
|
|
"num_tokens": 1883259.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.193487119674683,
|
|
"epoch": 0.08603407951887738,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999337477753,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.12691283002495765,
|
|
"num_tokens": 1891897.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.166404056549072,
|
|
"epoch": 0.08645172068159038,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999999089327344,
|
|
"loss": 6.1476,
|
|
"mean_token_accuracy": 0.12759166434407235,
|
|
"num_tokens": 1901011.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.058528995513916,
|
|
"epoch": 0.08686936184430337,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999998801787993,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.13580385074019433,
|
|
"num_tokens": 1910132.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.21063199043274,
|
|
"epoch": 0.08728700300701638,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999998474859704,
|
|
"loss": 6.1796,
|
|
"mean_token_accuracy": 0.13001134023070335,
|
|
"num_tokens": 1919938.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.021421146392822,
|
|
"epoch": 0.08770464416972937,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999998108542483,
|
|
"loss": 6.0474,
|
|
"mean_token_accuracy": 0.1303606778383255,
|
|
"num_tokens": 1928199.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.149118709564209,
|
|
"epoch": 0.08812228533244236,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999997702836339,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.1368630550801754,
|
|
"num_tokens": 1937133.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.19862322807312,
|
|
"epoch": 0.08853992649515537,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999997257741274,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.13205777183175088,
|
|
"num_tokens": 1946580.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.109546327590943,
|
|
"epoch": 0.08895756765786836,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049999967732573,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.1276082694530487,
|
|
"num_tokens": 1955413.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.293388748168946,
|
|
"epoch": 0.08937520882058135,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999996249384425,
|
|
"loss": 6.1897,
|
|
"mean_token_accuracy": 0.1298133671283722,
|
|
"num_tokens": 1964716.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.0309676170349125,
|
|
"epoch": 0.08979284998329436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999995686122657,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.13794475570321083,
|
|
"num_tokens": 1974081.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.057157135009765,
|
|
"epoch": 0.09021049114600735,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999995083472006,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.13763214722275735,
|
|
"num_tokens": 1983035.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.133276653289795,
|
|
"epoch": 0.09062813230872034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999994441432481,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.1399047665297985,
|
|
"num_tokens": 1992475.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.012667560577393,
|
|
"epoch": 0.09104577347143335,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999993760004097,
|
|
"loss": 6.1266,
|
|
"mean_token_accuracy": 0.12739486023783683,
|
|
"num_tokens": 2002729.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.0253236293792725,
|
|
"epoch": 0.09146341463414634,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999993039186864,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.13841661661863328,
|
|
"num_tokens": 2011319.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.083655738830567,
|
|
"epoch": 0.09188105579685933,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999992278980794,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.1362566351890564,
|
|
"num_tokens": 2020456.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.034357261657715,
|
|
"epoch": 0.09229869695957234,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999991479385901,
|
|
"loss": 6.0927,
|
|
"mean_token_accuracy": 0.13392627835273743,
|
|
"num_tokens": 2029417.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.154821872711182,
|
|
"epoch": 0.09271633812228533,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999990640402198,
|
|
"loss": 6.1738,
|
|
"mean_token_accuracy": 0.1311173379421234,
|
|
"num_tokens": 2039290.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.101737451553345,
|
|
"epoch": 0.09313397928499834,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999989762029701,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.13381630852818488,
|
|
"num_tokens": 2048485.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 5.9683490753173825,
|
|
"epoch": 0.09355162044771133,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999988844268425,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.14155827090144157,
|
|
"num_tokens": 2057131.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.020996618270874,
|
|
"epoch": 0.09396926161042432,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999987887118387,
|
|
"loss": 5.9606,
|
|
"mean_token_accuracy": 0.1338317573070526,
|
|
"num_tokens": 2066295.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.021601724624634,
|
|
"epoch": 0.09438690277313733,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999986890579602,
|
|
"loss": 5.9637,
|
|
"mean_token_accuracy": 0.1408805377781391,
|
|
"num_tokens": 2075656.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.0348409652709964,
|
|
"epoch": 0.09480454393585032,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999985854652087,
|
|
"loss": 6.1381,
|
|
"mean_token_accuracy": 0.129783895611763,
|
|
"num_tokens": 2086046.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.1812419414520265,
|
|
"epoch": 0.09522218509856331,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999984779335862,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.13610694855451583,
|
|
"num_tokens": 2094808.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 5.959377193450928,
|
|
"epoch": 0.09563982626127632,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999983664630945,
|
|
"loss": 6.0585,
|
|
"mean_token_accuracy": 0.1390154741704464,
|
|
"num_tokens": 2104155.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.033576393127442,
|
|
"epoch": 0.09605746742398931,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999982510537357,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.1419323816895485,
|
|
"num_tokens": 2112517.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 5.961051750183105,
|
|
"epoch": 0.0964751085867023,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999981317055116,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.1370644360780716,
|
|
"num_tokens": 2121355.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.07532811164856,
|
|
"epoch": 0.09689274974941531,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999980084184244,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.14000216126441956,
|
|
"num_tokens": 2129278.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.112037467956543,
|
|
"epoch": 0.0973103909121283,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999978811924762,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.13468564450740814,
|
|
"num_tokens": 2139548.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.011156606674194,
|
|
"epoch": 0.09772803207484129,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999977500276693,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.13282948657870292,
|
|
"num_tokens": 2148765.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.156813764572144,
|
|
"epoch": 0.0981456732375543,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999976149240058,
|
|
"loss": 5.9998,
|
|
"mean_token_accuracy": 0.14147626087069512,
|
|
"num_tokens": 2157482.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.06043438911438,
|
|
"epoch": 0.09856331440026729,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999974758814884,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.12927817851305007,
|
|
"num_tokens": 2167320.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.090041780471802,
|
|
"epoch": 0.09898095556298028,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999973329001193,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.13234857842326164,
|
|
"num_tokens": 2175454.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.048929071426391,
|
|
"epoch": 0.09939859672569329,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999971859799009,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.137349022179842,
|
|
"num_tokens": 2184391.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 5.9458996772766115,
|
|
"epoch": 0.09981623788840628,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999970351208361,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.1423418328166008,
|
|
"num_tokens": 2193309.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.062114095687866,
|
|
"epoch": 0.10023387905111927,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999968803229275,
|
|
"loss": 6.0268,
|
|
"mean_token_accuracy": 0.13685409501194953,
|
|
"num_tokens": 2202057.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.010811853408813,
|
|
"epoch": 0.10065152021383228,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999967215861775,
|
|
"loss": 6.1207,
|
|
"mean_token_accuracy": 0.13319561630487442,
|
|
"num_tokens": 2212384.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.149314880371094,
|
|
"epoch": 0.10106916137654527,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499996558910589,
|
|
"loss": 6.0364,
|
|
"mean_token_accuracy": 0.13858548328280448,
|
|
"num_tokens": 2221451.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 5.897707605361939,
|
|
"epoch": 0.10148680253925826,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499996392296165,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.1363538235425949,
|
|
"num_tokens": 2230440.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.108274269104004,
|
|
"epoch": 0.10190444370197127,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999962217429083,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.1263136975467205,
|
|
"num_tokens": 2239985.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.034344911575317,
|
|
"epoch": 0.10232208486468426,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.13609189465641974,
|
|
"num_tokens": 2250391.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.079465055465699,
|
|
"epoch": 0.10273972602739725,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499995868819909,
|
|
"loss": 6.0937,
|
|
"mean_token_accuracy": 0.12762524262070657,
|
|
"num_tokens": 2260620.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.125043344497681,
|
|
"epoch": 0.10315736719011026,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999956864501725,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.13054439499974252,
|
|
"num_tokens": 2271176.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.024161291122437,
|
|
"epoch": 0.10357500835282325,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999955001416156,
|
|
"loss": 5.9637,
|
|
"mean_token_accuracy": 0.1394001565873623,
|
|
"num_tokens": 2280371.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 5.873808765411377,
|
|
"epoch": 0.10399264951553625,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999953098942417,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.13987089917063714,
|
|
"num_tokens": 2289015.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 5.993573093414307,
|
|
"epoch": 0.10441029067824925,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999951157080541,
|
|
"loss": 6.011,
|
|
"mean_token_accuracy": 0.14008186012506485,
|
|
"num_tokens": 2297409.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.020661783218384,
|
|
"epoch": 0.10482793184096224,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999949175830561,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.137710864841938,
|
|
"num_tokens": 2307017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 5.966087722778321,
|
|
"epoch": 0.10524557300367524,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999947155192514,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.14721441268920898,
|
|
"num_tokens": 2316014.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.035770273208618,
|
|
"epoch": 0.10566321416638824,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999945095166433,
|
|
"loss": 5.9742,
|
|
"mean_token_accuracy": 0.14057080522179605,
|
|
"num_tokens": 2326326.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.115755558013916,
|
|
"epoch": 0.10608085532910123,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999942995752354,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.13691574186086655,
|
|
"num_tokens": 2335108.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 5.959864377975464,
|
|
"epoch": 0.10649849649181423,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999940856950315,
|
|
"loss": 5.9885,
|
|
"mean_token_accuracy": 0.14240883886814118,
|
|
"num_tokens": 2343971.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.033252716064453,
|
|
"epoch": 0.10691613765452723,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999938678760354,
|
|
"loss": 6.0546,
|
|
"mean_token_accuracy": 0.13366041257977485,
|
|
"num_tokens": 2353742.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 5.9920961380004885,
|
|
"epoch": 0.10733377881724022,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999936461182507,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.14326683208346366,
|
|
"num_tokens": 2363629.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 5.8916154384613035,
|
|
"epoch": 0.10775141997995323,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999934204216814,
|
|
"loss": 5.8557,
|
|
"mean_token_accuracy": 0.14521737545728683,
|
|
"num_tokens": 2372705.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 5.9855352401733395,
|
|
"epoch": 0.10816906114266622,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999931907863315,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.14111716747283937,
|
|
"num_tokens": 2382136.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 5.877673768997193,
|
|
"epoch": 0.10858670230537922,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499992957212205,
|
|
"loss": 5.9341,
|
|
"mean_token_accuracy": 0.1387516625225544,
|
|
"num_tokens": 2391060.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.04531421661377,
|
|
"epoch": 0.10900434346809222,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999927196993059,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.136396811157465,
|
|
"num_tokens": 2399885.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.001427459716797,
|
|
"epoch": 0.10942198463080521,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999924782476384,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.14695603102445604,
|
|
"num_tokens": 2409654.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.023379850387573,
|
|
"epoch": 0.1098396257935182,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999922328572068,
|
|
"loss": 6.0087,
|
|
"mean_token_accuracy": 0.13872749507427215,
|
|
"num_tokens": 2419342.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 5.900698280334472,
|
|
"epoch": 0.11025726695623121,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999919835280154,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.14329665824770926,
|
|
"num_tokens": 2428845.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.046743535995484,
|
|
"epoch": 0.1106749081189442,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999917302600684,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.14875416159629823,
|
|
"num_tokens": 2437134.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 5.708086442947388,
|
|
"epoch": 0.1110925492816572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999914730533704,
|
|
"loss": 5.7293,
|
|
"mean_token_accuracy": 0.15531845688819884,
|
|
"num_tokens": 2445438.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.002161979675293,
|
|
"epoch": 0.1115101904443702,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999912119079258,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.13914170265197753,
|
|
"num_tokens": 2455039.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.0124329090118405,
|
|
"epoch": 0.1119278316070832,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999909468237393,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.13686869218945502,
|
|
"num_tokens": 2465170.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.87831563949585,
|
|
"epoch": 0.11234547276979619,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999906778008153,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.1533431127667427,
|
|
"num_tokens": 2473688.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 5.915750741958618,
|
|
"epoch": 0.11276311393250919,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999904048391588,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.13419281020760537,
|
|
"num_tokens": 2482335.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 5.989591646194458,
|
|
"epoch": 0.11318075509522219,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999901279387743,
|
|
"loss": 5.9312,
|
|
"mean_token_accuracy": 0.14448264613747597,
|
|
"num_tokens": 2491808.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.086487817764282,
|
|
"epoch": 0.11359839625793518,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999898470996669,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.13440220579504966,
|
|
"num_tokens": 2501422.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 5.9091236114501955,
|
|
"epoch": 0.11401603742064818,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999895623218415,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.14603495746850967,
|
|
"num_tokens": 2511201.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 5.936640071868896,
|
|
"epoch": 0.11443367858336118,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999892736053027,
|
|
"loss": 5.8957,
|
|
"mean_token_accuracy": 0.1403353899717331,
|
|
"num_tokens": 2519798.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.891090345382691,
|
|
"epoch": 0.11485131974607417,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999889809500561,
|
|
"loss": 5.8755,
|
|
"mean_token_accuracy": 0.1445053994655609,
|
|
"num_tokens": 2529177.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.015834188461303,
|
|
"epoch": 0.11526896090878717,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999886843561065,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.14721576496958733,
|
|
"num_tokens": 2537571.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 5.768728446960449,
|
|
"epoch": 0.11568660207150017,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999883838234592,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.1494941793382168,
|
|
"num_tokens": 2546258.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.879445552825928,
|
|
"epoch": 0.11610424323421316,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999880793521194,
|
|
"loss": 5.8101,
|
|
"mean_token_accuracy": 0.14160490334033965,
|
|
"num_tokens": 2555862.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.703860473632813,
|
|
"epoch": 0.11652188439692616,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999877709420924,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.14771698862314225,
|
|
"num_tokens": 2564583.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.946020936965942,
|
|
"epoch": 0.11693952555963916,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999874585933837,
|
|
"loss": 5.9224,
|
|
"mean_token_accuracy": 0.14428764581680298,
|
|
"num_tokens": 2574217.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 5.874564838409424,
|
|
"epoch": 0.11735716672235215,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999871423059987,
|
|
"loss": 5.8278,
|
|
"mean_token_accuracy": 0.14492169469594957,
|
|
"num_tokens": 2582821.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.90300989151001,
|
|
"epoch": 0.11777480788506516,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499986822079943,
|
|
"loss": 6.0026,
|
|
"mean_token_accuracy": 0.1350848987698555,
|
|
"num_tokens": 2592748.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.979686975479126,
|
|
"epoch": 0.11819244904777815,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999864979152221,
|
|
"loss": 5.8824,
|
|
"mean_token_accuracy": 0.14854978621006013,
|
|
"num_tokens": 2602053.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.808524131774902,
|
|
"epoch": 0.11861009021049114,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999861698118417,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.14355539306998252,
|
|
"num_tokens": 2610557.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.955320358276367,
|
|
"epoch": 0.11902773137320415,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999858377698076,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.14397183433175087,
|
|
"num_tokens": 2619628.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.067613363265991,
|
|
"epoch": 0.11944537253591714,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999855017891256,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.14067387729883193,
|
|
"num_tokens": 2629284.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.882795715332032,
|
|
"epoch": 0.11986301369863013,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999851618698017,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.14827706664800644,
|
|
"num_tokens": 2638001.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 5.891476774215699,
|
|
"epoch": 0.12028065486134314,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999848180118416,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.15219354629516602,
|
|
"num_tokens": 2647071.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.973889017105103,
|
|
"epoch": 0.12069829602405613,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999844702152516,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.14990584850311278,
|
|
"num_tokens": 2655826.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.833336019515992,
|
|
"epoch": 0.12111593718676913,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999841184800374,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.15365617871284484,
|
|
"num_tokens": 2664431.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.761509227752685,
|
|
"epoch": 0.12153357834948213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999837628062055,
|
|
"loss": 5.6995,
|
|
"mean_token_accuracy": 0.15763423219323158,
|
|
"num_tokens": 2673631.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 5.807348442077637,
|
|
"epoch": 0.12195121951219512,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999834031937621,
|
|
"loss": 5.9755,
|
|
"mean_token_accuracy": 0.1450788274407387,
|
|
"num_tokens": 2683363.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.004406070709228,
|
|
"epoch": 0.12236886067490813,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999830396427133,
|
|
"loss": 5.9219,
|
|
"mean_token_accuracy": 0.14206716865301133,
|
|
"num_tokens": 2692533.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.8194908618927,
|
|
"epoch": 0.12278650183762112,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999826721530657,
|
|
"loss": 5.9232,
|
|
"mean_token_accuracy": 0.15276242047548294,
|
|
"num_tokens": 2701211.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.959702110290527,
|
|
"epoch": 0.12320414300033411,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999823007248255,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.14682099223136902,
|
|
"num_tokens": 2709543.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.9004326343536375,
|
|
"epoch": 0.12362178416304712,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999819253579992,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.14219618514180182,
|
|
"num_tokens": 2718336.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.887391233444214,
|
|
"epoch": 0.12403942532576011,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999815460525938,
|
|
"loss": 5.8491,
|
|
"mean_token_accuracy": 0.15181448459625244,
|
|
"num_tokens": 2726504.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.889515399932861,
|
|
"epoch": 0.1244570664884731,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999811628086155,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.14508116692304612,
|
|
"num_tokens": 2736076.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.805719614028931,
|
|
"epoch": 0.1248747076511861,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499980775626071,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.1503925770521164,
|
|
"num_tokens": 2745497.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.8484405994415285,
|
|
"epoch": 0.12529234881389908,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999803845049674,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.14518412500619887,
|
|
"num_tokens": 2754455.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.031361675262451,
|
|
"epoch": 0.1257099899766121,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999799894453112,
|
|
"loss": 5.9596,
|
|
"mean_token_accuracy": 0.14515393003821372,
|
|
"num_tokens": 2763603.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.842563438415527,
|
|
"epoch": 0.1261276311393251,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999795904471095,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.14701997935771943,
|
|
"num_tokens": 2772152.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.936494588851929,
|
|
"epoch": 0.12654527230203808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999791875103694,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.14711305350065232,
|
|
"num_tokens": 2781459.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.912358713150025,
|
|
"epoch": 0.12696291346475108,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999787806350977,
|
|
"loss": 5.8773,
|
|
"mean_token_accuracy": 0.14168751537799834,
|
|
"num_tokens": 2791177.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.809263038635254,
|
|
"epoch": 0.1273805546274641,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999783698213016,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.1511882796883583,
|
|
"num_tokens": 2800543.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.718258190155029,
|
|
"epoch": 0.12779819579017707,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999779550689885,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.1562495306134224,
|
|
"num_tokens": 2809301.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.946142387390137,
|
|
"epoch": 0.12821583695289007,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999775363781654,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.13951645120978357,
|
|
"num_tokens": 2818269.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.855810689926147,
|
|
"epoch": 0.12863347811560308,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999771137488395,
|
|
"loss": 5.7879,
|
|
"mean_token_accuracy": 0.15382847785949708,
|
|
"num_tokens": 2827170.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.764991426467896,
|
|
"epoch": 0.12905111927831608,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999766871810188,
|
|
"loss": 5.7656,
|
|
"mean_token_accuracy": 0.15415056496858598,
|
|
"num_tokens": 2835320.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.850279855728149,
|
|
"epoch": 0.12946876044102906,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999762566747101,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.14932266920804976,
|
|
"num_tokens": 2843755.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.914557886123657,
|
|
"epoch": 0.12988640160374207,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999758222299214,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.1388828009366989,
|
|
"num_tokens": 2853462.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.80288872718811,
|
|
"epoch": 0.13030404276645507,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999753838466601,
|
|
"loss": 5.8131,
|
|
"mean_token_accuracy": 0.14732857197523117,
|
|
"num_tokens": 2863041.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.004314374923706,
|
|
"epoch": 0.13072168392916805,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999749415249338,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.14584584459662436,
|
|
"num_tokens": 2873019.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.770129728317261,
|
|
"epoch": 0.13113932509188106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999744952647505,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.14778472259640693,
|
|
"num_tokens": 2881467.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.8767143249511715,
|
|
"epoch": 0.13155696625459407,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999740450661176,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.14663312584161758,
|
|
"num_tokens": 2890914.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.784161996841431,
|
|
"epoch": 0.13197460741730704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999735909290436,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.14994997084140776,
|
|
"num_tokens": 2901164.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.883551549911499,
|
|
"epoch": 0.13239224858002005,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999731328535358,
|
|
"loss": 5.9144,
|
|
"mean_token_accuracy": 0.1454067997634411,
|
|
"num_tokens": 2910560.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.796862983703614,
|
|
"epoch": 0.13280988974273306,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999726708396026,
|
|
"loss": 5.7264,
|
|
"mean_token_accuracy": 0.1551614746451378,
|
|
"num_tokens": 2918980.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.845749855041504,
|
|
"epoch": 0.13322753090544603,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499972204887252,
|
|
"loss": 5.9292,
|
|
"mean_token_accuracy": 0.14284173548221588,
|
|
"num_tokens": 2929516.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.866528034210205,
|
|
"epoch": 0.13364517206815904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999717349964922,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.13401781842112542,
|
|
"num_tokens": 2940603.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.975286054611206,
|
|
"epoch": 0.13406281323087205,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999712611673313,
|
|
"loss": 5.8426,
|
|
"mean_token_accuracy": 0.1439616158604622,
|
|
"num_tokens": 2950082.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.723266506195069,
|
|
"epoch": 0.13448045439358502,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999707833997777,
|
|
"loss": 5.7138,
|
|
"mean_token_accuracy": 0.1633479043841362,
|
|
"num_tokens": 2959098.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.87523307800293,
|
|
"epoch": 0.13489809555629803,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999703016938398,
|
|
"loss": 5.8386,
|
|
"mean_token_accuracy": 0.15109211057424546,
|
|
"num_tokens": 2968585.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.831326818466186,
|
|
"epoch": 0.13531573671901104,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499969816049526,
|
|
"loss": 5.878,
|
|
"mean_token_accuracy": 0.14930004104971886,
|
|
"num_tokens": 2978430.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.996936225891114,
|
|
"epoch": 0.13573337788172402,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999693264668446,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.14231408908963203,
|
|
"num_tokens": 2988398.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.878012323379517,
|
|
"epoch": 0.13615101904443702,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999688329458045,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.14286330938339234,
|
|
"num_tokens": 2999255.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.927907991409302,
|
|
"epoch": 0.13656866020715003,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999683354864141,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.14798136353492736,
|
|
"num_tokens": 3008638.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.776216173171997,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999678340886823,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.1482193261384964,
|
|
"num_tokens": 3018070.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.791409111022949,
|
|
"epoch": 0.137403942532576,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999673287526176,
|
|
"loss": 5.8119,
|
|
"mean_token_accuracy": 0.14728376343846322,
|
|
"num_tokens": 3027878.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.978458023071289,
|
|
"epoch": 0.13782158369528902,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999668194782291,
|
|
"loss": 5.9885,
|
|
"mean_token_accuracy": 0.1419169157743454,
|
|
"num_tokens": 3037031.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.949056673049927,
|
|
"epoch": 0.138239224858002,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999663062655257,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.140587417781353,
|
|
"num_tokens": 3046311.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.834480047225952,
|
|
"epoch": 0.138656866020715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999657891145162,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.1507701277732849,
|
|
"num_tokens": 3055108.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.703247451782227,
|
|
"epoch": 0.139074507183428,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999652680252099,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.15281276553869247,
|
|
"num_tokens": 3063492.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.96858491897583,
|
|
"epoch": 0.139492148346141,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999647429976157,
|
|
"loss": 5.839,
|
|
"mean_token_accuracy": 0.15251049250364304,
|
|
"num_tokens": 3072572.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.884686231613159,
|
|
"epoch": 0.139909789508854,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999642140317429,
|
|
"loss": 5.8876,
|
|
"mean_token_accuracy": 0.1460355408489704,
|
|
"num_tokens": 3082942.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.78411111831665,
|
|
"epoch": 0.140327430671567,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999636811276007,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.14870428889989853,
|
|
"num_tokens": 3091410.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.933750295639038,
|
|
"epoch": 0.14074507183427998,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999631442851986,
|
|
"loss": 5.9126,
|
|
"mean_token_accuracy": 0.1502613291144371,
|
|
"num_tokens": 3100626.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.747744131088257,
|
|
"epoch": 0.14116271299699298,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999626035045458,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.15668077766895294,
|
|
"num_tokens": 3109339.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.869397354125977,
|
|
"epoch": 0.141580354159706,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999620587856519,
|
|
"loss": 5.8462,
|
|
"mean_token_accuracy": 0.1474672093987465,
|
|
"num_tokens": 3118636.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.770104169845581,
|
|
"epoch": 0.14199799532241897,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999615101285262,
|
|
"loss": 5.8111,
|
|
"mean_token_accuracy": 0.14746451154351234,
|
|
"num_tokens": 3128162.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.8655181407928465,
|
|
"epoch": 0.14241563648513197,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999609575331786,
|
|
"loss": 5.8179,
|
|
"mean_token_accuracy": 0.15379944443702698,
|
|
"num_tokens": 3136451.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.857501363754272,
|
|
"epoch": 0.14283327764784498,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999604009996186,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.14673274308443068,
|
|
"num_tokens": 3146599.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.884437608718872,
|
|
"epoch": 0.14325091881055796,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499959840527856,
|
|
"loss": 5.8732,
|
|
"mean_token_accuracy": 0.14682791605591775,
|
|
"num_tokens": 3155941.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.824529457092285,
|
|
"epoch": 0.14366855997327097,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999592761179007,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.15331910401582718,
|
|
"num_tokens": 3164641.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.833645057678223,
|
|
"epoch": 0.14408620113598397,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999587077697624,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.15982660353183747,
|
|
"num_tokens": 3173701.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.684833717346192,
|
|
"epoch": 0.14450384229869695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999581354834512,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.1520286552608013,
|
|
"num_tokens": 3182268.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.74345817565918,
|
|
"epoch": 0.14492148346140996,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499957559258977,
|
|
"loss": 5.7711,
|
|
"mean_token_accuracy": 0.15220290571451187,
|
|
"num_tokens": 3191513.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.77564492225647,
|
|
"epoch": 0.14533912462412296,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049995697909635,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.15256546586751937,
|
|
"num_tokens": 3200580.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.737341022491455,
|
|
"epoch": 0.14575676578683594,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999563949955803,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.15687910318374634,
|
|
"num_tokens": 3209053.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.808221817016602,
|
|
"epoch": 0.14617440694954895,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499955806956678,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.1543448254466057,
|
|
"num_tokens": 3218241.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.880738401412964,
|
|
"epoch": 0.14659204811226195,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999552149796536,
|
|
"loss": 5.8514,
|
|
"mean_token_accuracy": 0.1490916818380356,
|
|
"num_tokens": 3227887.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.768217468261719,
|
|
"epoch": 0.14700968927497493,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999546190645175,
|
|
"loss": 5.6692,
|
|
"mean_token_accuracy": 0.16196279525756835,
|
|
"num_tokens": 3237281.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.684476280212403,
|
|
"epoch": 0.14742733043768794,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999540192112799,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.15405311733484267,
|
|
"num_tokens": 3246907.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.660418939590454,
|
|
"epoch": 0.14784497160040094,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999534154199514,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.1486714243888855,
|
|
"num_tokens": 3256312.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.922216749191284,
|
|
"epoch": 0.14826261276311392,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999528076905426,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.1525414004921913,
|
|
"num_tokens": 3265554.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.621938705444336,
|
|
"epoch": 0.14868025392582693,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999521960230641,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.15837963819503784,
|
|
"num_tokens": 3274731.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.7696099281311035,
|
|
"epoch": 0.14909789508853993,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.1475925050675869,
|
|
"num_tokens": 3283518.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.852998208999634,
|
|
"epoch": 0.1495155362512529,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499950960873941,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.1533878356218338,
|
|
"num_tokens": 3292244.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.8209583282470705,
|
|
"epoch": 0.14993317741396592,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999503373923182,
|
|
"loss": 5.7746,
|
|
"mean_token_accuracy": 0.15582873076200485,
|
|
"num_tokens": 3301198.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.733056211471558,
|
|
"epoch": 0.15035081857667892,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999497099726687,
|
|
"loss": 5.7494,
|
|
"mean_token_accuracy": 0.15889813750982285,
|
|
"num_tokens": 3309983.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.81738691329956,
|
|
"epoch": 0.1507684597393919,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999490786150039,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.147987063229084,
|
|
"num_tokens": 3319313.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.742344903945923,
|
|
"epoch": 0.1511861009021049,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999484433193348,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.15073793679475783,
|
|
"num_tokens": 3327497.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.707638788223266,
|
|
"epoch": 0.15160374206481791,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999478040856722,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.1553061291575432,
|
|
"num_tokens": 3337029.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.660393095016479,
|
|
"epoch": 0.1520213832275309,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999471609140276,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.15133372247219085,
|
|
"num_tokens": 3346243.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.844138050079346,
|
|
"epoch": 0.1524390243902439,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999465138044122,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.150594063103199,
|
|
"num_tokens": 3354846.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.748153495788574,
|
|
"epoch": 0.1528566655529569,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999458627568373,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.1485428184270859,
|
|
"num_tokens": 3364683.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.829200696945191,
|
|
"epoch": 0.15327430671566988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999452077713144,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.14999438524246217,
|
|
"num_tokens": 3374652.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.692996788024902,
|
|
"epoch": 0.1536919478783829,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999445488478547,
|
|
"loss": 5.7464,
|
|
"mean_token_accuracy": 0.1528235137462616,
|
|
"num_tokens": 3384040.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.801222896575927,
|
|
"epoch": 0.1541095890410959,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00049994388598647,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.14949264377355576,
|
|
"num_tokens": 3393185.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.708631277084351,
|
|
"epoch": 0.15452723020380887,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999432191871719,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.15880197882652283,
|
|
"num_tokens": 3403077.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.772182989120483,
|
|
"epoch": 0.15494487136652188,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999425484499718,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.16176845729351044,
|
|
"num_tokens": 3412165.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.772862243652344,
|
|
"epoch": 0.1553625125292349,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999418737748817,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.14864142686128617,
|
|
"num_tokens": 3421162.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.872934341430664,
|
|
"epoch": 0.15578015369194786,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999411951619134,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.1428262896835804,
|
|
"num_tokens": 3430363.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.807984781265259,
|
|
"epoch": 0.15619779485466087,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999405126110786,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.15092551931738854,
|
|
"num_tokens": 3439199.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.957257461547852,
|
|
"epoch": 0.15661543601737388,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999398261223895,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.14979226514697075,
|
|
"num_tokens": 3448720.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.749342966079712,
|
|
"epoch": 0.15703307718008688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999391356958579,
|
|
"loss": 5.8455,
|
|
"mean_token_accuracy": 0.14971398413181305,
|
|
"num_tokens": 3458472.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.749511766433716,
|
|
"epoch": 0.15745071834279986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499938441331496,
|
|
"loss": 5.7952,
|
|
"mean_token_accuracy": 0.15146801769733428,
|
|
"num_tokens": 3467140.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.867589330673217,
|
|
"epoch": 0.15786835950551287,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999377430293159,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.15411789417266847,
|
|
"num_tokens": 3476431.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.766841220855713,
|
|
"epoch": 0.15828600066822587,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999370407893299,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.15346913933753967,
|
|
"num_tokens": 3485768.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.807104873657226,
|
|
"epoch": 0.15870364183093885,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999363346115501,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.14504164904356004,
|
|
"num_tokens": 3495678.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.785052108764648,
|
|
"epoch": 0.15912128299365186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999356244959893,
|
|
"loss": 5.8342,
|
|
"mean_token_accuracy": 0.1516023814678192,
|
|
"num_tokens": 3505168.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.740941047668457,
|
|
"epoch": 0.15953892415636486,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999349104426594,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.15149827301502228,
|
|
"num_tokens": 3514498.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.848452997207642,
|
|
"epoch": 0.15995656531907784,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999341924515732,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.15026968866586685,
|
|
"num_tokens": 3524617.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.668032789230347,
|
|
"epoch": 0.16037420648179085,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999334705227431,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.15639639049768447,
|
|
"num_tokens": 3533523.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.7723455905914305,
|
|
"epoch": 0.16079184764450385,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499932744656182,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.15217868536710738,
|
|
"num_tokens": 3542922.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.797222757339478,
|
|
"epoch": 0.16120948880721683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999320148519024,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.154755599796772,
|
|
"num_tokens": 3551827.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.708801507949829,
|
|
"epoch": 0.16162712996992984,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999312811099171,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.15864891856908797,
|
|
"num_tokens": 3560911.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.6975208759307865,
|
|
"epoch": 0.16204477113264285,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999305434302391,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.14677345082163812,
|
|
"num_tokens": 3569473.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.7810064315795895,
|
|
"epoch": 0.16246241229535582,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499929801812881,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.15499909371137618,
|
|
"num_tokens": 3578843.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.788356876373291,
|
|
"epoch": 0.16288005345806883,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999290562578561,
|
|
"loss": 5.7561,
|
|
"mean_token_accuracy": 0.15244330316781998,
|
|
"num_tokens": 3588304.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.7127964973449705,
|
|
"epoch": 0.16329769462078184,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999283067651773,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.14917491376399994,
|
|
"num_tokens": 3598354.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.894095182418823,
|
|
"epoch": 0.16371533578349481,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999275533348577,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.14917806088924407,
|
|
"num_tokens": 3607503.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.645402431488037,
|
|
"epoch": 0.16413297694620782,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999267959669106,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.15993930548429489,
|
|
"num_tokens": 3617467.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.7752259254455565,
|
|
"epoch": 0.16455061810892083,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999260346613491,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.15142679512500762,
|
|
"num_tokens": 3627048.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.651623249053955,
|
|
"epoch": 0.1649682592716338,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999252694181867,
|
|
"loss": 5.6978,
|
|
"mean_token_accuracy": 0.1521272361278534,
|
|
"num_tokens": 3636683.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.696958827972412,
|
|
"epoch": 0.1653859004343468,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999245002374367,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.16368645280599595,
|
|
"num_tokens": 3645231.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.720323944091797,
|
|
"epoch": 0.16580354159705982,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999237271191125,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.15285556465387345,
|
|
"num_tokens": 3653851.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.692817211151123,
|
|
"epoch": 0.1662211827597728,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999229500632279,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.1602617844939232,
|
|
"num_tokens": 3662720.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.616102457046509,
|
|
"epoch": 0.1666388239224858,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999221690697961,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.15996311008930206,
|
|
"num_tokens": 3671777.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.6898268699646,
|
|
"epoch": 0.1670564650851988,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999213841388312,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.16112901419401168,
|
|
"num_tokens": 3681390.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.791441488265991,
|
|
"epoch": 0.16747410624791179,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999205952703466,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.15657739117741584,
|
|
"num_tokens": 3690899.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.80651216506958,
|
|
"epoch": 0.1678917474106248,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999198024643563,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.14452483803033828,
|
|
"num_tokens": 3699891.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.6384241580963135,
|
|
"epoch": 0.1683093885733378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999190057208741,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.1593468502163887,
|
|
"num_tokens": 3709860.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.729552555084228,
|
|
"epoch": 0.16872702973605078,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499918205039914,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.15205028057098388,
|
|
"num_tokens": 3718896.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.710118341445923,
|
|
"epoch": 0.16914467089876378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999174004214899,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.1561296820640564,
|
|
"num_tokens": 3727355.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.6436944007873535,
|
|
"epoch": 0.1695623120614768,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999165918656161,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.15167264267802238,
|
|
"num_tokens": 3736191.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.8228062152862545,
|
|
"epoch": 0.16997995322418977,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999157793723065,
|
|
"loss": 5.7164,
|
|
"mean_token_accuracy": 0.1563839003443718,
|
|
"num_tokens": 3744832.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.607315397262573,
|
|
"epoch": 0.17039759438690277,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999149629415755,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.15334342569112777,
|
|
"num_tokens": 3753835.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.858393764495849,
|
|
"epoch": 0.17081523554961578,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999141425734374,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.15258873701095582,
|
|
"num_tokens": 3762816.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.651172780990601,
|
|
"epoch": 0.17123287671232876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999133182679064,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.1495609924197197,
|
|
"num_tokens": 3773244.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.733507108688355,
|
|
"epoch": 0.17165051787504176,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999124900249971,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.16301829516887664,
|
|
"num_tokens": 3782122.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.688563394546509,
|
|
"epoch": 0.17206815903775477,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999116578447239,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.16714497208595275,
|
|
"num_tokens": 3791303.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.7102601528167725,
|
|
"epoch": 0.17248580020046775,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999108217271015,
|
|
"loss": 5.7161,
|
|
"mean_token_accuracy": 0.15428307950496672,
|
|
"num_tokens": 3800991.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.698825216293335,
|
|
"epoch": 0.17290344136318075,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999099816721444,
|
|
"loss": 5.6302,
|
|
"mean_token_accuracy": 0.15540433079004287,
|
|
"num_tokens": 3811293.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.766291332244873,
|
|
"epoch": 0.17332108252589376,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999091376798673,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.15168866515159607,
|
|
"num_tokens": 3820013.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.655336523056031,
|
|
"epoch": 0.17373872368860674,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999082897502849,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.1611282467842102,
|
|
"num_tokens": 3829099.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.651612615585327,
|
|
"epoch": 0.17415636485131974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999074378834123,
|
|
"loss": 5.7326,
|
|
"mean_token_accuracy": 0.15682385265827178,
|
|
"num_tokens": 3838308.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.738585424423218,
|
|
"epoch": 0.17457400601403275,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999065820792644,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.15595242530107498,
|
|
"num_tokens": 3847650.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.805827569961548,
|
|
"epoch": 0.17499164717674573,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999057223378559,
|
|
"loss": 5.8611,
|
|
"mean_token_accuracy": 0.14233408570289613,
|
|
"num_tokens": 3857252.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.754422426223755,
|
|
"epoch": 0.17540928833945874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499904858659202,
|
|
"loss": 5.6955,
|
|
"mean_token_accuracy": 0.15864840149879456,
|
|
"num_tokens": 3865747.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.674372434616089,
|
|
"epoch": 0.17582692950217174,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999039910433179,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.16594497859477997,
|
|
"num_tokens": 3874958.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.588525819778442,
|
|
"epoch": 0.17624457066488472,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999031194902187,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.16458353102207185,
|
|
"num_tokens": 3885216.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.748322677612305,
|
|
"epoch": 0.17666221182759773,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999022439999198,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.16610947996377945,
|
|
"num_tokens": 3893973.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.731654167175293,
|
|
"epoch": 0.17707985299031073,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999013645724362,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.15839334726333618,
|
|
"num_tokens": 3903532.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.741130352020264,
|
|
"epoch": 0.1774974941530237,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999004812077836,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.16057559847831726,
|
|
"num_tokens": 3913427.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.7038579940795895,
|
|
"epoch": 0.17791513531573672,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998995939059773,
|
|
"loss": 5.8097,
|
|
"mean_token_accuracy": 0.14798093736171722,
|
|
"num_tokens": 3923870.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.693835687637329,
|
|
"epoch": 0.17833277647844972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499898702667033,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.16271054297685622,
|
|
"num_tokens": 3933469.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.6254839420318605,
|
|
"epoch": 0.1787504176411627,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998978074909661,
|
|
"loss": 5.6403,
|
|
"mean_token_accuracy": 0.16687489449977874,
|
|
"num_tokens": 3942427.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.688601303100586,
|
|
"epoch": 0.1791680588038757,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998969083777925,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.16252454817295076,
|
|
"num_tokens": 3951250.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.682954549789429,
|
|
"epoch": 0.1795856999665887,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998960053275277,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.15424496978521346,
|
|
"num_tokens": 3959969.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.671282815933227,
|
|
"epoch": 0.1800033411293017,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998950983401875,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.1546568527817726,
|
|
"num_tokens": 3968171.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.702560186386108,
|
|
"epoch": 0.1804209822920147,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998941874157882,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.16684609055519103,
|
|
"num_tokens": 3976686.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.5957166194915775,
|
|
"epoch": 0.1808386234547277,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998932725543453,
|
|
"loss": 5.7366,
|
|
"mean_token_accuracy": 0.1542557030916214,
|
|
"num_tokens": 3986552.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.746101808547974,
|
|
"epoch": 0.18125626461744068,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998923537558749,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.15404898673295975,
|
|
"num_tokens": 3995501.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.577417039871216,
|
|
"epoch": 0.1816739057801537,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998914310203932,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.16384028941392897,
|
|
"num_tokens": 4004423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.705241107940674,
|
|
"epoch": 0.1820915469428667,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998905043479163,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.15359411537647247,
|
|
"num_tokens": 4013324.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.720277500152588,
|
|
"epoch": 0.18250918810557967,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998895737384605,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.15625456869602203,
|
|
"num_tokens": 4021896.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.585773658752442,
|
|
"epoch": 0.18292682926829268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998886391920418,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.15853976160287858,
|
|
"num_tokens": 4030590.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.639527130126953,
|
|
"epoch": 0.18334447043100568,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998877007086769,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.16841819733381272,
|
|
"num_tokens": 4040041.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.724634075164795,
|
|
"epoch": 0.18376211159371866,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998867582883821,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.14944272637367248,
|
|
"num_tokens": 4049119.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.675548553466797,
|
|
"epoch": 0.18417975275643167,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998858119311739,
|
|
"loss": 5.6431,
|
|
"mean_token_accuracy": 0.1540763944387436,
|
|
"num_tokens": 4059265.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.692709350585938,
|
|
"epoch": 0.18459739391914468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998848616370689,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.15441271513700486,
|
|
"num_tokens": 4068363.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.612869834899902,
|
|
"epoch": 0.18501503508185768,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998839074060837,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.16939774602651597,
|
|
"num_tokens": 4077390.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.602217435836792,
|
|
"epoch": 0.18543267624457066,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499882949238235,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.15488070547580718,
|
|
"num_tokens": 4087331.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.898349380493164,
|
|
"epoch": 0.18585031740728367,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998819871335396,
|
|
"loss": 5.8585,
|
|
"mean_token_accuracy": 0.1453448213636875,
|
|
"num_tokens": 4096425.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.599613237380981,
|
|
"epoch": 0.18626795856999667,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998810210920142,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.16011494100093843,
|
|
"num_tokens": 4106056.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.683730888366699,
|
|
"epoch": 0.18668559973270965,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998800511136759,
|
|
"loss": 5.6968,
|
|
"mean_token_accuracy": 0.1584601417183876,
|
|
"num_tokens": 4115133.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.667567729949951,
|
|
"epoch": 0.18710324089542266,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998790771985417,
|
|
"loss": 5.5964,
|
|
"mean_token_accuracy": 0.1586738795042038,
|
|
"num_tokens": 4123630.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.640010595321655,
|
|
"epoch": 0.18752088205813566,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998780993466284,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.15695928037166595,
|
|
"num_tokens": 4133337.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.728957223892212,
|
|
"epoch": 0.18793852322084864,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998771175579534,
|
|
"loss": 5.6701,
|
|
"mean_token_accuracy": 0.15720749497413636,
|
|
"num_tokens": 4142240.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.650001859664917,
|
|
"epoch": 0.18835616438356165,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998761318325337,
|
|
"loss": 5.6434,
|
|
"mean_token_accuracy": 0.15715699940919875,
|
|
"num_tokens": 4151297.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.6392778873443605,
|
|
"epoch": 0.18877380554627465,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998751421703868,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.16495950818061828,
|
|
"num_tokens": 4160193.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.726975584030152,
|
|
"epoch": 0.18919144670898763,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998741485715297,
|
|
"loss": 5.7615,
|
|
"mean_token_accuracy": 0.15852496922016143,
|
|
"num_tokens": 4169948.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.873078060150147,
|
|
"epoch": 0.18960908787170064,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049987315103598,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.1499393455684185,
|
|
"num_tokens": 4179981.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.655186462402344,
|
|
"epoch": 0.19002672903441364,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998721495637551,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.15085280686616898,
|
|
"num_tokens": 4189172.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.6853272914886475,
|
|
"epoch": 0.19044437019712662,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998711441548726,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.15680087357759476,
|
|
"num_tokens": 4197312.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.708002233505249,
|
|
"epoch": 0.19086201135983963,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998701348093499,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.15665152966976165,
|
|
"num_tokens": 4206828.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.730845022201538,
|
|
"epoch": 0.19127965252255263,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499869121527205,
|
|
"loss": 5.6132,
|
|
"mean_token_accuracy": 0.16018779575824738,
|
|
"num_tokens": 4214835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.6554999351501465,
|
|
"epoch": 0.1916972936852656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998681043084553,
|
|
"loss": 5.7972,
|
|
"mean_token_accuracy": 0.147630412876606,
|
|
"num_tokens": 4225119.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.660569190979004,
|
|
"epoch": 0.19211493484797862,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998670831531188,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.15618418008089066,
|
|
"num_tokens": 4235257.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.665428733825683,
|
|
"epoch": 0.19253257601069163,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998660580612135,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.16061737835407258,
|
|
"num_tokens": 4244211.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.724985074996948,
|
|
"epoch": 0.1929502171734046,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998650290327569,
|
|
"loss": 5.7158,
|
|
"mean_token_accuracy": 0.15692965239286422,
|
|
"num_tokens": 4253149.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.6536462783813475,
|
|
"epoch": 0.1933678583361176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998639960677675,
|
|
"loss": 5.6279,
|
|
"mean_token_accuracy": 0.15889257192611694,
|
|
"num_tokens": 4262557.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.657335042953491,
|
|
"epoch": 0.19378549949883062,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998629591662631,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.16159564554691314,
|
|
"num_tokens": 4272881.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.599450969696045,
|
|
"epoch": 0.1942031406615436,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499861918328262,
|
|
"loss": 5.6326,
|
|
"mean_token_accuracy": 0.16337416023015977,
|
|
"num_tokens": 4281158.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.6304497718811035,
|
|
"epoch": 0.1946207818242566,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998608735537822,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.15982079207897187,
|
|
"num_tokens": 4290319.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.665145397186279,
|
|
"epoch": 0.1950384229869696,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998598248428423,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.16070850789546967,
|
|
"num_tokens": 4299276.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.7335333824157715,
|
|
"epoch": 0.19545606414968258,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998587721954604,
|
|
"loss": 5.687,
|
|
"mean_token_accuracy": 0.1566752687096596,
|
|
"num_tokens": 4308291.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.622469186782837,
|
|
"epoch": 0.1958737053123956,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.155308535695076,
|
|
"num_tokens": 4316654.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.631796360015869,
|
|
"epoch": 0.1962913464751086,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998566550914448,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.15566373467445374,
|
|
"num_tokens": 4325911.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.719413614273071,
|
|
"epoch": 0.19670898763782158,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998555906348481,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.15533148795366286,
|
|
"num_tokens": 4334846.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.713936042785645,
|
|
"epoch": 0.19712662880053458,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998545222418836,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.16010912209749223,
|
|
"num_tokens": 4343728.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.609404993057251,
|
|
"epoch": 0.1975442699632476,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998534499125701,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.1628926530480385,
|
|
"num_tokens": 4352774.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.750800704956054,
|
|
"epoch": 0.19796191112596057,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998523736469263,
|
|
"loss": 5.746,
|
|
"mean_token_accuracy": 0.15442651212215425,
|
|
"num_tokens": 4361663.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.65933666229248,
|
|
"epoch": 0.19837955228867357,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499851293444971,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.1717977210879326,
|
|
"num_tokens": 4370278.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.68487024307251,
|
|
"epoch": 0.19879719345138658,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998502093067231,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.16009533107280732,
|
|
"num_tokens": 4379010.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.69346399307251,
|
|
"epoch": 0.19921483461409956,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998491212322017,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.1543926328420639,
|
|
"num_tokens": 4388145.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.6455628871917725,
|
|
"epoch": 0.19963247577681256,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998480292214258,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.1530858799815178,
|
|
"num_tokens": 4396321.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.702960968017578,
|
|
"epoch": 0.20005011693952557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998469332744144,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.16541909873485566,
|
|
"num_tokens": 4404854.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.469099617004394,
|
|
"epoch": 0.20046775810223855,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998458333911869,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.16603398621082305,
|
|
"num_tokens": 4413890.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.7079826354980465,
|
|
"epoch": 0.20088539926495155,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998447295717624,
|
|
"loss": 5.6872,
|
|
"mean_token_accuracy": 0.15662553459405898,
|
|
"num_tokens": 4423019.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.715851497650147,
|
|
"epoch": 0.20130304042766456,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998436218161602,
|
|
"loss": 5.6255,
|
|
"mean_token_accuracy": 0.15582710802555083,
|
|
"num_tokens": 4432340.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.611751461029053,
|
|
"epoch": 0.20172068159037754,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998425101243999,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.1572697326540947,
|
|
"num_tokens": 4441834.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.6097025871276855,
|
|
"epoch": 0.20213832275309054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998413944965007,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.16356834024190903,
|
|
"num_tokens": 4450864.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.6114274024963375,
|
|
"epoch": 0.20255596391580355,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998402749324823,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.15567796379327775,
|
|
"num_tokens": 4460697.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.893751335144043,
|
|
"epoch": 0.20297360507851653,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998391514323642,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.153797747194767,
|
|
"num_tokens": 4469926.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.583089590072632,
|
|
"epoch": 0.20339124624122953,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998380239961661,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.15996050238609313,
|
|
"num_tokens": 4478818.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.703447008132935,
|
|
"epoch": 0.20380888740394254,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998368926239078,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.15723517835140227,
|
|
"num_tokens": 4487451.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.678385782241821,
|
|
"epoch": 0.20422652856665552,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499835757315609,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.15110710263252258,
|
|
"num_tokens": 4497674.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.581616687774658,
|
|
"epoch": 0.20464416972936852,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998346180712898,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.16663052439689635,
|
|
"num_tokens": 4507666.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.625546884536743,
|
|
"epoch": 0.20506181089208153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998334748909698,
|
|
"loss": 5.7454,
|
|
"mean_token_accuracy": 0.15425530821084976,
|
|
"num_tokens": 4517409.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.657826280593872,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998323277746694,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.16149946302175522,
|
|
"num_tokens": 4526495.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.665003061294556,
|
|
"epoch": 0.20589709321750752,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998311767224081,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.16810937523841857,
|
|
"num_tokens": 4535240.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.631776237487793,
|
|
"epoch": 0.20631473438022052,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998300217342067,
|
|
"loss": 5.7025,
|
|
"mean_token_accuracy": 0.156618569791317,
|
|
"num_tokens": 4544716.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.6214515209198,
|
|
"epoch": 0.2067323755429335,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998288628100851,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.1633414626121521,
|
|
"num_tokens": 4553867.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.647698307037354,
|
|
"epoch": 0.2071500167056465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998276999500636,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.1532789349555969,
|
|
"num_tokens": 4562529.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.562749671936035,
|
|
"epoch": 0.2075676578683595,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.1752343535423279,
|
|
"num_tokens": 4571041.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.565519905090332,
|
|
"epoch": 0.2079852990310725,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998253624224026,
|
|
"loss": 5.6044,
|
|
"mean_token_accuracy": 0.161303348839283,
|
|
"num_tokens": 4579914.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.644900465011597,
|
|
"epoch": 0.2084029401937855,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499824187754804,
|
|
"loss": 5.6815,
|
|
"mean_token_accuracy": 0.16097000390291213,
|
|
"num_tokens": 4590277.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.66708197593689,
|
|
"epoch": 0.2088205813564985,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998230091513872,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.16419181376695632,
|
|
"num_tokens": 4598719.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.624560022354126,
|
|
"epoch": 0.20923822251921148,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998218266121731,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.1620894342660904,
|
|
"num_tokens": 4607804.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.510728168487549,
|
|
"epoch": 0.2096558636819245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998206401371823,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.16698947846889495,
|
|
"num_tokens": 4616529.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.637687015533447,
|
|
"epoch": 0.2100735048446375,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998194497264357,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.15697978138923646,
|
|
"num_tokens": 4624545.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.640446758270263,
|
|
"epoch": 0.21049114600735047,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998182553799538,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.1600236177444458,
|
|
"num_tokens": 4633316.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.585673189163208,
|
|
"epoch": 0.21090878717006348,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998170570977579,
|
|
"loss": 5.5394,
|
|
"mean_token_accuracy": 0.16961861550807952,
|
|
"num_tokens": 4643353.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.584037351608276,
|
|
"epoch": 0.21132642833277648,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998158548798687,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.16008919924497605,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.621504116058349,
|
|
"epoch": 0.21174406949548946,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998146487263074,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.16083284914493562,
|
|
"num_tokens": 4659937.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.583824634552002,
|
|
"epoch": 0.21216171065820247,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998134386370951,
|
|
"loss": 5.5981,
|
|
"mean_token_accuracy": 0.1597536824643612,
|
|
"num_tokens": 4669396.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.717773294448852,
|
|
"epoch": 0.21257935182091547,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998122246122529,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.16459225714206696,
|
|
"num_tokens": 4679320.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.6832643985748295,
|
|
"epoch": 0.21299699298362845,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998110066518021,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.16294638812541962,
|
|
"num_tokens": 4688807.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.633354759216308,
|
|
"epoch": 0.21341463414634146,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499809784755764,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.17056376934051515,
|
|
"num_tokens": 4697819.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.584991502761841,
|
|
"epoch": 0.21383227530905446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049980855892416,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.16347702592611313,
|
|
"num_tokens": 4706931.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.608094644546509,
|
|
"epoch": 0.21424991647176747,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998073291570116,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.1649039328098297,
|
|
"num_tokens": 4716262.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.627374076843262,
|
|
"epoch": 0.21466755763448045,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998060954543404,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.16122105121612548,
|
|
"num_tokens": 4725415.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.546875810623169,
|
|
"epoch": 0.21508519879719346,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998048578161678,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.16040805876255035,
|
|
"num_tokens": 4734580.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.58602876663208,
|
|
"epoch": 0.21550283995990646,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998036162425155,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.17046085894107818,
|
|
"num_tokens": 4742966.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.587724733352661,
|
|
"epoch": 0.21592048112261944,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998023707334055,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.1627469092607498,
|
|
"num_tokens": 4751696.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.655860662460327,
|
|
"epoch": 0.21633812228533245,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998011212888592,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.16377044171094896,
|
|
"num_tokens": 4760460.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.668825340270996,
|
|
"epoch": 0.21675576344804545,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997998679088988,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.16344082206487656,
|
|
"num_tokens": 4769004.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.5735485553741455,
|
|
"epoch": 0.21717340461075843,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997986105935461,
|
|
"loss": 5.5641,
|
|
"mean_token_accuracy": 0.17153629660606384,
|
|
"num_tokens": 4777204.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.688373565673828,
|
|
"epoch": 0.21759104577347144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997973493428231,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.1608117088675499,
|
|
"num_tokens": 4786766.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.573904323577881,
|
|
"epoch": 0.21800868693618444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997960841567519,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.16307419240474702,
|
|
"num_tokens": 4796676.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.784175872802734,
|
|
"epoch": 0.21842632809889742,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997948150353548,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.16198533475399018,
|
|
"num_tokens": 4805514.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.579783344268799,
|
|
"epoch": 0.21884396926161043,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997935419786537,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.15730978101491927,
|
|
"num_tokens": 4815487.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.642004919052124,
|
|
"epoch": 0.21926161042432343,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997922649866712,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.162903268635273,
|
|
"num_tokens": 4825044.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.533287715911865,
|
|
"epoch": 0.2196792515870364,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997909840594294,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.17537373900413514,
|
|
"num_tokens": 4833875.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.520668888092041,
|
|
"epoch": 0.22009689274974942,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997896991969509,
|
|
"loss": 5.646,
|
|
"mean_token_accuracy": 0.1582174703478813,
|
|
"num_tokens": 4843317.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.6602888107299805,
|
|
"epoch": 0.22051453391246242,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997884103992581,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.15556131601333617,
|
|
"num_tokens": 4852514.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.6012287616729735,
|
|
"epoch": 0.2209321750751754,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997871176663736,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.1639481171965599,
|
|
"num_tokens": 4861260.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.607472705841064,
|
|
"epoch": 0.2213498162378884,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997858209983201,
|
|
"loss": 5.5261,
|
|
"mean_token_accuracy": 0.1611647054553032,
|
|
"num_tokens": 4869654.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.620398616790771,
|
|
"epoch": 0.22176745740060141,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997845203951202,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.15774784982204437,
|
|
"num_tokens": 4878311.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.723662614822388,
|
|
"epoch": 0.2221850985633144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997832158567967,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.15765633732080458,
|
|
"num_tokens": 4887251.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.582074880599976,
|
|
"epoch": 0.2226027397260274,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997819073833724,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.16348181664943695,
|
|
"num_tokens": 4896528.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.570661401748657,
|
|
"epoch": 0.2230203808887404,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997805949748702,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.16215746700763703,
|
|
"num_tokens": 4904962.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.605434513092041,
|
|
"epoch": 0.22343802205145338,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997792786313132,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.15934820771217345,
|
|
"num_tokens": 4914735.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.416878604888916,
|
|
"epoch": 0.2238556632141664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997779583527243,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.15913522839546204,
|
|
"num_tokens": 4924271.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.731436920166016,
|
|
"epoch": 0.2242733043768794,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997766341391268,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.15840027630329132,
|
|
"num_tokens": 4933928.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.586864900588989,
|
|
"epoch": 0.22469094553959237,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997753059905437,
|
|
"loss": 5.4023,
|
|
"mean_token_accuracy": 0.1752420797944069,
|
|
"num_tokens": 4942714.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.399338579177856,
|
|
"epoch": 0.22510858670230538,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997739739069981,
|
|
"loss": 5.5313,
|
|
"mean_token_accuracy": 0.164621265232563,
|
|
"num_tokens": 4952297.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.644370079040527,
|
|
"epoch": 0.22552622786501839,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997726378885138,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.1743430182337761,
|
|
"num_tokens": 4960947.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.593647527694702,
|
|
"epoch": 0.22594386902773136,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997712979351137,
|
|
"loss": 5.6253,
|
|
"mean_token_accuracy": 0.1603491149842739,
|
|
"num_tokens": 4969705.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.6281603336334225,
|
|
"epoch": 0.22636151019044437,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997699540468216,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.16521542072296141,
|
|
"num_tokens": 4979112.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.5321063041687015,
|
|
"epoch": 0.22677915135315738,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997686062236609,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.16602300256490707,
|
|
"num_tokens": 4987894.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.633674669265747,
|
|
"epoch": 0.22719679251587035,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997672544656553,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.1612725928425789,
|
|
"num_tokens": 4997774.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.698086166381836,
|
|
"epoch": 0.22761443367858336,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997658987728283,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.1690062776207924,
|
|
"num_tokens": 5006183.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.591877269744873,
|
|
"epoch": 0.22803207484129637,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997645391452035,
|
|
"loss": 5.5916,
|
|
"mean_token_accuracy": 0.1632835417985916,
|
|
"num_tokens": 5016909.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.610874843597412,
|
|
"epoch": 0.22844971600400935,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499763175582805,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.1621117740869522,
|
|
"num_tokens": 5027326.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.632061624526978,
|
|
"epoch": 0.22886735716672235,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997618080856566,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.15901436507701874,
|
|
"num_tokens": 5037043.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.541202545166016,
|
|
"epoch": 0.22928499832943536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997604366537823,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.16744935959577562,
|
|
"num_tokens": 5045992.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.564315366744995,
|
|
"epoch": 0.22970263949214834,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997590612872058,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.16942261159420013,
|
|
"num_tokens": 5055568.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.63058443069458,
|
|
"epoch": 0.23012028065486134,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997576819859515,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.16200867295265198,
|
|
"num_tokens": 5065512.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.484599208831787,
|
|
"epoch": 0.23053792181757435,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997562987500434,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.17104848176240922,
|
|
"num_tokens": 5074776.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.583745384216309,
|
|
"epoch": 0.23095556298028733,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997549115795058,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.16588549315929413,
|
|
"num_tokens": 5084743.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.682448768615723,
|
|
"epoch": 0.23137320414300033,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499753520474363,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.16034545600414277,
|
|
"num_tokens": 5095387.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.587224912643433,
|
|
"epoch": 0.23179084530571334,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997521254346391,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.16626937463879585,
|
|
"num_tokens": 5104628.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.622297048568726,
|
|
"epoch": 0.23220848646842632,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997507264603589,
|
|
"loss": 5.5347,
|
|
"mean_token_accuracy": 0.16671543717384338,
|
|
"num_tokens": 5113169.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.549988460540772,
|
|
"epoch": 0.23262612763113932,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997493235515466,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.16756106466054915,
|
|
"num_tokens": 5122294.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.531440925598145,
|
|
"epoch": 0.23304376879385233,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997479167082269,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.17597562521696092,
|
|
"num_tokens": 5131191.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.549725675582886,
|
|
"epoch": 0.2334614099565653,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997465059304243,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.16252151429653167,
|
|
"num_tokens": 5141974.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.6808897972106935,
|
|
"epoch": 0.23387905111927831,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997450912181637,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.16537160128355027,
|
|
"num_tokens": 5151412.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.547338819503784,
|
|
"epoch": 0.23429669228199132,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997436725714696,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.1739228755235672,
|
|
"num_tokens": 5160989.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.551234436035156,
|
|
"epoch": 0.2347143334447043,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997422499903671,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.16309013664722444,
|
|
"num_tokens": 5170241.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.731640720367432,
|
|
"epoch": 0.2351319746074173,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499740823474881,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.1557489424943924,
|
|
"num_tokens": 5180247.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.54374361038208,
|
|
"epoch": 0.2355496157701303,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997393930250363,
|
|
"loss": 5.5933,
|
|
"mean_token_accuracy": 0.16376214027404784,
|
|
"num_tokens": 5189144.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.623880338668823,
|
|
"epoch": 0.2359672569328433,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499737958640858,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.16290141642093658,
|
|
"num_tokens": 5199410.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.6456780433654785,
|
|
"epoch": 0.2363848980955563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997365203223711,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.17000638246536254,
|
|
"num_tokens": 5209032.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.440157270431518,
|
|
"epoch": 0.2368025392582693,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499735078069601,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.17118311822414398,
|
|
"num_tokens": 5217787.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.555545091629028,
|
|
"epoch": 0.23722018042098228,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997336318825728,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.1703398510813713,
|
|
"num_tokens": 5226962.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.52580771446228,
|
|
"epoch": 0.23763782158369529,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997321817613119,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.16689039915800094,
|
|
"num_tokens": 5236111.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.645787096023559,
|
|
"epoch": 0.2380554627464083,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997307277058436,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.16265233159065245,
|
|
"num_tokens": 5246628.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.622815704345703,
|
|
"epoch": 0.23847310390912127,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997292697161935,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.15912623330950737,
|
|
"num_tokens": 5255543.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.467281913757324,
|
|
"epoch": 0.23889074507183428,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499727807792387,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.17852753698825835,
|
|
"num_tokens": 5264559.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.447366380691529,
|
|
"epoch": 0.23930838623454728,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997263419344495,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.16848173439502717,
|
|
"num_tokens": 5274599.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.553721141815186,
|
|
"epoch": 0.23972602739726026,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997248721424071,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.17135296761989594,
|
|
"num_tokens": 5283495.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.591934013366699,
|
|
"epoch": 0.24014366855997327,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997233984162853,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.1711369827389717,
|
|
"num_tokens": 5292064.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.527604627609253,
|
|
"epoch": 0.24056130972268627,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997219207561099,
|
|
"loss": 5.535,
|
|
"mean_token_accuracy": 0.16105968952178956,
|
|
"num_tokens": 5301696.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.675354480743408,
|
|
"epoch": 0.24097895088539925,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997204391619068,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.15840594172477723,
|
|
"num_tokens": 5311427.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.684924793243408,
|
|
"epoch": 0.24139659204811226,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997189536337018,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.16174941658973693,
|
|
"num_tokens": 5321406.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.551355266571045,
|
|
"epoch": 0.24181423321082526,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997174641715211,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.1644423484802246,
|
|
"num_tokens": 5332257.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.504457902908325,
|
|
"epoch": 0.24223187437353827,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997159707753906,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.1703709304332733,
|
|
"num_tokens": 5341857.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.511201333999634,
|
|
"epoch": 0.24264951553625125,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.16949305385351182,
|
|
"num_tokens": 5351367.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.391738796234131,
|
|
"epoch": 0.24306715669896425,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997129721813853,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.17349923253059388,
|
|
"num_tokens": 5360627.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.531809091567993,
|
|
"epoch": 0.24348479786167726,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997114669835629,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.17700317949056626,
|
|
"num_tokens": 5369703.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.5716290950775145,
|
|
"epoch": 0.24390243902439024,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997099578518959,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.16404612362384796,
|
|
"num_tokens": 5378432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.438390588760376,
|
|
"epoch": 0.24432008018710324,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997084447864105,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.1708747535943985,
|
|
"num_tokens": 5386489.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.610124492645264,
|
|
"epoch": 0.24473772134981625,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997069277871333,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.16265049129724501,
|
|
"num_tokens": 5395908.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.710176420211792,
|
|
"epoch": 0.24515536251252923,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997054068540908,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.16824057847261428,
|
|
"num_tokens": 5404822.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.442877244949341,
|
|
"epoch": 0.24557300367524224,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997038819873098,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.1711698964238167,
|
|
"num_tokens": 5413980.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.5252721309661865,
|
|
"epoch": 0.24599064483795524,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997023531868167,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.16247909963130952,
|
|
"num_tokens": 5423538.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.515257501602173,
|
|
"epoch": 0.24640828600066822,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997008204526386,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.16875504106283187,
|
|
"num_tokens": 5431930.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.48965220451355,
|
|
"epoch": 0.24682592716338123,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996992837848021,
|
|
"loss": 5.4508,
|
|
"mean_token_accuracy": 0.1761811926960945,
|
|
"num_tokens": 5440721.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.506892585754395,
|
|
"epoch": 0.24724356832609423,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996977431833342,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.1642148897051811,
|
|
"num_tokens": 5449617.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.5657142162322994,
|
|
"epoch": 0.2476612094888072,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996961986482618,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.16744059771299363,
|
|
"num_tokens": 5458827.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.565783166885376,
|
|
"epoch": 0.24807885065152022,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996946501796119,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.17086558043956757,
|
|
"num_tokens": 5467348.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.554220914840698,
|
|
"epoch": 0.24849649181423322,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996930977774118,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.15979193449020385,
|
|
"num_tokens": 5476645.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.590994024276734,
|
|
"epoch": 0.2489141329769462,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996915414416885,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.16303199231624604,
|
|
"num_tokens": 5486120.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.6555492877960205,
|
|
"epoch": 0.2493317741396592,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996899811724693,
|
|
"loss": 5.5378,
|
|
"mean_token_accuracy": 0.1691664695739746,
|
|
"num_tokens": 5495313.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.537061023712158,
|
|
"epoch": 0.2497494153023722,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996884169697816,
|
|
"loss": 5.5371,
|
|
"mean_token_accuracy": 0.16722940653562546,
|
|
"num_tokens": 5504587.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.468687248229981,
|
|
"epoch": 0.2501670564650852,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996868488336526,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.16358605027198792,
|
|
"num_tokens": 5514188.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.579990291595459,
|
|
"epoch": 0.25058469762779817,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996852767641099,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.16043460369110107,
|
|
"num_tokens": 5524075.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.25058469762779817,
|
|
"eval_entropy": 5.461522004887654,
|
|
"eval_loss": 5.523029327392578,
|
|
"eval_mean_token_accuracy": 0.17474948998569836,
|
|
"eval_num_tokens": 5524075.0,
|
|
"eval_runtime": 27.2289,
|
|
"eval_samples_per_second": 1386.87,
|
|
"eval_steps_per_second": 173.382,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.4971150875091555,
|
|
"epoch": 0.2510023387905112,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996837007611811,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.17106565684080124,
|
|
"num_tokens": 5533323.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.4650226593017575,
|
|
"epoch": 0.2514199799532242,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996821208248935,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.17289367467164993,
|
|
"num_tokens": 5542288.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.613493633270264,
|
|
"epoch": 0.25183762111593716,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996805369552749,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.163363116979599,
|
|
"num_tokens": 5550869.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.449234056472778,
|
|
"epoch": 0.2522552622786502,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996789491523532,
|
|
"loss": 5.4819,
|
|
"mean_token_accuracy": 0.17674408853054047,
|
|
"num_tokens": 5560147.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.469293308258057,
|
|
"epoch": 0.2526729034413632,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996773574161559,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.17348119765520095,
|
|
"num_tokens": 5568358.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.484114408493042,
|
|
"epoch": 0.25309054460407615,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996757617467112,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.1649644508957863,
|
|
"num_tokens": 5577755.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.547186088562012,
|
|
"epoch": 0.2535081857667892,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996741621440466,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.1583195373415947,
|
|
"num_tokens": 5587515.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.662641334533691,
|
|
"epoch": 0.25392582692950216,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996725586081906,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.15580229461193085,
|
|
"num_tokens": 5597860.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.5714374542236325,
|
|
"epoch": 0.25434346809221514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996709511391709,
|
|
"loss": 5.5374,
|
|
"mean_token_accuracy": 0.1693472683429718,
|
|
"num_tokens": 5607302.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.583249855041504,
|
|
"epoch": 0.2547611092549282,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996693397370158,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.16309259384870528,
|
|
"num_tokens": 5616345.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.533199739456177,
|
|
"epoch": 0.25517875041764115,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996677244017534,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.16947476267814637,
|
|
"num_tokens": 5624745.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.5545299530029295,
|
|
"epoch": 0.25559639158035413,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996661051334121,
|
|
"loss": 5.5197,
|
|
"mean_token_accuracy": 0.15930449813604355,
|
|
"num_tokens": 5634022.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.545503568649292,
|
|
"epoch": 0.25601403274306717,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996644819320201,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.16942096054553984,
|
|
"num_tokens": 5643631.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.583652544021606,
|
|
"epoch": 0.25643167390578014,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996628547976061,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.16339723616838456,
|
|
"num_tokens": 5653155.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.585376787185669,
|
|
"epoch": 0.2568493150684932,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996612237301983,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.16842040419578552,
|
|
"num_tokens": 5663091.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.438110208511352,
|
|
"epoch": 0.25726695623120616,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996595887298254,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.1753868818283081,
|
|
"num_tokens": 5671885.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.550532436370849,
|
|
"epoch": 0.25768459739391913,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499657949796516,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.1669400379061699,
|
|
"num_tokens": 5680225.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.392565679550171,
|
|
"epoch": 0.25810223855663217,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996563069302986,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.17783385515213013,
|
|
"num_tokens": 5689456.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.4940855503082275,
|
|
"epoch": 0.25851987971934515,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996546601312023,
|
|
"loss": 5.4581,
|
|
"mean_token_accuracy": 0.17149127870798112,
|
|
"num_tokens": 5698127.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.550233840942383,
|
|
"epoch": 0.2589375208820581,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996530093992558,
|
|
"loss": 5.5085,
|
|
"mean_token_accuracy": 0.17063496112823487,
|
|
"num_tokens": 5706825.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.553879499435425,
|
|
"epoch": 0.25935516204477116,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996513547344877,
|
|
"loss": 5.4587,
|
|
"mean_token_accuracy": 0.1669582650065422,
|
|
"num_tokens": 5715677.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.416211986541748,
|
|
"epoch": 0.25977280320748414,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996496961369274,
|
|
"loss": 5.3803,
|
|
"mean_token_accuracy": 0.1699922949075699,
|
|
"num_tokens": 5725371.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.537308883666992,
|
|
"epoch": 0.2601904443701971,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996480336066037,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.17023330479860305,
|
|
"num_tokens": 5734664.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.552717208862305,
|
|
"epoch": 0.26060808553291015,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996463671435458,
|
|
"loss": 5.4886,
|
|
"mean_token_accuracy": 0.1722761482000351,
|
|
"num_tokens": 5743870.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.432164907455444,
|
|
"epoch": 0.26102572669562313,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996446967477829,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.16911642849445344,
|
|
"num_tokens": 5752855.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.552587652206421,
|
|
"epoch": 0.2614433678583361,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996430224193441,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.16505547910928725,
|
|
"num_tokens": 5762435.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.599203205108642,
|
|
"epoch": 0.26186100902104914,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996413441582589,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.16358712464570999,
|
|
"num_tokens": 5771463.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.583684873580933,
|
|
"epoch": 0.2622786501837621,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996396619645564,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.16209518164396286,
|
|
"num_tokens": 5780530.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.507178544998169,
|
|
"epoch": 0.2626962913464751,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996379758382662,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.17605946063995362,
|
|
"num_tokens": 5789199.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.605119609832764,
|
|
"epoch": 0.26311393250918813,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499636285779418,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.16322802305221557,
|
|
"num_tokens": 5799170.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.559698247909546,
|
|
"epoch": 0.2635315736719011,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996345917880412,
|
|
"loss": 5.5178,
|
|
"mean_token_accuracy": 0.1654113933444023,
|
|
"num_tokens": 5807662.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.459578895568848,
|
|
"epoch": 0.2639492148346141,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996328938641654,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.17274057120084763,
|
|
"num_tokens": 5815790.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.572559070587158,
|
|
"epoch": 0.2643668559973271,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996311920078204,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.1730218067765236,
|
|
"num_tokens": 5824746.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.449925374984741,
|
|
"epoch": 0.2647844971600401,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996294862190361,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.17265160679817199,
|
|
"num_tokens": 5833678.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.483268070220947,
|
|
"epoch": 0.2652021383227531,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499627776497842,
|
|
"loss": 5.4971,
|
|
"mean_token_accuracy": 0.1684225857257843,
|
|
"num_tokens": 5842218.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.695554304122925,
|
|
"epoch": 0.2656197794854661,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996260628442686,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.15670068114995955,
|
|
"num_tokens": 5853250.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.482328844070435,
|
|
"epoch": 0.2660374206481791,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996243452583454,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.17305591702461243,
|
|
"num_tokens": 5862661.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.569812154769897,
|
|
"epoch": 0.26645506181089207,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996226237401028,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.16395057886838912,
|
|
"num_tokens": 5872327.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.441321468353271,
|
|
"epoch": 0.2668727029736051,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996208982895706,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.17318300008773804,
|
|
"num_tokens": 5881539.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.619724702835083,
|
|
"epoch": 0.2672903441363181,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996191689067794,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.16643642708659173,
|
|
"num_tokens": 5891602.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.484193992614746,
|
|
"epoch": 0.26770798529903106,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996174355917591,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.1677042007446289,
|
|
"num_tokens": 5899831.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.6453687191009525,
|
|
"epoch": 0.2681256264617441,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996156983445404,
|
|
"loss": 5.6128,
|
|
"mean_token_accuracy": 0.15973187386989593,
|
|
"num_tokens": 5909193.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.596530437469482,
|
|
"epoch": 0.26854326762445707,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996139571651534,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.1631033092737198,
|
|
"num_tokens": 5919353.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.430617761611939,
|
|
"epoch": 0.26896090878717005,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996122120536288,
|
|
"loss": 5.4745,
|
|
"mean_token_accuracy": 0.17367395162582397,
|
|
"num_tokens": 5927853.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.4728278636932375,
|
|
"epoch": 0.2693785499498831,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996104630099969,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.16607874929904937,
|
|
"num_tokens": 5937943.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.565532922744751,
|
|
"epoch": 0.26979619111259606,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996087100342885,
|
|
"loss": 5.4689,
|
|
"mean_token_accuracy": 0.17290828227996827,
|
|
"num_tokens": 5946213.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.501755237579346,
|
|
"epoch": 0.27021383227530904,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996069531265345,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.17148633301258087,
|
|
"num_tokens": 5954997.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.414116048812867,
|
|
"epoch": 0.2706314734380221,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996051922867653,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.17986717075109482,
|
|
"num_tokens": 5963947.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.482024765014648,
|
|
"epoch": 0.27104911460073505,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996034275150118,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.16966199427843093,
|
|
"num_tokens": 5972077.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.4911558628082275,
|
|
"epoch": 0.27146675576344803,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499601658811305,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.16965609639883042,
|
|
"num_tokens": 5982649.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.577063179016113,
|
|
"epoch": 0.27188439692616106,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995998861756758,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.16891886293888092,
|
|
"num_tokens": 5991349.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.471480846405029,
|
|
"epoch": 0.27230203808887404,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995981096081552,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.1755162000656128,
|
|
"num_tokens": 6000555.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.650067710876465,
|
|
"epoch": 0.272719679251587,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995963291087744,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.15589477270841598,
|
|
"num_tokens": 6009554.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.569346714019775,
|
|
"epoch": 0.27313732041430006,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995945446775645,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.16038435250520705,
|
|
"num_tokens": 6019330.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.587334251403808,
|
|
"epoch": 0.27355496157701303,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995927563145566,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.16468510627746583,
|
|
"num_tokens": 6028527.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.563228559494019,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995909640197825,
|
|
"loss": 5.4647,
|
|
"mean_token_accuracy": 0.17105194479227065,
|
|
"num_tokens": 6038223.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.444104480743408,
|
|
"epoch": 0.27439024390243905,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995891677932729,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.17711416333913804,
|
|
"num_tokens": 6047459.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.602990055084229,
|
|
"epoch": 0.274807885065152,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995873676350597,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.16400577127933502,
|
|
"num_tokens": 6057322.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.64007306098938,
|
|
"epoch": 0.275225526227865,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995855635451743,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.15748985335230828,
|
|
"num_tokens": 6067520.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.563010215759277,
|
|
"epoch": 0.27564316739057804,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995837555236484,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.16345635652542115,
|
|
"num_tokens": 6076729.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.6180760860443115,
|
|
"epoch": 0.276060808553291,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995819435705133,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.16132914572954177,
|
|
"num_tokens": 6086529.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.601102066040039,
|
|
"epoch": 0.276478449716004,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995801276858011,
|
|
"loss": 5.5461,
|
|
"mean_token_accuracy": 0.17339718639850615,
|
|
"num_tokens": 6095784.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.643276929855347,
|
|
"epoch": 0.276896090878717,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995783078695434,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.1667674422264099,
|
|
"num_tokens": 6104626.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.467655038833618,
|
|
"epoch": 0.27731373204143,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499576484121772,
|
|
"loss": 5.4733,
|
|
"mean_token_accuracy": 0.1719300702214241,
|
|
"num_tokens": 6113758.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.589902544021607,
|
|
"epoch": 0.277731373204143,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995746564425191,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.17106839418411254,
|
|
"num_tokens": 6123265.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.580819034576416,
|
|
"epoch": 0.278149014366856,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995728248318163,
|
|
"loss": 5.5676,
|
|
"mean_token_accuracy": 0.16482732594013214,
|
|
"num_tokens": 6132855.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.468076133728028,
|
|
"epoch": 0.278566655529569,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995709892896961,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.16931613385677338,
|
|
"num_tokens": 6142739.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.483571529388428,
|
|
"epoch": 0.278984296692282,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995691498161903,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.1695520266890526,
|
|
"num_tokens": 6152169.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.3815367221832275,
|
|
"epoch": 0.279401937854995,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995673064113313,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.1787784531712532,
|
|
"num_tokens": 6160235.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.49701042175293,
|
|
"epoch": 0.279819579017708,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995654590751513,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.16954068541526796,
|
|
"num_tokens": 6169440.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.473315906524658,
|
|
"epoch": 0.28023722018042097,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995636078076825,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.1779964342713356,
|
|
"num_tokens": 6178456.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.461573886871338,
|
|
"epoch": 0.280654861343134,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995617526089575,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.16690640151500702,
|
|
"num_tokens": 6186844.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.531739711761475,
|
|
"epoch": 0.281072502505847,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995598934790087,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.17161790579557418,
|
|
"num_tokens": 6196117.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.4806375980377195,
|
|
"epoch": 0.28149014366855996,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995580304178687,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.17214852422475815,
|
|
"num_tokens": 6204636.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.398985528945923,
|
|
"epoch": 0.281907784831273,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995561634255701,
|
|
"loss": 5.4457,
|
|
"mean_token_accuracy": 0.1673709973692894,
|
|
"num_tokens": 6214537.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.4943078517913815,
|
|
"epoch": 0.28232542599398597,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995542925021455,
|
|
"loss": 5.5147,
|
|
"mean_token_accuracy": 0.16867199391126633,
|
|
"num_tokens": 6224753.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.747494173049927,
|
|
"epoch": 0.28274306715669895,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995524176476277,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.16499322801828384,
|
|
"num_tokens": 6233842.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.621364450454712,
|
|
"epoch": 0.283160708319412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995505388620497,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.17118486315011977,
|
|
"num_tokens": 6243467.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.429578542709351,
|
|
"epoch": 0.28357834948212496,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499548656145444,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.1568418487906456,
|
|
"num_tokens": 6253263.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.573283243179321,
|
|
"epoch": 0.28399599064483794,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995467694978439,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.17850250601768494,
|
|
"num_tokens": 6262249.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.463663387298584,
|
|
"epoch": 0.28441363180755097,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995448789192823,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.1717173531651497,
|
|
"num_tokens": 6271154.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.4220223903656,
|
|
"epoch": 0.28483127297026395,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995429844097922,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.1784306287765503,
|
|
"num_tokens": 6280377.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.57632474899292,
|
|
"epoch": 0.2852489141329769,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995410859694071,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.1689310923218727,
|
|
"num_tokens": 6289941.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.488957262039184,
|
|
"epoch": 0.28566655529568996,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995391835981599,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.16624608933925628,
|
|
"num_tokens": 6299281.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.595778846740723,
|
|
"epoch": 0.28608419645840294,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499537277296084,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.16632925122976303,
|
|
"num_tokens": 6309408.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.50165581703186,
|
|
"epoch": 0.2865018376211159,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995353670632127,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.17109988778829574,
|
|
"num_tokens": 6318979.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.483353614807129,
|
|
"epoch": 0.28691947878382895,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995334528995797,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.17871294766664506,
|
|
"num_tokens": 6327616.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.409444570541382,
|
|
"epoch": 0.28733711994654193,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995315348052182,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.1814719870686531,
|
|
"num_tokens": 6336486.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.418563032150269,
|
|
"epoch": 0.2877547611092549,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499529612780162,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.16858992278575896,
|
|
"num_tokens": 6345671.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.611011266708374,
|
|
"epoch": 0.28817240227196794,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995276868244446,
|
|
"loss": 5.5455,
|
|
"mean_token_accuracy": 0.16791318058967591,
|
|
"num_tokens": 6354534.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.499365186691284,
|
|
"epoch": 0.2885900434346809,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995257569380998,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.1744227558374405,
|
|
"num_tokens": 6364052.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.545021820068359,
|
|
"epoch": 0.2890076845973939,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995238231211614,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.1676422566175461,
|
|
"num_tokens": 6373305.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.512579870223999,
|
|
"epoch": 0.28942532576010693,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995218853736631,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.1660549208521843,
|
|
"num_tokens": 6382673.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.534687423706055,
|
|
"epoch": 0.2898429669228199,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995199436956391,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.16030752062797546,
|
|
"num_tokens": 6392122.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.603588008880616,
|
|
"epoch": 0.2902606080855329,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995179980871231,
|
|
"loss": 5.5507,
|
|
"mean_token_accuracy": 0.1647276908159256,
|
|
"num_tokens": 6401130.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.497493600845337,
|
|
"epoch": 0.2906782492482459,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995160485481493,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.17015280574560165,
|
|
"num_tokens": 6409471.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.416902780532837,
|
|
"epoch": 0.2910958904109589,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499514095078752,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.16760370135307312,
|
|
"num_tokens": 6418902.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.552921962738037,
|
|
"epoch": 0.2915135315736719,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499512137678965,
|
|
"loss": 5.5363,
|
|
"mean_token_accuracy": 0.1662679061293602,
|
|
"num_tokens": 6428529.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.490020132064819,
|
|
"epoch": 0.2919311727363849,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995101763488229,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.17481506168842315,
|
|
"num_tokens": 6437460.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.474491262435913,
|
|
"epoch": 0.2923488138990979,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995082110883599,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.1738422319293022,
|
|
"num_tokens": 6446005.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.478244733810425,
|
|
"epoch": 0.29276645506181087,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995062418976104,
|
|
"loss": 5.4825,
|
|
"mean_token_accuracy": 0.17011081129312516,
|
|
"num_tokens": 6455241.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.546651840209961,
|
|
"epoch": 0.2931840962245239,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995042687766089,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.1717524617910385,
|
|
"num_tokens": 6464748.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.584757280349732,
|
|
"epoch": 0.2936017373872369,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995022917253899,
|
|
"loss": 5.524,
|
|
"mean_token_accuracy": 0.16998693495988845,
|
|
"num_tokens": 6473834.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.469439220428467,
|
|
"epoch": 0.29401937854994986,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995003107439882,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.1739688917994499,
|
|
"num_tokens": 6482169.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.410130739212036,
|
|
"epoch": 0.2944370197126629,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994983258324383,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.17411208897829056,
|
|
"num_tokens": 6491798.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.402098608016968,
|
|
"epoch": 0.2948546608753759,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994963369907748,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.17219721227884294,
|
|
"num_tokens": 6500143.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.369478321075439,
|
|
"epoch": 0.29527230203808885,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994943442190328,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.16979831457138062,
|
|
"num_tokens": 6509745.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.628178644180298,
|
|
"epoch": 0.2956899432008019,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994923475172471,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.163117353618145,
|
|
"num_tokens": 6520931.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.5175331115722654,
|
|
"epoch": 0.29610758436351486,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994903468854527,
|
|
"loss": 5.4896,
|
|
"mean_token_accuracy": 0.17120033651590347,
|
|
"num_tokens": 6529774.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.425450468063355,
|
|
"epoch": 0.29652522552622784,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994883423236843,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.16883310824632644,
|
|
"num_tokens": 6538922.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.456408739089966,
|
|
"epoch": 0.2969428666889409,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994863338319775,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.1734740749001503,
|
|
"num_tokens": 6548891.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.396758222579956,
|
|
"epoch": 0.29736050785165385,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994843214103672,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.16934687346220018,
|
|
"num_tokens": 6557025.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.520787620544434,
|
|
"epoch": 0.29777814901436683,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994823050588886,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.17021430730819703,
|
|
"num_tokens": 6567037.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.481213045120239,
|
|
"epoch": 0.29819579017707987,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499480284777577,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.17070177495479583,
|
|
"num_tokens": 6576766.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.488879442214966,
|
|
"epoch": 0.29861343133979285,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994782605664677,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.17389861792325972,
|
|
"num_tokens": 6585576.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.533296680450439,
|
|
"epoch": 0.2990310725025058,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004994762324255965,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.16581012904644013,
|
|
"num_tokens": 6594463.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.436222791671753,
|
|
"epoch": 0.29944871366521886,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994742003549986,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.16841213405132294,
|
|
"num_tokens": 6603651.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.515470027923584,
|
|
"epoch": 0.29986635482793184,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994721643547095,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.17240571826696396,
|
|
"num_tokens": 6612950.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.525665330886841,
|
|
"epoch": 0.3002839959906448,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499470124424765,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.1754685029387474,
|
|
"num_tokens": 6622013.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.503145170211792,
|
|
"epoch": 0.30070163715335785,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994680805652008,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.17114405781030656,
|
|
"num_tokens": 6632046.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.509345245361328,
|
|
"epoch": 0.3011192783160708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994660327760527,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.17287831604480744,
|
|
"num_tokens": 6641169.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.460749101638794,
|
|
"epoch": 0.3015369194787838,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994639810573565,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.18106640875339508,
|
|
"num_tokens": 6649663.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.547510719299316,
|
|
"epoch": 0.30195456064149684,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499461925409148,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.16402754783630372,
|
|
"num_tokens": 6659448.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.565422201156617,
|
|
"epoch": 0.3023722018042098,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994598658314634,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.17040248960256577,
|
|
"num_tokens": 6670314.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.487205886840821,
|
|
"epoch": 0.3027898429669228,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994578023243386,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.17701876014471055,
|
|
"num_tokens": 6679413.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.462418937683106,
|
|
"epoch": 0.30320748412963583,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994557348878098,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.17467287182807922,
|
|
"num_tokens": 6688439.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.500660133361817,
|
|
"epoch": 0.3036251252923488,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994536635219133,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.17729663252830505,
|
|
"num_tokens": 6697471.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.53426079750061,
|
|
"epoch": 0.3040427664550618,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994515882266852,
|
|
"loss": 5.4637,
|
|
"mean_token_accuracy": 0.1736002594232559,
|
|
"num_tokens": 6706698.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.389495468139648,
|
|
"epoch": 0.3044604076177748,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994495090021618,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.1806873559951782,
|
|
"num_tokens": 6715676.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.371573352813721,
|
|
"epoch": 0.3048780487804878,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994474258483796,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.17871695756912231,
|
|
"num_tokens": 6723818.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.5329201221466064,
|
|
"epoch": 0.3052956899432008,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994453387653751,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.17155028581619264,
|
|
"num_tokens": 6733450.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.5077282905578615,
|
|
"epoch": 0.3057133311059138,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994432477531847,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.1691980928182602,
|
|
"num_tokens": 6743142.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.3698314189910885,
|
|
"epoch": 0.3061309722686268,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994411528118452,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.17547308504581452,
|
|
"num_tokens": 6752185.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.382838296890259,
|
|
"epoch": 0.30654861343133977,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994390539413931,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.16950728744268417,
|
|
"num_tokens": 6761549.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.464862394332886,
|
|
"epoch": 0.3069662545940528,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994369511418652,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.17317559719085693,
|
|
"num_tokens": 6770395.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.665520048141479,
|
|
"epoch": 0.3073838957567658,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994348444132983,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.17058894634246827,
|
|
"num_tokens": 6779154.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.412521505355835,
|
|
"epoch": 0.30780153691947876,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994327337557293,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.18299008756875992,
|
|
"num_tokens": 6789263.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.45570969581604,
|
|
"epoch": 0.3082191780821918,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994306191691952,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.166125063598156,
|
|
"num_tokens": 6797985.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.499072170257568,
|
|
"epoch": 0.30863681924490477,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994285006537329,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.17336190789937972,
|
|
"num_tokens": 6807566.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.451264333724976,
|
|
"epoch": 0.30905446040761775,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994263782093796,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.17076193541288376,
|
|
"num_tokens": 6815637.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.440542793273925,
|
|
"epoch": 0.3094721015703308,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994242518361723,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.17853307276964187,
|
|
"num_tokens": 6823721.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.552204942703247,
|
|
"epoch": 0.30988974273304376,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994221215341484,
|
|
"loss": 5.4947,
|
|
"mean_token_accuracy": 0.16985803246498107,
|
|
"num_tokens": 6833437.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.461875104904175,
|
|
"epoch": 0.31030738389575674,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994199873033452,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.16892331689596177,
|
|
"num_tokens": 6842287.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.549509859085083,
|
|
"epoch": 0.3107250250584698,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994178491437999,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.16952035278081895,
|
|
"num_tokens": 6851520.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.418500137329102,
|
|
"epoch": 0.31114266622118275,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994157070555501,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.17235054969787597,
|
|
"num_tokens": 6861219.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.520118331909179,
|
|
"epoch": 0.31156030738389573,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994135610386331,
|
|
"loss": 5.5773,
|
|
"mean_token_accuracy": 0.16754324436187745,
|
|
"num_tokens": 6870525.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.609558916091919,
|
|
"epoch": 0.31197794854660876,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994114110930867,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.16462523490190506,
|
|
"num_tokens": 6880183.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.485359001159668,
|
|
"epoch": 0.31239558970932174,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994092572189483,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.16772003024816512,
|
|
"num_tokens": 6890442.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.494738817214966,
|
|
"epoch": 0.3128132308720348,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994070994162558,
|
|
"loss": 5.4216,
|
|
"mean_token_accuracy": 0.17486200034618377,
|
|
"num_tokens": 6900091.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.4695563316345215,
|
|
"epoch": 0.31323087203474775,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994049376850471,
|
|
"loss": 5.4689,
|
|
"mean_token_accuracy": 0.17180595993995668,
|
|
"num_tokens": 6910489.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.496180200576783,
|
|
"epoch": 0.31364851319746073,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994027720253596,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.1682304173707962,
|
|
"num_tokens": 6919895.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.693031644821167,
|
|
"epoch": 0.31406615436017377,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994006024372315,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.16491315960884095,
|
|
"num_tokens": 6929511.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.454358005523682,
|
|
"epoch": 0.31448379552288674,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993984289207007,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.18178811967372893,
|
|
"num_tokens": 6938059.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.404311084747315,
|
|
"epoch": 0.3149014366855997,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993962514758054,
|
|
"loss": 5.3914,
|
|
"mean_token_accuracy": 0.17555590122938156,
|
|
"num_tokens": 6946894.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.5242852687835695,
|
|
"epoch": 0.31531907784831276,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993940701025836,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.1679450422525406,
|
|
"num_tokens": 6955494.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.482671546936035,
|
|
"epoch": 0.31573671901102573,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993918848010734,
|
|
"loss": 5.4947,
|
|
"mean_token_accuracy": 0.1700427144765854,
|
|
"num_tokens": 6964347.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.541811227798462,
|
|
"epoch": 0.3161543601737387,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993896955713133,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.16363491863012314,
|
|
"num_tokens": 6974750.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.4976883888244625,
|
|
"epoch": 0.31657200133645175,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993875024133414,
|
|
"loss": 5.4639,
|
|
"mean_token_accuracy": 0.1697466790676117,
|
|
"num_tokens": 6984228.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.449398231506348,
|
|
"epoch": 0.3169896424991647,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993853053271962,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.17396792620420456,
|
|
"num_tokens": 6993173.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.663131284713745,
|
|
"epoch": 0.3174072836618777,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993831043129161,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.1585911437869072,
|
|
"num_tokens": 7003486.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.448543548583984,
|
|
"epoch": 0.31782492482459074,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004993808993705397,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.17939800918102264,
|
|
"num_tokens": 7011985.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.462221574783325,
|
|
"epoch": 0.3182425659873037,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993786905001055,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.176728555560112,
|
|
"num_tokens": 7021148.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.46138858795166,
|
|
"epoch": 0.3186602071500167,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993764777016524,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.1701902762055397,
|
|
"num_tokens": 7030110.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.465259981155396,
|
|
"epoch": 0.31907784831272973,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993742609752188,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.1755315348505974,
|
|
"num_tokens": 7039428.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.609820795059204,
|
|
"epoch": 0.3194954894754427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993720403208438,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.1672436237335205,
|
|
"num_tokens": 7048703.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.4761299133300785,
|
|
"epoch": 0.3199131306381557,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499369815738566,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.16614928096532822,
|
|
"num_tokens": 7057612.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.477329874038697,
|
|
"epoch": 0.3203307718008687,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993675872284248,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.1730633869767189,
|
|
"num_tokens": 7066660.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.435452938079834,
|
|
"epoch": 0.3207484129635817,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993653547904586,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.16408761739730834,
|
|
"num_tokens": 7075368.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.454200029373169,
|
|
"epoch": 0.3211660541262947,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499363118424707,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.17837097644805908,
|
|
"num_tokens": 7085276.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.4827862739562985,
|
|
"epoch": 0.3215836952890077,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993608781312088,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.16890606433153152,
|
|
"num_tokens": 7094292.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.619381523132324,
|
|
"epoch": 0.3220013364517207,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993586339100035,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.16210833191871643,
|
|
"num_tokens": 7104712.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.581846046447754,
|
|
"epoch": 0.32241897761443367,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993563857611301,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.18202234506607057,
|
|
"num_tokens": 7113297.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.394202089309692,
|
|
"epoch": 0.3228366187771467,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993541336846283,
|
|
"loss": 5.4533,
|
|
"mean_token_accuracy": 0.1653970956802368,
|
|
"num_tokens": 7122706.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.512542057037353,
|
|
"epoch": 0.3232542599398597,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993518776805372,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.17372276186943053,
|
|
"num_tokens": 7131939.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.3669188022613525,
|
|
"epoch": 0.32367190110257266,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993496177488965,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.18179777413606643,
|
|
"num_tokens": 7141016.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.382031631469727,
|
|
"epoch": 0.3240895422652857,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993473538897457,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.18906042873859405,
|
|
"num_tokens": 7149177.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.469439220428467,
|
|
"epoch": 0.32450718342799867,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993450861031243,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.17814804166555404,
|
|
"num_tokens": 7157839.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.582052564620971,
|
|
"epoch": 0.32492482459071165,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993428143890722,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.16474749743938447,
|
|
"num_tokens": 7167759.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.6012077808380125,
|
|
"epoch": 0.3253424657534247,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993405387476291,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.16357818096876145,
|
|
"num_tokens": 7177141.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.377801370620728,
|
|
"epoch": 0.32576010691613766,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993382591788349,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.17757417857646943,
|
|
"num_tokens": 7185350.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.352601861953735,
|
|
"epoch": 0.32617774807885064,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993359756827293,
|
|
"loss": 5.3258,
|
|
"mean_token_accuracy": 0.17330418080091475,
|
|
"num_tokens": 7194073.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.51496434211731,
|
|
"epoch": 0.32659538924156367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993336882593524,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.16401236206293107,
|
|
"num_tokens": 7203421.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.389591217041016,
|
|
"epoch": 0.32701303040427665,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993313969087444,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.17551216781139373,
|
|
"num_tokens": 7212548.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.519296264648437,
|
|
"epoch": 0.32743067156698963,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993291016309452,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.1692492887377739,
|
|
"num_tokens": 7221668.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.46710615158081,
|
|
"epoch": 0.32784831272970266,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499326802425995,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.1661408171057701,
|
|
"num_tokens": 7231775.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.508456468582153,
|
|
"epoch": 0.32826595389241564,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993244992939342,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.17021936625242234,
|
|
"num_tokens": 7241264.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.513637828826904,
|
|
"epoch": 0.3286835950551286,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499322192234803,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.16775393933057786,
|
|
"num_tokens": 7250519.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.558846855163575,
|
|
"epoch": 0.32910123621784165,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993198812486418,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.16846247613430024,
|
|
"num_tokens": 7259533.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.421068096160889,
|
|
"epoch": 0.32951887738055463,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499317566335491,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.17600925415754318,
|
|
"num_tokens": 7268980.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.460406970977783,
|
|
"epoch": 0.3299365185432676,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993152474953913,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.16838183552026748,
|
|
"num_tokens": 7277126.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.517564821243286,
|
|
"epoch": 0.33035415970598064,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993129247283831,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.18117072880268098,
|
|
"num_tokens": 7286223.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.446171569824219,
|
|
"epoch": 0.3307718008686936,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993105980345071,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.17625371664762496,
|
|
"num_tokens": 7295054.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.449082612991333,
|
|
"epoch": 0.3311894420314066,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993082674138042,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.17082341611385346,
|
|
"num_tokens": 7304502.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.513706970214844,
|
|
"epoch": 0.33160708319411963,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499305932866315,
|
|
"loss": 5.4101,
|
|
"mean_token_accuracy": 0.17128008902072905,
|
|
"num_tokens": 7314093.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.487787532806396,
|
|
"epoch": 0.3320247243568326,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993035943920805,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.17096492648124695,
|
|
"num_tokens": 7323059.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.577842712402344,
|
|
"epoch": 0.3324423655195456,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993012519911416,
|
|
"loss": 5.5601,
|
|
"mean_token_accuracy": 0.16351205110549927,
|
|
"num_tokens": 7332596.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.440038442611694,
|
|
"epoch": 0.3328600066822586,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992989056635392,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.17744496315717698,
|
|
"num_tokens": 7341671.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.377516365051269,
|
|
"epoch": 0.3332776478449716,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992965554093146,
|
|
"loss": 5.4915,
|
|
"mean_token_accuracy": 0.17166960388422012,
|
|
"num_tokens": 7350344.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.5424505233764645,
|
|
"epoch": 0.3336952890076846,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992942012285086,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.17335852086544037,
|
|
"num_tokens": 7359844.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.500360536575317,
|
|
"epoch": 0.3341129301703976,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992918431211629,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.17371536046266556,
|
|
"num_tokens": 7369377.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.457582235336304,
|
|
"epoch": 0.3345305713331106,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992894810873183,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.1774983748793602,
|
|
"num_tokens": 7378814.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.443440914154053,
|
|
"epoch": 0.33494821249582357,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992871151270165,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.1764570638537407,
|
|
"num_tokens": 7387333.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.421675539016723,
|
|
"epoch": 0.3353658536585366,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992847452402986,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.17375606745481492,
|
|
"num_tokens": 7396895.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.496244049072265,
|
|
"epoch": 0.3357834948212496,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992823714272064,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.17418541759252548,
|
|
"num_tokens": 7406430.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.433465576171875,
|
|
"epoch": 0.33620113598396256,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004992799936877813,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.18776014894247056,
|
|
"num_tokens": 7415224.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.561156797409057,
|
|
"epoch": 0.3366187771466756,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004992776120220649,
|
|
"loss": 5.607,
|
|
"mean_token_accuracy": 0.161159510910511,
|
|
"num_tokens": 7424250.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.531838226318359,
|
|
"epoch": 0.3370364183093886,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992752264300989,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.1759601816534996,
|
|
"num_tokens": 7433579.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.38196702003479,
|
|
"epoch": 0.33745405947210155,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004992728369119252,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.17414322048425673,
|
|
"num_tokens": 7442621.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.533233785629273,
|
|
"epoch": 0.3378717006348146,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992704434675855,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.16609173864126206,
|
|
"num_tokens": 7452077.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.438749504089356,
|
|
"epoch": 0.33828934179752757,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992680460971218,
|
|
"loss": 5.4049,
|
|
"mean_token_accuracy": 0.1703796476125717,
|
|
"num_tokens": 7461146.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.381596326828003,
|
|
"epoch": 0.33870698296024054,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992656448005758,
|
|
"loss": 5.3923,
|
|
"mean_token_accuracy": 0.175481915473938,
|
|
"num_tokens": 7470335.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.518864488601684,
|
|
"epoch": 0.3391246241229536,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992632395779899,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.1677387461066246,
|
|
"num_tokens": 7479458.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.304780340194702,
|
|
"epoch": 0.33954226528566656,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992608304294061,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.1870820254087448,
|
|
"num_tokens": 7488005.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.345000314712524,
|
|
"epoch": 0.33995990644837953,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992584173548664,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.17666814774274825,
|
|
"num_tokens": 7496807.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.497731494903564,
|
|
"epoch": 0.34037754761109257,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992560003544131,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.18096455782651902,
|
|
"num_tokens": 7505383.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.504910802841186,
|
|
"epoch": 0.34079518877380555,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992535794280887,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.16868881583213807,
|
|
"num_tokens": 7515093.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.515105199813843,
|
|
"epoch": 0.3412128299365185,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992511545759354,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.16774399131536483,
|
|
"num_tokens": 7524067.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.307038259506226,
|
|
"epoch": 0.34163047109923156,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992487257979958,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.1704171895980835,
|
|
"num_tokens": 7533197.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.53603777885437,
|
|
"epoch": 0.34204811226194454,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992462930943123,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.16514680087566375,
|
|
"num_tokens": 7543030.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.470230436325073,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992438564649275,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.16946968883275987,
|
|
"num_tokens": 7551556.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.487739992141724,
|
|
"epoch": 0.34288339458737055,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992414159098841,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.17220384776592254,
|
|
"num_tokens": 7559284.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.544583940505982,
|
|
"epoch": 0.3433010357500835,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992389714292247,
|
|
"loss": 5.4741,
|
|
"mean_token_accuracy": 0.1721594214439392,
|
|
"num_tokens": 7568750.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.374774599075318,
|
|
"epoch": 0.3437186769127965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992365230229922,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.17926724553108214,
|
|
"num_tokens": 7578309.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.357023048400879,
|
|
"epoch": 0.34413631807550954,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992340706912295,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.17205804735422134,
|
|
"num_tokens": 7586760.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.409601068496704,
|
|
"epoch": 0.3445539592382225,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992316144339794,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.1809419348835945,
|
|
"num_tokens": 7595472.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.4892051219940186,
|
|
"epoch": 0.3449716004009355,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992291542512852,
|
|
"loss": 5.519,
|
|
"mean_token_accuracy": 0.15911627560853958,
|
|
"num_tokens": 7605663.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.534612464904785,
|
|
"epoch": 0.34538924156364853,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992266901431895,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.1721968099474907,
|
|
"num_tokens": 7616110.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.4140078067779545,
|
|
"epoch": 0.3458068827263615,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992242221097358,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.17137768119573593,
|
|
"num_tokens": 7625311.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.474600219726563,
|
|
"epoch": 0.3462245238890745,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992217501509672,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.1727500230073929,
|
|
"num_tokens": 7634562.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.388373994827271,
|
|
"epoch": 0.3466421650517875,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499219274266927,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.17528713196516038,
|
|
"num_tokens": 7643231.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.455113363265991,
|
|
"epoch": 0.3470598062145005,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992167944576584,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.17543056905269622,
|
|
"num_tokens": 7653556.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.442866277694702,
|
|
"epoch": 0.3474774473772135,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499214310723205,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.179081429541111,
|
|
"num_tokens": 7662295.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.40164589881897,
|
|
"epoch": 0.3478950885399265,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992118230636102,
|
|
"loss": 5.3895,
|
|
"mean_token_accuracy": 0.17207947075366975,
|
|
"num_tokens": 7671429.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.3517780780792235,
|
|
"epoch": 0.3483127297026395,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992093314789176,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.17298997491598128,
|
|
"num_tokens": 7680589.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.411142587661743,
|
|
"epoch": 0.34873037086535247,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992068359691707,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.178671196103096,
|
|
"num_tokens": 7689005.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.334112358093262,
|
|
"epoch": 0.3491480120280655,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992043365344132,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.17627826929092408,
|
|
"num_tokens": 7698231.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.532045602798462,
|
|
"epoch": 0.3495656531907785,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992018331746891,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.17696067690849304,
|
|
"num_tokens": 7706678.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.509274339675903,
|
|
"epoch": 0.34998329435349146,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004991993258900418,
|
|
"loss": 5.4457,
|
|
"mean_token_accuracy": 0.17433779835700988,
|
|
"num_tokens": 7715506.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.482197046279907,
|
|
"epoch": 0.3504009355162045,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991968146805156,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.1729229286313057,
|
|
"num_tokens": 7726549.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.44385256767273,
|
|
"epoch": 0.35081857667891747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991942995461542,
|
|
"loss": 5.5096,
|
|
"mean_token_accuracy": 0.16654945462942122,
|
|
"num_tokens": 7735563.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.555334234237671,
|
|
"epoch": 0.35123621784163045,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991917804870018,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.17427832037210464,
|
|
"num_tokens": 7746144.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.482233190536499,
|
|
"epoch": 0.3516538590043435,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991892575031024,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.17850037515163422,
|
|
"num_tokens": 7755394.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.3845151424407955,
|
|
"epoch": 0.35207150016705646,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991867305945001,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.17939516454935073,
|
|
"num_tokens": 7764855.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.381243753433227,
|
|
"epoch": 0.35248914132976944,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991841997612394,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.16915800273418427,
|
|
"num_tokens": 7773394.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.479357719421387,
|
|
"epoch": 0.3529067824924825,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991816650033643,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.16887461990118027,
|
|
"num_tokens": 7783111.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.550615119934082,
|
|
"epoch": 0.35332442365519545,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991791263209194,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.17079004645347595,
|
|
"num_tokens": 7792569.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.416995286941528,
|
|
"epoch": 0.35374206481790843,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991765837139491,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.17731060981750488,
|
|
"num_tokens": 7801483.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.509868335723877,
|
|
"epoch": 0.35415970598062146,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991740371824977,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.1633282110095024,
|
|
"num_tokens": 7812274.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.4453041553497314,
|
|
"epoch": 0.35457734714333444,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049917148672661,
|
|
"loss": 5.3439,
|
|
"mean_token_accuracy": 0.17422096878290178,
|
|
"num_tokens": 7821101.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.492163610458374,
|
|
"epoch": 0.3549949883060474,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991689323463306,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.1771793395280838,
|
|
"num_tokens": 7829805.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.395871925354004,
|
|
"epoch": 0.35541262946876045,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991663740417042,
|
|
"loss": 5.4292,
|
|
"mean_token_accuracy": 0.16598358154296874,
|
|
"num_tokens": 7839772.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.419190835952759,
|
|
"epoch": 0.35583027063147343,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991638118127757,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.16540692001581192,
|
|
"num_tokens": 7850290.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.612323188781739,
|
|
"epoch": 0.3562479117941864,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991612456595896,
|
|
"loss": 5.4877,
|
|
"mean_token_accuracy": 0.165177820622921,
|
|
"num_tokens": 7860180.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.363939237594605,
|
|
"epoch": 0.35666555295689945,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004991586755821913,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.1823292627930641,
|
|
"num_tokens": 7869625.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.370387601852417,
|
|
"epoch": 0.3570831941196124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991561015806254,
|
|
"loss": 5.2875,
|
|
"mean_token_accuracy": 0.1758848696947098,
|
|
"num_tokens": 7878671.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.464903545379639,
|
|
"epoch": 0.3575008352823254,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991535236549372,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.18005224019289018,
|
|
"num_tokens": 7887225.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.377832698822021,
|
|
"epoch": 0.35791847644503844,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991509418051718,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.18242234736680984,
|
|
"num_tokens": 7895504.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.526500511169433,
|
|
"epoch": 0.3583361176077514,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991483560313743,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.175752092897892,
|
|
"num_tokens": 7904875.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.467843961715698,
|
|
"epoch": 0.3587537587704644,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049914576633359,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.17353366315364838,
|
|
"num_tokens": 7914747.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.422105979919434,
|
|
"epoch": 0.3591713999331774,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991431727118643,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.1721815288066864,
|
|
"num_tokens": 7923858.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.432664155960083,
|
|
"epoch": 0.3595890410958904,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991405751662426,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.17276132702827454,
|
|
"num_tokens": 7932396.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.454059314727783,
|
|
"epoch": 0.3600066822586034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991379736967703,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.1802230089902878,
|
|
"num_tokens": 7940763.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.351620006561279,
|
|
"epoch": 0.3604243234213164,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991353683034929,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.16648114025592803,
|
|
"num_tokens": 7949424.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.438655281066895,
|
|
"epoch": 0.3608419645840294,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991327589864563,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.18122622966766358,
|
|
"num_tokens": 7958805.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.5220118999481205,
|
|
"epoch": 0.3612596057467424,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991301457457057,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.17593965083360671,
|
|
"num_tokens": 7967859.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.565468502044678,
|
|
"epoch": 0.3616772469094554,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991275285812873,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.16238001137971877,
|
|
"num_tokens": 7978357.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.5675276756286625,
|
|
"epoch": 0.3620948880721684,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004991249074932466,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.17491962164640426,
|
|
"num_tokens": 7986637.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.391841077804566,
|
|
"epoch": 0.36251252923488136,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004991222824816296,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.17362402230501175,
|
|
"num_tokens": 7995954.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.500148963928223,
|
|
"epoch": 0.3629301703975944,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991196535464824,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.16786658018827438,
|
|
"num_tokens": 8005193.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.545471715927124,
|
|
"epoch": 0.3633478115603074,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991170206878508,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.17339856028556824,
|
|
"num_tokens": 8014419.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.448093557357788,
|
|
"epoch": 0.36376545272302035,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499114383905781,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.16827281564474106,
|
|
"num_tokens": 8024133.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.407823801040649,
|
|
"epoch": 0.3641830938857334,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004991117432003192,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.1798083484172821,
|
|
"num_tokens": 8033059.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.4817417621612545,
|
|
"epoch": 0.36460073504844637,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991090985715116,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.17707774192094802,
|
|
"num_tokens": 8041866.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.485598945617676,
|
|
"epoch": 0.36501837621115935,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991064500194043,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.169550259411335,
|
|
"num_tokens": 8051541.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.580405807495117,
|
|
"epoch": 0.3654360173738724,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004991037975440439,
|
|
"loss": 5.5277,
|
|
"mean_token_accuracy": 0.16821610182523727,
|
|
"num_tokens": 8061964.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.369140577316284,
|
|
"epoch": 0.36585365853658536,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991011411454769,
|
|
"loss": 5.334,
|
|
"mean_token_accuracy": 0.1683669298887253,
|
|
"num_tokens": 8071006.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.381167030334472,
|
|
"epoch": 0.36627129969929834,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990984808237495,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.17772201001644133,
|
|
"num_tokens": 8080104.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.47397289276123,
|
|
"epoch": 0.36668894086201137,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990958165789086,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.17768747508525848,
|
|
"num_tokens": 8089397.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.458541488647461,
|
|
"epoch": 0.36710658202472435,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990931484110005,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.17549906820058822,
|
|
"num_tokens": 8099055.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.469098377227783,
|
|
"epoch": 0.3675242231874373,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990904763200722,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.17544038593769073,
|
|
"num_tokens": 8107609.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.4731487274169925,
|
|
"epoch": 0.36794186435015036,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990878003061705,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.18331958800554277,
|
|
"num_tokens": 8116905.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.367913866043091,
|
|
"epoch": 0.36835950551286334,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990851203693419,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.1775816261768341,
|
|
"num_tokens": 8125580.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.379986810684204,
|
|
"epoch": 0.3687771466755763,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990824365096336,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.17180398106575012,
|
|
"num_tokens": 8134568.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.334994173049926,
|
|
"epoch": 0.36919478783828935,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990797487270926,
|
|
"loss": 5.2734,
|
|
"mean_token_accuracy": 0.1837972655892372,
|
|
"num_tokens": 8143044.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.4388011455535885,
|
|
"epoch": 0.36961242900100233,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990770570217659,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.17175349444150925,
|
|
"num_tokens": 8153701.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.403829574584961,
|
|
"epoch": 0.37003007016371536,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990743613937005,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.1803583025932312,
|
|
"num_tokens": 8163264.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.365253925323486,
|
|
"epoch": 0.37044771132642834,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990716618429436,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.1691998392343521,
|
|
"num_tokens": 8173332.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.477272033691406,
|
|
"epoch": 0.3708653524891413,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004990689583695428,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.17341262996196746,
|
|
"num_tokens": 8181881.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.485300540924072,
|
|
"epoch": 0.37128299365185435,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499066250973545,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.1675601840019226,
|
|
"num_tokens": 8190771.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.41284670829773,
|
|
"epoch": 0.37170063481456733,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990635396549978,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.169596266746521,
|
|
"num_tokens": 8200740.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.361733341217041,
|
|
"epoch": 0.3721182759772803,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990608244139486,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.17281728684902192,
|
|
"num_tokens": 8209935.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.480435037612915,
|
|
"epoch": 0.37253591713999334,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499058105250445,
|
|
"loss": 5.4323,
|
|
"mean_token_accuracy": 0.17257851213216782,
|
|
"num_tokens": 8219137.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.5401466369628904,
|
|
"epoch": 0.3729535583027063,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990553821645346,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.17586126327514648,
|
|
"num_tokens": 8228076.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.352044868469238,
|
|
"epoch": 0.3733711994654193,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499052655156265,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.17877929359674455,
|
|
"num_tokens": 8237581.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.456056451797485,
|
|
"epoch": 0.37378884062813234,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990499242256839,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.16744532585144042,
|
|
"num_tokens": 8247384.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.5242781162261965,
|
|
"epoch": 0.3742064817908453,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990471893728394,
|
|
"loss": 5.4786,
|
|
"mean_token_accuracy": 0.17573148906230926,
|
|
"num_tokens": 8256383.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.433877658843994,
|
|
"epoch": 0.3746241229535583,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499044450597779,
|
|
"loss": 5.3368,
|
|
"mean_token_accuracy": 0.1774474561214447,
|
|
"num_tokens": 8264848.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.404270029067993,
|
|
"epoch": 0.3750417641162713,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990417079005508,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.17153847068548203,
|
|
"num_tokens": 8274403.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.402362918853759,
|
|
"epoch": 0.3754594052789843,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499038961281203,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.18346159905195236,
|
|
"num_tokens": 8282700.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.384265756607055,
|
|
"epoch": 0.3758770464416973,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990362107397834,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.18079284429550171,
|
|
"num_tokens": 8291718.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.3855781078338625,
|
|
"epoch": 0.3762946876044103,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990334562763401,
|
|
"loss": 5.3805,
|
|
"mean_token_accuracy": 0.1737850561738014,
|
|
"num_tokens": 8301113.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.481485652923584,
|
|
"epoch": 0.3767123287671233,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990306978909216,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.17322600334882737,
|
|
"num_tokens": 8310357.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.519826745986938,
|
|
"epoch": 0.3771299699298363,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990279355835761,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.17298668026924133,
|
|
"num_tokens": 8319680.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.442970657348633,
|
|
"epoch": 0.3775476110925493,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990251693543519,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.17046769857406616,
|
|
"num_tokens": 8329127.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.341222906112671,
|
|
"epoch": 0.3779652522552623,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004990223992032975,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.17672463953495027,
|
|
"num_tokens": 8338308.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.412484121322632,
|
|
"epoch": 0.37838289341797526,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004990196251304612,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.17839513421058656,
|
|
"num_tokens": 8347491.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.337620973587036,
|
|
"epoch": 0.3788005345806883,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000499016847135892,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.17211673855781556,
|
|
"num_tokens": 8357112.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.385684013366699,
|
|
"epoch": 0.3792181757434013,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499014065219638,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.1788911998271942,
|
|
"num_tokens": 8366285.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.390375089645386,
|
|
"epoch": 0.37963581690611425,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004990112793817481,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.1836492419242859,
|
|
"num_tokens": 8374362.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.383315944671631,
|
|
"epoch": 0.3800534580688273,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990084896222713,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.17287468016147614,
|
|
"num_tokens": 8383297.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.403417682647705,
|
|
"epoch": 0.38047109923154027,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004990056959412562,
|
|
"loss": 5.3412,
|
|
"mean_token_accuracy": 0.18178841322660447,
|
|
"num_tokens": 8391926.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.517784595489502,
|
|
"epoch": 0.38088874039425324,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004990028983387517,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.175078184902668,
|
|
"num_tokens": 8401226.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.393605709075928,
|
|
"epoch": 0.3813063815569663,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990000968148068,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.17882849872112275,
|
|
"num_tokens": 8409966.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.295736312866211,
|
|
"epoch": 0.38172402271967926,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989972913694707,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.1859448716044426,
|
|
"num_tokens": 8418281.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.2785608768463135,
|
|
"epoch": 0.38214166388239224,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989944820027923,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.18151139318943024,
|
|
"num_tokens": 8427436.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.460799217224121,
|
|
"epoch": 0.38255930504510527,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989916687148209,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.17874803096055986,
|
|
"num_tokens": 8436066.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.419190311431885,
|
|
"epoch": 0.38297694620781825,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004989888515056057,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.17505231499671936,
|
|
"num_tokens": 8445572.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.444575595855713,
|
|
"epoch": 0.3833945873705312,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498986030375196,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.17158419489860535,
|
|
"num_tokens": 8454781.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.506966257095337,
|
|
"epoch": 0.38381222853324426,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004989832053236413,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.16998900324106217,
|
|
"num_tokens": 8463239.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.521318006515503,
|
|
"epoch": 0.38422986969595724,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000498980376350991,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.17278695106506348,
|
|
"num_tokens": 8472664.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.39429235458374,
|
|
"epoch": 0.3846475108586702,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989775434572945,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.17073088139295578,
|
|
"num_tokens": 8483149.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.548193073272705,
|
|
"epoch": 0.38506515202138325,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989747066426015,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.17684950828552246,
|
|
"num_tokens": 8492297.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.465753412246704,
|
|
"epoch": 0.38548279318409623,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989718659069618,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.171021269261837,
|
|
"num_tokens": 8502092.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.4493889808654785,
|
|
"epoch": 0.3859004343468092,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000498969021250425,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.17595359086990356,
|
|
"num_tokens": 8510816.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.475935745239258,
|
|
"epoch": 0.38631807550952224,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989661726730407,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.17920992225408555,
|
|
"num_tokens": 8520055.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.4450061321258545,
|
|
"epoch": 0.3867357166722352,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989633201748591,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.1788432076573372,
|
|
"num_tokens": 8528271.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.379427671432495,
|
|
"epoch": 0.3871533578349482,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989604637559299,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.18760859370231628,
|
|
"num_tokens": 8537360.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.320774173736572,
|
|
"epoch": 0.38757099899766123,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989576034163033,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.1910588413476944,
|
|
"num_tokens": 8546574.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.38830828666687,
|
|
"epoch": 0.3879886401603742,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989547391560293,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.17621755599975586,
|
|
"num_tokens": 8555581.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.429186201095581,
|
|
"epoch": 0.3884062813230872,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498951870975158,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.18038074523210526,
|
|
"num_tokens": 8564539.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.448959732055664,
|
|
"epoch": 0.3888239224858002,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989489988737395,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.1747396320104599,
|
|
"num_tokens": 8573804.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.450884819030762,
|
|
"epoch": 0.3892415636485132,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989461228518243,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.1754891902208328,
|
|
"num_tokens": 8583262.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.43102765083313,
|
|
"epoch": 0.3896592048112262,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004989432429094627,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.1750425562262535,
|
|
"num_tokens": 8592763.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.493407201766968,
|
|
"epoch": 0.3900768459739392,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989403590467049,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.178767366707325,
|
|
"num_tokens": 8601884.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.363888597488403,
|
|
"epoch": 0.3904944871366522,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004989374712636017,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.1706961750984192,
|
|
"num_tokens": 8611207.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.304356241226197,
|
|
"epoch": 0.39091212829936517,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004989345795602036,
|
|
"loss": 5.1684,
|
|
"mean_token_accuracy": 0.19175629168748856,
|
|
"num_tokens": 8620104.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.444139051437378,
|
|
"epoch": 0.3913297694620782,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989316839365609,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.17283373326063156,
|
|
"num_tokens": 8629552.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.383452367782593,
|
|
"epoch": 0.3917474106247912,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004989287843927246,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.17732003927230836,
|
|
"num_tokens": 8638961.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.368448734283447,
|
|
"epoch": 0.39216505178750416,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989258809287455,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.17787770181894302,
|
|
"num_tokens": 8648051.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.459696626663208,
|
|
"epoch": 0.3925826929502172,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989229735446743,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.17427610903978347,
|
|
"num_tokens": 8656863.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.235874509811401,
|
|
"epoch": 0.39300033411293017,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989200622405619,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.190497462451458,
|
|
"num_tokens": 8665455.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.341135787963867,
|
|
"epoch": 0.39341797527564315,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989171470164592,
|
|
"loss": 5.2642,
|
|
"mean_token_accuracy": 0.18486505299806594,
|
|
"num_tokens": 8674119.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.447092962265015,
|
|
"epoch": 0.3938356164383562,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989142278724173,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.17342129051685334,
|
|
"num_tokens": 8682979.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.436543989181518,
|
|
"epoch": 0.39425325760106916,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989113048084874,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.1758004441857338,
|
|
"num_tokens": 8692392.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.3052526950836185,
|
|
"epoch": 0.39467089876378214,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989083778247206,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.18246010392904283,
|
|
"num_tokens": 8700932.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.563783454895019,
|
|
"epoch": 0.3950885399264952,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000498905446921168,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.16393214464187622,
|
|
"num_tokens": 8710683.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.347655344009399,
|
|
"epoch": 0.39550618108920815,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989025120978812,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.1803911566734314,
|
|
"num_tokens": 8719939.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.438155937194824,
|
|
"epoch": 0.39592382225192113,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988995733549113,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.1774156004190445,
|
|
"num_tokens": 8729275.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.342011165618897,
|
|
"epoch": 0.39634146341463417,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988966306923099,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.18361410945653917,
|
|
"num_tokens": 8738048.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.422035169601441,
|
|
"epoch": 0.39675910457734714,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988936841101284,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.1750010848045349,
|
|
"num_tokens": 8746967.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.353234767913818,
|
|
"epoch": 0.3971767457400601,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004988907336084186,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.18189094662666322,
|
|
"num_tokens": 8754908.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.369625997543335,
|
|
"epoch": 0.39759438690277316,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988877791872319,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.18776927441358565,
|
|
"num_tokens": 8764489.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.504715442657471,
|
|
"epoch": 0.39801202806548613,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988848208466202,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.15817637890577316,
|
|
"num_tokens": 8774365.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.444577646255493,
|
|
"epoch": 0.3984296692281991,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988818585866351,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.17653939872980118,
|
|
"num_tokens": 8783538.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.358550214767456,
|
|
"epoch": 0.39884731039091215,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004988788924073288,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.17767149358987808,
|
|
"num_tokens": 8792171.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.404060745239258,
|
|
"epoch": 0.3992649515536251,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004988759223087528,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.17320301830768586,
|
|
"num_tokens": 8801325.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.445061063766479,
|
|
"epoch": 0.3996825927163381,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988729482909595,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.18149494826793672,
|
|
"num_tokens": 8810566.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.3350725173950195,
|
|
"epoch": 0.40010023387905114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988699703540006,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.18389502614736558,
|
|
"num_tokens": 8819735.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.356999015808105,
|
|
"epoch": 0.4005178750417641,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988669884979284,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.17396778911352156,
|
|
"num_tokens": 8828820.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.423072004318238,
|
|
"epoch": 0.4009355162044771,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988640027227951,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.17254929840564728,
|
|
"num_tokens": 8837858.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.387976026535034,
|
|
"epoch": 0.4013531573671901,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498861013028653,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.18501665890216829,
|
|
"num_tokens": 8847172.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.371137475967407,
|
|
"epoch": 0.4017707985299031,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988580194155544,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.17536961734294892,
|
|
"num_tokens": 8856700.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.294289445877075,
|
|
"epoch": 0.4021884396926161,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004988550218835517,
|
|
"loss": 5.1902,
|
|
"mean_token_accuracy": 0.18726896494627,
|
|
"num_tokens": 8866108.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.357527589797973,
|
|
"epoch": 0.4026060808553291,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004988520204326975,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.18764663934707643,
|
|
"num_tokens": 8874833.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.440208768844604,
|
|
"epoch": 0.4030237220180421,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988490150630441,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.17777276188135147,
|
|
"num_tokens": 8884211.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.470197916030884,
|
|
"epoch": 0.4034413631807551,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988460057746443,
|
|
"loss": 5.4681,
|
|
"mean_token_accuracy": 0.17849488854408263,
|
|
"num_tokens": 8893443.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.328664779663086,
|
|
"epoch": 0.4038590043434681,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004988429925675507,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.17989784330129624,
|
|
"num_tokens": 8903544.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.440176105499267,
|
|
"epoch": 0.4042766455061811,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988399754418161,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.17989243417978287,
|
|
"num_tokens": 8912270.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.539068412780762,
|
|
"epoch": 0.40469428666889407,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988369543974932,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.17070268467068672,
|
|
"num_tokens": 8922155.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.381599950790405,
|
|
"epoch": 0.4051119278316071,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988339294346351,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.17393961548805237,
|
|
"num_tokens": 8931844.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.4250129699707035,
|
|
"epoch": 0.4055295689943201,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988309005532946,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.18272562175989152,
|
|
"num_tokens": 8940874.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.370961380004883,
|
|
"epoch": 0.40594721015703306,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988278677535247,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.18261157870292663,
|
|
"num_tokens": 8950108.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.42987847328186,
|
|
"epoch": 0.4063648513197461,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988248310353788,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.17099629342556,
|
|
"num_tokens": 8960610.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.376508474349976,
|
|
"epoch": 0.40678249248245907,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004988217903989095,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.17501236051321029,
|
|
"num_tokens": 8969853.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.462110900878907,
|
|
"epoch": 0.40720013364517205,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988187458441704,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.17498612254858018,
|
|
"num_tokens": 8979800.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.426138687133789,
|
|
"epoch": 0.4076177748078851,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004988156973712149,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.17958766967058182,
|
|
"num_tokens": 8988667.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.289855289459228,
|
|
"epoch": 0.40803541597059806,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004988126449800961,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.1811926245689392,
|
|
"num_tokens": 8997385.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.332584190368652,
|
|
"epoch": 0.40845305713331104,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004988095886708676,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.18289996385574342,
|
|
"num_tokens": 9005999.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.475919389724732,
|
|
"epoch": 0.40887069829602407,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988065284435828,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.18217089772224426,
|
|
"num_tokens": 9014837.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.474930286407471,
|
|
"epoch": 0.40928833945873705,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988034642982954,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.1781845659017563,
|
|
"num_tokens": 9023956.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.425081396102906,
|
|
"epoch": 0.40970598062145,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988003962350589,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.17241764217615127,
|
|
"num_tokens": 9032945.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.421437549591064,
|
|
"epoch": 0.41012362178416306,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000498797324253927,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.18210716545581818,
|
|
"num_tokens": 9042109.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.321787977218628,
|
|
"epoch": 0.41054126294687604,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004987942483549537,
|
|
"loss": 5.2942,
|
|
"mean_token_accuracy": 0.17567227482795716,
|
|
"num_tokens": 9052210.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.35203971862793,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004987911685381926,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.18420227468013764,
|
|
"num_tokens": 9060089.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.4903594017028805,
|
|
"epoch": 0.41137654527230205,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987880848036977,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.1727112799882889,
|
|
"num_tokens": 9069235.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.364435195922852,
|
|
"epoch": 0.41179418643501503,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004987849971515232,
|
|
"loss": 5.316,
|
|
"mean_token_accuracy": 0.18092474788427354,
|
|
"num_tokens": 9077509.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.3612274646759035,
|
|
"epoch": 0.412211827597728,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987819055817227,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.19235456585884095,
|
|
"num_tokens": 9085493.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.198392677307129,
|
|
"epoch": 0.41262946876044104,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987788100943507,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.18430102318525315,
|
|
"num_tokens": 9094748.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.369553852081299,
|
|
"epoch": 0.413047109923154,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987757106894613,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.18725120276212692,
|
|
"num_tokens": 9103678.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.419416522979736,
|
|
"epoch": 0.413464751085867,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987726073671086,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.1809053748846054,
|
|
"num_tokens": 9112851.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.473608207702637,
|
|
"epoch": 0.41388239224858003,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987695001273471,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.16060083359479904,
|
|
"num_tokens": 9122106.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.39730806350708,
|
|
"epoch": 0.414300033411293,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987663889702313,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.1870732367038727,
|
|
"num_tokens": 9131580.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.452555704116821,
|
|
"epoch": 0.414717674574006,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987632738958155,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.17870815396308898,
|
|
"num_tokens": 9141642.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.485944128036499,
|
|
"epoch": 0.415135315736719,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004987601549041541,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.16735972315073014,
|
|
"num_tokens": 9151192.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.405943584442139,
|
|
"epoch": 0.415552956899432,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004987570319953018,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.17551329880952835,
|
|
"num_tokens": 9161316.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.416285467147827,
|
|
"epoch": 0.415970598062145,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004987539051693134,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.1752282813191414,
|
|
"num_tokens": 9169535.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.4347559928894045,
|
|
"epoch": 0.416388239224858,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987507744262436,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.17112898379564284,
|
|
"num_tokens": 9178187.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.336753177642822,
|
|
"epoch": 0.416805880387571,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987476397661472,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.17952335774898528,
|
|
"num_tokens": 9186342.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.433024072647095,
|
|
"epoch": 0.41722352155028397,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004987445011890789,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.17493401765823363,
|
|
"num_tokens": 9196470.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.40567421913147,
|
|
"epoch": 0.417641162712997,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498741358695094,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.1819268971681595,
|
|
"num_tokens": 9206587.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.351897239685059,
|
|
"epoch": 0.41805880387571,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000498738212284247,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.17583694010972978,
|
|
"num_tokens": 9216459.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.543639469146728,
|
|
"epoch": 0.41847644503842296,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987350619565934,
|
|
"loss": 5.4109,
|
|
"mean_token_accuracy": 0.173588390648365,
|
|
"num_tokens": 9227301.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.440727043151855,
|
|
"epoch": 0.418894086201136,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004987319077121884,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.1722140923142433,
|
|
"num_tokens": 9236577.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.341638374328613,
|
|
"epoch": 0.419311727363849,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987287495510869,
|
|
"loss": 5.3458,
|
|
"mean_token_accuracy": 0.18006064742803574,
|
|
"num_tokens": 9246451.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.386490249633789,
|
|
"epoch": 0.41972936852656195,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987255874733444,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.17657777816057205,
|
|
"num_tokens": 9256108.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.293013095855713,
|
|
"epoch": 0.420147009689275,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987224214790161,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.1810378149151802,
|
|
"num_tokens": 9265173.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.3749912738800045,
|
|
"epoch": 0.42056465085198796,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987192515681575,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.1769643172621727,
|
|
"num_tokens": 9273979.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.359067821502686,
|
|
"epoch": 0.42098229201470094,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004987160777408243,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.1761663630604744,
|
|
"num_tokens": 9281893.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.4864922046661375,
|
|
"epoch": 0.421399933177414,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987128999970717,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.17744186595082284,
|
|
"num_tokens": 9290799.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.495283555984497,
|
|
"epoch": 0.42181757434012696,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987097183369555,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.17196936160326004,
|
|
"num_tokens": 9300562.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.305688667297363,
|
|
"epoch": 0.42223521550283993,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004987065327605315,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.18683690279722215,
|
|
"num_tokens": 9308889.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.289650535583496,
|
|
"epoch": 0.42265285666555297,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987033432678553,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.17782160639762878,
|
|
"num_tokens": 9317957.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.473822784423828,
|
|
"epoch": 0.42307049782826595,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004987001498589828,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.16878805607557296,
|
|
"num_tokens": 9327849.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.426246404647827,
|
|
"epoch": 0.4234881389909789,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049869695253397,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.17408983856439592,
|
|
"num_tokens": 9337165.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.373740291595459,
|
|
"epoch": 0.42390578015369196,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004986937512928727,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.18019959777593614,
|
|
"num_tokens": 9346817.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.473091650009155,
|
|
"epoch": 0.42432342131640494,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498690546135747,
|
|
"loss": 5.365,
|
|
"mean_token_accuracy": 0.1764334335923195,
|
|
"num_tokens": 9356420.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.322289037704468,
|
|
"epoch": 0.4247410624791179,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004986873370626491,
|
|
"loss": 5.287,
|
|
"mean_token_accuracy": 0.18042603135108948,
|
|
"num_tokens": 9365580.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.360691070556641,
|
|
"epoch": 0.42515870364183095,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498684124073635,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.17079622596502303,
|
|
"num_tokens": 9375116.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.448138332366943,
|
|
"epoch": 0.4255763448045439,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004986809071687612,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.17626895606517792,
|
|
"num_tokens": 9384129.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.353268814086914,
|
|
"epoch": 0.4259939859672569,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004986776863480838,
|
|
"loss": 5.2626,
|
|
"mean_token_accuracy": 0.17728972136974336,
|
|
"num_tokens": 9392757.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.281383848190307,
|
|
"epoch": 0.42641162712996994,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004986744616116593,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.18091434091329575,
|
|
"num_tokens": 9401753.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.399411725997925,
|
|
"epoch": 0.4268292682926829,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000498671232959544,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.1719147503376007,
|
|
"num_tokens": 9411400.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.466083431243897,
|
|
"epoch": 0.42724690945539595,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986680003917947,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.18127259761095046,
|
|
"num_tokens": 9420206.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.359201669692993,
|
|
"epoch": 0.42766455061810893,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986647639084677,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.1818522483110428,
|
|
"num_tokens": 9428418.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.450143098831177,
|
|
"epoch": 0.4280821917808219,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00049866152350962,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.17638176530599595,
|
|
"num_tokens": 9437624.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.328964281082153,
|
|
"epoch": 0.42849983294353494,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004986582791953078,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.18318878710269929,
|
|
"num_tokens": 9446857.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.368569469451904,
|
|
"epoch": 0.4289174741062479,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004986550309655884,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.1741127997636795,
|
|
"num_tokens": 9456024.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.385288286209106,
|
|
"epoch": 0.4293351152689609,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004986517788205184,
|
|
"loss": 5.2471,
|
|
"mean_token_accuracy": 0.18674221485853196,
|
|
"num_tokens": 9464018.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.322151327133179,
|
|
"epoch": 0.42975275643167393,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986485227601548,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.18010206669569015,
|
|
"num_tokens": 9472430.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.3633181095123295,
|
|
"epoch": 0.4301703975943869,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004986452627845547,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.1861819475889206,
|
|
"num_tokens": 9480592.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.374464511871338,
|
|
"epoch": 0.4305880387570999,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000498641998893775,
|
|
"loss": 5.2301,
|
|
"mean_token_accuracy": 0.1861698091030121,
|
|
"num_tokens": 9489162.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.34882435798645,
|
|
"epoch": 0.4310056799198129,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986387310878728,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.18348312079906465,
|
|
"num_tokens": 9499210.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.419818878173828,
|
|
"epoch": 0.4314233210825259,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986354593669056,
|
|
"loss": 5.342,
|
|
"mean_token_accuracy": 0.18277039229869843,
|
|
"num_tokens": 9508062.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.442840671539306,
|
|
"epoch": 0.4318409622452389,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986321837309304,
|
|
"loss": 5.2918,
|
|
"mean_token_accuracy": 0.18474480360746384,
|
|
"num_tokens": 9516756.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.345137739181519,
|
|
"epoch": 0.4322586034079519,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004986289041800046,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.18207624405622483,
|
|
"num_tokens": 9525305.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.369629335403443,
|
|
"epoch": 0.4326762445706649,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004986256207141857,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.18715112209320067,
|
|
"num_tokens": 9534310.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.473608112335205,
|
|
"epoch": 0.43309388573337787,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986223333335311,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.17821064591407776,
|
|
"num_tokens": 9543648.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.32420244216919,
|
|
"epoch": 0.4335115268960909,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004986190420380985,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.17708334922790528,
|
|
"num_tokens": 9553081.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.454599094390869,
|
|
"epoch": 0.4339291680588039,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004986157468279453,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.17734083980321885,
|
|
"num_tokens": 9563184.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.3927582740783695,
|
|
"epoch": 0.43434680922151686,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004986124477031293,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.1813582643866539,
|
|
"num_tokens": 9572550.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.31060209274292,
|
|
"epoch": 0.4347644503842299,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004986091446637083,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.17946574985980987,
|
|
"num_tokens": 9580900.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.402362823486328,
|
|
"epoch": 0.4351820915469429,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00049860583770974,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.18296932131052018,
|
|
"num_tokens": 9589340.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.423223400115967,
|
|
"epoch": 0.43559973270965585,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004986025268412823,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.1766061156988144,
|
|
"num_tokens": 9599316.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.457963228225708,
|
|
"epoch": 0.4360173738723689,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004985992120583933,
|
|
"loss": 5.3374,
|
|
"mean_token_accuracy": 0.17567280381917955,
|
|
"num_tokens": 9609350.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.489837169647217,
|
|
"epoch": 0.43643501503508186,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498595893361131,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.18076670318841934,
|
|
"num_tokens": 9618491.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.389662647247315,
|
|
"epoch": 0.43685265619779484,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985925707495533,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.16912828981876374,
|
|
"num_tokens": 9629613.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.350446987152099,
|
|
"epoch": 0.4372702973605079,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985892442237186,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.17980844527482986,
|
|
"num_tokens": 9638035.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.479083681106568,
|
|
"epoch": 0.43768793852322085,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985859137836851,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.17037070393562317,
|
|
"num_tokens": 9647378.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.439112854003906,
|
|
"epoch": 0.43810557968593383,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004985825794295109,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.18021205067634583,
|
|
"num_tokens": 9655728.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.371652317047119,
|
|
"epoch": 0.43852322084864687,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985792411612546,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.18552555292844772,
|
|
"num_tokens": 9665063.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.4210280418396,
|
|
"epoch": 0.43894086201135984,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004985758989789746,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.1793728917837143,
|
|
"num_tokens": 9674406.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.350600242614746,
|
|
"epoch": 0.4393585031740728,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985725528827293,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.17866162061691285,
|
|
"num_tokens": 9683303.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.358454942703247,
|
|
"epoch": 0.43977614433678586,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985692028725774,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.17754778861999512,
|
|
"num_tokens": 9692938.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.429182291030884,
|
|
"epoch": 0.44019378549949884,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985658489485774,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.18046221733093262,
|
|
"num_tokens": 9702192.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.387715005874634,
|
|
"epoch": 0.4406114266622118,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004985624911107882,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.1722553476691246,
|
|
"num_tokens": 9711301.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.342666530609131,
|
|
"epoch": 0.44102906782492485,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985591293592685,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.17638202905654907,
|
|
"num_tokens": 9720768.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.433481502532959,
|
|
"epoch": 0.4414467089876378,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004985557636940771,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.17637849897146224,
|
|
"num_tokens": 9730007.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.497163009643555,
|
|
"epoch": 0.4418643501503508,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498552394115273,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.17280904501676558,
|
|
"num_tokens": 9739546.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.344863986968994,
|
|
"epoch": 0.44228199131306384,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985490206229151,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.18390890061855317,
|
|
"num_tokens": 9749615.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.466024589538574,
|
|
"epoch": 0.4426996324757768,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004985456432170626,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.17096854895353317,
|
|
"num_tokens": 9759285.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.338745927810669,
|
|
"epoch": 0.4431172736384898,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985422618977744,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.1765191838145256,
|
|
"num_tokens": 9769396.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.379651117324829,
|
|
"epoch": 0.44353491480120283,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00049853887666511,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.17065683305263518,
|
|
"num_tokens": 9779632.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.511491537094116,
|
|
"epoch": 0.4439525559639158,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004985354875191283,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.18027861267328263,
|
|
"num_tokens": 9788090.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.255291843414307,
|
|
"epoch": 0.4443701971266288,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004985320944598889,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.18982870131731033,
|
|
"num_tokens": 9795844.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.249967241287232,
|
|
"epoch": 0.4447878382893418,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985286974874512,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.1883803591132164,
|
|
"num_tokens": 9805119.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.439846801757812,
|
|
"epoch": 0.4452054794520548,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004985252966018745,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.18204206973314285,
|
|
"num_tokens": 9813842.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.441546678543091,
|
|
"epoch": 0.4456231206147678,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985218918032184,
|
|
"loss": 5.3271,
|
|
"mean_token_accuracy": 0.17488853931427,
|
|
"num_tokens": 9822872.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.438081836700439,
|
|
"epoch": 0.4460407617774808,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985184830915426,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.16981665343046187,
|
|
"num_tokens": 9832710.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.504905652999878,
|
|
"epoch": 0.4464584029401938,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004985150704669067,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.17520561516284944,
|
|
"num_tokens": 9841047.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.4110023975372314,
|
|
"epoch": 0.44687604410290677,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985116539293704,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.17695399969816208,
|
|
"num_tokens": 9850168.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.354893350601197,
|
|
"epoch": 0.4472936852656198,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004985082334789936,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.1664320170879364,
|
|
"num_tokens": 9859550.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.461143445968628,
|
|
"epoch": 0.4477113264283328,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004985048091158361,
|
|
"loss": 5.3081,
|
|
"mean_token_accuracy": 0.17618091255426407,
|
|
"num_tokens": 9868317.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.520910835266113,
|
|
"epoch": 0.44812896759104576,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985013808399578,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.16146971583366393,
|
|
"num_tokens": 9878421.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.452930593490601,
|
|
"epoch": 0.4485466087537588,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004984979486514189,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.18397300988435744,
|
|
"num_tokens": 9887213.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.377728796005249,
|
|
"epoch": 0.44896424991647177,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984945125502795,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.17348188757896424,
|
|
"num_tokens": 9897274.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.336976003646851,
|
|
"epoch": 0.44938189107918475,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004984910725365994,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.17537881433963776,
|
|
"num_tokens": 9906765.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.482185411453247,
|
|
"epoch": 0.4497995322418978,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004984876286104392,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.17005700916051864,
|
|
"num_tokens": 9916149.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.419423675537109,
|
|
"epoch": 0.45021717340461076,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984841807718591,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.17702989429235458,
|
|
"num_tokens": 9925657.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.366682529449463,
|
|
"epoch": 0.45063481456732374,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004984807290209193,
|
|
"loss": 5.3034,
|
|
"mean_token_accuracy": 0.17391487210988998,
|
|
"num_tokens": 9934740.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.554361343383789,
|
|
"epoch": 0.45105245573003677,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984772733576803,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.1729282855987549,
|
|
"num_tokens": 9943516.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.4826559066772464,
|
|
"epoch": 0.45147009689274975,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004984738137822028,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.1681110993027687,
|
|
"num_tokens": 9952998.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.384304571151733,
|
|
"epoch": 0.45188773805546273,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498470350294547,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.18386478573083878,
|
|
"num_tokens": 9961698.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.374800205230713,
|
|
"epoch": 0.45230537921817576,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004984668828947739,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.17178037017583847,
|
|
"num_tokens": 9972015.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.40453519821167,
|
|
"epoch": 0.45272302038088874,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004984634115829439,
|
|
"loss": 5.4344,
|
|
"mean_token_accuracy": 0.17172151505947114,
|
|
"num_tokens": 9981834.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.331679344177246,
|
|
"epoch": 0.4531406615436017,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000498459936359118,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.18475869297981262,
|
|
"num_tokens": 9991113.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.386208820343017,
|
|
"epoch": 0.45355830270631475,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984564572233568,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.185154689848423,
|
|
"num_tokens": 10000048.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.427082777023315,
|
|
"epoch": 0.45397594386902773,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984529741757216,
|
|
"loss": 5.3136,
|
|
"mean_token_accuracy": 0.18205272108316423,
|
|
"num_tokens": 10009389.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.335471868515015,
|
|
"epoch": 0.4543935850317407,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004984494872162728,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.18400882184505463,
|
|
"num_tokens": 10018342.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.422104072570801,
|
|
"epoch": 0.45481122619445374,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000498445996345072,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.1807814508676529,
|
|
"num_tokens": 10027219.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.291424751281738,
|
|
"epoch": 0.4552288673571667,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004984425015621799,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.17668753862380981,
|
|
"num_tokens": 10036635.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.309024143218994,
|
|
"epoch": 0.4556465085198797,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000498439002867658,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.1802414745092392,
|
|
"num_tokens": 10045655.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.528062772750855,
|
|
"epoch": 0.45606414968259273,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004984355002615673,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.16974907964468003,
|
|
"num_tokens": 10054366.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.380119657516479,
|
|
"epoch": 0.4564817908453057,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004984319937439693,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.1861657440662384,
|
|
"num_tokens": 10062548.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.329405069351196,
|
|
"epoch": 0.4568994320080187,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004984284833149252,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.17789616137742997,
|
|
"num_tokens": 10071333.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.279886627197266,
|
|
"epoch": 0.4573170731707317,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004984249689744966,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.18658134043216706,
|
|
"num_tokens": 10079502.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.323281526565552,
|
|
"epoch": 0.4577347143334447,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498421450722745,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.18677007406949997,
|
|
"num_tokens": 10088648.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.322705841064453,
|
|
"epoch": 0.4581523554961577,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498417928559732,
|
|
"loss": 5.2418,
|
|
"mean_token_accuracy": 0.18585171401500702,
|
|
"num_tokens": 10097742.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.403957986831665,
|
|
"epoch": 0.4585699966588707,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004984144024855191,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.1740902915596962,
|
|
"num_tokens": 10107228.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.359741067886352,
|
|
"epoch": 0.4589876378215837,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004984108725001683,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.18054186105728148,
|
|
"num_tokens": 10115488.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.276429319381714,
|
|
"epoch": 0.45940527898429667,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004984073386037413,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.18593759089708328,
|
|
"num_tokens": 10124235.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.282084178924561,
|
|
"epoch": 0.4598229201470097,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004984038007962997,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.18730263113975526,
|
|
"num_tokens": 10133208.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.338069248199463,
|
|
"epoch": 0.4602405613097227,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004984002590779059,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.18483959138393402,
|
|
"num_tokens": 10142754.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.421583557128907,
|
|
"epoch": 0.46065820247243566,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004983967134486215,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.18001955896615982,
|
|
"num_tokens": 10152114.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.357906293869019,
|
|
"epoch": 0.4610758436351487,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983931639085088,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.18192300349473953,
|
|
"num_tokens": 10161562.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.395240306854248,
|
|
"epoch": 0.4614934847978617,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983896104576298,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.17601957768201829,
|
|
"num_tokens": 10170461.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.41256160736084,
|
|
"epoch": 0.46191112596057465,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498386053096047,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.17777144759893418,
|
|
"num_tokens": 10179243.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.392285537719727,
|
|
"epoch": 0.4623287671232877,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983824918238221,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.18495858013629912,
|
|
"num_tokens": 10187935.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.435108327865601,
|
|
"epoch": 0.46274640828600067,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498378926641018,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.17514135539531708,
|
|
"num_tokens": 10196185.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.4282838821411135,
|
|
"epoch": 0.46316404944871364,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004983753575476969,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.1728462278842926,
|
|
"num_tokens": 10205373.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.3686912059783936,
|
|
"epoch": 0.4635816906114267,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983717845439212,
|
|
"loss": 5.3222,
|
|
"mean_token_accuracy": 0.18750559240579606,
|
|
"num_tokens": 10214464.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.397244310379028,
|
|
"epoch": 0.46399933177413966,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004983682076297536,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.1748291254043579,
|
|
"num_tokens": 10224462.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.490514850616455,
|
|
"epoch": 0.46441697293685263,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983646268052567,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.18098523914813996,
|
|
"num_tokens": 10233123.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.338079309463501,
|
|
"epoch": 0.46483461409956567,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983610420704931,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.1845409706234932,
|
|
"num_tokens": 10241613.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.43339262008667,
|
|
"epoch": 0.46525225526227865,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004983574534255256,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.16590092927217484,
|
|
"num_tokens": 10251809.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.359250164031982,
|
|
"epoch": 0.4656698964249916,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000498353860870417,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.18127120435237884,
|
|
"num_tokens": 10260198.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.4148660659790036,
|
|
"epoch": 0.46608753758770466,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004983502644052303,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.1783775269985199,
|
|
"num_tokens": 10268906.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.307451057434082,
|
|
"epoch": 0.46650517875041764,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983466640300282,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.18028734028339385,
|
|
"num_tokens": 10278526.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.332444190979004,
|
|
"epoch": 0.4669228199131306,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004983430597448741,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.18263361006975173,
|
|
"num_tokens": 10287428.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.506376791000366,
|
|
"epoch": 0.46734046107584365,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983394515498308,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.17286923974752427,
|
|
"num_tokens": 10297136.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.388471555709839,
|
|
"epoch": 0.46775810223855663,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004983358394449616,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.177946974337101,
|
|
"num_tokens": 10305678.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.251855993270874,
|
|
"epoch": 0.4681757434012696,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004983322234303297,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.1755787819623947,
|
|
"num_tokens": 10314690.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.3856062412261965,
|
|
"epoch": 0.46859338456398264,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004983286035059984,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.17978821098804473,
|
|
"num_tokens": 10323521.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.373954200744629,
|
|
"epoch": 0.4690110257266956,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004983249796720311,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.18739869743585585,
|
|
"num_tokens": 10333077.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.315990686416626,
|
|
"epoch": 0.4694286668894086,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004983213519284912,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.1791898638010025,
|
|
"num_tokens": 10342194.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.298461961746216,
|
|
"epoch": 0.46984630805212163,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004983177202754421,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.19010407328605652,
|
|
"num_tokens": 10351009.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.410635614395142,
|
|
"epoch": 0.4702639492148346,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983140847129476,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.17841810435056688,
|
|
"num_tokens": 10360872.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.368702793121338,
|
|
"epoch": 0.4706815903775476,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004983104452410713,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.18015502095222474,
|
|
"num_tokens": 10370159.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.339200353622436,
|
|
"epoch": 0.4710992315402606,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004983068018598768,
|
|
"loss": 5.251,
|
|
"mean_token_accuracy": 0.1864570513367653,
|
|
"num_tokens": 10379219.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.379155874252319,
|
|
"epoch": 0.4715168727029736,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498303154569428,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.17841103971004485,
|
|
"num_tokens": 10389425.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.391329765319824,
|
|
"epoch": 0.4719345138656866,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004982995033697887,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.18286772966384887,
|
|
"num_tokens": 10398023.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.385508298873901,
|
|
"epoch": 0.4723521550283996,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004982958482610226,
|
|
"loss": 5.2503,
|
|
"mean_token_accuracy": 0.1814128801226616,
|
|
"num_tokens": 10406578.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.273907423019409,
|
|
"epoch": 0.4727697961911126,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000498292189243194,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.18512603789567947,
|
|
"num_tokens": 10416448.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.385401105880737,
|
|
"epoch": 0.47318743735382557,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000498288526316367,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.17727738469839097,
|
|
"num_tokens": 10425414.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.361488723754883,
|
|
"epoch": 0.4736050785165386,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004982848594806054,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.18584574311971663,
|
|
"num_tokens": 10433900.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.416553497314453,
|
|
"epoch": 0.4740227196792516,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004982811887359736,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.17688911110162736,
|
|
"num_tokens": 10443077.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.431783676147461,
|
|
"epoch": 0.47444036084196456,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004982775140825359,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.1801500827074051,
|
|
"num_tokens": 10452791.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.464850807189942,
|
|
"epoch": 0.4748580020046776,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004982738355203565,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.16853803396224976,
|
|
"num_tokens": 10462087.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.489383697509766,
|
|
"epoch": 0.47527564316739057,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004982701530494998,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.1620257392525673,
|
|
"num_tokens": 10472576.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.422889518737793,
|
|
"epoch": 0.47569328433010355,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982664666700304,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.18758722692728041,
|
|
"num_tokens": 10481176.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.33063063621521,
|
|
"epoch": 0.4761109254928166,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004982627763820128,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.17557826787233352,
|
|
"num_tokens": 10490558.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.420174217224121,
|
|
"epoch": 0.47652856665552956,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004982590821855115,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.17991894334554673,
|
|
"num_tokens": 10499543.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.348049879074097,
|
|
"epoch": 0.47694620781824254,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004982553840805912,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.18451592773199083,
|
|
"num_tokens": 10508162.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.332060480117798,
|
|
"epoch": 0.4773638489809556,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004982516820673167,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.1859285429120064,
|
|
"num_tokens": 10516837.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.348451137542725,
|
|
"epoch": 0.47778149014366855,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004982479761457528,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.18323100209236146,
|
|
"num_tokens": 10526208.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.4435309886932375,
|
|
"epoch": 0.47819913130638153,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982442663159643,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.1724609911441803,
|
|
"num_tokens": 10536002.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.425581312179565,
|
|
"epoch": 0.47861677246909456,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004982405525780162,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.17911448329687119,
|
|
"num_tokens": 10545861.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.382137107849121,
|
|
"epoch": 0.47903441363180754,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004982368349319736,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.1853106439113617,
|
|
"num_tokens": 10555357.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.369589853286743,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004982331133779014,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.17767890989780427,
|
|
"num_tokens": 10564744.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.314902353286743,
|
|
"epoch": 0.47986969595723356,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004982293879158649,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.18325549662113189,
|
|
"num_tokens": 10573736.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.375504016876221,
|
|
"epoch": 0.48028733711994653,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004982256585459293,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.1777355268597603,
|
|
"num_tokens": 10583238.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.455562448501587,
|
|
"epoch": 0.4807049782826595,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982219252681597,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.1724510073661804,
|
|
"num_tokens": 10592316.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.407722091674804,
|
|
"epoch": 0.48112261944537255,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982181880826218,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.18294421583414078,
|
|
"num_tokens": 10601418.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.333720922470093,
|
|
"epoch": 0.4815402606080855,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982144469893807,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.18337585180997848,
|
|
"num_tokens": 10610513.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.368336915969849,
|
|
"epoch": 0.4819579017707985,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498210701988502,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.18447786718606948,
|
|
"num_tokens": 10619529.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.485368061065674,
|
|
"epoch": 0.48237554293351154,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982069530800514,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.1866314858198166,
|
|
"num_tokens": 10628263.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.438887739181519,
|
|
"epoch": 0.4827931840962245,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004982032002640943,
|
|
"loss": 5.3464,
|
|
"mean_token_accuracy": 0.18147321790456772,
|
|
"num_tokens": 10637605.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.40214958190918,
|
|
"epoch": 0.48321082525893755,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004981994435406965,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.1765257492661476,
|
|
"num_tokens": 10647113.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.340604686737061,
|
|
"epoch": 0.4836284664216505,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981956829099239,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.18975128680467607,
|
|
"num_tokens": 10655464.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.403401851654053,
|
|
"epoch": 0.4840461075843635,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981919183718422,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.18043090552091598,
|
|
"num_tokens": 10664689.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.264755392074585,
|
|
"epoch": 0.48446374874707654,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004981881499265173,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.18198387920856476,
|
|
"num_tokens": 10673440.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.299979114532471,
|
|
"epoch": 0.4848813899097895,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004981843775740151,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.18126818984746934,
|
|
"num_tokens": 10683075.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.384060907363891,
|
|
"epoch": 0.4852990310725025,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981806013144017,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.18361429870128632,
|
|
"num_tokens": 10692663.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.366247510910034,
|
|
"epoch": 0.48571667223521553,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981768211477434,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.1851995274424553,
|
|
"num_tokens": 10702068.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.3900166034698485,
|
|
"epoch": 0.4861343133979285,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000498173037074106,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.1716886818408966,
|
|
"num_tokens": 10711230.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.321808528900147,
|
|
"epoch": 0.4865519545606415,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004981692490935561,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.18573111295700073,
|
|
"num_tokens": 10719651.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.370608282089234,
|
|
"epoch": 0.4869695957233545,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004981654572061597,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.18043226301670073,
|
|
"num_tokens": 10729342.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.434235668182373,
|
|
"epoch": 0.4873872368860675,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004981616614119836,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.185221067070961,
|
|
"num_tokens": 10738617.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.412237596511841,
|
|
"epoch": 0.4878048780487805,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004981578617110938,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.1808386668562889,
|
|
"num_tokens": 10746881.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.320700454711914,
|
|
"epoch": 0.4882225192114935,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004981540581035571,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.19013732820749282,
|
|
"num_tokens": 10755848.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.322195291519165,
|
|
"epoch": 0.4886401603742065,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00049815025058944,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.1823713093996048,
|
|
"num_tokens": 10765519.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.298445796966552,
|
|
"epoch": 0.48905780153691947,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981464391688092,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.17206095159053802,
|
|
"num_tokens": 10776408.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.365063190460205,
|
|
"epoch": 0.4894754426996325,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004981426238417312,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.18536051958799363,
|
|
"num_tokens": 10785499.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.382756567001342,
|
|
"epoch": 0.4898930838623455,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004981388046082731,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.1825641930103302,
|
|
"num_tokens": 10794736.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.368501281738281,
|
|
"epoch": 0.49031072502505846,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981349814685016,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.17694495171308516,
|
|
"num_tokens": 10804125.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.485472869873047,
|
|
"epoch": 0.4907283661877715,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004981311544224838,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.18018668740987778,
|
|
"num_tokens": 10813465.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.334915399551392,
|
|
"epoch": 0.49114600735048447,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981273234702864,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.1875336542725563,
|
|
"num_tokens": 10821550.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.338493299484253,
|
|
"epoch": 0.49156364851319745,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004981234886119767,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.18219776451587677,
|
|
"num_tokens": 10830683.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.369595909118653,
|
|
"epoch": 0.4919812896759105,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981196498476217,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.18770304918289185,
|
|
"num_tokens": 10839492.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.3159058570861815,
|
|
"epoch": 0.49239893083862346,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004981158071772887,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.19166890382766724,
|
|
"num_tokens": 10847998.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.240080451965332,
|
|
"epoch": 0.49281657200133644,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004981119606010449,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.189774052798748,
|
|
"num_tokens": 10856438.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.267599725723267,
|
|
"epoch": 0.4932342131640495,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004981081101189577,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.181645205616951,
|
|
"num_tokens": 10865936.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.358993434906006,
|
|
"epoch": 0.49365185432676245,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004981042557310945,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.18553776443004608,
|
|
"num_tokens": 10874621.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.33198766708374,
|
|
"epoch": 0.49406949548947543,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004981003974375227,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.1845684453845024,
|
|
"num_tokens": 10883516.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.3517989158630375,
|
|
"epoch": 0.49448713665218846,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004980965352383099,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.1766266942024231,
|
|
"num_tokens": 10892580.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.357056951522827,
|
|
"epoch": 0.49490477781490144,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004980926691335238,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.18829175233840942,
|
|
"num_tokens": 10901227.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.3624979019165036,
|
|
"epoch": 0.4953224189776144,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004980887991232318,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.17593953758478165,
|
|
"num_tokens": 10909454.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.474798393249512,
|
|
"epoch": 0.49574006014032745,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000498084925207502,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.17890977412462233,
|
|
"num_tokens": 10919792.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.422196006774902,
|
|
"epoch": 0.49615770130304043,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000498081047386402,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.17535832524299622,
|
|
"num_tokens": 10930523.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.304169750213623,
|
|
"epoch": 0.4965753424657534,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004980771656599998,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.18457962125539779,
|
|
"num_tokens": 10940075.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.379092025756836,
|
|
"epoch": 0.49699298362846644,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004980732800283633,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.17703412622213363,
|
|
"num_tokens": 10949059.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.374813175201416,
|
|
"epoch": 0.4974106247911794,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980693904915604,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.1839677095413208,
|
|
"num_tokens": 10958313.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.287323093414306,
|
|
"epoch": 0.4978282659538924,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004980654970496595,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.1837708458304405,
|
|
"num_tokens": 10967666.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.385119342803955,
|
|
"epoch": 0.49824590711660544,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004980615997027284,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.1810262307524681,
|
|
"num_tokens": 10976519.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.468370676040649,
|
|
"epoch": 0.4986635482793184,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004980576984508356,
|
|
"loss": 5.4155,
|
|
"mean_token_accuracy": 0.1726203069090843,
|
|
"num_tokens": 10987138.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.394054555892945,
|
|
"epoch": 0.4990811894420314,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004980537932940492,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.18088141530752183,
|
|
"num_tokens": 10996517.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.35601921081543,
|
|
"epoch": 0.4994988306047444,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004980498842324377,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.1789805054664612,
|
|
"num_tokens": 11006312.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.3022911071777346,
|
|
"epoch": 0.4999164717674574,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004980459712660694,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.18762718588113786,
|
|
"num_tokens": 11015535.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.340489625930786,
|
|
"epoch": 0.5003341129301704,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004980420543950131,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.18379236608743668,
|
|
"num_tokens": 11024887.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.253097724914551,
|
|
"epoch": 0.5007517540928834,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004980381336193371,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.1922702133655548,
|
|
"num_tokens": 11033147.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.330597829818726,
|
|
"epoch": 0.5011693952555963,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004980342089391099,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.18446871489286423,
|
|
"num_tokens": 11042726.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5011693952555963,
|
|
"eval_entropy": 5.122171156892734,
|
|
"eval_loss": 5.276597023010254,
|
|
"eval_mean_token_accuracy": 0.19089796238106782,
|
|
"eval_num_tokens": 11042726.0,
|
|
"eval_runtime": 27.3546,
|
|
"eval_samples_per_second": 1380.499,
|
|
"eval_steps_per_second": 172.585,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.3341082572937015,
|
|
"epoch": 0.5015870364183094,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980302803544006,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.1802077740430832,
|
|
"num_tokens": 11052181.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.4133617877960205,
|
|
"epoch": 0.5020046775810224,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980263478652778,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.1810848146677017,
|
|
"num_tokens": 11061586.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.479144477844239,
|
|
"epoch": 0.5024223187437353,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980224114718102,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.1872189611196518,
|
|
"num_tokens": 11070914.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.252730751037598,
|
|
"epoch": 0.5028399599064484,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004980184711740669,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.1886384144425392,
|
|
"num_tokens": 11079836.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.248090744018555,
|
|
"epoch": 0.5032576010691614,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004980145269721168,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.1809512495994568,
|
|
"num_tokens": 11088320.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.397958278656006,
|
|
"epoch": 0.5036752422318743,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498010578866029,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.18020374923944474,
|
|
"num_tokens": 11097803.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.469384574890137,
|
|
"epoch": 0.5040928833945874,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980066268558726,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.17793723195791245,
|
|
"num_tokens": 11107218.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.43264799118042,
|
|
"epoch": 0.5045105245573004,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980026709417167,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.18189581483602524,
|
|
"num_tokens": 11115599.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.2718737602233885,
|
|
"epoch": 0.5049281657200133,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004979987111236306,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.18838154375553132,
|
|
"num_tokens": 11124312.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.3155444145202635,
|
|
"epoch": 0.5053458068827263,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004979947474016837,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.18409484922885894,
|
|
"num_tokens": 11133117.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.507103681564331,
|
|
"epoch": 0.5057634480454394,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004979907797759453,
|
|
"loss": 5.3329,
|
|
"mean_token_accuracy": 0.17988639920949936,
|
|
"num_tokens": 11141972.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.437141990661621,
|
|
"epoch": 0.5061810892081523,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004979868082464849,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.17766742259263993,
|
|
"num_tokens": 11151416.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.344732427597046,
|
|
"epoch": 0.5065987303708653,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004979828328133719,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.17817157208919526,
|
|
"num_tokens": 11160727.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.356343793869018,
|
|
"epoch": 0.5070163715335784,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004979788534766762,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.17333008646965026,
|
|
"num_tokens": 11171350.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.357258081436157,
|
|
"epoch": 0.5074340126962913,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004979748702364672,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.17688867598772048,
|
|
"num_tokens": 11180233.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.3647864818572994,
|
|
"epoch": 0.5078516538590043,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004979708830928147,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.18030519783496857,
|
|
"num_tokens": 11189269.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.394839859008789,
|
|
"epoch": 0.5082692950217174,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004979668920457884,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.17938395589590073,
|
|
"num_tokens": 11199072.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.323867988586426,
|
|
"epoch": 0.5086869361844303,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004979628970954584,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.18903121054172517,
|
|
"num_tokens": 11207164.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.287879514694214,
|
|
"epoch": 0.5091045773471433,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004979588982418944,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.1728105887770653,
|
|
"num_tokens": 11216557.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.535755586624146,
|
|
"epoch": 0.5095222185098564,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004979548954851666,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.17514478415250778,
|
|
"num_tokens": 11227277.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.391517972946167,
|
|
"epoch": 0.5099398596725693,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497950888825345,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.18890394270420074,
|
|
"num_tokens": 11236226.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.3458089351654055,
|
|
"epoch": 0.5103575008352823,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004979468782624996,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.18111661821603775,
|
|
"num_tokens": 11245246.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.333164882659912,
|
|
"epoch": 0.5107751419979953,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004979428637967009,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.1781592220067978,
|
|
"num_tokens": 11254437.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.41632308959961,
|
|
"epoch": 0.5111927831607083,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004979388454280189,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.19035724103450774,
|
|
"num_tokens": 11262413.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.405248832702637,
|
|
"epoch": 0.5116104243234213,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000497934823156524,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.17728246599435807,
|
|
"num_tokens": 11272061.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.3317732334136965,
|
|
"epoch": 0.5120280654861343,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004979307969822869,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.18845614194869995,
|
|
"num_tokens": 11281623.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.251134586334229,
|
|
"epoch": 0.5124457066488474,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004979267669053776,
|
|
"loss": 5.0858,
|
|
"mean_token_accuracy": 0.19723618477582933,
|
|
"num_tokens": 11290202.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.342445135116577,
|
|
"epoch": 0.5128633478115603,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004979227329258671,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.18314483612775803,
|
|
"num_tokens": 11299040.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.418828630447388,
|
|
"epoch": 0.5132809889742733,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004979186950438256,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.18070457875728607,
|
|
"num_tokens": 11307938.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.378529262542725,
|
|
"epoch": 0.5136986301369864,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004979146532593243,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.18071874380111694,
|
|
"num_tokens": 11316915.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.346374654769898,
|
|
"epoch": 0.5141162712996993,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004979106075724334,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.176848366856575,
|
|
"num_tokens": 11326634.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.443122911453247,
|
|
"epoch": 0.5145339124624123,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004979065579832242,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.1679534450173378,
|
|
"num_tokens": 11336502.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.377861785888672,
|
|
"epoch": 0.5149515536251253,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004979025044917673,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.1782236009836197,
|
|
"num_tokens": 11346125.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.454143762588501,
|
|
"epoch": 0.5153691947878383,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004978984470981339,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.16891748160123826,
|
|
"num_tokens": 11355713.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.386297178268433,
|
|
"epoch": 0.5157868359505513,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004978943858023946,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.1821313038468361,
|
|
"num_tokens": 11364726.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.37279748916626,
|
|
"epoch": 0.5162044771132643,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000497890320604621,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.1816943421959877,
|
|
"num_tokens": 11373779.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.277878665924073,
|
|
"epoch": 0.5166221182759773,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000497886251504884,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.18144305646419526,
|
|
"num_tokens": 11382641.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.302442121505737,
|
|
"epoch": 0.5170397594386903,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004978821785032549,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.18470952212810515,
|
|
"num_tokens": 11392200.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.387860345840454,
|
|
"epoch": 0.5174574006014033,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.3157,
|
|
"mean_token_accuracy": 0.17309316545724868,
|
|
"num_tokens": 11401884.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.348043489456177,
|
|
"epoch": 0.5178750417641163,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004978740207946056,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.1886736273765564,
|
|
"num_tokens": 11410710.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.267181253433227,
|
|
"epoch": 0.5182926829268293,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004978699360877281,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.19061697721481324,
|
|
"num_tokens": 11419622.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.267860460281372,
|
|
"epoch": 0.5187103240895423,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004978658474792442,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.19042179584503174,
|
|
"num_tokens": 11427631.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.332252073287964,
|
|
"epoch": 0.5191279652522552,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004978617549692253,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.1809620276093483,
|
|
"num_tokens": 11437630.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.458483409881592,
|
|
"epoch": 0.5195456064149683,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978576585577432,
|
|
"loss": 5.4633,
|
|
"mean_token_accuracy": 0.1654739946126938,
|
|
"num_tokens": 11447962.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.490985774993897,
|
|
"epoch": 0.5199632475776813,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004978535582448695,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.17904573380947114,
|
|
"num_tokens": 11458154.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.315806674957275,
|
|
"epoch": 0.5203808887403942,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004978494540306761,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.18527811467647554,
|
|
"num_tokens": 11467449.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.3177930355072025,
|
|
"epoch": 0.5207985299031073,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004978453459152346,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.17112648785114287,
|
|
"num_tokens": 11477775.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.40331506729126,
|
|
"epoch": 0.5212161710658203,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004978412338986172,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.18052331507205963,
|
|
"num_tokens": 11486921.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.360177278518677,
|
|
"epoch": 0.5216338122285332,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004978371179808958,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.18757482320070268,
|
|
"num_tokens": 11496562.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.310189580917358,
|
|
"epoch": 0.5220514533912463,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004978329981621424,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.18194289207458497,
|
|
"num_tokens": 11504906.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.298901605606079,
|
|
"epoch": 0.5224690945539593,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000497828874442429,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.18324219882488252,
|
|
"num_tokens": 11513757.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.2840211391448975,
|
|
"epoch": 0.5228867357166722,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000497824746821828,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.17947673201560974,
|
|
"num_tokens": 11523195.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.385505962371826,
|
|
"epoch": 0.5233043768793852,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004978206153004117,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.180406354367733,
|
|
"num_tokens": 11532348.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.402559614181518,
|
|
"epoch": 0.5237220180420983,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004978164798782523,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.1870359420776367,
|
|
"num_tokens": 11542356.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.347551870346069,
|
|
"epoch": 0.5241396592048112,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004978123405554221,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.18448646366596222,
|
|
"num_tokens": 11550914.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.362148094177246,
|
|
"epoch": 0.5245573003675242,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004978081973319938,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.18454992920160293,
|
|
"num_tokens": 11559314.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.28530478477478,
|
|
"epoch": 0.5249749415302373,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004978040502080398,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.1808277413249016,
|
|
"num_tokens": 11567990.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.3501801013946535,
|
|
"epoch": 0.5253925826929502,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004977998991836327,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.17986629903316498,
|
|
"num_tokens": 11577133.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.369371223449707,
|
|
"epoch": 0.5258102238556632,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004977957442588451,
|
|
"loss": 5.3297,
|
|
"mean_token_accuracy": 0.17925186157226564,
|
|
"num_tokens": 11585330.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.421820878982544,
|
|
"epoch": 0.5262278650183763,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004977915854337498,
|
|
"loss": 5.2774,
|
|
"mean_token_accuracy": 0.17785076349973677,
|
|
"num_tokens": 11595005.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.323221492767334,
|
|
"epoch": 0.5266455061810892,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004977874227084197,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.1909732237458229,
|
|
"num_tokens": 11603969.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.273255443572998,
|
|
"epoch": 0.5270631473438022,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977832560829277,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.18179108798503876,
|
|
"num_tokens": 11613118.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.305721616744995,
|
|
"epoch": 0.5274807885065153,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004977790855573464,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.18721737563610077,
|
|
"num_tokens": 11621799.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.288804006576538,
|
|
"epoch": 0.5278984296692282,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004977749111317492,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.18319330960512162,
|
|
"num_tokens": 11630557.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.36851134300232,
|
|
"epoch": 0.5283160708319412,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000497770732806209,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.18259372413158417,
|
|
"num_tokens": 11639179.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.415849304199218,
|
|
"epoch": 0.5287337119946542,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000497766550580799,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.17368093580007554,
|
|
"num_tokens": 11648273.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.332431697845459,
|
|
"epoch": 0.5291513531573672,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977623644555923,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.18116851449012755,
|
|
"num_tokens": 11656372.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.327931547164917,
|
|
"epoch": 0.5295689943200802,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004977581744306624,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.18387259691953659,
|
|
"num_tokens": 11665007.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.37454047203064,
|
|
"epoch": 0.5299866354827932,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977539805060824,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.18091593384742738,
|
|
"num_tokens": 11674519.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.404172754287719,
|
|
"epoch": 0.5304042766455062,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004977497826819259,
|
|
"loss": 5.2521,
|
|
"mean_token_accuracy": 0.18294285833835602,
|
|
"num_tokens": 11683705.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.350062894821167,
|
|
"epoch": 0.5308219178082192,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004977455809582664,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.18395105600357056,
|
|
"num_tokens": 11693152.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.365998888015747,
|
|
"epoch": 0.5312395589709322,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004977413753351772,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.17858757078647614,
|
|
"num_tokens": 11702584.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.336689805984497,
|
|
"epoch": 0.5316572001336451,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004977371658127323,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.18464104682207108,
|
|
"num_tokens": 11711633.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.288880968093872,
|
|
"epoch": 0.5320748412963582,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004977329523910051,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.18570223748683928,
|
|
"num_tokens": 11720116.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.385643768310547,
|
|
"epoch": 0.5324924824590712,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004977287350700695,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.17931191474199296,
|
|
"num_tokens": 11729564.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.341831684112549,
|
|
"epoch": 0.5329101236217841,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004977245138499993,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.19463744014501572,
|
|
"num_tokens": 11737935.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.315127897262573,
|
|
"epoch": 0.5333277647844972,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004977202887308684,
|
|
"loss": 5.1643,
|
|
"mean_token_accuracy": 0.186013887822628,
|
|
"num_tokens": 11745989.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.346630334854126,
|
|
"epoch": 0.5337454059472102,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004977160597127507,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.18391820639371873,
|
|
"num_tokens": 11755530.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.392025470733643,
|
|
"epoch": 0.5341630471099231,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004977118267957204,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.17761826366186143,
|
|
"num_tokens": 11764546.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.4786036014556885,
|
|
"epoch": 0.5345806882726362,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004977075899798513,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.17362408041954042,
|
|
"num_tokens": 11774117.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.394445466995239,
|
|
"epoch": 0.5349983294353492,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497703349265218,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.19093178063631058,
|
|
"num_tokens": 11782952.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.368710231781006,
|
|
"epoch": 0.5354159705980621,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004976991046518943,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.17221387028694152,
|
|
"num_tokens": 11792369.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.316056966781616,
|
|
"epoch": 0.5358336117607752,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004976948561399549,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.18843212723731995,
|
|
"num_tokens": 11801365.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.381639766693115,
|
|
"epoch": 0.5362512529234882,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004976906037294738,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.18221500366926194,
|
|
"num_tokens": 11809785.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.366283702850342,
|
|
"epoch": 0.5366688940862011,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004976863474205257,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.18574026674032212,
|
|
"num_tokens": 11817978.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.356812143325806,
|
|
"epoch": 0.5370865352489141,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004976820872131851,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.18172308206558227,
|
|
"num_tokens": 11827796.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.255517959594727,
|
|
"epoch": 0.5375041764116272,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004976778231075266,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.18679563701152802,
|
|
"num_tokens": 11836439.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.324428701400757,
|
|
"epoch": 0.5379218175743401,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004976735551036245,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.17596723586320878,
|
|
"num_tokens": 11845268.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.403821802139282,
|
|
"epoch": 0.5383394587370531,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000497669283201554,
|
|
"loss": 5.2689,
|
|
"mean_token_accuracy": 0.17970362454652786,
|
|
"num_tokens": 11855185.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.315844249725342,
|
|
"epoch": 0.5387570998997662,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004976650074013895,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.18441420644521714,
|
|
"num_tokens": 11865073.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.36966233253479,
|
|
"epoch": 0.5391747410624791,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976607277032061,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.18345875293016434,
|
|
"num_tokens": 11875004.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.3333975315094,
|
|
"epoch": 0.5395923822251921,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004976564441070788,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.1773657128214836,
|
|
"num_tokens": 11884905.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.417646837234497,
|
|
"epoch": 0.5400100233879052,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004976521566130823,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.1761803388595581,
|
|
"num_tokens": 11894669.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.512452220916748,
|
|
"epoch": 0.5404276645506181,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976478652212918,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.1686572551727295,
|
|
"num_tokens": 11904127.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.4485691547393795,
|
|
"epoch": 0.5408453057133311,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004976435699317824,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.18013800978660582,
|
|
"num_tokens": 11912031.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.291551780700684,
|
|
"epoch": 0.5412629468760441,
|
|
"grad_norm": 14.625,
|
|
"learning_rate": 0.0004976392707446293,
|
|
"loss": 5.1936,
|
|
"mean_token_accuracy": 0.19379432648420333,
|
|
"num_tokens": 11920961.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.406322240829468,
|
|
"epoch": 0.5416805880387571,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004976349676599078,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.17953124791383743,
|
|
"num_tokens": 11930454.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.31783766746521,
|
|
"epoch": 0.5420982292014701,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004976306606776932,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.18430352956056595,
|
|
"num_tokens": 11938610.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.341507530212402,
|
|
"epoch": 0.5425158703641831,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004976263497980609,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.18581376671791078,
|
|
"num_tokens": 11947882.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.37786717414856,
|
|
"epoch": 0.5429335115268961,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004976220350210864,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.17941107898950576,
|
|
"num_tokens": 11957552.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.35598783493042,
|
|
"epoch": 0.5433511526896091,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004976177163468451,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.1838558703660965,
|
|
"num_tokens": 11967350.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.350469017028809,
|
|
"epoch": 0.5437687938523221,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004976133937754128,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.1827439084649086,
|
|
"num_tokens": 11976107.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.373798465728759,
|
|
"epoch": 0.544186435015035,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004976090673068651,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.18852132707834243,
|
|
"num_tokens": 11985059.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.3296410083770756,
|
|
"epoch": 0.5446040761777481,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004976047369412778,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.1862734004855156,
|
|
"num_tokens": 11993453.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.236110258102417,
|
|
"epoch": 0.5450217173404611,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004976004026787266,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.1915011450648308,
|
|
"num_tokens": 12002524.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.261706590652466,
|
|
"epoch": 0.545439358503174,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004975960645192873,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.18687387853860854,
|
|
"num_tokens": 12011516.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.389655351638794,
|
|
"epoch": 0.5458569996658871,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004975917224630359,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.17607234567403793,
|
|
"num_tokens": 12020058.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.430317354202271,
|
|
"epoch": 0.5462746408286001,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004975873765100487,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.17935390025377274,
|
|
"num_tokens": 12029167.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.413573980331421,
|
|
"epoch": 0.546692281991313,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004975830266604013,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.18287244141101838,
|
|
"num_tokens": 12038298.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.399274921417236,
|
|
"epoch": 0.5471099231540261,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004975786729141702,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.18066378235816954,
|
|
"num_tokens": 12047437.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.372140121459961,
|
|
"epoch": 0.5475275643167391,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004975743152714314,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.1853661999106407,
|
|
"num_tokens": 12055821.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.335363817214966,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004975699537322616,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.19055379927158356,
|
|
"num_tokens": 12064378.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.275246906280517,
|
|
"epoch": 0.5483628466421651,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004975655882967366,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.18328310996294023,
|
|
"num_tokens": 12073110.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.386295366287231,
|
|
"epoch": 0.5487804878048781,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004975612189649331,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.18681494295597076,
|
|
"num_tokens": 12081224.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.444203853607178,
|
|
"epoch": 0.549198128967591,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004975568457369276,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.1844761922955513,
|
|
"num_tokens": 12090279.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.360468578338623,
|
|
"epoch": 0.549615770130304,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004975524686127966,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.1804049789905548,
|
|
"num_tokens": 12098818.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.335679626464843,
|
|
"epoch": 0.5500334112930171,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004975480875926168,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.18969240933656692,
|
|
"num_tokens": 12107358.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.354188394546509,
|
|
"epoch": 0.55045105245573,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004975437026764648,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.17559485733509064,
|
|
"num_tokens": 12116802.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.372743368148804,
|
|
"epoch": 0.550868693618443,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004975393138644175,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.18506044149398804,
|
|
"num_tokens": 12126347.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.2828162670135494,
|
|
"epoch": 0.5512863347811561,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004975349211565515,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.1851177468895912,
|
|
"num_tokens": 12136138.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.269084787368774,
|
|
"epoch": 0.551703975943869,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000497530524552944,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.18324491530656814,
|
|
"num_tokens": 12146436.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.394599580764771,
|
|
"epoch": 0.552121617106582,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004975261240536716,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.1781994119286537,
|
|
"num_tokens": 12157003.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.396362686157227,
|
|
"epoch": 0.5525392582692951,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004975217196588117,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.19297451823949813,
|
|
"num_tokens": 12166671.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.309810495376587,
|
|
"epoch": 0.552956899432008,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004975173113684413,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.18909222781658172,
|
|
"num_tokens": 12176474.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.369884920120239,
|
|
"epoch": 0.553374540594721,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004975128991826374,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.18444299697875977,
|
|
"num_tokens": 12185307.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.3402153015136715,
|
|
"epoch": 0.553792181757434,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004975084831014774,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.18116243183612823,
|
|
"num_tokens": 12195179.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.241352272033692,
|
|
"epoch": 0.554209822920147,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004975040631250386,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.1890150398015976,
|
|
"num_tokens": 12204083.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.283638286590576,
|
|
"epoch": 0.55462746408286,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004974996392533983,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.19065252989530562,
|
|
"num_tokens": 12213322.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.343265342712402,
|
|
"epoch": 0.555045105245573,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000497495211486634,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.18546016663312911,
|
|
"num_tokens": 12222305.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.381438827514648,
|
|
"epoch": 0.555462746408286,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004974907798248232,
|
|
"loss": 5.3211,
|
|
"mean_token_accuracy": 0.17728150337934495,
|
|
"num_tokens": 12232196.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.40497350692749,
|
|
"epoch": 0.555880387570999,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004974863442680434,
|
|
"loss": 5.2544,
|
|
"mean_token_accuracy": 0.1843208283185959,
|
|
"num_tokens": 12241914.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.254424905776977,
|
|
"epoch": 0.556298028733712,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004974819048163725,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.1960676372051239,
|
|
"num_tokens": 12250185.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.338935422897339,
|
|
"epoch": 0.556715669896425,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000497477461469888,
|
|
"loss": 5.311,
|
|
"mean_token_accuracy": 0.18130231350660325,
|
|
"num_tokens": 12258954.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.422602319717408,
|
|
"epoch": 0.557133311059138,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004974730142286677,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.17598465085029602,
|
|
"num_tokens": 12268320.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.267890453338623,
|
|
"epoch": 0.557550952221851,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974685630927895,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.1799112319946289,
|
|
"num_tokens": 12276804.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.440449333190918,
|
|
"epoch": 0.557968593384564,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974641080623314,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.17954966872930528,
|
|
"num_tokens": 12286024.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.4408424377441404,
|
|
"epoch": 0.558386234547277,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004974596491373711,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.18255170434713364,
|
|
"num_tokens": 12295154.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.397327518463134,
|
|
"epoch": 0.55880387570999,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004974551863179871,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.1708329826593399,
|
|
"num_tokens": 12306349.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.368606328964233,
|
|
"epoch": 0.5592215168727029,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004974507196042572,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.18280256688594818,
|
|
"num_tokens": 12315496.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.2260963916778564,
|
|
"epoch": 0.559639158035416,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004974462489962597,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.18630271255970002,
|
|
"num_tokens": 12325070.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.328977012634278,
|
|
"epoch": 0.560056799198129,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004974417744940729,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.17674152851104735,
|
|
"num_tokens": 12333509.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.396507406234742,
|
|
"epoch": 0.5604744403608419,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000497437296097775,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.18092448711395265,
|
|
"num_tokens": 12342495.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.354132032394409,
|
|
"epoch": 0.560892081523555,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004974328138074445,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.18410516530275345,
|
|
"num_tokens": 12351560.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.321539878845215,
|
|
"epoch": 0.561309722686268,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974283276231599,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.18035029768943786,
|
|
"num_tokens": 12360773.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.375478458404541,
|
|
"epoch": 0.5617273638489809,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004974238375449996,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.17522581219673156,
|
|
"num_tokens": 12370519.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.3802210807800295,
|
|
"epoch": 0.562145005011694,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004974193435730424,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.1791001543402672,
|
|
"num_tokens": 12380563.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.437316846847534,
|
|
"epoch": 0.562562646174407,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004974148457073668,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.18318154364824296,
|
|
"num_tokens": 12389291.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.401554870605469,
|
|
"epoch": 0.5629802873371199,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004974103439480517,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.18205004781484604,
|
|
"num_tokens": 12399037.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.295340442657471,
|
|
"epoch": 0.563397928499833,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004974058382951757,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.1885618582367897,
|
|
"num_tokens": 12407553.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.246711587905883,
|
|
"epoch": 0.563815569662546,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004974013287488177,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.1863757476210594,
|
|
"num_tokens": 12416298.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.3530566692352295,
|
|
"epoch": 0.5642332108252589,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004973968153090569,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.17042685747146608,
|
|
"num_tokens": 12425918.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.436422061920166,
|
|
"epoch": 0.5646508519879719,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004973922979759722,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.18476276099681854,
|
|
"num_tokens": 12434693.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.2864480972290036,
|
|
"epoch": 0.565068493150685,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004973877767496424,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.18800848424434663,
|
|
"num_tokens": 12444055.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.280451107025146,
|
|
"epoch": 0.5654861343133979,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004973832516301472,
|
|
"loss": 5.1922,
|
|
"mean_token_accuracy": 0.1876409873366356,
|
|
"num_tokens": 12453012.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.295413780212402,
|
|
"epoch": 0.5659037754761109,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004973787226175652,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.18886158466339112,
|
|
"num_tokens": 12462292.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.292002534866333,
|
|
"epoch": 0.566321416638824,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004973741897119761,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.19201604574918746,
|
|
"num_tokens": 12471178.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.315654134750366,
|
|
"epoch": 0.5667390578015369,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004973696529134592,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.18952189832925798,
|
|
"num_tokens": 12479977.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.33144588470459,
|
|
"epoch": 0.5671566989642499,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004973651122220938,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.18171906769275664,
|
|
"num_tokens": 12489004.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.384362840652466,
|
|
"epoch": 0.567574340126963,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004973605676379595,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.1782091274857521,
|
|
"num_tokens": 12498979.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.387359476089477,
|
|
"epoch": 0.5679919812896759,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004973560191611357,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.17661321610212327,
|
|
"num_tokens": 12508293.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.517708206176758,
|
|
"epoch": 0.5684096224523889,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004973514667917021,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.17277874499559404,
|
|
"num_tokens": 12517828.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.382287263870239,
|
|
"epoch": 0.5688272636151019,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004973469105297386,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.1828594297170639,
|
|
"num_tokens": 12526569.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.34793701171875,
|
|
"epoch": 0.5692449047778149,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004973423503753247,
|
|
"loss": 5.3519,
|
|
"mean_token_accuracy": 0.17847722619771958,
|
|
"num_tokens": 12535706.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.418070983886719,
|
|
"epoch": 0.5696625459405279,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004973377863285403,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.18181915283203126,
|
|
"num_tokens": 12544689.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.332527208328247,
|
|
"epoch": 0.5700801871032409,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004973332183894653,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.18357685655355455,
|
|
"num_tokens": 12553318.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.286745500564575,
|
|
"epoch": 0.5704978282659539,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004973286465581798,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.19722501188516617,
|
|
"num_tokens": 12562009.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.440903806686402,
|
|
"epoch": 0.5709154694286669,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004973240708347637,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.18447528183460235,
|
|
"num_tokens": 12571043.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.487530755996704,
|
|
"epoch": 0.5713331105913799,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004973194912192971,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.18016863763332366,
|
|
"num_tokens": 12581151.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.394162034988403,
|
|
"epoch": 0.5717507517540928,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004973149077118602,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.18303738087415694,
|
|
"num_tokens": 12590671.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.329015398025513,
|
|
"epoch": 0.5721683929168059,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004973103203125333,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.18117813766002655,
|
|
"num_tokens": 12599693.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.351763391494751,
|
|
"epoch": 0.5725860340795189,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004973057290213965,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.18840961754322053,
|
|
"num_tokens": 12609238.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.418849325180053,
|
|
"epoch": 0.5730036752422318,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004973011338385304,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.18453244715929032,
|
|
"num_tokens": 12618273.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.37387866973877,
|
|
"epoch": 0.5734213164049449,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004972965347640154,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.17970575392246246,
|
|
"num_tokens": 12628229.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.366715145111084,
|
|
"epoch": 0.5738389575676579,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497291931797932,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.19457005858421325,
|
|
"num_tokens": 12636533.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.288800144195557,
|
|
"epoch": 0.5742565987303708,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004972873249403608,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.18472814112901687,
|
|
"num_tokens": 12645503.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.354816198348999,
|
|
"epoch": 0.5746742398930839,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004972827141913822,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.18137926906347274,
|
|
"num_tokens": 12654355.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.415995168685913,
|
|
"epoch": 0.5750918810557969,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004972780995510773,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.18634467124938964,
|
|
"num_tokens": 12663774.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.2255223274230955,
|
|
"epoch": 0.5755095222185098,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004972734810195266,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.18272623121738435,
|
|
"num_tokens": 12674436.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.394057369232177,
|
|
"epoch": 0.5759271633812229,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004972688585968112,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.1799162283539772,
|
|
"num_tokens": 12682891.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.271082019805908,
|
|
"epoch": 0.5763448045439359,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004972642322830118,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.19736090451478958,
|
|
"num_tokens": 12691170.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.26110053062439,
|
|
"epoch": 0.5767624457066488,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004972596020782096,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.1865182638168335,
|
|
"num_tokens": 12700314.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.320359992980957,
|
|
"epoch": 0.5771800868693618,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004972549679824853,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.18710872828960418,
|
|
"num_tokens": 12709418.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.372145700454712,
|
|
"epoch": 0.5775977280320749,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004972503299959204,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.17934612184762955,
|
|
"num_tokens": 12719287.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.327325820922852,
|
|
"epoch": 0.5780153691947878,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000497245688118596,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.19210369884967804,
|
|
"num_tokens": 12728836.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.356794595718384,
|
|
"epoch": 0.5784330103575008,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004972410423505932,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.17989090979099273,
|
|
"num_tokens": 12738173.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.308476448059082,
|
|
"epoch": 0.5788506515202139,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972363926919935,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.18660370409488677,
|
|
"num_tokens": 12747428.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.349858331680298,
|
|
"epoch": 0.5792682926829268,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004972317391428782,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.17450422048568726,
|
|
"num_tokens": 12757148.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.4827470779418945,
|
|
"epoch": 0.5796859338456398,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004972270817033288,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.17227669209241867,
|
|
"num_tokens": 12766820.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.4383704662323,
|
|
"epoch": 0.5801035750083529,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004972224203734269,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.17507237195968628,
|
|
"num_tokens": 12776082.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.291722059249878,
|
|
"epoch": 0.5805212161710658,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497217755153254,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.18722181618213654,
|
|
"num_tokens": 12785057.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.311150979995728,
|
|
"epoch": 0.5809388573337788,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004972130860428918,
|
|
"loss": 5.2884,
|
|
"mean_token_accuracy": 0.19013078063726424,
|
|
"num_tokens": 12793599.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.400493526458741,
|
|
"epoch": 0.5813564984964918,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004972084130424222,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.17608216851949693,
|
|
"num_tokens": 12803775.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.351313972473145,
|
|
"epoch": 0.5817741396592048,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004972037361519267,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.1831551507115364,
|
|
"num_tokens": 12812327.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.352539682388306,
|
|
"epoch": 0.5821917808219178,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004971990553714874,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.1919349417090416,
|
|
"num_tokens": 12821218.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.350169467926025,
|
|
"epoch": 0.5826094219846308,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004971943707011861,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.18081563264131545,
|
|
"num_tokens": 12831579.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.395135354995728,
|
|
"epoch": 0.5830270631473438,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000497189682141105,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.18033974319696428,
|
|
"num_tokens": 12841026.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.288710975646973,
|
|
"epoch": 0.5834447043100568,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004971849896913259,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.17693693190813065,
|
|
"num_tokens": 12850136.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.420898962020874,
|
|
"epoch": 0.5838623454727698,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004971802933519312,
|
|
"loss": 5.3363,
|
|
"mean_token_accuracy": 0.1791166216135025,
|
|
"num_tokens": 12860345.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.33952693939209,
|
|
"epoch": 0.5842799866354828,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004971755931230031,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.1843261569738388,
|
|
"num_tokens": 12868995.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.439844036102295,
|
|
"epoch": 0.5846976277981958,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004971708890046236,
|
|
"loss": 5.4114,
|
|
"mean_token_accuracy": 0.17483607530593873,
|
|
"num_tokens": 12878043.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.341176462173462,
|
|
"epoch": 0.5851152689609088,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004971661809968755,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.18325130194425582,
|
|
"num_tokens": 12887090.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.326449537277222,
|
|
"epoch": 0.5855329101236217,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004971614690998409,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.19785908460617066,
|
|
"num_tokens": 12896349.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.385544300079346,
|
|
"epoch": 0.5859505512863348,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971567533136024,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.1823991373181343,
|
|
"num_tokens": 12905698.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.27918815612793,
|
|
"epoch": 0.5863681924490478,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004971520336382424,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.1906791776418686,
|
|
"num_tokens": 12915146.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.205868577957153,
|
|
"epoch": 0.5867858336117607,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004971473100738437,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.1962924838066101,
|
|
"num_tokens": 12924933.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.396005582809448,
|
|
"epoch": 0.5872034747744738,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497142582620489,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.17793653458356856,
|
|
"num_tokens": 12934959.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.342319345474243,
|
|
"epoch": 0.5876211159371868,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004971378512782609,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.19512684494256974,
|
|
"num_tokens": 12943470.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.198559999465942,
|
|
"epoch": 0.5880387570998997,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004971331160472424,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.19097486287355422,
|
|
"num_tokens": 12953592.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.412131643295288,
|
|
"epoch": 0.5884563982626128,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004971283769275163,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.17394380867481232,
|
|
"num_tokens": 12962893.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.350337505340576,
|
|
"epoch": 0.5888740394253258,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004971236339191656,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.18977117091417312,
|
|
"num_tokens": 12971635.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.201319980621338,
|
|
"epoch": 0.5892916805880387,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004971188870222734,
|
|
"loss": 5.1694,
|
|
"mean_token_accuracy": 0.19135574549436568,
|
|
"num_tokens": 12981040.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.355551242828369,
|
|
"epoch": 0.5897093217507517,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004971141362369226,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.18889567255973816,
|
|
"num_tokens": 12989898.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.38842282295227,
|
|
"epoch": 0.5901269629134648,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971093815631965,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.18946857899427413,
|
|
"num_tokens": 12998584.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.267561054229736,
|
|
"epoch": 0.5905446040761777,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004971046230011783,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.18272117227315904,
|
|
"num_tokens": 13008007.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.3609912395477295,
|
|
"epoch": 0.5909622452388907,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004970998605509514,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.1790837287902832,
|
|
"num_tokens": 13017034.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.466132068634034,
|
|
"epoch": 0.5913798864016038,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000497095094212599,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.1699241131544113,
|
|
"num_tokens": 13025916.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.443122339248657,
|
|
"epoch": 0.5917975275643167,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004970903239862047,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.1773509755730629,
|
|
"num_tokens": 13035242.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.343547201156616,
|
|
"epoch": 0.5922151687270297,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004970855498718519,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.18576087355613707,
|
|
"num_tokens": 13044123.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.339623832702637,
|
|
"epoch": 0.5926328098897428,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004970807718696243,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.17808963507413864,
|
|
"num_tokens": 13053503.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.338616991043091,
|
|
"epoch": 0.5930504510524557,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004970759899796055,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.1856381982564926,
|
|
"num_tokens": 13062106.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.375444459915161,
|
|
"epoch": 0.5934680922151687,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004970712042018791,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.18249546736478806,
|
|
"num_tokens": 13071509.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.29193081855774,
|
|
"epoch": 0.5938857333778818,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004970664145365289,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.18653131276369095,
|
|
"num_tokens": 13080469.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.317806673049927,
|
|
"epoch": 0.5943033745405947,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000497061620983639,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.1925976499915123,
|
|
"num_tokens": 13089826.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.362063884735107,
|
|
"epoch": 0.5947210157033077,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004970568235432931,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.17771779298782348,
|
|
"num_tokens": 13098630.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.333346843719482,
|
|
"epoch": 0.5951386568660207,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004970520222155751,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.18532659113407135,
|
|
"num_tokens": 13106819.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.388774776458741,
|
|
"epoch": 0.5955562980287337,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004970472170005692,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.18373559415340424,
|
|
"num_tokens": 13115471.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.285980701446533,
|
|
"epoch": 0.5959739391914467,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004970424078983596,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.19347502142190934,
|
|
"num_tokens": 13124537.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.302227973937988,
|
|
"epoch": 0.5963915803541597,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004970375949090302,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.18323099315166474,
|
|
"num_tokens": 13135326.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.431037044525146,
|
|
"epoch": 0.5968092215168727,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004970327780326655,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.17709604054689407,
|
|
"num_tokens": 13145502.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.390539216995239,
|
|
"epoch": 0.5972268626795857,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004970279572693498,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.1896309569478035,
|
|
"num_tokens": 13154808.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.285022211074829,
|
|
"epoch": 0.5976445038422987,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004970231326191674,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.17192819863557815,
|
|
"num_tokens": 13163982.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.379360580444336,
|
|
"epoch": 0.5980621450050116,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004970183040822029,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.18212141543626786,
|
|
"num_tokens": 13172446.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.3797863006591795,
|
|
"epoch": 0.5984797861677247,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004970134716585407,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.17862303853034972,
|
|
"num_tokens": 13181671.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.264983320236206,
|
|
"epoch": 0.5988974273304377,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004970086353482654,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.18219546973705292,
|
|
"num_tokens": 13190207.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.283562469482422,
|
|
"epoch": 0.5993150684931506,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004970037951514617,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.1897499144077301,
|
|
"num_tokens": 13198866.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.266381168365479,
|
|
"epoch": 0.5997327096558637,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004969989510682143,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.19003028124570848,
|
|
"num_tokens": 13207921.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.441741847991944,
|
|
"epoch": 0.6001503508185767,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004969941030986082,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.17731461375951768,
|
|
"num_tokens": 13217759.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.310184001922607,
|
|
"epoch": 0.6005679919812896,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000496989251242728,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.1870572417974472,
|
|
"num_tokens": 13226592.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.2749436378479,
|
|
"epoch": 0.6009856331440027,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004969843955006588,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.18484863340854646,
|
|
"num_tokens": 13236123.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.3280675411224365,
|
|
"epoch": 0.6014032743067157,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969795358724855,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.18016528859734535,
|
|
"num_tokens": 13246169.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.3149556636810305,
|
|
"epoch": 0.6018209154694286,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004969746723582932,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.19074517488479614,
|
|
"num_tokens": 13256141.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.384066438674926,
|
|
"epoch": 0.6022385566321417,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004969698049581672,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.18261153548955916,
|
|
"num_tokens": 13265491.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.488926124572754,
|
|
"epoch": 0.6026561977948547,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004969649336721924,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.18465238213539123,
|
|
"num_tokens": 13274805.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.40759916305542,
|
|
"epoch": 0.6030738389575676,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004969600585004544,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.18210784196853638,
|
|
"num_tokens": 13284589.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.267890977859497,
|
|
"epoch": 0.6034914801202806,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004969551794430383,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.19712562263011932,
|
|
"num_tokens": 13293370.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.411610698699951,
|
|
"epoch": 0.6039091212829937,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004969502965000297,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.18510427922010422,
|
|
"num_tokens": 13302555.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.279111528396607,
|
|
"epoch": 0.6043267624457066,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000496945409671514,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.18550454825162888,
|
|
"num_tokens": 13311632.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.320348691940308,
|
|
"epoch": 0.6047444036084196,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004969405189575768,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.19313837885856627,
|
|
"num_tokens": 13320593.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.328238487243652,
|
|
"epoch": 0.6051620447711327,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004969356243583036,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.19189489483833314,
|
|
"num_tokens": 13329095.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.264534997940063,
|
|
"epoch": 0.6055796859338456,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004969307258737802,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.19089837074279786,
|
|
"num_tokens": 13338404.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.287572193145752,
|
|
"epoch": 0.6059973270965586,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004969258235040921,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.190699964761734,
|
|
"num_tokens": 13347095.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.331546020507813,
|
|
"epoch": 0.6064149682592717,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004969209172493255,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.18628860563039779,
|
|
"num_tokens": 13356606.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.3542115688323975,
|
|
"epoch": 0.6068326094219846,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004969160071095661,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.17968995571136476,
|
|
"num_tokens": 13366889.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.3427972316741945,
|
|
"epoch": 0.6072502505846976,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004969110930848999,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.1801399767398834,
|
|
"num_tokens": 13376761.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.345357751846313,
|
|
"epoch": 0.6076678917474106,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004969061751754129,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.18946549892425538,
|
|
"num_tokens": 13386226.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.24541597366333,
|
|
"epoch": 0.6080855329101236,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004969012533811911,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.19180119186639785,
|
|
"num_tokens": 13394243.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.297079992294312,
|
|
"epoch": 0.6085031740728366,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004968963277023208,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.1712947428226471,
|
|
"num_tokens": 13403708.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.289767599105835,
|
|
"epoch": 0.6089208152355496,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004968913981388882,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.1913897216320038,
|
|
"num_tokens": 13412911.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.420920896530151,
|
|
"epoch": 0.6093384563982626,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004968864646909797,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.18042888194322587,
|
|
"num_tokens": 13422423.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.339856433868408,
|
|
"epoch": 0.6097560975609756,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004968815273586814,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.18344418108463287,
|
|
"num_tokens": 13430984.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.313500881195068,
|
|
"epoch": 0.6101737387236886,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004968765861420799,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.18218379020690917,
|
|
"num_tokens": 13440492.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.378695392608643,
|
|
"epoch": 0.6105913798864016,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004968716410412617,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.1780386224389076,
|
|
"num_tokens": 13449222.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.316129922866821,
|
|
"epoch": 0.6110090210491146,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004968666920563134,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.1849824532866478,
|
|
"num_tokens": 13459126.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.447695922851563,
|
|
"epoch": 0.6114266622118276,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004968617391873216,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.17276448756456375,
|
|
"num_tokens": 13468811.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.394797897338867,
|
|
"epoch": 0.6118443033745405,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004968567824343729,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.18289622515439988,
|
|
"num_tokens": 13477765.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.354283380508423,
|
|
"epoch": 0.6122619445372536,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004968518217975542,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.17394291758537292,
|
|
"num_tokens": 13487184.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.325632810592651,
|
|
"epoch": 0.6126795856999666,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004968468572769524,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.18050160109996796,
|
|
"num_tokens": 13496784.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.360996294021606,
|
|
"epoch": 0.6130972268626795,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004968418888726543,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.1839147076010704,
|
|
"num_tokens": 13505824.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.321667623519898,
|
|
"epoch": 0.6135148680253926,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004968369165847469,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.19074717164039612,
|
|
"num_tokens": 13515111.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.265428972244263,
|
|
"epoch": 0.6139325091881056,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004968319404133173,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.19337067902088165,
|
|
"num_tokens": 13524163.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.2426989555358885,
|
|
"epoch": 0.6143501503508185,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004968269603584525,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.19729869216680526,
|
|
"num_tokens": 13533368.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.348956775665283,
|
|
"epoch": 0.6147677915135316,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004968219764202397,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.1793224424123764,
|
|
"num_tokens": 13543708.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.328090858459473,
|
|
"epoch": 0.6151854326762446,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004968169885987663,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.178127159178257,
|
|
"num_tokens": 13552561.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.493785858154297,
|
|
"epoch": 0.6156030738389575,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004968119968941193,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.17047833055257797,
|
|
"num_tokens": 13562050.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.292812633514404,
|
|
"epoch": 0.6160207150016705,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004968070013063866,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.18223292082548143,
|
|
"num_tokens": 13571356.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.280111265182495,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004968020018356552,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.17824804931879043,
|
|
"num_tokens": 13581357.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.334889364242554,
|
|
"epoch": 0.6168559973270965,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004967969984820128,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.18418300598859788,
|
|
"num_tokens": 13589392.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.3280601978302,
|
|
"epoch": 0.6172736384898095,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004967919912455469,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.19772139340639114,
|
|
"num_tokens": 13598376.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.216180658340454,
|
|
"epoch": 0.6176912796525226,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004967869801263454,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.201987686753273,
|
|
"num_tokens": 13607014.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.273418521881103,
|
|
"epoch": 0.6181089208152355,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004967819651244957,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.18187806010246277,
|
|
"num_tokens": 13615700.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.40106315612793,
|
|
"epoch": 0.6185265619779485,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004967769462400857,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.1862255647778511,
|
|
"num_tokens": 13625230.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.480621004104615,
|
|
"epoch": 0.6189442031406616,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004967719234732033,
|
|
"loss": 5.4279,
|
|
"mean_token_accuracy": 0.18136966973543167,
|
|
"num_tokens": 13635258.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.23916802406311,
|
|
"epoch": 0.6193618443033745,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004967668968239365,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.18889791518449783,
|
|
"num_tokens": 13643688.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.297773933410644,
|
|
"epoch": 0.6197794854660875,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004967618662923732,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.18282823413610458,
|
|
"num_tokens": 13652894.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.33356122970581,
|
|
"epoch": 0.6201971266288006,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004967568318786016,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.18684618920087814,
|
|
"num_tokens": 13662852.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.36697096824646,
|
|
"epoch": 0.6206147677915135,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004967517935827097,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.1854433074593544,
|
|
"num_tokens": 13671457.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.349347496032715,
|
|
"epoch": 0.6210324089542265,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004967467514047856,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.18863174319267273,
|
|
"num_tokens": 13681002.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.352931785583496,
|
|
"epoch": 0.6214500501169395,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004967417053449178,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.18377165794372557,
|
|
"num_tokens": 13690677.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.292918729782104,
|
|
"epoch": 0.6218676912796525,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004967366554031945,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.19274694174528123,
|
|
"num_tokens": 13699151.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.2490105628967285,
|
|
"epoch": 0.6222853324423655,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004967316015797042,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.18493798971176148,
|
|
"num_tokens": 13708105.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.3417497158050535,
|
|
"epoch": 0.6227029736050785,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004967265438745352,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.17622340694069863,
|
|
"num_tokens": 13717094.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.4337269306182865,
|
|
"epoch": 0.6231206147677915,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004967214822877763,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.1915486201643944,
|
|
"num_tokens": 13726639.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.335785913467407,
|
|
"epoch": 0.6235382559305045,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004967164168195159,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.18517189621925353,
|
|
"num_tokens": 13735220.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.207172584533692,
|
|
"epoch": 0.6239558970932175,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004967113474698428,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.19569428712129594,
|
|
"num_tokens": 13743277.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.3403395652771,
|
|
"epoch": 0.6243735382559304,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004967062742388456,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.1846537321805954,
|
|
"num_tokens": 13752946.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.3574121475219725,
|
|
"epoch": 0.6247911794186435,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004967011971266132,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.18475013822317124,
|
|
"num_tokens": 13761297.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.327942609786987,
|
|
"epoch": 0.6252088205813565,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004966961161332346,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.18386684060096742,
|
|
"num_tokens": 13771238.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.364589881896973,
|
|
"epoch": 0.6256264617440696,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004966910312587985,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.18339993059635162,
|
|
"num_tokens": 13781420.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.308527183532715,
|
|
"epoch": 0.6260441029067825,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004966859425033941,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.1881234809756279,
|
|
"num_tokens": 13789833.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.390172338485717,
|
|
"epoch": 0.6264617440694955,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004966808498671104,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.17690399289131165,
|
|
"num_tokens": 13799202.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.399218368530273,
|
|
"epoch": 0.6268793852322085,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004966757533500367,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.18487776964902877,
|
|
"num_tokens": 13809097.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.355049562454224,
|
|
"epoch": 0.6272970263949215,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000496670652952262,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.18850983381271363,
|
|
"num_tokens": 13818437.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.331247568130493,
|
|
"epoch": 0.6277146675576345,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004966655486738757,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.18493678718805312,
|
|
"num_tokens": 13827083.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.306726598739624,
|
|
"epoch": 0.6281323087203475,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004966604405149672,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.1843095228075981,
|
|
"num_tokens": 13835905.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.290187835693359,
|
|
"epoch": 0.6285499498830605,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004966553284756257,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.19366546273231505,
|
|
"num_tokens": 13845136.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.283191108703614,
|
|
"epoch": 0.6289675910457735,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004966502125559411,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.1859496995806694,
|
|
"num_tokens": 13855087.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.367642831802368,
|
|
"epoch": 0.6293852322084865,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004966450927560026,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.18497766703367233,
|
|
"num_tokens": 13864077.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.348160266876221,
|
|
"epoch": 0.6298028733711994,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004966399690759,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.18485676795244216,
|
|
"num_tokens": 13873404.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.4055322170257565,
|
|
"epoch": 0.6302205145339125,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000496634841515723,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.18193374574184418,
|
|
"num_tokens": 13883231.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.205918598175049,
|
|
"epoch": 0.6306381556966255,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004966297100755613,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.1982281342148781,
|
|
"num_tokens": 13892314.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.220934677124023,
|
|
"epoch": 0.6310557968593384,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004966245747555047,
|
|
"loss": 5.1708,
|
|
"mean_token_accuracy": 0.1904767259955406,
|
|
"num_tokens": 13900771.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.313705539703369,
|
|
"epoch": 0.6314734380220515,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004966194355556432,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.19047312587499618,
|
|
"num_tokens": 13909615.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.355904197692871,
|
|
"epoch": 0.6318910791847645,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004966142924760666,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.1856594130396843,
|
|
"num_tokens": 13918491.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.301749563217163,
|
|
"epoch": 0.6323087203474774,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004966091455168652,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.17914954125881194,
|
|
"num_tokens": 13927935.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.298324489593506,
|
|
"epoch": 0.6327263615101905,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004966039946781289,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.19273121207952498,
|
|
"num_tokens": 13936524.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.23538384437561,
|
|
"epoch": 0.6331440026729035,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000496598839959948,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.18347153812646866,
|
|
"num_tokens": 13945544.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.293307542800903,
|
|
"epoch": 0.6335616438356164,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004965936813624126,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.193753482401371,
|
|
"num_tokens": 13955016.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.325612735748291,
|
|
"epoch": 0.6339792849983295,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000496588518885613,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.18419731855392457,
|
|
"num_tokens": 13964045.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.332293176651001,
|
|
"epoch": 0.6343969261610425,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004965833525296397,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.18768487274646758,
|
|
"num_tokens": 13973554.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.290938854217529,
|
|
"epoch": 0.6348145673237554,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004965781822945831,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.18466798812150956,
|
|
"num_tokens": 13982669.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.369865846633911,
|
|
"epoch": 0.6352322084864684,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004965730081805338,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.17964046746492385,
|
|
"num_tokens": 13993392.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.4114116668701175,
|
|
"epoch": 0.6356498496491815,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004965678301875821,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.17811712324619294,
|
|
"num_tokens": 14002659.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.315918636322022,
|
|
"epoch": 0.6360674908118944,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000496562648315819,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.18533693999052048,
|
|
"num_tokens": 14011561.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.342669439315796,
|
|
"epoch": 0.6364851319746074,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496557462565335,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.18481769561767578,
|
|
"num_tokens": 14021286.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.307096338272094,
|
|
"epoch": 0.6369027731373205,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004965522729362209,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.19055305868387223,
|
|
"num_tokens": 14031901.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.328595161437988,
|
|
"epoch": 0.6373204143000334,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004965470794285676,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.18768050372600556,
|
|
"num_tokens": 14041000.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.415085124969482,
|
|
"epoch": 0.6377380554627464,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000496541882042466,
|
|
"loss": 5.3154,
|
|
"mean_token_accuracy": 0.17772594690322877,
|
|
"num_tokens": 14050567.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.298159551620484,
|
|
"epoch": 0.6381556966254595,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004965366807780071,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.18856868594884874,
|
|
"num_tokens": 14059990.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.282280111312867,
|
|
"epoch": 0.6385733377881724,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004965314756352818,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.18284620642662047,
|
|
"num_tokens": 14069317.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.34216046333313,
|
|
"epoch": 0.6389909789508854,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004965262666143816,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.18454798310995102,
|
|
"num_tokens": 14078809.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.365179538726807,
|
|
"epoch": 0.6394086201135984,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004965210537153973,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.17834798991680145,
|
|
"num_tokens": 14087660.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.392992258071899,
|
|
"epoch": 0.6398262612763114,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004965158369384204,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.17948950380086898,
|
|
"num_tokens": 14096585.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.28318452835083,
|
|
"epoch": 0.6402439024390244,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000496510616283542,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.19040281027555467,
|
|
"num_tokens": 14106079.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.296985054016114,
|
|
"epoch": 0.6406615436017374,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004965053917508537,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.1832717940211296,
|
|
"num_tokens": 14115988.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.363583993911743,
|
|
"epoch": 0.6410791847644504,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004965001633404469,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.17442837357521057,
|
|
"num_tokens": 14126980.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.401338386535644,
|
|
"epoch": 0.6414968259271634,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004964949310524131,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.18376351296901702,
|
|
"num_tokens": 14135780.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.393174266815185,
|
|
"epoch": 0.6419144670898764,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004964896948868439,
|
|
"loss": 5.2884,
|
|
"mean_token_accuracy": 0.17311108410358428,
|
|
"num_tokens": 14145655.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.334845304489136,
|
|
"epoch": 0.6423321082525894,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004964844548438311,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.19475809633731841,
|
|
"num_tokens": 14154157.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.3640824317932125,
|
|
"epoch": 0.6427497494153024,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004964792109234662,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.18169961273670196,
|
|
"num_tokens": 14163749.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.284685802459717,
|
|
"epoch": 0.6431673905780154,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004964739631258411,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.18628758788108826,
|
|
"num_tokens": 14174170.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.33451657295227,
|
|
"epoch": 0.6435850317407283,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004964687114510478,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.18481380492448807,
|
|
"num_tokens": 14182625.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.381241226196289,
|
|
"epoch": 0.6440026729034414,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000496463455899178,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.18117601424455643,
|
|
"num_tokens": 14192351.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.215759181976319,
|
|
"epoch": 0.6444203140661544,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004964581964703239,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.18823303878307343,
|
|
"num_tokens": 14201107.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.334169054031372,
|
|
"epoch": 0.6448379552288673,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004964529331645776,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.19227225780487062,
|
|
"num_tokens": 14209540.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.29780330657959,
|
|
"epoch": 0.6452555963915804,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000496447665982031,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.19178706109523774,
|
|
"num_tokens": 14217944.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.256038570404053,
|
|
"epoch": 0.6456732375542934,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004964423949227765,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.1919618457555771,
|
|
"num_tokens": 14226044.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.3067868709564205,
|
|
"epoch": 0.6460908787170063,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004964371199869062,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.17858000248670577,
|
|
"num_tokens": 14235566.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.320413303375244,
|
|
"epoch": 0.6465085198797194,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004964318411745127,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.19364046007394792,
|
|
"num_tokens": 14244511.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.3206816673278805,
|
|
"epoch": 0.6469261610424324,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004964265584856883,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.17933887243270874,
|
|
"num_tokens": 14254299.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.242252397537231,
|
|
"epoch": 0.6473438022051453,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004964212719205254,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.1874264359474182,
|
|
"num_tokens": 14262915.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.305627775192261,
|
|
"epoch": 0.6477614433678583,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004964159814791167,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.18672461062669754,
|
|
"num_tokens": 14272606.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.325691652297974,
|
|
"epoch": 0.6481790845305714,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004964106871615547,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.1769751340150833,
|
|
"num_tokens": 14282117.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.266233634948731,
|
|
"epoch": 0.6485967256932843,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000496405388967932,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.19108301848173143,
|
|
"num_tokens": 14290421.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.417497158050537,
|
|
"epoch": 0.6490143668559973,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004964000868983416,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.18283947557210922,
|
|
"num_tokens": 14299870.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.4342268943786625,
|
|
"epoch": 0.6494320080187104,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004963947809528761,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.18015625774860383,
|
|
"num_tokens": 14309916.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.295298337936401,
|
|
"epoch": 0.6498496491814233,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004963894711316285,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.18146929442882537,
|
|
"num_tokens": 14319061.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.293241739273071,
|
|
"epoch": 0.6502672903441363,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004963841574346917,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.19493246227502822,
|
|
"num_tokens": 14327241.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.354121112823487,
|
|
"epoch": 0.6506849315068494,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004963788398621587,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.18239463865756989,
|
|
"num_tokens": 14336586.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.3281457901000975,
|
|
"epoch": 0.6511025726695623,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004963735184141227,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.1824356123805046,
|
|
"num_tokens": 14346484.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.422971963882446,
|
|
"epoch": 0.6515202138322753,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004963681930906768,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.17493996769189835,
|
|
"num_tokens": 14356255.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.365948581695557,
|
|
"epoch": 0.6519378549949884,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004963628638919141,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.18347094655036927,
|
|
"num_tokens": 14365680.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.353703498840332,
|
|
"epoch": 0.6523554961577013,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004963575308179281,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.1850593239068985,
|
|
"num_tokens": 14374546.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.357265901565552,
|
|
"epoch": 0.6527731373204143,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004963521938688122,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.1900917574763298,
|
|
"num_tokens": 14383624.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.378614139556885,
|
|
"epoch": 0.6531907784831273,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004963468530446596,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.17858231961727142,
|
|
"num_tokens": 14392482.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.3555823802948,
|
|
"epoch": 0.6536084196458403,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004963415083455639,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.1824125111103058,
|
|
"num_tokens": 14401940.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.3768706798553465,
|
|
"epoch": 0.6540260608085533,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004963361597716186,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.18103145509958268,
|
|
"num_tokens": 14411127.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.329895257949829,
|
|
"epoch": 0.6544437019712663,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004963308073229175,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.1840163514018059,
|
|
"num_tokens": 14421358.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.319847917556762,
|
|
"epoch": 0.6548613431339793,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004963254509995542,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.17936811447143555,
|
|
"num_tokens": 14430507.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.300984907150268,
|
|
"epoch": 0.6552789842966923,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004963200908016224,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.18744567632675171,
|
|
"num_tokens": 14439723.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.364639043807983,
|
|
"epoch": 0.6556966254594053,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000496314726729216,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.18130225986242293,
|
|
"num_tokens": 14449011.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.322962141036987,
|
|
"epoch": 0.6561142666221182,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004963093587824289,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.1883500710129738,
|
|
"num_tokens": 14457676.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.317316293716431,
|
|
"epoch": 0.6565319077848313,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004963039869613551,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.18281662315130234,
|
|
"num_tokens": 14466956.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.330993938446045,
|
|
"epoch": 0.6569495489475443,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004962986112660887,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.18978717774152756,
|
|
"num_tokens": 14476083.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.380226421356201,
|
|
"epoch": 0.6573671901102572,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004962932316967237,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.1838265299797058,
|
|
"num_tokens": 14484980.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.340812683105469,
|
|
"epoch": 0.6577848312729703,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004962878482533544,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.18076233118772506,
|
|
"num_tokens": 14493965.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.385230588912964,
|
|
"epoch": 0.6582024724356833,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004962824609360748,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.1849704399704933,
|
|
"num_tokens": 14501914.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.274803495407104,
|
|
"epoch": 0.6586201135983962,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004962770697449794,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.18560997247695923,
|
|
"num_tokens": 14511447.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.26126184463501,
|
|
"epoch": 0.6590377547611093,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004962716746801625,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.18252527862787246,
|
|
"num_tokens": 14520558.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.332695484161377,
|
|
"epoch": 0.6594553959238223,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004962662757417187,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.18705461770296097,
|
|
"num_tokens": 14529995.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.33423376083374,
|
|
"epoch": 0.6598730370865352,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004962608729297424,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.1774620771408081,
|
|
"num_tokens": 14538972.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.345441484451294,
|
|
"epoch": 0.6602906782492483,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004962554662443281,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.18200966119766235,
|
|
"num_tokens": 14548255.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.284280252456665,
|
|
"epoch": 0.6607083194119613,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004962500556855706,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.18816303312778473,
|
|
"num_tokens": 14557265.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.380446290969848,
|
|
"epoch": 0.6611259605746742,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004962446412535645,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.1826505497097969,
|
|
"num_tokens": 14566650.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.3239155292510985,
|
|
"epoch": 0.6615436017373872,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962392229484046,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.19616436660289766,
|
|
"num_tokens": 14575550.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.337485313415527,
|
|
"epoch": 0.6619612429001003,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000496233800770186,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.18520848751068114,
|
|
"num_tokens": 14584459.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.392370510101318,
|
|
"epoch": 0.6623788840628132,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004962283747190033,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.1802950844168663,
|
|
"num_tokens": 14593709.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.258808040618897,
|
|
"epoch": 0.6627965252255262,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004962229447949515,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.19028683751821518,
|
|
"num_tokens": 14602071.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.41706166267395,
|
|
"epoch": 0.6632141663882393,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004962175109981259,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.17619150280952453,
|
|
"num_tokens": 14612842.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.463220453262329,
|
|
"epoch": 0.6636318075509522,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004962120733286215,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.18361104130744935,
|
|
"num_tokens": 14621645.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.245592975616455,
|
|
"epoch": 0.6640494487136652,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004962066317865334,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.1886135458946228,
|
|
"num_tokens": 14630447.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.263873529434204,
|
|
"epoch": 0.6644670898763783,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496201186371957,
|
|
"loss": 5.2422,
|
|
"mean_token_accuracy": 0.191739284992218,
|
|
"num_tokens": 14639371.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.375819110870362,
|
|
"epoch": 0.6648847310390912,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004961957370849875,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.18274612724781036,
|
|
"num_tokens": 14648540.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.384054374694824,
|
|
"epoch": 0.6653023722018042,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004961902839257205,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.183157841861248,
|
|
"num_tokens": 14658130.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.386115550994873,
|
|
"epoch": 0.6657200133645172,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004961848268942513,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.1771568238735199,
|
|
"num_tokens": 14667538.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.374794006347656,
|
|
"epoch": 0.6661376545272302,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004961793659906754,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.177203768491745,
|
|
"num_tokens": 14677115.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.437082386016845,
|
|
"epoch": 0.6665552956899432,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004961739012150885,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.18960783183574675,
|
|
"num_tokens": 14686444.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.325315284729004,
|
|
"epoch": 0.6669729368526562,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004961684325675862,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.19141027480363845,
|
|
"num_tokens": 14695951.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.31355094909668,
|
|
"epoch": 0.6673905780153692,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004961629600482643,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.18038068562746049,
|
|
"num_tokens": 14705415.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.417062187194825,
|
|
"epoch": 0.6678082191780822,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004961574836572186,
|
|
"loss": 5.2723,
|
|
"mean_token_accuracy": 0.18219208866357803,
|
|
"num_tokens": 14714793.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.276196432113648,
|
|
"epoch": 0.6682258603407952,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004961520033945448,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.19502789080142974,
|
|
"num_tokens": 14723820.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.288319492340088,
|
|
"epoch": 0.6686435015035082,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004961465192603391,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.19178766310214995,
|
|
"num_tokens": 14733055.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.338773727416992,
|
|
"epoch": 0.6690611426662212,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004961410312546974,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.1862553045153618,
|
|
"num_tokens": 14742416.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.295219945907593,
|
|
"epoch": 0.6694787838289342,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004961355393777158,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.18526092320680618,
|
|
"num_tokens": 14751384.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.250601530075073,
|
|
"epoch": 0.6698964249916471,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004961300436294902,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.18689117580652237,
|
|
"num_tokens": 14760525.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.3468163967132565,
|
|
"epoch": 0.6703140661543602,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004961245440101171,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.1819304719567299,
|
|
"num_tokens": 14769405.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.238767528533936,
|
|
"epoch": 0.6707317073170732,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004961190405196928,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.18605050891637803,
|
|
"num_tokens": 14778945.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.373712873458862,
|
|
"epoch": 0.6711493484797861,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004961135331583135,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.1771259590983391,
|
|
"num_tokens": 14788289.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.292560672760009,
|
|
"epoch": 0.6715669896424992,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004961080219260755,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.18261197507381438,
|
|
"num_tokens": 14797761.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.344115161895752,
|
|
"epoch": 0.6719846308052122,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004961025068230757,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.1875170111656189,
|
|
"num_tokens": 14806424.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.29541711807251,
|
|
"epoch": 0.6724022719679251,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004960969878494103,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.1792940229177475,
|
|
"num_tokens": 14815816.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.263209342956543,
|
|
"epoch": 0.6728199131306382,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004960914650051758,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.1867182433605194,
|
|
"num_tokens": 14824877.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.24476809501648,
|
|
"epoch": 0.6732375542933512,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004960859382904691,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.19761217534542083,
|
|
"num_tokens": 14833095.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.392882919311523,
|
|
"epoch": 0.6736551954560641,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000496080407705387,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.180871120095253,
|
|
"num_tokens": 14842963.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.411832475662232,
|
|
"epoch": 0.6740728366187771,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004960748732500263,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.18388109803199768,
|
|
"num_tokens": 14851552.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.34446907043457,
|
|
"epoch": 0.6744904777814902,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004960693349244838,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.18630302846431732,
|
|
"num_tokens": 14859997.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.321320629119873,
|
|
"epoch": 0.6749081189442031,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004960637927288566,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.18813525140285492,
|
|
"num_tokens": 14868050.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.301049709320068,
|
|
"epoch": 0.6753257601069161,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004960582466632414,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.1822244793176651,
|
|
"num_tokens": 14877774.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.240277290344238,
|
|
"epoch": 0.6757434012696292,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004960526967277356,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.1926938235759735,
|
|
"num_tokens": 14886971.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.238359546661377,
|
|
"epoch": 0.6761610424323421,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004960471429224363,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.1871116504073143,
|
|
"num_tokens": 14895815.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.296923542022705,
|
|
"epoch": 0.6765786835950551,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004960415852474406,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.19421091228723525,
|
|
"num_tokens": 14904082.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.280825757980347,
|
|
"epoch": 0.6769963247577682,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000496036023702846,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.1913072794675827,
|
|
"num_tokens": 14913533.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.277411365509034,
|
|
"epoch": 0.6774139659204811,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004960304582887497,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.18801499307155609,
|
|
"num_tokens": 14922063.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.314997434616089,
|
|
"epoch": 0.6778316070831941,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004960248890052493,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.1813928097486496,
|
|
"num_tokens": 14930219.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.381176519393921,
|
|
"epoch": 0.6782492482459072,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000496019315852442,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.18256254643201827,
|
|
"num_tokens": 14939463.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.402235221862793,
|
|
"epoch": 0.6786668894086201,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004960137388304255,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.1897577852010727,
|
|
"num_tokens": 14948289.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.347008609771729,
|
|
"epoch": 0.6790845305713331,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004960081579392975,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.18622678965330125,
|
|
"num_tokens": 14958172.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.241091251373291,
|
|
"epoch": 0.6795021717340461,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004960025731791558,
|
|
"loss": 5.0896,
|
|
"mean_token_accuracy": 0.19144905507564544,
|
|
"num_tokens": 14967362.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.273113155364991,
|
|
"epoch": 0.6799198128967591,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004959969845500979,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.1805402860045433,
|
|
"num_tokens": 14975942.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.323067092895508,
|
|
"epoch": 0.6803374540594721,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004959913920522218,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.18757303953170776,
|
|
"num_tokens": 14985428.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.32785005569458,
|
|
"epoch": 0.6807550952221851,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004959857956856254,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.1838672325015068,
|
|
"num_tokens": 14994558.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.326738452911377,
|
|
"epoch": 0.6811727363848981,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004959801954504067,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.1867782175540924,
|
|
"num_tokens": 15003674.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.315521955490112,
|
|
"epoch": 0.6815903775476111,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004959745913466635,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.18782551288604737,
|
|
"num_tokens": 15012569.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.327926349639893,
|
|
"epoch": 0.6820080187103241,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004959689833744942,
|
|
"loss": 5.2356,
|
|
"mean_token_accuracy": 0.18866464048624038,
|
|
"num_tokens": 15021863.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.3411026954650875,
|
|
"epoch": 0.682425659873037,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004959633715339969,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.17385224550962447,
|
|
"num_tokens": 15032272.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.29858512878418,
|
|
"epoch": 0.6828433010357501,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004959577558252698,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.18027757704257966,
|
|
"num_tokens": 15041066.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.4229888916015625,
|
|
"epoch": 0.6832609421984631,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004959521362484112,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.18273967504501343,
|
|
"num_tokens": 15050855.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.31981406211853,
|
|
"epoch": 0.683678583361176,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004959465128035195,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.192647847533226,
|
|
"num_tokens": 15060810.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.296506929397583,
|
|
"epoch": 0.6840962245238891,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004959408854906932,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.1906803071498871,
|
|
"num_tokens": 15069761.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.253224277496338,
|
|
"epoch": 0.6845138656866021,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004959352543100306,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.18826841562986374,
|
|
"num_tokens": 15078691.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.253979873657227,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004959296192616305,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.19228082299232482,
|
|
"num_tokens": 15087068.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.297430467605591,
|
|
"epoch": 0.6853491480120281,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004959239803455916,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.1919408455491066,
|
|
"num_tokens": 15095962.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.271142101287841,
|
|
"epoch": 0.6857667891747411,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004959183375620123,
|
|
"loss": 5.2207,
|
|
"mean_token_accuracy": 0.18081678003072738,
|
|
"num_tokens": 15105835.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.2731605052948,
|
|
"epoch": 0.686184430337454,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004959126909109918,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.19526263922452927,
|
|
"num_tokens": 15114140.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.344247579574585,
|
|
"epoch": 0.686602071500167,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004959070403926286,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.18727920651435853,
|
|
"num_tokens": 15123253.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.445370769500732,
|
|
"epoch": 0.6870197126628801,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004959013860070217,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.17764439433813095,
|
|
"num_tokens": 15133699.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.3401844024658205,
|
|
"epoch": 0.687437353825593,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004958957277542701,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.19175320714712143,
|
|
"num_tokens": 15142133.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.279022932052612,
|
|
"epoch": 0.687854994988306,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004958900656344731,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.18504478335380553,
|
|
"num_tokens": 15151367.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.283271741867066,
|
|
"epoch": 0.6882726361510191,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004958843996477296,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.18199769407510757,
|
|
"num_tokens": 15160938.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.4045368194580075,
|
|
"epoch": 0.688690277313732,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004958787297941386,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.1807729035615921,
|
|
"num_tokens": 15170507.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.393487977981567,
|
|
"epoch": 0.689107918476445,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004958730560737998,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.18554342314600944,
|
|
"num_tokens": 15179822.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.3177588939666744,
|
|
"epoch": 0.6895255596391581,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004958673784868121,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.18469705432653427,
|
|
"num_tokens": 15189353.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.343029642105103,
|
|
"epoch": 0.689943200801871,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004958616970332752,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.17982738912105561,
|
|
"num_tokens": 15197772.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.288300085067749,
|
|
"epoch": 0.690360841964584,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004958560117132884,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.18857772499322892,
|
|
"num_tokens": 15207453.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.289036798477173,
|
|
"epoch": 0.6907784831272971,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004958503225269513,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.19024553447961806,
|
|
"num_tokens": 15215787.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.41863865852356,
|
|
"epoch": 0.69119612429001,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004958446294743633,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.18338089287281037,
|
|
"num_tokens": 15225148.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.372235584259033,
|
|
"epoch": 0.691613765452723,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004958389325556245,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.18188745975494386,
|
|
"num_tokens": 15234533.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.300735425949097,
|
|
"epoch": 0.692031406615436,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004958332317708341,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.17238677889108658,
|
|
"num_tokens": 15243805.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.406217336654663,
|
|
"epoch": 0.692449047778149,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004958275271200924,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.18325183987617494,
|
|
"num_tokens": 15253298.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.314294815063477,
|
|
"epoch": 0.692866688940862,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004958218186034988,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.1871773287653923,
|
|
"num_tokens": 15261860.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.314128017425537,
|
|
"epoch": 0.693284330103575,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004958161062211537,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.18709763884544373,
|
|
"num_tokens": 15271021.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.282918977737427,
|
|
"epoch": 0.693701971266288,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004958103899731566,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.18143055588006973,
|
|
"num_tokens": 15280489.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.330470991134644,
|
|
"epoch": 0.694119612429001,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004958046698596081,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.19208525270223617,
|
|
"num_tokens": 15289387.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.350530004501342,
|
|
"epoch": 0.694537253591714,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004957989458806079,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.1837986633181572,
|
|
"num_tokens": 15299334.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.330388498306275,
|
|
"epoch": 0.694954894754427,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004957932180362564,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.18512164205312728,
|
|
"num_tokens": 15309174.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.378217935562134,
|
|
"epoch": 0.69537253591714,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004957874863266538,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.18431434631347657,
|
|
"num_tokens": 15318722.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.436281538009643,
|
|
"epoch": 0.695790177079853,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004957817507519006,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.18671645671129228,
|
|
"num_tokens": 15327606.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.309534358978271,
|
|
"epoch": 0.696207818242566,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004957760113120971,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19387727379798889,
|
|
"num_tokens": 15336520.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.378321361541748,
|
|
"epoch": 0.696625459405279,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004957702680073437,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.18018345087766646,
|
|
"num_tokens": 15345437.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.409728097915649,
|
|
"epoch": 0.697043100567992,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004957645208377411,
|
|
"loss": 5.2033,
|
|
"mean_token_accuracy": 0.186541286110878,
|
|
"num_tokens": 15354660.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.334236431121826,
|
|
"epoch": 0.6974607417307049,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004957587698033898,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.1862293854355812,
|
|
"num_tokens": 15363958.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.34509129524231,
|
|
"epoch": 0.697878382893418,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004957530149043905,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.19260832369327546,
|
|
"num_tokens": 15373351.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.418985795974732,
|
|
"epoch": 0.698296024056131,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004957472561408438,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.1887256145477295,
|
|
"num_tokens": 15383069.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.3014484405517575,
|
|
"epoch": 0.6987136652188439,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004957414935128509,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.18785572946071624,
|
|
"num_tokens": 15391394.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.318035697937011,
|
|
"epoch": 0.699131306381557,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004957357270205123,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.1832756981253624,
|
|
"num_tokens": 15399993.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.291863489151001,
|
|
"epoch": 0.69954894754427,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004957299566639292,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.18668273985385894,
|
|
"num_tokens": 15409886.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.346201705932617,
|
|
"epoch": 0.6999665887069829,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004957241824432025,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.18907375484704972,
|
|
"num_tokens": 15419772.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.353672170639038,
|
|
"epoch": 0.700384229869696,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004957184043584333,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.1868671089410782,
|
|
"num_tokens": 15429631.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.304797792434693,
|
|
"epoch": 0.700801871032409,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004957126224097227,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.1953100398182869,
|
|
"num_tokens": 15438411.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.218867683410645,
|
|
"epoch": 0.7012195121951219,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000495706836597172,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.1908182442188263,
|
|
"num_tokens": 15448943.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.322815656661987,
|
|
"epoch": 0.7016371533578349,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004957010469208825,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.1907452329993248,
|
|
"num_tokens": 15457908.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.398818445205689,
|
|
"epoch": 0.702054794520548,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004956952533809554,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.18379063457250594,
|
|
"num_tokens": 15467390.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.355314254760742,
|
|
"epoch": 0.7024724356832609,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004956894559774923,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.185761496424675,
|
|
"num_tokens": 15476419.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.22340760231018,
|
|
"epoch": 0.7028900768459739,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004956836547105947,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.1945248782634735,
|
|
"num_tokens": 15485147.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.319608354568482,
|
|
"epoch": 0.703307718008687,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004956778495803641,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.18875861316919326,
|
|
"num_tokens": 15493816.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.342964315414429,
|
|
"epoch": 0.7037253591713999,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000495672040586902,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.1840755820274353,
|
|
"num_tokens": 15503051.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.316436672210694,
|
|
"epoch": 0.7041430003341129,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004956662277303103,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.19207129925489425,
|
|
"num_tokens": 15511854.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.30217661857605,
|
|
"epoch": 0.704560641496826,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004956604110106905,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.18537282645702363,
|
|
"num_tokens": 15521492.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.464894580841064,
|
|
"epoch": 0.7049782826595389,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004956545904281447,
|
|
"loss": 5.3147,
|
|
"mean_token_accuracy": 0.1746738463640213,
|
|
"num_tokens": 15530983.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.297878646850586,
|
|
"epoch": 0.7053959238222519,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004956487659827748,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.19397141933441162,
|
|
"num_tokens": 15539722.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.2263692855834964,
|
|
"epoch": 0.705813564984965,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004956429376746825,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.1891203999519348,
|
|
"num_tokens": 15548738.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.235093307495117,
|
|
"epoch": 0.7062312061476779,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004956371055039701,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.19618828296661378,
|
|
"num_tokens": 15557520.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.387892389297486,
|
|
"epoch": 0.7066488473103909,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004956312694707395,
|
|
"loss": 5.2469,
|
|
"mean_token_accuracy": 0.17590499818325042,
|
|
"num_tokens": 15567860.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.376634550094605,
|
|
"epoch": 0.7070664884731039,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000495625429575093,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.17584866136312485,
|
|
"num_tokens": 15577174.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.230661010742187,
|
|
"epoch": 0.7074841296358169,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004956195858171327,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.19701918065547944,
|
|
"num_tokens": 15585476.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.195006275177002,
|
|
"epoch": 0.7079017707985299,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004956137381969611,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.18857980370521546,
|
|
"num_tokens": 15595422.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.3309242725372314,
|
|
"epoch": 0.7083194119612429,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004956078867146805,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.18028816431760789,
|
|
"num_tokens": 15604223.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.39313907623291,
|
|
"epoch": 0.7087370531239559,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004956020313703933,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.18230718821287156,
|
|
"num_tokens": 15613715.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.282086181640625,
|
|
"epoch": 0.7091546942866689,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004955961721642018,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.19790386408567429,
|
|
"num_tokens": 15623826.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.3074768543243405,
|
|
"epoch": 0.7095723354493819,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000495590309096209,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.1797385260462761,
|
|
"num_tokens": 15633311.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.309714984893799,
|
|
"epoch": 0.7099899766120948,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004955844421665171,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.18832795321941376,
|
|
"num_tokens": 15642785.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.471587228775024,
|
|
"epoch": 0.7104076177748079,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004955785713752292,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.18039360791444778,
|
|
"num_tokens": 15653009.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.359288024902344,
|
|
"epoch": 0.7108252589375209,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004955726967224479,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.1898520588874817,
|
|
"num_tokens": 15661672.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.261266231536865,
|
|
"epoch": 0.7112429001002338,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000495566818208276,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.17999346405267716,
|
|
"num_tokens": 15672186.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.263257932662964,
|
|
"epoch": 0.7116605412629469,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004955609358328163,
|
|
"loss": 5.2018,
|
|
"mean_token_accuracy": 0.19061159789562226,
|
|
"num_tokens": 15680351.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.33342432975769,
|
|
"epoch": 0.7120781824256599,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004955550495961722,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.18149695098400115,
|
|
"num_tokens": 15690140.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.353526830673218,
|
|
"epoch": 0.7124958235883728,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004955491594984462,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.17878417074680328,
|
|
"num_tokens": 15699968.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.304271030426025,
|
|
"epoch": 0.7129134647510859,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004955432655397419,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.19037148207426072,
|
|
"num_tokens": 15709061.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.357570028305053,
|
|
"epoch": 0.7133311059137989,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004955373677201621,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.17969775050878525,
|
|
"num_tokens": 15718350.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.321164226531982,
|
|
"epoch": 0.7137487470765118,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004955314660398105,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.19132979661226274,
|
|
"num_tokens": 15727120.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.318919515609741,
|
|
"epoch": 0.7141663882392248,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004955255604987899,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.18388740569353104,
|
|
"num_tokens": 15735865.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.334926176071167,
|
|
"epoch": 0.7145840294019379,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000495519651097204,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.18114018738269805,
|
|
"num_tokens": 15745239.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.339488744735718,
|
|
"epoch": 0.7150016705646508,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004955137378351561,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.1935678794980049,
|
|
"num_tokens": 15754418.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.23320837020874,
|
|
"epoch": 0.7154193117273638,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004955078207127498,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.1880308657884598,
|
|
"num_tokens": 15764175.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.28746280670166,
|
|
"epoch": 0.7158369528900769,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004955018997300886,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.1876701757311821,
|
|
"num_tokens": 15772766.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.26781816482544,
|
|
"epoch": 0.7162545940527898,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004954959748872764,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.188557930290699,
|
|
"num_tokens": 15781768.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.360330533981323,
|
|
"epoch": 0.7166722352155028,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004954900461844167,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.18298709094524385,
|
|
"num_tokens": 15791706.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.3711076259613035,
|
|
"epoch": 0.7170898763782159,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004954841136216132,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.182969132065773,
|
|
"num_tokens": 15802015.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.390833330154419,
|
|
"epoch": 0.7175075175409288,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004954781771989701,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.18598561882972717,
|
|
"num_tokens": 15811116.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.370823907852173,
|
|
"epoch": 0.7179251587036418,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000495472236916591,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.18811384439468384,
|
|
"num_tokens": 15819240.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.246731090545654,
|
|
"epoch": 0.7183427998663549,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004954662927745799,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.1792804092168808,
|
|
"num_tokens": 15827740.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.252020025253296,
|
|
"epoch": 0.7187604410290678,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004954603447730411,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.1856865718960762,
|
|
"num_tokens": 15836763.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.484684085845947,
|
|
"epoch": 0.7191780821917808,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004954543929120786,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.18425522446632386,
|
|
"num_tokens": 15846624.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.3179261684417725,
|
|
"epoch": 0.7195957233544938,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004954484371917967,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.18258151710033416,
|
|
"num_tokens": 15855713.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.25519208908081,
|
|
"epoch": 0.7200133645172068,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004954424776122993,
|
|
"loss": 5.0484,
|
|
"mean_token_accuracy": 0.1937964841723442,
|
|
"num_tokens": 15863577.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.310612058639526,
|
|
"epoch": 0.7204310056799198,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004954365141736913,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.18976670354604722,
|
|
"num_tokens": 15872479.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.366736268997192,
|
|
"epoch": 0.7208486468426328,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004954305468760765,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.18595676273107528,
|
|
"num_tokens": 15882170.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.297217178344726,
|
|
"epoch": 0.7212662880053458,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004954245757195598,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.19112035632133484,
|
|
"num_tokens": 15891694.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.342066907882691,
|
|
"epoch": 0.7216839291680588,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004954186007042454,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.1751521810889244,
|
|
"num_tokens": 15902232.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.355078458786011,
|
|
"epoch": 0.7221015703307718,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004954126218302382,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.1850830689072609,
|
|
"num_tokens": 15912218.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.295679426193237,
|
|
"epoch": 0.7225192114934847,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004954066390976427,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.1954933747649193,
|
|
"num_tokens": 15922011.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.214598512649536,
|
|
"epoch": 0.7229368526561978,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004954006525065639,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.18943319767713546,
|
|
"num_tokens": 15930394.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.2756795406341555,
|
|
"epoch": 0.7233544938189108,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004953946620571061,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.1842021256685257,
|
|
"num_tokens": 15939880.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.294782829284668,
|
|
"epoch": 0.7237721349816237,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004953886677493746,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.19848918318748474,
|
|
"num_tokens": 15948521.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.2965775489807125,
|
|
"epoch": 0.7241897761443368,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004953826695834741,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.18476293385028839,
|
|
"num_tokens": 15956811.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.289892244338989,
|
|
"epoch": 0.7246074173070498,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004953766675595098,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.18657170236110687,
|
|
"num_tokens": 15967019.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.426598834991455,
|
|
"epoch": 0.7250250584697627,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004953706616775866,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.18381640315055847,
|
|
"num_tokens": 15976149.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.339119338989258,
|
|
"epoch": 0.7254426996324758,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004953646519378097,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.1894015073776245,
|
|
"num_tokens": 15986711.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.259220027923584,
|
|
"epoch": 0.7258603407951888,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004953586383402844,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.18817801922559738,
|
|
"num_tokens": 15996482.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.132692193984985,
|
|
"epoch": 0.7262779819579017,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004953526208851157,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.18728736639022828,
|
|
"num_tokens": 16005801.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.223638677597046,
|
|
"epoch": 0.7266956231206148,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004953465995724092,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.18736834675073624,
|
|
"num_tokens": 16014807.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.381020355224609,
|
|
"epoch": 0.7271132642833278,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004953405744022705,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.18292548656463622,
|
|
"num_tokens": 16023326.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.430472993850708,
|
|
"epoch": 0.7275309054460407,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004953345453748045,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.18610840290784836,
|
|
"num_tokens": 16031648.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.307134485244751,
|
|
"epoch": 0.7279485466087537,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004953285124901171,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.19232644140720367,
|
|
"num_tokens": 16040179.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.301759386062622,
|
|
"epoch": 0.7283661877714668,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000495322475748314,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.17622517049312592,
|
|
"num_tokens": 16050770.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.340561103820801,
|
|
"epoch": 0.7287838289341797,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004953164351495007,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.18876151144504547,
|
|
"num_tokens": 16060504.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.281233406066894,
|
|
"epoch": 0.7292014700968927,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004953103906937831,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.20289447158575058,
|
|
"num_tokens": 16069240.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.201758241653442,
|
|
"epoch": 0.7296191112596058,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004953043423812669,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.18410247266292573,
|
|
"num_tokens": 16079098.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.213766145706177,
|
|
"epoch": 0.7300367524223187,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004952982902120579,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.19202603101730348,
|
|
"num_tokens": 16088454.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.362329149246216,
|
|
"epoch": 0.7304543935850317,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004952922341862622,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.18529306799173356,
|
|
"num_tokens": 16096985.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.428350830078125,
|
|
"epoch": 0.7308720347477448,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004952861743039858,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.1782863602042198,
|
|
"num_tokens": 16105434.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.224010896682739,
|
|
"epoch": 0.7312896759104577,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004952801105653347,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.1973409339785576,
|
|
"num_tokens": 16114933.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.372373008728028,
|
|
"epoch": 0.7317073170731707,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004952740429704152,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.18186335861682892,
|
|
"num_tokens": 16124954.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.326339387893677,
|
|
"epoch": 0.7321249582358837,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004952679715193334,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.19299455881118774,
|
|
"num_tokens": 16134442.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.337293004989624,
|
|
"epoch": 0.7325425993985967,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004952618962121956,
|
|
"loss": 5.2484,
|
|
"mean_token_accuracy": 0.18174122124910355,
|
|
"num_tokens": 16143994.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.2761390209198,
|
|
"epoch": 0.7329602405613097,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004952558170491082,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.18572575896978377,
|
|
"num_tokens": 16152931.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.270718765258789,
|
|
"epoch": 0.7333778817240227,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004952497340301776,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.18109920769929885,
|
|
"num_tokens": 16162716.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.346599483489991,
|
|
"epoch": 0.7337955228867357,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004952436471555103,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.18129942566156387,
|
|
"num_tokens": 16172371.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.311984920501709,
|
|
"epoch": 0.7342131640494487,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004952375564252128,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.18387712836265563,
|
|
"num_tokens": 16181823.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.302162504196167,
|
|
"epoch": 0.7346308052121617,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004952314618393919,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.18727488070726395,
|
|
"num_tokens": 16190720.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.323683071136474,
|
|
"epoch": 0.7350484463748747,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000495225363398154,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.18795779943466187,
|
|
"num_tokens": 16199589.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.39074182510376,
|
|
"epoch": 0.7354660875375877,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004952192611016061,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.18400349467992783,
|
|
"num_tokens": 16208800.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.388135766983032,
|
|
"epoch": 0.7358837287003007,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000495213154949855,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18048720359802245,
|
|
"num_tokens": 16218835.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.376900386810303,
|
|
"epoch": 0.7363013698630136,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004952070449430075,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.1812291622161865,
|
|
"num_tokens": 16228441.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.403039264678955,
|
|
"epoch": 0.7367190110257267,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004952009310811706,
|
|
"loss": 5.2191,
|
|
"mean_token_accuracy": 0.19410694092512132,
|
|
"num_tokens": 16237877.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.265282154083252,
|
|
"epoch": 0.7371366521884397,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004951948133644514,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.19013114124536515,
|
|
"num_tokens": 16246809.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.3557374477386475,
|
|
"epoch": 0.7375542933511526,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000495188691792957,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.19548689126968383,
|
|
"num_tokens": 16255754.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.33818097114563,
|
|
"epoch": 0.7379719345138657,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004951825663667943,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.1831888809800148,
|
|
"num_tokens": 16264861.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.298843860626221,
|
|
"epoch": 0.7383895756765787,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000495176437086071,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.1878280982375145,
|
|
"num_tokens": 16273628.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.345774793624878,
|
|
"epoch": 0.7388072168392917,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000495170303950894,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.1875653460621834,
|
|
"num_tokens": 16282958.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.316007518768311,
|
|
"epoch": 0.7392248580020047,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004951641669613708,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.18460226953029632,
|
|
"num_tokens": 16292763.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.329687404632568,
|
|
"epoch": 0.7396424991647177,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004951580261176088,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19027262479066848,
|
|
"num_tokens": 16302216.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.23100438117981,
|
|
"epoch": 0.7400601403274307,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004951518814197156,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.19242411851882935,
|
|
"num_tokens": 16311672.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.275502109527588,
|
|
"epoch": 0.7404777814901436,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004951457328677989,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.18861838132143022,
|
|
"num_tokens": 16321027.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.375608444213867,
|
|
"epoch": 0.7408954226528567,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004951395804619659,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.18391497284173966,
|
|
"num_tokens": 16329471.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.309133386611938,
|
|
"epoch": 0.7413130638155697,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004951334242023247,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.18458560705184937,
|
|
"num_tokens": 16339085.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.363067388534546,
|
|
"epoch": 0.7417307049782826,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004951272640889828,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.19278847724199294,
|
|
"num_tokens": 16347950.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.304359006881714,
|
|
"epoch": 0.7421483461409957,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004951211001220484,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.1945688992738724,
|
|
"num_tokens": 16357129.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.282190561294556,
|
|
"epoch": 0.7425659873037087,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000495114932301629,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.18669179528951646,
|
|
"num_tokens": 16365768.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.2501928329467775,
|
|
"epoch": 0.7429836284664216,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004951087606278328,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.1911521926522255,
|
|
"num_tokens": 16375548.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.325199222564697,
|
|
"epoch": 0.7434012696291347,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004951025851007678,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.19053663462400436,
|
|
"num_tokens": 16385472.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.321870899200439,
|
|
"epoch": 0.7438189107918477,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004950964057205421,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.18921963274478912,
|
|
"num_tokens": 16395048.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.388301944732666,
|
|
"epoch": 0.7442365519545606,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000495090222487264,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.1784229427576065,
|
|
"num_tokens": 16405378.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.316306924819946,
|
|
"epoch": 0.7446541931172737,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004950840354010415,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.19073249250650406,
|
|
"num_tokens": 16415206.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.375656604766846,
|
|
"epoch": 0.7450718342799867,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004950778444619831,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.19712818264961243,
|
|
"num_tokens": 16424185.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.329453420639038,
|
|
"epoch": 0.7454894754426996,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000495071649670197,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.1838183030486107,
|
|
"num_tokens": 16433330.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.271111345291137,
|
|
"epoch": 0.7459071166054126,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000495065451025792,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.1852631837129593,
|
|
"num_tokens": 16442777.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.310748481750489,
|
|
"epoch": 0.7463247577681257,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004950592485288761,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.19424661993980408,
|
|
"num_tokens": 16451838.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.314354085922242,
|
|
"epoch": 0.7467423989308386,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004950530421795584,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.19498806148767472,
|
|
"num_tokens": 16460022.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.21478157043457,
|
|
"epoch": 0.7471600400935516,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004950468319779472,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.19858380109071733,
|
|
"num_tokens": 16468891.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.1760947704315186,
|
|
"epoch": 0.7475776812562647,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004950406179241515,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.20099257677793503,
|
|
"num_tokens": 16478020.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.3247462749481205,
|
|
"epoch": 0.7479953224189776,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004950344000182798,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.185774627327919,
|
|
"num_tokens": 16487536.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.343104982376099,
|
|
"epoch": 0.7484129635816906,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004950281782604411,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.17981323897838591,
|
|
"num_tokens": 16495786.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.380094528198242,
|
|
"epoch": 0.7488306047444037,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004950219526507442,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.1816750258207321,
|
|
"num_tokens": 16505535.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.417230463027954,
|
|
"epoch": 0.7492482459071166,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004950157231892983,
|
|
"loss": 5.2806,
|
|
"mean_token_accuracy": 0.18207372725009918,
|
|
"num_tokens": 16515387.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.290445327758789,
|
|
"epoch": 0.7496658870698296,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004950094898762123,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.18433275073766708,
|
|
"num_tokens": 16524421.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.390057373046875,
|
|
"epoch": 0.7500835282325427,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004950032527115954,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.18798471987247467,
|
|
"num_tokens": 16534533.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.400622415542602,
|
|
"epoch": 0.7505011693952556,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004949970116955566,
|
|
"loss": 5.2418,
|
|
"mean_token_accuracy": 0.17809109389781952,
|
|
"num_tokens": 16543712.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.364700078964233,
|
|
"epoch": 0.7509188105579686,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004949907668282054,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.1881457805633545,
|
|
"num_tokens": 16552475.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.34286322593689,
|
|
"epoch": 0.7513364517206816,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000494984518109651,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.18579161614179612,
|
|
"num_tokens": 16562237.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.346833086013794,
|
|
"epoch": 0.7517540928833946,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004949782655400028,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.19135233908891677,
|
|
"num_tokens": 16570508.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7517540928833946,
|
|
"eval_entropy": 5.133677991005708,
|
|
"eval_loss": 5.168975830078125,
|
|
"eval_mean_token_accuracy": 0.19775329205923428,
|
|
"eval_num_tokens": 16570508.0,
|
|
"eval_runtime": 27.3441,
|
|
"eval_samples_per_second": 1381.027,
|
|
"eval_steps_per_second": 172.651,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.272634363174438,
|
|
"epoch": 0.7521717340461076,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004949720091193704,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.19876011908054353,
|
|
"num_tokens": 16578561.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.300364828109741,
|
|
"epoch": 0.7525893752088206,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000494965748847863,
|
|
"loss": 5.0734,
|
|
"mean_token_accuracy": 0.19513107985258102,
|
|
"num_tokens": 16587168.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.328412818908691,
|
|
"epoch": 0.7530070163715336,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004949594847255905,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.18871351927518845,
|
|
"num_tokens": 16597252.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.2942945003509525,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004949532167526625,
|
|
"loss": 5.0876,
|
|
"mean_token_accuracy": 0.19655826091766357,
|
|
"num_tokens": 16607558.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.419779872894287,
|
|
"epoch": 0.7538422986969596,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004949469449291886,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.1777003213763237,
|
|
"num_tokens": 16617019.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.312467765808106,
|
|
"epoch": 0.7542599398596725,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004949406692552787,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.1900804117321968,
|
|
"num_tokens": 16625815.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.358976984024048,
|
|
"epoch": 0.7546775810223856,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004949343897310426,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.17723113745450975,
|
|
"num_tokens": 16634876.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.319064283370972,
|
|
"epoch": 0.7550952221850986,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004949281063565904,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.18531542420387268,
|
|
"num_tokens": 16643770.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.3930223941802975,
|
|
"epoch": 0.7555128633478115,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004949218191320319,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.18985310196876526,
|
|
"num_tokens": 16652845.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.336880540847778,
|
|
"epoch": 0.7559305045105246,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004949155280574772,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.1917647212743759,
|
|
"num_tokens": 16662224.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.3161591529846195,
|
|
"epoch": 0.7563481456732376,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004949092331330365,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.18797622621059418,
|
|
"num_tokens": 16671114.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.347621059417724,
|
|
"epoch": 0.7567657868359505,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00049490293435882,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.1742393746972084,
|
|
"num_tokens": 16680395.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.377555990219117,
|
|
"epoch": 0.7571834279986636,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004948966317349379,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.19361136853694916,
|
|
"num_tokens": 16690251.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.27882399559021,
|
|
"epoch": 0.7576010691613766,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004948903252615006,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.2000073954463005,
|
|
"num_tokens": 16698945.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.349974203109741,
|
|
"epoch": 0.7580187103240895,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004948840149386184,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.18208573907613754,
|
|
"num_tokens": 16708325.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.315873098373413,
|
|
"epoch": 0.7584363514868026,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000494877700766402,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.1909972459077835,
|
|
"num_tokens": 16716392.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.320262050628662,
|
|
"epoch": 0.7588539926495156,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004948713827449616,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.18527687340974808,
|
|
"num_tokens": 16725284.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.2729230403900145,
|
|
"epoch": 0.7592716338122285,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004948650608744081,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.1946970194578171,
|
|
"num_tokens": 16734658.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.419935989379883,
|
|
"epoch": 0.7596892749749415,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000494858735154852,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.1810906082391739,
|
|
"num_tokens": 16744403.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.41253628730774,
|
|
"epoch": 0.7601069161376546,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004948524055864041,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.18740759789943695,
|
|
"num_tokens": 16754254.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.3168446063995365,
|
|
"epoch": 0.7605245573003675,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004948460721691752,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.18386004269123077,
|
|
"num_tokens": 16763941.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.364061737060547,
|
|
"epoch": 0.7609421984630805,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004948397349032762,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.1827145352959633,
|
|
"num_tokens": 16773181.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.2379027843475345,
|
|
"epoch": 0.7613598396257936,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000494833393788818,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.1977047637104988,
|
|
"num_tokens": 16782622.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.358839702606201,
|
|
"epoch": 0.7617774807885065,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004948270488259117,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.1830137401819229,
|
|
"num_tokens": 16792805.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.32723560333252,
|
|
"epoch": 0.7621951219512195,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004948207000146682,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.18766830265522003,
|
|
"num_tokens": 16802641.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.391316843032837,
|
|
"epoch": 0.7626127631139326,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004948143473551989,
|
|
"loss": 5.2224,
|
|
"mean_token_accuracy": 0.1805815115571022,
|
|
"num_tokens": 16812037.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.2934071063995365,
|
|
"epoch": 0.7630304042766455,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004948079908476147,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.19688214212656022,
|
|
"num_tokens": 16820279.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.285008192062378,
|
|
"epoch": 0.7634480454393585,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004948016304920271,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.18657118529081346,
|
|
"num_tokens": 16829396.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.311561822891235,
|
|
"epoch": 0.7638656866020715,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004947952662885473,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.194387049973011,
|
|
"num_tokens": 16838389.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.374364137649536,
|
|
"epoch": 0.7642833277647845,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000494788898237287,
|
|
"loss": 5.2669,
|
|
"mean_token_accuracy": 0.18704009801149368,
|
|
"num_tokens": 16848012.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.387968873977661,
|
|
"epoch": 0.7647009689274975,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004947825263383573,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.18611233234405516,
|
|
"num_tokens": 16857591.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.392985248565674,
|
|
"epoch": 0.7651186100902105,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00049477615059187,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.17910126298666001,
|
|
"num_tokens": 16866792.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.325544166564941,
|
|
"epoch": 0.7655362512529235,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004947697709979367,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.18787939697504044,
|
|
"num_tokens": 16876602.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.3107171058654785,
|
|
"epoch": 0.7659538924156365,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004947633875566688,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.18358664959669113,
|
|
"num_tokens": 16886992.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.3244751453399655,
|
|
"epoch": 0.7663715335783495,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004947570002681785,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.1884155884385109,
|
|
"num_tokens": 16895716.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.3303642749786375,
|
|
"epoch": 0.7667891747410625,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004947506091325772,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.19776746332645417,
|
|
"num_tokens": 16904568.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.410282278060913,
|
|
"epoch": 0.7672068159037755,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004947442141499771,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.18748794198036195,
|
|
"num_tokens": 16913667.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.33154182434082,
|
|
"epoch": 0.7676244570664885,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004947378153204899,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.18723595887422562,
|
|
"num_tokens": 16922897.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.321815347671508,
|
|
"epoch": 0.7680420982292014,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004947314126442279,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.18120656311511993,
|
|
"num_tokens": 16931559.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.326811933517456,
|
|
"epoch": 0.7684597393919145,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000494725006121303,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.1848924219608307,
|
|
"num_tokens": 16940191.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.371112871170044,
|
|
"epoch": 0.7688773805546275,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004947185957518273,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.18787964135408403,
|
|
"num_tokens": 16948971.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.376923370361328,
|
|
"epoch": 0.7692950217173404,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004947121815359133,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.19100566506385802,
|
|
"num_tokens": 16957944.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.32720103263855,
|
|
"epoch": 0.7697126628800535,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004947057634736729,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.18390686362981795,
|
|
"num_tokens": 16967418.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.265461206436157,
|
|
"epoch": 0.7701303040427665,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004946993415652186,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.1907045751810074,
|
|
"num_tokens": 16977233.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.309878253936768,
|
|
"epoch": 0.7705479452054794,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000494692915810663,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.1941950038075447,
|
|
"num_tokens": 16986023.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.371839141845703,
|
|
"epoch": 0.7709655863681925,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004946864862101185,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.18917000889778138,
|
|
"num_tokens": 16994987.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.297115755081177,
|
|
"epoch": 0.7713832275309055,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004946800527636975,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.18845341652631759,
|
|
"num_tokens": 17003902.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.363648509979248,
|
|
"epoch": 0.7718008686936184,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004946736154715129,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.18313714861869812,
|
|
"num_tokens": 17013258.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.406899166107178,
|
|
"epoch": 0.7722185098563314,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004946671743336771,
|
|
"loss": 5.2462,
|
|
"mean_token_accuracy": 0.1832134172320366,
|
|
"num_tokens": 17022258.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.3464460372924805,
|
|
"epoch": 0.7726361510190445,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004946607293503031,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.18468582928180693,
|
|
"num_tokens": 17031485.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.22146167755127,
|
|
"epoch": 0.7730537921817574,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004946542805215036,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.19387171864509584,
|
|
"num_tokens": 17039916.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.280299949645996,
|
|
"epoch": 0.7734714333444704,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004946478278473914,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.1912824898958206,
|
|
"num_tokens": 17048153.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.310075855255127,
|
|
"epoch": 0.7738890745071835,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004946413713280797,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.18531114161014556,
|
|
"num_tokens": 17057473.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.363498067855835,
|
|
"epoch": 0.7743067156698964,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004946349109636814,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.1903122827410698,
|
|
"num_tokens": 17066431.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.39309287071228,
|
|
"epoch": 0.7747243568326094,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004946284467543096,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.1767013356089592,
|
|
"num_tokens": 17076519.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.35628457069397,
|
|
"epoch": 0.7751419979953225,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004946219787000776,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.18584041744470597,
|
|
"num_tokens": 17084651.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.425425672531128,
|
|
"epoch": 0.7755596391580354,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004946155068010984,
|
|
"loss": 5.2682,
|
|
"mean_token_accuracy": 0.1853787124156952,
|
|
"num_tokens": 17094943.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.2977934837341305,
|
|
"epoch": 0.7759772803207484,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004946090310574854,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.19857468008995055,
|
|
"num_tokens": 17103548.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.27626314163208,
|
|
"epoch": 0.7763949214834615,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004946025514693519,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.18831444829702376,
|
|
"num_tokens": 17112472.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.424504995346069,
|
|
"epoch": 0.7768125626461744,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004945960680368115,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.1821184054017067,
|
|
"num_tokens": 17121536.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.452235221862793,
|
|
"epoch": 0.7772302038088874,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004945895807599775,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.1766143783926964,
|
|
"num_tokens": 17130708.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.259407567977905,
|
|
"epoch": 0.7776478449716004,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004945830896389636,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.19628924280405044,
|
|
"num_tokens": 17139437.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.295243883132935,
|
|
"epoch": 0.7780654861343134,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004945765946738835,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.18049858659505844,
|
|
"num_tokens": 17149107.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.3829522132873535,
|
|
"epoch": 0.7784831272970264,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004945700958648507,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.18175995647907256,
|
|
"num_tokens": 17158866.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.346366882324219,
|
|
"epoch": 0.7789007684597394,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000494563593211979,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.19358669072389603,
|
|
"num_tokens": 17167909.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.34268593788147,
|
|
"epoch": 0.7793184096224524,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004945570867153826,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.1824558898806572,
|
|
"num_tokens": 17176746.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.31865668296814,
|
|
"epoch": 0.7797360507851654,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004945505763751749,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.1797788992524147,
|
|
"num_tokens": 17186219.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.359292221069336,
|
|
"epoch": 0.7801536919478784,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004945440621914702,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.19835327565670013,
|
|
"num_tokens": 17195811.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.29733943939209,
|
|
"epoch": 0.7805713331105913,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004945375441643823,
|
|
"loss": 5.237,
|
|
"mean_token_accuracy": 0.18875968903303147,
|
|
"num_tokens": 17205333.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.36309585571289,
|
|
"epoch": 0.7809889742733044,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004945310222940254,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.18497316241264344,
|
|
"num_tokens": 17214493.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.447697019577026,
|
|
"epoch": 0.7814066154360174,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004945244965805138,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.18682510107755662,
|
|
"num_tokens": 17223602.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.441306400299072,
|
|
"epoch": 0.7818242565987303,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004945179670239616,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.17852559983730315,
|
|
"num_tokens": 17232915.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.338666677474976,
|
|
"epoch": 0.7822418977614434,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004945114336244832,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.18359384685754776,
|
|
"num_tokens": 17242489.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.22138524055481,
|
|
"epoch": 0.7826595389241564,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000494504896382193,
|
|
"loss": 4.9625,
|
|
"mean_token_accuracy": 0.1995940700173378,
|
|
"num_tokens": 17251496.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.272387266159058,
|
|
"epoch": 0.7830771800868693,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004944983552972053,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.19191693365573884,
|
|
"num_tokens": 17260550.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.31194658279419,
|
|
"epoch": 0.7834948212495824,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004944918103696347,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.19449665546417236,
|
|
"num_tokens": 17269085.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.404148912429809,
|
|
"epoch": 0.7839124624122954,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004944852615995956,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.18360071033239364,
|
|
"num_tokens": 17278766.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.463492679595947,
|
|
"epoch": 0.7843301035750083,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000494478708987203,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.18161397576332092,
|
|
"num_tokens": 17288316.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.2378357410430905,
|
|
"epoch": 0.7847477447377214,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004944721525325713,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.18655068576335906,
|
|
"num_tokens": 17297829.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.304569292068481,
|
|
"epoch": 0.7851653859004344,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004944655922358154,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.18702153265476226,
|
|
"num_tokens": 17306631.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.32991132736206,
|
|
"epoch": 0.7855830270631473,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004944590280970503,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.19350167214870453,
|
|
"num_tokens": 17316829.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.319064426422119,
|
|
"epoch": 0.7860006682258603,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004944524601163905,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.18373969346284866,
|
|
"num_tokens": 17326568.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.375158071517944,
|
|
"epoch": 0.7864183093885734,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004944458882939513,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.1819099396467209,
|
|
"num_tokens": 17335524.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.443592643737793,
|
|
"epoch": 0.7868359505512863,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004944393126298478,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.18035196363925934,
|
|
"num_tokens": 17346198.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.311717510223389,
|
|
"epoch": 0.7872535917139993,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000494432733124195,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.18798684179782868,
|
|
"num_tokens": 17354696.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.210242652893067,
|
|
"epoch": 0.7876712328767124,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000494426149777108,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.1907953992486,
|
|
"num_tokens": 17363314.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.270390796661377,
|
|
"epoch": 0.7880888740394253,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000494419562588702,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.19028382301330565,
|
|
"num_tokens": 17372662.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.316920042037964,
|
|
"epoch": 0.7885065152021383,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004944129715590927,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.1886994644999504,
|
|
"num_tokens": 17381931.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.3894792079925535,
|
|
"epoch": 0.7889241563648514,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000494406376688395,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.18322570770978927,
|
|
"num_tokens": 17391210.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.243765878677368,
|
|
"epoch": 0.7893417975275643,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004943997779767248,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.19628691226243972,
|
|
"num_tokens": 17401102.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.261760663986206,
|
|
"epoch": 0.7897594386902773,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004943931754241972,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.1869055986404419,
|
|
"num_tokens": 17410036.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.318477916717529,
|
|
"epoch": 0.7901770798529903,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000494386569030928,
|
|
"loss": 5.1692,
|
|
"mean_token_accuracy": 0.18524761795997619,
|
|
"num_tokens": 17419348.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.360423946380616,
|
|
"epoch": 0.7905947210157033,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004943799587970328,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.1848449930548668,
|
|
"num_tokens": 17427937.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.277559375762939,
|
|
"epoch": 0.7910123621784163,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004943733447226275,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.19531989693641663,
|
|
"num_tokens": 17436259.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.35192346572876,
|
|
"epoch": 0.7914300033411293,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004943667268078277,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.18139349669218063,
|
|
"num_tokens": 17445202.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.317629814147949,
|
|
"epoch": 0.7918476445038423,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004943601050527493,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.19007206559181214,
|
|
"num_tokens": 17453928.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.3239970207214355,
|
|
"epoch": 0.7922652856665553,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004943534794575081,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.1924855336546898,
|
|
"num_tokens": 17462609.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.336129665374756,
|
|
"epoch": 0.7926829268292683,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004943468500222203,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.18830626904964448,
|
|
"num_tokens": 17471326.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.284777736663818,
|
|
"epoch": 0.7931005679919813,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004943402167470019,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.19210643768310548,
|
|
"num_tokens": 17480296.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.250183916091919,
|
|
"epoch": 0.7935182091546943,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000494333579631969,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.1895009309053421,
|
|
"num_tokens": 17489779.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.308423089981079,
|
|
"epoch": 0.7939358503174073,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004943269386772376,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.18017989993095399,
|
|
"num_tokens": 17499796.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.392049121856689,
|
|
"epoch": 0.7943534914801202,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004943202938829243,
|
|
"loss": 5.287,
|
|
"mean_token_accuracy": 0.18167537897825242,
|
|
"num_tokens": 17509223.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.340440464019776,
|
|
"epoch": 0.7947711326428333,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004943136452491452,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.18735254257917405,
|
|
"num_tokens": 17518712.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.278647708892822,
|
|
"epoch": 0.7951887738055463,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004943069927760168,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.19221056997776031,
|
|
"num_tokens": 17528648.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.215114593505859,
|
|
"epoch": 0.7956064149682592,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004943003364636554,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.18678269982337953,
|
|
"num_tokens": 17537859.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.372722578048706,
|
|
"epoch": 0.7960240561309723,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004942936763121777,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.18087439835071564,
|
|
"num_tokens": 17546438.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.311570692062378,
|
|
"epoch": 0.7964416972936853,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004942870123217002,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.19542259871959686,
|
|
"num_tokens": 17554537.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.428062295913696,
|
|
"epoch": 0.7968593384563982,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004942803444923398,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.17997895628213884,
|
|
"num_tokens": 17564239.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.310004758834839,
|
|
"epoch": 0.7972769796191113,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004942736728242127,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.18477356284856797,
|
|
"num_tokens": 17574437.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.249059724807739,
|
|
"epoch": 0.7976946207818243,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004942669973174363,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.18902096301317214,
|
|
"num_tokens": 17583173.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.3453527927398685,
|
|
"epoch": 0.7981122619445372,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000494260317972127,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.1859835907816887,
|
|
"num_tokens": 17591731.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.38207745552063,
|
|
"epoch": 0.7985299031072502,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004942536347884019,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.18607254177331925,
|
|
"num_tokens": 17600778.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.273932456970215,
|
|
"epoch": 0.7989475442699633,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004942469477663782,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.2019364818930626,
|
|
"num_tokens": 17609470.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.2391273975372314,
|
|
"epoch": 0.7993651854326762,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004942402569061726,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.19261219650506972,
|
|
"num_tokens": 17618434.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.2402228832244875,
|
|
"epoch": 0.7997828265953892,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004942335622079025,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.1846891924738884,
|
|
"num_tokens": 17628170.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.277979469299316,
|
|
"epoch": 0.8002004677581023,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004942268636716848,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.18975522816181184,
|
|
"num_tokens": 17637391.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.34949049949646,
|
|
"epoch": 0.8006181089208152,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004942201612976372,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.19083760529756547,
|
|
"num_tokens": 17647466.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.313105869293213,
|
|
"epoch": 0.8010357500835282,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004942134550858767,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.19590833485126496,
|
|
"num_tokens": 17656155.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.417249298095703,
|
|
"epoch": 0.8014533912462413,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004942067450365208,
|
|
"loss": 5.2324,
|
|
"mean_token_accuracy": 0.18625636547803878,
|
|
"num_tokens": 17665242.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.3511634349823,
|
|
"epoch": 0.8018710324089542,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004942000311496871,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.18960424214601518,
|
|
"num_tokens": 17674964.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.402841711044312,
|
|
"epoch": 0.8022886735716672,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004941933134254928,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.1859276622533798,
|
|
"num_tokens": 17683275.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.266304683685303,
|
|
"epoch": 0.8027063147343803,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004941865918640559,
|
|
"loss": 5.1913,
|
|
"mean_token_accuracy": 0.18445036709308624,
|
|
"num_tokens": 17691841.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.318730354309082,
|
|
"epoch": 0.8031239558970932,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004941798664654937,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.19045049995183944,
|
|
"num_tokens": 17701258.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.415330648422241,
|
|
"epoch": 0.8035415970598062,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004941731372299241,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.1848721519112587,
|
|
"num_tokens": 17711028.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.370194816589356,
|
|
"epoch": 0.8039592382225192,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004941664041574651,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.2002640411257744,
|
|
"num_tokens": 17720175.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.322130966186523,
|
|
"epoch": 0.8043768793852322,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004941596672482343,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.18256354182958603,
|
|
"num_tokens": 17730420.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.32376012802124,
|
|
"epoch": 0.8047945205479452,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004941529265023498,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.1815265953540802,
|
|
"num_tokens": 17739802.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.34448390007019,
|
|
"epoch": 0.8052121617106582,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004941461819199293,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.192313115298748,
|
|
"num_tokens": 17749450.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.457966899871826,
|
|
"epoch": 0.8056298028733712,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004941394335010912,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.1806011214852333,
|
|
"num_tokens": 17758733.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.298712062835693,
|
|
"epoch": 0.8060474440360842,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004941326812459535,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.18545981049537658,
|
|
"num_tokens": 17769037.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.266812705993653,
|
|
"epoch": 0.8064650851987972,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004941259251546346,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.17927865833044052,
|
|
"num_tokens": 17777603.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.304557132720947,
|
|
"epoch": 0.8068827263615101,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004941191652272526,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.1796041786670685,
|
|
"num_tokens": 17787513.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.31368932723999,
|
|
"epoch": 0.8073003675242232,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004941124014639258,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.19038289189338684,
|
|
"num_tokens": 17796720.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.333065700531006,
|
|
"epoch": 0.8077180086869362,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004941056338647726,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.19311497509479522,
|
|
"num_tokens": 17806024.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.235565567016602,
|
|
"epoch": 0.8081356498496491,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004940988624299116,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.18659957349300385,
|
|
"num_tokens": 17815247.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.419852590560913,
|
|
"epoch": 0.8085532910123622,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004940920871594613,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.18847472071647645,
|
|
"num_tokens": 17824024.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.292865324020386,
|
|
"epoch": 0.8089709321750752,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004940853080535403,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.18051009625196457,
|
|
"num_tokens": 17832782.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.228757667541504,
|
|
"epoch": 0.8093885733377881,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004940785251122673,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.1954245463013649,
|
|
"num_tokens": 17841961.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.27298641204834,
|
|
"epoch": 0.8098062145005012,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004940717383357608,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.19371180683374406,
|
|
"num_tokens": 17851364.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.415110397338867,
|
|
"epoch": 0.8102238556632142,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004940649477241401,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.18041903972625734,
|
|
"num_tokens": 17860871.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.341606140136719,
|
|
"epoch": 0.8106414968259271,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004940581532775237,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.18526162207126617,
|
|
"num_tokens": 17869687.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.299842596054077,
|
|
"epoch": 0.8110591379886402,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004940513549960306,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.1847122862935066,
|
|
"num_tokens": 17878815.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.254646492004395,
|
|
"epoch": 0.8114767791513532,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004940445528797798,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.190871062874794,
|
|
"num_tokens": 17888302.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.218020725250244,
|
|
"epoch": 0.8118944203140661,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004940377469288906,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.19915541261434555,
|
|
"num_tokens": 17896807.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.281565999984741,
|
|
"epoch": 0.8123120614767791,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004940309371434819,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.19083558171987533,
|
|
"num_tokens": 17905988.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.387138223648071,
|
|
"epoch": 0.8127297026394922,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004940241235236731,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.18090667426586152,
|
|
"num_tokens": 17915917.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.409555864334107,
|
|
"epoch": 0.8131473438022051,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004940173060695833,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.1853630855679512,
|
|
"num_tokens": 17926158.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.284359407424927,
|
|
"epoch": 0.8135649849649181,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004940104847813319,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.18690650314092636,
|
|
"num_tokens": 17935488.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.35828652381897,
|
|
"epoch": 0.8139826261276312,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004940036596590384,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.18699391931295395,
|
|
"num_tokens": 17944850.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.310150384902954,
|
|
"epoch": 0.8144002672903441,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004939968307028221,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.19170355647802353,
|
|
"num_tokens": 17954796.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.236877679824829,
|
|
"epoch": 0.8148179084530571,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004939899979128028,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.19769725501537322,
|
|
"num_tokens": 17963875.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.264697742462158,
|
|
"epoch": 0.8152355496157702,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004939831612890999,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.18781137466430664,
|
|
"num_tokens": 17972789.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.26484956741333,
|
|
"epoch": 0.8156531907784831,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004939763208318332,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.1855485737323761,
|
|
"num_tokens": 17982355.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.362791919708252,
|
|
"epoch": 0.8160708319411961,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004939694765411225,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.1848495841026306,
|
|
"num_tokens": 17992046.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.287937593460083,
|
|
"epoch": 0.8164884731039092,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004939626284170874,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.19881495088338852,
|
|
"num_tokens": 18001440.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.4196573257446286,
|
|
"epoch": 0.8169061142666221,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000493955776459848,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.17994987219572067,
|
|
"num_tokens": 18010817.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.3791358947753904,
|
|
"epoch": 0.8173237554293351,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004939489206695241,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.18664075583219528,
|
|
"num_tokens": 18019547.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.309901094436645,
|
|
"epoch": 0.8177413965920481,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004939420610462359,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.1869453087449074,
|
|
"num_tokens": 18029191.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.341063547134399,
|
|
"epoch": 0.8181590377547611,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004939351975901034,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.1871086061000824,
|
|
"num_tokens": 18038831.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.357484006881714,
|
|
"epoch": 0.8185766789174741,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004939283303012467,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.19173508286476135,
|
|
"num_tokens": 18049243.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.23955454826355,
|
|
"epoch": 0.8189943200801871,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000493921459179786,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.1906172439455986,
|
|
"num_tokens": 18057960.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.30379090309143,
|
|
"epoch": 0.8194119612429,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004939145842258418,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.1840106263756752,
|
|
"num_tokens": 18066677.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.389127445220947,
|
|
"epoch": 0.8198296024056131,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004939077054395341,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.1844009429216385,
|
|
"num_tokens": 18075830.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.340755653381348,
|
|
"epoch": 0.8202472435683261,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004939008228209836,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.18784936964511872,
|
|
"num_tokens": 18085335.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.30837197303772,
|
|
"epoch": 0.820664884731039,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004938939363703106,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.18218090534210205,
|
|
"num_tokens": 18094531.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.2695659637451175,
|
|
"epoch": 0.8210825258937521,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004938870460876359,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.19451568573713302,
|
|
"num_tokens": 18103593.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.316597127914429,
|
|
"epoch": 0.8215001670564651,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00049388015197308,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.19050071984529496,
|
|
"num_tokens": 18112826.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.365003681182861,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004938732540267635,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.18888215273618697,
|
|
"num_tokens": 18121687.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.345579147338867,
|
|
"epoch": 0.8223354493818911,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004938663522488072,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.19906752705574035,
|
|
"num_tokens": 18130071.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.380211639404297,
|
|
"epoch": 0.8227530905446041,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004938594466393321,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.1846168205142021,
|
|
"num_tokens": 18139077.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.34048023223877,
|
|
"epoch": 0.823170731707317,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004938525371984588,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.19228179156780242,
|
|
"num_tokens": 18147173.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.235449695587159,
|
|
"epoch": 0.8235883728700301,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004938456239263085,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.19033245891332626,
|
|
"num_tokens": 18157061.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.2925516128540036,
|
|
"epoch": 0.8240060140327431,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004938387068230021,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.1912828728556633,
|
|
"num_tokens": 18166115.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.3132106304168705,
|
|
"epoch": 0.824423655195456,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004938317858886606,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.19255006164312363,
|
|
"num_tokens": 18174978.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.307817506790161,
|
|
"epoch": 0.824841296358169,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004938248611234055,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.1895279109477997,
|
|
"num_tokens": 18184948.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.3290262699127195,
|
|
"epoch": 0.8252589375208821,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004938179325273577,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.19005334973335267,
|
|
"num_tokens": 18193443.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.354461336135865,
|
|
"epoch": 0.825676578683595,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004938110001006385,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.1891029730439186,
|
|
"num_tokens": 18202512.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.361838436126709,
|
|
"epoch": 0.826094219846308,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004938040638433694,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.19064506739377976,
|
|
"num_tokens": 18212328.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.320434808731079,
|
|
"epoch": 0.8265118610090211,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004937971237556719,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.1904003605246544,
|
|
"num_tokens": 18221155.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.325121593475342,
|
|
"epoch": 0.826929502171734,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004937901798376672,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.1933050587773323,
|
|
"num_tokens": 18230604.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.316837215423584,
|
|
"epoch": 0.827347143334447,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004937832320894772,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.191922527551651,
|
|
"num_tokens": 18239126.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.282761669158935,
|
|
"epoch": 0.8277647844971601,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004937762805112233,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.18285557478666306,
|
|
"num_tokens": 18248634.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.326156663894653,
|
|
"epoch": 0.828182425659873,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004937693251030273,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.17551200985908508,
|
|
"num_tokens": 18258500.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.399630689620972,
|
|
"epoch": 0.828600066822586,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000493762365865011,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.18955700248479843,
|
|
"num_tokens": 18268374.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.373224115371704,
|
|
"epoch": 0.8290177079852991,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004937554027972961,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.18239429891109465,
|
|
"num_tokens": 18277667.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.306133794784546,
|
|
"epoch": 0.829435349148012,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004937484359000046,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.18764786720275878,
|
|
"num_tokens": 18287516.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.292248153686524,
|
|
"epoch": 0.829852990310725,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004937414651732584,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.19411901384592056,
|
|
"num_tokens": 18296534.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.35420503616333,
|
|
"epoch": 0.830270631473438,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004937344906171795,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.18965759575366975,
|
|
"num_tokens": 18305743.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.36882586479187,
|
|
"epoch": 0.830688272636151,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004937275122318902,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.18101778775453567,
|
|
"num_tokens": 18315524.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.297546863555908,
|
|
"epoch": 0.831105913798864,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004937205300175123,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.19682240039110183,
|
|
"num_tokens": 18324280.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.363136672973633,
|
|
"epoch": 0.831523554961577,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004937135439741682,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.18807094991207124,
|
|
"num_tokens": 18332661.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.384078884124756,
|
|
"epoch": 0.83194119612429,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004937065541019806,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.1700368896126747,
|
|
"num_tokens": 18342986.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.396446323394775,
|
|
"epoch": 0.832358837287003,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004936995604010711,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.18414016664028168,
|
|
"num_tokens": 18351873.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.399761438369751,
|
|
"epoch": 0.832776478449716,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004936925628715628,
|
|
"loss": 5.3191,
|
|
"mean_token_accuracy": 0.18092354089021684,
|
|
"num_tokens": 18362174.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.335303449630738,
|
|
"epoch": 0.833194119612429,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004936855615135779,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.19510533511638642,
|
|
"num_tokens": 18371272.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.361533784866333,
|
|
"epoch": 0.833611760775142,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000493678556327239,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.18942816257476808,
|
|
"num_tokens": 18380526.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.2963732242584225,
|
|
"epoch": 0.834029401937855,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004936715473126688,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.1921591728925705,
|
|
"num_tokens": 18390027.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.242372179031372,
|
|
"epoch": 0.8344470431005679,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00049366453446999,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.19045700430870055,
|
|
"num_tokens": 18399012.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.216147613525391,
|
|
"epoch": 0.834864684263281,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004936575177993251,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.19057831168174744,
|
|
"num_tokens": 18408891.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.264990663528442,
|
|
"epoch": 0.835282325425994,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004936504973007973,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.19354889839887618,
|
|
"num_tokens": 18417909.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.27159948348999,
|
|
"epoch": 0.8356999665887069,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004936434729745294,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.19167029708623887,
|
|
"num_tokens": 18427250.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.294535732269287,
|
|
"epoch": 0.83611760775142,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004936364448206442,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.19149200171232222,
|
|
"num_tokens": 18435851.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.231304550170899,
|
|
"epoch": 0.836535248914133,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004936294128392649,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.1829630732536316,
|
|
"num_tokens": 18444535.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.337705469131469,
|
|
"epoch": 0.8369528900768459,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004936223770305146,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.1871430516242981,
|
|
"num_tokens": 18454453.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.411758995056152,
|
|
"epoch": 0.837370531239559,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004936153373945165,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.18302317559719086,
|
|
"num_tokens": 18465033.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.334819173812866,
|
|
"epoch": 0.837788172402272,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004936082939313936,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.1861498937010765,
|
|
"num_tokens": 18473786.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.284872436523438,
|
|
"epoch": 0.8382058135649849,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004936012466412695,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.1824897602200508,
|
|
"num_tokens": 18483282.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.4622749328613285,
|
|
"epoch": 0.838623454727698,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004935941955242674,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.1818353682756424,
|
|
"num_tokens": 18492612.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.348860359191894,
|
|
"epoch": 0.839041095890411,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004935871405805109,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.19514228105545045,
|
|
"num_tokens": 18501120.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.301193523406982,
|
|
"epoch": 0.8394587370531239,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004935800818101232,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.18511967957019806,
|
|
"num_tokens": 18510613.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.27965784072876,
|
|
"epoch": 0.8398763782158369,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004935730192132282,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.19652514904737473,
|
|
"num_tokens": 18518854.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.348846578598023,
|
|
"epoch": 0.84029401937855,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.0004935659527899493,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.1909124955534935,
|
|
"num_tokens": 18527592.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.223753356933594,
|
|
"epoch": 0.8407116605412629,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004935588825404104,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.2033865198493004,
|
|
"num_tokens": 18536396.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.2362908840179445,
|
|
"epoch": 0.8411293017039759,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004935518084647351,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.20289033353328706,
|
|
"num_tokens": 18545201.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.311696910858155,
|
|
"epoch": 0.841546942866689,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004935447305630474,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.18510085046291352,
|
|
"num_tokens": 18554944.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.298465013504028,
|
|
"epoch": 0.8419645840294019,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004935376488354711,
|
|
"loss": 5.1372,
|
|
"mean_token_accuracy": 0.18965242207050323,
|
|
"num_tokens": 18564642.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.321731233596802,
|
|
"epoch": 0.8423822251921149,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004935305632821303,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.19197022020816804,
|
|
"num_tokens": 18573897.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.34338345527649,
|
|
"epoch": 0.842799866354828,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004935234739031488,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.18661972284317016,
|
|
"num_tokens": 18583174.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.326038074493408,
|
|
"epoch": 0.8432175075175409,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004935163806986508,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.19799598753452302,
|
|
"num_tokens": 18592540.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.268729209899902,
|
|
"epoch": 0.8436351486802539,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004935092836687607,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.19314343929290773,
|
|
"num_tokens": 18602743.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.22485122680664,
|
|
"epoch": 0.8440527898429669,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004935021828136025,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.19164522588253022,
|
|
"num_tokens": 18611544.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.3677003383636475,
|
|
"epoch": 0.8444704310056799,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004934950781333005,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.18606801629066466,
|
|
"num_tokens": 18620841.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.367251348495484,
|
|
"epoch": 0.8448880721683929,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004934879696279793,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.18908178210258483,
|
|
"num_tokens": 18630890.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.355392265319824,
|
|
"epoch": 0.8453057133311059,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004934808572977632,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.18310176432132722,
|
|
"num_tokens": 18639768.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.249336194992066,
|
|
"epoch": 0.8457233544938189,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004934737411427765,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.19338246583938598,
|
|
"num_tokens": 18649578.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.265984725952149,
|
|
"epoch": 0.8461409956565319,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004934666211631442,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.1938577711582184,
|
|
"num_tokens": 18658470.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.264990043640137,
|
|
"epoch": 0.8465586368192449,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004934594973589906,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.1872977375984192,
|
|
"num_tokens": 18668037.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.295865106582641,
|
|
"epoch": 0.8469762779819578,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004934523697304406,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.18623916655778885,
|
|
"num_tokens": 18677841.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.404227352142334,
|
|
"epoch": 0.8473939191446709,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004934452382776189,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.18454785794019699,
|
|
"num_tokens": 18686244.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.313640069961548,
|
|
"epoch": 0.8478115603073839,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004934381030006504,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.18657472729682922,
|
|
"num_tokens": 18695129.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.181084680557251,
|
|
"epoch": 0.8482292014700968,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00049343096389966,
|
|
"loss": 5.028,
|
|
"mean_token_accuracy": 0.20085298717021943,
|
|
"num_tokens": 18703566.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.384372615814209,
|
|
"epoch": 0.8486468426328099,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004934238209747724,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.17773670852184295,
|
|
"num_tokens": 18713616.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.421914100646973,
|
|
"epoch": 0.8490644837955229,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004934166742261132,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.1845224305987358,
|
|
"num_tokens": 18722851.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.356164598464966,
|
|
"epoch": 0.8494821249582358,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000493409523653807,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.1861880376935005,
|
|
"num_tokens": 18731961.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.365734815597534,
|
|
"epoch": 0.8498997661209489,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004934023692579793,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.18228207230567933,
|
|
"num_tokens": 18741267.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.303253555297852,
|
|
"epoch": 0.8503174072836619,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004933952110387553,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.18911945819854736,
|
|
"num_tokens": 18750266.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.2705018520355225,
|
|
"epoch": 0.8507350484463748,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004933880489962602,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.18801131546497346,
|
|
"num_tokens": 18759910.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.439163112640381,
|
|
"epoch": 0.8511526896090879,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004933808831306194,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.17844336181879045,
|
|
"num_tokens": 18769510.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.300149202346802,
|
|
"epoch": 0.8515703307718009,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004933737134419583,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.1858849734067917,
|
|
"num_tokens": 18779893.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.327555704116821,
|
|
"epoch": 0.8519879719345138,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004933665399304025,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.19460691660642623,
|
|
"num_tokens": 18788802.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.280136299133301,
|
|
"epoch": 0.8524056130972268,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004933593625960777,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.18462813794612884,
|
|
"num_tokens": 18797154.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.303889799118042,
|
|
"epoch": 0.8528232542599399,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004933521814391094,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.18324453979730607,
|
|
"num_tokens": 18806151.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.385970687866211,
|
|
"epoch": 0.8532408954226529,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004933449964596232,
|
|
"loss": 5.0983,
|
|
"mean_token_accuracy": 0.19556251168251038,
|
|
"num_tokens": 18815162.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.244508266448975,
|
|
"epoch": 0.8536585365853658,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004933378076577451,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.18822017908096314,
|
|
"num_tokens": 18823676.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.357374906539917,
|
|
"epoch": 0.8540761777480789,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004933306150336009,
|
|
"loss": 5.3943,
|
|
"mean_token_accuracy": 0.17783361673355103,
|
|
"num_tokens": 18832991.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.480168008804322,
|
|
"epoch": 0.8544938189107919,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004933234185873164,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.18567426204681398,
|
|
"num_tokens": 18842614.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.451560068130493,
|
|
"epoch": 0.8549114600735048,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004933162183190177,
|
|
"loss": 5.3161,
|
|
"mean_token_accuracy": 0.17856184989213944,
|
|
"num_tokens": 18852747.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.244213247299195,
|
|
"epoch": 0.8553291012362179,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004933090142288308,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.19237858057022095,
|
|
"num_tokens": 18862005.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.309420824050903,
|
|
"epoch": 0.8557467423989309,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004933018063168819,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.1995083510875702,
|
|
"num_tokens": 18870172.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.3396923542022705,
|
|
"epoch": 0.8561643835616438,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000493294594583297,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.18443857431411742,
|
|
"num_tokens": 18879428.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.296653985977173,
|
|
"epoch": 0.8565820247243568,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004932873790282026,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.2006555438041687,
|
|
"num_tokens": 18888694.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.408766222000122,
|
|
"epoch": 0.8569996658870699,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004932801596517248,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.18389252275228501,
|
|
"num_tokens": 18898317.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.274123239517212,
|
|
"epoch": 0.8574173070497828,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004932729364539901,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.18400730639696122,
|
|
"num_tokens": 18906749.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.280352401733398,
|
|
"epoch": 0.8578349482124958,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004932657094351248,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.19361914098262786,
|
|
"num_tokens": 18915404.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.2740716457366945,
|
|
"epoch": 0.8582525893752089,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004932584785952555,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.18665087223052979,
|
|
"num_tokens": 18925512.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.284380483627319,
|
|
"epoch": 0.8586702305379218,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000493251243934509,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.19272940307855607,
|
|
"num_tokens": 18934278.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.322548866271973,
|
|
"epoch": 0.8590878717006348,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004932440054530116,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.18642934262752534,
|
|
"num_tokens": 18943126.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.337692451477051,
|
|
"epoch": 0.8595055128633479,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004932367631508903,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.19143159240484237,
|
|
"num_tokens": 18951716.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.29817156791687,
|
|
"epoch": 0.8599231540260608,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004932295170282717,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.18123940676450728,
|
|
"num_tokens": 18960692.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.280509328842163,
|
|
"epoch": 0.8603407951887738,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004932222670852828,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.1924230858683586,
|
|
"num_tokens": 18969813.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.352678060531616,
|
|
"epoch": 0.8607584363514869,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004932150133220504,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.193808476626873,
|
|
"num_tokens": 18978536.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.290709447860718,
|
|
"epoch": 0.8611760775141998,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004932077557387015,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.18996871411800384,
|
|
"num_tokens": 18987637.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.175679302215576,
|
|
"epoch": 0.8615937186769128,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004932004943353633,
|
|
"loss": 4.9682,
|
|
"mean_token_accuracy": 0.20098690539598466,
|
|
"num_tokens": 18997010.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.327095413208008,
|
|
"epoch": 0.8620113598396258,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004931932291121627,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.1873937502503395,
|
|
"num_tokens": 19005685.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.307133674621582,
|
|
"epoch": 0.8624290010023388,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004931859600692269,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.1900626540184021,
|
|
"num_tokens": 19014836.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.344813346862793,
|
|
"epoch": 0.8628466421650518,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004931786872066833,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.1814238429069519,
|
|
"num_tokens": 19024442.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.33070740699768,
|
|
"epoch": 0.8632642833277648,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004931714105246592,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.19128657281398773,
|
|
"num_tokens": 19033730.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.310273504257202,
|
|
"epoch": 0.8636819244904778,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004931641300232819,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.2026464730501175,
|
|
"num_tokens": 19042765.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.308903694152832,
|
|
"epoch": 0.8640995656531908,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004931568457026789,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.18763562738895417,
|
|
"num_tokens": 19051408.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.32097806930542,
|
|
"epoch": 0.8645172068159038,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004931495575629778,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.17876803129911423,
|
|
"num_tokens": 19061145.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.31494722366333,
|
|
"epoch": 0.8649348479786167,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000493142265604306,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.18291258364915847,
|
|
"num_tokens": 19070157.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.256790208816528,
|
|
"epoch": 0.8653524891413298,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004931349698267914,
|
|
"loss": 5.0146,
|
|
"mean_token_accuracy": 0.2009235605597496,
|
|
"num_tokens": 19078532.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.263900661468506,
|
|
"epoch": 0.8657701303040428,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004931276702305615,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.1976345658302307,
|
|
"num_tokens": 19087283.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.322926759719849,
|
|
"epoch": 0.8661877714667557,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004931203668157441,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.19001127183437347,
|
|
"num_tokens": 19097568.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.374041128158569,
|
|
"epoch": 0.8666054126294688,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004931130595824672,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.18117907494306565,
|
|
"num_tokens": 19107218.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.334418821334839,
|
|
"epoch": 0.8670230537921818,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004931057485308587,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.1926760733127594,
|
|
"num_tokens": 19116128.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.229773235321045,
|
|
"epoch": 0.8674406949548947,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004930984336610465,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.19678619652986526,
|
|
"num_tokens": 19124885.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.4001775741577145,
|
|
"epoch": 0.8678583361176078,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004930911149731587,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.19020774364471435,
|
|
"num_tokens": 19134125.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.273541212081909,
|
|
"epoch": 0.8682759772803208,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004930837924673233,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.1925998941063881,
|
|
"num_tokens": 19141925.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.30088586807251,
|
|
"epoch": 0.8686936184430337,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004930764661436688,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.19022163450717927,
|
|
"num_tokens": 19151440.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.368042755126953,
|
|
"epoch": 0.8691112596057468,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004930691360023231,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.19069868624210357,
|
|
"num_tokens": 19161447.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.383994102478027,
|
|
"epoch": 0.8695289007684598,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004930618020434147,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.18452608585357666,
|
|
"num_tokens": 19170804.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.431319618225098,
|
|
"epoch": 0.8699465419311727,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004930544642670721,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.18168249875307083,
|
|
"num_tokens": 19179898.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.241486978530884,
|
|
"epoch": 0.8703641830938857,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004930471226734235,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.19783590137958526,
|
|
"num_tokens": 19188919.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.33616042137146,
|
|
"epoch": 0.8707818242565988,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004930397772625976,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.18918959349393843,
|
|
"num_tokens": 19197745.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.2575071334838865,
|
|
"epoch": 0.8711994654193117,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000493032428034723,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.18823064863681793,
|
|
"num_tokens": 19206681.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.380467176437378,
|
|
"epoch": 0.8716171065820247,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004930250749899282,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.1915568307042122,
|
|
"num_tokens": 19215806.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.374777555465698,
|
|
"epoch": 0.8720347477447378,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004930177181283422,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.18793948143720626,
|
|
"num_tokens": 19224681.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.287902545928955,
|
|
"epoch": 0.8724523889074507,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004930103574500934,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.1879182666540146,
|
|
"num_tokens": 19232684.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.311669063568115,
|
|
"epoch": 0.8728700300701637,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004930029929553109,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.18654640167951583,
|
|
"num_tokens": 19242538.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.341206121444702,
|
|
"epoch": 0.8732876712328768,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004929956246441237,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.1860884830355644,
|
|
"num_tokens": 19251146.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.400697851181031,
|
|
"epoch": 0.8737053123955897,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004929882525166608,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.18426415473222732,
|
|
"num_tokens": 19259931.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.306517648696899,
|
|
"epoch": 0.8741229535583027,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004929808765730509,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.1874943718314171,
|
|
"num_tokens": 19268796.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.295291614532471,
|
|
"epoch": 0.8745405947210158,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004929734968134235,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.18509959131479264,
|
|
"num_tokens": 19278396.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.361218738555908,
|
|
"epoch": 0.8749582358837287,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004929661132379076,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.1819717988371849,
|
|
"num_tokens": 19287914.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.388542318344117,
|
|
"epoch": 0.8753758770464417,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004929587258466326,
|
|
"loss": 5.201,
|
|
"mean_token_accuracy": 0.1837903916835785,
|
|
"num_tokens": 19297304.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.357698440551758,
|
|
"epoch": 0.8757935182091547,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004929513346397278,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.19044652879238128,
|
|
"num_tokens": 19306245.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.345926094055176,
|
|
"epoch": 0.8762111593718677,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004929439396173223,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.17997460663318635,
|
|
"num_tokens": 19316160.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.294673013687134,
|
|
"epoch": 0.8766288005345807,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000492936540779546,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.18372495323419571,
|
|
"num_tokens": 19325411.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.377767562866211,
|
|
"epoch": 0.8770464416972937,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004929291381265281,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.18904377818107604,
|
|
"num_tokens": 19334297.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.402296447753907,
|
|
"epoch": 0.8774640828600067,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004929217316583985,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.18171188086271287,
|
|
"num_tokens": 19344121.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.380285930633545,
|
|
"epoch": 0.8778817240227197,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004929143213752865,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.18814597725868226,
|
|
"num_tokens": 19353428.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.40724811553955,
|
|
"epoch": 0.8782993651854327,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000492906907277322,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.1868235781788826,
|
|
"num_tokens": 19362661.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.2036622047424315,
|
|
"epoch": 0.8787170063481456,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000492899489364635,
|
|
"loss": 5.0407,
|
|
"mean_token_accuracy": 0.20076248794794083,
|
|
"num_tokens": 19371246.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.288510274887085,
|
|
"epoch": 0.8791346475108587,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004928920676373549,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.19001537412405015,
|
|
"num_tokens": 19379777.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.292198038101196,
|
|
"epoch": 0.8795522886735717,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.000492884642095612,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.18770332336425782,
|
|
"num_tokens": 19388717.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.430406284332276,
|
|
"epoch": 0.8799699298362846,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004928772127395361,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.17967021018266677,
|
|
"num_tokens": 19397936.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.449111366271973,
|
|
"epoch": 0.8803875709989977,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004928697795692575,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.1796219006180763,
|
|
"num_tokens": 19406830.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.391684436798096,
|
|
"epoch": 0.8808052121617107,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000492862342584906,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.18780584782361984,
|
|
"num_tokens": 19415131.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.293669986724853,
|
|
"epoch": 0.8812228533244236,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000492854901786612,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.20062102228403092,
|
|
"num_tokens": 19423585.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.236867094039917,
|
|
"epoch": 0.8816404944871367,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004928474571745058,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.2019955188035965,
|
|
"num_tokens": 19431890.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.3149364471435545,
|
|
"epoch": 0.8820581356498497,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004928400087487175,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.18816973268985748,
|
|
"num_tokens": 19441377.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.341273832321167,
|
|
"epoch": 0.8824757768125626,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004928325565093777,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.18512748777866364,
|
|
"num_tokens": 19451003.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.263963937759399,
|
|
"epoch": 0.8828934179752757,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004928251004566167,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.1944951444864273,
|
|
"num_tokens": 19460166.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.249623775482178,
|
|
"epoch": 0.8833110591379887,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004928176405905653,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.19052540510892868,
|
|
"num_tokens": 19469417.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.357008075714111,
|
|
"epoch": 0.8837287003007016,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004928101769113537,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.19121133685112,
|
|
"num_tokens": 19479275.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.377585363388062,
|
|
"epoch": 0.8841463414634146,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000492802709419113,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.1852693811058998,
|
|
"num_tokens": 19488804.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.372596406936646,
|
|
"epoch": 0.8845639826261277,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004927952381139735,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.19373662322759627,
|
|
"num_tokens": 19497701.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.350929021835327,
|
|
"epoch": 0.8849816237888406,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004927877629960663,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.1899461030960083,
|
|
"num_tokens": 19508177.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.321989917755127,
|
|
"epoch": 0.8853992649515536,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004927802840655221,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.18899890333414077,
|
|
"num_tokens": 19516866.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.357509136199951,
|
|
"epoch": 0.8858169061142667,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000492772801322472,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.1834711253643036,
|
|
"num_tokens": 19525788.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.330137538909912,
|
|
"epoch": 0.8862345472769796,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004927653147670468,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.19043076783418655,
|
|
"num_tokens": 19534748.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.2439979076385494,
|
|
"epoch": 0.8866521884396926,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004927578243993777,
|
|
"loss": 5.128,
|
|
"mean_token_accuracy": 0.19365649223327636,
|
|
"num_tokens": 19544083.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.21814603805542,
|
|
"epoch": 0.8870698296024057,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004927503302195957,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.18991438597440718,
|
|
"num_tokens": 19553978.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.35388216972351,
|
|
"epoch": 0.8874874707651186,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000492742832227832,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.18995462059974672,
|
|
"num_tokens": 19563265.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.413037967681885,
|
|
"epoch": 0.8879051119278316,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000492735330424218,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.17343059033155442,
|
|
"num_tokens": 19572904.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.40406641960144,
|
|
"epoch": 0.8883227530905446,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000492727824808885,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.1931409627199173,
|
|
"num_tokens": 19581680.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.270676708221435,
|
|
"epoch": 0.8887403942532576,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004927203153819643,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.1901499405503273,
|
|
"num_tokens": 19590885.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.241280460357666,
|
|
"epoch": 0.8891580354159706,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004927128021435875,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.19374241679906845,
|
|
"num_tokens": 19599901.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.370092678070068,
|
|
"epoch": 0.8895756765786836,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000492705285093886,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.18349129408597947,
|
|
"num_tokens": 19608745.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.277809715270996,
|
|
"epoch": 0.8899933177413966,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004926977642329913,
|
|
"loss": 5.0146,
|
|
"mean_token_accuracy": 0.19165204763412474,
|
|
"num_tokens": 19618418.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.279439640045166,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004926902395610353,
|
|
"loss": 5.0896,
|
|
"mean_token_accuracy": 0.18721594661474228,
|
|
"num_tokens": 19627118.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.3316254138946535,
|
|
"epoch": 0.8908286000668226,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004926827110781496,
|
|
"loss": 5.2442,
|
|
"mean_token_accuracy": 0.18570893853902817,
|
|
"num_tokens": 19636565.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.270682525634766,
|
|
"epoch": 0.8912462412295356,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000492675178784466,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.1896353021264076,
|
|
"num_tokens": 19645038.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.279138278961182,
|
|
"epoch": 0.8916638823922486,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004926676426801164,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.19063107967376708,
|
|
"num_tokens": 19654088.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.321343564987183,
|
|
"epoch": 0.8920815235549616,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004926601027652328,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.18899362981319429,
|
|
"num_tokens": 19662551.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.398276138305664,
|
|
"epoch": 0.8924991647176745,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000492652559039947,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.19150290936231612,
|
|
"num_tokens": 19672405.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.265410947799682,
|
|
"epoch": 0.8929168058803876,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004926450115043912,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.18920089155435563,
|
|
"num_tokens": 19681288.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.2466329574584964,
|
|
"epoch": 0.8933344470431006,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004926374601586975,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.1912362590432167,
|
|
"num_tokens": 19690723.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.358538722991943,
|
|
"epoch": 0.8937520882058135,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004926299050029981,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.18955470472574235,
|
|
"num_tokens": 19699642.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.320053577423096,
|
|
"epoch": 0.8941697293685266,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004926223460374251,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.1930806428194046,
|
|
"num_tokens": 19707563.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.3053521633148195,
|
|
"epoch": 0.8945873705312396,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004926147832621111,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.18802300244569778,
|
|
"num_tokens": 19717109.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.22956428527832,
|
|
"epoch": 0.8950050116939525,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004926072166771884,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.19896597117185594,
|
|
"num_tokens": 19725585.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.175854825973511,
|
|
"epoch": 0.8954226528566656,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004925996462827895,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.20378232896327972,
|
|
"num_tokens": 19733502.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.299879360198974,
|
|
"epoch": 0.8958402940193786,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004925920720790466,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.1861718401312828,
|
|
"num_tokens": 19742926.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.264319705963135,
|
|
"epoch": 0.8962579351820915,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004925844940660928,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.19325936138629912,
|
|
"num_tokens": 19752488.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.363840627670288,
|
|
"epoch": 0.8966755763448045,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004925769122440606,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.17976808696985244,
|
|
"num_tokens": 19762705.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.22624888420105,
|
|
"epoch": 0.8970932175075176,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004925693266130824,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.2002018615603447,
|
|
"num_tokens": 19771156.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.264958715438842,
|
|
"epoch": 0.8975108586702305,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004925617371732914,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.1936448633670807,
|
|
"num_tokens": 19780788.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.199323940277099,
|
|
"epoch": 0.8979284998329435,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004925541439248203,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.20016645640134811,
|
|
"num_tokens": 19790169.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.388787126541137,
|
|
"epoch": 0.8983461409956566,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000492546546867802,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.17736679315567017,
|
|
"num_tokens": 19800249.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.318563222885132,
|
|
"epoch": 0.8987637821583695,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004925389460023696,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.19099222868680954,
|
|
"num_tokens": 19809797.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.230153274536133,
|
|
"epoch": 0.8991814233210825,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004925313413286559,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.1953825056552887,
|
|
"num_tokens": 19818826.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.286236763000488,
|
|
"epoch": 0.8995990644837956,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004925237328467945,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.19076265394687653,
|
|
"num_tokens": 19827947.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.361205387115478,
|
|
"epoch": 0.9000167056465085,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004925161205569182,
|
|
"loss": 5.2106,
|
|
"mean_token_accuracy": 0.18659184724092484,
|
|
"num_tokens": 19835734.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.411896657943726,
|
|
"epoch": 0.9004343468092215,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004925085044591604,
|
|
"loss": 5.3222,
|
|
"mean_token_accuracy": 0.17887253314256668,
|
|
"num_tokens": 19845175.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.305286407470703,
|
|
"epoch": 0.9008519879719346,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004925008845536544,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.18973954319953917,
|
|
"num_tokens": 19853684.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.348168087005615,
|
|
"epoch": 0.9012696291346475,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004924932608405336,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.1882624715566635,
|
|
"num_tokens": 19862813.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.347144985198975,
|
|
"epoch": 0.9016872702973605,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004924856333199315,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.1923440143465996,
|
|
"num_tokens": 19871545.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.308362054824829,
|
|
"epoch": 0.9021049114600735,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004924780019919816,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.186128169298172,
|
|
"num_tokens": 19880060.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.289190149307251,
|
|
"epoch": 0.9025225526227865,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004924703668568174,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.18785108178853988,
|
|
"num_tokens": 19889151.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.363161087036133,
|
|
"epoch": 0.9029401937854995,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004924627279145728,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.1965825855731964,
|
|
"num_tokens": 19898087.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.298778772354126,
|
|
"epoch": 0.9033578349482125,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004924550851653814,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.19995987564325332,
|
|
"num_tokens": 19906196.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.31768798828125,
|
|
"epoch": 0.9037754761109255,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004924474386093769,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.18674472272396087,
|
|
"num_tokens": 19915837.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.273045253753662,
|
|
"epoch": 0.9041931172736385,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004924397882466933,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.18707826882600784,
|
|
"num_tokens": 19926012.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.275276613235474,
|
|
"epoch": 0.9046107584363515,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004924321340774644,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.1945568010210991,
|
|
"num_tokens": 19935987.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.277724266052246,
|
|
"epoch": 0.9050283995990644,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004924244761018243,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.18308883309364318,
|
|
"num_tokens": 19945865.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.3237203598022464,
|
|
"epoch": 0.9054460407617775,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000492416814319907,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.19275479316711425,
|
|
"num_tokens": 19954824.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.264316654205322,
|
|
"epoch": 0.9058636819244905,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004924091487318468,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.18456410467624665,
|
|
"num_tokens": 19964740.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.248150300979614,
|
|
"epoch": 0.9062813230872034,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004924014793377776,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.19337785840034485,
|
|
"num_tokens": 19974310.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.235246229171753,
|
|
"epoch": 0.9066989642499165,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004923938061378339,
|
|
"loss": 5.0035,
|
|
"mean_token_accuracy": 0.19750896394252776,
|
|
"num_tokens": 19982943.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.2883970737457275,
|
|
"epoch": 0.9071166054126295,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004923861291321499,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.1913818299770355,
|
|
"num_tokens": 19991971.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.354921817779541,
|
|
"epoch": 0.9075342465753424,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004923784483208601,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.18568297028541564,
|
|
"num_tokens": 20001491.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.290411901473999,
|
|
"epoch": 0.9079518877380555,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004923707637040989,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.1971973344683647,
|
|
"num_tokens": 20010605.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.130425500869751,
|
|
"epoch": 0.9083695289007685,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004923630752820008,
|
|
"loss": 4.9342,
|
|
"mean_token_accuracy": 0.2001164361834526,
|
|
"num_tokens": 20019291.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.232851934432984,
|
|
"epoch": 0.9087871700634814,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004923553830547004,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.18514347672462464,
|
|
"num_tokens": 20029048.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.386471128463745,
|
|
"epoch": 0.9092048112261945,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004923476870223324,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.18818991929292678,
|
|
"num_tokens": 20037878.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.286022520065307,
|
|
"epoch": 0.9096224523889075,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004923399871850315,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.1949710115790367,
|
|
"num_tokens": 20046662.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.223567628860474,
|
|
"epoch": 0.9100400935516204,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004923322835429326,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.19120468497276305,
|
|
"num_tokens": 20055329.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.195465993881226,
|
|
"epoch": 0.9104577347143334,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004923245760961704,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.2026669815182686,
|
|
"num_tokens": 20064024.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.33611044883728,
|
|
"epoch": 0.9108753758770465,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004923168648448799,
|
|
"loss": 5.2224,
|
|
"mean_token_accuracy": 0.18506976813077927,
|
|
"num_tokens": 20073022.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.30430588722229,
|
|
"epoch": 0.9112930170397594,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004923091497891961,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.18535736501216887,
|
|
"num_tokens": 20081495.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.344881772994995,
|
|
"epoch": 0.9117106582024724,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004923014309292541,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.19913057386875152,
|
|
"num_tokens": 20090545.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.327037811279297,
|
|
"epoch": 0.9121282993651855,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000492293708265189,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.19455758184194566,
|
|
"num_tokens": 20100236.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.265479278564453,
|
|
"epoch": 0.9125459405278984,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004922859817971359,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.18306612074375153,
|
|
"num_tokens": 20109522.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.263588905334473,
|
|
"epoch": 0.9129635816906114,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004922782515252302,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.19643136113882065,
|
|
"num_tokens": 20118248.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.158023881912231,
|
|
"epoch": 0.9133812228533245,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004922705174496072,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.188995860517025,
|
|
"num_tokens": 20127096.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.232941007614135,
|
|
"epoch": 0.9137988640160374,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004922627795704022,
|
|
"loss": 5.1304,
|
|
"mean_token_accuracy": 0.18677591234445573,
|
|
"num_tokens": 20136815.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.323242568969727,
|
|
"epoch": 0.9142165051787504,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004922550378877507,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.19914378374814987,
|
|
"num_tokens": 20145455.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.339954042434693,
|
|
"epoch": 0.9146341463414634,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004922472924017882,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.18386811316013335,
|
|
"num_tokens": 20156139.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.345303297042847,
|
|
"epoch": 0.9150517875041764,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004922395431126506,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.18810480535030366,
|
|
"num_tokens": 20166266.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.416538572311401,
|
|
"epoch": 0.9154694286668894,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004922317900204732,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.18291556239128112,
|
|
"num_tokens": 20175005.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.225204706192017,
|
|
"epoch": 0.9158870698296024,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004922240331253916,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.1997062399983406,
|
|
"num_tokens": 20183488.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.266636800765991,
|
|
"epoch": 0.9163047109923154,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004922162724275421,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.1962377279996872,
|
|
"num_tokens": 20193724.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.342124700546265,
|
|
"epoch": 0.9167223521550284,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004922085079270602,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.1881588250398636,
|
|
"num_tokens": 20203733.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.452734661102295,
|
|
"epoch": 0.9171399933177414,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004922007396240819,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.19434769153594972,
|
|
"num_tokens": 20213448.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.356554937362671,
|
|
"epoch": 0.9175576344804544,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004921929675187433,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.18734360635280609,
|
|
"num_tokens": 20222837.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.323911523818969,
|
|
"epoch": 0.9179752756431674,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004921851916111802,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.1847895488142967,
|
|
"num_tokens": 20232056.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.361779308319091,
|
|
"epoch": 0.9183929168058804,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004921774119015289,
|
|
"loss": 5.2158,
|
|
"mean_token_accuracy": 0.18765031099319457,
|
|
"num_tokens": 20241052.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.379041576385498,
|
|
"epoch": 0.9188105579685933,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004921696283899257,
|
|
"loss": 5.2776,
|
|
"mean_token_accuracy": 0.18354066982865333,
|
|
"num_tokens": 20251015.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.271229314804077,
|
|
"epoch": 0.9192281991313064,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004921618410765067,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.19168516099452973,
|
|
"num_tokens": 20259388.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.378978967666626,
|
|
"epoch": 0.9196458402940194,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004921540499614083,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.19158013612031938,
|
|
"num_tokens": 20268146.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.273536682128906,
|
|
"epoch": 0.9200634814567323,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004921462550447669,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.1963006317615509,
|
|
"num_tokens": 20277559.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.276912784576416,
|
|
"epoch": 0.9204811226194454,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004921384563267189,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.18395720720291137,
|
|
"num_tokens": 20285661.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.326535844802857,
|
|
"epoch": 0.9208987637821584,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004921306538074008,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.1907956123352051,
|
|
"num_tokens": 20294636.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.3194504737854,
|
|
"epoch": 0.9213164049448713,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004921228474869493,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.1956602394580841,
|
|
"num_tokens": 20302372.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.30044379234314,
|
|
"epoch": 0.9217340461075844,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000492115037365501,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.19145287573337555,
|
|
"num_tokens": 20311974.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.297578382492065,
|
|
"epoch": 0.9221516872702974,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004921072234431925,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.1912020057439804,
|
|
"num_tokens": 20321720.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.326252603530884,
|
|
"epoch": 0.9225693284330103,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000492099405720161,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.18220922201871873,
|
|
"num_tokens": 20331324.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.349126148223877,
|
|
"epoch": 0.9229869695957233,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004920915841965429,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.185405170917511,
|
|
"num_tokens": 20340921.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.402704906463623,
|
|
"epoch": 0.9234046107584364,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004920837588724753,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.19052685499191285,
|
|
"num_tokens": 20349871.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.206499862670898,
|
|
"epoch": 0.9238222519211493,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004920759297480953,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.19570755064487458,
|
|
"num_tokens": 20359171.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.247551012039184,
|
|
"epoch": 0.9242398930838623,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004920680968235397,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.19701757580041884,
|
|
"num_tokens": 20367779.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.256858015060425,
|
|
"epoch": 0.9246575342465754,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004920602600989459,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.19889040440320968,
|
|
"num_tokens": 20377568.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.340265560150146,
|
|
"epoch": 0.9250751754092883,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004920524195744509,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.18503626585006713,
|
|
"num_tokens": 20385915.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.243323707580567,
|
|
"epoch": 0.9254928165720013,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004920445752501921,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.1943541631102562,
|
|
"num_tokens": 20394877.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.265145397186279,
|
|
"epoch": 0.9259104577347144,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004920367271263066,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.1932800829410553,
|
|
"num_tokens": 20403741.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.271869754791259,
|
|
"epoch": 0.9263280988974273,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004920288752029321,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.19450776129961014,
|
|
"num_tokens": 20412702.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.250715827941894,
|
|
"epoch": 0.9267457400601403,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004920210194802059,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.19392989724874496,
|
|
"num_tokens": 20421776.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.363069295883179,
|
|
"epoch": 0.9271633812228534,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004920131599582654,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.1774836540222168,
|
|
"num_tokens": 20432204.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.401186466217041,
|
|
"epoch": 0.9275810223855663,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004920052966372485,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.18065235167741775,
|
|
"num_tokens": 20441344.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.299026727676392,
|
|
"epoch": 0.9279986635482793,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004919974295172926,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.193643781542778,
|
|
"num_tokens": 20449800.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.238025188446045,
|
|
"epoch": 0.9284163047109923,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004919895585985353,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.20537518113851547,
|
|
"num_tokens": 20458326.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.28767580986023,
|
|
"epoch": 0.9288339458737053,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004919816838811149,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.18285572230815889,
|
|
"num_tokens": 20468050.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.346377992630005,
|
|
"epoch": 0.9292515870364183,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004919738053651687,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.19551948606967925,
|
|
"num_tokens": 20477046.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.274564123153686,
|
|
"epoch": 0.9296692281991313,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000491965923050835,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.18730415105819703,
|
|
"num_tokens": 20486228.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.310534954071045,
|
|
"epoch": 0.9300868693618443,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004919580369382516,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.18330602049827577,
|
|
"num_tokens": 20494764.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.310151481628418,
|
|
"epoch": 0.9305045105245573,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004919501470275567,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.19177802354097367,
|
|
"num_tokens": 20502805.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.246659469604492,
|
|
"epoch": 0.9309221516872703,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004919422533188882,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.1869480162858963,
|
|
"num_tokens": 20512322.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.272397565841675,
|
|
"epoch": 0.9313397928499833,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004919343558123845,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.18849266916513444,
|
|
"num_tokens": 20520680.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.285646057128906,
|
|
"epoch": 0.9317574340126963,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004919264545081838,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.2047054126858711,
|
|
"num_tokens": 20528864.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.260857439041137,
|
|
"epoch": 0.9321750751754093,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004919185494064244,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.1858099415898323,
|
|
"num_tokens": 20538195.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.279745483398438,
|
|
"epoch": 0.9325927163381222,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004919106405072446,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.19002094566822053,
|
|
"num_tokens": 20547312.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.331996822357178,
|
|
"epoch": 0.9330103575008353,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000491902727810783,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.18345918357372284,
|
|
"num_tokens": 20557184.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.2742408275604244,
|
|
"epoch": 0.9334279986635483,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004918948113171781,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.19250834733247757,
|
|
"num_tokens": 20565819.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.260569286346436,
|
|
"epoch": 0.9338456398262612,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004918868910265684,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.19066485911607742,
|
|
"num_tokens": 20574761.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.406101369857788,
|
|
"epoch": 0.9342632809889743,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004918789669390927,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.18671819418668748,
|
|
"num_tokens": 20584003.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.283585691452027,
|
|
"epoch": 0.9346809221516873,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004918710390548895,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.18976902812719346,
|
|
"num_tokens": 20593123.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.250103616714478,
|
|
"epoch": 0.9350985633144002,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004918631073740977,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.18998567759990692,
|
|
"num_tokens": 20602582.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.296892309188843,
|
|
"epoch": 0.9355162044771133,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004918551718968562,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.19461484998464584,
|
|
"num_tokens": 20611681.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.290851354598999,
|
|
"epoch": 0.9359338456398263,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000491847232623304,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.1950131133198738,
|
|
"num_tokens": 20620671.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.283709478378296,
|
|
"epoch": 0.9363514868025392,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004918392895535798,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.18826131671667098,
|
|
"num_tokens": 20629986.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.3349779605865475,
|
|
"epoch": 0.9367691279652522,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000491831342687823,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.19026129245758056,
|
|
"num_tokens": 20639274.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.308081912994385,
|
|
"epoch": 0.9371867691279653,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004918233920261723,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.1903127670288086,
|
|
"num_tokens": 20647753.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.17316951751709,
|
|
"epoch": 0.9376044102906782,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004918154375687673,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.20007274597883223,
|
|
"num_tokens": 20656226.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.194850063323974,
|
|
"epoch": 0.9380220514533912,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004918074793157472,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.19764335155487062,
|
|
"num_tokens": 20664682.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.331245851516724,
|
|
"epoch": 0.9384396926161043,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004917995172672511,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.18766049295663834,
|
|
"num_tokens": 20672909.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.212302780151367,
|
|
"epoch": 0.9388573337788172,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004917915514234184,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.2021414890885353,
|
|
"num_tokens": 20681316.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.279926443099976,
|
|
"epoch": 0.9392749749415302,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004917835817843887,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.18689426630735398,
|
|
"num_tokens": 20690360.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.330228090286255,
|
|
"epoch": 0.9396926161042433,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004917756083503014,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.18522235304117202,
|
|
"num_tokens": 20700398.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.363566207885742,
|
|
"epoch": 0.9401102572669562,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004917676311212962,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.18600541204214097,
|
|
"num_tokens": 20709705.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.238001728057862,
|
|
"epoch": 0.9405278984296692,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004917596500975127,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.1972285643219948,
|
|
"num_tokens": 20717774.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.296810054779053,
|
|
"epoch": 0.9409455395923823,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004917516652790907,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.1933752939105034,
|
|
"num_tokens": 20725966.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.339372205734253,
|
|
"epoch": 0.9413631807550952,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004917436766661697,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.19547368437051774,
|
|
"num_tokens": 20735254.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.292354536056519,
|
|
"epoch": 0.9417808219178082,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00049173568425889,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.20186227560043335,
|
|
"num_tokens": 20743331.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.275941276550293,
|
|
"epoch": 0.9421984630805212,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004917276880573911,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.1867146834731102,
|
|
"num_tokens": 20753966.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.270225381851196,
|
|
"epoch": 0.9426161042432342,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004917196880618132,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.19647087901830673,
|
|
"num_tokens": 20762608.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.209722185134888,
|
|
"epoch": 0.9430337454059472,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004917116842722962,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.19446980357170104,
|
|
"num_tokens": 20771194.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.278521490097046,
|
|
"epoch": 0.9434513865686602,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004917036766889804,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.19536812752485275,
|
|
"num_tokens": 20779700.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.364008235931396,
|
|
"epoch": 0.9438690277313732,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004916956653120058,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.18282273262739182,
|
|
"num_tokens": 20788117.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.3220068454742435,
|
|
"epoch": 0.9442866688940862,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004916876501415129,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.18652146607637404,
|
|
"num_tokens": 20798041.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.310404253005982,
|
|
"epoch": 0.9447043100567992,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004916796311776417,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.1839068502187729,
|
|
"num_tokens": 20807423.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.2947508811950685,
|
|
"epoch": 0.9451219512195121,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004916716084205328,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.19841802716255189,
|
|
"num_tokens": 20816727.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.262984037399292,
|
|
"epoch": 0.9455395923822252,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004916635818703266,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.18846407979726792,
|
|
"num_tokens": 20824855.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.201770353317261,
|
|
"epoch": 0.9459572335449382,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004916555515271635,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.196591155230999,
|
|
"num_tokens": 20833096.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.2126647472381595,
|
|
"epoch": 0.9463748747076511,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004916475173911844,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.19711389988660813,
|
|
"num_tokens": 20842398.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.326529884338379,
|
|
"epoch": 0.9467925158703642,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004916394794625296,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.18619543313980103,
|
|
"num_tokens": 20851745.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.459332418441773,
|
|
"epoch": 0.9472101570330772,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004916314377413399,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.18649569600820542,
|
|
"num_tokens": 20860935.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.332683086395264,
|
|
"epoch": 0.9476277981957901,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004916233922277562,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.18652458041906356,
|
|
"num_tokens": 20871088.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.267989206314087,
|
|
"epoch": 0.9480454393585032,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004916153429219192,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.19276488721370696,
|
|
"num_tokens": 20879313.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.288082408905029,
|
|
"epoch": 0.9484630805212162,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004916072898239699,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.188817335665226,
|
|
"num_tokens": 20888392.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.3171515464782715,
|
|
"epoch": 0.9488807216839291,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004915992329340493,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.18004927039146423,
|
|
"num_tokens": 20897456.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.319647026062012,
|
|
"epoch": 0.9492983628466422,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004915911722522984,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.1874665066599846,
|
|
"num_tokens": 20906621.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.4354753494262695,
|
|
"epoch": 0.9497160040093552,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004915831077788583,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.18478410840034484,
|
|
"num_tokens": 20916929.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.323004484176636,
|
|
"epoch": 0.9501336451720681,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004915750395138702,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.19146731793880462,
|
|
"num_tokens": 20926028.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.309450626373291,
|
|
"epoch": 0.9505512863347811,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004915669674574754,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.18093163669109344,
|
|
"num_tokens": 20935516.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.2704212188720705,
|
|
"epoch": 0.9509689274974942,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004915588916098151,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.19577372819185257,
|
|
"num_tokens": 20944100.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.292933511734009,
|
|
"epoch": 0.9513865686602071,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004915508119710307,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.18894966691732407,
|
|
"num_tokens": 20953733.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.375700569152832,
|
|
"epoch": 0.9518042098229201,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004915427285412636,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.1801777586340904,
|
|
"num_tokens": 20962413.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.241631650924683,
|
|
"epoch": 0.9522218509856332,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004915346413206555,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.2037292703986168,
|
|
"num_tokens": 20971172.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.231201124191284,
|
|
"epoch": 0.9526394921483461,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004915265503093478,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.1976637974381447,
|
|
"num_tokens": 20979450.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.260703754425049,
|
|
"epoch": 0.9530571333110591,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004915184555074824,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.18479856103658676,
|
|
"num_tokens": 20988518.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.44167914390564,
|
|
"epoch": 0.9534747744737722,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004915103569152005,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.18017488569021226,
|
|
"num_tokens": 20998721.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.3801109313964846,
|
|
"epoch": 0.9538924156364851,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004915022545326444,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.1904640778899193,
|
|
"num_tokens": 21008007.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.293911361694336,
|
|
"epoch": 0.9543100567991981,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004914941483599558,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.18404674232006074,
|
|
"num_tokens": 21017199.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.188850021362304,
|
|
"epoch": 0.9547276979619111,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004914860383972763,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.19653122425079345,
|
|
"num_tokens": 21025571.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.330324983596801,
|
|
"epoch": 0.9551453391246241,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004914779246447483,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.19278790205717086,
|
|
"num_tokens": 21035040.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.365421342849731,
|
|
"epoch": 0.9555629802873371,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004914698071025136,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.19380325675010682,
|
|
"num_tokens": 21044018.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.254361629486084,
|
|
"epoch": 0.9559806214500501,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004914616857707143,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.19683144390583038,
|
|
"num_tokens": 21052489.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.305207538604736,
|
|
"epoch": 0.9563982626127631,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004914535606494927,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.19891838133335113,
|
|
"num_tokens": 21061153.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.240456485748291,
|
|
"epoch": 0.9568159037754761,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000491445431738991,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.1911842942237854,
|
|
"num_tokens": 21069671.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.408563566207886,
|
|
"epoch": 0.9572335449381891,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004914372990393515,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.17980122417211533,
|
|
"num_tokens": 21079339.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.296997117996216,
|
|
"epoch": 0.957651186100902,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004914291625507164,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.19713663309812546,
|
|
"num_tokens": 21087868.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.303809928894043,
|
|
"epoch": 0.9580688272636151,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004914210222732284,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.19415508657693864,
|
|
"num_tokens": 21096258.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.257193231582642,
|
|
"epoch": 0.9584864684263281,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004914128782070299,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.18823350816965104,
|
|
"num_tokens": 21104504.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.261191463470459,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004914047303522636,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.19104788154363633,
|
|
"num_tokens": 21114402.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.26935601234436,
|
|
"epoch": 0.9593217507517541,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004913965787090718,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.19183927476406099,
|
|
"num_tokens": 21123572.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.382525205612183,
|
|
"epoch": 0.9597393919144671,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004913884232775974,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.1748875617980957,
|
|
"num_tokens": 21132385.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.203315162658692,
|
|
"epoch": 0.96015703307718,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004913802640579833,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.19596102833747864,
|
|
"num_tokens": 21140383.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.394109916687012,
|
|
"epoch": 0.9605746742398931,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004913721010503722,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.18963964134454728,
|
|
"num_tokens": 21149793.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.343473768234253,
|
|
"epoch": 0.9609923154026061,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000491363934254907,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.18909443020820618,
|
|
"num_tokens": 21158955.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.326027345657349,
|
|
"epoch": 0.961409956565319,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004913557636717307,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.18643326908349991,
|
|
"num_tokens": 21167900.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.24142804145813,
|
|
"epoch": 0.9618275977280321,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004913475893009864,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.19366782605648042,
|
|
"num_tokens": 21177243.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.299542379379273,
|
|
"epoch": 0.9622452388907451,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000491339411142817,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.19068634510040283,
|
|
"num_tokens": 21186118.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.347597646713257,
|
|
"epoch": 0.962662880053458,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004913312291973659,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.18620602041482925,
|
|
"num_tokens": 21195032.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.380717658996582,
|
|
"epoch": 0.963080521216171,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004913230434647762,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.1849704220890999,
|
|
"num_tokens": 21205388.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.302324724197388,
|
|
"epoch": 0.9634981623788841,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004913148539451912,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.19199014604091644,
|
|
"num_tokens": 21215181.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.189516878128051,
|
|
"epoch": 0.963915803541597,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004913066606387544,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.19661485999822617,
|
|
"num_tokens": 21223668.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.189825487136841,
|
|
"epoch": 0.96433344470431,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000491298463545609,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.18589077442884444,
|
|
"num_tokens": 21232448.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.2891865253448485,
|
|
"epoch": 0.9647510858670231,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004912902626658988,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.19474891871213912,
|
|
"num_tokens": 21240777.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.354679107666016,
|
|
"epoch": 0.965168727029736,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004912820579997672,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.18303453028202057,
|
|
"num_tokens": 21248803.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.3409021377563475,
|
|
"epoch": 0.965586368192449,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004912738495473577,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.1852123960852623,
|
|
"num_tokens": 21257861.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.314940071105957,
|
|
"epoch": 0.9660040093551621,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004912656373088142,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.20077644139528275,
|
|
"num_tokens": 21267140.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.28928689956665,
|
|
"epoch": 0.9664216505178751,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004912574212842804,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.1886407658457756,
|
|
"num_tokens": 21276313.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.23785252571106,
|
|
"epoch": 0.966839291680588,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004912492014739001,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.19174057245254517,
|
|
"num_tokens": 21286156.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.362173986434937,
|
|
"epoch": 0.967256932843301,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004912409778778173,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.19431511759757997,
|
|
"num_tokens": 21295420.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.403459548950195,
|
|
"epoch": 0.9676745740060141,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004912327504961758,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.18076042234897613,
|
|
"num_tokens": 21306292.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.322366619110108,
|
|
"epoch": 0.968092215168727,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004912245193291198,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.18871198445558549,
|
|
"num_tokens": 21315165.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.335630273818969,
|
|
"epoch": 0.96850985633144,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004912162843767932,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.18643238097429277,
|
|
"num_tokens": 21324608.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.315397024154663,
|
|
"epoch": 0.9689274974941531,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004912080456393404,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.18949589729309083,
|
|
"num_tokens": 21333609.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.347077798843384,
|
|
"epoch": 0.969345138656866,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004911998031169056,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.18186257034540176,
|
|
"num_tokens": 21344397.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.331781530380249,
|
|
"epoch": 0.969762779819579,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004911915568096328,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.1849284753203392,
|
|
"num_tokens": 21354111.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.214372158050537,
|
|
"epoch": 0.9701804209822921,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004911833067176666,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.19430746287107467,
|
|
"num_tokens": 21362807.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.325587177276612,
|
|
"epoch": 0.970598062145005,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004911750528411515,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.1845437690615654,
|
|
"num_tokens": 21372609.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.27841272354126,
|
|
"epoch": 0.971015703307718,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004911667951802318,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.18883326947689055,
|
|
"num_tokens": 21381182.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.225793695449829,
|
|
"epoch": 0.9714333444704311,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004911585337350524,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.196099953353405,
|
|
"num_tokens": 21389930.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.333341789245606,
|
|
"epoch": 0.971850985633144,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004911502685057573,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.18482903987169266,
|
|
"num_tokens": 21399315.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.329329252243042,
|
|
"epoch": 0.972268626795857,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004911419994924918,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.18919351249933242,
|
|
"num_tokens": 21408857.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.29211835861206,
|
|
"epoch": 0.97268626795857,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004911337266954004,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.19436143785715104,
|
|
"num_tokens": 21417452.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.260520315170288,
|
|
"epoch": 0.973103909121283,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004911254501146279,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.19158775210380555,
|
|
"num_tokens": 21427315.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.3140082359313965,
|
|
"epoch": 0.973521550283996,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004911171697503193,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.1894884452223778,
|
|
"num_tokens": 21437080.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.281603193283081,
|
|
"epoch": 0.973939191446709,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004911088856026194,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.2041848510503769,
|
|
"num_tokens": 21445421.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.306150197982788,
|
|
"epoch": 0.974356832609422,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004911005976716734,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.19587866216897964,
|
|
"num_tokens": 21454684.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.159938526153565,
|
|
"epoch": 0.974774473772135,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004910923059576264,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.19672162532806398,
|
|
"num_tokens": 21464287.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.216953611373901,
|
|
"epoch": 0.975192114934848,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004910840104606234,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.1888881504535675,
|
|
"num_tokens": 21472835.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.312102174758911,
|
|
"epoch": 0.975609756097561,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004910757111808097,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.19668349921703338,
|
|
"num_tokens": 21482327.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.332135915756226,
|
|
"epoch": 0.976027397260274,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004910674081183305,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.1831653743982315,
|
|
"num_tokens": 21492257.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.208573675155639,
|
|
"epoch": 0.976445038422987,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004910591012733313,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.18686803430318832,
|
|
"num_tokens": 21501930.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.351539659500122,
|
|
"epoch": 0.9768626795857,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004910507906459575,
|
|
"loss": 5.1643,
|
|
"mean_token_accuracy": 0.18271103650331497,
|
|
"num_tokens": 21511924.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.38795576095581,
|
|
"epoch": 0.977280320748413,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004910424762363545,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.18678227066993713,
|
|
"num_tokens": 21522279.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.247772216796875,
|
|
"epoch": 0.977697961911126,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000491034158044668,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.18947492092847823,
|
|
"num_tokens": 21532016.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.293446969985962,
|
|
"epoch": 0.9781156030738389,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004910258360710434,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.18152908682823182,
|
|
"num_tokens": 21541952.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.299660634994507,
|
|
"epoch": 0.978533244236552,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004910175103156266,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.20440198630094528,
|
|
"num_tokens": 21550185.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.325966167449951,
|
|
"epoch": 0.978950885399265,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004910091807785632,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.19157318621873856,
|
|
"num_tokens": 21558891.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.286233568191529,
|
|
"epoch": 0.9793685265619779,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004910008474599991,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.1881268322467804,
|
|
"num_tokens": 21568808.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.3441784381866455,
|
|
"epoch": 0.979786167724691,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004909925103600801,
|
|
"loss": 5.2066,
|
|
"mean_token_accuracy": 0.182724791765213,
|
|
"num_tokens": 21578838.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.234168863296508,
|
|
"epoch": 0.980203808887404,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004909841694789523,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.19667238146066665,
|
|
"num_tokens": 21588008.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.287701797485352,
|
|
"epoch": 0.9806214500501169,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004909758248167616,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.18925960808992387,
|
|
"num_tokens": 21597036.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.349890089035034,
|
|
"epoch": 0.98103909121283,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004909674763736542,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.18791257888078688,
|
|
"num_tokens": 21606028.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.362050580978393,
|
|
"epoch": 0.981456732375543,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004909591241497761,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.19296300411224365,
|
|
"num_tokens": 21615377.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.435769844055176,
|
|
"epoch": 0.9818743735382559,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004909507681452736,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.17882558107376098,
|
|
"num_tokens": 21625751.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.416766548156739,
|
|
"epoch": 0.9822920147009689,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004909424083602929,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.18734355568885802,
|
|
"num_tokens": 21634825.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.399048328399658,
|
|
"epoch": 0.982709655863682,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004909340447949805,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.19860923737287522,
|
|
"num_tokens": 21644286.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.369190263748169,
|
|
"epoch": 0.9831272970263949,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004909256774494827,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.19318927228450775,
|
|
"num_tokens": 21653384.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.287894582748413,
|
|
"epoch": 0.9835449381891079,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000490917306323946,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.19105462729930878,
|
|
"num_tokens": 21662126.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.267673778533935,
|
|
"epoch": 0.983962579351821,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004909089314185169,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.18622952252626418,
|
|
"num_tokens": 21671940.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.209247636795044,
|
|
"epoch": 0.9843802205145339,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004909005527333421,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.1980053663253784,
|
|
"num_tokens": 21680928.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.254646968841553,
|
|
"epoch": 0.9847978616772469,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004908921702685683,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.18791358321905136,
|
|
"num_tokens": 21689712.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.310435771942139,
|
|
"epoch": 0.98521550283996,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004908837840243421,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.19554044753313066,
|
|
"num_tokens": 21698325.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.2651325225830075,
|
|
"epoch": 0.9856331440026729,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004908753940008105,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.19559344202280043,
|
|
"num_tokens": 21707607.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.1734973907470705,
|
|
"epoch": 0.9860507851653859,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004908670001981201,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.19553141593933104,
|
|
"num_tokens": 21715887.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.235254240036011,
|
|
"epoch": 0.986468426328099,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004908586026164182,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.19380661100149155,
|
|
"num_tokens": 21724992.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.3405735969543455,
|
|
"epoch": 0.9868860674908119,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004908502012558516,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.18751619160175323,
|
|
"num_tokens": 21734317.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.3303934097290036,
|
|
"epoch": 0.9873037086535249,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004908417961165674,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.18783560991287232,
|
|
"num_tokens": 21743014.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.33513298034668,
|
|
"epoch": 0.9877213498162379,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004908333871987126,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.19073102325201036,
|
|
"num_tokens": 21751058.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.371034145355225,
|
|
"epoch": 0.9881389909789509,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004908249745024347,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.18869234770536422,
|
|
"num_tokens": 21760549.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.293810033798218,
|
|
"epoch": 0.9885566321416639,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000490816558027881,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.1943634942173958,
|
|
"num_tokens": 21769873.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.346495151519775,
|
|
"epoch": 0.9889742733043769,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004908081377751985,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.19356146156787873,
|
|
"num_tokens": 21779036.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.422462463378906,
|
|
"epoch": 0.9893919144670899,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004907997137445347,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.18284029066562651,
|
|
"num_tokens": 21787671.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.393016958236695,
|
|
"epoch": 0.9898095556298029,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004907912859360373,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.1853944331407547,
|
|
"num_tokens": 21797269.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.389364719390869,
|
|
"epoch": 0.9902271967925159,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004907828543498536,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.18878703266382219,
|
|
"num_tokens": 21806738.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.315618324279785,
|
|
"epoch": 0.9906448379552288,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004907744189861313,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.1888543501496315,
|
|
"num_tokens": 21815612.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.297834730148315,
|
|
"epoch": 0.9910624791179419,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000490765979845018,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.19539257884025574,
|
|
"num_tokens": 21824222.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.372282075881958,
|
|
"epoch": 0.9914801202806549,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004907575369266617,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.19222169518470764,
|
|
"num_tokens": 21833929.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.306639719009399,
|
|
"epoch": 0.9918977614433678,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004907490902312099,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.18780184388160706,
|
|
"num_tokens": 21843261.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.365342092514038,
|
|
"epoch": 0.9923154026060809,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004907406397588106,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.18705663979053497,
|
|
"num_tokens": 21853004.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.315323257446289,
|
|
"epoch": 0.9927330437687939,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004907321855096117,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.18834714442491532,
|
|
"num_tokens": 21862628.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.276562643051148,
|
|
"epoch": 0.9931506849315068,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004907237274837613,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.19038716852664947,
|
|
"num_tokens": 21872041.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.309222984313965,
|
|
"epoch": 0.9935683260942199,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004907152656814072,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.18281338661909102,
|
|
"num_tokens": 21881834.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.4300117015838625,
|
|
"epoch": 0.9939859672569329,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004907068001026978,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.18365519046783446,
|
|
"num_tokens": 21892349.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.383771467208862,
|
|
"epoch": 0.9944036084196458,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004906983307477813,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.19515896290540696,
|
|
"num_tokens": 21901427.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.267907905578613,
|
|
"epoch": 0.9948212495823588,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004906898576168057,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.19798390865325927,
|
|
"num_tokens": 21910654.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.219382905960083,
|
|
"epoch": 0.9952388907450719,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004906813807099197,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.20003349632024764,
|
|
"num_tokens": 21919583.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.2093384742736815,
|
|
"epoch": 0.9956565319077848,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004906729000272714,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.1949403002858162,
|
|
"num_tokens": 21927843.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.280549144744873,
|
|
"epoch": 0.9960741730704978,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004906644155690095,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.19122098833322526,
|
|
"num_tokens": 21937269.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.496305274963379,
|
|
"epoch": 0.9964918142332109,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004906559273352823,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.18277825117111207,
|
|
"num_tokens": 21946965.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.353962135314942,
|
|
"epoch": 0.9969094553959238,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004906474353262386,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.18749611526727678,
|
|
"num_tokens": 21955957.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.250110530853272,
|
|
"epoch": 0.9973270965586368,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004906389395420269,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.19533012956380844,
|
|
"num_tokens": 21965643.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.307873106002807,
|
|
"epoch": 0.9977447377213499,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000490630439982796,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19904470890760423,
|
|
"num_tokens": 21974789.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.25768461227417,
|
|
"epoch": 0.9981623788840628,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004906219366486947,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.20398582220077516,
|
|
"num_tokens": 21983411.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.322871732711792,
|
|
"epoch": 0.9985800200467758,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004906134295398719,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.1877253919839859,
|
|
"num_tokens": 21992570.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.268395280838012,
|
|
"epoch": 0.9989976612094889,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004906049186564764,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.20317024737596512,
|
|
"num_tokens": 22001411.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.4146442890167235,
|
|
"epoch": 0.9994153023722018,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004905964039986574,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.1825779139995575,
|
|
"num_tokens": 22010882.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.368969488143921,
|
|
"epoch": 0.9998329435349148,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004905878855665637,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.18160374611616134,
|
|
"num_tokens": 22020885.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.37403244972229,
|
|
"epoch": 1.0002505846976277,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004905793633603446,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.19897338449954988,
|
|
"num_tokens": 22030278.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.339780664443969,
|
|
"epoch": 1.0006682258603408,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004905708373801492,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.18481556475162506,
|
|
"num_tokens": 22039601.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.226790142059326,
|
|
"epoch": 1.0010858670230538,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004905623076261269,
|
|
"loss": 5.0162,
|
|
"mean_token_accuracy": 0.19655622839927672,
|
|
"num_tokens": 22049158.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.328135681152344,
|
|
"epoch": 1.0015035081857668,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000490553774098427,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.18671782016754152,
|
|
"num_tokens": 22059278.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.360319375991821,
|
|
"epoch": 1.0019211493484799,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004905452367971986,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.1948260560631752,
|
|
"num_tokens": 22068415.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.3181774616241455,
|
|
"epoch": 1.0023387905111927,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004905366957225916,
|
|
"loss": 5.0707,
|
|
"mean_token_accuracy": 0.19402292519807815,
|
|
"num_tokens": 22077815.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0023387905111927,
|
|
"eval_entropy": 5.0716266818431395,
|
|
"eval_loss": 5.101118087768555,
|
|
"eval_mean_token_accuracy": 0.203080904427612,
|
|
"eval_num_tokens": 22077815.0,
|
|
"eval_runtime": 27.2587,
|
|
"eval_samples_per_second": 1385.357,
|
|
"eval_steps_per_second": 173.193,
|
|
"step": 12000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119720,
|
|
"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": 3.2678381832192e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|