99ae1ba0c6
Model: fpadovani/heb-hebr-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
66156 lines
1.8 MiB
66156 lines
1.8 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.531328589009578,
|
|
"eval_steps": 3000,
|
|
"global_step": 33000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 8.172043609619141,
|
|
"epoch": 0.0005350741077639254,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.9195,
|
|
"mean_token_accuracy": 0.06807812452316284,
|
|
"num_tokens": 10038.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 8.173345184326172,
|
|
"epoch": 0.0010701482155278507,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.9519,
|
|
"mean_token_accuracy": 0.06761166527867317,
|
|
"num_tokens": 21916.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 8.15230588912964,
|
|
"epoch": 0.0016052223232917758,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.8809,
|
|
"mean_token_accuracy": 0.07487182170152665,
|
|
"num_tokens": 33434.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 8.150416851043701,
|
|
"epoch": 0.0021402964310557014,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.9178,
|
|
"mean_token_accuracy": 0.07305535562336445,
|
|
"num_tokens": 44216.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 8.19902458190918,
|
|
"epoch": 0.0026753705388196263,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.9382,
|
|
"mean_token_accuracy": 0.07128040939569473,
|
|
"num_tokens": 54874.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 8.148491477966308,
|
|
"epoch": 0.0032104446465835517,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.939,
|
|
"mean_token_accuracy": 0.06835630089044571,
|
|
"num_tokens": 65085.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 8.145433521270752,
|
|
"epoch": 0.003745518754347477,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.8478,
|
|
"mean_token_accuracy": 0.07239970788359643,
|
|
"num_tokens": 75601.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 8.129260540008545,
|
|
"epoch": 0.004280592862111403,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.8539,
|
|
"mean_token_accuracy": 0.07086838148534298,
|
|
"num_tokens": 86193.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 8.110703659057616,
|
|
"epoch": 0.004815666969875327,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.868,
|
|
"mean_token_accuracy": 0.07200616635382176,
|
|
"num_tokens": 96957.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 8.097426462173463,
|
|
"epoch": 0.005350741077639253,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.8701,
|
|
"mean_token_accuracy": 0.07447938099503518,
|
|
"num_tokens": 108408.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 8.082033777236939,
|
|
"epoch": 0.005885815185403178,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.8899,
|
|
"mean_token_accuracy": 0.0776177041232586,
|
|
"num_tokens": 119273.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 8.075964164733886,
|
|
"epoch": 0.006420889293167103,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.8943,
|
|
"mean_token_accuracy": 0.07140903994441032,
|
|
"num_tokens": 130817.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 8.11206226348877,
|
|
"epoch": 0.006955963400931029,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.8565,
|
|
"mean_token_accuracy": 0.07345039658248424,
|
|
"num_tokens": 142599.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 8.122138023376465,
|
|
"epoch": 0.007491037508694954,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.9386,
|
|
"mean_token_accuracy": 0.07604096084833145,
|
|
"num_tokens": 153617.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 8.110438632965089,
|
|
"epoch": 0.00802611161645888,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.9032,
|
|
"mean_token_accuracy": 0.07372927628457546,
|
|
"num_tokens": 165280.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 8.064451265335084,
|
|
"epoch": 0.008561185724222806,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.9103,
|
|
"mean_token_accuracy": 0.07471717111766338,
|
|
"num_tokens": 176896.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 8.096488285064698,
|
|
"epoch": 0.00909625983198673,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.9333,
|
|
"mean_token_accuracy": 0.07502413280308247,
|
|
"num_tokens": 188000.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 8.13657898902893,
|
|
"epoch": 0.009631333939750655,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.9588,
|
|
"mean_token_accuracy": 0.0756196528673172,
|
|
"num_tokens": 199360.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 8.187862300872803,
|
|
"epoch": 0.01016640804751458,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.939,
|
|
"mean_token_accuracy": 0.07151137851178646,
|
|
"num_tokens": 210214.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 8.11329288482666,
|
|
"epoch": 0.010701482155278505,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.8869,
|
|
"mean_token_accuracy": 0.07601158879697323,
|
|
"num_tokens": 220567.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 8.091031312942505,
|
|
"epoch": 0.011236556263042432,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.8088,
|
|
"mean_token_accuracy": 0.08166341260075569,
|
|
"num_tokens": 230585.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 8.062711715698242,
|
|
"epoch": 0.011771630370806356,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.8571,
|
|
"mean_token_accuracy": 0.07631958648562431,
|
|
"num_tokens": 241996.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 8.094353532791137,
|
|
"epoch": 0.012306704478570282,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.9555,
|
|
"mean_token_accuracy": 0.07188590094447136,
|
|
"num_tokens": 253348.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 8.148624420166016,
|
|
"epoch": 0.012841778586334207,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.889,
|
|
"mean_token_accuracy": 0.07277357392013073,
|
|
"num_tokens": 264239.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 8.139824962615966,
|
|
"epoch": 0.013376852694098133,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.89,
|
|
"mean_token_accuracy": 0.07517567798495292,
|
|
"num_tokens": 274522.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 8.114822006225586,
|
|
"epoch": 0.013911926801862057,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.8113,
|
|
"mean_token_accuracy": 0.07706562504172325,
|
|
"num_tokens": 284492.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 8.067396926879884,
|
|
"epoch": 0.014447000909625984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8514,
|
|
"mean_token_accuracy": 0.07260387018322945,
|
|
"num_tokens": 294796.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 8.12016191482544,
|
|
"epoch": 0.014982075017389908,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.8603,
|
|
"mean_token_accuracy": 0.06997270435094834,
|
|
"num_tokens": 305252.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.123533344268798,
|
|
"epoch": 0.015517149125153834,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.8396,
|
|
"mean_token_accuracy": 0.07271061241626739,
|
|
"num_tokens": 315505.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.117444324493409,
|
|
"epoch": 0.01605222323291776,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.8922,
|
|
"mean_token_accuracy": 0.07951539009809494,
|
|
"num_tokens": 326997.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.110684204101563,
|
|
"epoch": 0.016587297340681685,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.875,
|
|
"mean_token_accuracy": 0.07424910478293896,
|
|
"num_tokens": 338089.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.073831605911256,
|
|
"epoch": 0.01712237144844561,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.8353,
|
|
"mean_token_accuracy": 0.07741920799016952,
|
|
"num_tokens": 348536.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.16912670135498,
|
|
"epoch": 0.017657445556209534,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.876,
|
|
"mean_token_accuracy": 0.07565471082925797,
|
|
"num_tokens": 359776.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.006576490402221,
|
|
"epoch": 0.01819251966397346,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.8271,
|
|
"mean_token_accuracy": 0.07974917851388455,
|
|
"num_tokens": 370810.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.157261371612549,
|
|
"epoch": 0.018727593771737387,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.8194,
|
|
"mean_token_accuracy": 0.0741695910692215,
|
|
"num_tokens": 381788.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.101666450500488,
|
|
"epoch": 0.01926266787950131,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.8579,
|
|
"mean_token_accuracy": 0.07514562532305717,
|
|
"num_tokens": 391984.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.0212833404541,
|
|
"epoch": 0.019797741987265235,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.8041,
|
|
"mean_token_accuracy": 0.0741691879928112,
|
|
"num_tokens": 403430.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.16499195098877,
|
|
"epoch": 0.02033281609502916,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.8366,
|
|
"mean_token_accuracy": 0.07594205625355244,
|
|
"num_tokens": 414467.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.895851373672485,
|
|
"epoch": 0.020867890202793088,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.8383,
|
|
"mean_token_accuracy": 0.0728034682571888,
|
|
"num_tokens": 425752.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.13976879119873,
|
|
"epoch": 0.02140296431055701,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.8465,
|
|
"mean_token_accuracy": 0.07538696676492691,
|
|
"num_tokens": 435908.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.162510967254638,
|
|
"epoch": 0.021938038418320937,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.8493,
|
|
"mean_token_accuracy": 0.07364911586046219,
|
|
"num_tokens": 446424.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.023038148880005,
|
|
"epoch": 0.022473112526084863,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.8633,
|
|
"mean_token_accuracy": 0.07611406669020652,
|
|
"num_tokens": 456854.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.120884990692138,
|
|
"epoch": 0.02300818663384879,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.8487,
|
|
"mean_token_accuracy": 0.07724661827087402,
|
|
"num_tokens": 467899.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.984131669998169,
|
|
"epoch": 0.023543260741612712,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.7948,
|
|
"mean_token_accuracy": 0.07440953776240349,
|
|
"num_tokens": 478683.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.137256622314453,
|
|
"epoch": 0.02407833484937664,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.8224,
|
|
"mean_token_accuracy": 0.07473525032401085,
|
|
"num_tokens": 488745.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.094204759597778,
|
|
"epoch": 0.024613408957140565,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.8853,
|
|
"mean_token_accuracy": 0.07554894238710404,
|
|
"num_tokens": 499448.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.142967748641968,
|
|
"epoch": 0.02514848306490449,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.8528,
|
|
"mean_token_accuracy": 0.07399334162473678,
|
|
"num_tokens": 510148.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.069922924041748,
|
|
"epoch": 0.025683557172668414,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.8017,
|
|
"mean_token_accuracy": 0.07167132794857026,
|
|
"num_tokens": 522093.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.040627574920654,
|
|
"epoch": 0.02621863128043234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.801,
|
|
"mean_token_accuracy": 0.07531477734446526,
|
|
"num_tokens": 532598.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.111019945144653,
|
|
"epoch": 0.026753705388196266,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.8009,
|
|
"mean_token_accuracy": 0.07633137851953506,
|
|
"num_tokens": 542652.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.048424530029298,
|
|
"epoch": 0.027288779495960192,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.8313,
|
|
"mean_token_accuracy": 0.07268497720360756,
|
|
"num_tokens": 552526.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.08319902420044,
|
|
"epoch": 0.027823853603724115,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.855,
|
|
"mean_token_accuracy": 0.07812338769435882,
|
|
"num_tokens": 563143.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.129153060913087,
|
|
"epoch": 0.02835892771148804,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.8048,
|
|
"mean_token_accuracy": 0.07328564301133156,
|
|
"num_tokens": 573814.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.936620903015137,
|
|
"epoch": 0.028894001819251967,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.7963,
|
|
"mean_token_accuracy": 0.08088002502918243,
|
|
"num_tokens": 585367.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.25247220993042,
|
|
"epoch": 0.02942907592701589,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.8577,
|
|
"mean_token_accuracy": 0.07499300055205822,
|
|
"num_tokens": 595902.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.961127281188965,
|
|
"epoch": 0.029964150034779816,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.7677,
|
|
"mean_token_accuracy": 0.07093185968697072,
|
|
"num_tokens": 607178.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.058710098266602,
|
|
"epoch": 0.030499224142543743,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.7653,
|
|
"mean_token_accuracy": 0.07953990697860717,
|
|
"num_tokens": 618604.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.963685512542725,
|
|
"epoch": 0.03103429825030767,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.8304,
|
|
"mean_token_accuracy": 0.07993247732520103,
|
|
"num_tokens": 628111.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.22060260772705,
|
|
"epoch": 0.03156937235807159,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.8365,
|
|
"mean_token_accuracy": 0.08120491243898868,
|
|
"num_tokens": 639358.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.96451735496521,
|
|
"epoch": 0.03210444646583552,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.7261,
|
|
"mean_token_accuracy": 0.07790916599333286,
|
|
"num_tokens": 649504.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.008040952682496,
|
|
"epoch": 0.032639520573599444,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.7134,
|
|
"mean_token_accuracy": 0.07555579096078872,
|
|
"num_tokens": 659924.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.075908136367797,
|
|
"epoch": 0.03317459468136337,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.8166,
|
|
"mean_token_accuracy": 0.07576014548540115,
|
|
"num_tokens": 671120.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.010063886642456,
|
|
"epoch": 0.033709668789127296,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.8239,
|
|
"mean_token_accuracy": 0.07674261815845966,
|
|
"num_tokens": 681956.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.071939706802368,
|
|
"epoch": 0.03424474289689122,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.8005,
|
|
"mean_token_accuracy": 0.07449028007686138,
|
|
"num_tokens": 693226.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.040113973617554,
|
|
"epoch": 0.03477981700465514,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.813,
|
|
"mean_token_accuracy": 0.08225274756550789,
|
|
"num_tokens": 704691.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.035579442977905,
|
|
"epoch": 0.03531489111241907,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.787,
|
|
"mean_token_accuracy": 0.07182234078645706,
|
|
"num_tokens": 716000.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.042577505111694,
|
|
"epoch": 0.035849965220182994,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.7025,
|
|
"mean_token_accuracy": 0.08112649023532867,
|
|
"num_tokens": 726723.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.864040803909302,
|
|
"epoch": 0.03638503932794692,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.7372,
|
|
"mean_token_accuracy": 0.08113703206181526,
|
|
"num_tokens": 736740.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.075887537002563,
|
|
"epoch": 0.03692011343571085,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.7682,
|
|
"mean_token_accuracy": 0.07558154836297035,
|
|
"num_tokens": 747567.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.016151714324952,
|
|
"epoch": 0.03745518754347477,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.7141,
|
|
"mean_token_accuracy": 0.07801906056702138,
|
|
"num_tokens": 757937.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.936876964569092,
|
|
"epoch": 0.0379902616512387,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.7553,
|
|
"mean_token_accuracy": 0.07931130304932595,
|
|
"num_tokens": 768003.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.079256439208985,
|
|
"epoch": 0.03852533575900262,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.7858,
|
|
"mean_token_accuracy": 0.07208012118935585,
|
|
"num_tokens": 779098.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.9655650615692135,
|
|
"epoch": 0.039060409866766545,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.7239,
|
|
"mean_token_accuracy": 0.07492073476314545,
|
|
"num_tokens": 790002.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.07114543914795,
|
|
"epoch": 0.03959548397453047,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.7535,
|
|
"mean_token_accuracy": 0.07890913225710391,
|
|
"num_tokens": 800444.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.981046056747436,
|
|
"epoch": 0.0401305580822944,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.6963,
|
|
"mean_token_accuracy": 0.08140306100249291,
|
|
"num_tokens": 810912.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.970801067352295,
|
|
"epoch": 0.04066563219005832,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.7453,
|
|
"mean_token_accuracy": 0.07234299220144749,
|
|
"num_tokens": 822809.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.04731183052063,
|
|
"epoch": 0.04120070629782225,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.7301,
|
|
"mean_token_accuracy": 0.08183165267109871,
|
|
"num_tokens": 833362.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.919857549667358,
|
|
"epoch": 0.041735780405586176,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.7339,
|
|
"mean_token_accuracy": 0.07847344167530537,
|
|
"num_tokens": 844239.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.939679098129273,
|
|
"epoch": 0.0422708545133501,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.7468,
|
|
"mean_token_accuracy": 0.07599632740020752,
|
|
"num_tokens": 855178.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.02885913848877,
|
|
"epoch": 0.04280592862111402,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.7205,
|
|
"mean_token_accuracy": 0.07995647490024567,
|
|
"num_tokens": 866120.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.912197017669678,
|
|
"epoch": 0.04334100272887795,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.7431,
|
|
"mean_token_accuracy": 0.08108401894569398,
|
|
"num_tokens": 876569.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.096347093582153,
|
|
"epoch": 0.043876076836641874,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.7897,
|
|
"mean_token_accuracy": 0.07478848099708557,
|
|
"num_tokens": 887580.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.903347396850586,
|
|
"epoch": 0.0444111509444058,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.6753,
|
|
"mean_token_accuracy": 0.07557728588581085,
|
|
"num_tokens": 897922.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.95268235206604,
|
|
"epoch": 0.044946225052169726,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.6564,
|
|
"mean_token_accuracy": 0.08323289379477501,
|
|
"num_tokens": 908522.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.964509391784668,
|
|
"epoch": 0.04548129915993365,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.6832,
|
|
"mean_token_accuracy": 0.07836998216807842,
|
|
"num_tokens": 918253.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.942329549789429,
|
|
"epoch": 0.04601637326769758,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.7008,
|
|
"mean_token_accuracy": 0.08039597496390342,
|
|
"num_tokens": 929150.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.961909246444702,
|
|
"epoch": 0.0465514473754615,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.7507,
|
|
"mean_token_accuracy": 0.08034233450889587,
|
|
"num_tokens": 941041.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.871124219894409,
|
|
"epoch": 0.047086521483225424,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.6639,
|
|
"mean_token_accuracy": 0.08978669568896294,
|
|
"num_tokens": 952714.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.911958646774292,
|
|
"epoch": 0.04762159559098935,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.7413,
|
|
"mean_token_accuracy": 0.0767839141190052,
|
|
"num_tokens": 964330.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.94795036315918,
|
|
"epoch": 0.04815666969875328,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.6848,
|
|
"mean_token_accuracy": 0.07758989408612252,
|
|
"num_tokens": 975257.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.941993951797485,
|
|
"epoch": 0.0486917438065172,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.6847,
|
|
"mean_token_accuracy": 0.08070862591266632,
|
|
"num_tokens": 986335.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.828902101516723,
|
|
"epoch": 0.04922681791428113,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.6039,
|
|
"mean_token_accuracy": 0.08260082677006722,
|
|
"num_tokens": 997521.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.859019327163696,
|
|
"epoch": 0.049761892022045055,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.642,
|
|
"mean_token_accuracy": 0.07671640515327453,
|
|
"num_tokens": 1008383.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.908183193206787,
|
|
"epoch": 0.05029696612980898,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.7061,
|
|
"mean_token_accuracy": 0.08019287064671517,
|
|
"num_tokens": 1020552.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.827936267852783,
|
|
"epoch": 0.0508320402375729,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.6924,
|
|
"mean_token_accuracy": 0.07920794561505318,
|
|
"num_tokens": 1031127.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.8519299030303955,
|
|
"epoch": 0.05136711434533683,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.6252,
|
|
"mean_token_accuracy": 0.0852290503680706,
|
|
"num_tokens": 1043209.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.008257150650024,
|
|
"epoch": 0.05190218845310075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.7358,
|
|
"mean_token_accuracy": 0.07626549825072289,
|
|
"num_tokens": 1054032.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.757750940322876,
|
|
"epoch": 0.05243726256086468,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.5824,
|
|
"mean_token_accuracy": 0.08520738780498505,
|
|
"num_tokens": 1064565.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.949021720886231,
|
|
"epoch": 0.052972336668628606,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.7047,
|
|
"mean_token_accuracy": 0.08036523126065731,
|
|
"num_tokens": 1076352.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.884907054901123,
|
|
"epoch": 0.05350741077639253,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.6239,
|
|
"mean_token_accuracy": 0.0878230832517147,
|
|
"num_tokens": 1087697.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.8866808891296385,
|
|
"epoch": 0.05404248488415646,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.6108,
|
|
"mean_token_accuracy": 0.08426605761051179,
|
|
"num_tokens": 1098056.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.793342256546021,
|
|
"epoch": 0.054577558991920384,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.5685,
|
|
"mean_token_accuracy": 0.08895699828863143,
|
|
"num_tokens": 1109219.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.788063955307007,
|
|
"epoch": 0.055112633099684304,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.6909,
|
|
"mean_token_accuracy": 0.07860136553645133,
|
|
"num_tokens": 1120248.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.8371082782745365,
|
|
"epoch": 0.05564770720744823,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.6891,
|
|
"mean_token_accuracy": 0.08039635419845581,
|
|
"num_tokens": 1131278.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.913965082168579,
|
|
"epoch": 0.056182781315212156,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.6912,
|
|
"mean_token_accuracy": 0.07047672085464,
|
|
"num_tokens": 1143147.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.861634349822998,
|
|
"epoch": 0.05671785542297608,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.6163,
|
|
"mean_token_accuracy": 0.07919415943324566,
|
|
"num_tokens": 1154316.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.795156002044678,
|
|
"epoch": 0.05725292953074001,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.6284,
|
|
"mean_token_accuracy": 0.08119702488183975,
|
|
"num_tokens": 1164696.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.818248176574707,
|
|
"epoch": 0.057788003638503935,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.6079,
|
|
"mean_token_accuracy": 0.08769951537251472,
|
|
"num_tokens": 1176129.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.891226720809937,
|
|
"epoch": 0.05832307774626786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.6067,
|
|
"mean_token_accuracy": 0.0797014981508255,
|
|
"num_tokens": 1186499.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.75864052772522,
|
|
"epoch": 0.05885815185403178,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.6008,
|
|
"mean_token_accuracy": 0.078534334897995,
|
|
"num_tokens": 1196841.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.817751502990722,
|
|
"epoch": 0.059393225961795706,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.5394,
|
|
"mean_token_accuracy": 0.08645424395799636,
|
|
"num_tokens": 1207647.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.717403888702393,
|
|
"epoch": 0.05992830006955963,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.5438,
|
|
"mean_token_accuracy": 0.08563198633491993,
|
|
"num_tokens": 1217072.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.8630136013031,
|
|
"epoch": 0.06046337417732356,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.673,
|
|
"mean_token_accuracy": 0.07517069838941097,
|
|
"num_tokens": 1228564.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.755182695388794,
|
|
"epoch": 0.060998448285087485,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.6117,
|
|
"mean_token_accuracy": 0.08110473416745663,
|
|
"num_tokens": 1238755.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.747598361968994,
|
|
"epoch": 0.06153352239285141,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.5684,
|
|
"mean_token_accuracy": 0.08383116647601127,
|
|
"num_tokens": 1248968.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.79936990737915,
|
|
"epoch": 0.06206859650061534,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.5403,
|
|
"mean_token_accuracy": 0.08267647698521614,
|
|
"num_tokens": 1259256.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.712107229232788,
|
|
"epoch": 0.06260367060837926,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.5666,
|
|
"mean_token_accuracy": 0.08285431116819382,
|
|
"num_tokens": 1270469.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.765189361572266,
|
|
"epoch": 0.06313874471614318,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.5491,
|
|
"mean_token_accuracy": 0.08401528745889664,
|
|
"num_tokens": 1280558.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.807211065292359,
|
|
"epoch": 0.06367381882390712,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.6139,
|
|
"mean_token_accuracy": 0.08002614453434945,
|
|
"num_tokens": 1291372.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.829832220077515,
|
|
"epoch": 0.06420889293167104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.6538,
|
|
"mean_token_accuracy": 0.07477352321147919,
|
|
"num_tokens": 1302521.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.637760925292969,
|
|
"epoch": 0.06474396703943497,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.4977,
|
|
"mean_token_accuracy": 0.08267719894647599,
|
|
"num_tokens": 1313632.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.775080394744873,
|
|
"epoch": 0.06527904114719889,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.5881,
|
|
"mean_token_accuracy": 0.08696693032979966,
|
|
"num_tokens": 1325247.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.754818916320801,
|
|
"epoch": 0.06581411525496281,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.5746,
|
|
"mean_token_accuracy": 0.08667751327157021,
|
|
"num_tokens": 1336026.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.712781190872192,
|
|
"epoch": 0.06634918936272674,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.502,
|
|
"mean_token_accuracy": 0.08229328319430351,
|
|
"num_tokens": 1346920.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.714415168762207,
|
|
"epoch": 0.06688426347049066,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.6459,
|
|
"mean_token_accuracy": 0.08195903673768043,
|
|
"num_tokens": 1359752.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.818537712097168,
|
|
"epoch": 0.06741933757825459,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.6415,
|
|
"mean_token_accuracy": 0.08333790749311447,
|
|
"num_tokens": 1370874.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.740803337097168,
|
|
"epoch": 0.06795441168601851,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.5492,
|
|
"mean_token_accuracy": 0.0865517497062683,
|
|
"num_tokens": 1382316.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.679195737838745,
|
|
"epoch": 0.06848948579378245,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.5851,
|
|
"mean_token_accuracy": 0.07738500684499741,
|
|
"num_tokens": 1394656.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.756368350982666,
|
|
"epoch": 0.06902455990154636,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.5499,
|
|
"mean_token_accuracy": 0.08601778075098991,
|
|
"num_tokens": 1405061.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.646595811843872,
|
|
"epoch": 0.06955963400931028,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.5231,
|
|
"mean_token_accuracy": 0.08854705616831779,
|
|
"num_tokens": 1415573.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.6589337348937985,
|
|
"epoch": 0.07009470811707422,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.5524,
|
|
"mean_token_accuracy": 0.08328185752034187,
|
|
"num_tokens": 1426103.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.728953456878662,
|
|
"epoch": 0.07062978222483814,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.5573,
|
|
"mean_token_accuracy": 0.07903586179018021,
|
|
"num_tokens": 1437256.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.691567277908325,
|
|
"epoch": 0.07116485633260207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.521,
|
|
"mean_token_accuracy": 0.08464005514979363,
|
|
"num_tokens": 1446975.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.705724573135376,
|
|
"epoch": 0.07169993044036599,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.5353,
|
|
"mean_token_accuracy": 0.080365489423275,
|
|
"num_tokens": 1457751.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.651171350479126,
|
|
"epoch": 0.07223500454812992,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.5179,
|
|
"mean_token_accuracy": 0.08747594058513641,
|
|
"num_tokens": 1468186.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.646878385543824,
|
|
"epoch": 0.07277007865589384,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.5674,
|
|
"mean_token_accuracy": 0.08277356252074242,
|
|
"num_tokens": 1479780.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.6683413028717045,
|
|
"epoch": 0.07330515276365776,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.4726,
|
|
"mean_token_accuracy": 0.0866861030459404,
|
|
"num_tokens": 1490565.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.719349336624146,
|
|
"epoch": 0.0738402268714217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.5349,
|
|
"mean_token_accuracy": 0.08366219028830528,
|
|
"num_tokens": 1501552.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.626680374145508,
|
|
"epoch": 0.07437530097918561,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.5036,
|
|
"mean_token_accuracy": 0.07987239845097065,
|
|
"num_tokens": 1513311.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.682998895645142,
|
|
"epoch": 0.07491037508694955,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.5551,
|
|
"mean_token_accuracy": 0.08537785261869431,
|
|
"num_tokens": 1524142.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.614016437530518,
|
|
"epoch": 0.07544544919471347,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.5286,
|
|
"mean_token_accuracy": 0.08181034475564956,
|
|
"num_tokens": 1535571.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.77970175743103,
|
|
"epoch": 0.0759805233024774,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.5527,
|
|
"mean_token_accuracy": 0.08348672389984131,
|
|
"num_tokens": 1546528.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.565948343276977,
|
|
"epoch": 0.07651559741024132,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.5634,
|
|
"mean_token_accuracy": 0.0795982949435711,
|
|
"num_tokens": 1557264.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.680731344223022,
|
|
"epoch": 0.07705067151800524,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.4939,
|
|
"mean_token_accuracy": 0.0882859081029892,
|
|
"num_tokens": 1566773.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.545563220977783,
|
|
"epoch": 0.07758574562576917,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.4698,
|
|
"mean_token_accuracy": 0.09191560298204422,
|
|
"num_tokens": 1578173.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.6455999374389645,
|
|
"epoch": 0.07812081973353309,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.4611,
|
|
"mean_token_accuracy": 0.0855359174311161,
|
|
"num_tokens": 1588537.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.49965648651123,
|
|
"epoch": 0.07865589384129702,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.4594,
|
|
"mean_token_accuracy": 0.09296399280428887,
|
|
"num_tokens": 1599159.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.620386981964112,
|
|
"epoch": 0.07919096794906094,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.5168,
|
|
"mean_token_accuracy": 0.0834181286394596,
|
|
"num_tokens": 1610378.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.585515832901001,
|
|
"epoch": 0.07972604205682488,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.5421,
|
|
"mean_token_accuracy": 0.08486890234053135,
|
|
"num_tokens": 1621215.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.641656970977783,
|
|
"epoch": 0.0802611161645888,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.5105,
|
|
"mean_token_accuracy": 0.08722797259688378,
|
|
"num_tokens": 1631170.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.653715991973877,
|
|
"epoch": 0.08079619027235273,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.5106,
|
|
"mean_token_accuracy": 0.07990852892398834,
|
|
"num_tokens": 1641897.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.6051116466522215,
|
|
"epoch": 0.08133126438011665,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.5798,
|
|
"mean_token_accuracy": 0.08361625298857689,
|
|
"num_tokens": 1653592.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.5156501770019535,
|
|
"epoch": 0.08186633848788057,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.5134,
|
|
"mean_token_accuracy": 0.0794034518301487,
|
|
"num_tokens": 1665760.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.652586936950684,
|
|
"epoch": 0.0824014125956445,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.4808,
|
|
"mean_token_accuracy": 0.09275959730148316,
|
|
"num_tokens": 1676211.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.628318643569946,
|
|
"epoch": 0.08293648670340842,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.5125,
|
|
"mean_token_accuracy": 0.08556769341230393,
|
|
"num_tokens": 1686405.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.617849349975586,
|
|
"epoch": 0.08347156081117235,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.5086,
|
|
"mean_token_accuracy": 0.08250572569668294,
|
|
"num_tokens": 1697340.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.555404567718506,
|
|
"epoch": 0.08400663491893627,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.4003,
|
|
"mean_token_accuracy": 0.09449514746665955,
|
|
"num_tokens": 1707250.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.466612195968628,
|
|
"epoch": 0.0845417090267002,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.3975,
|
|
"mean_token_accuracy": 0.08475929126143456,
|
|
"num_tokens": 1718333.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.5835918426513675,
|
|
"epoch": 0.08507678313446412,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.4962,
|
|
"mean_token_accuracy": 0.0763777457177639,
|
|
"num_tokens": 1730520.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.55741515159607,
|
|
"epoch": 0.08561185724222804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.5552,
|
|
"mean_token_accuracy": 0.07963615767657757,
|
|
"num_tokens": 1741898.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.54046630859375,
|
|
"epoch": 0.08614693134999198,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.4987,
|
|
"mean_token_accuracy": 0.08333209455013275,
|
|
"num_tokens": 1751671.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.5205401420593265,
|
|
"epoch": 0.0866820054577559,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.5163,
|
|
"mean_token_accuracy": 0.0879331462085247,
|
|
"num_tokens": 1762076.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.609332609176636,
|
|
"epoch": 0.08721707956551983,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.4735,
|
|
"mean_token_accuracy": 0.08462397307157517,
|
|
"num_tokens": 1772666.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.601525020599365,
|
|
"epoch": 0.08775215367328375,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.5034,
|
|
"mean_token_accuracy": 0.08532712645828724,
|
|
"num_tokens": 1783621.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.5773783206939695,
|
|
"epoch": 0.08828722778104768,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.5739,
|
|
"mean_token_accuracy": 0.0806800290942192,
|
|
"num_tokens": 1794654.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.463850975036621,
|
|
"epoch": 0.0888223018888116,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.4682,
|
|
"mean_token_accuracy": 0.08854547813534737,
|
|
"num_tokens": 1805853.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.505795669555664,
|
|
"epoch": 0.08935737599657552,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.4489,
|
|
"mean_token_accuracy": 0.08519805371761321,
|
|
"num_tokens": 1817006.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.583885574340821,
|
|
"epoch": 0.08989245010433945,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.4355,
|
|
"mean_token_accuracy": 0.08483640179038048,
|
|
"num_tokens": 1827166.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.5850004196167,
|
|
"epoch": 0.09042752421210337,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.525,
|
|
"mean_token_accuracy": 0.07825911939144134,
|
|
"num_tokens": 1837182.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.491214847564697,
|
|
"epoch": 0.0909625983198673,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.4868,
|
|
"mean_token_accuracy": 0.08787625655531883,
|
|
"num_tokens": 1849034.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.437751960754395,
|
|
"epoch": 0.09149767242763122,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.3616,
|
|
"mean_token_accuracy": 0.09659026935696602,
|
|
"num_tokens": 1859033.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.510915803909302,
|
|
"epoch": 0.09203274653539516,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.4807,
|
|
"mean_token_accuracy": 0.08575069010257722,
|
|
"num_tokens": 1870274.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.390764904022217,
|
|
"epoch": 0.09256782064315908,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.4171,
|
|
"mean_token_accuracy": 0.09046047702431678,
|
|
"num_tokens": 1881306.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.484241676330567,
|
|
"epoch": 0.093102894750923,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.4006,
|
|
"mean_token_accuracy": 0.08314777314662933,
|
|
"num_tokens": 1892464.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.537802791595459,
|
|
"epoch": 0.09363796885868693,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.4881,
|
|
"mean_token_accuracy": 0.08111159168183804,
|
|
"num_tokens": 1903743.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.457689571380615,
|
|
"epoch": 0.09417304296645085,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.4545,
|
|
"mean_token_accuracy": 0.08882787078619003,
|
|
"num_tokens": 1915253.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.526367330551148,
|
|
"epoch": 0.09470811707421478,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.3926,
|
|
"mean_token_accuracy": 0.0867061398923397,
|
|
"num_tokens": 1926113.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.4687563419342045,
|
|
"epoch": 0.0952431911819787,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.5099,
|
|
"mean_token_accuracy": 0.08852507770061493,
|
|
"num_tokens": 1937718.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.511999654769897,
|
|
"epoch": 0.09577826528974263,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.5,
|
|
"mean_token_accuracy": 0.0858601987361908,
|
|
"num_tokens": 1948307.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.451641511917114,
|
|
"epoch": 0.09631333939750655,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.3121,
|
|
"mean_token_accuracy": 0.09499122053384781,
|
|
"num_tokens": 1957861.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.375934410095215,
|
|
"epoch": 0.09684841350527049,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.353,
|
|
"mean_token_accuracy": 0.09795267134904861,
|
|
"num_tokens": 1967984.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.425767183303833,
|
|
"epoch": 0.0973834876130344,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.344,
|
|
"mean_token_accuracy": 0.09382129013538361,
|
|
"num_tokens": 1978608.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.466197538375854,
|
|
"epoch": 0.09791856172079832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.3934,
|
|
"mean_token_accuracy": 0.08854326158761978,
|
|
"num_tokens": 1989355.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.344980144500733,
|
|
"epoch": 0.09845363582856226,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.3994,
|
|
"mean_token_accuracy": 0.09236646220088005,
|
|
"num_tokens": 1999754.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.47080078125,
|
|
"epoch": 0.09898870993632618,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.3879,
|
|
"mean_token_accuracy": 0.08912354037165642,
|
|
"num_tokens": 2010877.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.541212749481201,
|
|
"epoch": 0.09952378404409011,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.4925,
|
|
"mean_token_accuracy": 0.08468883112072945,
|
|
"num_tokens": 2022301.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.4023819923400875,
|
|
"epoch": 0.10005885815185403,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.3971,
|
|
"mean_token_accuracy": 0.08642457351088524,
|
|
"num_tokens": 2033537.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.3656556606292725,
|
|
"epoch": 0.10059393225961796,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.3013,
|
|
"mean_token_accuracy": 0.08984294459223748,
|
|
"num_tokens": 2044360.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.446710872650146,
|
|
"epoch": 0.10112900636738188,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.441,
|
|
"mean_token_accuracy": 0.08957641422748566,
|
|
"num_tokens": 2055000.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.370997333526612,
|
|
"epoch": 0.1016640804751458,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.4239,
|
|
"mean_token_accuracy": 0.09220219105482101,
|
|
"num_tokens": 2064807.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.488531112670898,
|
|
"epoch": 0.10219915458290973,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.3926,
|
|
"mean_token_accuracy": 0.08401189967989922,
|
|
"num_tokens": 2075618.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.366859388351441,
|
|
"epoch": 0.10273422869067365,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.3898,
|
|
"mean_token_accuracy": 0.08558554649353027,
|
|
"num_tokens": 2086226.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.435228681564331,
|
|
"epoch": 0.10326930279843759,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.3806,
|
|
"mean_token_accuracy": 0.08150073923170567,
|
|
"num_tokens": 2097222.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.409606075286865,
|
|
"epoch": 0.1038043769062015,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.422,
|
|
"mean_token_accuracy": 0.090543332695961,
|
|
"num_tokens": 2108919.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.371023559570313,
|
|
"epoch": 0.10433945101396544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.3811,
|
|
"mean_token_accuracy": 0.08817952051758766,
|
|
"num_tokens": 2120215.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.42234091758728,
|
|
"epoch": 0.10487452512172936,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.4002,
|
|
"mean_token_accuracy": 0.08778398633003234,
|
|
"num_tokens": 2131503.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.365479326248169,
|
|
"epoch": 0.10540959922949328,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.3376,
|
|
"mean_token_accuracy": 0.09631536826491356,
|
|
"num_tokens": 2141551.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.368793535232544,
|
|
"epoch": 0.10594467333725721,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.3454,
|
|
"mean_token_accuracy": 0.09466473385691643,
|
|
"num_tokens": 2151821.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.307546615600586,
|
|
"epoch": 0.10647974744502113,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.3927,
|
|
"mean_token_accuracy": 0.08924503847956658,
|
|
"num_tokens": 2162474.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.453886079788208,
|
|
"epoch": 0.10701482155278506,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.4497,
|
|
"mean_token_accuracy": 0.09008113294839859,
|
|
"num_tokens": 2173985.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.3950518608093265,
|
|
"epoch": 0.10754989566054898,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999999979210101,
|
|
"loss": 7.4669,
|
|
"mean_token_accuracy": 0.08625381216406822,
|
|
"num_tokens": 2186432.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.386218738555908,
|
|
"epoch": 0.10808496976831292,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999894751138,
|
|
"loss": 7.331,
|
|
"mean_token_accuracy": 0.08911918997764587,
|
|
"num_tokens": 2197085.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.326195859909058,
|
|
"epoch": 0.10862004387607684,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999745323744,
|
|
"loss": 7.3106,
|
|
"mean_token_accuracy": 0.09575477167963982,
|
|
"num_tokens": 2207162.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.389324140548706,
|
|
"epoch": 0.10915511798384077,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999999530927923,
|
|
"loss": 7.4269,
|
|
"mean_token_accuracy": 0.08239098042249679,
|
|
"num_tokens": 2218714.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.396574306488037,
|
|
"epoch": 0.10969019209160469,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999251563682,
|
|
"loss": 7.3741,
|
|
"mean_token_accuracy": 0.08852500319480897,
|
|
"num_tokens": 2229711.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.334770202636719,
|
|
"epoch": 0.11022526619936861,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999998907231029,
|
|
"loss": 7.368,
|
|
"mean_token_accuracy": 0.08981707468628883,
|
|
"num_tokens": 2239885.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.3592136859893795,
|
|
"epoch": 0.11076034030713254,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999998497929974,
|
|
"loss": 7.3731,
|
|
"mean_token_accuracy": 0.08999298885464668,
|
|
"num_tokens": 2250221.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.336800050735474,
|
|
"epoch": 0.11129541441489646,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999998023660527,
|
|
"loss": 7.4528,
|
|
"mean_token_accuracy": 0.0816170632839203,
|
|
"num_tokens": 2261059.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.3705222606658936,
|
|
"epoch": 0.11183048852266039,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999997484422705,
|
|
"loss": 7.2994,
|
|
"mean_token_accuracy": 0.09296035394072533,
|
|
"num_tokens": 2271174.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.307314395904541,
|
|
"epoch": 0.11236556263042431,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999996880216521,
|
|
"loss": 7.402,
|
|
"mean_token_accuracy": 0.08877327442169189,
|
|
"num_tokens": 2282431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.3447693347930905,
|
|
"epoch": 0.11290063673818825,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999996211041994,
|
|
"loss": 7.3696,
|
|
"mean_token_accuracy": 0.09118950441479683,
|
|
"num_tokens": 2292891.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.394657135009766,
|
|
"epoch": 0.11343571084595216,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999995476899141,
|
|
"loss": 7.3946,
|
|
"mean_token_accuracy": 0.08678853958845138,
|
|
"num_tokens": 2303764.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.24360089302063,
|
|
"epoch": 0.11397078495371608,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999994677787987,
|
|
"loss": 7.306,
|
|
"mean_token_accuracy": 0.09111010134220124,
|
|
"num_tokens": 2314172.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.3992757320404055,
|
|
"epoch": 0.11450585906148002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993813708551,
|
|
"loss": 7.2911,
|
|
"mean_token_accuracy": 0.09467030167579651,
|
|
"num_tokens": 2324848.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.23645977973938,
|
|
"epoch": 0.11504093316924394,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499999288466086,
|
|
"loss": 7.3134,
|
|
"mean_token_accuracy": 0.08993211090564728,
|
|
"num_tokens": 2336601.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.271498298645019,
|
|
"epoch": 0.11557600727700787,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999991890644941,
|
|
"loss": 7.2982,
|
|
"mean_token_accuracy": 0.08822696208953858,
|
|
"num_tokens": 2347281.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.264888286590576,
|
|
"epoch": 0.11611108138477179,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999990831660822,
|
|
"loss": 7.3075,
|
|
"mean_token_accuracy": 0.09646312147378922,
|
|
"num_tokens": 2358199.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.390944719314575,
|
|
"epoch": 0.11664615549253572,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999989707708534,
|
|
"loss": 7.3665,
|
|
"mean_token_accuracy": 0.08797665126621723,
|
|
"num_tokens": 2369092.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.266194009780884,
|
|
"epoch": 0.11718122960029964,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999988518788111,
|
|
"loss": 7.346,
|
|
"mean_token_accuracy": 0.09059268310666084,
|
|
"num_tokens": 2378849.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.295655584335327,
|
|
"epoch": 0.11771630370806356,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999987264899583,
|
|
"loss": 7.3429,
|
|
"mean_token_accuracy": 0.09276795759797096,
|
|
"num_tokens": 2389587.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.434128189086914,
|
|
"epoch": 0.1182513778158275,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499998594604299,
|
|
"loss": 7.3326,
|
|
"mean_token_accuracy": 0.08941550850868225,
|
|
"num_tokens": 2400442.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.190779304504394,
|
|
"epoch": 0.11878645192359141,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499998456221837,
|
|
"loss": 7.2916,
|
|
"mean_token_accuracy": 0.09264838397502899,
|
|
"num_tokens": 2410771.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.338149070739746,
|
|
"epoch": 0.11932152603135535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999983113425762,
|
|
"loss": 7.3261,
|
|
"mean_token_accuracy": 0.09488410204648971,
|
|
"num_tokens": 2421112.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.299089956283569,
|
|
"epoch": 0.11985660013911927,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999981599665207,
|
|
"loss": 7.3102,
|
|
"mean_token_accuracy": 0.0882981389760971,
|
|
"num_tokens": 2431891.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.262867403030396,
|
|
"epoch": 0.1203916742468832,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999980020936748,
|
|
"loss": 7.2716,
|
|
"mean_token_accuracy": 0.09344939067959786,
|
|
"num_tokens": 2442987.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.208923196792602,
|
|
"epoch": 0.12092674835464712,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999978377240434,
|
|
"loss": 7.2906,
|
|
"mean_token_accuracy": 0.09081464558839798,
|
|
"num_tokens": 2452703.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.347393655776978,
|
|
"epoch": 0.12146182246241104,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499997666857631,
|
|
"loss": 7.3421,
|
|
"mean_token_accuracy": 0.0911066085100174,
|
|
"num_tokens": 2462975.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.26486177444458,
|
|
"epoch": 0.12199689657017497,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999974894944426,
|
|
"loss": 7.2973,
|
|
"mean_token_accuracy": 0.08943878263235092,
|
|
"num_tokens": 2473853.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.349594688415527,
|
|
"epoch": 0.12253197067793889,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999973056344832,
|
|
"loss": 7.2744,
|
|
"mean_token_accuracy": 0.08951021954417229,
|
|
"num_tokens": 2485633.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.180385971069336,
|
|
"epoch": 0.12306704478570282,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999971152777583,
|
|
"loss": 7.2294,
|
|
"mean_token_accuracy": 0.08965703323483468,
|
|
"num_tokens": 2496922.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.369343852996826,
|
|
"epoch": 0.12360211889346674,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999969184242733,
|
|
"loss": 7.2917,
|
|
"mean_token_accuracy": 0.09407783150672913,
|
|
"num_tokens": 2507890.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.187175321578979,
|
|
"epoch": 0.12413719300123068,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499996715074034,
|
|
"loss": 7.2939,
|
|
"mean_token_accuracy": 0.09616836681962013,
|
|
"num_tokens": 2519749.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.24845552444458,
|
|
"epoch": 0.1246722671089946,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999965052270461,
|
|
"loss": 7.3137,
|
|
"mean_token_accuracy": 0.09240455776453019,
|
|
"num_tokens": 2530666.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.2619400978088375,
|
|
"epoch": 0.12520734121675853,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999962888833157,
|
|
"loss": 7.3139,
|
|
"mean_token_accuracy": 0.09363392889499664,
|
|
"num_tokens": 2541594.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.283105421066284,
|
|
"epoch": 0.12574241532452243,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999960660428491,
|
|
"loss": 7.2992,
|
|
"mean_token_accuracy": 0.09548846408724784,
|
|
"num_tokens": 2552330.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.361569499969482,
|
|
"epoch": 0.12627748943228637,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999958367056526,
|
|
"loss": 7.3528,
|
|
"mean_token_accuracy": 0.08479058220982552,
|
|
"num_tokens": 2564601.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.248473691940307,
|
|
"epoch": 0.1268125635400503,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499995600871733,
|
|
"loss": 7.3185,
|
|
"mean_token_accuracy": 0.09062025472521781,
|
|
"num_tokens": 2575539.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.264167356491089,
|
|
"epoch": 0.12734763764781423,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999953585410971,
|
|
"loss": 7.2642,
|
|
"mean_token_accuracy": 0.09182353541254998,
|
|
"num_tokens": 2586635.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.278759431838989,
|
|
"epoch": 0.12788271175557814,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999951097137518,
|
|
"loss": 7.2785,
|
|
"mean_token_accuracy": 0.09316747561097145,
|
|
"num_tokens": 2596814.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.198076295852661,
|
|
"epoch": 0.12841778586334207,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999948543897044,
|
|
"loss": 7.3038,
|
|
"mean_token_accuracy": 0.08896985203027725,
|
|
"num_tokens": 2608087.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.3914577007293705,
|
|
"epoch": 0.128952859971106,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999945925689621,
|
|
"loss": 7.3115,
|
|
"mean_token_accuracy": 0.09337142929434776,
|
|
"num_tokens": 2619377.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.158187961578369,
|
|
"epoch": 0.12948793407886994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999943242515325,
|
|
"loss": 7.2166,
|
|
"mean_token_accuracy": 0.09437886625528336,
|
|
"num_tokens": 2629089.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.2671790599823,
|
|
"epoch": 0.13002300818663384,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999940494374236,
|
|
"loss": 7.27,
|
|
"mean_token_accuracy": 0.09492316246032714,
|
|
"num_tokens": 2639743.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.342409324645996,
|
|
"epoch": 0.13055808229439778,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499993768126643,
|
|
"loss": 7.3257,
|
|
"mean_token_accuracy": 0.09084919095039368,
|
|
"num_tokens": 2650631.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.165309810638428,
|
|
"epoch": 0.1310931564021617,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499993480319199,
|
|
"loss": 7.266,
|
|
"mean_token_accuracy": 0.09525621384382248,
|
|
"num_tokens": 2660197.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.2947486400604244,
|
|
"epoch": 0.13162823050992561,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999931860150999,
|
|
"loss": 7.2486,
|
|
"mean_token_accuracy": 0.09175238981842995,
|
|
"num_tokens": 2670162.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.265993690490722,
|
|
"epoch": 0.13216330461768955,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999928852143541,
|
|
"loss": 7.246,
|
|
"mean_token_accuracy": 0.09490691721439362,
|
|
"num_tokens": 2681233.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.14599871635437,
|
|
"epoch": 0.13269837872545348,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999925779169703,
|
|
"loss": 7.229,
|
|
"mean_token_accuracy": 0.09406721666455269,
|
|
"num_tokens": 2692145.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.240669584274292,
|
|
"epoch": 0.13323345283321741,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999922641229575,
|
|
"loss": 7.2451,
|
|
"mean_token_accuracy": 0.0951724499464035,
|
|
"num_tokens": 2703192.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.287291526794434,
|
|
"epoch": 0.13376852694098132,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999919438323248,
|
|
"loss": 7.2557,
|
|
"mean_token_accuracy": 0.09338495507836342,
|
|
"num_tokens": 2714804.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.189889049530029,
|
|
"epoch": 0.13430360104874525,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999916170450812,
|
|
"loss": 7.2268,
|
|
"mean_token_accuracy": 0.09526428878307343,
|
|
"num_tokens": 2724340.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.2332368850708,
|
|
"epoch": 0.13483867515650919,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999912837612364,
|
|
"loss": 7.2267,
|
|
"mean_token_accuracy": 0.09549205154180526,
|
|
"num_tokens": 2735767.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.299641370773315,
|
|
"epoch": 0.1353737492642731,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999909439807997,
|
|
"loss": 7.2781,
|
|
"mean_token_accuracy": 0.08812019154429436,
|
|
"num_tokens": 2747658.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.161581182479859,
|
|
"epoch": 0.13590882337203702,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999905977037813,
|
|
"loss": 7.1398,
|
|
"mean_token_accuracy": 0.09851738065481186,
|
|
"num_tokens": 2757901.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.185445737838745,
|
|
"epoch": 0.13644389747980096,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999902449301909,
|
|
"loss": 7.2005,
|
|
"mean_token_accuracy": 0.09269871562719345,
|
|
"num_tokens": 2768945.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.128801107406616,
|
|
"epoch": 0.1369789715875649,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999898856600387,
|
|
"loss": 7.1859,
|
|
"mean_token_accuracy": 0.10609000697731971,
|
|
"num_tokens": 2780276.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.273564100265503,
|
|
"epoch": 0.1375140456953288,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999895198933354,
|
|
"loss": 7.2574,
|
|
"mean_token_accuracy": 0.09712079018354416,
|
|
"num_tokens": 2791183.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.189338302612304,
|
|
"epoch": 0.13804911980309273,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999891476300911,
|
|
"loss": 7.1645,
|
|
"mean_token_accuracy": 0.09277313947677612,
|
|
"num_tokens": 2801928.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.217353820800781,
|
|
"epoch": 0.13858419391085666,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499988768870317,
|
|
"loss": 7.2484,
|
|
"mean_token_accuracy": 0.08946470692753791,
|
|
"num_tokens": 2813415.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.241245889663697,
|
|
"epoch": 0.13911926801862057,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999883836140236,
|
|
"loss": 7.2526,
|
|
"mean_token_accuracy": 0.09227527827024459,
|
|
"num_tokens": 2825288.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.2402081966400145,
|
|
"epoch": 0.1396543421263845,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999879918612224,
|
|
"loss": 7.2119,
|
|
"mean_token_accuracy": 0.09847836419939995,
|
|
"num_tokens": 2836298.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.167675733566284,
|
|
"epoch": 0.14018941623414843,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999875936119245,
|
|
"loss": 7.1996,
|
|
"mean_token_accuracy": 0.09501123502850532,
|
|
"num_tokens": 2846367.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.157606840133667,
|
|
"epoch": 0.14072449034191237,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999871888661415,
|
|
"loss": 7.2085,
|
|
"mean_token_accuracy": 0.09355056807398796,
|
|
"num_tokens": 2856832.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.234083890914917,
|
|
"epoch": 0.14125956444967627,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499986777623885,
|
|
"loss": 7.2303,
|
|
"mean_token_accuracy": 0.08869453743100167,
|
|
"num_tokens": 2867954.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.287561988830566,
|
|
"epoch": 0.1417946385574402,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999863598851669,
|
|
"loss": 7.2555,
|
|
"mean_token_accuracy": 0.09643668159842492,
|
|
"num_tokens": 2878714.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.991106748580933,
|
|
"epoch": 0.14232971266520414,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999859356499992,
|
|
"loss": 7.1981,
|
|
"mean_token_accuracy": 0.10334166139364243,
|
|
"num_tokens": 2890697.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.246985292434692,
|
|
"epoch": 0.14286478677296804,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999855049183943,
|
|
"loss": 7.2216,
|
|
"mean_token_accuracy": 0.0913633793592453,
|
|
"num_tokens": 2901468.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.159916067123413,
|
|
"epoch": 0.14339986088073198,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999850676903646,
|
|
"loss": 7.1861,
|
|
"mean_token_accuracy": 0.09884981662034989,
|
|
"num_tokens": 2913466.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.178111553192139,
|
|
"epoch": 0.1439349349884959,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999846239659226,
|
|
"loss": 7.1578,
|
|
"mean_token_accuracy": 0.1024281658232212,
|
|
"num_tokens": 2923638.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.1597270488739015,
|
|
"epoch": 0.14447000909625984,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999841737450812,
|
|
"loss": 7.2306,
|
|
"mean_token_accuracy": 0.09842249751091003,
|
|
"num_tokens": 2934790.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.1113499164581295,
|
|
"epoch": 0.14500508320402375,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999837170278535,
|
|
"loss": 7.179,
|
|
"mean_token_accuracy": 0.09384954497218131,
|
|
"num_tokens": 2946320.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.278202247619629,
|
|
"epoch": 0.14554015731178768,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999832538142526,
|
|
"loss": 7.1427,
|
|
"mean_token_accuracy": 0.09324340000748635,
|
|
"num_tokens": 2957077.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.021162271499634,
|
|
"epoch": 0.14607523141955162,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999827841042917,
|
|
"loss": 7.1726,
|
|
"mean_token_accuracy": 0.0902546539902687,
|
|
"num_tokens": 2967286.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.243258142471314,
|
|
"epoch": 0.14661030552731552,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999823078979846,
|
|
"loss": 7.2087,
|
|
"mean_token_accuracy": 0.09563320577144623,
|
|
"num_tokens": 2979516.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.189844799041748,
|
|
"epoch": 0.14714537963507945,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999818251953449,
|
|
"loss": 7.3292,
|
|
"mean_token_accuracy": 0.09014673680067062,
|
|
"num_tokens": 2991594.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.227779912948608,
|
|
"epoch": 0.1476804537428434,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999813359963867,
|
|
"loss": 7.2036,
|
|
"mean_token_accuracy": 0.09412026777863503,
|
|
"num_tokens": 3002487.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.201776075363159,
|
|
"epoch": 0.14821552785060732,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999808403011241,
|
|
"loss": 7.2109,
|
|
"mean_token_accuracy": 0.0977674312889576,
|
|
"num_tokens": 3013197.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.144187164306641,
|
|
"epoch": 0.14875060195837123,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999803381095712,
|
|
"loss": 7.2453,
|
|
"mean_token_accuracy": 0.09458124712109565,
|
|
"num_tokens": 3024512.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.235658025741577,
|
|
"epoch": 0.14928567606613516,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999798294217428,
|
|
"loss": 7.2111,
|
|
"mean_token_accuracy": 0.09474866688251496,
|
|
"num_tokens": 3035621.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.163389682769775,
|
|
"epoch": 0.1498207501738991,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999793142376533,
|
|
"loss": 7.1779,
|
|
"mean_token_accuracy": 0.09404783025383949,
|
|
"num_tokens": 3046492.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.159232759475708,
|
|
"epoch": 0.150355824281663,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999787925573177,
|
|
"loss": 7.2202,
|
|
"mean_token_accuracy": 0.09497016146779061,
|
|
"num_tokens": 3057715.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.300630807876587,
|
|
"epoch": 0.15089089838942693,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999782643807513,
|
|
"loss": 7.1824,
|
|
"mean_token_accuracy": 0.09338649213314057,
|
|
"num_tokens": 3068344.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.0725761413574215,
|
|
"epoch": 0.15142597249719086,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999777297079689,
|
|
"loss": 7.157,
|
|
"mean_token_accuracy": 0.09506282061338425,
|
|
"num_tokens": 3079576.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.227912521362304,
|
|
"epoch": 0.1519610466049548,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999771885389863,
|
|
"loss": 7.1408,
|
|
"mean_token_accuracy": 0.09675386250019073,
|
|
"num_tokens": 3090201.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.07097864151001,
|
|
"epoch": 0.1524961207127187,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999766408738189,
|
|
"loss": 7.1071,
|
|
"mean_token_accuracy": 0.10306708961725235,
|
|
"num_tokens": 3099824.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.119161462783813,
|
|
"epoch": 0.15303119482048264,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999760867124827,
|
|
"loss": 7.1967,
|
|
"mean_token_accuracy": 0.09370788037776948,
|
|
"num_tokens": 3109948.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.2363121032714846,
|
|
"epoch": 0.15356626892824657,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999755260549937,
|
|
"loss": 7.1778,
|
|
"mean_token_accuracy": 0.10212581753730773,
|
|
"num_tokens": 3121492.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.081883907318115,
|
|
"epoch": 0.15410134303601047,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004999749589013677,
|
|
"loss": 6.9771,
|
|
"mean_token_accuracy": 0.11389621570706368,
|
|
"num_tokens": 3131990.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.00419282913208,
|
|
"epoch": 0.1546364171437744,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999743852516217,
|
|
"loss": 7.146,
|
|
"mean_token_accuracy": 0.09606294631958008,
|
|
"num_tokens": 3142567.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.194999074935913,
|
|
"epoch": 0.15517149125153834,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004999738051057717,
|
|
"loss": 7.1512,
|
|
"mean_token_accuracy": 0.09972617551684379,
|
|
"num_tokens": 3153083.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.111984634399414,
|
|
"epoch": 0.15570656535930227,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999732184638347,
|
|
"loss": 7.1537,
|
|
"mean_token_accuracy": 0.0935523934662342,
|
|
"num_tokens": 3163985.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.149391937255859,
|
|
"epoch": 0.15624163946706618,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999726253258278,
|
|
"loss": 7.1476,
|
|
"mean_token_accuracy": 0.09505921602249146,
|
|
"num_tokens": 3175259.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.14017391204834,
|
|
"epoch": 0.1567767135748301,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999720256917678,
|
|
"loss": 7.1135,
|
|
"mean_token_accuracy": 0.10178006291389466,
|
|
"num_tokens": 3185487.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.029543256759643,
|
|
"epoch": 0.15731178768259405,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999714195616723,
|
|
"loss": 7.0917,
|
|
"mean_token_accuracy": 0.10098810642957687,
|
|
"num_tokens": 3196200.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.233420753479004,
|
|
"epoch": 0.15784686179035795,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999708069355586,
|
|
"loss": 7.2247,
|
|
"mean_token_accuracy": 0.08620018288493156,
|
|
"num_tokens": 3207675.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.065043163299561,
|
|
"epoch": 0.15838193589812188,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999701878134445,
|
|
"loss": 7.0881,
|
|
"mean_token_accuracy": 0.09926359876990318,
|
|
"num_tokens": 3218117.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.1511718273162845,
|
|
"epoch": 0.15891701000588582,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999695621953477,
|
|
"loss": 7.1542,
|
|
"mean_token_accuracy": 0.10217127278447151,
|
|
"num_tokens": 3229208.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.146858739852905,
|
|
"epoch": 0.15945208411364975,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999689300812866,
|
|
"loss": 7.051,
|
|
"mean_token_accuracy": 0.10721841007471085,
|
|
"num_tokens": 3239586.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.119947052001953,
|
|
"epoch": 0.15998715822141366,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999682914712791,
|
|
"loss": 7.132,
|
|
"mean_token_accuracy": 0.10072574242949486,
|
|
"num_tokens": 3250103.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.145537424087524,
|
|
"epoch": 0.1605222323291776,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999676463653439,
|
|
"loss": 7.1263,
|
|
"mean_token_accuracy": 0.1042477697134018,
|
|
"num_tokens": 3261844.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.1070863723754885,
|
|
"epoch": 0.16105730643694152,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999669947634996,
|
|
"loss": 7.0823,
|
|
"mean_token_accuracy": 0.10051160603761673,
|
|
"num_tokens": 3272073.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.099180889129639,
|
|
"epoch": 0.16159238054470546,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999663366657647,
|
|
"loss": 7.0711,
|
|
"mean_token_accuracy": 0.09962419345974922,
|
|
"num_tokens": 3281725.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.10269718170166,
|
|
"epoch": 0.16212745465246936,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999656720721586,
|
|
"loss": 7.2146,
|
|
"mean_token_accuracy": 0.09675706773996354,
|
|
"num_tokens": 3292708.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.203677415847778,
|
|
"epoch": 0.1626625287602333,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999650009827004,
|
|
"loss": 7.2064,
|
|
"mean_token_accuracy": 0.09477584436535835,
|
|
"num_tokens": 3303548.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.078126525878906,
|
|
"epoch": 0.16319760286799723,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999643233974092,
|
|
"loss": 7.0705,
|
|
"mean_token_accuracy": 0.10342822223901749,
|
|
"num_tokens": 3314261.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.067970943450928,
|
|
"epoch": 0.16373267697576113,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999636393163049,
|
|
"loss": 7.0828,
|
|
"mean_token_accuracy": 0.10165008082985878,
|
|
"num_tokens": 3324833.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.004071617126465,
|
|
"epoch": 0.16426775108352507,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999629487394071,
|
|
"loss": 6.9848,
|
|
"mean_token_accuracy": 0.10750006660819053,
|
|
"num_tokens": 3334790.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.110624504089356,
|
|
"epoch": 0.164802825191289,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999622516667358,
|
|
"loss": 7.1113,
|
|
"mean_token_accuracy": 0.10276103839278221,
|
|
"num_tokens": 3345115.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.02404932975769,
|
|
"epoch": 0.16533789929905293,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499961548098311,
|
|
"loss": 7.0019,
|
|
"mean_token_accuracy": 0.10630428940057754,
|
|
"num_tokens": 3356187.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.009617757797241,
|
|
"epoch": 0.16587297340681684,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999608380341533,
|
|
"loss": 7.0332,
|
|
"mean_token_accuracy": 0.10402404069900513,
|
|
"num_tokens": 3367218.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.075384426116943,
|
|
"epoch": 0.16640804751458077,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999601214742829,
|
|
"loss": 7.1838,
|
|
"mean_token_accuracy": 0.09452657997608185,
|
|
"num_tokens": 3377557.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.236601543426514,
|
|
"epoch": 0.1669431216223447,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999593984187206,
|
|
"loss": 7.1688,
|
|
"mean_token_accuracy": 0.09885648638010025,
|
|
"num_tokens": 3387402.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.009947204589844,
|
|
"epoch": 0.1674781957301086,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999586688674872,
|
|
"loss": 7.0329,
|
|
"mean_token_accuracy": 0.10211480408906937,
|
|
"num_tokens": 3397924.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.1467907428741455,
|
|
"epoch": 0.16801326983787254,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499957932820604,
|
|
"loss": 7.1262,
|
|
"mean_token_accuracy": 0.09135372191667557,
|
|
"num_tokens": 3408622.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.128115224838257,
|
|
"epoch": 0.16854834394563648,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499957190278092,
|
|
"loss": 7.0847,
|
|
"mean_token_accuracy": 0.0968036450445652,
|
|
"num_tokens": 3419692.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.991016530990601,
|
|
"epoch": 0.1690834180534004,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999564412399728,
|
|
"loss": 7.1449,
|
|
"mean_token_accuracy": 0.09633105620741844,
|
|
"num_tokens": 3430986.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.10005898475647,
|
|
"epoch": 0.1696184921611643,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499955685706268,
|
|
"loss": 7.0656,
|
|
"mean_token_accuracy": 0.10031602829694748,
|
|
"num_tokens": 3442211.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.937238311767578,
|
|
"epoch": 0.17015356626892825,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999549236769993,
|
|
"loss": 7.0491,
|
|
"mean_token_accuracy": 0.10472746640443802,
|
|
"num_tokens": 3453585.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.097245359420777,
|
|
"epoch": 0.17068864037669218,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999541551521888,
|
|
"loss": 7.0967,
|
|
"mean_token_accuracy": 0.09863503649830818,
|
|
"num_tokens": 3464156.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.113105726242066,
|
|
"epoch": 0.17122371448445609,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999533801318587,
|
|
"loss": 7.1512,
|
|
"mean_token_accuracy": 0.09326506778597832,
|
|
"num_tokens": 3474853.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.1461693286895756,
|
|
"epoch": 0.17175878859222002,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999525986160313,
|
|
"loss": 7.1285,
|
|
"mean_token_accuracy": 0.10076401606202126,
|
|
"num_tokens": 3486841.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.064342927932739,
|
|
"epoch": 0.17229386269998395,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999518106047293,
|
|
"loss": 7.14,
|
|
"mean_token_accuracy": 0.09933508709073066,
|
|
"num_tokens": 3498735.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.0867256164550785,
|
|
"epoch": 0.17282893680774788,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999510160979754,
|
|
"loss": 7.1682,
|
|
"mean_token_accuracy": 0.0990536592900753,
|
|
"num_tokens": 3508829.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.060147380828857,
|
|
"epoch": 0.1733640109155118,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999502150957925,
|
|
"loss": 7.0744,
|
|
"mean_token_accuracy": 0.09967830777168274,
|
|
"num_tokens": 3519465.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.124733781814575,
|
|
"epoch": 0.17389908502327572,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999494075982037,
|
|
"loss": 7.05,
|
|
"mean_token_accuracy": 0.1039630189538002,
|
|
"num_tokens": 3530401.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.01870551109314,
|
|
"epoch": 0.17443415913103966,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999485936052324,
|
|
"loss": 7.1136,
|
|
"mean_token_accuracy": 0.10137991532683373,
|
|
"num_tokens": 3541136.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.156218004226685,
|
|
"epoch": 0.17496923323880356,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499947773116902,
|
|
"loss": 7.0954,
|
|
"mean_token_accuracy": 0.09797013625502586,
|
|
"num_tokens": 3552525.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.006080770492554,
|
|
"epoch": 0.1755043073465675,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999469461332365,
|
|
"loss": 7.0628,
|
|
"mean_token_accuracy": 0.1024592712521553,
|
|
"num_tokens": 3563028.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.124646234512329,
|
|
"epoch": 0.17603938145433143,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999461126542592,
|
|
"loss": 7.0201,
|
|
"mean_token_accuracy": 0.1019650749862194,
|
|
"num_tokens": 3573354.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.836950874328613,
|
|
"epoch": 0.17657445556209536,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999452726799947,
|
|
"loss": 7.01,
|
|
"mean_token_accuracy": 0.09837546199560165,
|
|
"num_tokens": 3585576.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.190705299377441,
|
|
"epoch": 0.17710952966985927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999444262104671,
|
|
"loss": 7.1133,
|
|
"mean_token_accuracy": 0.09539903774857521,
|
|
"num_tokens": 3596478.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.0374476432800295,
|
|
"epoch": 0.1776446037776232,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999435732457007,
|
|
"loss": 7.0623,
|
|
"mean_token_accuracy": 0.09882038906216621,
|
|
"num_tokens": 3608014.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.125629949569702,
|
|
"epoch": 0.17817967788538713,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999427137857203,
|
|
"loss": 7.1265,
|
|
"mean_token_accuracy": 0.09716841951012611,
|
|
"num_tokens": 3620120.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.016817283630371,
|
|
"epoch": 0.17871475199315104,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999418478305506,
|
|
"loss": 7.0394,
|
|
"mean_token_accuracy": 0.1033493585884571,
|
|
"num_tokens": 3632578.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.062435150146484,
|
|
"epoch": 0.17924982610091497,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999409753802167,
|
|
"loss": 7.0509,
|
|
"mean_token_accuracy": 0.10514670312404632,
|
|
"num_tokens": 3643245.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.039481115341187,
|
|
"epoch": 0.1797849002086789,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999400964347437,
|
|
"loss": 7.055,
|
|
"mean_token_accuracy": 0.10101916566491127,
|
|
"num_tokens": 3655832.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.071658515930176,
|
|
"epoch": 0.18031997431644284,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999392109941571,
|
|
"loss": 7.0264,
|
|
"mean_token_accuracy": 0.10084607303142548,
|
|
"num_tokens": 3666566.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.078416633605957,
|
|
"epoch": 0.18085504842420674,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999383190584822,
|
|
"loss": 7.077,
|
|
"mean_token_accuracy": 0.09968247041106224,
|
|
"num_tokens": 3677572.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.993009233474732,
|
|
"epoch": 0.18139012253197068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999374206277451,
|
|
"loss": 6.9841,
|
|
"mean_token_accuracy": 0.10505180954933166,
|
|
"num_tokens": 3687116.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.02902774810791,
|
|
"epoch": 0.1819251966397346,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999365157019717,
|
|
"loss": 7.1006,
|
|
"mean_token_accuracy": 0.10133999511599541,
|
|
"num_tokens": 3697961.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.110463190078735,
|
|
"epoch": 0.18246027074749852,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999356042811878,
|
|
"loss": 7.0024,
|
|
"mean_token_accuracy": 0.1060384027659893,
|
|
"num_tokens": 3708834.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.942103624343872,
|
|
"epoch": 0.18299534485526245,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049993468636542,
|
|
"loss": 7.0757,
|
|
"mean_token_accuracy": 0.10011870935559272,
|
|
"num_tokens": 3719835.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.059339475631714,
|
|
"epoch": 0.18353041896302638,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999337619546948,
|
|
"loss": 6.9647,
|
|
"mean_token_accuracy": 0.10536348894238472,
|
|
"num_tokens": 3730408.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.996431350708008,
|
|
"epoch": 0.18406549307079031,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999328310490387,
|
|
"loss": 7.0514,
|
|
"mean_token_accuracy": 0.10348244979977608,
|
|
"num_tokens": 3741257.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.094743442535401,
|
|
"epoch": 0.18460056717855422,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999318936484789,
|
|
"loss": 7.0466,
|
|
"mean_token_accuracy": 0.10182052180171013,
|
|
"num_tokens": 3752615.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.988143110275269,
|
|
"epoch": 0.18513564128631815,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999309497530422,
|
|
"loss": 7.0771,
|
|
"mean_token_accuracy": 0.09553842768073081,
|
|
"num_tokens": 3763656.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.9603125095367435,
|
|
"epoch": 0.1856707153940821,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999299993627558,
|
|
"loss": 7.0461,
|
|
"mean_token_accuracy": 0.10526920706033707,
|
|
"num_tokens": 3775257.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.999796199798584,
|
|
"epoch": 0.186205789501846,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999290424776475,
|
|
"loss": 7.0041,
|
|
"mean_token_accuracy": 0.10799972862005233,
|
|
"num_tokens": 3786094.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.1879129886627195,
|
|
"epoch": 0.18674086360960993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999280790977445,
|
|
"loss": 7.0932,
|
|
"mean_token_accuracy": 0.09330181926488876,
|
|
"num_tokens": 3796672.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.052556037902832,
|
|
"epoch": 0.18727593771737386,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499927109223075,
|
|
"loss": 7.0792,
|
|
"mean_token_accuracy": 0.10074590295553207,
|
|
"num_tokens": 3807910.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.00290265083313,
|
|
"epoch": 0.1878110118251378,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999261328536667,
|
|
"loss": 7.0367,
|
|
"mean_token_accuracy": 0.10434340015053749,
|
|
"num_tokens": 3820792.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.971473217010498,
|
|
"epoch": 0.1883460859329017,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999251499895479,
|
|
"loss": 6.9408,
|
|
"mean_token_accuracy": 0.10545228272676468,
|
|
"num_tokens": 3831126.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.043059158325195,
|
|
"epoch": 0.18888116004066563,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999241606307471,
|
|
"loss": 7.0742,
|
|
"mean_token_accuracy": 0.10196674540638924,
|
|
"num_tokens": 3841923.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.108615827560425,
|
|
"epoch": 0.18941623414842956,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999231647772927,
|
|
"loss": 6.9747,
|
|
"mean_token_accuracy": 0.10711026415228844,
|
|
"num_tokens": 3852504.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.88094048500061,
|
|
"epoch": 0.1899513082561935,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999221624292136,
|
|
"loss": 6.9834,
|
|
"mean_token_accuracy": 0.10533660650253296,
|
|
"num_tokens": 3862761.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.012593936920166,
|
|
"epoch": 0.1904863823639574,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999211535865385,
|
|
"loss": 6.9989,
|
|
"mean_token_accuracy": 0.10127102062106133,
|
|
"num_tokens": 3873662.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.945406341552735,
|
|
"epoch": 0.19102145647172133,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999201382492969,
|
|
"loss": 6.9436,
|
|
"mean_token_accuracy": 0.10270186215639114,
|
|
"num_tokens": 3884835.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.015659761428833,
|
|
"epoch": 0.19155653057948527,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999191164175178,
|
|
"loss": 7.0831,
|
|
"mean_token_accuracy": 0.10108552053570748,
|
|
"num_tokens": 3895073.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.105494022369385,
|
|
"epoch": 0.19209160468724917,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999180880912309,
|
|
"loss": 7.0455,
|
|
"mean_token_accuracy": 0.10267279669642448,
|
|
"num_tokens": 3905440.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.966555213928222,
|
|
"epoch": 0.1926266787950131,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999170532704657,
|
|
"loss": 7.0569,
|
|
"mean_token_accuracy": 0.09851616621017456,
|
|
"num_tokens": 3917135.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.071110677719116,
|
|
"epoch": 0.19316175290277704,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999160119552523,
|
|
"loss": 7.0492,
|
|
"mean_token_accuracy": 0.10489852800965309,
|
|
"num_tokens": 3928247.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.99960880279541,
|
|
"epoch": 0.19369682701054097,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999149641456206,
|
|
"loss": 7.0329,
|
|
"mean_token_accuracy": 0.10273249596357345,
|
|
"num_tokens": 3938609.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.065947103500366,
|
|
"epoch": 0.19423190111830488,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499913909841601,
|
|
"loss": 7.0113,
|
|
"mean_token_accuracy": 0.10417041927576065,
|
|
"num_tokens": 3949221.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.938427543640136,
|
|
"epoch": 0.1947669752260688,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999128490432238,
|
|
"loss": 6.9842,
|
|
"mean_token_accuracy": 0.09849274829030037,
|
|
"num_tokens": 3959475.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.9746458530426025,
|
|
"epoch": 0.19530204933383274,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999117817505196,
|
|
"loss": 6.9831,
|
|
"mean_token_accuracy": 0.11270087212324142,
|
|
"num_tokens": 3969638.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.9958281993865965,
|
|
"epoch": 0.19583712344159665,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999107079635194,
|
|
"loss": 7.0404,
|
|
"mean_token_accuracy": 0.10607995018362999,
|
|
"num_tokens": 3980543.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.199732780456543,
|
|
"epoch": 0.19637219754936058,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499909627682254,
|
|
"loss": 7.0771,
|
|
"mean_token_accuracy": 0.0923505112528801,
|
|
"num_tokens": 3993518.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.989639043807983,
|
|
"epoch": 0.19690727165712452,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999085409067549,
|
|
"loss": 7.0803,
|
|
"mean_token_accuracy": 0.09985442981123924,
|
|
"num_tokens": 4002940.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.968360519409179,
|
|
"epoch": 0.19744234576488845,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999074476370531,
|
|
"loss": 6.9977,
|
|
"mean_token_accuracy": 0.10686009526252746,
|
|
"num_tokens": 4013982.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.023968601226807,
|
|
"epoch": 0.19797741987265235,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999063478731805,
|
|
"loss": 6.9808,
|
|
"mean_token_accuracy": 0.11021318733692169,
|
|
"num_tokens": 4025607.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.987985277175904,
|
|
"epoch": 0.1985124939804163,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999052416151687,
|
|
"loss": 7.0426,
|
|
"mean_token_accuracy": 0.10169775560498237,
|
|
"num_tokens": 4037467.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.049751329421997,
|
|
"epoch": 0.19904756808818022,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999041288630496,
|
|
"loss": 7.0427,
|
|
"mean_token_accuracy": 0.10394901558756828,
|
|
"num_tokens": 4049146.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.08274736404419,
|
|
"epoch": 0.19958264219594413,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999030096168553,
|
|
"loss": 7.0763,
|
|
"mean_token_accuracy": 0.102626833319664,
|
|
"num_tokens": 4060500.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.0754108905792235,
|
|
"epoch": 0.20011771630370806,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999018838766182,
|
|
"loss": 7.0366,
|
|
"mean_token_accuracy": 0.10197209641337394,
|
|
"num_tokens": 4070553.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.014403486251831,
|
|
"epoch": 0.200652790411472,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499900751642371,
|
|
"loss": 6.9599,
|
|
"mean_token_accuracy": 0.11636236384510994,
|
|
"num_tokens": 4079653.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.94902081489563,
|
|
"epoch": 0.20118786451923593,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998996129141461,
|
|
"loss": 7.051,
|
|
"mean_token_accuracy": 0.10020570904016494,
|
|
"num_tokens": 4089912.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.10851526260376,
|
|
"epoch": 0.20172293862699983,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998984676919764,
|
|
"loss": 7.0157,
|
|
"mean_token_accuracy": 0.09695038646459579,
|
|
"num_tokens": 4100577.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.972286224365234,
|
|
"epoch": 0.20225801273476376,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998973159758952,
|
|
"loss": 7.0356,
|
|
"mean_token_accuracy": 0.10260565429925919,
|
|
"num_tokens": 4111752.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.941117143630981,
|
|
"epoch": 0.2027930868425277,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998961577659355,
|
|
"loss": 6.9848,
|
|
"mean_token_accuracy": 0.10373990684747696,
|
|
"num_tokens": 4122616.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.100810861587524,
|
|
"epoch": 0.2033281609502916,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998949930621309,
|
|
"loss": 7.1003,
|
|
"mean_token_accuracy": 0.10509847998619079,
|
|
"num_tokens": 4134275.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.981368684768677,
|
|
"epoch": 0.20386323505805554,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998938218645149,
|
|
"loss": 6.9822,
|
|
"mean_token_accuracy": 0.1013522982597351,
|
|
"num_tokens": 4146412.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.951316595077515,
|
|
"epoch": 0.20439830916581947,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998926441731215,
|
|
"loss": 6.9838,
|
|
"mean_token_accuracy": 0.10630400627851486,
|
|
"num_tokens": 4157592.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.005149888992309,
|
|
"epoch": 0.2049333832735834,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998914599879845,
|
|
"loss": 6.9695,
|
|
"mean_token_accuracy": 0.10409662276506423,
|
|
"num_tokens": 4168637.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.942488479614258,
|
|
"epoch": 0.2054684573813473,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998902693091382,
|
|
"loss": 7.0184,
|
|
"mean_token_accuracy": 0.10043711066246033,
|
|
"num_tokens": 4179951.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.960629844665528,
|
|
"epoch": 0.20600353148911124,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998890721366171,
|
|
"loss": 6.901,
|
|
"mean_token_accuracy": 0.10442391037940979,
|
|
"num_tokens": 4189895.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.995759773254394,
|
|
"epoch": 0.20653860559687517,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998878684704556,
|
|
"loss": 6.9624,
|
|
"mean_token_accuracy": 0.10788150206208229,
|
|
"num_tokens": 4199796.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.939257526397705,
|
|
"epoch": 0.20707367970463908,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998866583106884,
|
|
"loss": 6.9973,
|
|
"mean_token_accuracy": 0.10173572450876237,
|
|
"num_tokens": 4210428.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.1006691455841064,
|
|
"epoch": 0.207608753812403,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998854416573506,
|
|
"loss": 7.0458,
|
|
"mean_token_accuracy": 0.10577386990189552,
|
|
"num_tokens": 4221515.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.972071933746338,
|
|
"epoch": 0.20814382792016695,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998842185104772,
|
|
"loss": 7.076,
|
|
"mean_token_accuracy": 0.0994568184018135,
|
|
"num_tokens": 4232580.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.98147554397583,
|
|
"epoch": 0.20867890202793088,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998829888701036,
|
|
"loss": 6.9875,
|
|
"mean_token_accuracy": 0.11094516292214393,
|
|
"num_tokens": 4242871.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.048088407516479,
|
|
"epoch": 0.20921397613569478,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998817527362654,
|
|
"loss": 7.0105,
|
|
"mean_token_accuracy": 0.10091942846775055,
|
|
"num_tokens": 4253419.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.935594701766968,
|
|
"epoch": 0.20974905024345872,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998805101089982,
|
|
"loss": 6.9958,
|
|
"mean_token_accuracy": 0.10472249984741211,
|
|
"num_tokens": 4264327.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.0764631748199465,
|
|
"epoch": 0.21028412435122265,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998792609883378,
|
|
"loss": 6.9836,
|
|
"mean_token_accuracy": 0.1075375609099865,
|
|
"num_tokens": 4274568.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.949454212188721,
|
|
"epoch": 0.21081919845898656,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998780053743203,
|
|
"loss": 6.9532,
|
|
"mean_token_accuracy": 0.10796868503093719,
|
|
"num_tokens": 4284895.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.989071989059449,
|
|
"epoch": 0.2113542725667505,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998767432669822,
|
|
"loss": 7.0061,
|
|
"mean_token_accuracy": 0.10241716429591179,
|
|
"num_tokens": 4297258.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.966968584060669,
|
|
"epoch": 0.21188934667451442,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998754746663595,
|
|
"loss": 6.9211,
|
|
"mean_token_accuracy": 0.10538342818617821,
|
|
"num_tokens": 4308307.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.958605146408081,
|
|
"epoch": 0.21242442078227836,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998741995724892,
|
|
"loss": 6.9878,
|
|
"mean_token_accuracy": 0.10546612218022347,
|
|
"num_tokens": 4318801.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.953232145309448,
|
|
"epoch": 0.21295949489004226,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998729179854079,
|
|
"loss": 6.956,
|
|
"mean_token_accuracy": 0.10459589958190918,
|
|
"num_tokens": 4329531.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.934867906570434,
|
|
"epoch": 0.2134945689978062,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998716299051527,
|
|
"loss": 6.9678,
|
|
"mean_token_accuracy": 0.102861238270998,
|
|
"num_tokens": 4341203.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.94436354637146,
|
|
"epoch": 0.21402964310557013,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998703353317609,
|
|
"loss": 7.0201,
|
|
"mean_token_accuracy": 0.09982240498065949,
|
|
"num_tokens": 4352426.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.063230895996094,
|
|
"epoch": 0.21456471721333403,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998690342652697,
|
|
"loss": 6.9587,
|
|
"mean_token_accuracy": 0.11106750443577766,
|
|
"num_tokens": 4363413.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.919417858123779,
|
|
"epoch": 0.21509979132109797,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998677267057166,
|
|
"loss": 6.8834,
|
|
"mean_token_accuracy": 0.10697573572397232,
|
|
"num_tokens": 4373470.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.898576736450195,
|
|
"epoch": 0.2156348654288619,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998664126531397,
|
|
"loss": 6.956,
|
|
"mean_token_accuracy": 0.10943344607949257,
|
|
"num_tokens": 4384438.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.99608736038208,
|
|
"epoch": 0.21616993953662583,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998650921075766,
|
|
"loss": 6.9333,
|
|
"mean_token_accuracy": 0.10496605783700944,
|
|
"num_tokens": 4395100.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.930504083633423,
|
|
"epoch": 0.21670501364438974,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998637650690656,
|
|
"loss": 7.0482,
|
|
"mean_token_accuracy": 0.10081744119524956,
|
|
"num_tokens": 4407131.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.987749719619751,
|
|
"epoch": 0.21724008775215367,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499862431537645,
|
|
"loss": 6.8874,
|
|
"mean_token_accuracy": 0.10455133765935898,
|
|
"num_tokens": 4417701.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.9407751083374025,
|
|
"epoch": 0.2177751618599176,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998610915133533,
|
|
"loss": 6.9543,
|
|
"mean_token_accuracy": 0.0995742492377758,
|
|
"num_tokens": 4429309.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.948079586029053,
|
|
"epoch": 0.21831023596768154,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998597449962292,
|
|
"loss": 7.0144,
|
|
"mean_token_accuracy": 0.10309403762221336,
|
|
"num_tokens": 4440850.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.931986236572266,
|
|
"epoch": 0.21884531007544544,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998583919863115,
|
|
"loss": 6.9959,
|
|
"mean_token_accuracy": 0.10206221267580987,
|
|
"num_tokens": 4451995.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.9314284324646,
|
|
"epoch": 0.21938038418320938,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998570324836393,
|
|
"loss": 6.8959,
|
|
"mean_token_accuracy": 0.10956206992268562,
|
|
"num_tokens": 4461916.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.981660795211792,
|
|
"epoch": 0.2199154582909733,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499855666488252,
|
|
"loss": 6.9973,
|
|
"mean_token_accuracy": 0.10489473640918731,
|
|
"num_tokens": 4471603.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.026265430450439,
|
|
"epoch": 0.22045053239873721,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998542940001889,
|
|
"loss": 7.0251,
|
|
"mean_token_accuracy": 0.10392524302005768,
|
|
"num_tokens": 4483166.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.931446123123169,
|
|
"epoch": 0.22098560650650115,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998529150194895,
|
|
"loss": 6.9344,
|
|
"mean_token_accuracy": 0.1028307020664215,
|
|
"num_tokens": 4493824.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.929507732391357,
|
|
"epoch": 0.22152068061426508,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998515295461939,
|
|
"loss": 6.8511,
|
|
"mean_token_accuracy": 0.1250505678355694,
|
|
"num_tokens": 4505674.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.889703559875488,
|
|
"epoch": 0.22205575472202901,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499850137580342,
|
|
"loss": 6.942,
|
|
"mean_token_accuracy": 0.10855949223041535,
|
|
"num_tokens": 4516516.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.92522497177124,
|
|
"epoch": 0.22259082882979292,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998487391219739,
|
|
"loss": 6.92,
|
|
"mean_token_accuracy": 0.0990898996591568,
|
|
"num_tokens": 4527811.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.947738695144653,
|
|
"epoch": 0.22312590293755685,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998473341711301,
|
|
"loss": 6.8778,
|
|
"mean_token_accuracy": 0.10222716778516769,
|
|
"num_tokens": 4538988.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.9012058734893795,
|
|
"epoch": 0.22366097704532079,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998459227278512,
|
|
"loss": 6.9047,
|
|
"mean_token_accuracy": 0.10971350893378258,
|
|
"num_tokens": 4550049.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.96103801727295,
|
|
"epoch": 0.2241960511530847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998445047921777,
|
|
"loss": 7.0301,
|
|
"mean_token_accuracy": 0.1055637203156948,
|
|
"num_tokens": 4559784.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.954623889923096,
|
|
"epoch": 0.22473112526084862,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998430803641509,
|
|
"loss": 6.8853,
|
|
"mean_token_accuracy": 0.10650338679552078,
|
|
"num_tokens": 4569982.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.876595544815063,
|
|
"epoch": 0.22526619936861256,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998416494438118,
|
|
"loss": 6.8835,
|
|
"mean_token_accuracy": 0.1076424852013588,
|
|
"num_tokens": 4581117.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.9081587314605715,
|
|
"epoch": 0.2258012734763765,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998402120312014,
|
|
"loss": 6.9568,
|
|
"mean_token_accuracy": 0.11032719910144806,
|
|
"num_tokens": 4592012.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.976634693145752,
|
|
"epoch": 0.2263363475841404,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998387681263616,
|
|
"loss": 6.9954,
|
|
"mean_token_accuracy": 0.10546118691563607,
|
|
"num_tokens": 4602591.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.943795967102051,
|
|
"epoch": 0.22687142169190433,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499837317729334,
|
|
"loss": 6.9311,
|
|
"mean_token_accuracy": 0.10475296303629875,
|
|
"num_tokens": 4613418.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.856068897247314,
|
|
"epoch": 0.22740649579966826,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998358608401603,
|
|
"loss": 6.8447,
|
|
"mean_token_accuracy": 0.11353197693824768,
|
|
"num_tokens": 4625156.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.97535138130188,
|
|
"epoch": 0.22794156990743217,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499834397458883,
|
|
"loss": 6.8859,
|
|
"mean_token_accuracy": 0.11059412583708764,
|
|
"num_tokens": 4634523.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.910711145401001,
|
|
"epoch": 0.2284766440151961,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998329275855438,
|
|
"loss": 6.8784,
|
|
"mean_token_accuracy": 0.11305185407400131,
|
|
"num_tokens": 4646292.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.910568618774414,
|
|
"epoch": 0.22901171812296003,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998314512201855,
|
|
"loss": 6.87,
|
|
"mean_token_accuracy": 0.09877351820468902,
|
|
"num_tokens": 4656417.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.880194187164307,
|
|
"epoch": 0.22954679223072397,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998299683628507,
|
|
"loss": 6.8746,
|
|
"mean_token_accuracy": 0.10891946405172348,
|
|
"num_tokens": 4666933.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.9828877449035645,
|
|
"epoch": 0.23008186633848787,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998284790135821,
|
|
"loss": 7.0497,
|
|
"mean_token_accuracy": 0.09953607842326165,
|
|
"num_tokens": 4678482.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.981028890609741,
|
|
"epoch": 0.2306169404462518,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998269831724228,
|
|
"loss": 6.8943,
|
|
"mean_token_accuracy": 0.1074309766292572,
|
|
"num_tokens": 4688454.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.829613304138183,
|
|
"epoch": 0.23115201455401574,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004998254808394159,
|
|
"loss": 6.931,
|
|
"mean_token_accuracy": 0.1070957824587822,
|
|
"num_tokens": 4699545.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.053047943115234,
|
|
"epoch": 0.23168708866177964,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998239720146048,
|
|
"loss": 6.9387,
|
|
"mean_token_accuracy": 0.10415649190545082,
|
|
"num_tokens": 4711149.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.836380195617676,
|
|
"epoch": 0.23222216276954358,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998224566980332,
|
|
"loss": 6.9489,
|
|
"mean_token_accuracy": 0.10446546524763108,
|
|
"num_tokens": 4722651.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.930455112457276,
|
|
"epoch": 0.2327572368773075,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998209348897447,
|
|
"loss": 6.9384,
|
|
"mean_token_accuracy": 0.09837790131568909,
|
|
"num_tokens": 4733883.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.116912317276001,
|
|
"epoch": 0.23329231098507144,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998194065897833,
|
|
"loss": 6.9102,
|
|
"mean_token_accuracy": 0.10532031208276749,
|
|
"num_tokens": 4744517.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.833180570602417,
|
|
"epoch": 0.23382738509283535,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499817871798193,
|
|
"loss": 6.926,
|
|
"mean_token_accuracy": 0.1177787572145462,
|
|
"num_tokens": 4755481.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.943826532363891,
|
|
"epoch": 0.23436245920059928,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998163305150185,
|
|
"loss": 6.8539,
|
|
"mean_token_accuracy": 0.1105301819741726,
|
|
"num_tokens": 4765535.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.894761371612549,
|
|
"epoch": 0.23489753330836322,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998147827403038,
|
|
"loss": 6.9646,
|
|
"mean_token_accuracy": 0.104603161662817,
|
|
"num_tokens": 4777045.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.95879225730896,
|
|
"epoch": 0.23543260741612712,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499813228474094,
|
|
"loss": 6.8388,
|
|
"mean_token_accuracy": 0.11467055454850197,
|
|
"num_tokens": 4787958.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.825476264953613,
|
|
"epoch": 0.23596768152389105,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998116677164338,
|
|
"loss": 6.8831,
|
|
"mean_token_accuracy": 0.1111849419772625,
|
|
"num_tokens": 4798502.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.885318279266357,
|
|
"epoch": 0.236502755631655,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998101004673682,
|
|
"loss": 6.9021,
|
|
"mean_token_accuracy": 0.11082184463739395,
|
|
"num_tokens": 4809179.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.027739429473877,
|
|
"epoch": 0.23703782973941892,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998085267269426,
|
|
"loss": 6.9699,
|
|
"mean_token_accuracy": 0.10047761201858521,
|
|
"num_tokens": 4819803.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.962998962402343,
|
|
"epoch": 0.23757290384718283,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998069464952025,
|
|
"loss": 6.9336,
|
|
"mean_token_accuracy": 0.10305302366614341,
|
|
"num_tokens": 4831226.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.906156587600708,
|
|
"epoch": 0.23810797795494676,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998053597721932,
|
|
"loss": 6.9565,
|
|
"mean_token_accuracy": 0.10782697647809983,
|
|
"num_tokens": 4842168.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.957432651519776,
|
|
"epoch": 0.2386430520627107,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998037665579608,
|
|
"loss": 6.9202,
|
|
"mean_token_accuracy": 0.11156222894787789,
|
|
"num_tokens": 4852655.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.845734071731568,
|
|
"epoch": 0.2391781261704746,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998021668525513,
|
|
"loss": 6.8226,
|
|
"mean_token_accuracy": 0.11052219197154045,
|
|
"num_tokens": 4862164.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.954825830459595,
|
|
"epoch": 0.23971320027823853,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998005606560107,
|
|
"loss": 6.9551,
|
|
"mean_token_accuracy": 0.10994420796632767,
|
|
"num_tokens": 4874233.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.940128040313721,
|
|
"epoch": 0.24024827438600246,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997989479683856,
|
|
"loss": 6.9501,
|
|
"mean_token_accuracy": 0.10953364297747611,
|
|
"num_tokens": 4885948.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.895329713821411,
|
|
"epoch": 0.2407833484937664,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997973287897224,
|
|
"loss": 6.9204,
|
|
"mean_token_accuracy": 0.10798448026180267,
|
|
"num_tokens": 4897128.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.940074491500854,
|
|
"epoch": 0.2413184226015303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997957031200681,
|
|
"loss": 6.8887,
|
|
"mean_token_accuracy": 0.11226024478673935,
|
|
"num_tokens": 4907699.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.78710708618164,
|
|
"epoch": 0.24185349670929424,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997940709594692,
|
|
"loss": 6.8369,
|
|
"mean_token_accuracy": 0.10901893302798271,
|
|
"num_tokens": 4918772.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 7.022173166275024,
|
|
"epoch": 0.24238857081705817,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997924323079733,
|
|
"loss": 6.8807,
|
|
"mean_token_accuracy": 0.10904730930924415,
|
|
"num_tokens": 4930046.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.846764373779297,
|
|
"epoch": 0.24292364492482207,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997907871656273,
|
|
"loss": 6.9125,
|
|
"mean_token_accuracy": 0.11078384071588517,
|
|
"num_tokens": 4940609.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.931916522979736,
|
|
"epoch": 0.243458719032586,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997891355324791,
|
|
"loss": 6.9172,
|
|
"mean_token_accuracy": 0.10807178467512131,
|
|
"num_tokens": 4951339.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.923230695724487,
|
|
"epoch": 0.24399379314034994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997874774085761,
|
|
"loss": 6.8348,
|
|
"mean_token_accuracy": 0.10518774688243866,
|
|
"num_tokens": 4961083.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.841183996200561,
|
|
"epoch": 0.24452886724811387,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997858127939662,
|
|
"loss": 6.8342,
|
|
"mean_token_accuracy": 0.11167632862925529,
|
|
"num_tokens": 4971399.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.936826086044311,
|
|
"epoch": 0.24506394135587778,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997841416886976,
|
|
"loss": 6.9039,
|
|
"mean_token_accuracy": 0.10855253934860229,
|
|
"num_tokens": 4982429.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.965252494812011,
|
|
"epoch": 0.2455990154636417,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997824640928186,
|
|
"loss": 6.9709,
|
|
"mean_token_accuracy": 0.11127365306019783,
|
|
"num_tokens": 4993706.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.93140139579773,
|
|
"epoch": 0.24613408957140565,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997807800063774,
|
|
"loss": 6.856,
|
|
"mean_token_accuracy": 0.11392047181725502,
|
|
"num_tokens": 5005411.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.895580244064331,
|
|
"epoch": 0.24666916367916958,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499779089429423,
|
|
"loss": 6.9879,
|
|
"mean_token_accuracy": 0.10498436391353608,
|
|
"num_tokens": 5016011.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.937919092178345,
|
|
"epoch": 0.24720423778693348,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997773923620037,
|
|
"loss": 6.946,
|
|
"mean_token_accuracy": 0.10605266690254211,
|
|
"num_tokens": 5027841.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 7.0313104629516605,
|
|
"epoch": 0.24773931189469742,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997756888041689,
|
|
"loss": 6.9343,
|
|
"mean_token_accuracy": 0.10023647099733353,
|
|
"num_tokens": 5038640.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.847754049301147,
|
|
"epoch": 0.24827438600246135,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997739787559677,
|
|
"loss": 6.8665,
|
|
"mean_token_accuracy": 0.11019023731350899,
|
|
"num_tokens": 5050423.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.873458576202393,
|
|
"epoch": 0.24880946011022526,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997722622174494,
|
|
"loss": 6.9018,
|
|
"mean_token_accuracy": 0.10377348437905312,
|
|
"num_tokens": 5060654.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.909244632720947,
|
|
"epoch": 0.2493445342179892,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997705391886636,
|
|
"loss": 6.8115,
|
|
"mean_token_accuracy": 0.11297802552580834,
|
|
"num_tokens": 5070165.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.870820236206055,
|
|
"epoch": 0.24987960832575312,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997688096696601,
|
|
"loss": 6.8627,
|
|
"mean_token_accuracy": 0.10569036602973939,
|
|
"num_tokens": 5080937.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.823880338668824,
|
|
"epoch": 0.25041468243351706,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997670736604888,
|
|
"loss": 6.818,
|
|
"mean_token_accuracy": 0.11626443266868591,
|
|
"num_tokens": 5090955.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.957943868637085,
|
|
"epoch": 0.250949756541281,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997653311611998,
|
|
"loss": 6.9679,
|
|
"mean_token_accuracy": 0.10086922571063042,
|
|
"num_tokens": 5102201.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.938482141494751,
|
|
"epoch": 0.25148483064904487,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997635821718435,
|
|
"loss": 6.8881,
|
|
"mean_token_accuracy": 0.11047171801328659,
|
|
"num_tokens": 5112235.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.816356945037842,
|
|
"epoch": 0.2520199047568088,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004997618266924704,
|
|
"loss": 6.7549,
|
|
"mean_token_accuracy": 0.1067312315106392,
|
|
"num_tokens": 5122360.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.923428773880005,
|
|
"epoch": 0.25255497886457273,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499760064723131,
|
|
"loss": 6.9306,
|
|
"mean_token_accuracy": 0.10218076333403588,
|
|
"num_tokens": 5133084.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.894084119796753,
|
|
"epoch": 0.25309005297233667,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997582962638764,
|
|
"loss": 6.8677,
|
|
"mean_token_accuracy": 0.10082524418830871,
|
|
"num_tokens": 5144495.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.919527053833008,
|
|
"epoch": 0.2536251270801006,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997565213147575,
|
|
"loss": 6.8834,
|
|
"mean_token_accuracy": 0.10920164585113526,
|
|
"num_tokens": 5154824.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.910584592819214,
|
|
"epoch": 0.25416020118786453,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997547398758257,
|
|
"loss": 6.8554,
|
|
"mean_token_accuracy": 0.10880272537469864,
|
|
"num_tokens": 5165061.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.875441551208496,
|
|
"epoch": 0.25469527529562846,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997529519471323,
|
|
"loss": 6.8352,
|
|
"mean_token_accuracy": 0.11507040783762931,
|
|
"num_tokens": 5174964.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.84457483291626,
|
|
"epoch": 0.25523034940339234,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997511575287291,
|
|
"loss": 6.883,
|
|
"mean_token_accuracy": 0.10771025717258453,
|
|
"num_tokens": 5185458.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.926706743240357,
|
|
"epoch": 0.2557654235111563,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997493566206677,
|
|
"loss": 6.8622,
|
|
"mean_token_accuracy": 0.10995001047849655,
|
|
"num_tokens": 5196193.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.884949541091919,
|
|
"epoch": 0.2563004976189202,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997475492230003,
|
|
"loss": 6.9753,
|
|
"mean_token_accuracy": 0.10006448924541474,
|
|
"num_tokens": 5208541.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.940023374557495,
|
|
"epoch": 0.25683557172668414,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499745735335779,
|
|
"loss": 6.8102,
|
|
"mean_token_accuracy": 0.10769248157739639,
|
|
"num_tokens": 5218567.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.903067255020142,
|
|
"epoch": 0.2573706458344481,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997439149590561,
|
|
"loss": 6.9019,
|
|
"mean_token_accuracy": 0.11087262630462646,
|
|
"num_tokens": 5228293.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.8589808464050295,
|
|
"epoch": 0.257905719942212,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997420880928843,
|
|
"loss": 6.8513,
|
|
"mean_token_accuracy": 0.11243690699338912,
|
|
"num_tokens": 5238880.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.952676296234131,
|
|
"epoch": 0.25844079404997594,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997402547373162,
|
|
"loss": 6.9499,
|
|
"mean_token_accuracy": 0.10374770835041999,
|
|
"num_tokens": 5250104.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 7.00459303855896,
|
|
"epoch": 0.2589758681577399,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997384148924049,
|
|
"loss": 6.9771,
|
|
"mean_token_accuracy": 0.10417036786675453,
|
|
"num_tokens": 5260355.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.921153402328491,
|
|
"epoch": 0.25951094226550375,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997365685582035,
|
|
"loss": 6.9007,
|
|
"mean_token_accuracy": 0.10504551604390144,
|
|
"num_tokens": 5272117.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.933792638778686,
|
|
"epoch": 0.2600460163732677,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997347157347651,
|
|
"loss": 6.9844,
|
|
"mean_token_accuracy": 0.10128821805119514,
|
|
"num_tokens": 5284583.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.901539659500122,
|
|
"epoch": 0.2605810904810316,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997328564221435,
|
|
"loss": 6.766,
|
|
"mean_token_accuracy": 0.12240908816456794,
|
|
"num_tokens": 5295846.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.857765197753906,
|
|
"epoch": 0.26111616458879555,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997309906203922,
|
|
"loss": 6.9367,
|
|
"mean_token_accuracy": 0.10391849651932716,
|
|
"num_tokens": 5307802.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 7.027815103530884,
|
|
"epoch": 0.2616512386965595,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997291183295652,
|
|
"loss": 6.8509,
|
|
"mean_token_accuracy": 0.10834813043475151,
|
|
"num_tokens": 5318263.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.920684576034546,
|
|
"epoch": 0.2621863128043234,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997272395497164,
|
|
"loss": 6.909,
|
|
"mean_token_accuracy": 0.10439276918768883,
|
|
"num_tokens": 5328555.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.829323577880859,
|
|
"epoch": 0.26272138691208735,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997253542809002,
|
|
"loss": 6.8587,
|
|
"mean_token_accuracy": 0.10975515842437744,
|
|
"num_tokens": 5339954.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.98386926651001,
|
|
"epoch": 0.26325646101985123,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997234625231709,
|
|
"loss": 6.9196,
|
|
"mean_token_accuracy": 0.10977022200822831,
|
|
"num_tokens": 5350919.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.865667390823364,
|
|
"epoch": 0.26379153512761516,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997215642765832,
|
|
"loss": 6.8833,
|
|
"mean_token_accuracy": 0.11174416020512581,
|
|
"num_tokens": 5361844.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.927380132675171,
|
|
"epoch": 0.2643266092353791,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499719659541192,
|
|
"loss": 6.9123,
|
|
"mean_token_accuracy": 0.10714837461709976,
|
|
"num_tokens": 5372026.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.941423130035401,
|
|
"epoch": 0.26486168334314303,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997177483170521,
|
|
"loss": 6.9514,
|
|
"mean_token_accuracy": 0.10840447247028351,
|
|
"num_tokens": 5382965.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.8894938945770265,
|
|
"epoch": 0.26539675745090696,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997158306042188,
|
|
"loss": 6.9196,
|
|
"mean_token_accuracy": 0.10659607201814651,
|
|
"num_tokens": 5393738.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.842194032669068,
|
|
"epoch": 0.2659318315586709,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997139064027476,
|
|
"loss": 6.7755,
|
|
"mean_token_accuracy": 0.1153898686170578,
|
|
"num_tokens": 5404059.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.849250745773316,
|
|
"epoch": 0.26646690566643483,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004997119757126938,
|
|
"loss": 6.8197,
|
|
"mean_token_accuracy": 0.11082051619887352,
|
|
"num_tokens": 5414152.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.916332626342774,
|
|
"epoch": 0.2670019797741987,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997100385341133,
|
|
"loss": 6.9818,
|
|
"mean_token_accuracy": 0.10668149292469024,
|
|
"num_tokens": 5425227.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.95630989074707,
|
|
"epoch": 0.26753705388196264,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997080948670621,
|
|
"loss": 6.8222,
|
|
"mean_token_accuracy": 0.10940428376197815,
|
|
"num_tokens": 5435716.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.869187307357788,
|
|
"epoch": 0.26807212798972657,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997061447115962,
|
|
"loss": 6.8925,
|
|
"mean_token_accuracy": 0.10535158514976502,
|
|
"num_tokens": 5446519.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.927534055709839,
|
|
"epoch": 0.2686072020974905,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997041880677719,
|
|
"loss": 6.8813,
|
|
"mean_token_accuracy": 0.10491925999522209,
|
|
"num_tokens": 5457496.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.855731201171875,
|
|
"epoch": 0.26914227620525444,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997022249356457,
|
|
"loss": 6.7804,
|
|
"mean_token_accuracy": 0.11086295917630196,
|
|
"num_tokens": 5469059.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.904585552215576,
|
|
"epoch": 0.26967735031301837,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004997002553152745,
|
|
"loss": 6.873,
|
|
"mean_token_accuracy": 0.10860639363527298,
|
|
"num_tokens": 5480324.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.874744558334351,
|
|
"epoch": 0.2702124244207823,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996982792067148,
|
|
"loss": 6.8983,
|
|
"mean_token_accuracy": 0.10033328384160996,
|
|
"num_tokens": 5491513.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.809928035736084,
|
|
"epoch": 0.2707474985285462,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499696296610024,
|
|
"loss": 6.8005,
|
|
"mean_token_accuracy": 0.10953768789768219,
|
|
"num_tokens": 5502414.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.870344495773315,
|
|
"epoch": 0.2712825726363101,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996943075252592,
|
|
"loss": 6.9431,
|
|
"mean_token_accuracy": 0.10491918995976449,
|
|
"num_tokens": 5512962.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.90476393699646,
|
|
"epoch": 0.27181764674407405,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996923119524777,
|
|
"loss": 6.7908,
|
|
"mean_token_accuracy": 0.11395590081810951,
|
|
"num_tokens": 5524648.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.79902868270874,
|
|
"epoch": 0.272352720851838,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996903098917375,
|
|
"loss": 6.8741,
|
|
"mean_token_accuracy": 0.10129198431968689,
|
|
"num_tokens": 5536158.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.882397985458374,
|
|
"epoch": 0.2728877949596019,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499688301343096,
|
|
"loss": 6.787,
|
|
"mean_token_accuracy": 0.11079020276665688,
|
|
"num_tokens": 5547374.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.9354483127594,
|
|
"epoch": 0.27342286906736585,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996862863066114,
|
|
"loss": 6.8667,
|
|
"mean_token_accuracy": 0.10993925333023072,
|
|
"num_tokens": 5559212.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.883192300796509,
|
|
"epoch": 0.2739579431751298,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996842647823419,
|
|
"loss": 6.8512,
|
|
"mean_token_accuracy": 0.1091854490339756,
|
|
"num_tokens": 5569302.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.83465051651001,
|
|
"epoch": 0.27449301728289366,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996822367703458,
|
|
"loss": 6.837,
|
|
"mean_token_accuracy": 0.10728960186243057,
|
|
"num_tokens": 5581688.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.896716356277466,
|
|
"epoch": 0.2750280913906576,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996802022706817,
|
|
"loss": 6.7679,
|
|
"mean_token_accuracy": 0.11490985676646233,
|
|
"num_tokens": 5591376.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.771258687973022,
|
|
"epoch": 0.2755631654984215,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996781612834083,
|
|
"loss": 6.8363,
|
|
"mean_token_accuracy": 0.11146841421723366,
|
|
"num_tokens": 5601510.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.9605508804321286,
|
|
"epoch": 0.27609823960618546,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996761138085846,
|
|
"loss": 6.9076,
|
|
"mean_token_accuracy": 0.10790455341339111,
|
|
"num_tokens": 5611436.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.874959659576416,
|
|
"epoch": 0.2766333137139494,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004996740598462697,
|
|
"loss": 6.8889,
|
|
"mean_token_accuracy": 0.10777795240283013,
|
|
"num_tokens": 5620470.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.786574125289917,
|
|
"epoch": 0.2771683878217133,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004996719993965229,
|
|
"loss": 6.7929,
|
|
"mean_token_accuracy": 0.11289525181055068,
|
|
"num_tokens": 5630740.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.820392370223999,
|
|
"epoch": 0.27770346192947726,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996699324594036,
|
|
"loss": 6.8056,
|
|
"mean_token_accuracy": 0.11668010428547859,
|
|
"num_tokens": 5641138.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.923859643936157,
|
|
"epoch": 0.27823853603724114,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996678590349717,
|
|
"loss": 6.925,
|
|
"mean_token_accuracy": 0.1053420752286911,
|
|
"num_tokens": 5652474.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.940411186218261,
|
|
"epoch": 0.27877361014500507,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996657791232868,
|
|
"loss": 6.8298,
|
|
"mean_token_accuracy": 0.11531029716134071,
|
|
"num_tokens": 5663178.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.810340118408203,
|
|
"epoch": 0.279308684252769,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996636927244092,
|
|
"loss": 6.8511,
|
|
"mean_token_accuracy": 0.10380723103880882,
|
|
"num_tokens": 5673565.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.986609363555909,
|
|
"epoch": 0.27984375836053293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499661599838399,
|
|
"loss": 6.8882,
|
|
"mean_token_accuracy": 0.10501667782664299,
|
|
"num_tokens": 5684651.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.8562994480133055,
|
|
"epoch": 0.28037883246829687,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996595004653167,
|
|
"loss": 6.7776,
|
|
"mean_token_accuracy": 0.10820791944861412,
|
|
"num_tokens": 5696081.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.8485575199127195,
|
|
"epoch": 0.2809139065760608,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996573946052229,
|
|
"loss": 6.8207,
|
|
"mean_token_accuracy": 0.11107847765088082,
|
|
"num_tokens": 5706830.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.877283096313477,
|
|
"epoch": 0.28144898068382473,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996552822581783,
|
|
"loss": 6.8511,
|
|
"mean_token_accuracy": 0.11357574313879013,
|
|
"num_tokens": 5717261.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.85238208770752,
|
|
"epoch": 0.2819840547915886,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499653163424244,
|
|
"loss": 6.8112,
|
|
"mean_token_accuracy": 0.10760234370827675,
|
|
"num_tokens": 5727280.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.920324659347534,
|
|
"epoch": 0.28251912889935255,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004996510381034814,
|
|
"loss": 6.8794,
|
|
"mean_token_accuracy": 0.10340792760252952,
|
|
"num_tokens": 5737485.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.889347553253174,
|
|
"epoch": 0.2830542030071165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996489062959515,
|
|
"loss": 6.8485,
|
|
"mean_token_accuracy": 0.10494941174983978,
|
|
"num_tokens": 5747683.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.7954267978668215,
|
|
"epoch": 0.2835892771148804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996467680017159,
|
|
"loss": 6.8968,
|
|
"mean_token_accuracy": 0.10509655699133873,
|
|
"num_tokens": 5758148.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.890285778045654,
|
|
"epoch": 0.28412435122264434,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996446232208365,
|
|
"loss": 6.8374,
|
|
"mean_token_accuracy": 0.11090912595391274,
|
|
"num_tokens": 5769109.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.86578254699707,
|
|
"epoch": 0.2846594253304083,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996424719533753,
|
|
"loss": 6.8432,
|
|
"mean_token_accuracy": 0.10779658704996109,
|
|
"num_tokens": 5780344.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.840816926956177,
|
|
"epoch": 0.2851944994381722,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996403141993941,
|
|
"loss": 6.6683,
|
|
"mean_token_accuracy": 0.12086173370480538,
|
|
"num_tokens": 5790167.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.881586742401123,
|
|
"epoch": 0.2857295735459361,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996381499589555,
|
|
"loss": 6.8347,
|
|
"mean_token_accuracy": 0.10883153080940247,
|
|
"num_tokens": 5800076.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.91086368560791,
|
|
"epoch": 0.2862646476537,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996359792321219,
|
|
"loss": 6.7659,
|
|
"mean_token_accuracy": 0.11435504630208015,
|
|
"num_tokens": 5810547.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.8048162937164305,
|
|
"epoch": 0.28679972176146395,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499633802018956,
|
|
"loss": 6.8252,
|
|
"mean_token_accuracy": 0.11114172041416168,
|
|
"num_tokens": 5821210.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.8217119693756105,
|
|
"epoch": 0.2873347958692279,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996316183195204,
|
|
"loss": 6.8542,
|
|
"mean_token_accuracy": 0.10784100592136384,
|
|
"num_tokens": 5832361.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.871018123626709,
|
|
"epoch": 0.2878698699769918,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004996294281338786,
|
|
"loss": 6.836,
|
|
"mean_token_accuracy": 0.10880450755357743,
|
|
"num_tokens": 5843242.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.958883285522461,
|
|
"epoch": 0.28840494408475575,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996272314620936,
|
|
"loss": 6.8922,
|
|
"mean_token_accuracy": 0.10425070151686669,
|
|
"num_tokens": 5855163.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.799886226654053,
|
|
"epoch": 0.2889400181925197,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996250283042288,
|
|
"loss": 6.8522,
|
|
"mean_token_accuracy": 0.11065445616841316,
|
|
"num_tokens": 5866908.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.870400524139404,
|
|
"epoch": 0.28947509230028357,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499622818660348,
|
|
"loss": 6.8662,
|
|
"mean_token_accuracy": 0.10945025980472564,
|
|
"num_tokens": 5877342.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.890243864059448,
|
|
"epoch": 0.2900101664080475,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996206025305147,
|
|
"loss": 6.8234,
|
|
"mean_token_accuracy": 0.10922683775424957,
|
|
"num_tokens": 5887960.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.841482019424438,
|
|
"epoch": 0.29054524051581143,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996183799147932,
|
|
"loss": 6.8,
|
|
"mean_token_accuracy": 0.10991375595331192,
|
|
"num_tokens": 5899887.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.88977279663086,
|
|
"epoch": 0.29108031462357536,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996161508132475,
|
|
"loss": 6.8117,
|
|
"mean_token_accuracy": 0.1017048753798008,
|
|
"num_tokens": 5911022.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.925865507125854,
|
|
"epoch": 0.2916153887313393,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499613915225942,
|
|
"loss": 6.8908,
|
|
"mean_token_accuracy": 0.11075199842453003,
|
|
"num_tokens": 5922780.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.832954025268554,
|
|
"epoch": 0.29215046283910323,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996116731529412,
|
|
"loss": 6.8937,
|
|
"mean_token_accuracy": 0.11031706780195236,
|
|
"num_tokens": 5934112.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.870949840545654,
|
|
"epoch": 0.29268553694686716,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00049960942459431,
|
|
"loss": 6.8451,
|
|
"mean_token_accuracy": 0.10947609469294547,
|
|
"num_tokens": 5944386.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.836471223831177,
|
|
"epoch": 0.29322061105463104,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996071695501132,
|
|
"loss": 6.7915,
|
|
"mean_token_accuracy": 0.1112366646528244,
|
|
"num_tokens": 5955552.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.866098165512085,
|
|
"epoch": 0.293755685162395,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996049080204159,
|
|
"loss": 6.7982,
|
|
"mean_token_accuracy": 0.1079338662326336,
|
|
"num_tokens": 5966790.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.922070741653442,
|
|
"epoch": 0.2942907592701589,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996026400052835,
|
|
"loss": 6.7898,
|
|
"mean_token_accuracy": 0.11280101761221886,
|
|
"num_tokens": 5977704.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.826333141326904,
|
|
"epoch": 0.29482583337792284,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996003655047814,
|
|
"loss": 6.8131,
|
|
"mean_token_accuracy": 0.11185725182294845,
|
|
"num_tokens": 5989221.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.800469446182251,
|
|
"epoch": 0.2953609074856868,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995980845189753,
|
|
"loss": 6.8493,
|
|
"mean_token_accuracy": 0.10706186145544053,
|
|
"num_tokens": 6000906.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.925901269912719,
|
|
"epoch": 0.2958959815934507,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995957970479312,
|
|
"loss": 6.861,
|
|
"mean_token_accuracy": 0.10586799681186676,
|
|
"num_tokens": 6012039.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.811472463607788,
|
|
"epoch": 0.29643105570121464,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995935030917148,
|
|
"loss": 6.7508,
|
|
"mean_token_accuracy": 0.1096365749835968,
|
|
"num_tokens": 6024383.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.902992296218872,
|
|
"epoch": 0.2969661298089785,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995912026503926,
|
|
"loss": 6.8175,
|
|
"mean_token_accuracy": 0.10661071166396141,
|
|
"num_tokens": 6034904.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.844438695907593,
|
|
"epoch": 0.29750120391674245,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000499588895724031,
|
|
"loss": 6.8281,
|
|
"mean_token_accuracy": 0.1071818120777607,
|
|
"num_tokens": 6044449.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.934893274307251,
|
|
"epoch": 0.2980362780245064,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004995865823126968,
|
|
"loss": 6.8406,
|
|
"mean_token_accuracy": 0.10777448788285256,
|
|
"num_tokens": 6054465.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.792693328857422,
|
|
"epoch": 0.2985713521322703,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004995842624164564,
|
|
"loss": 6.8585,
|
|
"mean_token_accuracy": 0.10810620859265327,
|
|
"num_tokens": 6065539.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.892361211776733,
|
|
"epoch": 0.29910642624003425,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000499581936035377,
|
|
"loss": 6.8215,
|
|
"mean_token_accuracy": 0.10853223651647567,
|
|
"num_tokens": 6076135.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.8402428150177,
|
|
"epoch": 0.2996415003477982,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995796031695257,
|
|
"loss": 6.8311,
|
|
"mean_token_accuracy": 0.11217288449406623,
|
|
"num_tokens": 6086604.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.84694619178772,
|
|
"epoch": 0.3001765744555621,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00049957726381897,
|
|
"loss": 6.8437,
|
|
"mean_token_accuracy": 0.10916305035352707,
|
|
"num_tokens": 6095672.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.85554347038269,
|
|
"epoch": 0.300711648563326,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995749179837773,
|
|
"loss": 6.7047,
|
|
"mean_token_accuracy": 0.11797482892870903,
|
|
"num_tokens": 6105652.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.773930311203003,
|
|
"epoch": 0.30124672267108993,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995725656640155,
|
|
"loss": 6.7678,
|
|
"mean_token_accuracy": 0.11047781035304069,
|
|
"num_tokens": 6116930.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.79344072341919,
|
|
"epoch": 0.30178179677885386,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995702068597524,
|
|
"loss": 6.7643,
|
|
"mean_token_accuracy": 0.11538932919502258,
|
|
"num_tokens": 6126659.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.878014659881591,
|
|
"epoch": 0.3023168708866178,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995678415710561,
|
|
"loss": 6.8063,
|
|
"mean_token_accuracy": 0.10656528547406197,
|
|
"num_tokens": 6137227.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.896840524673462,
|
|
"epoch": 0.3028519449943817,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000499565469797995,
|
|
"loss": 6.8635,
|
|
"mean_token_accuracy": 0.1080358736217022,
|
|
"num_tokens": 6147800.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.800867891311645,
|
|
"epoch": 0.30338701910214566,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995630915406374,
|
|
"loss": 6.7026,
|
|
"mean_token_accuracy": 0.11739906817674636,
|
|
"num_tokens": 6157671.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.8740137100219725,
|
|
"epoch": 0.3039220932099096,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995607067990521,
|
|
"loss": 6.843,
|
|
"mean_token_accuracy": 0.10825344622135162,
|
|
"num_tokens": 6168651.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.845859146118164,
|
|
"epoch": 0.30445716731767347,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000499558315573308,
|
|
"loss": 6.8321,
|
|
"mean_token_accuracy": 0.10733111053705216,
|
|
"num_tokens": 6179925.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.755564451217651,
|
|
"epoch": 0.3049922414254374,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995559178634741,
|
|
"loss": 6.8108,
|
|
"mean_token_accuracy": 0.11236448213458061,
|
|
"num_tokens": 6190541.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.9959348201751705,
|
|
"epoch": 0.30552731553320134,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995535136696196,
|
|
"loss": 6.86,
|
|
"mean_token_accuracy": 0.101121586561203,
|
|
"num_tokens": 6201491.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.768679523468018,
|
|
"epoch": 0.30606238964096527,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499551102991814,
|
|
"loss": 6.669,
|
|
"mean_token_accuracy": 0.1128725491464138,
|
|
"num_tokens": 6212443.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.8172203540802006,
|
|
"epoch": 0.3065974637487292,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995486858301268,
|
|
"loss": 6.8775,
|
|
"mean_token_accuracy": 0.10187524557113647,
|
|
"num_tokens": 6222623.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.841892099380493,
|
|
"epoch": 0.30713253785649314,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995462621846279,
|
|
"loss": 6.7649,
|
|
"mean_token_accuracy": 0.10936387330293655,
|
|
"num_tokens": 6233712.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.847410821914673,
|
|
"epoch": 0.30766761196425707,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995438320553871,
|
|
"loss": 6.8175,
|
|
"mean_token_accuracy": 0.10677930638194084,
|
|
"num_tokens": 6244254.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.818604850769043,
|
|
"epoch": 0.30820268607202095,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995413954424748,
|
|
"loss": 6.7178,
|
|
"mean_token_accuracy": 0.11558739468455315,
|
|
"num_tokens": 6254202.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.813026285171508,
|
|
"epoch": 0.3087377601797849,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995389523459612,
|
|
"loss": 6.8018,
|
|
"mean_token_accuracy": 0.10679139941930771,
|
|
"num_tokens": 6264496.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.809697580337525,
|
|
"epoch": 0.3092728342875488,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499536502765917,
|
|
"loss": 6.8077,
|
|
"mean_token_accuracy": 0.11276716142892837,
|
|
"num_tokens": 6275835.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.855095958709716,
|
|
"epoch": 0.30980790839531275,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995340467024128,
|
|
"loss": 6.7478,
|
|
"mean_token_accuracy": 0.11199733167886734,
|
|
"num_tokens": 6286805.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.821068143844604,
|
|
"epoch": 0.3103429825030767,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995315841555195,
|
|
"loss": 6.758,
|
|
"mean_token_accuracy": 0.10581445917487145,
|
|
"num_tokens": 6298444.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.7351460456848145,
|
|
"epoch": 0.3108780566108406,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995291151253083,
|
|
"loss": 6.7087,
|
|
"mean_token_accuracy": 0.1133358970284462,
|
|
"num_tokens": 6308259.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.783745813369751,
|
|
"epoch": 0.31141313071860455,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995266396118505,
|
|
"loss": 6.7765,
|
|
"mean_token_accuracy": 0.10394766032695771,
|
|
"num_tokens": 6320058.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.834055233001709,
|
|
"epoch": 0.3119482048263684,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995241576152174,
|
|
"loss": 6.746,
|
|
"mean_token_accuracy": 0.10653191581368446,
|
|
"num_tokens": 6331203.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.847873878479004,
|
|
"epoch": 0.31248327893413236,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499521669135481,
|
|
"loss": 6.865,
|
|
"mean_token_accuracy": 0.10627863183617592,
|
|
"num_tokens": 6342027.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.82856764793396,
|
|
"epoch": 0.3130183530418963,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995191741727128,
|
|
"loss": 6.7631,
|
|
"mean_token_accuracy": 0.11083006113767624,
|
|
"num_tokens": 6352580.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.842922592163086,
|
|
"epoch": 0.3135534271496602,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499516672726985,
|
|
"loss": 6.7884,
|
|
"mean_token_accuracy": 0.11612819582223892,
|
|
"num_tokens": 6363997.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.759811305999756,
|
|
"epoch": 0.31408850125742416,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995141647983699,
|
|
"loss": 6.8297,
|
|
"mean_token_accuracy": 0.1118119165301323,
|
|
"num_tokens": 6375284.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.876916217803955,
|
|
"epoch": 0.3146235753651881,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995116503869398,
|
|
"loss": 6.7239,
|
|
"mean_token_accuracy": 0.11943885236978531,
|
|
"num_tokens": 6386698.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.8405262470245365,
|
|
"epoch": 0.315158649472952,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995091294927673,
|
|
"loss": 6.8008,
|
|
"mean_token_accuracy": 0.10860055312514305,
|
|
"num_tokens": 6397237.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.879640722274781,
|
|
"epoch": 0.3156937235807159,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995066021159253,
|
|
"loss": 6.9112,
|
|
"mean_token_accuracy": 0.10427958816289902,
|
|
"num_tokens": 6408266.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.7258257389068605,
|
|
"epoch": 0.31622879768847983,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995040682564867,
|
|
"loss": 6.7992,
|
|
"mean_token_accuracy": 0.1148921512067318,
|
|
"num_tokens": 6419563.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.841591644287109,
|
|
"epoch": 0.31676387179624377,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995015279145247,
|
|
"loss": 6.7586,
|
|
"mean_token_accuracy": 0.11175140738487244,
|
|
"num_tokens": 6430220.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.83943738937378,
|
|
"epoch": 0.3172989459040077,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994989810901126,
|
|
"loss": 6.7692,
|
|
"mean_token_accuracy": 0.11018451079726219,
|
|
"num_tokens": 6440157.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.7851283073425295,
|
|
"epoch": 0.31783402001177163,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994964277833239,
|
|
"loss": 6.8115,
|
|
"mean_token_accuracy": 0.1146237537264824,
|
|
"num_tokens": 6449511.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.883852767944336,
|
|
"epoch": 0.31836909411953557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994938679942324,
|
|
"loss": 6.8141,
|
|
"mean_token_accuracy": 0.10362748950719833,
|
|
"num_tokens": 6460608.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.832978010177612,
|
|
"epoch": 0.3189041682272995,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004994913017229121,
|
|
"loss": 6.8057,
|
|
"mean_token_accuracy": 0.11033113375306129,
|
|
"num_tokens": 6472737.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.801235628128052,
|
|
"epoch": 0.31943924233506343,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994887289694371,
|
|
"loss": 6.7104,
|
|
"mean_token_accuracy": 0.11842553317546844,
|
|
"num_tokens": 6482993.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.89878888130188,
|
|
"epoch": 0.3199743164428273,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994861497338814,
|
|
"loss": 6.8957,
|
|
"mean_token_accuracy": 0.10716022476553917,
|
|
"num_tokens": 6494530.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.804651165008545,
|
|
"epoch": 0.32050939055059124,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994835640163198,
|
|
"loss": 6.7251,
|
|
"mean_token_accuracy": 0.10995796993374825,
|
|
"num_tokens": 6504691.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.851648616790771,
|
|
"epoch": 0.3210444646583552,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994809718168267,
|
|
"loss": 6.7702,
|
|
"mean_token_accuracy": 0.11220109388232231,
|
|
"num_tokens": 6514924.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3210444646583552,
|
|
"eval_entropy": 6.663155538502408,
|
|
"eval_loss": 6.872208595275879,
|
|
"eval_mean_token_accuracy": 0.11419496110206184,
|
|
"eval_num_tokens": 6514924.0,
|
|
"eval_runtime": 22.687,
|
|
"eval_samples_per_second": 1308.193,
|
|
"eval_steps_per_second": 163.53,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.745563745498657,
|
|
"epoch": 0.3215795387661191,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994783731354771,
|
|
"loss": 6.7117,
|
|
"mean_token_accuracy": 0.11273391768336297,
|
|
"num_tokens": 6526097.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.84506573677063,
|
|
"epoch": 0.32211461287388304,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994757679723461,
|
|
"loss": 6.798,
|
|
"mean_token_accuracy": 0.10792320370674133,
|
|
"num_tokens": 6536384.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.854998588562012,
|
|
"epoch": 0.322649686981647,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994731563275088,
|
|
"loss": 6.8462,
|
|
"mean_token_accuracy": 0.10304803922772407,
|
|
"num_tokens": 6547161.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.727174854278564,
|
|
"epoch": 0.3231847610894109,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994705382010406,
|
|
"loss": 6.7479,
|
|
"mean_token_accuracy": 0.11188101395964622,
|
|
"num_tokens": 6556751.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.803781652450562,
|
|
"epoch": 0.3237198351971748,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994679135930174,
|
|
"loss": 6.8008,
|
|
"mean_token_accuracy": 0.11748359650373459,
|
|
"num_tokens": 6567655.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.928503513336182,
|
|
"epoch": 0.3242549093049387,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004994652825035144,
|
|
"loss": 6.8405,
|
|
"mean_token_accuracy": 0.10758018866181374,
|
|
"num_tokens": 6579127.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.875131845474243,
|
|
"epoch": 0.32478998341270265,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994626449326081,
|
|
"loss": 6.8049,
|
|
"mean_token_accuracy": 0.11168428286910057,
|
|
"num_tokens": 6590779.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.774374866485596,
|
|
"epoch": 0.3253250575204666,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994600008803745,
|
|
"loss": 6.7335,
|
|
"mean_token_accuracy": 0.11798494532704354,
|
|
"num_tokens": 6600849.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.798848724365234,
|
|
"epoch": 0.3258601316282305,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994573503468899,
|
|
"loss": 6.7321,
|
|
"mean_token_accuracy": 0.11672844365239143,
|
|
"num_tokens": 6610633.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.771644926071167,
|
|
"epoch": 0.32639520573599445,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994546933322308,
|
|
"loss": 6.7739,
|
|
"mean_token_accuracy": 0.11045937165617943,
|
|
"num_tokens": 6621327.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.874581432342529,
|
|
"epoch": 0.3269302798437584,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499452029836474,
|
|
"loss": 6.7295,
|
|
"mean_token_accuracy": 0.11313018202781677,
|
|
"num_tokens": 6632267.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.786725950241089,
|
|
"epoch": 0.32746535395152226,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994493598596963,
|
|
"loss": 6.7551,
|
|
"mean_token_accuracy": 0.10917075648903847,
|
|
"num_tokens": 6642714.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.825065422058105,
|
|
"epoch": 0.3280004280592862,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004994466834019749,
|
|
"loss": 6.7567,
|
|
"mean_token_accuracy": 0.11459867134690285,
|
|
"num_tokens": 6652353.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.794483184814453,
|
|
"epoch": 0.32853550216705013,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994440004633871,
|
|
"loss": 6.7356,
|
|
"mean_token_accuracy": 0.11090541109442711,
|
|
"num_tokens": 6663133.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.734937572479248,
|
|
"epoch": 0.32907057627481406,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004994413110440103,
|
|
"loss": 6.7047,
|
|
"mean_token_accuracy": 0.11492902711033821,
|
|
"num_tokens": 6673984.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.844591569900513,
|
|
"epoch": 0.329605650382578,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994386151439222,
|
|
"loss": 6.7803,
|
|
"mean_token_accuracy": 0.10733171626925468,
|
|
"num_tokens": 6686171.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.93147349357605,
|
|
"epoch": 0.33014072449034193,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004994359127632006,
|
|
"loss": 6.8192,
|
|
"mean_token_accuracy": 0.1099952794611454,
|
|
"num_tokens": 6696609.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.821014881134033,
|
|
"epoch": 0.33067579859810586,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994332039019235,
|
|
"loss": 6.763,
|
|
"mean_token_accuracy": 0.11340149566531181,
|
|
"num_tokens": 6706188.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.705182504653931,
|
|
"epoch": 0.33121087270586974,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994304885601694,
|
|
"loss": 6.7418,
|
|
"mean_token_accuracy": 0.10889102444052697,
|
|
"num_tokens": 6716276.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.740193796157837,
|
|
"epoch": 0.3317459468136337,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994277667380162,
|
|
"loss": 6.7062,
|
|
"mean_token_accuracy": 0.11886503547430038,
|
|
"num_tokens": 6727176.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.819032144546509,
|
|
"epoch": 0.3322810209213976,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994250384355429,
|
|
"loss": 6.7953,
|
|
"mean_token_accuracy": 0.11346929892897606,
|
|
"num_tokens": 6737768.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.8038139820098875,
|
|
"epoch": 0.33281609502916154,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004994223036528282,
|
|
"loss": 6.7227,
|
|
"mean_token_accuracy": 0.1112707644701004,
|
|
"num_tokens": 6747962.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.7923671245574955,
|
|
"epoch": 0.3333511691369255,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499419562389951,
|
|
"loss": 6.7364,
|
|
"mean_token_accuracy": 0.11729706302285195,
|
|
"num_tokens": 6758400.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.8117434024810795,
|
|
"epoch": 0.3338862432446894,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994168146469904,
|
|
"loss": 6.7423,
|
|
"mean_token_accuracy": 0.11491606682538986,
|
|
"num_tokens": 6768855.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.806019639968872,
|
|
"epoch": 0.33442131735245334,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994140604240259,
|
|
"loss": 6.7074,
|
|
"mean_token_accuracy": 0.10914952158927918,
|
|
"num_tokens": 6778656.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.780620765686035,
|
|
"epoch": 0.3349563914602172,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994112997211369,
|
|
"loss": 6.7966,
|
|
"mean_token_accuracy": 0.11377846822142601,
|
|
"num_tokens": 6789960.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.753642463684082,
|
|
"epoch": 0.33549146556798115,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994085325384031,
|
|
"loss": 6.7635,
|
|
"mean_token_accuracy": 0.11045785918831826,
|
|
"num_tokens": 6800188.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.871442890167236,
|
|
"epoch": 0.3360265396757451,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994057588759045,
|
|
"loss": 6.722,
|
|
"mean_token_accuracy": 0.11737764328718185,
|
|
"num_tokens": 6811032.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.7277820110321045,
|
|
"epoch": 0.336561613783509,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994029787337212,
|
|
"loss": 6.736,
|
|
"mean_token_accuracy": 0.11023216396570205,
|
|
"num_tokens": 6823060.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.802412271499634,
|
|
"epoch": 0.33709668789127295,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004994001921119333,
|
|
"loss": 6.8219,
|
|
"mean_token_accuracy": 0.1107473075389862,
|
|
"num_tokens": 6833559.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.853548192977906,
|
|
"epoch": 0.3376317619990369,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993973990106215,
|
|
"loss": 6.7542,
|
|
"mean_token_accuracy": 0.11447353884577752,
|
|
"num_tokens": 6843657.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.792013549804688,
|
|
"epoch": 0.3381668361068008,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993945994298662,
|
|
"loss": 6.702,
|
|
"mean_token_accuracy": 0.10676191747188568,
|
|
"num_tokens": 6853615.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.795974826812744,
|
|
"epoch": 0.3387019102145647,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993917933697484,
|
|
"loss": 6.8142,
|
|
"mean_token_accuracy": 0.1132157288491726,
|
|
"num_tokens": 6865256.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.959893465042114,
|
|
"epoch": 0.3392369843223286,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993889808303493,
|
|
"loss": 6.8499,
|
|
"mean_token_accuracy": 0.11078018173575402,
|
|
"num_tokens": 6875358.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.717615413665771,
|
|
"epoch": 0.33977205843009256,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993861618117498,
|
|
"loss": 6.7472,
|
|
"mean_token_accuracy": 0.11126919835805893,
|
|
"num_tokens": 6886584.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.791712093353271,
|
|
"epoch": 0.3403071325378565,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993833363140314,
|
|
"loss": 6.6961,
|
|
"mean_token_accuracy": 0.11922059878706932,
|
|
"num_tokens": 6896958.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.775498533248902,
|
|
"epoch": 0.3408422066456204,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993805043372756,
|
|
"loss": 6.7571,
|
|
"mean_token_accuracy": 0.11386067494750023,
|
|
"num_tokens": 6907944.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.860631656646729,
|
|
"epoch": 0.34137728075338436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993776658815644,
|
|
"loss": 6.8337,
|
|
"mean_token_accuracy": 0.10652636811137199,
|
|
"num_tokens": 6919486.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.90429196357727,
|
|
"epoch": 0.3419123548611483,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004993748209469796,
|
|
"loss": 6.8248,
|
|
"mean_token_accuracy": 0.11483817845582962,
|
|
"num_tokens": 6930650.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.78099422454834,
|
|
"epoch": 0.34244742896891217,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004993719695336033,
|
|
"loss": 6.7568,
|
|
"mean_token_accuracy": 0.10781802982091904,
|
|
"num_tokens": 6941519.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.730162286758423,
|
|
"epoch": 0.3429825030766761,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993691116415179,
|
|
"loss": 6.8018,
|
|
"mean_token_accuracy": 0.11166835129261017,
|
|
"num_tokens": 6952952.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.847195672988891,
|
|
"epoch": 0.34351757718444004,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499366247270806,
|
|
"loss": 6.7639,
|
|
"mean_token_accuracy": 0.11426469087600707,
|
|
"num_tokens": 6962867.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.813245677947998,
|
|
"epoch": 0.34405265129220397,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993633764215502,
|
|
"loss": 6.7098,
|
|
"mean_token_accuracy": 0.11524691209197044,
|
|
"num_tokens": 6973434.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.814610481262207,
|
|
"epoch": 0.3445877253999679,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004993604990938336,
|
|
"loss": 6.708,
|
|
"mean_token_accuracy": 0.12139374017715454,
|
|
"num_tokens": 6984161.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.788215398788452,
|
|
"epoch": 0.34512279950773184,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993576152877389,
|
|
"loss": 6.6851,
|
|
"mean_token_accuracy": 0.11097052693367004,
|
|
"num_tokens": 6994700.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.797618675231933,
|
|
"epoch": 0.34565787361549577,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993547250033496,
|
|
"loss": 6.8513,
|
|
"mean_token_accuracy": 0.1027825728058815,
|
|
"num_tokens": 7006497.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.857847785949707,
|
|
"epoch": 0.34619294772325965,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993518282407493,
|
|
"loss": 6.764,
|
|
"mean_token_accuracy": 0.11577967777848244,
|
|
"num_tokens": 7016415.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.754112482070923,
|
|
"epoch": 0.3467280218310236,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004993489250000213,
|
|
"loss": 6.7178,
|
|
"mean_token_accuracy": 0.1137387789785862,
|
|
"num_tokens": 7026610.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.782814884185791,
|
|
"epoch": 0.3472630959387875,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993460152812497,
|
|
"loss": 6.7111,
|
|
"mean_token_accuracy": 0.11138368397951126,
|
|
"num_tokens": 7038236.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.791642427444458,
|
|
"epoch": 0.34779817004655145,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993430990845184,
|
|
"loss": 6.7648,
|
|
"mean_token_accuracy": 0.11891621202230454,
|
|
"num_tokens": 7049438.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.776367568969727,
|
|
"epoch": 0.3483332441543154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993401764099118,
|
|
"loss": 6.7353,
|
|
"mean_token_accuracy": 0.10871460661292076,
|
|
"num_tokens": 7061001.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.793423700332641,
|
|
"epoch": 0.3488683182620793,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993372472575139,
|
|
"loss": 6.7209,
|
|
"mean_token_accuracy": 0.11650840044021607,
|
|
"num_tokens": 7071328.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.850569820404052,
|
|
"epoch": 0.34940339236984325,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993343116274096,
|
|
"loss": 6.9068,
|
|
"mean_token_accuracy": 0.10371987372636796,
|
|
"num_tokens": 7082597.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.807454252243042,
|
|
"epoch": 0.3499384664776071,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993313695196836,
|
|
"loss": 6.7332,
|
|
"mean_token_accuracy": 0.11512698754668235,
|
|
"num_tokens": 7093463.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.7837098121643065,
|
|
"epoch": 0.35047354058537106,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993284209344208,
|
|
"loss": 6.7997,
|
|
"mean_token_accuracy": 0.1145312875509262,
|
|
"num_tokens": 7104350.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.870277261734008,
|
|
"epoch": 0.351008614693135,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993254658717065,
|
|
"loss": 6.7369,
|
|
"mean_token_accuracy": 0.1199392855167389,
|
|
"num_tokens": 7114851.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.812195873260498,
|
|
"epoch": 0.3515436888008989,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993225043316257,
|
|
"loss": 6.7939,
|
|
"mean_token_accuracy": 0.10890180021524429,
|
|
"num_tokens": 7126440.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.865800571441651,
|
|
"epoch": 0.35207876290866286,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993195363142643,
|
|
"loss": 6.8197,
|
|
"mean_token_accuracy": 0.1106312945485115,
|
|
"num_tokens": 7137884.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.832308912277222,
|
|
"epoch": 0.3526138370164268,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993165618197076,
|
|
"loss": 6.7948,
|
|
"mean_token_accuracy": 0.10431528687477112,
|
|
"num_tokens": 7147930.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.803113508224487,
|
|
"epoch": 0.3531489111241907,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993135808480418,
|
|
"loss": 6.6503,
|
|
"mean_token_accuracy": 0.1201249398291111,
|
|
"num_tokens": 7159200.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.816599941253662,
|
|
"epoch": 0.3536839852319546,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004993105933993529,
|
|
"loss": 6.7626,
|
|
"mean_token_accuracy": 0.11429173201322555,
|
|
"num_tokens": 7169601.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.66412386894226,
|
|
"epoch": 0.35421905933971853,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993075994737271,
|
|
"loss": 6.6744,
|
|
"mean_token_accuracy": 0.11934652402997017,
|
|
"num_tokens": 7180465.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.818277883529663,
|
|
"epoch": 0.35475413344748247,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993045990712508,
|
|
"loss": 6.708,
|
|
"mean_token_accuracy": 0.11447355002164841,
|
|
"num_tokens": 7190603.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.783639717102051,
|
|
"epoch": 0.3552892075552464,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993015921920109,
|
|
"loss": 6.6647,
|
|
"mean_token_accuracy": 0.11898905709385872,
|
|
"num_tokens": 7201017.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.625533580780029,
|
|
"epoch": 0.35582428166301033,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499298578836094,
|
|
"loss": 6.6605,
|
|
"mean_token_accuracy": 0.11563685759902001,
|
|
"num_tokens": 7210908.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.863593101501465,
|
|
"epoch": 0.35635935577077427,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499295559003587,
|
|
"loss": 6.7213,
|
|
"mean_token_accuracy": 0.11133797988295555,
|
|
"num_tokens": 7221306.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.822593641281128,
|
|
"epoch": 0.3568944298785382,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992925326945774,
|
|
"loss": 6.8278,
|
|
"mean_token_accuracy": 0.10899438485503196,
|
|
"num_tokens": 7233076.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.80994987487793,
|
|
"epoch": 0.3574295039863021,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004992894999091524,
|
|
"loss": 6.8078,
|
|
"mean_token_accuracy": 0.11141066178679467,
|
|
"num_tokens": 7244703.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.87962965965271,
|
|
"epoch": 0.357964578094066,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004992864606473996,
|
|
"loss": 6.7946,
|
|
"mean_token_accuracy": 0.10520617961883545,
|
|
"num_tokens": 7255438.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.798658418655395,
|
|
"epoch": 0.35849965220182994,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992834149094069,
|
|
"loss": 6.7395,
|
|
"mean_token_accuracy": 0.11447354853153228,
|
|
"num_tokens": 7265720.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.858418321609497,
|
|
"epoch": 0.3590347263095939,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992803626952619,
|
|
"loss": 6.793,
|
|
"mean_token_accuracy": 0.11047556102275849,
|
|
"num_tokens": 7277791.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.7222527980804445,
|
|
"epoch": 0.3595698004173578,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499277304005053,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.12052367404103279,
|
|
"num_tokens": 7288521.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.798248815536499,
|
|
"epoch": 0.36010487452512174,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004992742388388686,
|
|
"loss": 6.8421,
|
|
"mean_token_accuracy": 0.10391957610845566,
|
|
"num_tokens": 7299298.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.781761646270752,
|
|
"epoch": 0.3606399486328857,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004992711671967968,
|
|
"loss": 6.6749,
|
|
"mean_token_accuracy": 0.11205682978034019,
|
|
"num_tokens": 7310271.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.819436931610108,
|
|
"epoch": 0.36117502274064955,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992680890789268,
|
|
"loss": 6.7204,
|
|
"mean_token_accuracy": 0.10891408175230026,
|
|
"num_tokens": 7321112.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.711510848999024,
|
|
"epoch": 0.3617100968484135,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992650044853471,
|
|
"loss": 6.6925,
|
|
"mean_token_accuracy": 0.11342240199446678,
|
|
"num_tokens": 7331976.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.83953218460083,
|
|
"epoch": 0.3622451709561774,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499261913416147,
|
|
"loss": 6.8077,
|
|
"mean_token_accuracy": 0.11410307884216309,
|
|
"num_tokens": 7342800.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.794235801696777,
|
|
"epoch": 0.36278024506394135,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992588158714157,
|
|
"loss": 6.6276,
|
|
"mean_token_accuracy": 0.11011371910572051,
|
|
"num_tokens": 7354213.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.776007080078125,
|
|
"epoch": 0.3633153191717053,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992557118512424,
|
|
"loss": 6.7167,
|
|
"mean_token_accuracy": 0.11738533824682236,
|
|
"num_tokens": 7363250.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.75283145904541,
|
|
"epoch": 0.3638503932794692,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992526013557171,
|
|
"loss": 6.7369,
|
|
"mean_token_accuracy": 0.11341856718063355,
|
|
"num_tokens": 7374185.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.711459302902222,
|
|
"epoch": 0.36438546738723315,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992494843849294,
|
|
"loss": 6.7078,
|
|
"mean_token_accuracy": 0.10516770109534264,
|
|
"num_tokens": 7384579.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.900410556793213,
|
|
"epoch": 0.36492054149499703,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992463609389694,
|
|
"loss": 6.7332,
|
|
"mean_token_accuracy": 0.1097166284918785,
|
|
"num_tokens": 7395277.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.7915020942687985,
|
|
"epoch": 0.36545561560276096,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992432310179272,
|
|
"loss": 6.7261,
|
|
"mean_token_accuracy": 0.11375608071684837,
|
|
"num_tokens": 7406688.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.689106082916259,
|
|
"epoch": 0.3659906897105249,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992400946218932,
|
|
"loss": 6.7707,
|
|
"mean_token_accuracy": 0.11034525856375695,
|
|
"num_tokens": 7417378.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.916859579086304,
|
|
"epoch": 0.36652576381828883,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004992369517509581,
|
|
"loss": 6.8004,
|
|
"mean_token_accuracy": 0.11413674354553223,
|
|
"num_tokens": 7427675.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.825582122802734,
|
|
"epoch": 0.36706083792605276,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992338024052123,
|
|
"loss": 6.8317,
|
|
"mean_token_accuracy": 0.10687674582004547,
|
|
"num_tokens": 7438083.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.752775859832764,
|
|
"epoch": 0.3675959120338167,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992306465847473,
|
|
"loss": 6.6768,
|
|
"mean_token_accuracy": 0.11751338317990304,
|
|
"num_tokens": 7449051.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.752591276168824,
|
|
"epoch": 0.36813098614158063,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992274842896536,
|
|
"loss": 6.7025,
|
|
"mean_token_accuracy": 0.11567284539341927,
|
|
"num_tokens": 7459074.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.787220621109009,
|
|
"epoch": 0.3686660602493445,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992243155200229,
|
|
"loss": 6.7755,
|
|
"mean_token_accuracy": 0.11534915417432785,
|
|
"num_tokens": 7470472.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.828776693344116,
|
|
"epoch": 0.36920113435710844,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992211402759466,
|
|
"loss": 6.7396,
|
|
"mean_token_accuracy": 0.1147568017244339,
|
|
"num_tokens": 7481477.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.774149703979492,
|
|
"epoch": 0.3697362084648724,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992179585575164,
|
|
"loss": 6.7033,
|
|
"mean_token_accuracy": 0.1158942274749279,
|
|
"num_tokens": 7491906.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.795584964752197,
|
|
"epoch": 0.3702712825726363,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499214770364824,
|
|
"loss": 6.6307,
|
|
"mean_token_accuracy": 0.10889941975474357,
|
|
"num_tokens": 7502447.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.701265859603882,
|
|
"epoch": 0.37080635668040024,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992115756979617,
|
|
"loss": 6.6362,
|
|
"mean_token_accuracy": 0.12357409447431564,
|
|
"num_tokens": 7513505.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.767413330078125,
|
|
"epoch": 0.3713414307881642,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992083745570218,
|
|
"loss": 6.6523,
|
|
"mean_token_accuracy": 0.12134870514273643,
|
|
"num_tokens": 7524884.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.713840341567993,
|
|
"epoch": 0.3718765048959281,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004992051669420964,
|
|
"loss": 6.7316,
|
|
"mean_token_accuracy": 0.11824962720274926,
|
|
"num_tokens": 7535942.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.757349061965942,
|
|
"epoch": 0.372411579003692,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992019528532785,
|
|
"loss": 6.7058,
|
|
"mean_token_accuracy": 0.11440639570355415,
|
|
"num_tokens": 7545506.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.827877569198608,
|
|
"epoch": 0.3729466531114559,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991987322906605,
|
|
"loss": 6.7843,
|
|
"mean_token_accuracy": 0.10873871818184852,
|
|
"num_tokens": 7555328.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.809679365158081,
|
|
"epoch": 0.37348172721921985,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991955052543357,
|
|
"loss": 6.6898,
|
|
"mean_token_accuracy": 0.11306628957390785,
|
|
"num_tokens": 7565762.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.832235860824585,
|
|
"epoch": 0.3740168013269838,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004991922717443972,
|
|
"loss": 6.701,
|
|
"mean_token_accuracy": 0.12100865170359612,
|
|
"num_tokens": 7575884.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.80165286064148,
|
|
"epoch": 0.3745518754347477,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991890317609384,
|
|
"loss": 6.7252,
|
|
"mean_token_accuracy": 0.11258633807301521,
|
|
"num_tokens": 7586100.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.787338972091675,
|
|
"epoch": 0.37508694954251165,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991857853040528,
|
|
"loss": 6.7466,
|
|
"mean_token_accuracy": 0.1115113340318203,
|
|
"num_tokens": 7597137.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.7378333568572994,
|
|
"epoch": 0.3756220236502756,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004991825323738341,
|
|
"loss": 6.7824,
|
|
"mean_token_accuracy": 0.11462030112743378,
|
|
"num_tokens": 7607640.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.825198125839234,
|
|
"epoch": 0.3761570977580395,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004991792729703763,
|
|
"loss": 6.8399,
|
|
"mean_token_accuracy": 0.11375791877508164,
|
|
"num_tokens": 7618319.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.861372232437134,
|
|
"epoch": 0.3766921718658034,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991760070937734,
|
|
"loss": 6.7157,
|
|
"mean_token_accuracy": 0.11241295039653779,
|
|
"num_tokens": 7628350.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.775536441802979,
|
|
"epoch": 0.3772272459735673,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991727347441199,
|
|
"loss": 6.7374,
|
|
"mean_token_accuracy": 0.10838376954197884,
|
|
"num_tokens": 7637857.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.840644407272339,
|
|
"epoch": 0.37776232008133126,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991694559215102,
|
|
"loss": 6.7405,
|
|
"mean_token_accuracy": 0.11169720366597176,
|
|
"num_tokens": 7648242.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.813172006607056,
|
|
"epoch": 0.3782973941890952,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499166170626039,
|
|
"loss": 6.7742,
|
|
"mean_token_accuracy": 0.11039445921778679,
|
|
"num_tokens": 7660565.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.728032398223877,
|
|
"epoch": 0.3788324682968591,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000499162878857801,
|
|
"loss": 6.7546,
|
|
"mean_token_accuracy": 0.11566273272037506,
|
|
"num_tokens": 7671600.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.7928694725036625,
|
|
"epoch": 0.37936754240462306,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991595806168915,
|
|
"loss": 6.7712,
|
|
"mean_token_accuracy": 0.11043274328112603,
|
|
"num_tokens": 7682453.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.808826303482055,
|
|
"epoch": 0.379902616512387,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991562759034055,
|
|
"loss": 6.7161,
|
|
"mean_token_accuracy": 0.11529388427734374,
|
|
"num_tokens": 7693490.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.77369909286499,
|
|
"epoch": 0.38043769062015087,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991529647174386,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.11225939691066741,
|
|
"num_tokens": 7703478.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.753496932983398,
|
|
"epoch": 0.3809727647279148,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991496470590864,
|
|
"loss": 6.7506,
|
|
"mean_token_accuracy": 0.11137450858950615,
|
|
"num_tokens": 7714647.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.797580623626709,
|
|
"epoch": 0.38150783883567874,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991463229284445,
|
|
"loss": 6.6918,
|
|
"mean_token_accuracy": 0.11793707832694053,
|
|
"num_tokens": 7725528.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.728217697143554,
|
|
"epoch": 0.38204291294344267,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004991429923256091,
|
|
"loss": 6.7626,
|
|
"mean_token_accuracy": 0.1149514652788639,
|
|
"num_tokens": 7737708.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.858790016174316,
|
|
"epoch": 0.3825779870512066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991396552506762,
|
|
"loss": 6.7393,
|
|
"mean_token_accuracy": 0.11154627427458763,
|
|
"num_tokens": 7749093.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.721363496780396,
|
|
"epoch": 0.38311306115897054,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991363117037423,
|
|
"loss": 6.6723,
|
|
"mean_token_accuracy": 0.11780490428209305,
|
|
"num_tokens": 7760024.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.753328323364258,
|
|
"epoch": 0.38364813526673447,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991329616849039,
|
|
"loss": 6.726,
|
|
"mean_token_accuracy": 0.11707820892333984,
|
|
"num_tokens": 7770801.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.811793375015259,
|
|
"epoch": 0.38418320937449835,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991296051942578,
|
|
"loss": 6.7764,
|
|
"mean_token_accuracy": 0.11302950009703636,
|
|
"num_tokens": 7782257.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.777999687194824,
|
|
"epoch": 0.3847182834822623,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004991262422319008,
|
|
"loss": 6.7062,
|
|
"mean_token_accuracy": 0.11388157904148102,
|
|
"num_tokens": 7793016.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.741271257400513,
|
|
"epoch": 0.3852533575900262,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00049912287279793,
|
|
"loss": 6.6244,
|
|
"mean_token_accuracy": 0.12548631727695464,
|
|
"num_tokens": 7802207.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.803160715103149,
|
|
"epoch": 0.38578843169779015,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991194968924429,
|
|
"loss": 6.7667,
|
|
"mean_token_accuracy": 0.11139355152845383,
|
|
"num_tokens": 7813487.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.820051670074463,
|
|
"epoch": 0.3863235058055541,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991161145155367,
|
|
"loss": 6.7436,
|
|
"mean_token_accuracy": 0.10898175165057182,
|
|
"num_tokens": 7824587.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.810724067687988,
|
|
"epoch": 0.386858579913318,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991127256673091,
|
|
"loss": 6.7258,
|
|
"mean_token_accuracy": 0.11021277531981469,
|
|
"num_tokens": 7836240.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.730466079711914,
|
|
"epoch": 0.38739365402108195,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991093303478582,
|
|
"loss": 6.6835,
|
|
"mean_token_accuracy": 0.1120126262307167,
|
|
"num_tokens": 7847014.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.777944612503052,
|
|
"epoch": 0.3879287281288458,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991059285572818,
|
|
"loss": 6.7889,
|
|
"mean_token_accuracy": 0.11452787667512894,
|
|
"num_tokens": 7857899.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.834170627593994,
|
|
"epoch": 0.38846380223660976,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991025202956781,
|
|
"loss": 6.6747,
|
|
"mean_token_accuracy": 0.11366800889372826,
|
|
"num_tokens": 7868987.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.789688396453857,
|
|
"epoch": 0.3889988763443737,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004990991055631457,
|
|
"loss": 6.7962,
|
|
"mean_token_accuracy": 0.10578811541199684,
|
|
"num_tokens": 7879547.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.7377862453460695,
|
|
"epoch": 0.3895339504521376,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990956843597832,
|
|
"loss": 6.6631,
|
|
"mean_token_accuracy": 0.11802548319101333,
|
|
"num_tokens": 7889824.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.69925103187561,
|
|
"epoch": 0.39006902455990156,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990922566856892,
|
|
"loss": 6.6561,
|
|
"mean_token_accuracy": 0.11325121521949769,
|
|
"num_tokens": 7901156.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.809516572952271,
|
|
"epoch": 0.3906040986676655,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004990888225409629,
|
|
"loss": 6.6966,
|
|
"mean_token_accuracy": 0.11288304328918457,
|
|
"num_tokens": 7911695.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.678881454467773,
|
|
"epoch": 0.3911391727754294,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990853819257033,
|
|
"loss": 6.6831,
|
|
"mean_token_accuracy": 0.11762734055519104,
|
|
"num_tokens": 7923559.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.829882717132568,
|
|
"epoch": 0.3916742468831933,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990819348400097,
|
|
"loss": 6.7028,
|
|
"mean_token_accuracy": 0.11330192908644676,
|
|
"num_tokens": 7935792.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.827629613876343,
|
|
"epoch": 0.39220932099095723,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004990784812839818,
|
|
"loss": 6.7259,
|
|
"mean_token_accuracy": 0.11621317267417908,
|
|
"num_tokens": 7946987.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.687596178054809,
|
|
"epoch": 0.39274439509872117,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990750212577192,
|
|
"loss": 6.6242,
|
|
"mean_token_accuracy": 0.11732003539800644,
|
|
"num_tokens": 7957160.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.75628023147583,
|
|
"epoch": 0.3932794692064851,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990715547613219,
|
|
"loss": 6.7267,
|
|
"mean_token_accuracy": 0.10887964740395546,
|
|
"num_tokens": 7968833.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.86474928855896,
|
|
"epoch": 0.39381454331424903,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990680817948898,
|
|
"loss": 6.7746,
|
|
"mean_token_accuracy": 0.10795791894197464,
|
|
"num_tokens": 7980661.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.82999620437622,
|
|
"epoch": 0.39434961742201297,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990646023585234,
|
|
"loss": 6.6961,
|
|
"mean_token_accuracy": 0.11407504081726075,
|
|
"num_tokens": 7992677.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.724775314331055,
|
|
"epoch": 0.3948846915297769,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990611164523231,
|
|
"loss": 6.6708,
|
|
"mean_token_accuracy": 0.11982596963644028,
|
|
"num_tokens": 8002796.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.676330137252807,
|
|
"epoch": 0.3954197656375408,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004990576240763896,
|
|
"loss": 6.7051,
|
|
"mean_token_accuracy": 0.1177534967660904,
|
|
"num_tokens": 8012779.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.781534337997437,
|
|
"epoch": 0.3959548397453047,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990541252308237,
|
|
"loss": 6.692,
|
|
"mean_token_accuracy": 0.11586613357067108,
|
|
"num_tokens": 8023442.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.77800612449646,
|
|
"epoch": 0.39648991385306864,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990506199157263,
|
|
"loss": 6.7827,
|
|
"mean_token_accuracy": 0.1080534890294075,
|
|
"num_tokens": 8035163.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.80181851387024,
|
|
"epoch": 0.3970249879608326,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004990471081311988,
|
|
"loss": 6.7055,
|
|
"mean_token_accuracy": 0.11133532226085663,
|
|
"num_tokens": 8045330.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.811718845367432,
|
|
"epoch": 0.3975600620685965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990435898773426,
|
|
"loss": 6.7351,
|
|
"mean_token_accuracy": 0.11524785310029984,
|
|
"num_tokens": 8056154.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.784503698348999,
|
|
"epoch": 0.39809513617636044,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990400651542592,
|
|
"loss": 6.6841,
|
|
"mean_token_accuracy": 0.11801928132772446,
|
|
"num_tokens": 8066101.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.792222738265991,
|
|
"epoch": 0.3986302102841244,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990365339620504,
|
|
"loss": 6.7648,
|
|
"mean_token_accuracy": 0.10933328941464424,
|
|
"num_tokens": 8077249.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.7601371765136715,
|
|
"epoch": 0.39916528439188825,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000499032996300818,
|
|
"loss": 6.6969,
|
|
"mean_token_accuracy": 0.11813873648643494,
|
|
"num_tokens": 8088532.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.811507701873779,
|
|
"epoch": 0.3997003584996522,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990294521706645,
|
|
"loss": 6.7442,
|
|
"mean_token_accuracy": 0.1067180298268795,
|
|
"num_tokens": 8099541.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.733289003372192,
|
|
"epoch": 0.4002354326074161,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000499025901571692,
|
|
"loss": 6.7865,
|
|
"mean_token_accuracy": 0.11544861868023873,
|
|
"num_tokens": 8110532.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.8296427726745605,
|
|
"epoch": 0.40077050671518005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990223445040031,
|
|
"loss": 6.7143,
|
|
"mean_token_accuracy": 0.12142985686659813,
|
|
"num_tokens": 8120991.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.763740015029907,
|
|
"epoch": 0.401305580822944,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990187809677004,
|
|
"loss": 6.6187,
|
|
"mean_token_accuracy": 0.11583676040172577,
|
|
"num_tokens": 8130737.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.621914052963257,
|
|
"epoch": 0.4018406549307079,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990152109628869,
|
|
"loss": 6.6428,
|
|
"mean_token_accuracy": 0.11762692779302597,
|
|
"num_tokens": 8142315.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.790521764755249,
|
|
"epoch": 0.40237572903847185,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004990116344896657,
|
|
"loss": 6.7367,
|
|
"mean_token_accuracy": 0.10920806154608727,
|
|
"num_tokens": 8153618.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.795371150970459,
|
|
"epoch": 0.40291080314623573,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049900805154814,
|
|
"loss": 6.681,
|
|
"mean_token_accuracy": 0.11820271760225295,
|
|
"num_tokens": 8164304.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.709203910827637,
|
|
"epoch": 0.40344587725399966,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990044621384134,
|
|
"loss": 6.6729,
|
|
"mean_token_accuracy": 0.11573547199368477,
|
|
"num_tokens": 8175289.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.818386125564575,
|
|
"epoch": 0.4039809513617636,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004990008662605893,
|
|
"loss": 6.7335,
|
|
"mean_token_accuracy": 0.1082306794822216,
|
|
"num_tokens": 8186274.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.820314836502075,
|
|
"epoch": 0.40451602546952753,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004989972639147717,
|
|
"loss": 6.6704,
|
|
"mean_token_accuracy": 0.11876931563019752,
|
|
"num_tokens": 8196380.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.734559679031372,
|
|
"epoch": 0.40505109957729146,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004989936551010646,
|
|
"loss": 6.7339,
|
|
"mean_token_accuracy": 0.11214953884482384,
|
|
"num_tokens": 8207204.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.630817031860351,
|
|
"epoch": 0.4055861736850554,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004989900398195722,
|
|
"loss": 6.6288,
|
|
"mean_token_accuracy": 0.12022271677851677,
|
|
"num_tokens": 8217745.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.71739935874939,
|
|
"epoch": 0.40612124779281933,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989864180703988,
|
|
"loss": 6.6365,
|
|
"mean_token_accuracy": 0.12018959075212479,
|
|
"num_tokens": 8228171.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.732503509521484,
|
|
"epoch": 0.4066563219005832,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004989827898536491,
|
|
"loss": 6.6778,
|
|
"mean_token_accuracy": 0.11271608099341393,
|
|
"num_tokens": 8239220.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.769748783111572,
|
|
"epoch": 0.40719139600834714,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989791551694279,
|
|
"loss": 6.7441,
|
|
"mean_token_accuracy": 0.1108921080827713,
|
|
"num_tokens": 8250363.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.749256992340088,
|
|
"epoch": 0.4077264701161111,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989755140178398,
|
|
"loss": 6.6972,
|
|
"mean_token_accuracy": 0.11420515179634094,
|
|
"num_tokens": 8261207.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.714679622650147,
|
|
"epoch": 0.408261544223875,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989718663989905,
|
|
"loss": 6.5966,
|
|
"mean_token_accuracy": 0.11439496502280236,
|
|
"num_tokens": 8272343.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.751222801208496,
|
|
"epoch": 0.40879661833163894,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989682123129849,
|
|
"loss": 6.6511,
|
|
"mean_token_accuracy": 0.11429359316825867,
|
|
"num_tokens": 8282677.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.628594398498535,
|
|
"epoch": 0.40933169243940287,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004989645517599286,
|
|
"loss": 6.6651,
|
|
"mean_token_accuracy": 0.1157628171145916,
|
|
"num_tokens": 8292753.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.7410119533538815,
|
|
"epoch": 0.4098667665471668,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989608847399275,
|
|
"loss": 6.6493,
|
|
"mean_token_accuracy": 0.11546954065561295,
|
|
"num_tokens": 8302747.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.788758563995361,
|
|
"epoch": 0.4104018406549307,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989572112530871,
|
|
"loss": 6.7205,
|
|
"mean_token_accuracy": 0.10800857022404671,
|
|
"num_tokens": 8314766.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.810330104827881,
|
|
"epoch": 0.4109369147626946,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989535312995139,
|
|
"loss": 6.7574,
|
|
"mean_token_accuracy": 0.11394470632076263,
|
|
"num_tokens": 8325791.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.70790843963623,
|
|
"epoch": 0.41147198887045855,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004989498448793139,
|
|
"loss": 6.669,
|
|
"mean_token_accuracy": 0.11584601849317551,
|
|
"num_tokens": 8335809.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.735694932937622,
|
|
"epoch": 0.4120070629782225,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989461519925935,
|
|
"loss": 6.6678,
|
|
"mean_token_accuracy": 0.11307423189282417,
|
|
"num_tokens": 8347505.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.809847497940064,
|
|
"epoch": 0.4125421370859864,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004989424526394596,
|
|
"loss": 6.6906,
|
|
"mean_token_accuracy": 0.1093782402575016,
|
|
"num_tokens": 8358363.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.754508018493652,
|
|
"epoch": 0.41307721119375035,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989387468200187,
|
|
"loss": 6.6878,
|
|
"mean_token_accuracy": 0.11631895303726196,
|
|
"num_tokens": 8369076.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.798090124130249,
|
|
"epoch": 0.4136122853015143,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000498935034534378,
|
|
"loss": 6.7307,
|
|
"mean_token_accuracy": 0.11500347554683685,
|
|
"num_tokens": 8380071.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.767126131057739,
|
|
"epoch": 0.41414735940927816,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004989313157826446,
|
|
"loss": 6.6987,
|
|
"mean_token_accuracy": 0.11583667397499084,
|
|
"num_tokens": 8390574.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.7329933643341064,
|
|
"epoch": 0.4146824335170421,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000498927590564926,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.11751513332128524,
|
|
"num_tokens": 8401154.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.821478986740113,
|
|
"epoch": 0.415217507624806,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989238588813296,
|
|
"loss": 6.7806,
|
|
"mean_token_accuracy": 0.10575368329882621,
|
|
"num_tokens": 8412113.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.873749494552612,
|
|
"epoch": 0.41575258173256996,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004989201207319634,
|
|
"loss": 6.7507,
|
|
"mean_token_accuracy": 0.1134581632912159,
|
|
"num_tokens": 8422734.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.756129789352417,
|
|
"epoch": 0.4162876558403339,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989163761169351,
|
|
"loss": 6.6987,
|
|
"mean_token_accuracy": 0.11055214703083038,
|
|
"num_tokens": 8433647.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.7640749454498295,
|
|
"epoch": 0.4168227299480978,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989126250363529,
|
|
"loss": 6.7122,
|
|
"mean_token_accuracy": 0.1113808773458004,
|
|
"num_tokens": 8444726.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.79126296043396,
|
|
"epoch": 0.41735780405586176,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004989088674903251,
|
|
"loss": 6.7312,
|
|
"mean_token_accuracy": 0.10955160930752754,
|
|
"num_tokens": 8455351.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.740010356903076,
|
|
"epoch": 0.41789287816362564,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989051034789602,
|
|
"loss": 6.7066,
|
|
"mean_token_accuracy": 0.12177284359931946,
|
|
"num_tokens": 8466423.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.71815242767334,
|
|
"epoch": 0.41842795227138957,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000498901333002367,
|
|
"loss": 6.6361,
|
|
"mean_token_accuracy": 0.11695924326777458,
|
|
"num_tokens": 8475841.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.785331583023071,
|
|
"epoch": 0.4189630263791535,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988975560606541,
|
|
"loss": 6.7534,
|
|
"mean_token_accuracy": 0.11003556698560715,
|
|
"num_tokens": 8487656.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.797838401794434,
|
|
"epoch": 0.41949810048691744,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004988937726539308,
|
|
"loss": 6.7546,
|
|
"mean_token_accuracy": 0.10969007089734077,
|
|
"num_tokens": 8497959.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.729758834838867,
|
|
"epoch": 0.42003317459468137,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004988899827823062,
|
|
"loss": 6.6696,
|
|
"mean_token_accuracy": 0.11463452354073525,
|
|
"num_tokens": 8508228.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.794983673095703,
|
|
"epoch": 0.4205682487024453,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00049888618644589,
|
|
"loss": 6.717,
|
|
"mean_token_accuracy": 0.1153414785861969,
|
|
"num_tokens": 8518999.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.710626888275146,
|
|
"epoch": 0.42110332281020924,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988823836447916,
|
|
"loss": 6.7565,
|
|
"mean_token_accuracy": 0.11152829825878144,
|
|
"num_tokens": 8529583.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.845953941345215,
|
|
"epoch": 0.4216383969179731,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004988785743791207,
|
|
"loss": 6.8116,
|
|
"mean_token_accuracy": 0.11097450107336045,
|
|
"num_tokens": 8540069.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.8115967273712155,
|
|
"epoch": 0.42217347102573705,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988747586489876,
|
|
"loss": 6.6778,
|
|
"mean_token_accuracy": 0.11443818733096123,
|
|
"num_tokens": 8550441.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.702272653579712,
|
|
"epoch": 0.422708545133501,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498870936454502,
|
|
"loss": 6.6471,
|
|
"mean_token_accuracy": 0.11951410844922065,
|
|
"num_tokens": 8560257.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.736100673675537,
|
|
"epoch": 0.4232436192412649,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988671077957749,
|
|
"loss": 6.7287,
|
|
"mean_token_accuracy": 0.11796722114086151,
|
|
"num_tokens": 8570991.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.852146434783935,
|
|
"epoch": 0.42377869334902885,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988632726729164,
|
|
"loss": 6.7792,
|
|
"mean_token_accuracy": 0.10974573194980622,
|
|
"num_tokens": 8583668.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.802029323577881,
|
|
"epoch": 0.4243137674567928,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988594310860374,
|
|
"loss": 6.7134,
|
|
"mean_token_accuracy": 0.11194633021950721,
|
|
"num_tokens": 8593727.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.697398519515991,
|
|
"epoch": 0.4248488415645567,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988555830352485,
|
|
"loss": 6.7122,
|
|
"mean_token_accuracy": 0.11545829698443413,
|
|
"num_tokens": 8605470.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.822403383255005,
|
|
"epoch": 0.4253839156723206,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004988517285206614,
|
|
"loss": 6.6439,
|
|
"mean_token_accuracy": 0.11119706183671951,
|
|
"num_tokens": 8617176.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.7473792552948,
|
|
"epoch": 0.4259189897800845,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004988478675423871,
|
|
"loss": 6.7288,
|
|
"mean_token_accuracy": 0.11152340099215508,
|
|
"num_tokens": 8627756.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.716528797149659,
|
|
"epoch": 0.42645406388784846,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988440001005369,
|
|
"loss": 6.6705,
|
|
"mean_token_accuracy": 0.11469498351216316,
|
|
"num_tokens": 8637766.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.825556993484497,
|
|
"epoch": 0.4269891379956124,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988401261952227,
|
|
"loss": 6.706,
|
|
"mean_token_accuracy": 0.11419713199138641,
|
|
"num_tokens": 8648562.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.837621450424194,
|
|
"epoch": 0.4275242121033763,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004988362458265565,
|
|
"loss": 6.7268,
|
|
"mean_token_accuracy": 0.1081519827246666,
|
|
"num_tokens": 8658393.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.648343229293824,
|
|
"epoch": 0.42805928621114026,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004988323589946499,
|
|
"loss": 6.6506,
|
|
"mean_token_accuracy": 0.115006672590971,
|
|
"num_tokens": 8668365.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.728427124023438,
|
|
"epoch": 0.4285943603189042,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988284656996156,
|
|
"loss": 6.6856,
|
|
"mean_token_accuracy": 0.11702194884419441,
|
|
"num_tokens": 8679228.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.747385787963867,
|
|
"epoch": 0.42912943442666807,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988245659415656,
|
|
"loss": 6.5737,
|
|
"mean_token_accuracy": 0.12146354094147682,
|
|
"num_tokens": 8688940.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.764614677429199,
|
|
"epoch": 0.429664508534432,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988206597206129,
|
|
"loss": 6.7362,
|
|
"mean_token_accuracy": 0.11172115281224251,
|
|
"num_tokens": 8699923.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.70063853263855,
|
|
"epoch": 0.43019958264219593,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00049881674703687,
|
|
"loss": 6.5675,
|
|
"mean_token_accuracy": 0.11938829645514488,
|
|
"num_tokens": 8710445.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.7165913581848145,
|
|
"epoch": 0.43073465674995987,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988128278904499,
|
|
"loss": 6.7093,
|
|
"mean_token_accuracy": 0.11114189699292183,
|
|
"num_tokens": 8720686.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.800965404510498,
|
|
"epoch": 0.4312697308577238,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000498808902281466,
|
|
"loss": 6.7301,
|
|
"mean_token_accuracy": 0.11561328247189522,
|
|
"num_tokens": 8732122.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.702591466903686,
|
|
"epoch": 0.43180480496548773,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988049702100315,
|
|
"loss": 6.6836,
|
|
"mean_token_accuracy": 0.11544679328799248,
|
|
"num_tokens": 8744122.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.817325067520142,
|
|
"epoch": 0.43233987907325166,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004988010316762598,
|
|
"loss": 6.6752,
|
|
"mean_token_accuracy": 0.11280133873224259,
|
|
"num_tokens": 8754758.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.716195344924927,
|
|
"epoch": 0.4328749531810156,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987970866802649,
|
|
"loss": 6.7162,
|
|
"mean_token_accuracy": 0.10749638751149178,
|
|
"num_tokens": 8766577.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.725743436813355,
|
|
"epoch": 0.4334100272887795,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004987931352221605,
|
|
"loss": 6.6932,
|
|
"mean_token_accuracy": 0.11314602792263032,
|
|
"num_tokens": 8777698.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.784752559661865,
|
|
"epoch": 0.4339451013965434,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987891773020606,
|
|
"loss": 6.7042,
|
|
"mean_token_accuracy": 0.1157095618546009,
|
|
"num_tokens": 8788637.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.75966739654541,
|
|
"epoch": 0.43448017550430734,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004987852129200799,
|
|
"loss": 6.6904,
|
|
"mean_token_accuracy": 0.12118750438094139,
|
|
"num_tokens": 8799709.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.763680171966553,
|
|
"epoch": 0.4350152496120713,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004987812420763326,
|
|
"loss": 6.6982,
|
|
"mean_token_accuracy": 0.11437618657946587,
|
|
"num_tokens": 8810469.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.7934815883636475,
|
|
"epoch": 0.4355503237198352,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004987772647709333,
|
|
"loss": 6.6646,
|
|
"mean_token_accuracy": 0.1136926494538784,
|
|
"num_tokens": 8821142.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.67820553779602,
|
|
"epoch": 0.43608539782759914,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000498773281003997,
|
|
"loss": 6.6126,
|
|
"mean_token_accuracy": 0.1220873899757862,
|
|
"num_tokens": 8832951.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.693231391906738,
|
|
"epoch": 0.4366204719353631,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004987692907756385,
|
|
"loss": 6.7212,
|
|
"mean_token_accuracy": 0.11040145382285119,
|
|
"num_tokens": 8843579.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.709018087387085,
|
|
"epoch": 0.43715554604312695,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987652940859733,
|
|
"loss": 6.6616,
|
|
"mean_token_accuracy": 0.1068007379770279,
|
|
"num_tokens": 8854612.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.724940013885498,
|
|
"epoch": 0.4376906201508909,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987612909351167,
|
|
"loss": 6.6025,
|
|
"mean_token_accuracy": 0.11898693069815636,
|
|
"num_tokens": 8865584.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.678734683990479,
|
|
"epoch": 0.4382256942586548,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987572813231842,
|
|
"loss": 6.6436,
|
|
"mean_token_accuracy": 0.12159312292933463,
|
|
"num_tokens": 8876662.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.733673048019409,
|
|
"epoch": 0.43876076836641875,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987532652502917,
|
|
"loss": 6.6882,
|
|
"mean_token_accuracy": 0.11322307661175728,
|
|
"num_tokens": 8887249.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.705870485305786,
|
|
"epoch": 0.4392958424741827,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004987492427165551,
|
|
"loss": 6.5221,
|
|
"mean_token_accuracy": 0.1308815859258175,
|
|
"num_tokens": 8898635.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.666793918609619,
|
|
"epoch": 0.4398309165819466,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987452137220906,
|
|
"loss": 6.6872,
|
|
"mean_token_accuracy": 0.11336872428655624,
|
|
"num_tokens": 8908794.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.823773908615112,
|
|
"epoch": 0.44036599068971055,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004987411782670144,
|
|
"loss": 6.7029,
|
|
"mean_token_accuracy": 0.1101386807858944,
|
|
"num_tokens": 8919015.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.81250901222229,
|
|
"epoch": 0.44090106479747443,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987371363514431,
|
|
"loss": 6.7245,
|
|
"mean_token_accuracy": 0.1101568505167961,
|
|
"num_tokens": 8929028.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.635428714752197,
|
|
"epoch": 0.44143613890523836,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004987330879754933,
|
|
"loss": 6.6238,
|
|
"mean_token_accuracy": 0.11282940730452537,
|
|
"num_tokens": 8939789.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.688043451309204,
|
|
"epoch": 0.4419712130130023,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004987290331392823,
|
|
"loss": 6.6084,
|
|
"mean_token_accuracy": 0.11892879232764245,
|
|
"num_tokens": 8950657.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.805780267715454,
|
|
"epoch": 0.44250628712076623,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004987249718429269,
|
|
"loss": 6.7204,
|
|
"mean_token_accuracy": 0.11565686762332916,
|
|
"num_tokens": 8960744.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.7055583000183105,
|
|
"epoch": 0.44304136122853016,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004987209040865441,
|
|
"loss": 6.5687,
|
|
"mean_token_accuracy": 0.12038824409246444,
|
|
"num_tokens": 8972411.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.730427551269531,
|
|
"epoch": 0.4435764353362941,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004987168298702519,
|
|
"loss": 6.7317,
|
|
"mean_token_accuracy": 0.1166949637234211,
|
|
"num_tokens": 8982818.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.724998998641968,
|
|
"epoch": 0.44411150944405803,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004987127491941675,
|
|
"loss": 6.6675,
|
|
"mean_token_accuracy": 0.11578278020024299,
|
|
"num_tokens": 8993227.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.677845239639282,
|
|
"epoch": 0.4446465835518219,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987086620584091,
|
|
"loss": 6.6091,
|
|
"mean_token_accuracy": 0.1162223570048809,
|
|
"num_tokens": 9003796.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.727551651000977,
|
|
"epoch": 0.44518165765958584,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004987045684630944,
|
|
"loss": 6.6369,
|
|
"mean_token_accuracy": 0.1215149775147438,
|
|
"num_tokens": 9014931.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.773304080963134,
|
|
"epoch": 0.44571673176734977,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004987004684083417,
|
|
"loss": 6.695,
|
|
"mean_token_accuracy": 0.11384897977113724,
|
|
"num_tokens": 9025312.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.698511838912964,
|
|
"epoch": 0.4462518058751137,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004986963618942694,
|
|
"loss": 6.6607,
|
|
"mean_token_accuracy": 0.12171419262886048,
|
|
"num_tokens": 9035563.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.79593334197998,
|
|
"epoch": 0.44678687998287764,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986922489209961,
|
|
"loss": 6.6928,
|
|
"mean_token_accuracy": 0.11618542000651359,
|
|
"num_tokens": 9046065.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.759232664108277,
|
|
"epoch": 0.44732195409064157,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004986881294886406,
|
|
"loss": 6.5975,
|
|
"mean_token_accuracy": 0.12073868811130524,
|
|
"num_tokens": 9056696.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.701839923858643,
|
|
"epoch": 0.4478570281984055,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986840035973218,
|
|
"loss": 6.6752,
|
|
"mean_token_accuracy": 0.11579028517007828,
|
|
"num_tokens": 9067035.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.638756370544433,
|
|
"epoch": 0.4483921023061694,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986798712471588,
|
|
"loss": 6.6443,
|
|
"mean_token_accuracy": 0.11565731018781662,
|
|
"num_tokens": 9078253.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.800721168518066,
|
|
"epoch": 0.4489271764139333,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004986757324382709,
|
|
"loss": 6.7076,
|
|
"mean_token_accuracy": 0.10884766504168511,
|
|
"num_tokens": 9088184.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.8079078674316404,
|
|
"epoch": 0.44946225052169725,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004986715871707777,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.10660546869039536,
|
|
"num_tokens": 9099321.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.796434831619263,
|
|
"epoch": 0.4499973246294612,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004986674354447988,
|
|
"loss": 6.7953,
|
|
"mean_token_accuracy": 0.11461175382137298,
|
|
"num_tokens": 9111410.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.752979707717896,
|
|
"epoch": 0.4505323987372251,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004986632772604543,
|
|
"loss": 6.6154,
|
|
"mean_token_accuracy": 0.116925810277462,
|
|
"num_tokens": 9121932.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.650112581253052,
|
|
"epoch": 0.45106747284498905,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986591126178639,
|
|
"loss": 6.7024,
|
|
"mean_token_accuracy": 0.12244073674082756,
|
|
"num_tokens": 9132686.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.689599466323853,
|
|
"epoch": 0.451602546952753,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004986549415171482,
|
|
"loss": 6.636,
|
|
"mean_token_accuracy": 0.1178563304245472,
|
|
"num_tokens": 9143582.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.856327199935913,
|
|
"epoch": 0.45213762106051686,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986507639584274,
|
|
"loss": 6.7034,
|
|
"mean_token_accuracy": 0.11118230447173119,
|
|
"num_tokens": 9156173.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.729980373382569,
|
|
"epoch": 0.4526726951682808,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986465799418223,
|
|
"loss": 6.7019,
|
|
"mean_token_accuracy": 0.1158701390028,
|
|
"num_tokens": 9166882.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.663695859909057,
|
|
"epoch": 0.4532077692760447,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986423894674534,
|
|
"loss": 6.6983,
|
|
"mean_token_accuracy": 0.10844632685184478,
|
|
"num_tokens": 9177525.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.789501523971557,
|
|
"epoch": 0.45374284338380866,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004986381925354422,
|
|
"loss": 6.6582,
|
|
"mean_token_accuracy": 0.11211462765932083,
|
|
"num_tokens": 9188586.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.768905687332153,
|
|
"epoch": 0.4542779174915726,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004986339891459094,
|
|
"loss": 6.5657,
|
|
"mean_token_accuracy": 0.11805166080594062,
|
|
"num_tokens": 9199920.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.551817274093628,
|
|
"epoch": 0.4548129915993365,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986297792989768,
|
|
"loss": 6.5788,
|
|
"mean_token_accuracy": 0.12117914929986,
|
|
"num_tokens": 9210923.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.800738334655762,
|
|
"epoch": 0.45534806570710046,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004986255629947655,
|
|
"loss": 6.7368,
|
|
"mean_token_accuracy": 0.11400101706385612,
|
|
"num_tokens": 9221459.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.817624425888061,
|
|
"epoch": 0.45588313981486434,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986213402333978,
|
|
"loss": 6.6856,
|
|
"mean_token_accuracy": 0.11327185034751892,
|
|
"num_tokens": 9231768.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.737683629989624,
|
|
"epoch": 0.45641821392262827,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986171110149951,
|
|
"loss": 6.6689,
|
|
"mean_token_accuracy": 0.11119912713766097,
|
|
"num_tokens": 9242230.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.731328105926513,
|
|
"epoch": 0.4569532880303922,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986128753396798,
|
|
"loss": 6.5908,
|
|
"mean_token_accuracy": 0.11729067414999009,
|
|
"num_tokens": 9252485.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.63718695640564,
|
|
"epoch": 0.45748836213815613,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004986086332075742,
|
|
"loss": 6.6474,
|
|
"mean_token_accuracy": 0.11773178726434708,
|
|
"num_tokens": 9263014.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.737563610076904,
|
|
"epoch": 0.45802343624592007,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004986043846188006,
|
|
"loss": 6.6907,
|
|
"mean_token_accuracy": 0.12012004256248474,
|
|
"num_tokens": 9273777.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.647010040283203,
|
|
"epoch": 0.458558510353684,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000498600129573482,
|
|
"loss": 6.6115,
|
|
"mean_token_accuracy": 0.11131804138422012,
|
|
"num_tokens": 9284738.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.825235176086426,
|
|
"epoch": 0.45909358446144793,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000498595868071741,
|
|
"loss": 6.6814,
|
|
"mean_token_accuracy": 0.11572107002139091,
|
|
"num_tokens": 9295921.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.783471202850341,
|
|
"epoch": 0.4596286585692118,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004985916001137006,
|
|
"loss": 6.6691,
|
|
"mean_token_accuracy": 0.11060161292552947,
|
|
"num_tokens": 9306568.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.6858655452728275,
|
|
"epoch": 0.46016373267697575,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985873256994843,
|
|
"loss": 6.607,
|
|
"mean_token_accuracy": 0.114323341101408,
|
|
"num_tokens": 9316468.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.6945489883422855,
|
|
"epoch": 0.4606988067847397,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985830448292154,
|
|
"loss": 6.6939,
|
|
"mean_token_accuracy": 0.11146686300635338,
|
|
"num_tokens": 9328185.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.783587503433227,
|
|
"epoch": 0.4612338808925036,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985787575030175,
|
|
"loss": 6.6404,
|
|
"mean_token_accuracy": 0.11596988141536713,
|
|
"num_tokens": 9338591.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.729450464248657,
|
|
"epoch": 0.46176895500026754,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985744637210144,
|
|
"loss": 6.6646,
|
|
"mean_token_accuracy": 0.11485074758529663,
|
|
"num_tokens": 9349286.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.733769798278809,
|
|
"epoch": 0.4623040291080315,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00049857016348333,
|
|
"loss": 6.6445,
|
|
"mean_token_accuracy": 0.11966344341635704,
|
|
"num_tokens": 9359752.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.770653200149536,
|
|
"epoch": 0.4628391032157954,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985658567900886,
|
|
"loss": 6.7118,
|
|
"mean_token_accuracy": 0.10913585424423218,
|
|
"num_tokens": 9371823.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.616776466369629,
|
|
"epoch": 0.4633741773235593,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004985615436414145,
|
|
"loss": 6.5723,
|
|
"mean_token_accuracy": 0.11298257783055306,
|
|
"num_tokens": 9383127.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.718986940383911,
|
|
"epoch": 0.4639092514313232,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004985572240374321,
|
|
"loss": 6.6758,
|
|
"mean_token_accuracy": 0.11775618195533752,
|
|
"num_tokens": 9394296.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.758514356613159,
|
|
"epoch": 0.46444432553908715,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004985528979782665,
|
|
"loss": 6.6659,
|
|
"mean_token_accuracy": 0.11210668310523034,
|
|
"num_tokens": 9405988.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.788887548446655,
|
|
"epoch": 0.4649793996468511,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004985485654640423,
|
|
"loss": 6.662,
|
|
"mean_token_accuracy": 0.11312065199017525,
|
|
"num_tokens": 9417479.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.646952819824219,
|
|
"epoch": 0.465514473754615,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004985442264948847,
|
|
"loss": 6.6233,
|
|
"mean_token_accuracy": 0.12258987501263618,
|
|
"num_tokens": 9428050.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.678357696533203,
|
|
"epoch": 0.46604954786237895,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004985398810709189,
|
|
"loss": 6.5779,
|
|
"mean_token_accuracy": 0.12279872298240661,
|
|
"num_tokens": 9438229.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.694482088088989,
|
|
"epoch": 0.4665846219701429,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985355291922704,
|
|
"loss": 6.6502,
|
|
"mean_token_accuracy": 0.1130458801984787,
|
|
"num_tokens": 9449611.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.6899035453796385,
|
|
"epoch": 0.46711969607790677,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000498531170859065,
|
|
"loss": 6.6153,
|
|
"mean_token_accuracy": 0.11360270753502846,
|
|
"num_tokens": 9460234.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.768774032592773,
|
|
"epoch": 0.4676547701856707,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004985268060714285,
|
|
"loss": 6.682,
|
|
"mean_token_accuracy": 0.11366551518440246,
|
|
"num_tokens": 9472136.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.685565567016601,
|
|
"epoch": 0.46818984429343463,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004985224348294868,
|
|
"loss": 6.6355,
|
|
"mean_token_accuracy": 0.11784549504518509,
|
|
"num_tokens": 9482602.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.7874668598175045,
|
|
"epoch": 0.46872491840119856,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004985180571333663,
|
|
"loss": 6.6296,
|
|
"mean_token_accuracy": 0.11935302391648292,
|
|
"num_tokens": 9493782.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.696510982513428,
|
|
"epoch": 0.4692599925089625,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004985136729831932,
|
|
"loss": 6.6032,
|
|
"mean_token_accuracy": 0.11815939024090767,
|
|
"num_tokens": 9504389.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.680622529983521,
|
|
"epoch": 0.46979506661672643,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004985092823790942,
|
|
"loss": 6.7378,
|
|
"mean_token_accuracy": 0.11527246832847596,
|
|
"num_tokens": 9515166.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.754097366333008,
|
|
"epoch": 0.47033014072449036,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004985048853211961,
|
|
"loss": 6.6354,
|
|
"mean_token_accuracy": 0.1160196453332901,
|
|
"num_tokens": 9525566.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.771543645858765,
|
|
"epoch": 0.47086521483225424,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000498500481809626,
|
|
"loss": 6.5404,
|
|
"mean_token_accuracy": 0.12670470625162125,
|
|
"num_tokens": 9536021.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.676743268966675,
|
|
"epoch": 0.4714002889400182,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004984960718445107,
|
|
"loss": 6.6619,
|
|
"mean_token_accuracy": 0.11299687251448631,
|
|
"num_tokens": 9546827.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.7357440948486325,
|
|
"epoch": 0.4719353630477821,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004984916554259778,
|
|
"loss": 6.779,
|
|
"mean_token_accuracy": 0.10542291179299354,
|
|
"num_tokens": 9558104.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.807965230941773,
|
|
"epoch": 0.47247043715554604,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004984872325541547,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.11875886842608452,
|
|
"num_tokens": 9568487.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.72672324180603,
|
|
"epoch": 0.47300551126331,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004984828032291692,
|
|
"loss": 6.6088,
|
|
"mean_token_accuracy": 0.12393661811947823,
|
|
"num_tokens": 9579509.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.716574716567993,
|
|
"epoch": 0.4735405853710739,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004984783674511492,
|
|
"loss": 6.6388,
|
|
"mean_token_accuracy": 0.11688132956624031,
|
|
"num_tokens": 9589931.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.7539482593536375,
|
|
"epoch": 0.47407565947883784,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004984739252202227,
|
|
"loss": 6.688,
|
|
"mean_token_accuracy": 0.11628134176135063,
|
|
"num_tokens": 9599764.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.757166957855224,
|
|
"epoch": 0.4746107335866017,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000498469476536518,
|
|
"loss": 6.6493,
|
|
"mean_token_accuracy": 0.11907771229743958,
|
|
"num_tokens": 9611145.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.693255519866943,
|
|
"epoch": 0.47514580769436565,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004984650214001636,
|
|
"loss": 6.6372,
|
|
"mean_token_accuracy": 0.11735451370477676,
|
|
"num_tokens": 9621441.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.723459720611572,
|
|
"epoch": 0.4756808818021296,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004984605598112881,
|
|
"loss": 6.6922,
|
|
"mean_token_accuracy": 0.11924364715814591,
|
|
"num_tokens": 9631874.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.672471523284912,
|
|
"epoch": 0.4762159559098935,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984560917700204,
|
|
"loss": 6.6712,
|
|
"mean_token_accuracy": 0.10813649892807006,
|
|
"num_tokens": 9643006.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.661323070526123,
|
|
"epoch": 0.47675103001765745,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004984516172764894,
|
|
"loss": 6.5508,
|
|
"mean_token_accuracy": 0.12179366350173951,
|
|
"num_tokens": 9653897.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.691922187805176,
|
|
"epoch": 0.4772861041254214,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984471363308243,
|
|
"loss": 6.6301,
|
|
"mean_token_accuracy": 0.11610539332032203,
|
|
"num_tokens": 9664460.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.757071876525879,
|
|
"epoch": 0.4778211782331853,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004984426489331546,
|
|
"loss": 6.6456,
|
|
"mean_token_accuracy": 0.11981170177459717,
|
|
"num_tokens": 9674534.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.799601793289185,
|
|
"epoch": 0.4783562523409492,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984381550836097,
|
|
"loss": 6.7187,
|
|
"mean_token_accuracy": 0.11188295409083367,
|
|
"num_tokens": 9684828.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.758711624145508,
|
|
"epoch": 0.47889132644871313,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004984336547823196,
|
|
"loss": 6.6933,
|
|
"mean_token_accuracy": 0.11652329340577125,
|
|
"num_tokens": 9694536.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.68265733718872,
|
|
"epoch": 0.47942640055647706,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498429148029414,
|
|
"loss": 6.5507,
|
|
"mean_token_accuracy": 0.12725870534777642,
|
|
"num_tokens": 9705715.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.687233924865723,
|
|
"epoch": 0.479961474664241,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004984246348250233,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.12101843059062958,
|
|
"num_tokens": 9717505.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.6921549320220945,
|
|
"epoch": 0.4804965487720049,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004984201151692775,
|
|
"loss": 6.5105,
|
|
"mean_token_accuracy": 0.11698877215385436,
|
|
"num_tokens": 9727910.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.705784749984741,
|
|
"epoch": 0.48103162287976886,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984155890623074,
|
|
"loss": 6.6029,
|
|
"mean_token_accuracy": 0.1223738431930542,
|
|
"num_tokens": 9738528.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.68727297782898,
|
|
"epoch": 0.4815666969875328,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004984110565042435,
|
|
"loss": 6.6413,
|
|
"mean_token_accuracy": 0.1166694700717926,
|
|
"num_tokens": 9749744.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.786122751235962,
|
|
"epoch": 0.48210177109529667,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004984065174952168,
|
|
"loss": 6.6433,
|
|
"mean_token_accuracy": 0.11737963259220123,
|
|
"num_tokens": 9759968.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.7307963371276855,
|
|
"epoch": 0.4826368452030606,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004984019720353582,
|
|
"loss": 6.6591,
|
|
"mean_token_accuracy": 0.11601342111825944,
|
|
"num_tokens": 9769791.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.613153791427612,
|
|
"epoch": 0.48317191931082454,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004983974201247991,
|
|
"loss": 6.6165,
|
|
"mean_token_accuracy": 0.12467638105154037,
|
|
"num_tokens": 9780369.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.6523078918457035,
|
|
"epoch": 0.48370699341858847,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004983928617636709,
|
|
"loss": 6.6717,
|
|
"mean_token_accuracy": 0.1142366997897625,
|
|
"num_tokens": 9791125.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.807734060287475,
|
|
"epoch": 0.4842420675263524,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004983882969521052,
|
|
"loss": 6.6638,
|
|
"mean_token_accuracy": 0.11914790123701095,
|
|
"num_tokens": 9801697.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.810341739654541,
|
|
"epoch": 0.48477714163411634,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004983837256902338,
|
|
"loss": 6.704,
|
|
"mean_token_accuracy": 0.11736872941255569,
|
|
"num_tokens": 9812171.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.725469064712525,
|
|
"epoch": 0.48531221574188027,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004983791479781887,
|
|
"loss": 6.5492,
|
|
"mean_token_accuracy": 0.12601315155625342,
|
|
"num_tokens": 9821596.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.740454387664795,
|
|
"epoch": 0.48584728984964415,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983745638161021,
|
|
"loss": 6.6622,
|
|
"mean_token_accuracy": 0.10746660381555558,
|
|
"num_tokens": 9831634.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.724510765075683,
|
|
"epoch": 0.4863823639574081,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004983699732041064,
|
|
"loss": 6.6345,
|
|
"mean_token_accuracy": 0.11942023038864136,
|
|
"num_tokens": 9841662.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.743528079986572,
|
|
"epoch": 0.486917438065172,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498365376142334,
|
|
"loss": 6.6175,
|
|
"mean_token_accuracy": 0.11318280696868896,
|
|
"num_tokens": 9853797.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.693184661865234,
|
|
"epoch": 0.48745251217293595,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004983607726309179,
|
|
"loss": 6.6665,
|
|
"mean_token_accuracy": 0.11820111572742462,
|
|
"num_tokens": 9865245.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.745386791229248,
|
|
"epoch": 0.4879875862806999,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983561626699908,
|
|
"loss": 6.7321,
|
|
"mean_token_accuracy": 0.10730336830019951,
|
|
"num_tokens": 9876207.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.771791172027588,
|
|
"epoch": 0.4885226603884638,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004983515462596859,
|
|
"loss": 6.5706,
|
|
"mean_token_accuracy": 0.11805153340101242,
|
|
"num_tokens": 9887210.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.77590970993042,
|
|
"epoch": 0.48905773449622775,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004983469234001365,
|
|
"loss": 6.7364,
|
|
"mean_token_accuracy": 0.11187749877572059,
|
|
"num_tokens": 9899607.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.614283847808838,
|
|
"epoch": 0.4895928086039917,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000498342294091476,
|
|
"loss": 6.5198,
|
|
"mean_token_accuracy": 0.12553614974021912,
|
|
"num_tokens": 9909910.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.625487995147705,
|
|
"epoch": 0.49012788271175556,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004983376583338382,
|
|
"loss": 6.6568,
|
|
"mean_token_accuracy": 0.11543531715869904,
|
|
"num_tokens": 9922137.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.735957527160645,
|
|
"epoch": 0.4906629568195195,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004983330161273569,
|
|
"loss": 6.6388,
|
|
"mean_token_accuracy": 0.11887715309858322,
|
|
"num_tokens": 9932514.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.728844404220581,
|
|
"epoch": 0.4911980309272834,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004983283674721662,
|
|
"loss": 6.6983,
|
|
"mean_token_accuracy": 0.1141705684363842,
|
|
"num_tokens": 9943054.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.811689996719361,
|
|
"epoch": 0.49173310503504736,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004983237123684002,
|
|
"loss": 6.6487,
|
|
"mean_token_accuracy": 0.11451672837138176,
|
|
"num_tokens": 9953791.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.690435552597046,
|
|
"epoch": 0.4922681791428113,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004983190508161934,
|
|
"loss": 6.5993,
|
|
"mean_token_accuracy": 0.11774043142795562,
|
|
"num_tokens": 9964782.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.71423020362854,
|
|
"epoch": 0.4928032532505752,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004983143828156804,
|
|
"loss": 6.674,
|
|
"mean_token_accuracy": 0.11906063780188561,
|
|
"num_tokens": 9975843.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.751412296295166,
|
|
"epoch": 0.49333832735833916,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004983097083669959,
|
|
"loss": 6.6477,
|
|
"mean_token_accuracy": 0.12174972966313362,
|
|
"num_tokens": 9987060.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.72445158958435,
|
|
"epoch": 0.49387340146610303,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004983050274702751,
|
|
"loss": 6.6159,
|
|
"mean_token_accuracy": 0.11575492694973946,
|
|
"num_tokens": 9997380.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.6969047546386715,
|
|
"epoch": 0.49440847557386697,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004983003401256529,
|
|
"loss": 6.6723,
|
|
"mean_token_accuracy": 0.11978892460465432,
|
|
"num_tokens": 10007955.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.840445518493652,
|
|
"epoch": 0.4949435496816309,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982956463332647,
|
|
"loss": 6.7401,
|
|
"mean_token_accuracy": 0.11213290095329284,
|
|
"num_tokens": 10017645.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.699553489685059,
|
|
"epoch": 0.49547862378939483,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004982909460932463,
|
|
"loss": 6.6667,
|
|
"mean_token_accuracy": 0.1187513791024685,
|
|
"num_tokens": 10027619.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.6246099948883055,
|
|
"epoch": 0.49601369789715877,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000498286239405733,
|
|
"loss": 6.5487,
|
|
"mean_token_accuracy": 0.1270728625357151,
|
|
"num_tokens": 10037551.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.668668556213379,
|
|
"epoch": 0.4965487720049227,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000498281526270861,
|
|
"loss": 6.5738,
|
|
"mean_token_accuracy": 0.126234732568264,
|
|
"num_tokens": 10047771.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.833411169052124,
|
|
"epoch": 0.49708384611268663,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982768066887663,
|
|
"loss": 6.7107,
|
|
"mean_token_accuracy": 0.11156112849712371,
|
|
"num_tokens": 10058771.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.687218379974365,
|
|
"epoch": 0.4976189202204505,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004982720806595851,
|
|
"loss": 6.5786,
|
|
"mean_token_accuracy": 0.1209044374525547,
|
|
"num_tokens": 10070318.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.636781406402588,
|
|
"epoch": 0.49815399432821444,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982673481834541,
|
|
"loss": 6.6068,
|
|
"mean_token_accuracy": 0.11889650225639344,
|
|
"num_tokens": 10081810.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.646404218673706,
|
|
"epoch": 0.4986890684359784,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004982626092605097,
|
|
"loss": 6.6221,
|
|
"mean_token_accuracy": 0.1171889565885067,
|
|
"num_tokens": 10091724.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.777220296859741,
|
|
"epoch": 0.4992241425437423,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982578638908888,
|
|
"loss": 6.6099,
|
|
"mean_token_accuracy": 0.11882191374897957,
|
|
"num_tokens": 10102510.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.6920019626617435,
|
|
"epoch": 0.49975921665150624,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004982531120747286,
|
|
"loss": 6.6661,
|
|
"mean_token_accuracy": 0.11249755322933197,
|
|
"num_tokens": 10112636.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.652344703674316,
|
|
"epoch": 0.5002942907592701,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000498248353812166,
|
|
"loss": 6.6787,
|
|
"mean_token_accuracy": 0.11986306384205818,
|
|
"num_tokens": 10123562.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.767915964126587,
|
|
"epoch": 0.5008293648670341,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004982435891033387,
|
|
"loss": 6.6374,
|
|
"mean_token_accuracy": 0.1114320233464241,
|
|
"num_tokens": 10134731.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.7398899555206295,
|
|
"epoch": 0.501364438974798,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000498238817948384,
|
|
"loss": 6.6234,
|
|
"mean_token_accuracy": 0.11613459065556526,
|
|
"num_tokens": 10145232.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.673232889175415,
|
|
"epoch": 0.501899513082562,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004982340403474398,
|
|
"loss": 6.5915,
|
|
"mean_token_accuracy": 0.1116428665816784,
|
|
"num_tokens": 10155857.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.683508396148682,
|
|
"epoch": 0.5024345871903259,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004982292563006441,
|
|
"loss": 6.5975,
|
|
"mean_token_accuracy": 0.12228783667087555,
|
|
"num_tokens": 10166145.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.740499687194824,
|
|
"epoch": 0.5029696612980897,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498224465808135,
|
|
"loss": 6.7254,
|
|
"mean_token_accuracy": 0.11173807680606843,
|
|
"num_tokens": 10177086.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.775094699859619,
|
|
"epoch": 0.5035047354058537,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004982196688700509,
|
|
"loss": 6.6056,
|
|
"mean_token_accuracy": 0.11548131629824639,
|
|
"num_tokens": 10187120.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.700378704071045,
|
|
"epoch": 0.5040398095136176,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982148654865302,
|
|
"loss": 6.6714,
|
|
"mean_token_accuracy": 0.116058349609375,
|
|
"num_tokens": 10197784.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.731067323684693,
|
|
"epoch": 0.5045748836213816,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004982100556577115,
|
|
"loss": 6.5272,
|
|
"mean_token_accuracy": 0.12650172412395477,
|
|
"num_tokens": 10209373.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.75590672492981,
|
|
"epoch": 0.5051099577291455,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004982052393837338,
|
|
"loss": 6.662,
|
|
"mean_token_accuracy": 0.12109206095337868,
|
|
"num_tokens": 10220316.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.6641072750091555,
|
|
"epoch": 0.5056450318369095,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004982004166647363,
|
|
"loss": 6.555,
|
|
"mean_token_accuracy": 0.12492926642298699,
|
|
"num_tokens": 10230478.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.577092838287354,
|
|
"epoch": 0.5061801059446733,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981955875008582,
|
|
"loss": 6.6348,
|
|
"mean_token_accuracy": 0.11583661809563636,
|
|
"num_tokens": 10240641.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.696561050415039,
|
|
"epoch": 0.5067151800524372,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004981907518922387,
|
|
"loss": 6.6138,
|
|
"mean_token_accuracy": 0.12158278226852418,
|
|
"num_tokens": 10250676.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.828497314453125,
|
|
"epoch": 0.5072502541602012,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004981859098390177,
|
|
"loss": 6.6949,
|
|
"mean_token_accuracy": 0.11689818948507309,
|
|
"num_tokens": 10262016.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.777277851104737,
|
|
"epoch": 0.5077853282679651,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004981810613413348,
|
|
"loss": 6.6381,
|
|
"mean_token_accuracy": 0.12088718265295029,
|
|
"num_tokens": 10271985.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.707176303863525,
|
|
"epoch": 0.5083204023757291,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004981762063993302,
|
|
"loss": 6.6092,
|
|
"mean_token_accuracy": 0.12419556155800819,
|
|
"num_tokens": 10282156.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.672820425033569,
|
|
"epoch": 0.5088554764834929,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000498171345013144,
|
|
"loss": 6.6133,
|
|
"mean_token_accuracy": 0.1135848581790924,
|
|
"num_tokens": 10292576.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.647624206542969,
|
|
"epoch": 0.5093905505912569,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981664771829165,
|
|
"loss": 6.6234,
|
|
"mean_token_accuracy": 0.11965413317084313,
|
|
"num_tokens": 10303648.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.7490908145904545,
|
|
"epoch": 0.5099256246990208,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004981616029087884,
|
|
"loss": 6.5074,
|
|
"mean_token_accuracy": 0.12869232892990112,
|
|
"num_tokens": 10314275.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.696971416473389,
|
|
"epoch": 0.5104606988067847,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004981567221909004,
|
|
"loss": 6.6413,
|
|
"mean_token_accuracy": 0.11142453476786614,
|
|
"num_tokens": 10325386.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.657241535186768,
|
|
"epoch": 0.5109957729145487,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004981518350293935,
|
|
"loss": 6.6256,
|
|
"mean_token_accuracy": 0.117152751237154,
|
|
"num_tokens": 10335041.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.6835949420928955,
|
|
"epoch": 0.5115308470223126,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004981469414244086,
|
|
"loss": 6.5783,
|
|
"mean_token_accuracy": 0.12038632929325103,
|
|
"num_tokens": 10345746.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.611367559432983,
|
|
"epoch": 0.5120659211300765,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000498142041376087,
|
|
"loss": 6.6877,
|
|
"mean_token_accuracy": 0.11743063405156136,
|
|
"num_tokens": 10356995.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.6938282489776615,
|
|
"epoch": 0.5126009952378404,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004981371348845705,
|
|
"loss": 6.5878,
|
|
"mean_token_accuracy": 0.12293134033679962,
|
|
"num_tokens": 10368445.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.774974012374878,
|
|
"epoch": 0.5131360693456044,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004981322219500006,
|
|
"loss": 6.5345,
|
|
"mean_token_accuracy": 0.12403296306729317,
|
|
"num_tokens": 10378256.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.728860235214233,
|
|
"epoch": 0.5136711434533683,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000498127302572519,
|
|
"loss": 6.6166,
|
|
"mean_token_accuracy": 0.12460722997784615,
|
|
"num_tokens": 10388698.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.613707876205444,
|
|
"epoch": 0.5142062175611322,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981223767522679,
|
|
"loss": 6.6095,
|
|
"mean_token_accuracy": 0.1258344203233719,
|
|
"num_tokens": 10399975.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.650073432922364,
|
|
"epoch": 0.5147412916688962,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981174444893896,
|
|
"loss": 6.6332,
|
|
"mean_token_accuracy": 0.1165822133421898,
|
|
"num_tokens": 10410480.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.698668336868286,
|
|
"epoch": 0.51527636577666,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004981125057840264,
|
|
"loss": 6.5883,
|
|
"mean_token_accuracy": 0.12364424616098404,
|
|
"num_tokens": 10421023.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.73700180053711,
|
|
"epoch": 0.515811439884424,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000498107560636321,
|
|
"loss": 6.6444,
|
|
"mean_token_accuracy": 0.11720668748021126,
|
|
"num_tokens": 10431152.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.710340929031372,
|
|
"epoch": 0.5163465139921879,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981026090464161,
|
|
"loss": 6.5545,
|
|
"mean_token_accuracy": 0.11190668419003487,
|
|
"num_tokens": 10441986.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.667047786712646,
|
|
"epoch": 0.5168815880999519,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004980976510144548,
|
|
"loss": 6.6265,
|
|
"mean_token_accuracy": 0.11371301561594009,
|
|
"num_tokens": 10452932.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.670616531372071,
|
|
"epoch": 0.5174166622077158,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004980926865405801,
|
|
"loss": 6.6947,
|
|
"mean_token_accuracy": 0.11335934177041054,
|
|
"num_tokens": 10463411.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.711873292922974,
|
|
"epoch": 0.5179517363154797,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004980877156249354,
|
|
"loss": 6.6047,
|
|
"mean_token_accuracy": 0.12172490879893302,
|
|
"num_tokens": 10474820.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.69803557395935,
|
|
"epoch": 0.5184868104232436,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004980827382676643,
|
|
"loss": 6.6062,
|
|
"mean_token_accuracy": 0.12013482972979546,
|
|
"num_tokens": 10485701.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.6993248462677,
|
|
"epoch": 0.5190218845310075,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004980777544689105,
|
|
"loss": 6.5844,
|
|
"mean_token_accuracy": 0.12140351459383965,
|
|
"num_tokens": 10495825.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.6549890518188475,
|
|
"epoch": 0.5195569586387715,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004980727642288178,
|
|
"loss": 6.5532,
|
|
"mean_token_accuracy": 0.12483188882470131,
|
|
"num_tokens": 10505847.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.708909797668457,
|
|
"epoch": 0.5200920327465354,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004980677675475305,
|
|
"loss": 6.6115,
|
|
"mean_token_accuracy": 0.11702346950769424,
|
|
"num_tokens": 10516596.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.7008233070373535,
|
|
"epoch": 0.5206271068542994,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004980627644251926,
|
|
"loss": 6.5554,
|
|
"mean_token_accuracy": 0.12680012062191964,
|
|
"num_tokens": 10528175.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.666421699523926,
|
|
"epoch": 0.5211621809620632,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004980577548619489,
|
|
"loss": 6.6463,
|
|
"mean_token_accuracy": 0.11762543395161629,
|
|
"num_tokens": 10540076.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.704486227035522,
|
|
"epoch": 0.5216972550698272,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004980527388579437,
|
|
"loss": 6.6509,
|
|
"mean_token_accuracy": 0.11489062979817391,
|
|
"num_tokens": 10552025.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.730651092529297,
|
|
"epoch": 0.5222323291775911,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004980477164133221,
|
|
"loss": 6.6459,
|
|
"mean_token_accuracy": 0.11571409627795219,
|
|
"num_tokens": 10562535.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.673344421386719,
|
|
"epoch": 0.522767403285355,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000498042687528229,
|
|
"loss": 6.5891,
|
|
"mean_token_accuracy": 0.11916224136948586,
|
|
"num_tokens": 10572989.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.67263822555542,
|
|
"epoch": 0.523302477393119,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004980376522028098,
|
|
"loss": 6.593,
|
|
"mean_token_accuracy": 0.12143604904413223,
|
|
"num_tokens": 10583033.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.745864820480347,
|
|
"epoch": 0.5238375515008828,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004980326104372095,
|
|
"loss": 6.6788,
|
|
"mean_token_accuracy": 0.11569171249866486,
|
|
"num_tokens": 10595205.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.741711235046386,
|
|
"epoch": 0.5243726256086468,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498027562231574,
|
|
"loss": 6.5294,
|
|
"mean_token_accuracy": 0.12321098670363426,
|
|
"num_tokens": 10605244.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.6820556640625,
|
|
"epoch": 0.5249076997164107,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000498022507586049,
|
|
"loss": 6.6115,
|
|
"mean_token_accuracy": 0.11927070915699005,
|
|
"num_tokens": 10615817.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.739273118972778,
|
|
"epoch": 0.5254427738241747,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004980174465007804,
|
|
"loss": 6.6369,
|
|
"mean_token_accuracy": 0.11548423320055008,
|
|
"num_tokens": 10627160.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.701236152648926,
|
|
"epoch": 0.5259778479319386,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004980123789759145,
|
|
"loss": 6.6288,
|
|
"mean_token_accuracy": 0.12106893360614776,
|
|
"num_tokens": 10637552.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.652713632583618,
|
|
"epoch": 0.5265129220397025,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004980073050115973,
|
|
"loss": 6.6653,
|
|
"mean_token_accuracy": 0.11880994513630867,
|
|
"num_tokens": 10648773.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.774326801300049,
|
|
"epoch": 0.5270479961474664,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004980022246079755,
|
|
"loss": 6.648,
|
|
"mean_token_accuracy": 0.11824332997202873,
|
|
"num_tokens": 10659537.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.787177610397339,
|
|
"epoch": 0.5275830702552303,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000497997137765196,
|
|
"loss": 6.6894,
|
|
"mean_token_accuracy": 0.11097191125154496,
|
|
"num_tokens": 10671390.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.683742904663086,
|
|
"epoch": 0.5281181443629943,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004979920444834054,
|
|
"loss": 6.5367,
|
|
"mean_token_accuracy": 0.12748999372124672,
|
|
"num_tokens": 10682389.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.614830350875854,
|
|
"epoch": 0.5286532184707582,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004979869447627508,
|
|
"loss": 6.5971,
|
|
"mean_token_accuracy": 0.11691061481833458,
|
|
"num_tokens": 10692400.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.658047914505005,
|
|
"epoch": 0.5291882925785222,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004979818386033795,
|
|
"loss": 6.5312,
|
|
"mean_token_accuracy": 0.12515476047992707,
|
|
"num_tokens": 10702396.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.689503908157349,
|
|
"epoch": 0.5297233666862861,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000497976726005439,
|
|
"loss": 6.6287,
|
|
"mean_token_accuracy": 0.11893323883414268,
|
|
"num_tokens": 10712863.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.741910123825074,
|
|
"epoch": 0.5302584407940499,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004979716069690768,
|
|
"loss": 6.6462,
|
|
"mean_token_accuracy": 0.1182481288909912,
|
|
"num_tokens": 10724234.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.784095907211304,
|
|
"epoch": 0.5307935149018139,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004979664814944409,
|
|
"loss": 6.6831,
|
|
"mean_token_accuracy": 0.11570578664541245,
|
|
"num_tokens": 10734405.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.778741836547852,
|
|
"epoch": 0.5313285890095778,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004979613495816791,
|
|
"loss": 6.6321,
|
|
"mean_token_accuracy": 0.11481416672468185,
|
|
"num_tokens": 10744573.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.718149614334107,
|
|
"epoch": 0.5318636631173418,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004979562112309397,
|
|
"loss": 6.6685,
|
|
"mean_token_accuracy": 0.11846106275916099,
|
|
"num_tokens": 10755555.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.686836433410645,
|
|
"epoch": 0.5323987372251057,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000497951066442371,
|
|
"loss": 6.6784,
|
|
"mean_token_accuracy": 0.11362863406538963,
|
|
"num_tokens": 10766493.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.777250051498413,
|
|
"epoch": 0.5329338113328697,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004979459152161215,
|
|
"loss": 6.6304,
|
|
"mean_token_accuracy": 0.11238612830638886,
|
|
"num_tokens": 10776735.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.693412494659424,
|
|
"epoch": 0.5334688854406335,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004979407575523402,
|
|
"loss": 6.6106,
|
|
"mean_token_accuracy": 0.12066147401928902,
|
|
"num_tokens": 10787500.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.690456914901733,
|
|
"epoch": 0.5340039595483974,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004979355934511757,
|
|
"loss": 6.6421,
|
|
"mean_token_accuracy": 0.1213709406554699,
|
|
"num_tokens": 10798002.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.6947132587432865,
|
|
"epoch": 0.5345390336561614,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004979304229127773,
|
|
"loss": 6.603,
|
|
"mean_token_accuracy": 0.11744242087006569,
|
|
"num_tokens": 10808982.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.681551885604859,
|
|
"epoch": 0.5350741077639253,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004979252459372944,
|
|
"loss": 6.5543,
|
|
"mean_token_accuracy": 0.1188325934112072,
|
|
"num_tokens": 10821619.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.6972753524780275,
|
|
"epoch": 0.5356091818716893,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979200625248761,
|
|
"loss": 6.5819,
|
|
"mean_token_accuracy": 0.12012385129928589,
|
|
"num_tokens": 10832344.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.714497470855713,
|
|
"epoch": 0.5361442559794531,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004979148726756725,
|
|
"loss": 6.5517,
|
|
"mean_token_accuracy": 0.11546608954668044,
|
|
"num_tokens": 10843149.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.675411415100098,
|
|
"epoch": 0.5366793300872171,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004979096763898333,
|
|
"loss": 6.5895,
|
|
"mean_token_accuracy": 0.12327387034893036,
|
|
"num_tokens": 10854590.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.743090057373047,
|
|
"epoch": 0.537214404194981,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004979044736675084,
|
|
"loss": 6.5735,
|
|
"mean_token_accuracy": 0.1187887541949749,
|
|
"num_tokens": 10865500.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.62291259765625,
|
|
"epoch": 0.5377494783027449,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004978992645088483,
|
|
"loss": 6.6013,
|
|
"mean_token_accuracy": 0.12360128462314605,
|
|
"num_tokens": 10876866.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.608084964752197,
|
|
"epoch": 0.5382845524105089,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497894048914003,
|
|
"loss": 6.5644,
|
|
"mean_token_accuracy": 0.11877960562705994,
|
|
"num_tokens": 10888627.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.748707246780396,
|
|
"epoch": 0.5388196265182728,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004978888268831236,
|
|
"loss": 6.6834,
|
|
"mean_token_accuracy": 0.11199896112084388,
|
|
"num_tokens": 10900992.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.803453779220581,
|
|
"epoch": 0.5393547006260367,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004978835984163606,
|
|
"loss": 6.706,
|
|
"mean_token_accuracy": 0.10869432613253593,
|
|
"num_tokens": 10912323.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.7344237804412845,
|
|
"epoch": 0.5398897747338006,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004978783635138649,
|
|
"loss": 6.668,
|
|
"mean_token_accuracy": 0.11559137850999832,
|
|
"num_tokens": 10923991.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.649737024307251,
|
|
"epoch": 0.5404248488415646,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004978731221757878,
|
|
"loss": 6.5077,
|
|
"mean_token_accuracy": 0.12473165020346641,
|
|
"num_tokens": 10934081.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.744383955001831,
|
|
"epoch": 0.5409599229493285,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004978678744022808,
|
|
"loss": 6.5946,
|
|
"mean_token_accuracy": 0.12126863822340965,
|
|
"num_tokens": 10944729.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.704465389251709,
|
|
"epoch": 0.5414949970570924,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000497862620193495,
|
|
"loss": 6.6605,
|
|
"mean_token_accuracy": 0.11823692843317986,
|
|
"num_tokens": 10955708.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.707375478744507,
|
|
"epoch": 0.5420300711648564,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004978573595495826,
|
|
"loss": 6.6073,
|
|
"mean_token_accuracy": 0.11719232201576232,
|
|
"num_tokens": 10966427.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.727742099761963,
|
|
"epoch": 0.5425651452726202,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000497852092470695,
|
|
"loss": 6.6438,
|
|
"mean_token_accuracy": 0.11848462522029876,
|
|
"num_tokens": 10977741.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.72758674621582,
|
|
"epoch": 0.5431002193803842,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004978468189569847,
|
|
"loss": 6.5907,
|
|
"mean_token_accuracy": 0.12363087236881257,
|
|
"num_tokens": 10989127.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.623909664154053,
|
|
"epoch": 0.5436352934881481,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004978415390086038,
|
|
"loss": 6.6138,
|
|
"mean_token_accuracy": 0.1132516548037529,
|
|
"num_tokens": 10999791.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.733290815353394,
|
|
"epoch": 0.5441703675959121,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004978362526257047,
|
|
"loss": 6.6768,
|
|
"mean_token_accuracy": 0.11073072254657745,
|
|
"num_tokens": 11010045.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.755488729476928,
|
|
"epoch": 0.544705441703676,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004978309598084403,
|
|
"loss": 6.5901,
|
|
"mean_token_accuracy": 0.11701643690466881,
|
|
"num_tokens": 11020729.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.685477638244629,
|
|
"epoch": 0.5452405158114398,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004978256605569631,
|
|
"loss": 6.6324,
|
|
"mean_token_accuracy": 0.11502022594213486,
|
|
"num_tokens": 11030641.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.73808445930481,
|
|
"epoch": 0.5457755899192038,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004978203548714262,
|
|
"loss": 6.6225,
|
|
"mean_token_accuracy": 0.11652573719620704,
|
|
"num_tokens": 11041533.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.728613567352295,
|
|
"epoch": 0.5463106640269677,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000497815042751983,
|
|
"loss": 6.5831,
|
|
"mean_token_accuracy": 0.11883758381009102,
|
|
"num_tokens": 11052170.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.692430257797241,
|
|
"epoch": 0.5468457381347317,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004978097241987868,
|
|
"loss": 6.5626,
|
|
"mean_token_accuracy": 0.12145586088299751,
|
|
"num_tokens": 11062872.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.696591234207153,
|
|
"epoch": 0.5473808122424956,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000497804399211991,
|
|
"loss": 6.651,
|
|
"mean_token_accuracy": 0.11530458331108093,
|
|
"num_tokens": 11074199.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.669123220443725,
|
|
"epoch": 0.5479158863502596,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004977990677917495,
|
|
"loss": 6.5981,
|
|
"mean_token_accuracy": 0.12415442764759063,
|
|
"num_tokens": 11083881.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.628405380249023,
|
|
"epoch": 0.5484509604580234,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004977937299382162,
|
|
"loss": 6.6456,
|
|
"mean_token_accuracy": 0.11557613834738731,
|
|
"num_tokens": 11094374.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.700885438919068,
|
|
"epoch": 0.5489860345657873,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004977883856515453,
|
|
"loss": 6.4988,
|
|
"mean_token_accuracy": 0.12920200750231742,
|
|
"num_tokens": 11105174.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.730715036392212,
|
|
"epoch": 0.5495211086735513,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000497783034931891,
|
|
"loss": 6.6494,
|
|
"mean_token_accuracy": 0.11611341387033462,
|
|
"num_tokens": 11117223.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.715358400344849,
|
|
"epoch": 0.5500561827813152,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000497777677779408,
|
|
"loss": 6.5769,
|
|
"mean_token_accuracy": 0.12152805551886559,
|
|
"num_tokens": 11127240.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.691393184661865,
|
|
"epoch": 0.5505912568890792,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004977723141942509,
|
|
"loss": 6.5762,
|
|
"mean_token_accuracy": 0.12875020131468773,
|
|
"num_tokens": 11137287.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.662536859512329,
|
|
"epoch": 0.551126330996843,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004977669441765743,
|
|
"loss": 6.7036,
|
|
"mean_token_accuracy": 0.11726266741752625,
|
|
"num_tokens": 11148988.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.754349040985107,
|
|
"epoch": 0.551661405104607,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004977615677265336,
|
|
"loss": 6.6381,
|
|
"mean_token_accuracy": 0.119845050573349,
|
|
"num_tokens": 11159874.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.7734168529510494,
|
|
"epoch": 0.5521964792123709,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000497756184844284,
|
|
"loss": 6.5946,
|
|
"mean_token_accuracy": 0.1255686677992344,
|
|
"num_tokens": 11170703.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.652176094055176,
|
|
"epoch": 0.5527315533201348,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977507955299809,
|
|
"loss": 6.486,
|
|
"mean_token_accuracy": 0.12536792755126952,
|
|
"num_tokens": 11182230.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.633540678024292,
|
|
"epoch": 0.5532666274278988,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004977453997837797,
|
|
"loss": 6.5519,
|
|
"mean_token_accuracy": 0.11289865449070931,
|
|
"num_tokens": 11192897.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.667209911346435,
|
|
"epoch": 0.5538017015356627,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004977399976058366,
|
|
"loss": 6.6543,
|
|
"mean_token_accuracy": 0.11275542676448821,
|
|
"num_tokens": 11203942.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.737595891952514,
|
|
"epoch": 0.5543367756434266,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004977345889963072,
|
|
"loss": 6.6878,
|
|
"mean_token_accuracy": 0.1157545953989029,
|
|
"num_tokens": 11214361.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.674620866775513,
|
|
"epoch": 0.5548718497511905,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004977291739553479,
|
|
"loss": 6.5811,
|
|
"mean_token_accuracy": 0.12168481573462486,
|
|
"num_tokens": 11225928.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.668534517288208,
|
|
"epoch": 0.5554069238589545,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004977237524831149,
|
|
"loss": 6.5477,
|
|
"mean_token_accuracy": 0.1131792739033699,
|
|
"num_tokens": 11236660.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.674350214004517,
|
|
"epoch": 0.5559419979667184,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977183245797649,
|
|
"loss": 6.5658,
|
|
"mean_token_accuracy": 0.12445326372981072,
|
|
"num_tokens": 11247272.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.749352884292603,
|
|
"epoch": 0.5564770720744823,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977128902454547,
|
|
"loss": 6.6736,
|
|
"mean_token_accuracy": 0.11154333502054214,
|
|
"num_tokens": 11258472.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.7011803150177,
|
|
"epoch": 0.5570121461822463,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004977074494803409,
|
|
"loss": 6.5757,
|
|
"mean_token_accuracy": 0.12596716955304146,
|
|
"num_tokens": 11268344.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.710012674331665,
|
|
"epoch": 0.5575472202900101,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004977020022845809,
|
|
"loss": 6.6642,
|
|
"mean_token_accuracy": 0.1116225503385067,
|
|
"num_tokens": 11279931.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.786263656616211,
|
|
"epoch": 0.5580822943977741,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004976965486583318,
|
|
"loss": 6.619,
|
|
"mean_token_accuracy": 0.11329972892999648,
|
|
"num_tokens": 11290595.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.69334135055542,
|
|
"epoch": 0.558617368505538,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004976910886017513,
|
|
"loss": 6.6231,
|
|
"mean_token_accuracy": 0.11819947510957718,
|
|
"num_tokens": 11300774.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.639355039596557,
|
|
"epoch": 0.559152442613302,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004976856221149969,
|
|
"loss": 6.4984,
|
|
"mean_token_accuracy": 0.12909843847155572,
|
|
"num_tokens": 11310288.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.635180282592773,
|
|
"epoch": 0.5596875167210659,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004976801491982263,
|
|
"loss": 6.6073,
|
|
"mean_token_accuracy": 0.1188632071018219,
|
|
"num_tokens": 11321599.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.753577756881714,
|
|
"epoch": 0.5602225908288297,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976746698515977,
|
|
"loss": 6.6551,
|
|
"mean_token_accuracy": 0.11815480217337608,
|
|
"num_tokens": 11331383.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.7181065559387205,
|
|
"epoch": 0.5607576649365937,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004976691840752694,
|
|
"loss": 6.6056,
|
|
"mean_token_accuracy": 0.1177519403398037,
|
|
"num_tokens": 11342085.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.724043464660644,
|
|
"epoch": 0.5612927390443576,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004976636918693996,
|
|
"loss": 6.6521,
|
|
"mean_token_accuracy": 0.1124167375266552,
|
|
"num_tokens": 11354061.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.7793741703033445,
|
|
"epoch": 0.5618278131521216,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004976581932341471,
|
|
"loss": 6.5874,
|
|
"mean_token_accuracy": 0.1198588714003563,
|
|
"num_tokens": 11364448.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.764813423156738,
|
|
"epoch": 0.5623628872598855,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004976526881696706,
|
|
"loss": 6.5707,
|
|
"mean_token_accuracy": 0.11909611076116562,
|
|
"num_tokens": 11374838.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.598009920120239,
|
|
"epoch": 0.5628979613676495,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004976471766761288,
|
|
"loss": 6.6143,
|
|
"mean_token_accuracy": 0.12120521515607834,
|
|
"num_tokens": 11385310.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.654865312576294,
|
|
"epoch": 0.5634330354754133,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004976416587536812,
|
|
"loss": 6.6152,
|
|
"mean_token_accuracy": 0.11421113684773446,
|
|
"num_tokens": 11396590.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.7150064468383786,
|
|
"epoch": 0.5639681095831772,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004976361344024871,
|
|
"loss": 6.5634,
|
|
"mean_token_accuracy": 0.11905626356601715,
|
|
"num_tokens": 11407218.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.613826513290405,
|
|
"epoch": 0.5645031836909412,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004976306036227056,
|
|
"loss": 6.5861,
|
|
"mean_token_accuracy": 0.11498884409666062,
|
|
"num_tokens": 11417716.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.735283041000367,
|
|
"epoch": 0.5650382577987051,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000497625066414497,
|
|
"loss": 6.6699,
|
|
"mean_token_accuracy": 0.11644284650683404,
|
|
"num_tokens": 11428295.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.76004843711853,
|
|
"epoch": 0.5655733319064691,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004976195227780207,
|
|
"loss": 6.5879,
|
|
"mean_token_accuracy": 0.11506432518363,
|
|
"num_tokens": 11439044.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.726730251312256,
|
|
"epoch": 0.566108406014233,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004976139727134371,
|
|
"loss": 6.5437,
|
|
"mean_token_accuracy": 0.1157782182097435,
|
|
"num_tokens": 11450029.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.680373620986939,
|
|
"epoch": 0.566643480121997,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004976084162209062,
|
|
"loss": 6.7158,
|
|
"mean_token_accuracy": 0.10938669890165328,
|
|
"num_tokens": 11461190.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.693241691589355,
|
|
"epoch": 0.5671785542297608,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004976028533005886,
|
|
"loss": 6.5658,
|
|
"mean_token_accuracy": 0.11855396032333373,
|
|
"num_tokens": 11472143.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.718105125427246,
|
|
"epoch": 0.5677136283375247,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004975972839526449,
|
|
"loss": 6.7015,
|
|
"mean_token_accuracy": 0.10698949694633483,
|
|
"num_tokens": 11483745.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.7316608905792235,
|
|
"epoch": 0.5682487024452887,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004975917081772358,
|
|
"loss": 6.5709,
|
|
"mean_token_accuracy": 0.11810784116387367,
|
|
"num_tokens": 11495695.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.704360294342041,
|
|
"epoch": 0.5687837765530526,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004975861259745225,
|
|
"loss": 6.6202,
|
|
"mean_token_accuracy": 0.11814290434122085,
|
|
"num_tokens": 11505576.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.6637914180755615,
|
|
"epoch": 0.5693188506608166,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004975805373446662,
|
|
"loss": 6.4714,
|
|
"mean_token_accuracy": 0.12663986161351204,
|
|
"num_tokens": 11516614.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.678481960296631,
|
|
"epoch": 0.5698539247685804,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000497574942287828,
|
|
"loss": 6.5993,
|
|
"mean_token_accuracy": 0.11633578389883041,
|
|
"num_tokens": 11528032.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.654755592346191,
|
|
"epoch": 0.5703889988763444,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.0004975693408041697,
|
|
"loss": 6.6168,
|
|
"mean_token_accuracy": 0.11541731208562851,
|
|
"num_tokens": 11538822.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.677396774291992,
|
|
"epoch": 0.5709240729841083,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004975637328938529,
|
|
"loss": 6.6259,
|
|
"mean_token_accuracy": 0.11113707721233368,
|
|
"num_tokens": 11548895.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.687600326538086,
|
|
"epoch": 0.5714591470918722,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004975581185570398,
|
|
"loss": 6.504,
|
|
"mean_token_accuracy": 0.1173204354941845,
|
|
"num_tokens": 11559613.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.692977571487427,
|
|
"epoch": 0.5719942211996362,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004975524977938921,
|
|
"loss": 6.5501,
|
|
"mean_token_accuracy": 0.12145494073629379,
|
|
"num_tokens": 11571092.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.6996602535247805,
|
|
"epoch": 0.5725292953074,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004975468706045722,
|
|
"loss": 6.6804,
|
|
"mean_token_accuracy": 0.12007683664560317,
|
|
"num_tokens": 11581448.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.734434652328491,
|
|
"epoch": 0.573064369415164,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004975412369892429,
|
|
"loss": 6.5773,
|
|
"mean_token_accuracy": 0.12340361326932907,
|
|
"num_tokens": 11592273.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.719641304016113,
|
|
"epoch": 0.5735994435229279,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004975355969480665,
|
|
"loss": 6.5633,
|
|
"mean_token_accuracy": 0.12459224984049797,
|
|
"num_tokens": 11602759.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.641370964050293,
|
|
"epoch": 0.5741345176306919,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004975299504812061,
|
|
"loss": 6.5977,
|
|
"mean_token_accuracy": 0.11472523659467697,
|
|
"num_tokens": 11613977.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.755290269851685,
|
|
"epoch": 0.5746695917384558,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004975242975888246,
|
|
"loss": 6.6451,
|
|
"mean_token_accuracy": 0.11898882836103439,
|
|
"num_tokens": 11625425.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.667579507827758,
|
|
"epoch": 0.5752046658462197,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004975186382710854,
|
|
"loss": 6.5923,
|
|
"mean_token_accuracy": 0.11569623947143555,
|
|
"num_tokens": 11636530.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.69462890625,
|
|
"epoch": 0.5757397399539836,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004975129725281516,
|
|
"loss": 6.5842,
|
|
"mean_token_accuracy": 0.12393845319747925,
|
|
"num_tokens": 11646516.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.668670988082885,
|
|
"epoch": 0.5762748140617475,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004975073003601871,
|
|
"loss": 6.579,
|
|
"mean_token_accuracy": 0.1199287973344326,
|
|
"num_tokens": 11657424.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.673134517669678,
|
|
"epoch": 0.5768098881695115,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004975016217673556,
|
|
"loss": 6.5883,
|
|
"mean_token_accuracy": 0.11663650795817375,
|
|
"num_tokens": 11669447.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.716589069366455,
|
|
"epoch": 0.5773449622772754,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000497495936749821,
|
|
"loss": 6.5611,
|
|
"mean_token_accuracy": 0.12475978508591652,
|
|
"num_tokens": 11679612.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.678430557250977,
|
|
"epoch": 0.5778800363850394,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004974902453077474,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.12052254527807235,
|
|
"num_tokens": 11689527.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.720280361175537,
|
|
"epoch": 0.5784151104928033,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004974845474412993,
|
|
"loss": 6.5765,
|
|
"mean_token_accuracy": 0.12422782853245735,
|
|
"num_tokens": 11700452.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.608441305160523,
|
|
"epoch": 0.5789501846005671,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004974788431506412,
|
|
"loss": 6.5868,
|
|
"mean_token_accuracy": 0.11873762682080269,
|
|
"num_tokens": 11710902.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.722711229324341,
|
|
"epoch": 0.5794852587083311,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004974731324359378,
|
|
"loss": 6.6202,
|
|
"mean_token_accuracy": 0.11096708253026008,
|
|
"num_tokens": 11721901.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.726794672012329,
|
|
"epoch": 0.580020332816095,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004974674152973538,
|
|
"loss": 6.6079,
|
|
"mean_token_accuracy": 0.115871462225914,
|
|
"num_tokens": 11733622.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.751911401748657,
|
|
"epoch": 0.580555406923859,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004974616917350545,
|
|
"loss": 6.6164,
|
|
"mean_token_accuracy": 0.12217370122671127,
|
|
"num_tokens": 11745116.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.629001712799072,
|
|
"epoch": 0.5810904810316229,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004974559617492052,
|
|
"loss": 6.5419,
|
|
"mean_token_accuracy": 0.12381923273205757,
|
|
"num_tokens": 11756203.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.742204999923706,
|
|
"epoch": 0.5816255551393869,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004974502253399712,
|
|
"loss": 6.6065,
|
|
"mean_token_accuracy": 0.11900223791599274,
|
|
"num_tokens": 11766797.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.743202018737793,
|
|
"epoch": 0.5821606292471507,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004974444825075182,
|
|
"loss": 6.6836,
|
|
"mean_token_accuracy": 0.11354267820715905,
|
|
"num_tokens": 11778110.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.611339521408081,
|
|
"epoch": 0.5826957033549146,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497438733252012,
|
|
"loss": 6.5464,
|
|
"mean_token_accuracy": 0.1208656445145607,
|
|
"num_tokens": 11788396.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.740115785598755,
|
|
"epoch": 0.5832307774626786,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004974329775736188,
|
|
"loss": 6.6253,
|
|
"mean_token_accuracy": 0.11759175732731819,
|
|
"num_tokens": 11798691.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.743464374542237,
|
|
"epoch": 0.5837658515704425,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004974272154725044,
|
|
"loss": 6.6862,
|
|
"mean_token_accuracy": 0.11484382227063179,
|
|
"num_tokens": 11808965.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.656184816360474,
|
|
"epoch": 0.5843009256782065,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004974214469488355,
|
|
"loss": 6.5029,
|
|
"mean_token_accuracy": 0.12686796858906746,
|
|
"num_tokens": 11819932.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.753126621246338,
|
|
"epoch": 0.5848359997859703,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004974156720027786,
|
|
"loss": 6.6071,
|
|
"mean_token_accuracy": 0.12075452283024787,
|
|
"num_tokens": 11831332.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.719524621963501,
|
|
"epoch": 0.5853710738937343,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004974098906345004,
|
|
"loss": 6.5902,
|
|
"mean_token_accuracy": 0.11421620100736618,
|
|
"num_tokens": 11840947.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.624907207489014,
|
|
"epoch": 0.5859061480014982,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004974041028441679,
|
|
"loss": 6.5378,
|
|
"mean_token_accuracy": 0.11265920177102089,
|
|
"num_tokens": 11851640.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.7370397567749025,
|
|
"epoch": 0.5864412221092621,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004973983086319481,
|
|
"loss": 6.6519,
|
|
"mean_token_accuracy": 0.11276995167136192,
|
|
"num_tokens": 11863608.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.752982711791992,
|
|
"epoch": 0.5869762962170261,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004973925079980085,
|
|
"loss": 6.5678,
|
|
"mean_token_accuracy": 0.11900977268815041,
|
|
"num_tokens": 11874707.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.644384241104126,
|
|
"epoch": 0.58751137032479,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004973867009425164,
|
|
"loss": 6.6379,
|
|
"mean_token_accuracy": 0.11783983260393142,
|
|
"num_tokens": 11885118.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.724728775024414,
|
|
"epoch": 0.5880464444325539,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004973808874656396,
|
|
"loss": 6.6162,
|
|
"mean_token_accuracy": 0.11670980975031853,
|
|
"num_tokens": 11895859.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.7954737663269045,
|
|
"epoch": 0.5885815185403178,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004973750675675458,
|
|
"loss": 6.6342,
|
|
"mean_token_accuracy": 0.11875612363219261,
|
|
"num_tokens": 11907019.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.744963645935059,
|
|
"epoch": 0.5891165926480818,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004973692412484034,
|
|
"loss": 6.5778,
|
|
"mean_token_accuracy": 0.11970652416348457,
|
|
"num_tokens": 11918257.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.671480941772461,
|
|
"epoch": 0.5896516667558457,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004973634085083802,
|
|
"loss": 6.576,
|
|
"mean_token_accuracy": 0.127632237970829,
|
|
"num_tokens": 11929003.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.736668920516967,
|
|
"epoch": 0.5901867408636096,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000497357569347645,
|
|
"loss": 6.7255,
|
|
"mean_token_accuracy": 0.1138952411711216,
|
|
"num_tokens": 11939786.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.755863952636719,
|
|
"epoch": 0.5907218149713735,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004973517237663661,
|
|
"loss": 6.6304,
|
|
"mean_token_accuracy": 0.11138334199786186,
|
|
"num_tokens": 11951042.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.740656137466431,
|
|
"epoch": 0.5912568890791374,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004973458717647124,
|
|
"loss": 6.5364,
|
|
"mean_token_accuracy": 0.12641868591308594,
|
|
"num_tokens": 11961982.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.707173919677734,
|
|
"epoch": 0.5917919631869014,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000497340013342853,
|
|
"loss": 6.5856,
|
|
"mean_token_accuracy": 0.11962274238467216,
|
|
"num_tokens": 11972078.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.688304281234741,
|
|
"epoch": 0.5923270372946653,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000497334148500957,
|
|
"loss": 6.638,
|
|
"mean_token_accuracy": 0.11932587698101997,
|
|
"num_tokens": 11984037.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.709690189361572,
|
|
"epoch": 0.5928621114024293,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004973282772391936,
|
|
"loss": 6.5695,
|
|
"mean_token_accuracy": 0.1173762895166874,
|
|
"num_tokens": 11993688.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.620822906494141,
|
|
"epoch": 0.5933971855101932,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004973223995577324,
|
|
"loss": 6.5427,
|
|
"mean_token_accuracy": 0.11914530023932457,
|
|
"num_tokens": 12003759.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.650865459442139,
|
|
"epoch": 0.593932259617957,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004973165154567432,
|
|
"loss": 6.5773,
|
|
"mean_token_accuracy": 0.1205617792904377,
|
|
"num_tokens": 12015030.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.700285911560059,
|
|
"epoch": 0.594467333725721,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004973106249363959,
|
|
"loss": 6.6351,
|
|
"mean_token_accuracy": 0.11812169402837754,
|
|
"num_tokens": 12026181.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.653229570388794,
|
|
"epoch": 0.5950024078334849,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004973047279968606,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.1311015099287033,
|
|
"num_tokens": 12037336.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.671442556381225,
|
|
"epoch": 0.5955374819412489,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004972988246383074,
|
|
"loss": 6.4958,
|
|
"mean_token_accuracy": 0.120445104688406,
|
|
"num_tokens": 12048425.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.553933811187744,
|
|
"epoch": 0.5960725560490128,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004972929148609068,
|
|
"loss": 6.4506,
|
|
"mean_token_accuracy": 0.13666753321886063,
|
|
"num_tokens": 12059814.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.609471130371094,
|
|
"epoch": 0.5966076301567768,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004972869986648296,
|
|
"loss": 6.5223,
|
|
"mean_token_accuracy": 0.12330262139439582,
|
|
"num_tokens": 12069377.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.679553031921387,
|
|
"epoch": 0.5971427042645406,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004972810760502467,
|
|
"loss": 6.65,
|
|
"mean_token_accuracy": 0.1143650807440281,
|
|
"num_tokens": 12080277.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.707303857803344,
|
|
"epoch": 0.5976777783723045,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972751470173287,
|
|
"loss": 6.5392,
|
|
"mean_token_accuracy": 0.11781578734517098,
|
|
"num_tokens": 12091375.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.6600456714630125,
|
|
"epoch": 0.5982128524800685,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004972692115662473,
|
|
"loss": 6.5835,
|
|
"mean_token_accuracy": 0.11931180357933044,
|
|
"num_tokens": 12103110.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.669634294509888,
|
|
"epoch": 0.5987479265878324,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004972632696971735,
|
|
"loss": 6.6412,
|
|
"mean_token_accuracy": 0.11558156907558441,
|
|
"num_tokens": 12112454.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.636322975158691,
|
|
"epoch": 0.5992830006955964,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004972573214102791,
|
|
"loss": 6.5229,
|
|
"mean_token_accuracy": 0.11954844370484352,
|
|
"num_tokens": 12125140.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.715576267242431,
|
|
"epoch": 0.5998180748033602,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004972513667057358,
|
|
"loss": 6.5519,
|
|
"mean_token_accuracy": 0.11657773405313492,
|
|
"num_tokens": 12136061.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.750255346298218,
|
|
"epoch": 0.6003531489111242,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004972454055837155,
|
|
"loss": 6.595,
|
|
"mean_token_accuracy": 0.12111319378018379,
|
|
"num_tokens": 12146654.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.75370192527771,
|
|
"epoch": 0.6008882230188881,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004972394380443903,
|
|
"loss": 6.5841,
|
|
"mean_token_accuracy": 0.11777229756116867,
|
|
"num_tokens": 12157881.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.691373348236084,
|
|
"epoch": 0.601423297126652,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004972334640879325,
|
|
"loss": 6.615,
|
|
"mean_token_accuracy": 0.11591439619660378,
|
|
"num_tokens": 12168534.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.640426683425903,
|
|
"epoch": 0.601958371234416,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004972274837145147,
|
|
"loss": 6.5329,
|
|
"mean_token_accuracy": 0.1218352235853672,
|
|
"num_tokens": 12178773.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.7092021942138675,
|
|
"epoch": 0.6024934453421799,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004972214969243096,
|
|
"loss": 6.5772,
|
|
"mean_token_accuracy": 0.11726051643490791,
|
|
"num_tokens": 12188819.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.635117769241333,
|
|
"epoch": 0.6030285194499438,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00049721550371749,
|
|
"loss": 6.5502,
|
|
"mean_token_accuracy": 0.12739348784089088,
|
|
"num_tokens": 12199198.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.721414947509766,
|
|
"epoch": 0.6035635935577077,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004972095040942289,
|
|
"loss": 6.5697,
|
|
"mean_token_accuracy": 0.11852023229002953,
|
|
"num_tokens": 12210765.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.656217288970947,
|
|
"epoch": 0.6040986676654717,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004972034980546996,
|
|
"loss": 6.5941,
|
|
"mean_token_accuracy": 0.11481459364295006,
|
|
"num_tokens": 12221067.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.645788288116455,
|
|
"epoch": 0.6046337417732356,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004971974855990755,
|
|
"loss": 6.5999,
|
|
"mean_token_accuracy": 0.12012394964694977,
|
|
"num_tokens": 12232994.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.729011297225952,
|
|
"epoch": 0.6051688158809995,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004971914667275302,
|
|
"loss": 6.5553,
|
|
"mean_token_accuracy": 0.11960238218307495,
|
|
"num_tokens": 12243327.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.600992822647095,
|
|
"epoch": 0.6057038899887635,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004971854414402377,
|
|
"loss": 6.4803,
|
|
"mean_token_accuracy": 0.12356549277901649,
|
|
"num_tokens": 12254249.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.654879474639893,
|
|
"epoch": 0.6062389640965273,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004971794097373716,
|
|
"loss": 6.5167,
|
|
"mean_token_accuracy": 0.11952641755342483,
|
|
"num_tokens": 12264487.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.57205753326416,
|
|
"epoch": 0.6067740382042913,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004971733716191063,
|
|
"loss": 6.5087,
|
|
"mean_token_accuracy": 0.12777614444494248,
|
|
"num_tokens": 12274801.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.634649610519409,
|
|
"epoch": 0.6073091123120552,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004971673270856162,
|
|
"loss": 6.477,
|
|
"mean_token_accuracy": 0.12111672386527061,
|
|
"num_tokens": 12284647.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.6497354984283445,
|
|
"epoch": 0.6078441864198192,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004971612761370756,
|
|
"loss": 6.5947,
|
|
"mean_token_accuracy": 0.12196626737713814,
|
|
"num_tokens": 12295215.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.636915922164917,
|
|
"epoch": 0.6083792605275831,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004971552187736596,
|
|
"loss": 6.503,
|
|
"mean_token_accuracy": 0.12083340361714363,
|
|
"num_tokens": 12305324.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.623749685287476,
|
|
"epoch": 0.6089143346353469,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004971491549955427,
|
|
"loss": 6.5314,
|
|
"mean_token_accuracy": 0.12515415251255035,
|
|
"num_tokens": 12316399.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.565249395370484,
|
|
"epoch": 0.6094494087431109,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004971430848029002,
|
|
"loss": 6.4953,
|
|
"mean_token_accuracy": 0.12863782942295074,
|
|
"num_tokens": 12328033.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.62008113861084,
|
|
"epoch": 0.6099844828508748,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004971370081959073,
|
|
"loss": 6.5432,
|
|
"mean_token_accuracy": 0.12434352040290833,
|
|
"num_tokens": 12338962.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.6729292392730715,
|
|
"epoch": 0.6105195569586388,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004971309251747396,
|
|
"loss": 6.5418,
|
|
"mean_token_accuracy": 0.1266559824347496,
|
|
"num_tokens": 12350216.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.681897783279419,
|
|
"epoch": 0.6110546310664027,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004971248357395726,
|
|
"loss": 6.5708,
|
|
"mean_token_accuracy": 0.1206928163766861,
|
|
"num_tokens": 12361277.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.585869026184082,
|
|
"epoch": 0.6115897051741667,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004971187398905821,
|
|
"loss": 6.4779,
|
|
"mean_token_accuracy": 0.12453080341219902,
|
|
"num_tokens": 12373308.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.745548439025879,
|
|
"epoch": 0.6121247792819305,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004971126376279443,
|
|
"loss": 6.7296,
|
|
"mean_token_accuracy": 0.10965547412633896,
|
|
"num_tokens": 12383943.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.67027587890625,
|
|
"epoch": 0.6126598533896944,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004971065289518354,
|
|
"loss": 6.4776,
|
|
"mean_token_accuracy": 0.1167394459247589,
|
|
"num_tokens": 12394575.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.698582744598388,
|
|
"epoch": 0.6131949274974584,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004971004138624315,
|
|
"loss": 6.5898,
|
|
"mean_token_accuracy": 0.11946821883320809,
|
|
"num_tokens": 12405536.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.607072544097901,
|
|
"epoch": 0.6137300016052223,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004970942923599094,
|
|
"loss": 6.4685,
|
|
"mean_token_accuracy": 0.12893888279795646,
|
|
"num_tokens": 12416148.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.632549238204956,
|
|
"epoch": 0.6142650757129863,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970881644444459,
|
|
"loss": 6.4754,
|
|
"mean_token_accuracy": 0.12886900901794435,
|
|
"num_tokens": 12426182.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.631240129470825,
|
|
"epoch": 0.6148001498207502,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004970820301162178,
|
|
"loss": 6.652,
|
|
"mean_token_accuracy": 0.11639525294303894,
|
|
"num_tokens": 12437548.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.722517490386963,
|
|
"epoch": 0.6153352239285141,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004970758893754022,
|
|
"loss": 6.603,
|
|
"mean_token_accuracy": 0.11473475024104118,
|
|
"num_tokens": 12449720.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.750303125381469,
|
|
"epoch": 0.615870298036278,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970697422221767,
|
|
"loss": 6.5825,
|
|
"mean_token_accuracy": 0.12193588614463806,
|
|
"num_tokens": 12460666.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.661549139022827,
|
|
"epoch": 0.6164053721440419,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004970635886567185,
|
|
"loss": 6.5831,
|
|
"mean_token_accuracy": 0.11829188615083694,
|
|
"num_tokens": 12471472.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.616854095458985,
|
|
"epoch": 0.6169404462518059,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004970574286792054,
|
|
"loss": 6.5729,
|
|
"mean_token_accuracy": 0.11929405927658081,
|
|
"num_tokens": 12482127.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.641938018798828,
|
|
"epoch": 0.6174755203595698,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004970512622898152,
|
|
"loss": 6.5611,
|
|
"mean_token_accuracy": 0.12291084676980972,
|
|
"num_tokens": 12493680.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.60687289237976,
|
|
"epoch": 0.6180105944673338,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000497045089488726,
|
|
"loss": 6.5172,
|
|
"mean_token_accuracy": 0.1259467586874962,
|
|
"num_tokens": 12505838.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.6949209690094,
|
|
"epoch": 0.6185456685750976,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004970389102761161,
|
|
"loss": 6.5121,
|
|
"mean_token_accuracy": 0.12690744772553444,
|
|
"num_tokens": 12516334.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.630453395843506,
|
|
"epoch": 0.6190807426828616,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004970327246521638,
|
|
"loss": 6.5966,
|
|
"mean_token_accuracy": 0.11633171513676643,
|
|
"num_tokens": 12526440.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.615752553939819,
|
|
"epoch": 0.6196158167906255,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004970265326170478,
|
|
"loss": 6.504,
|
|
"mean_token_accuracy": 0.12056778073310852,
|
|
"num_tokens": 12538127.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.725585842132569,
|
|
"epoch": 0.6201508908983894,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004970203341709469,
|
|
"loss": 6.6113,
|
|
"mean_token_accuracy": 0.11749014109373093,
|
|
"num_tokens": 12548459.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.602406692504883,
|
|
"epoch": 0.6206859650061534,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00049701412931404,
|
|
"loss": 6.5617,
|
|
"mean_token_accuracy": 0.12014793530106545,
|
|
"num_tokens": 12558989.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.618525218963623,
|
|
"epoch": 0.6212210391139172,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004970079180465064,
|
|
"loss": 6.4752,
|
|
"mean_token_accuracy": 0.12559444829821587,
|
|
"num_tokens": 12569449.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.649777793884278,
|
|
"epoch": 0.6217561132216812,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004970017003685253,
|
|
"loss": 6.5174,
|
|
"mean_token_accuracy": 0.12333801165223121,
|
|
"num_tokens": 12580733.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.639023208618164,
|
|
"epoch": 0.6222911873294451,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004969954762802763,
|
|
"loss": 6.5246,
|
|
"mean_token_accuracy": 0.12096468210220337,
|
|
"num_tokens": 12590869.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.714621353149414,
|
|
"epoch": 0.6228262614372091,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000496989245781939,
|
|
"loss": 6.6116,
|
|
"mean_token_accuracy": 0.11883088201284409,
|
|
"num_tokens": 12602109.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.678238773345948,
|
|
"epoch": 0.623361335544973,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004969830088736937,
|
|
"loss": 6.5447,
|
|
"mean_token_accuracy": 0.11637340411543846,
|
|
"num_tokens": 12612234.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.74876914024353,
|
|
"epoch": 0.6238964096527368,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00049697676555572,
|
|
"loss": 6.6934,
|
|
"mean_token_accuracy": 0.11071206331253051,
|
|
"num_tokens": 12623252.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.725121641159058,
|
|
"epoch": 0.6244314837605008,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004969705158281985,
|
|
"loss": 6.4462,
|
|
"mean_token_accuracy": 0.12263509407639503,
|
|
"num_tokens": 12632796.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.633543968200684,
|
|
"epoch": 0.6249665578682647,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004969642596913095,
|
|
"loss": 6.5394,
|
|
"mean_token_accuracy": 0.11995783001184464,
|
|
"num_tokens": 12643278.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.672138452529907,
|
|
"epoch": 0.6255016319760287,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004969579971452337,
|
|
"loss": 6.6234,
|
|
"mean_token_accuracy": 0.12050508707761765,
|
|
"num_tokens": 12654446.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.699638795852661,
|
|
"epoch": 0.6260367060837926,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004969517281901519,
|
|
"loss": 6.5899,
|
|
"mean_token_accuracy": 0.12274675741791725,
|
|
"num_tokens": 12664281.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.671421384811401,
|
|
"epoch": 0.6265717801915566,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004969454528262451,
|
|
"loss": 6.5693,
|
|
"mean_token_accuracy": 0.11972746700048446,
|
|
"num_tokens": 12675252.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.648418712615967,
|
|
"epoch": 0.6271068542993204,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004969391710536946,
|
|
"loss": 6.5626,
|
|
"mean_token_accuracy": 0.11940335035324097,
|
|
"num_tokens": 12685764.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.590697622299194,
|
|
"epoch": 0.6276419284070843,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004969328828726817,
|
|
"loss": 6.4542,
|
|
"mean_token_accuracy": 0.12306086346507072,
|
|
"num_tokens": 12696974.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.753077173233033,
|
|
"epoch": 0.6281770025148483,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004969265882833879,
|
|
"loss": 6.6187,
|
|
"mean_token_accuracy": 0.11165008768439293,
|
|
"num_tokens": 12708217.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.6730287075042725,
|
|
"epoch": 0.6287120766226122,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004969202872859952,
|
|
"loss": 6.4866,
|
|
"mean_token_accuracy": 0.12286026254296303,
|
|
"num_tokens": 12717840.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.617942667007446,
|
|
"epoch": 0.6292471507303762,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004969139798806854,
|
|
"loss": 6.5918,
|
|
"mean_token_accuracy": 0.11480392217636108,
|
|
"num_tokens": 12728390.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.630872583389282,
|
|
"epoch": 0.6297822248381401,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004969076660676405,
|
|
"loss": 6.5987,
|
|
"mean_token_accuracy": 0.12041830644011497,
|
|
"num_tokens": 12738650.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.697933101654053,
|
|
"epoch": 0.630317298945904,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000496901345847043,
|
|
"loss": 6.591,
|
|
"mean_token_accuracy": 0.11938764452934265,
|
|
"num_tokens": 12748989.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.668829250335693,
|
|
"epoch": 0.6308523730536679,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004968950192190752,
|
|
"loss": 6.5492,
|
|
"mean_token_accuracy": 0.12053480222821236,
|
|
"num_tokens": 12761132.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.63626651763916,
|
|
"epoch": 0.6313874471614318,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00049688868618392,
|
|
"loss": 6.5544,
|
|
"mean_token_accuracy": 0.12361529469490051,
|
|
"num_tokens": 12771478.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.671739768981934,
|
|
"epoch": 0.6319225212691958,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004968823467417602,
|
|
"loss": 6.6274,
|
|
"mean_token_accuracy": 0.11821751520037652,
|
|
"num_tokens": 12782096.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.6624290466308596,
|
|
"epoch": 0.6324575953769597,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004968760008927788,
|
|
"loss": 6.5292,
|
|
"mean_token_accuracy": 0.12572447210550308,
|
|
"num_tokens": 12792467.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.674447631835937,
|
|
"epoch": 0.6329926694847237,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496869648637159,
|
|
"loss": 6.5279,
|
|
"mean_token_accuracy": 0.12715904042124748,
|
|
"num_tokens": 12803248.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.694916152954102,
|
|
"epoch": 0.6335277435924875,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004968632899750844,
|
|
"loss": 6.5523,
|
|
"mean_token_accuracy": 0.12229961976408958,
|
|
"num_tokens": 12813701.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.736898612976074,
|
|
"epoch": 0.6340628177002515,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004968569249067383,
|
|
"loss": 6.6224,
|
|
"mean_token_accuracy": 0.11488275229930878,
|
|
"num_tokens": 12824945.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.657941913604736,
|
|
"epoch": 0.6345978918080154,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004968505534323047,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.11723481565713882,
|
|
"num_tokens": 12836699.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.6175376892089846,
|
|
"epoch": 0.6351329659157794,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004968441755519677,
|
|
"loss": 6.5205,
|
|
"mean_token_accuracy": 0.11750935465097427,
|
|
"num_tokens": 12846905.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.667795610427857,
|
|
"epoch": 0.6356680400235433,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004968377912659112,
|
|
"loss": 6.4846,
|
|
"mean_token_accuracy": 0.12737148776650428,
|
|
"num_tokens": 12856919.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.586252641677857,
|
|
"epoch": 0.6362031141313071,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004968314005743196,
|
|
"loss": 6.4499,
|
|
"mean_token_accuracy": 0.12662240564823152,
|
|
"num_tokens": 12867863.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.576164484024048,
|
|
"epoch": 0.6367381882390711,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004968250034773776,
|
|
"loss": 6.5458,
|
|
"mean_token_accuracy": 0.12098130509257317,
|
|
"num_tokens": 12877877.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.740300512313842,
|
|
"epoch": 0.637273262346835,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004968185999752697,
|
|
"loss": 6.6226,
|
|
"mean_token_accuracy": 0.11211201325058937,
|
|
"num_tokens": 12887954.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.667530632019043,
|
|
"epoch": 0.637808336454599,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004968121900681809,
|
|
"loss": 6.5458,
|
|
"mean_token_accuracy": 0.1223320372402668,
|
|
"num_tokens": 12897744.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.6086818218231205,
|
|
"epoch": 0.6383434105623629,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004968057737562964,
|
|
"loss": 6.6132,
|
|
"mean_token_accuracy": 0.11974837332963943,
|
|
"num_tokens": 12909193.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.65242075920105,
|
|
"epoch": 0.6388784846701269,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004967993510398012,
|
|
"loss": 6.4832,
|
|
"mean_token_accuracy": 0.1264573447406292,
|
|
"num_tokens": 12919879.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.632117652893067,
|
|
"epoch": 0.6394135587778907,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004967929219188809,
|
|
"loss": 6.5361,
|
|
"mean_token_accuracy": 0.12129070311784744,
|
|
"num_tokens": 12930297.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.657332706451416,
|
|
"epoch": 0.6399486328856546,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004967864863937212,
|
|
"loss": 6.5143,
|
|
"mean_token_accuracy": 0.12851046174764633,
|
|
"num_tokens": 12940467.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.6095727443695065,
|
|
"epoch": 0.6404837069934186,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004967800444645079,
|
|
"loss": 6.4992,
|
|
"mean_token_accuracy": 0.11969673112034798,
|
|
"num_tokens": 12950417.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.600736427307129,
|
|
"epoch": 0.6410187811011825,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004967735961314269,
|
|
"loss": 6.461,
|
|
"mean_token_accuracy": 0.12727241218090057,
|
|
"num_tokens": 12960957.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.65483922958374,
|
|
"epoch": 0.6415538552089465,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004967671413946646,
|
|
"loss": 6.5729,
|
|
"mean_token_accuracy": 0.11923076584935188,
|
|
"num_tokens": 12971194.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.6494788646698,
|
|
"epoch": 0.6420889293167104,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004967606802544071,
|
|
"loss": 6.5702,
|
|
"mean_token_accuracy": 0.11753485649824143,
|
|
"num_tokens": 12982479.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6420889293167104,
|
|
"eval_entropy": 6.531758780877866,
|
|
"eval_loss": 6.6282525062561035,
|
|
"eval_mean_token_accuracy": 0.12331635652315825,
|
|
"eval_num_tokens": 12982479.0,
|
|
"eval_runtime": 22.5385,
|
|
"eval_samples_per_second": 1316.811,
|
|
"eval_steps_per_second": 164.607,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.68715763092041,
|
|
"epoch": 0.6426240034244743,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004967542127108412,
|
|
"loss": 6.6258,
|
|
"mean_token_accuracy": 0.11803628206253051,
|
|
"num_tokens": 12994119.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.707434272766113,
|
|
"epoch": 0.6431590775322382,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004967477387641537,
|
|
"loss": 6.5338,
|
|
"mean_token_accuracy": 0.12097589150071145,
|
|
"num_tokens": 13005437.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.632017135620117,
|
|
"epoch": 0.6436941516400021,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004967412584145312,
|
|
"loss": 6.5444,
|
|
"mean_token_accuracy": 0.1208797350525856,
|
|
"num_tokens": 13017278.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.632179546356201,
|
|
"epoch": 0.6442292257477661,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004967347716621611,
|
|
"loss": 6.5249,
|
|
"mean_token_accuracy": 0.12122005820274354,
|
|
"num_tokens": 13028010.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.646252059936524,
|
|
"epoch": 0.64476429985553,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004967282785072306,
|
|
"loss": 6.5297,
|
|
"mean_token_accuracy": 0.12329597547650337,
|
|
"num_tokens": 13038740.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.61085844039917,
|
|
"epoch": 0.645299373963294,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004967217789499272,
|
|
"loss": 6.5311,
|
|
"mean_token_accuracy": 0.12402113229036331,
|
|
"num_tokens": 13049921.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.576950168609619,
|
|
"epoch": 0.6458344480710578,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004967152729904386,
|
|
"loss": 6.4542,
|
|
"mean_token_accuracy": 0.1269497275352478,
|
|
"num_tokens": 13060907.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.66811900138855,
|
|
"epoch": 0.6463695221788218,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004967087606289527,
|
|
"loss": 6.487,
|
|
"mean_token_accuracy": 0.12562344297766687,
|
|
"num_tokens": 13071720.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.643046426773071,
|
|
"epoch": 0.6469045962865857,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004967022418656575,
|
|
"loss": 6.5537,
|
|
"mean_token_accuracy": 0.12515400797128678,
|
|
"num_tokens": 13082474.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.535715913772583,
|
|
"epoch": 0.6474396703943496,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004966957167007412,
|
|
"loss": 6.4539,
|
|
"mean_token_accuracy": 0.12264144271612168,
|
|
"num_tokens": 13092777.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.619180631637573,
|
|
"epoch": 0.6479747445021136,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004966891851343922,
|
|
"loss": 6.4624,
|
|
"mean_token_accuracy": 0.12598160430788993,
|
|
"num_tokens": 13104019.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.6781152248382565,
|
|
"epoch": 0.6485098186098774,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004966826471667992,
|
|
"loss": 6.4965,
|
|
"mean_token_accuracy": 0.12487390413880348,
|
|
"num_tokens": 13115741.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.600745773315429,
|
|
"epoch": 0.6490448927176414,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004966761027981509,
|
|
"loss": 6.5014,
|
|
"mean_token_accuracy": 0.12369894310832023,
|
|
"num_tokens": 13126838.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.6506952285766605,
|
|
"epoch": 0.6495799668254053,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004966695520286362,
|
|
"loss": 6.6208,
|
|
"mean_token_accuracy": 0.11757588386535645,
|
|
"num_tokens": 13137485.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.683424711227417,
|
|
"epoch": 0.6501150409331693,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004966629948584444,
|
|
"loss": 6.4704,
|
|
"mean_token_accuracy": 0.1255775049328804,
|
|
"num_tokens": 13147631.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.545761299133301,
|
|
"epoch": 0.6506501150409332,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004966564312877647,
|
|
"loss": 6.5401,
|
|
"mean_token_accuracy": 0.127092856913805,
|
|
"num_tokens": 13158468.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.673073577880859,
|
|
"epoch": 0.651185189148697,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004966498613167868,
|
|
"loss": 6.5742,
|
|
"mean_token_accuracy": 0.11650417298078537,
|
|
"num_tokens": 13169263.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.688106441497803,
|
|
"epoch": 0.651720263256461,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004966432849457002,
|
|
"loss": 6.4977,
|
|
"mean_token_accuracy": 0.13137751147150994,
|
|
"num_tokens": 13178647.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.592944383621216,
|
|
"epoch": 0.6522553373642249,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000496636702174695,
|
|
"loss": 6.4745,
|
|
"mean_token_accuracy": 0.12567707225680352,
|
|
"num_tokens": 13189883.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.637817287445069,
|
|
"epoch": 0.6527904114719889,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004966301130039611,
|
|
"loss": 6.5929,
|
|
"mean_token_accuracy": 0.12274678125977516,
|
|
"num_tokens": 13200920.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.630142402648926,
|
|
"epoch": 0.6533254855797528,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004966235174336889,
|
|
"loss": 6.5989,
|
|
"mean_token_accuracy": 0.11455288678407669,
|
|
"num_tokens": 13211765.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.6219785690307615,
|
|
"epoch": 0.6538605596875168,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004966169154640687,
|
|
"loss": 6.5026,
|
|
"mean_token_accuracy": 0.12158372178673744,
|
|
"num_tokens": 13221768.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.609707498550415,
|
|
"epoch": 0.6543956337952807,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004966103070952912,
|
|
"loss": 6.5186,
|
|
"mean_token_accuracy": 0.1261971466243267,
|
|
"num_tokens": 13233545.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.690781784057617,
|
|
"epoch": 0.6549307079030445,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004966036923275472,
|
|
"loss": 6.5734,
|
|
"mean_token_accuracy": 0.12779439017176628,
|
|
"num_tokens": 13245018.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.602278470993042,
|
|
"epoch": 0.6554657820108085,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004965970711610278,
|
|
"loss": 6.4852,
|
|
"mean_token_accuracy": 0.12193110585212708,
|
|
"num_tokens": 13255772.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.650724649429321,
|
|
"epoch": 0.6560008561185724,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004965904435959241,
|
|
"loss": 6.5582,
|
|
"mean_token_accuracy": 0.12058316096663475,
|
|
"num_tokens": 13267271.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.687188005447387,
|
|
"epoch": 0.6565359302263364,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004965838096324274,
|
|
"loss": 6.5699,
|
|
"mean_token_accuracy": 0.12321074530482293,
|
|
"num_tokens": 13278467.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.6781120777130125,
|
|
"epoch": 0.6570710043341003,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004965771692707294,
|
|
"loss": 6.6236,
|
|
"mean_token_accuracy": 0.11595560312271118,
|
|
"num_tokens": 13288522.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.707428073883056,
|
|
"epoch": 0.6576060784418643,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004965705225110218,
|
|
"loss": 6.6084,
|
|
"mean_token_accuracy": 0.1100751057267189,
|
|
"num_tokens": 13299355.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.695277214050293,
|
|
"epoch": 0.6581411525496281,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004965638693534964,
|
|
"loss": 6.5344,
|
|
"mean_token_accuracy": 0.12395478188991546,
|
|
"num_tokens": 13310334.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.728033018112183,
|
|
"epoch": 0.658676226657392,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004965572097983455,
|
|
"loss": 6.5709,
|
|
"mean_token_accuracy": 0.11907820329070092,
|
|
"num_tokens": 13320917.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.646379995346069,
|
|
"epoch": 0.659211300765156,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004965505438457613,
|
|
"loss": 6.4835,
|
|
"mean_token_accuracy": 0.12329676076769829,
|
|
"num_tokens": 13331707.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.620332956314087,
|
|
"epoch": 0.6597463748729199,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004965438714959363,
|
|
"loss": 6.6398,
|
|
"mean_token_accuracy": 0.11810507029294967,
|
|
"num_tokens": 13341784.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.73358678817749,
|
|
"epoch": 0.6602814489806839,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000496537192749063,
|
|
"loss": 6.5848,
|
|
"mean_token_accuracy": 0.11754154190421104,
|
|
"num_tokens": 13351633.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.67577805519104,
|
|
"epoch": 0.6608165230884477,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004965305076053345,
|
|
"loss": 6.476,
|
|
"mean_token_accuracy": 0.13062218949198723,
|
|
"num_tokens": 13362444.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.606122398376465,
|
|
"epoch": 0.6613515971962117,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004965238160649437,
|
|
"loss": 6.6003,
|
|
"mean_token_accuracy": 0.11387802809476852,
|
|
"num_tokens": 13374322.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.647821712493896,
|
|
"epoch": 0.6618866713039756,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004965171181280838,
|
|
"loss": 6.582,
|
|
"mean_token_accuracy": 0.1202354334294796,
|
|
"num_tokens": 13384188.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.721444606781006,
|
|
"epoch": 0.6624217454117395,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004965104137949483,
|
|
"loss": 6.5758,
|
|
"mean_token_accuracy": 0.11213141530752183,
|
|
"num_tokens": 13395648.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.724832010269165,
|
|
"epoch": 0.6629568195195035,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004965037030657308,
|
|
"loss": 6.603,
|
|
"mean_token_accuracy": 0.12132872119545937,
|
|
"num_tokens": 13406769.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.696256256103515,
|
|
"epoch": 0.6634918936272673,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004964969859406248,
|
|
"loss": 6.5638,
|
|
"mean_token_accuracy": 0.11531667485833168,
|
|
"num_tokens": 13417509.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.6637779712677006,
|
|
"epoch": 0.6640269677350313,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004964902624198246,
|
|
"loss": 6.4888,
|
|
"mean_token_accuracy": 0.11672274023294449,
|
|
"num_tokens": 13429441.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.667134714126587,
|
|
"epoch": 0.6645620418427952,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004964835325035243,
|
|
"loss": 6.5156,
|
|
"mean_token_accuracy": 0.12254025638103486,
|
|
"num_tokens": 13439332.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.625695705413818,
|
|
"epoch": 0.6650971159505592,
|
|
"grad_norm": 6.1875,
|
|
"learning_rate": 0.0004964767961919179,
|
|
"loss": 6.497,
|
|
"mean_token_accuracy": 0.1214800864458084,
|
|
"num_tokens": 13449400.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.6120294570922855,
|
|
"epoch": 0.6656321900583231,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004964700534852003,
|
|
"loss": 6.6244,
|
|
"mean_token_accuracy": 0.11580300778150558,
|
|
"num_tokens": 13460134.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.672207880020141,
|
|
"epoch": 0.666167264166087,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004964633043835658,
|
|
"loss": 6.5424,
|
|
"mean_token_accuracy": 0.12483972460031509,
|
|
"num_tokens": 13469954.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.7172047138214115,
|
|
"epoch": 0.666702338273851,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004964565488872097,
|
|
"loss": 6.5417,
|
|
"mean_token_accuracy": 0.12203371152281761,
|
|
"num_tokens": 13479866.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.646776103973389,
|
|
"epoch": 0.6672374123816148,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004964497869963268,
|
|
"loss": 6.4767,
|
|
"mean_token_accuracy": 0.12304605394601822,
|
|
"num_tokens": 13490088.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.673387241363526,
|
|
"epoch": 0.6677724864893788,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004964430187111125,
|
|
"loss": 6.5862,
|
|
"mean_token_accuracy": 0.1177720382809639,
|
|
"num_tokens": 13500898.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.690912532806396,
|
|
"epoch": 0.6683075605971427,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004964362440317621,
|
|
"loss": 6.594,
|
|
"mean_token_accuracy": 0.11831463947892189,
|
|
"num_tokens": 13511537.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.626743984222412,
|
|
"epoch": 0.6688426347049067,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004964294629584712,
|
|
"loss": 6.5348,
|
|
"mean_token_accuracy": 0.1219833180308342,
|
|
"num_tokens": 13522916.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.65344729423523,
|
|
"epoch": 0.6693777088126706,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004964226754914357,
|
|
"loss": 6.4781,
|
|
"mean_token_accuracy": 0.12433587163686752,
|
|
"num_tokens": 13533817.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.669587135314941,
|
|
"epoch": 0.6699127829204344,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004964158816308517,
|
|
"loss": 6.5762,
|
|
"mean_token_accuracy": 0.11544739753007889,
|
|
"num_tokens": 13543723.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.593756771087646,
|
|
"epoch": 0.6704478570281984,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004964090813769151,
|
|
"loss": 6.4475,
|
|
"mean_token_accuracy": 0.12525615096092224,
|
|
"num_tokens": 13555269.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.620897197723389,
|
|
"epoch": 0.6709829311359623,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004964022747298224,
|
|
"loss": 6.6239,
|
|
"mean_token_accuracy": 0.11643384471535682,
|
|
"num_tokens": 13567465.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.735973596572876,
|
|
"epoch": 0.6715180052437263,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004963954616897701,
|
|
"loss": 6.5502,
|
|
"mean_token_accuracy": 0.11959524899721145,
|
|
"num_tokens": 13578637.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.673555660247803,
|
|
"epoch": 0.6720530793514902,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000496388642256955,
|
|
"loss": 6.5536,
|
|
"mean_token_accuracy": 0.12261009439826012,
|
|
"num_tokens": 13589074.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.61491174697876,
|
|
"epoch": 0.6725881534592542,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000496381816431574,
|
|
"loss": 6.5229,
|
|
"mean_token_accuracy": 0.12160132974386215,
|
|
"num_tokens": 13599624.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.696811199188232,
|
|
"epoch": 0.673123227567018,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004963749842138241,
|
|
"loss": 6.5385,
|
|
"mean_token_accuracy": 0.12809548079967498,
|
|
"num_tokens": 13610293.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.701215744018555,
|
|
"epoch": 0.6736583016747819,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004963681456039027,
|
|
"loss": 6.5647,
|
|
"mean_token_accuracy": 0.11978377178311347,
|
|
"num_tokens": 13621641.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.626857423782349,
|
|
"epoch": 0.6741933757825459,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004963613006020072,
|
|
"loss": 6.532,
|
|
"mean_token_accuracy": 0.1207999274134636,
|
|
"num_tokens": 13632083.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.5864670753479,
|
|
"epoch": 0.6747284498903098,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004963544492083352,
|
|
"loss": 6.4052,
|
|
"mean_token_accuracy": 0.13996648415923119,
|
|
"num_tokens": 13644084.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.590694761276245,
|
|
"epoch": 0.6752635239980738,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004963475914230845,
|
|
"loss": 6.5384,
|
|
"mean_token_accuracy": 0.12063725888729096,
|
|
"num_tokens": 13656231.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.672213792800903,
|
|
"epoch": 0.6757985981058376,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004963407272464533,
|
|
"loss": 6.6007,
|
|
"mean_token_accuracy": 0.11924332976341248,
|
|
"num_tokens": 13667334.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.71707592010498,
|
|
"epoch": 0.6763336722136016,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004963338566786398,
|
|
"loss": 6.5731,
|
|
"mean_token_accuracy": 0.12016325145959854,
|
|
"num_tokens": 13678615.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.716625833511353,
|
|
"epoch": 0.6768687463213655,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004963269797198422,
|
|
"loss": 6.5803,
|
|
"mean_token_accuracy": 0.12315328940749168,
|
|
"num_tokens": 13689890.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.55970950126648,
|
|
"epoch": 0.6774038204291294,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004963200963702592,
|
|
"loss": 6.442,
|
|
"mean_token_accuracy": 0.1283822812139988,
|
|
"num_tokens": 13699120.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.598990535736084,
|
|
"epoch": 0.6779388945368934,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004963132066300894,
|
|
"loss": 6.5339,
|
|
"mean_token_accuracy": 0.1192587710916996,
|
|
"num_tokens": 13710016.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.7227997303009035,
|
|
"epoch": 0.6784739686446573,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004963063104995319,
|
|
"loss": 6.6452,
|
|
"mean_token_accuracy": 0.11179172545671463,
|
|
"num_tokens": 13721576.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.686770296096801,
|
|
"epoch": 0.6790090427524212,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004962994079787859,
|
|
"loss": 6.607,
|
|
"mean_token_accuracy": 0.1248549573123455,
|
|
"num_tokens": 13732568.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.676553964614868,
|
|
"epoch": 0.6795441168601851,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004962924990680504,
|
|
"loss": 6.4628,
|
|
"mean_token_accuracy": 0.12426734790205955,
|
|
"num_tokens": 13742569.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.65596489906311,
|
|
"epoch": 0.6800791909679491,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004962855837675252,
|
|
"loss": 6.6009,
|
|
"mean_token_accuracy": 0.11601043120026588,
|
|
"num_tokens": 13752689.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.685011625289917,
|
|
"epoch": 0.680614265075713,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004962786620774099,
|
|
"loss": 6.5968,
|
|
"mean_token_accuracy": 0.11843189746141433,
|
|
"num_tokens": 13763709.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.689084672927857,
|
|
"epoch": 0.6811493391834769,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004962717339979043,
|
|
"loss": 6.4895,
|
|
"mean_token_accuracy": 0.12877231389284133,
|
|
"num_tokens": 13773726.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.629152297973633,
|
|
"epoch": 0.6816844132912409,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004962647995292084,
|
|
"loss": 6.5316,
|
|
"mean_token_accuracy": 0.12225151285529137,
|
|
"num_tokens": 13785435.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.635885381698609,
|
|
"epoch": 0.6822194873990047,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004962578586715226,
|
|
"loss": 6.5138,
|
|
"mean_token_accuracy": 0.11540746614336968,
|
|
"num_tokens": 13797104.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.745242309570313,
|
|
"epoch": 0.6827545615067687,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962509114250471,
|
|
"loss": 6.6154,
|
|
"mean_token_accuracy": 0.1163165308535099,
|
|
"num_tokens": 13807756.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.530831623077392,
|
|
"epoch": 0.6832896356145326,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004962439577899828,
|
|
"loss": 6.3179,
|
|
"mean_token_accuracy": 0.1424747809767723,
|
|
"num_tokens": 13818490.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.685521221160888,
|
|
"epoch": 0.6838247097222966,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004962369977665301,
|
|
"loss": 6.5822,
|
|
"mean_token_accuracy": 0.11557067930698395,
|
|
"num_tokens": 13829465.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.757493400573731,
|
|
"epoch": 0.6843597838300605,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004962300313548903,
|
|
"loss": 6.556,
|
|
"mean_token_accuracy": 0.12193023264408112,
|
|
"num_tokens": 13840863.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.697213411331177,
|
|
"epoch": 0.6848948579378243,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004962230585552645,
|
|
"loss": 6.5524,
|
|
"mean_token_accuracy": 0.12303654924035072,
|
|
"num_tokens": 13851711.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.637270164489746,
|
|
"epoch": 0.6854299320455883,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962160793678539,
|
|
"loss": 6.5915,
|
|
"mean_token_accuracy": 0.11985049769282341,
|
|
"num_tokens": 13864576.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.68571834564209,
|
|
"epoch": 0.6859650061533522,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00049620909379286,
|
|
"loss": 6.4934,
|
|
"mean_token_accuracy": 0.1263975717127323,
|
|
"num_tokens": 13875150.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.636159086227417,
|
|
"epoch": 0.6865000802611162,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004962021018304847,
|
|
"loss": 6.5296,
|
|
"mean_token_accuracy": 0.12008381858468056,
|
|
"num_tokens": 13886070.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.610868358612061,
|
|
"epoch": 0.6870351543688801,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004961951034809298,
|
|
"loss": 6.4657,
|
|
"mean_token_accuracy": 0.1190903440117836,
|
|
"num_tokens": 13897898.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.732908868789673,
|
|
"epoch": 0.6875702284766441,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004961880987443974,
|
|
"loss": 6.5986,
|
|
"mean_token_accuracy": 0.11787607669830322,
|
|
"num_tokens": 13909578.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.599007511138916,
|
|
"epoch": 0.6881053025844079,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004961810876210897,
|
|
"loss": 6.4492,
|
|
"mean_token_accuracy": 0.12546025216579437,
|
|
"num_tokens": 13920537.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.608020877838134,
|
|
"epoch": 0.6886403766921718,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004961740701112091,
|
|
"loss": 6.513,
|
|
"mean_token_accuracy": 0.12447056546807289,
|
|
"num_tokens": 13931015.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.658354997634888,
|
|
"epoch": 0.6891754507999358,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004961670462149583,
|
|
"loss": 6.5581,
|
|
"mean_token_accuracy": 0.11875083073973655,
|
|
"num_tokens": 13942691.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.785366678237915,
|
|
"epoch": 0.6897105249076997,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004961600159325403,
|
|
"loss": 6.6469,
|
|
"mean_token_accuracy": 0.10971695557236671,
|
|
"num_tokens": 13953945.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.7479382991790775,
|
|
"epoch": 0.6902455990154637,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004961529792641577,
|
|
"loss": 6.6332,
|
|
"mean_token_accuracy": 0.11458315700292587,
|
|
"num_tokens": 13965658.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.70365629196167,
|
|
"epoch": 0.6907806731232276,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004961459362100141,
|
|
"loss": 6.6046,
|
|
"mean_token_accuracy": 0.11868626773357391,
|
|
"num_tokens": 13976184.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.646018838882446,
|
|
"epoch": 0.6913157472309915,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004961388867703125,
|
|
"loss": 6.5219,
|
|
"mean_token_accuracy": 0.11236939951777458,
|
|
"num_tokens": 13986243.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.714858293533325,
|
|
"epoch": 0.6918508213387554,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004961318309452566,
|
|
"loss": 6.5075,
|
|
"mean_token_accuracy": 0.12324988022446633,
|
|
"num_tokens": 13995904.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.672885084152222,
|
|
"epoch": 0.6923858954465193,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004961247687350504,
|
|
"loss": 6.5707,
|
|
"mean_token_accuracy": 0.12211783155798912,
|
|
"num_tokens": 14006711.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.600964450836182,
|
|
"epoch": 0.6929209695542833,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004961177001398974,
|
|
"loss": 6.5373,
|
|
"mean_token_accuracy": 0.11900808811187744,
|
|
"num_tokens": 14018177.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.689823198318481,
|
|
"epoch": 0.6934560436620472,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004961106251600018,
|
|
"loss": 6.4936,
|
|
"mean_token_accuracy": 0.11595293655991554,
|
|
"num_tokens": 14028725.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.625997304916382,
|
|
"epoch": 0.6939911177698111,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.0004961035437955681,
|
|
"loss": 6.5258,
|
|
"mean_token_accuracy": 0.13137827664613724,
|
|
"num_tokens": 14040448.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.6649363994598385,
|
|
"epoch": 0.694526191877575,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004960964560468005,
|
|
"loss": 6.5723,
|
|
"mean_token_accuracy": 0.11377164348959923,
|
|
"num_tokens": 14051731.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.726572895050049,
|
|
"epoch": 0.695061265985339,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004960893619139039,
|
|
"loss": 6.5831,
|
|
"mean_token_accuracy": 0.11940285116434098,
|
|
"num_tokens": 14062330.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.643697881698609,
|
|
"epoch": 0.6955963400931029,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004960822613970831,
|
|
"loss": 6.4587,
|
|
"mean_token_accuracy": 0.12076596394181252,
|
|
"num_tokens": 14073991.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.73063063621521,
|
|
"epoch": 0.6961314142008668,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004960751544965431,
|
|
"loss": 6.5114,
|
|
"mean_token_accuracy": 0.11781129390001296,
|
|
"num_tokens": 14085132.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.621297025680542,
|
|
"epoch": 0.6966664883086308,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004960680412124889,
|
|
"loss": 6.4674,
|
|
"mean_token_accuracy": 0.12507544681429864,
|
|
"num_tokens": 14095371.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.519982624053955,
|
|
"epoch": 0.6972015624163946,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004960609215451261,
|
|
"loss": 6.5303,
|
|
"mean_token_accuracy": 0.11983035057783127,
|
|
"num_tokens": 14106117.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.595883226394653,
|
|
"epoch": 0.6977366365241586,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004960537954946604,
|
|
"loss": 6.5514,
|
|
"mean_token_accuracy": 0.12254466786980629,
|
|
"num_tokens": 14117112.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.632784509658814,
|
|
"epoch": 0.6982717106319225,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004960466630612974,
|
|
"loss": 6.4537,
|
|
"mean_token_accuracy": 0.1302560441195965,
|
|
"num_tokens": 14128037.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.597909259796142,
|
|
"epoch": 0.6988067847396865,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004960395242452429,
|
|
"loss": 6.4654,
|
|
"mean_token_accuracy": 0.12598486840724946,
|
|
"num_tokens": 14140183.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.670381021499634,
|
|
"epoch": 0.6993418588474504,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004960323790467033,
|
|
"loss": 6.6122,
|
|
"mean_token_accuracy": 0.11773319840431214,
|
|
"num_tokens": 14151635.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.745558500289917,
|
|
"epoch": 0.6998769329552142,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004960252274658849,
|
|
"loss": 6.5728,
|
|
"mean_token_accuracy": 0.11875017359852791,
|
|
"num_tokens": 14162660.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.7268280506134035,
|
|
"epoch": 0.7004120070629782,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004960180695029939,
|
|
"loss": 6.5552,
|
|
"mean_token_accuracy": 0.12919444888830184,
|
|
"num_tokens": 14173496.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.575908613204956,
|
|
"epoch": 0.7009470811707421,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004960109051582374,
|
|
"loss": 6.477,
|
|
"mean_token_accuracy": 0.11857445687055587,
|
|
"num_tokens": 14185479.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.646364021301269,
|
|
"epoch": 0.7014821552785061,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004960037344318221,
|
|
"loss": 6.4656,
|
|
"mean_token_accuracy": 0.11840324476361275,
|
|
"num_tokens": 14197441.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.597741746902466,
|
|
"epoch": 0.70201722938627,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004959965573239548,
|
|
"loss": 6.4287,
|
|
"mean_token_accuracy": 0.1321484237909317,
|
|
"num_tokens": 14207832.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.571916627883911,
|
|
"epoch": 0.702552303494034,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004959893738348432,
|
|
"loss": 6.4825,
|
|
"mean_token_accuracy": 0.13146081268787385,
|
|
"num_tokens": 14217976.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.70243353843689,
|
|
"epoch": 0.7030873776017978,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004959821839646943,
|
|
"loss": 6.4579,
|
|
"mean_token_accuracy": 0.12275309711694718,
|
|
"num_tokens": 14227557.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.685915279388428,
|
|
"epoch": 0.7036224517095617,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000495974987713716,
|
|
"loss": 6.5805,
|
|
"mean_token_accuracy": 0.11485387086868286,
|
|
"num_tokens": 14238912.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.62240080833435,
|
|
"epoch": 0.7041575258173257,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004959677850821159,
|
|
"loss": 6.508,
|
|
"mean_token_accuracy": 0.12129662483930588,
|
|
"num_tokens": 14249968.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.649249601364136,
|
|
"epoch": 0.7046925999250896,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004959605760701021,
|
|
"loss": 6.5733,
|
|
"mean_token_accuracy": 0.12394237816333771,
|
|
"num_tokens": 14260809.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.651643848419189,
|
|
"epoch": 0.7052276740328536,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004959533606778827,
|
|
"loss": 6.5371,
|
|
"mean_token_accuracy": 0.12085935771465302,
|
|
"num_tokens": 14271971.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.727529716491699,
|
|
"epoch": 0.7057627481406175,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004959461389056661,
|
|
"loss": 6.6001,
|
|
"mean_token_accuracy": 0.12835183441638948,
|
|
"num_tokens": 14283550.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.606536054611206,
|
|
"epoch": 0.7062978222483814,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004959389107536608,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.12371281832456589,
|
|
"num_tokens": 14293769.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.639873313903808,
|
|
"epoch": 0.7068328963561453,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004959316762220754,
|
|
"loss": 6.5333,
|
|
"mean_token_accuracy": 0.12135410904884339,
|
|
"num_tokens": 14304668.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.676944828033447,
|
|
"epoch": 0.7073679704639092,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000495924435311119,
|
|
"loss": 6.5981,
|
|
"mean_token_accuracy": 0.1185402013361454,
|
|
"num_tokens": 14315912.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.585085868835449,
|
|
"epoch": 0.7079030445716732,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004959171880210005,
|
|
"loss": 6.5502,
|
|
"mean_token_accuracy": 0.12489008754491807,
|
|
"num_tokens": 14327386.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.615741300582886,
|
|
"epoch": 0.7084381186794371,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004959099343519294,
|
|
"loss": 6.5295,
|
|
"mean_token_accuracy": 0.11725055053830147,
|
|
"num_tokens": 14338629.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.719633960723877,
|
|
"epoch": 0.7089731927872011,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004959026743041148,
|
|
"loss": 6.5559,
|
|
"mean_token_accuracy": 0.12487508654594422,
|
|
"num_tokens": 14349195.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.696239042282104,
|
|
"epoch": 0.7095082668949649,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004958954078777665,
|
|
"loss": 6.5819,
|
|
"mean_token_accuracy": 0.1186837948858738,
|
|
"num_tokens": 14359449.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.668183755874634,
|
|
"epoch": 0.7100433410027289,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004958881350730944,
|
|
"loss": 6.4936,
|
|
"mean_token_accuracy": 0.1254967123270035,
|
|
"num_tokens": 14369904.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.600764179229737,
|
|
"epoch": 0.7105784151104928,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004958808558903085,
|
|
"loss": 6.5159,
|
|
"mean_token_accuracy": 0.1256258577108383,
|
|
"num_tokens": 14382635.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.634089136123658,
|
|
"epoch": 0.7111134892182567,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004958735703296189,
|
|
"loss": 6.4644,
|
|
"mean_token_accuracy": 0.12675622776150702,
|
|
"num_tokens": 14393238.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.648471689224243,
|
|
"epoch": 0.7116485633260207,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000495866278391236,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.11887225434184075,
|
|
"num_tokens": 14403734.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.613070011138916,
|
|
"epoch": 0.7121836374337845,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004958589800753703,
|
|
"loss": 6.4929,
|
|
"mean_token_accuracy": 0.12244713827967643,
|
|
"num_tokens": 14414201.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.66301646232605,
|
|
"epoch": 0.7127187115415485,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004958516753822326,
|
|
"loss": 6.5289,
|
|
"mean_token_accuracy": 0.12371218875050545,
|
|
"num_tokens": 14425153.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.657406902313232,
|
|
"epoch": 0.7132537856493124,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004958443643120338,
|
|
"loss": 6.5241,
|
|
"mean_token_accuracy": 0.12605875432491304,
|
|
"num_tokens": 14435942.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.6519585132598875,
|
|
"epoch": 0.7137888597570764,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000495837046864985,
|
|
"loss": 6.4932,
|
|
"mean_token_accuracy": 0.12007287368178368,
|
|
"num_tokens": 14446371.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.603639745712281,
|
|
"epoch": 0.7143239338648403,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004958297230412976,
|
|
"loss": 6.441,
|
|
"mean_token_accuracy": 0.1266750544309616,
|
|
"num_tokens": 14456598.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.604157829284668,
|
|
"epoch": 0.7148590079726042,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004958223928411829,
|
|
"loss": 6.5335,
|
|
"mean_token_accuracy": 0.11728418618440628,
|
|
"num_tokens": 14466775.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.580257797241211,
|
|
"epoch": 0.7153940820803681,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004958150562648526,
|
|
"loss": 6.4875,
|
|
"mean_token_accuracy": 0.12353915274143219,
|
|
"num_tokens": 14476876.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.611274766921997,
|
|
"epoch": 0.715929156188132,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004958077133125187,
|
|
"loss": 6.4791,
|
|
"mean_token_accuracy": 0.12515356838703157,
|
|
"num_tokens": 14487698.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.68314151763916,
|
|
"epoch": 0.716464230295896,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000495800363984393,
|
|
"loss": 6.5109,
|
|
"mean_token_accuracy": 0.12278886809945107,
|
|
"num_tokens": 14498572.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.646966648101807,
|
|
"epoch": 0.7169993044036599,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004957930082806878,
|
|
"loss": 6.541,
|
|
"mean_token_accuracy": 0.12309601157903671,
|
|
"num_tokens": 14509673.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.733594274520874,
|
|
"epoch": 0.7175343785114239,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004957856462016155,
|
|
"loss": 6.6175,
|
|
"mean_token_accuracy": 0.1101705901324749,
|
|
"num_tokens": 14519974.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.673442077636719,
|
|
"epoch": 0.7180694526191878,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004957782777473888,
|
|
"loss": 6.5471,
|
|
"mean_token_accuracy": 0.11924330070614815,
|
|
"num_tokens": 14531194.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.6633258819580075,
|
|
"epoch": 0.7186045267269516,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004957709029182203,
|
|
"loss": 6.5071,
|
|
"mean_token_accuracy": 0.12078327909111977,
|
|
"num_tokens": 14542393.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.610497236251831,
|
|
"epoch": 0.7191396008347156,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004957635217143231,
|
|
"loss": 6.5048,
|
|
"mean_token_accuracy": 0.1303972415626049,
|
|
"num_tokens": 14552934.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.642151308059693,
|
|
"epoch": 0.7196746749424795,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00049575613413591,
|
|
"loss": 6.509,
|
|
"mean_token_accuracy": 0.1191837377846241,
|
|
"num_tokens": 14563643.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.6576708316802975,
|
|
"epoch": 0.7202097490502435,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004957487401831947,
|
|
"loss": 6.4417,
|
|
"mean_token_accuracy": 0.12699811831116675,
|
|
"num_tokens": 14574422.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.593110275268555,
|
|
"epoch": 0.7207448231580074,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004957413398563906,
|
|
"loss": 6.4382,
|
|
"mean_token_accuracy": 0.12065286710858344,
|
|
"num_tokens": 14585002.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.601973056793213,
|
|
"epoch": 0.7212798972657714,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004957339331557113,
|
|
"loss": 6.4717,
|
|
"mean_token_accuracy": 0.12474464699625969,
|
|
"num_tokens": 14595172.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.596518468856812,
|
|
"epoch": 0.7218149713735352,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004957265200813706,
|
|
"loss": 6.5807,
|
|
"mean_token_accuracy": 0.117759720236063,
|
|
"num_tokens": 14606316.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.714927291870117,
|
|
"epoch": 0.7223500454812991,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004957191006335827,
|
|
"loss": 6.5014,
|
|
"mean_token_accuracy": 0.1220408745110035,
|
|
"num_tokens": 14616394.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.60237946510315,
|
|
"epoch": 0.7228851195890631,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004957116748125618,
|
|
"loss": 6.4925,
|
|
"mean_token_accuracy": 0.12060601785778999,
|
|
"num_tokens": 14627474.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.641674566268921,
|
|
"epoch": 0.723420193696827,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004957042426185223,
|
|
"loss": 6.4355,
|
|
"mean_token_accuracy": 0.12912295013666153,
|
|
"num_tokens": 14638343.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.584613227844239,
|
|
"epoch": 0.723955267804591,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004956968040516789,
|
|
"loss": 6.5065,
|
|
"mean_token_accuracy": 0.1257261261343956,
|
|
"num_tokens": 14649115.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.56942195892334,
|
|
"epoch": 0.7244903419123548,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004956893591122461,
|
|
"loss": 6.5586,
|
|
"mean_token_accuracy": 0.12064994722604752,
|
|
"num_tokens": 14659714.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.771765947341919,
|
|
"epoch": 0.7250254160201188,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004956819078004392,
|
|
"loss": 6.6168,
|
|
"mean_token_accuracy": 0.11653464138507844,
|
|
"num_tokens": 14670481.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.666208028793335,
|
|
"epoch": 0.7255604901278827,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004956744501164732,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.12804916352033616,
|
|
"num_tokens": 14680816.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.61568808555603,
|
|
"epoch": 0.7260955642356466,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004956669860605634,
|
|
"loss": 6.5171,
|
|
"mean_token_accuracy": 0.12335993722081184,
|
|
"num_tokens": 14692723.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.673191213607788,
|
|
"epoch": 0.7266306383434106,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004956595156329254,
|
|
"loss": 6.5452,
|
|
"mean_token_accuracy": 0.12135704010725021,
|
|
"num_tokens": 14703824.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.702169513702392,
|
|
"epoch": 0.7271657124511745,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000495652038833775,
|
|
"loss": 6.5392,
|
|
"mean_token_accuracy": 0.12599010914564132,
|
|
"num_tokens": 14715934.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.59684648513794,
|
|
"epoch": 0.7277007865589384,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004956445556633279,
|
|
"loss": 6.5196,
|
|
"mean_token_accuracy": 0.12015130892395973,
|
|
"num_tokens": 14725617.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.650826406478882,
|
|
"epoch": 0.7282358606667023,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004956370661218003,
|
|
"loss": 6.5067,
|
|
"mean_token_accuracy": 0.12521070688962938,
|
|
"num_tokens": 14736430.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.667752599716186,
|
|
"epoch": 0.7287709347744663,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004956295702094084,
|
|
"loss": 6.5226,
|
|
"mean_token_accuracy": 0.12099665999412537,
|
|
"num_tokens": 14746740.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.595202827453614,
|
|
"epoch": 0.7293060088822302,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004956220679263687,
|
|
"loss": 6.4525,
|
|
"mean_token_accuracy": 0.12821099907159805,
|
|
"num_tokens": 14756884.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.620295190811158,
|
|
"epoch": 0.7298410829899941,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004956145592728976,
|
|
"loss": 6.4671,
|
|
"mean_token_accuracy": 0.12958234176039696,
|
|
"num_tokens": 14766974.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.61234450340271,
|
|
"epoch": 0.730376157097758,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004956070442492123,
|
|
"loss": 6.6338,
|
|
"mean_token_accuracy": 0.11591043546795846,
|
|
"num_tokens": 14778449.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.737421226501465,
|
|
"epoch": 0.7309112312055219,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004955995228555296,
|
|
"loss": 6.5585,
|
|
"mean_token_accuracy": 0.11935022845864296,
|
|
"num_tokens": 14788989.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.686759901046753,
|
|
"epoch": 0.7314463053132859,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004955919950920666,
|
|
"loss": 6.5359,
|
|
"mean_token_accuracy": 0.12702804654836655,
|
|
"num_tokens": 14798454.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.6847405433654785,
|
|
"epoch": 0.7319813794210498,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004955844609590408,
|
|
"loss": 6.4718,
|
|
"mean_token_accuracy": 0.12432443201541901,
|
|
"num_tokens": 14808920.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.660966157913208,
|
|
"epoch": 0.7325164535288138,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004955769204566696,
|
|
"loss": 6.4604,
|
|
"mean_token_accuracy": 0.12395694106817245,
|
|
"num_tokens": 14819250.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.6774553775787355,
|
|
"epoch": 0.7330515276365777,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004955693735851709,
|
|
"loss": 6.5337,
|
|
"mean_token_accuracy": 0.12554732635617255,
|
|
"num_tokens": 14829789.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.619939994812012,
|
|
"epoch": 0.7335866017443415,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004955618203447625,
|
|
"loss": 6.5029,
|
|
"mean_token_accuracy": 0.11812217831611634,
|
|
"num_tokens": 14840527.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.63070821762085,
|
|
"epoch": 0.7341216758521055,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004955542607356625,
|
|
"loss": 6.5723,
|
|
"mean_token_accuracy": 0.12455330342054367,
|
|
"num_tokens": 14850922.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.681782007217407,
|
|
"epoch": 0.7346567499598694,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004955466947580893,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.12653468996286393,
|
|
"num_tokens": 14862226.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.644733047485351,
|
|
"epoch": 0.7351918240676334,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004955391224122611,
|
|
"loss": 6.43,
|
|
"mean_token_accuracy": 0.1362067751586437,
|
|
"num_tokens": 14872461.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.562652635574341,
|
|
"epoch": 0.7357268981753973,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000495531543698397,
|
|
"loss": 6.5358,
|
|
"mean_token_accuracy": 0.12401769161224366,
|
|
"num_tokens": 14883088.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.700959300994873,
|
|
"epoch": 0.7362619722831613,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004955239586167153,
|
|
"loss": 6.56,
|
|
"mean_token_accuracy": 0.12005669027566909,
|
|
"num_tokens": 14894055.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.678454971313476,
|
|
"epoch": 0.7367970463909251,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004955163671674354,
|
|
"loss": 6.541,
|
|
"mean_token_accuracy": 0.1164636678993702,
|
|
"num_tokens": 14904760.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.714098310470581,
|
|
"epoch": 0.737332120498689,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004955087693507764,
|
|
"loss": 6.6366,
|
|
"mean_token_accuracy": 0.11821030676364899,
|
|
"num_tokens": 14915983.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.6209839344024655,
|
|
"epoch": 0.737867194606453,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004955011651669577,
|
|
"loss": 6.5292,
|
|
"mean_token_accuracy": 0.12145930454134941,
|
|
"num_tokens": 14925959.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.624723815917969,
|
|
"epoch": 0.7384022687142169,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004954935546161988,
|
|
"loss": 6.4746,
|
|
"mean_token_accuracy": 0.12642812803387643,
|
|
"num_tokens": 14936138.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.725174236297607,
|
|
"epoch": 0.7389373428219809,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004954859376987195,
|
|
"loss": 6.489,
|
|
"mean_token_accuracy": 0.1262475609779358,
|
|
"num_tokens": 14946979.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.584106826782227,
|
|
"epoch": 0.7394724169297447,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004954783144147397,
|
|
"loss": 6.5651,
|
|
"mean_token_accuracy": 0.11757045090198517,
|
|
"num_tokens": 14958324.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.6707359790802006,
|
|
"epoch": 0.7400074910375087,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004954706847644796,
|
|
"loss": 6.5684,
|
|
"mean_token_accuracy": 0.1211273081600666,
|
|
"num_tokens": 14969048.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.694032001495361,
|
|
"epoch": 0.7405425651452726,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004954630487481594,
|
|
"loss": 6.5692,
|
|
"mean_token_accuracy": 0.11960589215159416,
|
|
"num_tokens": 14979825.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.620651435852051,
|
|
"epoch": 0.7410776392530365,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004954554063659998,
|
|
"loss": 6.4985,
|
|
"mean_token_accuracy": 0.12779693081974983,
|
|
"num_tokens": 14990138.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.595761060714722,
|
|
"epoch": 0.7416127133608005,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004954477576182212,
|
|
"loss": 6.4541,
|
|
"mean_token_accuracy": 0.1236427053809166,
|
|
"num_tokens": 15002276.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.62862548828125,
|
|
"epoch": 0.7421477874685644,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004954401025050445,
|
|
"loss": 6.5908,
|
|
"mean_token_accuracy": 0.12096235230565071,
|
|
"num_tokens": 15013622.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.696679782867432,
|
|
"epoch": 0.7426828615763283,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004954324410266909,
|
|
"loss": 6.5389,
|
|
"mean_token_accuracy": 0.12324451431632041,
|
|
"num_tokens": 15024067.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.690721940994263,
|
|
"epoch": 0.7432179356840922,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004954247731833815,
|
|
"loss": 6.426,
|
|
"mean_token_accuracy": 0.13052220717072488,
|
|
"num_tokens": 15033646.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.586018133163452,
|
|
"epoch": 0.7437530097918562,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004954170989753377,
|
|
"loss": 6.4792,
|
|
"mean_token_accuracy": 0.12448109984397888,
|
|
"num_tokens": 15044655.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.656375455856323,
|
|
"epoch": 0.7442880838996201,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004954094184027813,
|
|
"loss": 6.5474,
|
|
"mean_token_accuracy": 0.12063681930303574,
|
|
"num_tokens": 15055492.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.646824169158935,
|
|
"epoch": 0.744823158007384,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004954017314659339,
|
|
"loss": 6.5472,
|
|
"mean_token_accuracy": 0.1146118775010109,
|
|
"num_tokens": 15066472.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.7163914203643795,
|
|
"epoch": 0.745358232115148,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004953940381650174,
|
|
"loss": 6.4972,
|
|
"mean_token_accuracy": 0.1269778162240982,
|
|
"num_tokens": 15076851.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.556030654907227,
|
|
"epoch": 0.7458933062229118,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004953863385002541,
|
|
"loss": 6.4307,
|
|
"mean_token_accuracy": 0.1233529731631279,
|
|
"num_tokens": 15086997.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.656186962127686,
|
|
"epoch": 0.7464283803306758,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004953786324718661,
|
|
"loss": 6.5893,
|
|
"mean_token_accuracy": 0.12068824991583824,
|
|
"num_tokens": 15098625.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.646282291412353,
|
|
"epoch": 0.7469634544384397,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004953709200800761,
|
|
"loss": 6.4115,
|
|
"mean_token_accuracy": 0.12885420992970467,
|
|
"num_tokens": 15108265.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.62951431274414,
|
|
"epoch": 0.7474985285462037,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004953632013251068,
|
|
"loss": 6.5082,
|
|
"mean_token_accuracy": 0.12161318883299828,
|
|
"num_tokens": 15118794.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.635647344589233,
|
|
"epoch": 0.7480336026539676,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004953554762071811,
|
|
"loss": 6.5331,
|
|
"mean_token_accuracy": 0.12119115442037583,
|
|
"num_tokens": 15130084.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.610635709762573,
|
|
"epoch": 0.7485686767617316,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004953477447265218,
|
|
"loss": 6.5208,
|
|
"mean_token_accuracy": 0.12170757949352265,
|
|
"num_tokens": 15142193.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.665874671936035,
|
|
"epoch": 0.7491037508694954,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004953400068833524,
|
|
"loss": 6.6493,
|
|
"mean_token_accuracy": 0.11788548156619072,
|
|
"num_tokens": 15152817.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.602761936187744,
|
|
"epoch": 0.7496388249772593,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004953322626778964,
|
|
"loss": 6.3167,
|
|
"mean_token_accuracy": 0.12905730307102203,
|
|
"num_tokens": 15162352.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.703404474258423,
|
|
"epoch": 0.7501738990850233,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004953245121103771,
|
|
"loss": 6.4961,
|
|
"mean_token_accuracy": 0.12932127937674523,
|
|
"num_tokens": 15173091.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.740525579452514,
|
|
"epoch": 0.7507089731927872,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004953167551810185,
|
|
"loss": 6.6655,
|
|
"mean_token_accuracy": 0.11352887824177742,
|
|
"num_tokens": 15184422.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.594454669952393,
|
|
"epoch": 0.7512440473005512,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004953089918900447,
|
|
"loss": 6.3914,
|
|
"mean_token_accuracy": 0.1325460284948349,
|
|
"num_tokens": 15194765.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.6288597106933596,
|
|
"epoch": 0.751779121408315,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004953012222376795,
|
|
"loss": 6.5574,
|
|
"mean_token_accuracy": 0.1187102161347866,
|
|
"num_tokens": 15206007.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.674781751632691,
|
|
"epoch": 0.752314195516079,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004952934462241476,
|
|
"loss": 6.5011,
|
|
"mean_token_accuracy": 0.12254004329442977,
|
|
"num_tokens": 15216634.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.678082895278931,
|
|
"epoch": 0.7528492696238429,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004952856638496734,
|
|
"loss": 6.5629,
|
|
"mean_token_accuracy": 0.1190415732562542,
|
|
"num_tokens": 15226931.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.638029479980469,
|
|
"epoch": 0.7533843437316068,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004952778751144817,
|
|
"loss": 6.5483,
|
|
"mean_token_accuracy": 0.12212915867567062,
|
|
"num_tokens": 15239034.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.661996650695801,
|
|
"epoch": 0.7539194178393708,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004952700800187971,
|
|
"loss": 6.549,
|
|
"mean_token_accuracy": 0.1195674143731594,
|
|
"num_tokens": 15250088.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.628537654876709,
|
|
"epoch": 0.7544544919471347,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000495262278562845,
|
|
"loss": 6.4688,
|
|
"mean_token_accuracy": 0.12291692420840264,
|
|
"num_tokens": 15261150.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.656700706481933,
|
|
"epoch": 0.7549895660548986,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004952544707468506,
|
|
"loss": 6.559,
|
|
"mean_token_accuracy": 0.12314437106251716,
|
|
"num_tokens": 15270865.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.710972547531128,
|
|
"epoch": 0.7555246401626625,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004952466565710391,
|
|
"loss": 6.5756,
|
|
"mean_token_accuracy": 0.11969075724482536,
|
|
"num_tokens": 15282809.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.71706256866455,
|
|
"epoch": 0.7560597142704265,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004952388360356366,
|
|
"loss": 6.5257,
|
|
"mean_token_accuracy": 0.12456669732928276,
|
|
"num_tokens": 15293166.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.624244499206543,
|
|
"epoch": 0.7565947883781904,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004952310091408685,
|
|
"loss": 6.4979,
|
|
"mean_token_accuracy": 0.12615071907639502,
|
|
"num_tokens": 15302985.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.661012649536133,
|
|
"epoch": 0.7571298624859543,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004952231758869611,
|
|
"loss": 6.5389,
|
|
"mean_token_accuracy": 0.12616140097379686,
|
|
"num_tokens": 15314737.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.635220861434936,
|
|
"epoch": 0.7576649365937183,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004952153362741403,
|
|
"loss": 6.4728,
|
|
"mean_token_accuracy": 0.12891757264733314,
|
|
"num_tokens": 15325441.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.596683406829834,
|
|
"epoch": 0.7582000107014821,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004952074903026327,
|
|
"loss": 6.4163,
|
|
"mean_token_accuracy": 0.12532624676823617,
|
|
"num_tokens": 15334939.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.6016768455505375,
|
|
"epoch": 0.7587350848092461,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004951996379726647,
|
|
"loss": 6.5682,
|
|
"mean_token_accuracy": 0.11918097287416458,
|
|
"num_tokens": 15345655.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.582686948776245,
|
|
"epoch": 0.75927015891701,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004951917792844631,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.13022494167089463,
|
|
"num_tokens": 15356035.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.677178382873535,
|
|
"epoch": 0.759805233024774,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004951839142382548,
|
|
"loss": 6.5202,
|
|
"mean_token_accuracy": 0.12313127294182777,
|
|
"num_tokens": 15368509.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.65141110420227,
|
|
"epoch": 0.7603403071325379,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000495176042834267,
|
|
"loss": 6.4974,
|
|
"mean_token_accuracy": 0.12508352920413018,
|
|
"num_tokens": 15379662.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.6174569606781,
|
|
"epoch": 0.7608753812403017,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004951681650727268,
|
|
"loss": 6.5051,
|
|
"mean_token_accuracy": 0.11847602352499961,
|
|
"num_tokens": 15389698.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.727388477325439,
|
|
"epoch": 0.7614104553480657,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004951602809538619,
|
|
"loss": 6.588,
|
|
"mean_token_accuracy": 0.11893510520458221,
|
|
"num_tokens": 15400724.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.745078134536743,
|
|
"epoch": 0.7619455294558296,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004951523904778997,
|
|
"loss": 6.591,
|
|
"mean_token_accuracy": 0.11919107511639596,
|
|
"num_tokens": 15410732.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.625560998916626,
|
|
"epoch": 0.7624806035635936,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004951444936450682,
|
|
"loss": 6.471,
|
|
"mean_token_accuracy": 0.12457225322723389,
|
|
"num_tokens": 15420185.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.608731412887574,
|
|
"epoch": 0.7630156776713575,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004951365904555954,
|
|
"loss": 6.4194,
|
|
"mean_token_accuracy": 0.128256955742836,
|
|
"num_tokens": 15431904.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.633652448654175,
|
|
"epoch": 0.7635507517791215,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004951286809097094,
|
|
"loss": 6.537,
|
|
"mean_token_accuracy": 0.11936908960342407,
|
|
"num_tokens": 15442650.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.586218214035034,
|
|
"epoch": 0.7640858258868853,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004951207650076388,
|
|
"loss": 6.5114,
|
|
"mean_token_accuracy": 0.12093442976474762,
|
|
"num_tokens": 15454273.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.6608314037323,
|
|
"epoch": 0.7646208999946492,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000495112842749612,
|
|
"loss": 6.5037,
|
|
"mean_token_accuracy": 0.1250052809715271,
|
|
"num_tokens": 15465751.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.676463317871094,
|
|
"epoch": 0.7651559741024132,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004951049141358578,
|
|
"loss": 6.5974,
|
|
"mean_token_accuracy": 0.11710449010133743,
|
|
"num_tokens": 15475340.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.740106821060181,
|
|
"epoch": 0.7656910482101771,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004950969791666051,
|
|
"loss": 6.5594,
|
|
"mean_token_accuracy": 0.1207512453198433,
|
|
"num_tokens": 15486246.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.715411233901977,
|
|
"epoch": 0.7662261223179411,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004950890378420831,
|
|
"loss": 6.5699,
|
|
"mean_token_accuracy": 0.11808683201670647,
|
|
"num_tokens": 15497331.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.654520702362061,
|
|
"epoch": 0.766761196425705,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000495081090162521,
|
|
"loss": 6.5096,
|
|
"mean_token_accuracy": 0.12088059484958649,
|
|
"num_tokens": 15508036.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.683218002319336,
|
|
"epoch": 0.7672962705334689,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004950731361281483,
|
|
"loss": 6.5029,
|
|
"mean_token_accuracy": 0.12600938752293586,
|
|
"num_tokens": 15518381.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.624848222732544,
|
|
"epoch": 0.7678313446412328,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004950651757391948,
|
|
"loss": 6.5085,
|
|
"mean_token_accuracy": 0.12033105567097664,
|
|
"num_tokens": 15528939.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.644553518295288,
|
|
"epoch": 0.7683664187489967,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004950572089958904,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.1190042331814766,
|
|
"num_tokens": 15539718.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.666055059432983,
|
|
"epoch": 0.7689014928567607,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004950492358984648,
|
|
"loss": 6.6481,
|
|
"mean_token_accuracy": 0.11551404148340225,
|
|
"num_tokens": 15550970.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.687109327316284,
|
|
"epoch": 0.7694365669645246,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004950412564471486,
|
|
"loss": 6.4337,
|
|
"mean_token_accuracy": 0.12744976207613945,
|
|
"num_tokens": 15560490.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.586294460296631,
|
|
"epoch": 0.7699716410722885,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000495033270642172,
|
|
"loss": 6.4215,
|
|
"mean_token_accuracy": 0.12735797762870787,
|
|
"num_tokens": 15570188.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.541706228256226,
|
|
"epoch": 0.7705067151800524,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004950252784837655,
|
|
"loss": 6.4627,
|
|
"mean_token_accuracy": 0.11572838947176933,
|
|
"num_tokens": 15581446.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.709228610992431,
|
|
"epoch": 0.7710417892878164,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004950172799721601,
|
|
"loss": 6.5606,
|
|
"mean_token_accuracy": 0.11891056299209594,
|
|
"num_tokens": 15594362.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.676780128479004,
|
|
"epoch": 0.7715768633955803,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004950092751075866,
|
|
"loss": 6.4434,
|
|
"mean_token_accuracy": 0.13257938623428345,
|
|
"num_tokens": 15605531.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.671533870697021,
|
|
"epoch": 0.7721119375033442,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004950012638902763,
|
|
"loss": 6.4662,
|
|
"mean_token_accuracy": 0.12182921767234803,
|
|
"num_tokens": 15614962.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.565979242324829,
|
|
"epoch": 0.7726470116111082,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004949932463204603,
|
|
"loss": 6.5319,
|
|
"mean_token_accuracy": 0.12246931493282318,
|
|
"num_tokens": 15625475.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.58702278137207,
|
|
"epoch": 0.773182085718872,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004949852223983703,
|
|
"loss": 6.5241,
|
|
"mean_token_accuracy": 0.120680171251297,
|
|
"num_tokens": 15637359.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.760842037200928,
|
|
"epoch": 0.773717159826636,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004949771921242379,
|
|
"loss": 6.5615,
|
|
"mean_token_accuracy": 0.11752678826451302,
|
|
"num_tokens": 15648368.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.755098438262939,
|
|
"epoch": 0.7742522339343999,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004949691554982951,
|
|
"loss": 6.4566,
|
|
"mean_token_accuracy": 0.12675629630684854,
|
|
"num_tokens": 15659295.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.602674770355224,
|
|
"epoch": 0.7747873080421639,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004949611125207737,
|
|
"loss": 6.4116,
|
|
"mean_token_accuracy": 0.1236474186182022,
|
|
"num_tokens": 15669975.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.5768678188323975,
|
|
"epoch": 0.7753223821499278,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000494953063191906,
|
|
"loss": 6.5094,
|
|
"mean_token_accuracy": 0.1212529256939888,
|
|
"num_tokens": 15680343.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.634136152267456,
|
|
"epoch": 0.7758574562576916,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004949450075119247,
|
|
"loss": 6.5648,
|
|
"mean_token_accuracy": 0.11556384637951851,
|
|
"num_tokens": 15692246.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.709217309951782,
|
|
"epoch": 0.7763925303654556,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004949369454810621,
|
|
"loss": 6.5163,
|
|
"mean_token_accuracy": 0.1260776087641716,
|
|
"num_tokens": 15704262.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.6387945175170895,
|
|
"epoch": 0.7769276044732195,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004949288770995512,
|
|
"loss": 6.5103,
|
|
"mean_token_accuracy": 0.12543663531541824,
|
|
"num_tokens": 15715078.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.650964450836182,
|
|
"epoch": 0.7774626785809835,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004949208023676249,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.1243963100016117,
|
|
"num_tokens": 15726503.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.579547500610351,
|
|
"epoch": 0.7779977526887474,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004949127212855161,
|
|
"loss": 6.4455,
|
|
"mean_token_accuracy": 0.12149401158094406,
|
|
"num_tokens": 15738854.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.612250089645386,
|
|
"epoch": 0.7785328267965114,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004949046338534587,
|
|
"loss": 6.5971,
|
|
"mean_token_accuracy": 0.11889164671301841,
|
|
"num_tokens": 15750836.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.752082014083863,
|
|
"epoch": 0.7790679009042752,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004948965400716857,
|
|
"loss": 6.608,
|
|
"mean_token_accuracy": 0.121877883374691,
|
|
"num_tokens": 15762355.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.758044195175171,
|
|
"epoch": 0.7796029750120391,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000494888439940431,
|
|
"loss": 6.5895,
|
|
"mean_token_accuracy": 0.12153554931282998,
|
|
"num_tokens": 15772952.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.582353353500366,
|
|
"epoch": 0.7801380491198031,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004948803334599286,
|
|
"loss": 6.409,
|
|
"mean_token_accuracy": 0.13075213581323625,
|
|
"num_tokens": 15782997.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.55920262336731,
|
|
"epoch": 0.780673123227567,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004948722206304123,
|
|
"loss": 6.5156,
|
|
"mean_token_accuracy": 0.11841614395380021,
|
|
"num_tokens": 15794060.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.693296957015991,
|
|
"epoch": 0.781208197335331,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004948641014521167,
|
|
"loss": 6.5705,
|
|
"mean_token_accuracy": 0.12151769399642945,
|
|
"num_tokens": 15804149.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.671383333206177,
|
|
"epoch": 0.7817432714430949,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000494855975925276,
|
|
"loss": 6.507,
|
|
"mean_token_accuracy": 0.12321450114250183,
|
|
"num_tokens": 15814643.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.649303817749024,
|
|
"epoch": 0.7822783455508588,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004948478440501249,
|
|
"loss": 6.4702,
|
|
"mean_token_accuracy": 0.12525373995304107,
|
|
"num_tokens": 15824640.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.579389524459839,
|
|
"epoch": 0.7828134196586227,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004948397058268982,
|
|
"loss": 6.4844,
|
|
"mean_token_accuracy": 0.12553136944770812,
|
|
"num_tokens": 15836160.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.663361024856568,
|
|
"epoch": 0.7833484937663866,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004948315612558308,
|
|
"loss": 6.547,
|
|
"mean_token_accuracy": 0.11733492165803909,
|
|
"num_tokens": 15846886.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.651957893371582,
|
|
"epoch": 0.7838835678741506,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000494823410337158,
|
|
"loss": 6.4735,
|
|
"mean_token_accuracy": 0.1267278976738453,
|
|
"num_tokens": 15857309.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.610154867172241,
|
|
"epoch": 0.7844186419819145,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004948152530711153,
|
|
"loss": 6.6044,
|
|
"mean_token_accuracy": 0.12071408331394196,
|
|
"num_tokens": 15869620.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.609307289123535,
|
|
"epoch": 0.7849537160896785,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004948070894579378,
|
|
"loss": 6.4403,
|
|
"mean_token_accuracy": 0.13011660799384117,
|
|
"num_tokens": 15880915.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.596193408966064,
|
|
"epoch": 0.7854887901974423,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004947989194978616,
|
|
"loss": 6.4983,
|
|
"mean_token_accuracy": 0.12866594642400742,
|
|
"num_tokens": 15891150.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.658902025222778,
|
|
"epoch": 0.7860238643052063,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004947907431911225,
|
|
"loss": 6.5106,
|
|
"mean_token_accuracy": 0.1270284228026867,
|
|
"num_tokens": 15902526.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.587319469451904,
|
|
"epoch": 0.7865589384129702,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004947825605379566,
|
|
"loss": 6.4472,
|
|
"mean_token_accuracy": 0.12495649605989456,
|
|
"num_tokens": 15913425.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.638164091110229,
|
|
"epoch": 0.7870940125207341,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004947743715386,
|
|
"loss": 6.4373,
|
|
"mean_token_accuracy": 0.1226458765566349,
|
|
"num_tokens": 15924324.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.563573503494263,
|
|
"epoch": 0.7876290866284981,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004947661761932894,
|
|
"loss": 6.4897,
|
|
"mean_token_accuracy": 0.1234087035059929,
|
|
"num_tokens": 15935533.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.585987091064453,
|
|
"epoch": 0.7881641607362619,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004947579745022613,
|
|
"loss": 6.4389,
|
|
"mean_token_accuracy": 0.1224522590637207,
|
|
"num_tokens": 15947007.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.623542547225952,
|
|
"epoch": 0.7886992348440259,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004947497664657527,
|
|
"loss": 6.5116,
|
|
"mean_token_accuracy": 0.11858915165066719,
|
|
"num_tokens": 15957405.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.620118808746338,
|
|
"epoch": 0.7892343089517898,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004947415520840003,
|
|
"loss": 6.4874,
|
|
"mean_token_accuracy": 0.12732534483075142,
|
|
"num_tokens": 15969895.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.622705030441284,
|
|
"epoch": 0.7897693830595538,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004947333313572416,
|
|
"loss": 6.3962,
|
|
"mean_token_accuracy": 0.13420234993100166,
|
|
"num_tokens": 15979854.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.584606695175171,
|
|
"epoch": 0.7903044571673177,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004947251042857137,
|
|
"loss": 6.4194,
|
|
"mean_token_accuracy": 0.12605082169175147,
|
|
"num_tokens": 15991341.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.575461292266846,
|
|
"epoch": 0.7908395312750816,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004947168708696544,
|
|
"loss": 6.4636,
|
|
"mean_token_accuracy": 0.12959639057517053,
|
|
"num_tokens": 16001944.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.567953586578369,
|
|
"epoch": 0.7913746053828455,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004947086311093013,
|
|
"loss": 6.4513,
|
|
"mean_token_accuracy": 0.12289869785308838,
|
|
"num_tokens": 16011771.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.685804033279419,
|
|
"epoch": 0.7919096794906094,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004947003850048924,
|
|
"loss": 6.6074,
|
|
"mean_token_accuracy": 0.11378901451826096,
|
|
"num_tokens": 16023901.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.685398006439209,
|
|
"epoch": 0.7924447535983734,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004946921325566656,
|
|
"loss": 6.523,
|
|
"mean_token_accuracy": 0.11848910003900529,
|
|
"num_tokens": 16035014.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.666433811187744,
|
|
"epoch": 0.7929798277061373,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004946838737648595,
|
|
"loss": 6.6137,
|
|
"mean_token_accuracy": 0.11679703816771507,
|
|
"num_tokens": 16046927.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.641306829452515,
|
|
"epoch": 0.7935149018139013,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004946756086297124,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.12602971494197845,
|
|
"num_tokens": 16057341.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.671058607101441,
|
|
"epoch": 0.7940499759216652,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004946673371514628,
|
|
"loss": 6.4891,
|
|
"mean_token_accuracy": 0.1256909728050232,
|
|
"num_tokens": 16068408.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.60824761390686,
|
|
"epoch": 0.794585050029429,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004946590593303499,
|
|
"loss": 6.4697,
|
|
"mean_token_accuracy": 0.12560921236872674,
|
|
"num_tokens": 16078693.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.6087244033813475,
|
|
"epoch": 0.795120124137193,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004946507751666124,
|
|
"loss": 6.5061,
|
|
"mean_token_accuracy": 0.12688896283507348,
|
|
"num_tokens": 16089127.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.621689891815185,
|
|
"epoch": 0.7956551982449569,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004946424846604897,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.1354895919561386,
|
|
"num_tokens": 16099726.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.6390087604522705,
|
|
"epoch": 0.7961902723527209,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004946341878122212,
|
|
"loss": 6.4647,
|
|
"mean_token_accuracy": 0.1274692714214325,
|
|
"num_tokens": 16111017.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.599430751800537,
|
|
"epoch": 0.7967253464604848,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004946258846220462,
|
|
"loss": 6.5404,
|
|
"mean_token_accuracy": 0.12424082234501839,
|
|
"num_tokens": 16121406.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.594069862365723,
|
|
"epoch": 0.7972604205682488,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004946175750902049,
|
|
"loss": 6.4731,
|
|
"mean_token_accuracy": 0.12630101516842843,
|
|
"num_tokens": 16131587.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.636374759674072,
|
|
"epoch": 0.7977954946760126,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004946092592169368,
|
|
"loss": 6.4493,
|
|
"mean_token_accuracy": 0.12778721749782562,
|
|
"num_tokens": 16142578.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.711662626266479,
|
|
"epoch": 0.7983305687837765,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004946009370024822,
|
|
"loss": 6.4386,
|
|
"mean_token_accuracy": 0.128027480840683,
|
|
"num_tokens": 16153501.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.5966109275817875,
|
|
"epoch": 0.7988656428915405,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004945926084470814,
|
|
"loss": 6.5275,
|
|
"mean_token_accuracy": 0.12179762721061707,
|
|
"num_tokens": 16164273.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.637197351455688,
|
|
"epoch": 0.7994007169993044,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004945842735509749,
|
|
"loss": 6.5045,
|
|
"mean_token_accuracy": 0.12241605445742607,
|
|
"num_tokens": 16175071.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.6747242450714115,
|
|
"epoch": 0.7999357911070684,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004945759323144034,
|
|
"loss": 6.5473,
|
|
"mean_token_accuracy": 0.11887720599770546,
|
|
"num_tokens": 16185404.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.6123066425323485,
|
|
"epoch": 0.8004708652148322,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004945675847376077,
|
|
"loss": 6.542,
|
|
"mean_token_accuracy": 0.12083189710974693,
|
|
"num_tokens": 16196881.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.676771831512451,
|
|
"epoch": 0.8010059393225962,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004945592308208288,
|
|
"loss": 6.5565,
|
|
"mean_token_accuracy": 0.12063202857971192,
|
|
"num_tokens": 16207534.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.694723606109619,
|
|
"epoch": 0.8015410134303601,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000494550870564308,
|
|
"loss": 6.4241,
|
|
"mean_token_accuracy": 0.13715741857886316,
|
|
"num_tokens": 16217371.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.663383913040161,
|
|
"epoch": 0.802076087538124,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004945425039682866,
|
|
"loss": 6.4825,
|
|
"mean_token_accuracy": 0.12449019849300384,
|
|
"num_tokens": 16227898.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.609432649612427,
|
|
"epoch": 0.802611161645888,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004945341310330064,
|
|
"loss": 6.4686,
|
|
"mean_token_accuracy": 0.1264779381453991,
|
|
"num_tokens": 16238966.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.603596830368042,
|
|
"epoch": 0.8031462357536518,
|
|
"grad_norm": 6.875,
|
|
"learning_rate": 0.0004945257517587089,
|
|
"loss": 6.5147,
|
|
"mean_token_accuracy": 0.13054847419261933,
|
|
"num_tokens": 16250129.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.603615140914917,
|
|
"epoch": 0.8036813098614158,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004945173661456361,
|
|
"loss": 6.5276,
|
|
"mean_token_accuracy": 0.12011083886027336,
|
|
"num_tokens": 16260877.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.680617380142212,
|
|
"epoch": 0.8042163839691797,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004945089741940303,
|
|
"loss": 6.5001,
|
|
"mean_token_accuracy": 0.12761500477790833,
|
|
"num_tokens": 16270548.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.632005786895752,
|
|
"epoch": 0.8047514580769437,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004945005759041338,
|
|
"loss": 6.5089,
|
|
"mean_token_accuracy": 0.11966138556599618,
|
|
"num_tokens": 16281014.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.672308731079101,
|
|
"epoch": 0.8052865321847076,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004944921712761889,
|
|
"loss": 6.5553,
|
|
"mean_token_accuracy": 0.1285837821662426,
|
|
"num_tokens": 16291653.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.670130491256714,
|
|
"epoch": 0.8058216062924715,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004944837603104383,
|
|
"loss": 6.4205,
|
|
"mean_token_accuracy": 0.12542239874601363,
|
|
"num_tokens": 16301703.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.587788438796997,
|
|
"epoch": 0.8063566804002354,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004944753430071252,
|
|
"loss": 6.4847,
|
|
"mean_token_accuracy": 0.12820887789130211,
|
|
"num_tokens": 16312252.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.5927026748657225,
|
|
"epoch": 0.8068917545079993,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004944669193664923,
|
|
"loss": 6.469,
|
|
"mean_token_accuracy": 0.12172207832336426,
|
|
"num_tokens": 16324073.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.664837837219238,
|
|
"epoch": 0.8074268286157633,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004944584893887829,
|
|
"loss": 6.4597,
|
|
"mean_token_accuracy": 0.12440455704927444,
|
|
"num_tokens": 16334637.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.654309034347534,
|
|
"epoch": 0.8079619027235272,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004944500530742404,
|
|
"loss": 6.6055,
|
|
"mean_token_accuracy": 0.11858819797635078,
|
|
"num_tokens": 16345581.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.684944152832031,
|
|
"epoch": 0.8084969768312912,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004944416104231086,
|
|
"loss": 6.5789,
|
|
"mean_token_accuracy": 0.1192588560283184,
|
|
"num_tokens": 16356995.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.693460464477539,
|
|
"epoch": 0.8090320509390551,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004944331614356311,
|
|
"loss": 6.5342,
|
|
"mean_token_accuracy": 0.11939701288938523,
|
|
"num_tokens": 16368841.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.670605850219727,
|
|
"epoch": 0.8095671250468189,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004944247061120519,
|
|
"loss": 6.4614,
|
|
"mean_token_accuracy": 0.12320000305771828,
|
|
"num_tokens": 16379295.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.655962562561035,
|
|
"epoch": 0.8101021991545829,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004944162444526151,
|
|
"loss": 6.4932,
|
|
"mean_token_accuracy": 0.1294848293066025,
|
|
"num_tokens": 16389512.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.5763404846191404,
|
|
"epoch": 0.8106372732623468,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004944077764575651,
|
|
"loss": 6.4292,
|
|
"mean_token_accuracy": 0.1295583054423332,
|
|
"num_tokens": 16400720.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.600707244873047,
|
|
"epoch": 0.8111723473701108,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004943993021271463,
|
|
"loss": 6.4876,
|
|
"mean_token_accuracy": 0.12405232936143876,
|
|
"num_tokens": 16411278.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.6749989032745365,
|
|
"epoch": 0.8117074214778747,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004943908214616035,
|
|
"loss": 6.5309,
|
|
"mean_token_accuracy": 0.12361326441168785,
|
|
"num_tokens": 16421665.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.674616718292237,
|
|
"epoch": 0.8122424955856387,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004943823344611818,
|
|
"loss": 6.5708,
|
|
"mean_token_accuracy": 0.1173178568482399,
|
|
"num_tokens": 16432943.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.698454856872559,
|
|
"epoch": 0.8127775696934025,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004943738411261258,
|
|
"loss": 6.4919,
|
|
"mean_token_accuracy": 0.12141416668891906,
|
|
"num_tokens": 16444506.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.642475366592407,
|
|
"epoch": 0.8133126438011664,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004943653414566809,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.12385025173425675,
|
|
"num_tokens": 16455403.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.731345081329346,
|
|
"epoch": 0.8138477179089304,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004943568354530927,
|
|
"loss": 6.613,
|
|
"mean_token_accuracy": 0.11516171023249626,
|
|
"num_tokens": 16465616.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.726811838150025,
|
|
"epoch": 0.8143827920166943,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004943483231156068,
|
|
"loss": 6.5872,
|
|
"mean_token_accuracy": 0.11804022192955017,
|
|
"num_tokens": 16476850.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.706709480285644,
|
|
"epoch": 0.8149178661244583,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004943398044444687,
|
|
"loss": 6.5154,
|
|
"mean_token_accuracy": 0.12309501916170121,
|
|
"num_tokens": 16489118.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.67537751197815,
|
|
"epoch": 0.8154529402322221,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004943312794399246,
|
|
"loss": 6.471,
|
|
"mean_token_accuracy": 0.12412431761622429,
|
|
"num_tokens": 16499336.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.6803254127502445,
|
|
"epoch": 0.8159880143399861,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004943227481022207,
|
|
"loss": 6.5545,
|
|
"mean_token_accuracy": 0.1191781371831894,
|
|
"num_tokens": 16510158.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.632819938659668,
|
|
"epoch": 0.81652308844775,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004943142104316033,
|
|
"loss": 6.478,
|
|
"mean_token_accuracy": 0.12543730065226555,
|
|
"num_tokens": 16521080.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.621398544311523,
|
|
"epoch": 0.8170581625555139,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004943056664283189,
|
|
"loss": 6.492,
|
|
"mean_token_accuracy": 0.12795101329684258,
|
|
"num_tokens": 16531072.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.613581657409668,
|
|
"epoch": 0.8175932366632779,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000494297116092614,
|
|
"loss": 6.5779,
|
|
"mean_token_accuracy": 0.11593121886253357,
|
|
"num_tokens": 16542588.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.68043966293335,
|
|
"epoch": 0.8181283107710418,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004942885594247359,
|
|
"loss": 6.4505,
|
|
"mean_token_accuracy": 0.12152803242206574,
|
|
"num_tokens": 16553466.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.655302667617798,
|
|
"epoch": 0.8186633848788057,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004942799964249314,
|
|
"loss": 6.475,
|
|
"mean_token_accuracy": 0.12144461870193482,
|
|
"num_tokens": 16564084.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.643061351776123,
|
|
"epoch": 0.8191984589865696,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004942714270934479,
|
|
"loss": 6.4978,
|
|
"mean_token_accuracy": 0.13362600430846214,
|
|
"num_tokens": 16575665.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.630150651931762,
|
|
"epoch": 0.8197335330943336,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004942628514305326,
|
|
"loss": 6.4987,
|
|
"mean_token_accuracy": 0.12221122458577156,
|
|
"num_tokens": 16586518.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.635692739486695,
|
|
"epoch": 0.8202686072020975,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004942542694364333,
|
|
"loss": 6.5133,
|
|
"mean_token_accuracy": 0.12400550916790962,
|
|
"num_tokens": 16597345.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.662454986572266,
|
|
"epoch": 0.8208036813098614,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004942456811113978,
|
|
"loss": 6.5252,
|
|
"mean_token_accuracy": 0.12513843253254892,
|
|
"num_tokens": 16609586.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.681049108505249,
|
|
"epoch": 0.8213387554176254,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004942370864556741,
|
|
"loss": 6.4085,
|
|
"mean_token_accuracy": 0.13168345540761947,
|
|
"num_tokens": 16620165.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.6004468441009525,
|
|
"epoch": 0.8218738295253892,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004942284854695104,
|
|
"loss": 6.515,
|
|
"mean_token_accuracy": 0.12508425787091254,
|
|
"num_tokens": 16631200.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.671335506439209,
|
|
"epoch": 0.8224089036331532,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004942198781531549,
|
|
"loss": 6.5396,
|
|
"mean_token_accuracy": 0.12049819454550743,
|
|
"num_tokens": 16642553.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.694266843795776,
|
|
"epoch": 0.8229439777409171,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004942112645068561,
|
|
"loss": 6.5416,
|
|
"mean_token_accuracy": 0.11660793125629425,
|
|
"num_tokens": 16653431.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.632432079315185,
|
|
"epoch": 0.8234790518486811,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000494202644530863,
|
|
"loss": 6.4823,
|
|
"mean_token_accuracy": 0.12479487210512161,
|
|
"num_tokens": 16664880.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.60318956375122,
|
|
"epoch": 0.824014125956445,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.0004941940182254244,
|
|
"loss": 6.5049,
|
|
"mean_token_accuracy": 0.12559020891785622,
|
|
"num_tokens": 16676224.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.6330766677856445,
|
|
"epoch": 0.8245492000642088,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004941853855907892,
|
|
"loss": 6.5469,
|
|
"mean_token_accuracy": 0.12000092715024949,
|
|
"num_tokens": 16687732.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.702239513397217,
|
|
"epoch": 0.8250842741719728,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004941767466272068,
|
|
"loss": 6.5091,
|
|
"mean_token_accuracy": 0.12498635873198509,
|
|
"num_tokens": 16698257.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.653573131561279,
|
|
"epoch": 0.8256193482797367,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004941681013349267,
|
|
"loss": 6.4478,
|
|
"mean_token_accuracy": 0.12467319518327713,
|
|
"num_tokens": 16708860.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.613043212890625,
|
|
"epoch": 0.8261544223875007,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004941594497141985,
|
|
"loss": 6.4475,
|
|
"mean_token_accuracy": 0.12525254786014556,
|
|
"num_tokens": 16719987.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.666272068023682,
|
|
"epoch": 0.8266894964952646,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004941507917652718,
|
|
"loss": 6.5514,
|
|
"mean_token_accuracy": 0.12144908234477043,
|
|
"num_tokens": 16730861.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.62738299369812,
|
|
"epoch": 0.8272245706030286,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004941421274883969,
|
|
"loss": 6.4127,
|
|
"mean_token_accuracy": 0.133733107149601,
|
|
"num_tokens": 16740968.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.641612339019775,
|
|
"epoch": 0.8277596447107924,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000494133456883824,
|
|
"loss": 6.503,
|
|
"mean_token_accuracy": 0.1232226848602295,
|
|
"num_tokens": 16750700.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.623130464553833,
|
|
"epoch": 0.8282947188185563,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004941247799518031,
|
|
"loss": 6.4921,
|
|
"mean_token_accuracy": 0.11922341287136078,
|
|
"num_tokens": 16760719.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.594596862792969,
|
|
"epoch": 0.8288297929263203,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004941160966925851,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.12437082976102828,
|
|
"num_tokens": 16771331.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.552067232131958,
|
|
"epoch": 0.8293648670340842,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004941074071064205,
|
|
"loss": 6.4636,
|
|
"mean_token_accuracy": 0.1285322904586792,
|
|
"num_tokens": 16781306.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.660621690750122,
|
|
"epoch": 0.8298999411418482,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004940987111935605,
|
|
"loss": 6.498,
|
|
"mean_token_accuracy": 0.12299665585160255,
|
|
"num_tokens": 16793013.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.6379204273223875,
|
|
"epoch": 0.830435015249612,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004940900089542558,
|
|
"loss": 6.4877,
|
|
"mean_token_accuracy": 0.1260430209338665,
|
|
"num_tokens": 16803987.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.598294115066528,
|
|
"epoch": 0.830970089357376,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000494081300388758,
|
|
"loss": 6.4931,
|
|
"mean_token_accuracy": 0.11670231968164443,
|
|
"num_tokens": 16815031.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.665700149536133,
|
|
"epoch": 0.8315051634651399,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004940725854973184,
|
|
"loss": 6.556,
|
|
"mean_token_accuracy": 0.12049141973257065,
|
|
"num_tokens": 16826313.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.712091159820557,
|
|
"epoch": 0.8320402375729038,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004940638642801886,
|
|
"loss": 6.5245,
|
|
"mean_token_accuracy": 0.12065903395414353,
|
|
"num_tokens": 16838470.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.629446649551392,
|
|
"epoch": 0.8325753116806678,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004940551367376205,
|
|
"loss": 6.4292,
|
|
"mean_token_accuracy": 0.12699209824204444,
|
|
"num_tokens": 16849266.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.622566843032837,
|
|
"epoch": 0.8331103857884317,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004940464028698662,
|
|
"loss": 6.5454,
|
|
"mean_token_accuracy": 0.12177014797925949,
|
|
"num_tokens": 16860720.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.6425587177276615,
|
|
"epoch": 0.8336454598961957,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004940376626771779,
|
|
"loss": 6.4998,
|
|
"mean_token_accuracy": 0.12133790627121925,
|
|
"num_tokens": 16872004.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.665201807022095,
|
|
"epoch": 0.8341805340039595,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004940289161598076,
|
|
"loss": 6.5488,
|
|
"mean_token_accuracy": 0.11539380699396133,
|
|
"num_tokens": 16882898.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.6538738250732425,
|
|
"epoch": 0.8347156081117235,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004940201633180084,
|
|
"loss": 6.464,
|
|
"mean_token_accuracy": 0.11394381150603294,
|
|
"num_tokens": 16894331.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.703577375411987,
|
|
"epoch": 0.8352506822194874,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004940114041520326,
|
|
"loss": 6.5504,
|
|
"mean_token_accuracy": 0.12355038300156593,
|
|
"num_tokens": 16903656.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.615875577926635,
|
|
"epoch": 0.8357857563272513,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004940026386621333,
|
|
"loss": 6.531,
|
|
"mean_token_accuracy": 0.12220551744103432,
|
|
"num_tokens": 16915878.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.686826181411743,
|
|
"epoch": 0.8363208304350153,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004939938668485636,
|
|
"loss": 6.5596,
|
|
"mean_token_accuracy": 0.12040482759475708,
|
|
"num_tokens": 16926577.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.588289070129394,
|
|
"epoch": 0.8368559045427791,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004939850887115768,
|
|
"loss": 6.4327,
|
|
"mean_token_accuracy": 0.13252562433481216,
|
|
"num_tokens": 16938012.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.627752494812012,
|
|
"epoch": 0.8373909786505431,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004939763042514263,
|
|
"loss": 6.4344,
|
|
"mean_token_accuracy": 0.11909441873431206,
|
|
"num_tokens": 16949007.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.517820024490357,
|
|
"epoch": 0.837926052758307,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004939675134683658,
|
|
"loss": 6.4005,
|
|
"mean_token_accuracy": 0.12949702590703965,
|
|
"num_tokens": 16959425.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.673564720153808,
|
|
"epoch": 0.838461126866071,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004939587163626491,
|
|
"loss": 6.5034,
|
|
"mean_token_accuracy": 0.12051056697964668,
|
|
"num_tokens": 16970002.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.663595056533813,
|
|
"epoch": 0.8389962009738349,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004939499129345302,
|
|
"loss": 6.5364,
|
|
"mean_token_accuracy": 0.1221657119691372,
|
|
"num_tokens": 16980739.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.65262770652771,
|
|
"epoch": 0.8395312750815987,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004939411031842633,
|
|
"loss": 6.4937,
|
|
"mean_token_accuracy": 0.1250368468463421,
|
|
"num_tokens": 16991643.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.563519716262817,
|
|
"epoch": 0.8400663491893627,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000493932287112103,
|
|
"loss": 6.3478,
|
|
"mean_token_accuracy": 0.14029302597045898,
|
|
"num_tokens": 17001975.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.65799355506897,
|
|
"epoch": 0.8406014232971266,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004939234647183035,
|
|
"loss": 6.4964,
|
|
"mean_token_accuracy": 0.12201631292700768,
|
|
"num_tokens": 17012658.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.662569141387939,
|
|
"epoch": 0.8411364974048906,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004939146360031197,
|
|
"loss": 6.5125,
|
|
"mean_token_accuracy": 0.11916863173246384,
|
|
"num_tokens": 17023196.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.6898315906524655,
|
|
"epoch": 0.8416715715126545,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004939058009668067,
|
|
"loss": 6.5473,
|
|
"mean_token_accuracy": 0.12000409588217735,
|
|
"num_tokens": 17034589.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.702956008911133,
|
|
"epoch": 0.8422066456204185,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004938969596096194,
|
|
"loss": 6.5027,
|
|
"mean_token_accuracy": 0.12456494793295861,
|
|
"num_tokens": 17046139.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.665690803527832,
|
|
"epoch": 0.8427417197281823,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000493888111931813,
|
|
"loss": 6.5067,
|
|
"mean_token_accuracy": 0.11791272163391113,
|
|
"num_tokens": 17056926.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.577418088912964,
|
|
"epoch": 0.8432767938359462,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004938792579336433,
|
|
"loss": 6.4672,
|
|
"mean_token_accuracy": 0.1280430294573307,
|
|
"num_tokens": 17067339.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.6744704246521,
|
|
"epoch": 0.8438118679437102,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004938703976153657,
|
|
"loss": 6.4797,
|
|
"mean_token_accuracy": 0.12503733932971955,
|
|
"num_tokens": 17078037.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.665802145004273,
|
|
"epoch": 0.8443469420514741,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004938615309772362,
|
|
"loss": 6.5011,
|
|
"mean_token_accuracy": 0.11592938974499703,
|
|
"num_tokens": 17089069.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.62218222618103,
|
|
"epoch": 0.8448820161592381,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004938526580195107,
|
|
"loss": 6.4874,
|
|
"mean_token_accuracy": 0.13059847727417945,
|
|
"num_tokens": 17100006.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.632329702377319,
|
|
"epoch": 0.845417090267002,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004938437787424454,
|
|
"loss": 6.5117,
|
|
"mean_token_accuracy": 0.12770421281456948,
|
|
"num_tokens": 17111896.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.644619989395141,
|
|
"epoch": 0.845952164374766,
|
|
"grad_norm": 5.78125,
|
|
"learning_rate": 0.0004938348931462969,
|
|
"loss": 6.5187,
|
|
"mean_token_accuracy": 0.12937232479453087,
|
|
"num_tokens": 17123202.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.616365671157837,
|
|
"epoch": 0.8464872384825298,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004938260012313215,
|
|
"loss": 6.4671,
|
|
"mean_token_accuracy": 0.1277104616165161,
|
|
"num_tokens": 17134013.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.549602222442627,
|
|
"epoch": 0.8470223125902937,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004938171029977761,
|
|
"loss": 6.4822,
|
|
"mean_token_accuracy": 0.12607489749789239,
|
|
"num_tokens": 17144041.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.620075321197509,
|
|
"epoch": 0.8475573866980577,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004938081984459176,
|
|
"loss": 6.4708,
|
|
"mean_token_accuracy": 0.1272951953113079,
|
|
"num_tokens": 17155334.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.642854404449463,
|
|
"epoch": 0.8480924608058216,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000493799287576003,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.12907181903719903,
|
|
"num_tokens": 17166243.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.596227931976318,
|
|
"epoch": 0.8486275349135856,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004937903703882898,
|
|
"loss": 6.4821,
|
|
"mean_token_accuracy": 0.12292805016040802,
|
|
"num_tokens": 17177709.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.596045446395874,
|
|
"epoch": 0.8491626090213494,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004937814468830353,
|
|
"loss": 6.4538,
|
|
"mean_token_accuracy": 0.12222009152173996,
|
|
"num_tokens": 17188275.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.661558198928833,
|
|
"epoch": 0.8496976831291134,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004937725170604975,
|
|
"loss": 6.5788,
|
|
"mean_token_accuracy": 0.11914105564355851,
|
|
"num_tokens": 17199527.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.702260112762451,
|
|
"epoch": 0.8502327572368773,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004937635809209339,
|
|
"loss": 6.4981,
|
|
"mean_token_accuracy": 0.12282656505703926,
|
|
"num_tokens": 17209500.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.626412963867187,
|
|
"epoch": 0.8507678313446412,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004937546384646027,
|
|
"loss": 6.4476,
|
|
"mean_token_accuracy": 0.1178506299853325,
|
|
"num_tokens": 17219589.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.650040340423584,
|
|
"epoch": 0.8513029054524052,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004937456896917619,
|
|
"loss": 6.4711,
|
|
"mean_token_accuracy": 0.126259146630764,
|
|
"num_tokens": 17230508.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.597875785827637,
|
|
"epoch": 0.851837979560169,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004937367346026702,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.12528541311621666,
|
|
"num_tokens": 17240886.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.58742389678955,
|
|
"epoch": 0.852373053667933,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004937277731975858,
|
|
"loss": 6.5213,
|
|
"mean_token_accuracy": 0.130964432656765,
|
|
"num_tokens": 17252247.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.625737190246582,
|
|
"epoch": 0.8529081277756969,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004937188054767679,
|
|
"loss": 6.4765,
|
|
"mean_token_accuracy": 0.12999607101082802,
|
|
"num_tokens": 17262845.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.665263938903808,
|
|
"epoch": 0.8534432018834609,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004937098314404751,
|
|
"loss": 6.4784,
|
|
"mean_token_accuracy": 0.126824226975441,
|
|
"num_tokens": 17274247.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.620522451400757,
|
|
"epoch": 0.8539782759912248,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004937008510889668,
|
|
"loss": 6.4982,
|
|
"mean_token_accuracy": 0.12837678343057632,
|
|
"num_tokens": 17285471.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.661442613601684,
|
|
"epoch": 0.8545133500989887,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004936918644225021,
|
|
"loss": 6.5465,
|
|
"mean_token_accuracy": 0.12399525567889214,
|
|
"num_tokens": 17296243.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.615818357467651,
|
|
"epoch": 0.8550484242067526,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004936828714413405,
|
|
"loss": 6.4741,
|
|
"mean_token_accuracy": 0.1283157154917717,
|
|
"num_tokens": 17307301.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.564626550674438,
|
|
"epoch": 0.8555834983145165,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004936738721457417,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.1331765443086624,
|
|
"num_tokens": 17318550.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.658585071563721,
|
|
"epoch": 0.8561185724222805,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004936648665359657,
|
|
"loss": 6.493,
|
|
"mean_token_accuracy": 0.12554465904831885,
|
|
"num_tokens": 17328577.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.699020481109619,
|
|
"epoch": 0.8566536465300444,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004936558546122723,
|
|
"loss": 6.543,
|
|
"mean_token_accuracy": 0.11733669638633729,
|
|
"num_tokens": 17341013.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.612721157073975,
|
|
"epoch": 0.8571887206378084,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004936468363749217,
|
|
"loss": 6.4956,
|
|
"mean_token_accuracy": 0.12534042000770568,
|
|
"num_tokens": 17351956.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.6302636623382565,
|
|
"epoch": 0.8577237947455723,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004936378118241746,
|
|
"loss": 6.4735,
|
|
"mean_token_accuracy": 0.1189095988869667,
|
|
"num_tokens": 17363465.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.625843572616577,
|
|
"epoch": 0.8582588688533361,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004936287809602913,
|
|
"loss": 6.5242,
|
|
"mean_token_accuracy": 0.12394155710935592,
|
|
"num_tokens": 17374458.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.647753000259399,
|
|
"epoch": 0.8587939429611001,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004936197437835329,
|
|
"loss": 6.5497,
|
|
"mean_token_accuracy": 0.12012193650007248,
|
|
"num_tokens": 17385492.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.703285789489746,
|
|
"epoch": 0.859329017068864,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004936107002941599,
|
|
"loss": 6.4724,
|
|
"mean_token_accuracy": 0.12847412005066872,
|
|
"num_tokens": 17395640.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.632746648788452,
|
|
"epoch": 0.859864091176628,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004936016504924337,
|
|
"loss": 6.4898,
|
|
"mean_token_accuracy": 0.12599302977323532,
|
|
"num_tokens": 17405211.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.611907625198365,
|
|
"epoch": 0.8603991652843919,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004935925943786155,
|
|
"loss": 6.4448,
|
|
"mean_token_accuracy": 0.12549460530281067,
|
|
"num_tokens": 17415421.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.633581686019897,
|
|
"epoch": 0.8609342393921559,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004935835319529669,
|
|
"loss": 6.5036,
|
|
"mean_token_accuracy": 0.12547684609889984,
|
|
"num_tokens": 17426040.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.594140100479126,
|
|
"epoch": 0.8614693134999197,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004935744632157496,
|
|
"loss": 6.5022,
|
|
"mean_token_accuracy": 0.12294603735208512,
|
|
"num_tokens": 17436305.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.617403411865235,
|
|
"epoch": 0.8620043876076836,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004935653881672253,
|
|
"loss": 6.5452,
|
|
"mean_token_accuracy": 0.1258605569601059,
|
|
"num_tokens": 17446786.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.648105812072754,
|
|
"epoch": 0.8625394617154476,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004935563068076561,
|
|
"loss": 6.4425,
|
|
"mean_token_accuracy": 0.13229886442422867,
|
|
"num_tokens": 17456613.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.568179798126221,
|
|
"epoch": 0.8630745358232115,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004935472191373044,
|
|
"loss": 6.3936,
|
|
"mean_token_accuracy": 0.12649988755583763,
|
|
"num_tokens": 17467281.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.618695306777954,
|
|
"epoch": 0.8636096099309755,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004935381251564324,
|
|
"loss": 6.5017,
|
|
"mean_token_accuracy": 0.12402761876583099,
|
|
"num_tokens": 17478271.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.631219005584716,
|
|
"epoch": 0.8641446840387393,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004935290248653027,
|
|
"loss": 6.4877,
|
|
"mean_token_accuracy": 0.12144652754068375,
|
|
"num_tokens": 17489519.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.65806016921997,
|
|
"epoch": 0.8646797581465033,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004935199182641781,
|
|
"loss": 6.4594,
|
|
"mean_token_accuracy": 0.12436033189296722,
|
|
"num_tokens": 17500076.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.681798982620239,
|
|
"epoch": 0.8652148322542672,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004935108053533216,
|
|
"loss": 6.4763,
|
|
"mean_token_accuracy": 0.11783101856708526,
|
|
"num_tokens": 17509898.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.596463298797607,
|
|
"epoch": 0.8657499063620312,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004935016861329964,
|
|
"loss": 6.4346,
|
|
"mean_token_accuracy": 0.12589452266693116,
|
|
"num_tokens": 17519890.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.578653573989868,
|
|
"epoch": 0.8662849804697951,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004934925606034656,
|
|
"loss": 6.4662,
|
|
"mean_token_accuracy": 0.1222758173942566,
|
|
"num_tokens": 17530927.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.684061336517334,
|
|
"epoch": 0.866820054577559,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004934834287649928,
|
|
"loss": 6.524,
|
|
"mean_token_accuracy": 0.12150460779666901,
|
|
"num_tokens": 17541174.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.681601905822754,
|
|
"epoch": 0.8673551286853229,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004934742906178417,
|
|
"loss": 6.4993,
|
|
"mean_token_accuracy": 0.12261729910969735,
|
|
"num_tokens": 17552460.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.7008894920349125,
|
|
"epoch": 0.8678902027930868,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004934651461622762,
|
|
"loss": 6.5192,
|
|
"mean_token_accuracy": 0.1258750893175602,
|
|
"num_tokens": 17563908.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.6201441287994385,
|
|
"epoch": 0.8684252769008508,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004934559953985603,
|
|
"loss": 6.5295,
|
|
"mean_token_accuracy": 0.12694232389330865,
|
|
"num_tokens": 17574314.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.6670092105865475,
|
|
"epoch": 0.8689603510086147,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004934468383269582,
|
|
"loss": 6.4756,
|
|
"mean_token_accuracy": 0.12882627919316292,
|
|
"num_tokens": 17583719.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.592183303833008,
|
|
"epoch": 0.8694954251163787,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004934376749477344,
|
|
"loss": 6.4571,
|
|
"mean_token_accuracy": 0.12707244530320166,
|
|
"num_tokens": 17594522.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.548756551742554,
|
|
"epoch": 0.8700304992241426,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004934285052611533,
|
|
"loss": 6.3933,
|
|
"mean_token_accuracy": 0.12934113889932633,
|
|
"num_tokens": 17604632.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.686312484741211,
|
|
"epoch": 0.8705655733319064,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00049341932926748,
|
|
"loss": 6.555,
|
|
"mean_token_accuracy": 0.12154021933674812,
|
|
"num_tokens": 17615459.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.6940545558929445,
|
|
"epoch": 0.8711006474396704,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004934101469669791,
|
|
"loss": 6.4971,
|
|
"mean_token_accuracy": 0.12597646862268447,
|
|
"num_tokens": 17625800.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.552589750289917,
|
|
"epoch": 0.8716357215474343,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004934009583599159,
|
|
"loss": 6.3218,
|
|
"mean_token_accuracy": 0.13671309277415275,
|
|
"num_tokens": 17637264.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.550005102157593,
|
|
"epoch": 0.8721707956551983,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004933917634465558,
|
|
"loss": 6.3701,
|
|
"mean_token_accuracy": 0.126920372992754,
|
|
"num_tokens": 17648256.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.555936527252197,
|
|
"epoch": 0.8727058697629622,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004933825622271642,
|
|
"loss": 6.5062,
|
|
"mean_token_accuracy": 0.12245367467403412,
|
|
"num_tokens": 17659096.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.6688987731933596,
|
|
"epoch": 0.8732409438707261,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004933733547020069,
|
|
"loss": 6.4959,
|
|
"mean_token_accuracy": 0.1260982222855091,
|
|
"num_tokens": 17669808.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.655553722381592,
|
|
"epoch": 0.87377601797849,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004933641408713495,
|
|
"loss": 6.4318,
|
|
"mean_token_accuracy": 0.12736403942108154,
|
|
"num_tokens": 17680375.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.562960958480835,
|
|
"epoch": 0.8743110920862539,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004933549207354582,
|
|
"loss": 6.3878,
|
|
"mean_token_accuracy": 0.1282447598874569,
|
|
"num_tokens": 17690780.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.646951627731323,
|
|
"epoch": 0.8748461661940179,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004933456942945994,
|
|
"loss": 6.5094,
|
|
"mean_token_accuracy": 0.12706121876835824,
|
|
"num_tokens": 17702170.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.6072039127349855,
|
|
"epoch": 0.8753812403017818,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004933364615490393,
|
|
"loss": 6.4566,
|
|
"mean_token_accuracy": 0.12158106192946434,
|
|
"num_tokens": 17712631.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.642406034469604,
|
|
"epoch": 0.8759163144095458,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004933272224990445,
|
|
"loss": 6.5373,
|
|
"mean_token_accuracy": 0.12108419612050056,
|
|
"num_tokens": 17723692.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.6679596424102785,
|
|
"epoch": 0.8764513885173096,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004933179771448819,
|
|
"loss": 6.4232,
|
|
"mean_token_accuracy": 0.13583495393395423,
|
|
"num_tokens": 17735264.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.5829291343688965,
|
|
"epoch": 0.8769864626250736,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004933087254868183,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.134719929844141,
|
|
"num_tokens": 17747060.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.533154249191284,
|
|
"epoch": 0.8775215367328375,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000493299467525121,
|
|
"loss": 6.4656,
|
|
"mean_token_accuracy": 0.1196682870388031,
|
|
"num_tokens": 17758159.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.638121843338013,
|
|
"epoch": 0.8780566108406014,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004932902032600573,
|
|
"loss": 6.4927,
|
|
"mean_token_accuracy": 0.12600281164050103,
|
|
"num_tokens": 17768444.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.666748094558716,
|
|
"epoch": 0.8785916849483654,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004932809326918945,
|
|
"loss": 6.3887,
|
|
"mean_token_accuracy": 0.13347016647458076,
|
|
"num_tokens": 17779303.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.593316507339478,
|
|
"epoch": 0.8791267590561292,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004932716558209005,
|
|
"loss": 6.5541,
|
|
"mean_token_accuracy": 0.1168032519519329,
|
|
"num_tokens": 17789853.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.684701633453369,
|
|
"epoch": 0.8796618331638932,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004932623726473432,
|
|
"loss": 6.425,
|
|
"mean_token_accuracy": 0.1359473004937172,
|
|
"num_tokens": 17799232.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.5917634010314945,
|
|
"epoch": 0.8801969072716571,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004932530831714904,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.12891010716557502,
|
|
"num_tokens": 17808870.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.576681613922119,
|
|
"epoch": 0.8807319813794211,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004932437873936107,
|
|
"loss": 6.5013,
|
|
"mean_token_accuracy": 0.11911470666527749,
|
|
"num_tokens": 17819394.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.6881123065948485,
|
|
"epoch": 0.881267055487185,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004932344853139721,
|
|
"loss": 6.4898,
|
|
"mean_token_accuracy": 0.12179769352078437,
|
|
"num_tokens": 17830220.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.614411115646362,
|
|
"epoch": 0.8818021295949489,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004932251769328436,
|
|
"loss": 6.4247,
|
|
"mean_token_accuracy": 0.12219362333416939,
|
|
"num_tokens": 17841971.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.620457124710083,
|
|
"epoch": 0.8823372037027128,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004932158622504937,
|
|
"loss": 6.437,
|
|
"mean_token_accuracy": 0.12712137401103973,
|
|
"num_tokens": 17851890.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.551126480102539,
|
|
"epoch": 0.8828722778104767,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004932065412671915,
|
|
"loss": 6.4494,
|
|
"mean_token_accuracy": 0.12583379372954367,
|
|
"num_tokens": 17862855.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.662340211868286,
|
|
"epoch": 0.8834073519182407,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004931972139832058,
|
|
"loss": 6.446,
|
|
"mean_token_accuracy": 0.12148565500974655,
|
|
"num_tokens": 17873550.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.645479822158814,
|
|
"epoch": 0.8839424260260046,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004931878803988066,
|
|
"loss": 6.4649,
|
|
"mean_token_accuracy": 0.12512604743242264,
|
|
"num_tokens": 17884067.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.621095943450928,
|
|
"epoch": 0.8844775001337686,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004931785405142627,
|
|
"loss": 6.484,
|
|
"mean_token_accuracy": 0.1258624605834484,
|
|
"num_tokens": 17894587.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.610942411422729,
|
|
"epoch": 0.8850125742415325,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004931691943298443,
|
|
"loss": 6.4838,
|
|
"mean_token_accuracy": 0.12366678640246391,
|
|
"num_tokens": 17905297.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.536123418807984,
|
|
"epoch": 0.8855476483492963,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000493159841845821,
|
|
"loss": 6.3926,
|
|
"mean_token_accuracy": 0.12698206976056098,
|
|
"num_tokens": 17916225.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.648953104019165,
|
|
"epoch": 0.8860827224570603,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004931504830624629,
|
|
"loss": 6.4311,
|
|
"mean_token_accuracy": 0.12626414149999618,
|
|
"num_tokens": 17925795.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.609307432174683,
|
|
"epoch": 0.8866177965648242,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004931411179800403,
|
|
"loss": 6.4584,
|
|
"mean_token_accuracy": 0.12168131545186042,
|
|
"num_tokens": 17936134.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.642501020431519,
|
|
"epoch": 0.8871528706725882,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004931317465988235,
|
|
"loss": 6.5107,
|
|
"mean_token_accuracy": 0.12415769174695016,
|
|
"num_tokens": 17946393.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.64236798286438,
|
|
"epoch": 0.8876879447803521,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004931223689190832,
|
|
"loss": 6.5182,
|
|
"mean_token_accuracy": 0.12109429538249969,
|
|
"num_tokens": 17957527.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.6200567245483395,
|
|
"epoch": 0.8882230188881161,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004931129849410903,
|
|
"loss": 6.5225,
|
|
"mean_token_accuracy": 0.12380363419651985,
|
|
"num_tokens": 17968390.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.6714503288269045,
|
|
"epoch": 0.8887580929958799,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004931035946651154,
|
|
"loss": 6.4363,
|
|
"mean_token_accuracy": 0.13457045406103135,
|
|
"num_tokens": 17978667.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.703409671783447,
|
|
"epoch": 0.8892931671036438,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004930941980914299,
|
|
"loss": 6.5145,
|
|
"mean_token_accuracy": 0.11639609187841415,
|
|
"num_tokens": 17989008.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.621966743469239,
|
|
"epoch": 0.8898282412114078,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004930847952203052,
|
|
"loss": 6.4428,
|
|
"mean_token_accuracy": 0.11936006546020508,
|
|
"num_tokens": 18000199.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.6108996868133545,
|
|
"epoch": 0.8903633153191717,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004930753860520126,
|
|
"loss": 6.3981,
|
|
"mean_token_accuracy": 0.12310235351324081,
|
|
"num_tokens": 18010941.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.664381504058838,
|
|
"epoch": 0.8908983894269357,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004930659705868237,
|
|
"loss": 6.5245,
|
|
"mean_token_accuracy": 0.12172655537724494,
|
|
"num_tokens": 18021519.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.643858480453491,
|
|
"epoch": 0.8914334635346995,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004930565488250108,
|
|
"loss": 6.4663,
|
|
"mean_token_accuracy": 0.11948546692728997,
|
|
"num_tokens": 18032773.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.5537638664245605,
|
|
"epoch": 0.8919685376424635,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004930471207668456,
|
|
"loss": 6.4138,
|
|
"mean_token_accuracy": 0.13167215883731842,
|
|
"num_tokens": 18043250.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.559721279144287,
|
|
"epoch": 0.8925036117502274,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004930376864126005,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.13107730820775032,
|
|
"num_tokens": 18055165.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.563991737365723,
|
|
"epoch": 0.8930386858579913,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004930282457625476,
|
|
"loss": 6.3912,
|
|
"mean_token_accuracy": 0.1331387609243393,
|
|
"num_tokens": 18065296.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.570724058151245,
|
|
"epoch": 0.8935737599657553,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00049301879881696,
|
|
"loss": 6.4031,
|
|
"mean_token_accuracy": 0.1266719304025173,
|
|
"num_tokens": 18075536.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.647785091400147,
|
|
"epoch": 0.8941088340735192,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004930093455761101,
|
|
"loss": 6.5153,
|
|
"mean_token_accuracy": 0.1265658438205719,
|
|
"num_tokens": 18086253.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.68550443649292,
|
|
"epoch": 0.8946439081812831,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000492999886040271,
|
|
"loss": 6.4925,
|
|
"mean_token_accuracy": 0.1257350318133831,
|
|
"num_tokens": 18097335.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.651350259780884,
|
|
"epoch": 0.895178982289047,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004929904202097159,
|
|
"loss": 6.45,
|
|
"mean_token_accuracy": 0.12403530329465866,
|
|
"num_tokens": 18107293.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.5929731845855715,
|
|
"epoch": 0.895714056396811,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004929809480847179,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.11672141477465629,
|
|
"num_tokens": 18117705.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.695660638809204,
|
|
"epoch": 0.8962491305045749,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004929714696655507,
|
|
"loss": 6.4613,
|
|
"mean_token_accuracy": 0.12161885723471641,
|
|
"num_tokens": 18129003.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.629467248916626,
|
|
"epoch": 0.8967842046123388,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000492961984952488,
|
|
"loss": 6.4143,
|
|
"mean_token_accuracy": 0.1348094515502453,
|
|
"num_tokens": 18140843.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.583462858200074,
|
|
"epoch": 0.8973192787201028,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004929524939458037,
|
|
"loss": 6.5083,
|
|
"mean_token_accuracy": 0.12148434221744538,
|
|
"num_tokens": 18151476.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.626362323760986,
|
|
"epoch": 0.8978543528278666,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004929429966457716,
|
|
"loss": 6.5163,
|
|
"mean_token_accuracy": 0.11925900503993034,
|
|
"num_tokens": 18161304.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.669924974441528,
|
|
"epoch": 0.8983894269356306,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004929334930526662,
|
|
"loss": 6.4523,
|
|
"mean_token_accuracy": 0.1279652498662472,
|
|
"num_tokens": 18173696.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.663748550415039,
|
|
"epoch": 0.8989245010433945,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004929239831667617,
|
|
"loss": 6.4716,
|
|
"mean_token_accuracy": 0.11967618018388748,
|
|
"num_tokens": 18186024.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.637021827697754,
|
|
"epoch": 0.8994595751511585,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004929144669883329,
|
|
"loss": 6.4925,
|
|
"mean_token_accuracy": 0.1306003175675869,
|
|
"num_tokens": 18196976.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.586773490905761,
|
|
"epoch": 0.8999946492589224,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004929049445176545,
|
|
"loss": 6.4845,
|
|
"mean_token_accuracy": 0.1220610924065113,
|
|
"num_tokens": 18208086.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.595044565200806,
|
|
"epoch": 0.9005297233666862,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004928954157550013,
|
|
"loss": 6.4347,
|
|
"mean_token_accuracy": 0.1335590250790119,
|
|
"num_tokens": 18218468.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.671721506118774,
|
|
"epoch": 0.9010647974744502,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004928858807006488,
|
|
"loss": 6.5494,
|
|
"mean_token_accuracy": 0.12909165546298026,
|
|
"num_tokens": 18230489.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.631244897842407,
|
|
"epoch": 0.9015998715822141,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004928763393548721,
|
|
"loss": 6.47,
|
|
"mean_token_accuracy": 0.12585487216711044,
|
|
"num_tokens": 18239968.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.604466485977173,
|
|
"epoch": 0.9021349456899781,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004928667917179465,
|
|
"loss": 6.5196,
|
|
"mean_token_accuracy": 0.12099517658352851,
|
|
"num_tokens": 18250902.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.713874816894531,
|
|
"epoch": 0.902670019797742,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004928572377901481,
|
|
"loss": 6.4961,
|
|
"mean_token_accuracy": 0.12910594344139098,
|
|
"num_tokens": 18262094.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.62224702835083,
|
|
"epoch": 0.903205093905506,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004928476775717524,
|
|
"loss": 6.4901,
|
|
"mean_token_accuracy": 0.11994085684418679,
|
|
"num_tokens": 18272765.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.59943642616272,
|
|
"epoch": 0.9037401680132698,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004928381110630358,
|
|
"loss": 6.3968,
|
|
"mean_token_accuracy": 0.13411153852939606,
|
|
"num_tokens": 18284570.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.760131788253784,
|
|
"epoch": 0.9042752421210337,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004928285382642742,
|
|
"loss": 6.5098,
|
|
"mean_token_accuracy": 0.11762636825442314,
|
|
"num_tokens": 18295170.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.663050270080566,
|
|
"epoch": 0.9048103162287977,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004928189591757443,
|
|
"loss": 6.4465,
|
|
"mean_token_accuracy": 0.12105149701237679,
|
|
"num_tokens": 18306388.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.642880535125732,
|
|
"epoch": 0.9053453903365616,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004928093737977225,
|
|
"loss": 6.4579,
|
|
"mean_token_accuracy": 0.12769906893372535,
|
|
"num_tokens": 18316363.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.513784170150757,
|
|
"epoch": 0.9058804644443256,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004927997821304856,
|
|
"loss": 6.4082,
|
|
"mean_token_accuracy": 0.13132378607988357,
|
|
"num_tokens": 18327397.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.6212035655975345,
|
|
"epoch": 0.9064155385520895,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004927901841743107,
|
|
"loss": 6.5211,
|
|
"mean_token_accuracy": 0.12287846431136132,
|
|
"num_tokens": 18338909.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.658081579208374,
|
|
"epoch": 0.9069506126598534,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004927805799294747,
|
|
"loss": 6.4979,
|
|
"mean_token_accuracy": 0.12273556888103485,
|
|
"num_tokens": 18350110.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.730619144439697,
|
|
"epoch": 0.9074856867676173,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004927709693962551,
|
|
"loss": 6.5432,
|
|
"mean_token_accuracy": 0.11587911248207092,
|
|
"num_tokens": 18361590.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.6245725631713865,
|
|
"epoch": 0.9080207608753812,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004927613525749295,
|
|
"loss": 6.4828,
|
|
"mean_token_accuracy": 0.11964484229683876,
|
|
"num_tokens": 18372602.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.612303972244263,
|
|
"epoch": 0.9085558349831452,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004927517294657753,
|
|
"loss": 6.542,
|
|
"mean_token_accuracy": 0.12091094478964806,
|
|
"num_tokens": 18384653.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.7338470935821535,
|
|
"epoch": 0.9090909090909091,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004927421000690705,
|
|
"loss": 6.4969,
|
|
"mean_token_accuracy": 0.11975472643971444,
|
|
"num_tokens": 18395379.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.696132564544678,
|
|
"epoch": 0.909625983198673,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004927324643850933,
|
|
"loss": 6.4631,
|
|
"mean_token_accuracy": 0.12538763508200645,
|
|
"num_tokens": 18405915.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.558605766296386,
|
|
"epoch": 0.9101610573064369,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004927228224141217,
|
|
"loss": 6.3757,
|
|
"mean_token_accuracy": 0.1420656271278858,
|
|
"num_tokens": 18416656.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.598984003067017,
|
|
"epoch": 0.9106961314142009,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004927131741564342,
|
|
"loss": 6.4803,
|
|
"mean_token_accuracy": 0.11981485709547997,
|
|
"num_tokens": 18427141.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.6146650314331055,
|
|
"epoch": 0.9112312055219648,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004927035196123094,
|
|
"loss": 6.5231,
|
|
"mean_token_accuracy": 0.1287735067307949,
|
|
"num_tokens": 18437135.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.716233634948731,
|
|
"epoch": 0.9117662796297287,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000492693858782026,
|
|
"loss": 6.5865,
|
|
"mean_token_accuracy": 0.11605971083045005,
|
|
"num_tokens": 18448567.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.772599935531616,
|
|
"epoch": 0.9123013537374927,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000492684191665863,
|
|
"loss": 6.5364,
|
|
"mean_token_accuracy": 0.1172192133963108,
|
|
"num_tokens": 18459385.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.649914979934692,
|
|
"epoch": 0.9128364278452565,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004926745182640996,
|
|
"loss": 6.5112,
|
|
"mean_token_accuracy": 0.12677259296178817,
|
|
"num_tokens": 18471376.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.638808155059815,
|
|
"epoch": 0.9133715019530205,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004926648385770152,
|
|
"loss": 6.5705,
|
|
"mean_token_accuracy": 0.11410852298140525,
|
|
"num_tokens": 18481950.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.685179424285889,
|
|
"epoch": 0.9139065760607844,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004926551526048891,
|
|
"loss": 6.4803,
|
|
"mean_token_accuracy": 0.12756372913718222,
|
|
"num_tokens": 18492436.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.627972507476807,
|
|
"epoch": 0.9144416501685484,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004926454603480009,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.128764096647501,
|
|
"num_tokens": 18504279.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.650672483444214,
|
|
"epoch": 0.9149767242763123,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004926357618066307,
|
|
"loss": 6.4708,
|
|
"mean_token_accuracy": 0.12192556336522102,
|
|
"num_tokens": 18515262.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.642165899276733,
|
|
"epoch": 0.9155117983840761,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004926260569810586,
|
|
"loss": 6.5307,
|
|
"mean_token_accuracy": 0.12208939194679261,
|
|
"num_tokens": 18525176.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.618933486938476,
|
|
"epoch": 0.9160468724918401,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004926163458715645,
|
|
"loss": 6.4942,
|
|
"mean_token_accuracy": 0.1219611756503582,
|
|
"num_tokens": 18536674.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.673080205917358,
|
|
"epoch": 0.916581946599604,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004926066284784292,
|
|
"loss": 6.4726,
|
|
"mean_token_accuracy": 0.12291558682918549,
|
|
"num_tokens": 18547398.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.624698495864868,
|
|
"epoch": 0.917117020707368,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004925969048019329,
|
|
"loss": 6.5103,
|
|
"mean_token_accuracy": 0.1284634552896023,
|
|
"num_tokens": 18558838.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.611716318130493,
|
|
"epoch": 0.9176520948151319,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004925871748423566,
|
|
"loss": 6.4551,
|
|
"mean_token_accuracy": 0.12822888791561127,
|
|
"num_tokens": 18569881.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.621056079864502,
|
|
"epoch": 0.9181871689228959,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004925774385999812,
|
|
"loss": 6.3686,
|
|
"mean_token_accuracy": 0.13034757301211358,
|
|
"num_tokens": 18579556.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.511433839797974,
|
|
"epoch": 0.9187222430306597,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004925676960750878,
|
|
"loss": 6.3729,
|
|
"mean_token_accuracy": 0.1375325158238411,
|
|
"num_tokens": 18590580.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.69870433807373,
|
|
"epoch": 0.9192573171384236,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004925579472679578,
|
|
"loss": 6.4974,
|
|
"mean_token_accuracy": 0.12330010756850243,
|
|
"num_tokens": 18600813.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.661010980606079,
|
|
"epoch": 0.9197923912461876,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004925481921788726,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.13030895143747329,
|
|
"num_tokens": 18610807.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.565768432617188,
|
|
"epoch": 0.9203274653539515,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000492538430808114,
|
|
"loss": 6.3881,
|
|
"mean_token_accuracy": 0.12881432548165322,
|
|
"num_tokens": 18622108.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.5940775871276855,
|
|
"epoch": 0.9208625394617155,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004925286631559636,
|
|
"loss": 6.5538,
|
|
"mean_token_accuracy": 0.1236357107758522,
|
|
"num_tokens": 18633098.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.662554740905762,
|
|
"epoch": 0.9213976135694794,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004925188892227038,
|
|
"loss": 6.4536,
|
|
"mean_token_accuracy": 0.12755847722291946,
|
|
"num_tokens": 18643603.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.676049280166626,
|
|
"epoch": 0.9219326876772433,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004925091090086166,
|
|
"loss": 6.48,
|
|
"mean_token_accuracy": 0.12892110347747804,
|
|
"num_tokens": 18654354.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.656309413909912,
|
|
"epoch": 0.9224677617850072,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004924993225139845,
|
|
"loss": 6.5401,
|
|
"mean_token_accuracy": 0.1253078192472458,
|
|
"num_tokens": 18665349.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.67702202796936,
|
|
"epoch": 0.9230028358927711,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004924895297390899,
|
|
"loss": 6.4902,
|
|
"mean_token_accuracy": 0.12262158021330834,
|
|
"num_tokens": 18676575.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.678769063949585,
|
|
"epoch": 0.9235379100005351,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004924797306842157,
|
|
"loss": 6.4436,
|
|
"mean_token_accuracy": 0.12487710490822793,
|
|
"num_tokens": 18686501.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.6677357196807865,
|
|
"epoch": 0.924072984108299,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004924699253496449,
|
|
"loss": 6.5018,
|
|
"mean_token_accuracy": 0.12649423480033875,
|
|
"num_tokens": 18697246.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.570757007598877,
|
|
"epoch": 0.924608058216063,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004924601137356605,
|
|
"loss": 6.4187,
|
|
"mean_token_accuracy": 0.13186311200261117,
|
|
"num_tokens": 18708177.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.675057649612427,
|
|
"epoch": 0.9251431323238268,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000492450295842546,
|
|
"loss": 6.4828,
|
|
"mean_token_accuracy": 0.12886969447135926,
|
|
"num_tokens": 18719334.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.669967079162598,
|
|
"epoch": 0.9256782064315908,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004924404716705847,
|
|
"loss": 6.4423,
|
|
"mean_token_accuracy": 0.1317922964692116,
|
|
"num_tokens": 18729174.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.579828310012817,
|
|
"epoch": 0.9262132805393547,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004924306412200603,
|
|
"loss": 6.5413,
|
|
"mean_token_accuracy": 0.12375770136713982,
|
|
"num_tokens": 18740277.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.686962556838989,
|
|
"epoch": 0.9267483546471186,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004924208044912567,
|
|
"loss": 6.5035,
|
|
"mean_token_accuracy": 0.12598727270960808,
|
|
"num_tokens": 18751864.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.634845733642578,
|
|
"epoch": 0.9272834287548826,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004924109614844579,
|
|
"loss": 6.4078,
|
|
"mean_token_accuracy": 0.1320377692580223,
|
|
"num_tokens": 18762786.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.565891075134277,
|
|
"epoch": 0.9278185028626464,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004924011121999482,
|
|
"loss": 6.4737,
|
|
"mean_token_accuracy": 0.1281440421938896,
|
|
"num_tokens": 18772913.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.588847541809082,
|
|
"epoch": 0.9283535769704104,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004923912566380118,
|
|
"loss": 6.4483,
|
|
"mean_token_accuracy": 0.12933889403939247,
|
|
"num_tokens": 18784204.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.567999982833863,
|
|
"epoch": 0.9288886510781743,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004923813947989336,
|
|
"loss": 6.5071,
|
|
"mean_token_accuracy": 0.12231356203556061,
|
|
"num_tokens": 18795425.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.698699951171875,
|
|
"epoch": 0.9294237251859383,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004923715266829981,
|
|
"loss": 6.4653,
|
|
"mean_token_accuracy": 0.12079897969961166,
|
|
"num_tokens": 18806850.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.64630126953125,
|
|
"epoch": 0.9299587992937022,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004923616522904903,
|
|
"loss": 6.4073,
|
|
"mean_token_accuracy": 0.13334384709596633,
|
|
"num_tokens": 18817272.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.604785394668579,
|
|
"epoch": 0.930493873401466,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004923517716216953,
|
|
"loss": 6.5333,
|
|
"mean_token_accuracy": 0.12438125461339951,
|
|
"num_tokens": 18827075.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.66113395690918,
|
|
"epoch": 0.93102894750923,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004923418846768985,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.12244063764810562,
|
|
"num_tokens": 18837635.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.653626823425293,
|
|
"epoch": 0.9315640216169939,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004923319914563852,
|
|
"loss": 6.4707,
|
|
"mean_token_accuracy": 0.13115439414978028,
|
|
"num_tokens": 18848559.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 6.710020685195923,
|
|
"epoch": 0.9320990957247579,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004923220919604413,
|
|
"loss": 6.5055,
|
|
"mean_token_accuracy": 0.11973880454897881,
|
|
"num_tokens": 18859327.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.624680995941162,
|
|
"epoch": 0.9326341698325218,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004923121861893525,
|
|
"loss": 6.4436,
|
|
"mean_token_accuracy": 0.12301542088389397,
|
|
"num_tokens": 18869403.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.6516646385192875,
|
|
"epoch": 0.9331692439402858,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004923022741434049,
|
|
"loss": 6.4679,
|
|
"mean_token_accuracy": 0.12050192058086395,
|
|
"num_tokens": 18879890.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.64061918258667,
|
|
"epoch": 0.9337043180480497,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004922923558228846,
|
|
"loss": 6.4889,
|
|
"mean_token_accuracy": 0.12326004803180694,
|
|
"num_tokens": 18890361.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.569211196899414,
|
|
"epoch": 0.9342393921558135,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004922824312280781,
|
|
"loss": 6.4057,
|
|
"mean_token_accuracy": 0.12972430661320686,
|
|
"num_tokens": 18902344.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.570722436904907,
|
|
"epoch": 0.9347744662635775,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000492272500359272,
|
|
"loss": 6.4062,
|
|
"mean_token_accuracy": 0.13201600834727287,
|
|
"num_tokens": 18911364.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.632805490493775,
|
|
"epoch": 0.9353095403713414,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004922625632167529,
|
|
"loss": 6.5036,
|
|
"mean_token_accuracy": 0.11896138563752175,
|
|
"num_tokens": 18922254.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.709387683868409,
|
|
"epoch": 0.9358446144791054,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004922526198008078,
|
|
"loss": 6.4647,
|
|
"mean_token_accuracy": 0.12372331023216247,
|
|
"num_tokens": 18932943.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.6208329677581785,
|
|
"epoch": 0.9363796885868693,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004922426701117239,
|
|
"loss": 6.5455,
|
|
"mean_token_accuracy": 0.12257308885455132,
|
|
"num_tokens": 18943523.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.6487444877624515,
|
|
"epoch": 0.9369147626946333,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004922327141497884,
|
|
"loss": 6.5204,
|
|
"mean_token_accuracy": 0.11690002381801605,
|
|
"num_tokens": 18955220.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.7481544494628904,
|
|
"epoch": 0.9374498368023971,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004922227519152888,
|
|
"loss": 6.5516,
|
|
"mean_token_accuracy": 0.12228794246912003,
|
|
"num_tokens": 18966714.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.587043571472168,
|
|
"epoch": 0.937984910910161,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004922127834085128,
|
|
"loss": 6.4039,
|
|
"mean_token_accuracy": 0.13071783185005187,
|
|
"num_tokens": 18977998.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.6106531620025635,
|
|
"epoch": 0.938519985017925,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004922028086297481,
|
|
"loss": 6.3983,
|
|
"mean_token_accuracy": 0.12865159437060356,
|
|
"num_tokens": 18990210.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.7083227157592775,
|
|
"epoch": 0.9390550591256889,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004921928275792828,
|
|
"loss": 6.5058,
|
|
"mean_token_accuracy": 0.12819522097706795,
|
|
"num_tokens": 19000529.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.611662530899048,
|
|
"epoch": 0.9395901332334529,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004921828402574052,
|
|
"loss": 6.4284,
|
|
"mean_token_accuracy": 0.1316968895494938,
|
|
"num_tokens": 19011386.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.5732118606567385,
|
|
"epoch": 0.9401252073412167,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.0004921728466644037,
|
|
"loss": 6.4279,
|
|
"mean_token_accuracy": 0.12721818760037423,
|
|
"num_tokens": 19022196.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.560956764221191,
|
|
"epoch": 0.9406602814489807,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004921628468005666,
|
|
"loss": 6.458,
|
|
"mean_token_accuracy": 0.12778538540005685,
|
|
"num_tokens": 19033221.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.616184377670288,
|
|
"epoch": 0.9411953555567446,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000492152840666183,
|
|
"loss": 6.5202,
|
|
"mean_token_accuracy": 0.11902409568428993,
|
|
"num_tokens": 19044953.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.698403549194336,
|
|
"epoch": 0.9417304296645085,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004921428282615415,
|
|
"loss": 6.5341,
|
|
"mean_token_accuracy": 0.11961584985256195,
|
|
"num_tokens": 19055512.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.707877111434937,
|
|
"epoch": 0.9422655037722725,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004921328095869313,
|
|
"loss": 6.5424,
|
|
"mean_token_accuracy": 0.1170853316783905,
|
|
"num_tokens": 19065659.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.682837629318238,
|
|
"epoch": 0.9428005778800364,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004921227846426418,
|
|
"loss": 6.4479,
|
|
"mean_token_accuracy": 0.13554048240184785,
|
|
"num_tokens": 19076955.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.630908536911011,
|
|
"epoch": 0.9433356519878003,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004921127534289624,
|
|
"loss": 6.5345,
|
|
"mean_token_accuracy": 0.11997396796941757,
|
|
"num_tokens": 19088305.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.6340724468231205,
|
|
"epoch": 0.9438707260955642,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004921027159461829,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.12113322243094445,
|
|
"num_tokens": 19098046.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.671371126174927,
|
|
"epoch": 0.9444058002033282,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004920926721945927,
|
|
"loss": 6.4321,
|
|
"mean_token_accuracy": 0.129939915984869,
|
|
"num_tokens": 19109019.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.638124275207519,
|
|
"epoch": 0.9449408743110921,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004920826221744823,
|
|
"loss": 6.4537,
|
|
"mean_token_accuracy": 0.12390751093626022,
|
|
"num_tokens": 19119624.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.62553038597107,
|
|
"epoch": 0.945475948418856,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004920725658861417,
|
|
"loss": 6.4987,
|
|
"mean_token_accuracy": 0.11999208480119705,
|
|
"num_tokens": 19130577.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.652018642425537,
|
|
"epoch": 0.94601102252662,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004920625033298611,
|
|
"loss": 6.4081,
|
|
"mean_token_accuracy": 0.12526340633630753,
|
|
"num_tokens": 19140254.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.637987852096558,
|
|
"epoch": 0.9465460966343838,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004920524345059314,
|
|
"loss": 6.4432,
|
|
"mean_token_accuracy": 0.12487659081816674,
|
|
"num_tokens": 19151357.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.680431222915649,
|
|
"epoch": 0.9470811707421478,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004920423594146431,
|
|
"loss": 6.4472,
|
|
"mean_token_accuracy": 0.12816984057426453,
|
|
"num_tokens": 19162069.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.558049917221069,
|
|
"epoch": 0.9476162448499117,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004920322780562872,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.13403208255767823,
|
|
"num_tokens": 19172515.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.504432582855225,
|
|
"epoch": 0.9481513189576757,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004920221904311546,
|
|
"loss": 6.3534,
|
|
"mean_token_accuracy": 0.128172717243433,
|
|
"num_tokens": 19182450.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.615408802032471,
|
|
"epoch": 0.9486863930654396,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004920120965395369,
|
|
"loss": 6.5534,
|
|
"mean_token_accuracy": 0.12120468094944954,
|
|
"num_tokens": 19193833.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.735569000244141,
|
|
"epoch": 0.9492214671732034,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004920019963817253,
|
|
"loss": 6.4938,
|
|
"mean_token_accuracy": 0.120438701659441,
|
|
"num_tokens": 19204970.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.660550594329834,
|
|
"epoch": 0.9497565412809674,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004919918899580117,
|
|
"loss": 6.4417,
|
|
"mean_token_accuracy": 0.12729626968503,
|
|
"num_tokens": 19215795.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.587117671966553,
|
|
"epoch": 0.9502916153887313,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004919817772686876,
|
|
"loss": 6.4851,
|
|
"mean_token_accuracy": 0.12257915437221527,
|
|
"num_tokens": 19226375.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.64892840385437,
|
|
"epoch": 0.9508266894964953,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004919716583140453,
|
|
"loss": 6.4759,
|
|
"mean_token_accuracy": 0.1330243282020092,
|
|
"num_tokens": 19236066.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.580484104156494,
|
|
"epoch": 0.9513617636042592,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004919615330943769,
|
|
"loss": 6.3546,
|
|
"mean_token_accuracy": 0.1333814412355423,
|
|
"num_tokens": 19246757.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.67290620803833,
|
|
"epoch": 0.9518968377120232,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004919514016099746,
|
|
"loss": 6.5138,
|
|
"mean_token_accuracy": 0.11956491172313691,
|
|
"num_tokens": 19257875.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.681473970413208,
|
|
"epoch": 0.952431911819787,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000491941263861131,
|
|
"loss": 6.4897,
|
|
"mean_token_accuracy": 0.1281803220510483,
|
|
"num_tokens": 19270236.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.591642904281616,
|
|
"epoch": 0.9529669859275509,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000491931119848139,
|
|
"loss": 6.4904,
|
|
"mean_token_accuracy": 0.12086865976452828,
|
|
"num_tokens": 19280877.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.557910919189453,
|
|
"epoch": 0.9535020600353149,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004919209695712915,
|
|
"loss": 6.3743,
|
|
"mean_token_accuracy": 0.13212507590651512,
|
|
"num_tokens": 19292852.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.685085773468018,
|
|
"epoch": 0.9540371341430788,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004919108130308814,
|
|
"loss": 6.571,
|
|
"mean_token_accuracy": 0.11689881011843681,
|
|
"num_tokens": 19305516.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.659373331069946,
|
|
"epoch": 0.9545722082508428,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004919006502272019,
|
|
"loss": 6.4084,
|
|
"mean_token_accuracy": 0.13058645725250245,
|
|
"num_tokens": 19315436.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.600830888748169,
|
|
"epoch": 0.9551072823586066,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004918904811605468,
|
|
"loss": 6.4527,
|
|
"mean_token_accuracy": 0.12625009566545486,
|
|
"num_tokens": 19325393.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.57855453491211,
|
|
"epoch": 0.9556423564663706,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004918803058312094,
|
|
"loss": 6.4359,
|
|
"mean_token_accuracy": 0.1306679517030716,
|
|
"num_tokens": 19336722.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.755772876739502,
|
|
"epoch": 0.9561774305741345,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004918701242394837,
|
|
"loss": 6.5996,
|
|
"mean_token_accuracy": 0.11706655621528625,
|
|
"num_tokens": 19348406.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.634890079498291,
|
|
"epoch": 0.9567125046818984,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004918599363856637,
|
|
"loss": 6.406,
|
|
"mean_token_accuracy": 0.1373704716563225,
|
|
"num_tokens": 19359714.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.598302412033081,
|
|
"epoch": 0.9572475787896624,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004918497422700434,
|
|
"loss": 6.4514,
|
|
"mean_token_accuracy": 0.12615504264831542,
|
|
"num_tokens": 19370833.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.653850555419922,
|
|
"epoch": 0.9577826528974263,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004918395418929174,
|
|
"loss": 6.5276,
|
|
"mean_token_accuracy": 0.12044409587979317,
|
|
"num_tokens": 19382098.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.6409813404083256,
|
|
"epoch": 0.9583177270051902,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00049182933525458,
|
|
"loss": 6.4955,
|
|
"mean_token_accuracy": 0.1270679734647274,
|
|
"num_tokens": 19393595.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.615951585769653,
|
|
"epoch": 0.9588528011129541,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000491819122355326,
|
|
"loss": 6.4364,
|
|
"mean_token_accuracy": 0.130043176561594,
|
|
"num_tokens": 19405296.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.660472297668457,
|
|
"epoch": 0.9593878752207181,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004918089031954503,
|
|
"loss": 6.4707,
|
|
"mean_token_accuracy": 0.12417094707489014,
|
|
"num_tokens": 19415693.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.66389274597168,
|
|
"epoch": 0.959922949328482,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000491798677775248,
|
|
"loss": 6.516,
|
|
"mean_token_accuracy": 0.1229399211704731,
|
|
"num_tokens": 19426140.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.739727592468261,
|
|
"epoch": 0.9604580234362459,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004917884460950144,
|
|
"loss": 6.554,
|
|
"mean_token_accuracy": 0.12139503434300422,
|
|
"num_tokens": 19437543.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.645191287994384,
|
|
"epoch": 0.9609930975440099,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000491778208155045,
|
|
"loss": 6.4712,
|
|
"mean_token_accuracy": 0.12503816932439804,
|
|
"num_tokens": 19447788.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.654383182525635,
|
|
"epoch": 0.9615281716517737,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004917679639556351,
|
|
"loss": 6.4813,
|
|
"mean_token_accuracy": 0.12615035399794577,
|
|
"num_tokens": 19457587.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.629149532318115,
|
|
"epoch": 0.9620632457595377,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004917577134970808,
|
|
"loss": 6.4036,
|
|
"mean_token_accuracy": 0.12516655772924423,
|
|
"num_tokens": 19467422.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.599620246887207,
|
|
"epoch": 0.9625983198673016,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004917474567796778,
|
|
"loss": 6.4471,
|
|
"mean_token_accuracy": 0.127543955296278,
|
|
"num_tokens": 19479037.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.597938489913941,
|
|
"epoch": 0.9631333939750656,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004917371938037226,
|
|
"loss": 6.3842,
|
|
"mean_token_accuracy": 0.1423794820904732,
|
|
"num_tokens": 19489639.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.9631333939750656,
|
|
"eval_entropy": 6.493540292030396,
|
|
"eval_loss": 6.537773132324219,
|
|
"eval_mean_token_accuracy": 0.1265094045730373,
|
|
"eval_num_tokens": 19489639.0,
|
|
"eval_runtime": 22.8003,
|
|
"eval_samples_per_second": 1301.691,
|
|
"eval_steps_per_second": 162.717,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 6.656441926956177,
|
|
"epoch": 0.9636684680828295,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004917269245695114,
|
|
"loss": 6.5165,
|
|
"mean_token_accuracy": 0.12059979364275933,
|
|
"num_tokens": 19500592.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 6.678815460205078,
|
|
"epoch": 0.9642035421905933,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004917166490773406,
|
|
"loss": 6.5043,
|
|
"mean_token_accuracy": 0.1199967049062252,
|
|
"num_tokens": 19510818.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 6.665318632125855,
|
|
"epoch": 0.9647386162983573,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004917063673275071,
|
|
"loss": 6.5286,
|
|
"mean_token_accuracy": 0.12441013976931573,
|
|
"num_tokens": 19521283.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 6.643071794509888,
|
|
"epoch": 0.9652736904061212,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004916960793203077,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.12617153972387313,
|
|
"num_tokens": 19531799.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 6.6218140602111815,
|
|
"epoch": 0.9658087645138852,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004916857850560394,
|
|
"loss": 6.3626,
|
|
"mean_token_accuracy": 0.1371275544166565,
|
|
"num_tokens": 19542377.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 6.599228096008301,
|
|
"epoch": 0.9663438386216491,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004916754845349996,
|
|
"loss": 6.3781,
|
|
"mean_token_accuracy": 0.1288759581744671,
|
|
"num_tokens": 19552654.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 6.590771245956421,
|
|
"epoch": 0.9668789127294131,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004916651777574856,
|
|
"loss": 6.4276,
|
|
"mean_token_accuracy": 0.12682240456342697,
|
|
"num_tokens": 19563439.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 6.598130130767823,
|
|
"epoch": 0.9674139868371769,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000491654864723795,
|
|
"loss": 6.4558,
|
|
"mean_token_accuracy": 0.1308298021554947,
|
|
"num_tokens": 19574264.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 6.4949644088745115,
|
|
"epoch": 0.9679490609449408,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004916445454342256,
|
|
"loss": 6.329,
|
|
"mean_token_accuracy": 0.13714528530836106,
|
|
"num_tokens": 19585293.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 6.618053579330445,
|
|
"epoch": 0.9684841350527048,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004916342198890754,
|
|
"loss": 6.3823,
|
|
"mean_token_accuracy": 0.1247588999569416,
|
|
"num_tokens": 19594384.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 6.5684973239898685,
|
|
"epoch": 0.9690192091604687,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004916238880886426,
|
|
"loss": 6.5096,
|
|
"mean_token_accuracy": 0.12653708159923555,
|
|
"num_tokens": 19605144.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 6.583761548995971,
|
|
"epoch": 0.9695542832682327,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004916135500332255,
|
|
"loss": 6.3935,
|
|
"mean_token_accuracy": 0.1302058443427086,
|
|
"num_tokens": 19615885.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 6.597869968414306,
|
|
"epoch": 0.9700893573759966,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004916032057231225,
|
|
"loss": 6.4027,
|
|
"mean_token_accuracy": 0.12344093546271324,
|
|
"num_tokens": 19625749.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 6.608986520767212,
|
|
"epoch": 0.9706244314837605,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004915928551586324,
|
|
"loss": 6.4954,
|
|
"mean_token_accuracy": 0.12440209984779357,
|
|
"num_tokens": 19638285.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 6.72171311378479,
|
|
"epoch": 0.9711595055915244,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004915824983400541,
|
|
"loss": 6.5374,
|
|
"mean_token_accuracy": 0.11889039278030396,
|
|
"num_tokens": 19649697.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 6.68416109085083,
|
|
"epoch": 0.9716945796992883,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004915721352676864,
|
|
"loss": 6.5164,
|
|
"mean_token_accuracy": 0.12317515462636948,
|
|
"num_tokens": 19659668.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 6.59567232131958,
|
|
"epoch": 0.9722296538070523,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004915617659418289,
|
|
"loss": 6.3903,
|
|
"mean_token_accuracy": 0.12933844700455666,
|
|
"num_tokens": 19670301.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 6.62542757987976,
|
|
"epoch": 0.9727647279148162,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004915513903627807,
|
|
"loss": 6.4312,
|
|
"mean_token_accuracy": 0.126902886480093,
|
|
"num_tokens": 19680926.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 6.562011623382569,
|
|
"epoch": 0.9732998020225802,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004915410085308417,
|
|
"loss": 6.4145,
|
|
"mean_token_accuracy": 0.1304332472383976,
|
|
"num_tokens": 19691467.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 6.623237371444702,
|
|
"epoch": 0.973834876130344,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004915306204463115,
|
|
"loss": 6.4149,
|
|
"mean_token_accuracy": 0.12685946375131607,
|
|
"num_tokens": 19701139.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 6.640606117248535,
|
|
"epoch": 0.974369950238108,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00049152022610949,
|
|
"loss": 6.4165,
|
|
"mean_token_accuracy": 0.1248056523501873,
|
|
"num_tokens": 19710628.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 6.631631469726562,
|
|
"epoch": 0.9749050243458719,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004915098255206773,
|
|
"loss": 6.4319,
|
|
"mean_token_accuracy": 0.1284477412700653,
|
|
"num_tokens": 19721824.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 6.597808074951172,
|
|
"epoch": 0.9754400984536358,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000491499418680174,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.12056017816066741,
|
|
"num_tokens": 19732557.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 6.605461311340332,
|
|
"epoch": 0.9759751725613998,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004914890055882804,
|
|
"loss": 6.4381,
|
|
"mean_token_accuracy": 0.11811697483062744,
|
|
"num_tokens": 19743436.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 6.5952520847320555,
|
|
"epoch": 0.9765102466691636,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000491478586245297,
|
|
"loss": 6.3791,
|
|
"mean_token_accuracy": 0.130065143853426,
|
|
"num_tokens": 19755305.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 6.6184971809387205,
|
|
"epoch": 0.9770453207769276,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000491468160651525,
|
|
"loss": 6.358,
|
|
"mean_token_accuracy": 0.134830953925848,
|
|
"num_tokens": 19766223.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 6.510128545761108,
|
|
"epoch": 0.9775803948846915,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004914577288072652,
|
|
"loss": 6.4355,
|
|
"mean_token_accuracy": 0.12992795631289483,
|
|
"num_tokens": 19777268.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 6.658121919631958,
|
|
"epoch": 0.9781154689924555,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004914472907128189,
|
|
"loss": 6.5503,
|
|
"mean_token_accuracy": 0.12386099994182587,
|
|
"num_tokens": 19787875.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 6.657345485687256,
|
|
"epoch": 0.9786505431002194,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004914368463684876,
|
|
"loss": 6.4367,
|
|
"mean_token_accuracy": 0.12749041765928268,
|
|
"num_tokens": 19798919.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 6.627368021011352,
|
|
"epoch": 0.9791856172079834,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004914263957745726,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.13380604833364487,
|
|
"num_tokens": 19809320.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 6.688372373580933,
|
|
"epoch": 0.9797206913157472,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004914159389313759,
|
|
"loss": 6.4906,
|
|
"mean_token_accuracy": 0.1275503568351269,
|
|
"num_tokens": 19819511.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 6.666792154312134,
|
|
"epoch": 0.9802557654235111,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004914054758391994,
|
|
"loss": 6.5245,
|
|
"mean_token_accuracy": 0.12252224758267402,
|
|
"num_tokens": 19830381.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 6.512205410003662,
|
|
"epoch": 0.9807908395312751,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004913950064983452,
|
|
"loss": 6.3722,
|
|
"mean_token_accuracy": 0.12669735103845597,
|
|
"num_tokens": 19840806.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 6.548713111877442,
|
|
"epoch": 0.981325913639039,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004913845309091156,
|
|
"loss": 6.363,
|
|
"mean_token_accuracy": 0.13637888729572295,
|
|
"num_tokens": 19851095.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 6.5859472274780275,
|
|
"epoch": 0.981860987746803,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004913740490718131,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.1384767584502697,
|
|
"num_tokens": 19860235.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 6.539888668060303,
|
|
"epoch": 0.9823960618545668,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004913635609867403,
|
|
"loss": 6.4349,
|
|
"mean_token_accuracy": 0.12136122882366181,
|
|
"num_tokens": 19872264.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 6.668402528762817,
|
|
"epoch": 0.9829311359623308,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004913530666542001,
|
|
"loss": 6.5348,
|
|
"mean_token_accuracy": 0.12160997837781906,
|
|
"num_tokens": 19883628.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 6.649431419372559,
|
|
"epoch": 0.9834662100700947,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004913425660744955,
|
|
"loss": 6.4202,
|
|
"mean_token_accuracy": 0.12248381748795509,
|
|
"num_tokens": 19894624.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 6.658456754684448,
|
|
"epoch": 0.9840012841778586,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 0.0004913320592479297,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.12467296943068504,
|
|
"num_tokens": 19904882.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 6.5607868194580075,
|
|
"epoch": 0.9845363582856226,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004913215461748061,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.12822477295994758,
|
|
"num_tokens": 19915344.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 6.525886154174804,
|
|
"epoch": 0.9850714323933865,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004913110268554282,
|
|
"loss": 6.5051,
|
|
"mean_token_accuracy": 0.11876617446541786,
|
|
"num_tokens": 19927527.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 6.581648349761963,
|
|
"epoch": 0.9856065065011504,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004913005012900998,
|
|
"loss": 6.4595,
|
|
"mean_token_accuracy": 0.12477364614605904,
|
|
"num_tokens": 19938893.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 6.611907911300659,
|
|
"epoch": 0.9861415806089143,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004912899694791248,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.12833005487918853,
|
|
"num_tokens": 19949297.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 6.5755777835845945,
|
|
"epoch": 0.9866766547166783,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004912794314228074,
|
|
"loss": 6.3816,
|
|
"mean_token_accuracy": 0.12894971445202827,
|
|
"num_tokens": 19959194.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 6.603084754943848,
|
|
"epoch": 0.9872117288244422,
|
|
"grad_norm": 10.125,
|
|
"learning_rate": 0.0004912688871214518,
|
|
"loss": 6.4384,
|
|
"mean_token_accuracy": 0.1258403018116951,
|
|
"num_tokens": 19969896.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 6.626691627502441,
|
|
"epoch": 0.9877468029322061,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004912583365753625,
|
|
"loss": 6.4113,
|
|
"mean_token_accuracy": 0.1297162726521492,
|
|
"num_tokens": 19981505.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 6.628116035461426,
|
|
"epoch": 0.9882818770399701,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004912477797848441,
|
|
"loss": 6.4046,
|
|
"mean_token_accuracy": 0.13139230236411095,
|
|
"num_tokens": 19992770.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 6.601294374465942,
|
|
"epoch": 0.9888169511477339,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004912372167502014,
|
|
"loss": 6.3915,
|
|
"mean_token_accuracy": 0.1270472601056099,
|
|
"num_tokens": 20003572.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 6.539927577972412,
|
|
"epoch": 0.9893520252554979,
|
|
"grad_norm": 3.890625,
|
|
"learning_rate": 0.0004912266474717394,
|
|
"loss": 6.4423,
|
|
"mean_token_accuracy": 0.12464056462049485,
|
|
"num_tokens": 20014500.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 6.595606756210327,
|
|
"epoch": 0.9898870993632618,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004912160719497635,
|
|
"loss": 6.4284,
|
|
"mean_token_accuracy": 0.12811992466449737,
|
|
"num_tokens": 20025745.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 6.550686597824097,
|
|
"epoch": 0.9904221734710258,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004912054901845788,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.1309215672314167,
|
|
"num_tokens": 20036346.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 6.501697254180908,
|
|
"epoch": 0.9909572475787897,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000491194902176491,
|
|
"loss": 6.4692,
|
|
"mean_token_accuracy": 0.12736540138721467,
|
|
"num_tokens": 20048162.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 6.603750467300415,
|
|
"epoch": 0.9914923216865535,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004911843079258057,
|
|
"loss": 6.5538,
|
|
"mean_token_accuracy": 0.11743113771080971,
|
|
"num_tokens": 20058947.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 6.71206374168396,
|
|
"epoch": 0.9920273957943175,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004911737074328289,
|
|
"loss": 6.4873,
|
|
"mean_token_accuracy": 0.1255404070019722,
|
|
"num_tokens": 20069282.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 6.630812120437622,
|
|
"epoch": 0.9925624699020814,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004911631006978667,
|
|
"loss": 6.4491,
|
|
"mean_token_accuracy": 0.13215150088071823,
|
|
"num_tokens": 20078347.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 6.616550254821777,
|
|
"epoch": 0.9930975440098454,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004911524877212254,
|
|
"loss": 6.4627,
|
|
"mean_token_accuracy": 0.12041875049471855,
|
|
"num_tokens": 20089129.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 6.652893495559693,
|
|
"epoch": 0.9936326181176093,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004911418685032114,
|
|
"loss": 6.4608,
|
|
"mean_token_accuracy": 0.12489487826824189,
|
|
"num_tokens": 20101008.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 6.572811889648437,
|
|
"epoch": 0.9941676922253733,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004911312430441312,
|
|
"loss": 6.4716,
|
|
"mean_token_accuracy": 0.12638648301362992,
|
|
"num_tokens": 20112272.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 6.59024395942688,
|
|
"epoch": 0.9947027663331371,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004911206113442918,
|
|
"loss": 6.3656,
|
|
"mean_token_accuracy": 0.13372359201312065,
|
|
"num_tokens": 20122814.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 6.526870536804199,
|
|
"epoch": 0.995237840440901,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004911099734040001,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.1285125881433487,
|
|
"num_tokens": 20133169.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 6.678136587142944,
|
|
"epoch": 0.995772914548665,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004910993292235634,
|
|
"loss": 6.4765,
|
|
"mean_token_accuracy": 0.11497483775019646,
|
|
"num_tokens": 20144355.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 6.691679811477661,
|
|
"epoch": 0.9963079886564289,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004910886788032887,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.12571135461330413,
|
|
"num_tokens": 20154486.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 6.6170188903808596,
|
|
"epoch": 0.9968430627641929,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004910780221434839,
|
|
"loss": 6.4473,
|
|
"mean_token_accuracy": 0.1292208530008793,
|
|
"num_tokens": 20166359.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 6.602609443664551,
|
|
"epoch": 0.9973781368719568,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004910673592444566,
|
|
"loss": 6.4321,
|
|
"mean_token_accuracy": 0.12575030997395514,
|
|
"num_tokens": 20176469.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 6.6265278339385985,
|
|
"epoch": 0.9979132109797207,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004910566901065147,
|
|
"loss": 6.4821,
|
|
"mean_token_accuracy": 0.12630784809589385,
|
|
"num_tokens": 20188334.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 6.631861209869385,
|
|
"epoch": 0.9984482850874846,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004910460147299661,
|
|
"loss": 6.3696,
|
|
"mean_token_accuracy": 0.13478620648384093,
|
|
"num_tokens": 20198594.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 6.624561452865601,
|
|
"epoch": 0.9989833591952485,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004910353331151193,
|
|
"loss": 6.4789,
|
|
"mean_token_accuracy": 0.12900208532810212,
|
|
"num_tokens": 20209456.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 6.588892841339112,
|
|
"epoch": 0.9995184333030125,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004910246452622825,
|
|
"loss": 6.466,
|
|
"mean_token_accuracy": 0.12764586359262467,
|
|
"num_tokens": 20219835.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 6.646910879347059,
|
|
"epoch": 1.0,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004910139511717646,
|
|
"loss": 6.4822,
|
|
"mean_token_accuracy": 0.12267948935429256,
|
|
"num_tokens": 20228258.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 6.6116338729858395,
|
|
"epoch": 1.0005350741077639,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004910032508438739,
|
|
"loss": 6.3472,
|
|
"mean_token_accuracy": 0.13001422286033631,
|
|
"num_tokens": 20238875.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 6.652476358413696,
|
|
"epoch": 1.0010701482155278,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00049099254427892,
|
|
"loss": 6.3876,
|
|
"mean_token_accuracy": 0.12094790488481522,
|
|
"num_tokens": 20249750.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 6.713427877426147,
|
|
"epoch": 1.0016052223232919,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004909818314772116,
|
|
"loss": 6.4249,
|
|
"mean_token_accuracy": 0.11998702734708785,
|
|
"num_tokens": 20259772.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 6.5642101764678955,
|
|
"epoch": 1.0021402964310557,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004909711124390582,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.13192544803023337,
|
|
"num_tokens": 20270230.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 6.47281322479248,
|
|
"epoch": 1.0026753705388196,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004909603871647692,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.14585858657956124,
|
|
"num_tokens": 20280317.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 6.604093933105469,
|
|
"epoch": 1.0032104446465835,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004909496556546544,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.13290477320551872,
|
|
"num_tokens": 20291147.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 6.564534425735474,
|
|
"epoch": 1.0037455187543476,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004909389179090238,
|
|
"loss": 6.354,
|
|
"mean_token_accuracy": 0.13291771113872528,
|
|
"num_tokens": 20301095.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 6.566314220428467,
|
|
"epoch": 1.0042805928621115,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004909281739281871,
|
|
"loss": 6.3677,
|
|
"mean_token_accuracy": 0.13257990628480912,
|
|
"num_tokens": 20311216.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 6.639392518997193,
|
|
"epoch": 1.0048156669698753,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004909174237124548,
|
|
"loss": 6.4148,
|
|
"mean_token_accuracy": 0.1151929646730423,
|
|
"num_tokens": 20321719.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 6.655008602142334,
|
|
"epoch": 1.0053507410776392,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004909066672621372,
|
|
"loss": 6.4134,
|
|
"mean_token_accuracy": 0.12979249581694602,
|
|
"num_tokens": 20331997.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 6.634089517593384,
|
|
"epoch": 1.005885815185403,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004908959045775449,
|
|
"loss": 6.4498,
|
|
"mean_token_accuracy": 0.12072990089654922,
|
|
"num_tokens": 20342973.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 6.580580997467041,
|
|
"epoch": 1.0064208892931672,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004908851356589887,
|
|
"loss": 6.3324,
|
|
"mean_token_accuracy": 0.12956621050834655,
|
|
"num_tokens": 20352652.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 6.632066440582276,
|
|
"epoch": 1.006955963400931,
|
|
"grad_norm": 11.375,
|
|
"learning_rate": 0.0004908743605067796,
|
|
"loss": 6.4074,
|
|
"mean_token_accuracy": 0.12797401919960977,
|
|
"num_tokens": 20364577.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 6.615362119674683,
|
|
"epoch": 1.007491037508695,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004908635791212287,
|
|
"loss": 6.4397,
|
|
"mean_token_accuracy": 0.1281264081597328,
|
|
"num_tokens": 20375451.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 6.609331274032593,
|
|
"epoch": 1.0080261116164588,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004908527915026472,
|
|
"loss": 6.3717,
|
|
"mean_token_accuracy": 0.12847210839390755,
|
|
"num_tokens": 20385174.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 6.596631097793579,
|
|
"epoch": 1.0085611857242227,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004908419976513467,
|
|
"loss": 6.3128,
|
|
"mean_token_accuracy": 0.12980904728174208,
|
|
"num_tokens": 20395710.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 6.500821256637574,
|
|
"epoch": 1.0090962598319868,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004908311975676388,
|
|
"loss": 6.3111,
|
|
"mean_token_accuracy": 0.1318104863166809,
|
|
"num_tokens": 20406572.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 6.49522705078125,
|
|
"epoch": 1.0096313339397507,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004908203912518355,
|
|
"loss": 6.3046,
|
|
"mean_token_accuracy": 0.13669004216790198,
|
|
"num_tokens": 20417786.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 6.682159757614135,
|
|
"epoch": 1.0101664080475146,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004908095787042487,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.1288808174431324,
|
|
"num_tokens": 20427680.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 6.553224849700928,
|
|
"epoch": 1.0107014821552784,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004907987599251907,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.12506312131881714,
|
|
"num_tokens": 20438640.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 6.545442390441894,
|
|
"epoch": 1.0112365562630425,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004907879349149737,
|
|
"loss": 6.3459,
|
|
"mean_token_accuracy": 0.13781134113669397,
|
|
"num_tokens": 20449939.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 6.522792005538941,
|
|
"epoch": 1.0117716303708064,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004907771036739105,
|
|
"loss": 6.2878,
|
|
"mean_token_accuracy": 0.13046553134918212,
|
|
"num_tokens": 20460845.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 6.607302570343018,
|
|
"epoch": 1.0123067044785703,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004907662662023137,
|
|
"loss": 6.4192,
|
|
"mean_token_accuracy": 0.12477940544486046,
|
|
"num_tokens": 20472407.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 6.6209321975708,
|
|
"epoch": 1.0128417785863342,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004907554225004962,
|
|
"loss": 6.4152,
|
|
"mean_token_accuracy": 0.12976087108254433,
|
|
"num_tokens": 20483192.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 6.686941289901734,
|
|
"epoch": 1.013376852694098,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004907445725687714,
|
|
"loss": 6.4642,
|
|
"mean_token_accuracy": 0.1248107336461544,
|
|
"num_tokens": 20493498.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 6.6130506038665775,
|
|
"epoch": 1.0139119268018622,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004907337164074523,
|
|
"loss": 6.4024,
|
|
"mean_token_accuracy": 0.13003687858581542,
|
|
"num_tokens": 20503781.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 6.5403910160064695,
|
|
"epoch": 1.014447000909626,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004907228540168523,
|
|
"loss": 6.4579,
|
|
"mean_token_accuracy": 0.12542894706130028,
|
|
"num_tokens": 20515142.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 6.563270521163941,
|
|
"epoch": 1.01498207501739,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004907119853972854,
|
|
"loss": 6.4057,
|
|
"mean_token_accuracy": 0.1261343017220497,
|
|
"num_tokens": 20527568.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 6.5474437236785885,
|
|
"epoch": 1.0155171491251538,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004907011105490651,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.13531249314546584,
|
|
"num_tokens": 20538198.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 6.6131363868713375,
|
|
"epoch": 1.0160522232329177,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004906902294725056,
|
|
"loss": 6.3069,
|
|
"mean_token_accuracy": 0.13496000096201896,
|
|
"num_tokens": 20549355.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 6.604595279693603,
|
|
"epoch": 1.0165872973406818,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000490679342167921,
|
|
"loss": 6.4229,
|
|
"mean_token_accuracy": 0.12729562073946,
|
|
"num_tokens": 20558984.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 6.606345987319946,
|
|
"epoch": 1.0171223714484456,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004906684486356258,
|
|
"loss": 6.4216,
|
|
"mean_token_accuracy": 0.12135640606284141,
|
|
"num_tokens": 20570143.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 6.611699104309082,
|
|
"epoch": 1.0176574455562095,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004906575488759343,
|
|
"loss": 6.4192,
|
|
"mean_token_accuracy": 0.12480204030871392,
|
|
"num_tokens": 20580973.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 6.638233613967896,
|
|
"epoch": 1.0181925196639734,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004906466428891616,
|
|
"loss": 6.3789,
|
|
"mean_token_accuracy": 0.12479526326060295,
|
|
"num_tokens": 20591473.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 6.615546989440918,
|
|
"epoch": 1.0187275937717375,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004906357306756222,
|
|
"loss": 6.3393,
|
|
"mean_token_accuracy": 0.1306021586060524,
|
|
"num_tokens": 20602347.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 6.608539628982544,
|
|
"epoch": 1.0192626678795014,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004906248122356315,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.1312938541173935,
|
|
"num_tokens": 20613168.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 6.558542537689209,
|
|
"epoch": 1.0197977419872652,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004906138875695045,
|
|
"loss": 6.296,
|
|
"mean_token_accuracy": 0.132112068682909,
|
|
"num_tokens": 20623523.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 6.486743068695068,
|
|
"epoch": 1.0203328160950291,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004906029566775569,
|
|
"loss": 6.3472,
|
|
"mean_token_accuracy": 0.13200024887919426,
|
|
"num_tokens": 20634085.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 6.5780562400817875,
|
|
"epoch": 1.020867890202793,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004905920195601042,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.12601158618927003,
|
|
"num_tokens": 20644747.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 6.594791412353516,
|
|
"epoch": 1.021402964310557,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004905810762174622,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.1227644331753254,
|
|
"num_tokens": 20655704.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 6.635960626602173,
|
|
"epoch": 1.021938038418321,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004905701266499469,
|
|
"loss": 6.33,
|
|
"mean_token_accuracy": 0.13520995900034904,
|
|
"num_tokens": 20665844.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 6.606992101669311,
|
|
"epoch": 1.0224731125260849,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004905591708578746,
|
|
"loss": 6.4599,
|
|
"mean_token_accuracy": 0.1187673568725586,
|
|
"num_tokens": 20676921.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 6.6138591289520265,
|
|
"epoch": 1.0230081866338487,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004905482088415615,
|
|
"loss": 6.4033,
|
|
"mean_token_accuracy": 0.1244032271206379,
|
|
"num_tokens": 20688476.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 6.597647380828858,
|
|
"epoch": 1.0235432607416126,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004905372406013241,
|
|
"loss": 6.4095,
|
|
"mean_token_accuracy": 0.12829091697931289,
|
|
"num_tokens": 20698588.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 6.611582708358765,
|
|
"epoch": 1.0240783348493767,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004905262661374792,
|
|
"loss": 6.3903,
|
|
"mean_token_accuracy": 0.1309063859283924,
|
|
"num_tokens": 20709181.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 6.587467670440674,
|
|
"epoch": 1.0246134089571406,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004905152854503436,
|
|
"loss": 6.3164,
|
|
"mean_token_accuracy": 0.13433003351092337,
|
|
"num_tokens": 20719724.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 6.586146974563599,
|
|
"epoch": 1.0251484830649045,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004905042985402345,
|
|
"loss": 6.4318,
|
|
"mean_token_accuracy": 0.1253502734005451,
|
|
"num_tokens": 20730548.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 6.608967018127442,
|
|
"epoch": 1.0256835571726683,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000490493305407469,
|
|
"loss": 6.3929,
|
|
"mean_token_accuracy": 0.12260351702570915,
|
|
"num_tokens": 20742124.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 6.6725348949432375,
|
|
"epoch": 1.0262186312804324,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004904823060523646,
|
|
"loss": 6.462,
|
|
"mean_token_accuracy": 0.12304821535944939,
|
|
"num_tokens": 20753313.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 6.668299865722656,
|
|
"epoch": 1.0267537053881963,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004904713004752389,
|
|
"loss": 6.4267,
|
|
"mean_token_accuracy": 0.12702021822333337,
|
|
"num_tokens": 20763539.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 6.611340618133545,
|
|
"epoch": 1.0272887794959602,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004904602886764097,
|
|
"loss": 6.5207,
|
|
"mean_token_accuracy": 0.12022551968693733,
|
|
"num_tokens": 20775849.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 6.580652952194214,
|
|
"epoch": 1.027823853603724,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004904492706561948,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.12456403076648712,
|
|
"num_tokens": 20787460.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 6.665969038009644,
|
|
"epoch": 1.028358927711488,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004904382464149127,
|
|
"loss": 6.3032,
|
|
"mean_token_accuracy": 0.1357816383242607,
|
|
"num_tokens": 20798478.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 6.661708354949951,
|
|
"epoch": 1.028894001819252,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004904272159528814,
|
|
"loss": 6.4172,
|
|
"mean_token_accuracy": 0.1287016086280346,
|
|
"num_tokens": 20809730.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 6.617967319488526,
|
|
"epoch": 1.029429075927016,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004904161792704195,
|
|
"loss": 6.3808,
|
|
"mean_token_accuracy": 0.13786366283893586,
|
|
"num_tokens": 20821438.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 6.5838010787963865,
|
|
"epoch": 1.0299641500347798,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004904051363678457,
|
|
"loss": 6.3719,
|
|
"mean_token_accuracy": 0.12156581953167915,
|
|
"num_tokens": 20832328.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 6.532840824127197,
|
|
"epoch": 1.0304992241425437,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004903940872454789,
|
|
"loss": 6.3493,
|
|
"mean_token_accuracy": 0.1308904320001602,
|
|
"num_tokens": 20843956.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 6.637317371368408,
|
|
"epoch": 1.0310342982503076,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004903830319036381,
|
|
"loss": 6.3963,
|
|
"mean_token_accuracy": 0.1296381212770939,
|
|
"num_tokens": 20854578.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 6.553709697723389,
|
|
"epoch": 1.0315693723580717,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004903719703426425,
|
|
"loss": 6.3185,
|
|
"mean_token_accuracy": 0.12925079762935637,
|
|
"num_tokens": 20865190.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 6.633975028991699,
|
|
"epoch": 1.0321044464658355,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004903609025628115,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.12583873495459558,
|
|
"num_tokens": 20875733.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 6.546547222137451,
|
|
"epoch": 1.0326395205735994,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004903498285644647,
|
|
"loss": 6.3682,
|
|
"mean_token_accuracy": 0.12934231758117676,
|
|
"num_tokens": 20886900.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 6.579946565628052,
|
|
"epoch": 1.0331745946813633,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004903387483479219,
|
|
"loss": 6.4159,
|
|
"mean_token_accuracy": 0.13026815727353097,
|
|
"num_tokens": 20898125.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 6.624790096282959,
|
|
"epoch": 1.0337096687891274,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004903276619135029,
|
|
"loss": 6.4406,
|
|
"mean_token_accuracy": 0.12643810659646987,
|
|
"num_tokens": 20909788.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 6.644028615951538,
|
|
"epoch": 1.0342447428968913,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000490316569261528,
|
|
"loss": 6.4271,
|
|
"mean_token_accuracy": 0.12895434722304344,
|
|
"num_tokens": 20921853.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 6.667061233520508,
|
|
"epoch": 1.0347798170046552,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004903054703923175,
|
|
"loss": 6.4247,
|
|
"mean_token_accuracy": 0.12020558714866639,
|
|
"num_tokens": 20932574.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 6.568372678756714,
|
|
"epoch": 1.035314891112419,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004902943653061916,
|
|
"loss": 6.3946,
|
|
"mean_token_accuracy": 0.12240477427840232,
|
|
"num_tokens": 20943458.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 6.593540334701538,
|
|
"epoch": 1.035849965220183,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004902832540034712,
|
|
"loss": 6.3521,
|
|
"mean_token_accuracy": 0.13370758667588234,
|
|
"num_tokens": 20953213.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 6.57708888053894,
|
|
"epoch": 1.036385039327947,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004902721364844773,
|
|
"loss": 6.3633,
|
|
"mean_token_accuracy": 0.12842451483011247,
|
|
"num_tokens": 20963885.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 6.604686164855957,
|
|
"epoch": 1.0369201134357109,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004902610127495305,
|
|
"loss": 6.398,
|
|
"mean_token_accuracy": 0.1327418267726898,
|
|
"num_tokens": 20975529.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 6.563743686676025,
|
|
"epoch": 1.0374551875434748,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004902498827989523,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.13423618525266648,
|
|
"num_tokens": 20985279.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 6.608705711364746,
|
|
"epoch": 1.0379902616512386,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004902387466330639,
|
|
"loss": 6.3871,
|
|
"mean_token_accuracy": 0.12676662355661392,
|
|
"num_tokens": 20995818.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 6.552085876464844,
|
|
"epoch": 1.0385253357590025,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000490227604252187,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.13119786307215692,
|
|
"num_tokens": 21006786.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 6.567106485366821,
|
|
"epoch": 1.0390604098667666,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004902164556566433,
|
|
"loss": 6.392,
|
|
"mean_token_accuracy": 0.13248898908495904,
|
|
"num_tokens": 21017441.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 6.46131706237793,
|
|
"epoch": 1.0395954839745305,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004902053008467546,
|
|
"loss": 6.2437,
|
|
"mean_token_accuracy": 0.13775770589709282,
|
|
"num_tokens": 21027812.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 6.611622095108032,
|
|
"epoch": 1.0401305580822944,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004901941398228431,
|
|
"loss": 6.4393,
|
|
"mean_token_accuracy": 0.1281151406466961,
|
|
"num_tokens": 21038960.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 6.630351972579956,
|
|
"epoch": 1.0406656321900583,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004901829725852311,
|
|
"loss": 6.4061,
|
|
"mean_token_accuracy": 0.12819884419441224,
|
|
"num_tokens": 21050467.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 6.554682826995849,
|
|
"epoch": 1.0412007062978224,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000490171799134241,
|
|
"loss": 6.3093,
|
|
"mean_token_accuracy": 0.12498523071408271,
|
|
"num_tokens": 21061208.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 6.585750341415405,
|
|
"epoch": 1.0417357804055862,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004901606194701954,
|
|
"loss": 6.4094,
|
|
"mean_token_accuracy": 0.12677378505468367,
|
|
"num_tokens": 21072872.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 6.641561460494995,
|
|
"epoch": 1.04227085451335,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004901494335934172,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.13010147139430045,
|
|
"num_tokens": 21084878.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 6.674085378646851,
|
|
"epoch": 1.042805928621114,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004901382415042293,
|
|
"loss": 6.4241,
|
|
"mean_token_accuracy": 0.1254999652504921,
|
|
"num_tokens": 21095289.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 6.604314184188842,
|
|
"epoch": 1.0433410027288779,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004901270432029549,
|
|
"loss": 6.3689,
|
|
"mean_token_accuracy": 0.12942948341369628,
|
|
"num_tokens": 21106077.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 6.479086446762085,
|
|
"epoch": 1.043876076836642,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004901158386899174,
|
|
"loss": 6.2759,
|
|
"mean_token_accuracy": 0.133281908929348,
|
|
"num_tokens": 21116548.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 6.54858889579773,
|
|
"epoch": 1.0444111509444058,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004901046279654402,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.13944821655750275,
|
|
"num_tokens": 21126163.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 6.651744794845581,
|
|
"epoch": 1.0449462250521697,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004900934110298471,
|
|
"loss": 6.4057,
|
|
"mean_token_accuracy": 0.12298655658960342,
|
|
"num_tokens": 21136830.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 6.637675952911377,
|
|
"epoch": 1.0454812991599336,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004900821878834621,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.13300308287143708,
|
|
"num_tokens": 21146793.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 6.602027320861817,
|
|
"epoch": 1.0460163732676975,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000490070958526609,
|
|
"loss": 6.4245,
|
|
"mean_token_accuracy": 0.12666706070303918,
|
|
"num_tokens": 21156799.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 6.554815435409546,
|
|
"epoch": 1.0465514473754616,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004900597229596124,
|
|
"loss": 6.4011,
|
|
"mean_token_accuracy": 0.12746700271964073,
|
|
"num_tokens": 21167757.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 6.6415627002716064,
|
|
"epoch": 1.0470865214832255,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004900484811827963,
|
|
"loss": 6.3985,
|
|
"mean_token_accuracy": 0.1274073228240013,
|
|
"num_tokens": 21178832.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 6.604257345199585,
|
|
"epoch": 1.0476215955909893,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004900372331964856,
|
|
"loss": 6.3111,
|
|
"mean_token_accuracy": 0.13047252520918845,
|
|
"num_tokens": 21189637.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 6.547916078567505,
|
|
"epoch": 1.0481566696987532,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000490025979001005,
|
|
"loss": 6.3358,
|
|
"mean_token_accuracy": 0.12895719334483147,
|
|
"num_tokens": 21200194.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 6.5093584060668945,
|
|
"epoch": 1.0486917438065173,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004900147185966795,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.12876641899347305,
|
|
"num_tokens": 21211405.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 6.617459726333618,
|
|
"epoch": 1.0492268179142812,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004900034519838342,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.12443060278892518,
|
|
"num_tokens": 21222722.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 6.5697776794433596,
|
|
"epoch": 1.049761892022045,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004899921791627945,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.13529631569981576,
|
|
"num_tokens": 21233510.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 6.638922691345215,
|
|
"epoch": 1.050296966129809,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004899809001338857,
|
|
"loss": 6.448,
|
|
"mean_token_accuracy": 0.12117964178323745,
|
|
"num_tokens": 21243235.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 6.608948469161987,
|
|
"epoch": 1.0508320402375728,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004899696148974338,
|
|
"loss": 6.3539,
|
|
"mean_token_accuracy": 0.12653318047523499,
|
|
"num_tokens": 21254680.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 6.572614431381226,
|
|
"epoch": 1.051367114345337,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004899583234537644,
|
|
"loss": 6.3434,
|
|
"mean_token_accuracy": 0.12788400650024415,
|
|
"num_tokens": 21265116.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 6.560759401321411,
|
|
"epoch": 1.0519021884531008,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004899470258032034,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.12871653363108634,
|
|
"num_tokens": 21277066.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 6.614169502258301,
|
|
"epoch": 1.0524372625608647,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004899357219460775,
|
|
"loss": 6.3749,
|
|
"mean_token_accuracy": 0.12782574817538261,
|
|
"num_tokens": 21287332.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 6.560963869094849,
|
|
"epoch": 1.0529723366686286,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004899244118827128,
|
|
"loss": 6.3661,
|
|
"mean_token_accuracy": 0.1294943742454052,
|
|
"num_tokens": 21298377.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 6.630348157882691,
|
|
"epoch": 1.0535074107763924,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004899130956134358,
|
|
"loss": 6.3714,
|
|
"mean_token_accuracy": 0.1264801986515522,
|
|
"num_tokens": 21309966.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 6.5181419372558596,
|
|
"epoch": 1.0540424848841565,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004899017731385735,
|
|
"loss": 6.2653,
|
|
"mean_token_accuracy": 0.13790045976638793,
|
|
"num_tokens": 21320399.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 6.584508657455444,
|
|
"epoch": 1.0545775589919204,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004898904444584527,
|
|
"loss": 6.3832,
|
|
"mean_token_accuracy": 0.12866907492280005,
|
|
"num_tokens": 21331716.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 6.635886335372925,
|
|
"epoch": 1.0551126330996843,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004898791095734004,
|
|
"loss": 6.401,
|
|
"mean_token_accuracy": 0.12521571815013885,
|
|
"num_tokens": 21341664.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 6.604288721084595,
|
|
"epoch": 1.0556477072074482,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000489867768483744,
|
|
"loss": 6.3495,
|
|
"mean_token_accuracy": 0.1305569663643837,
|
|
"num_tokens": 21352220.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 6.650424575805664,
|
|
"epoch": 1.0561827813152123,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004898564211898111,
|
|
"loss": 6.4625,
|
|
"mean_token_accuracy": 0.1256709650158882,
|
|
"num_tokens": 21363947.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 6.652794408798218,
|
|
"epoch": 1.0567178554229761,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004898450676919291,
|
|
"loss": 6.3694,
|
|
"mean_token_accuracy": 0.12833540216088296,
|
|
"num_tokens": 21374011.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 6.603279066085816,
|
|
"epoch": 1.05725292953074,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000489833707990426,
|
|
"loss": 6.4019,
|
|
"mean_token_accuracy": 0.1298233076930046,
|
|
"num_tokens": 21384232.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 6.57667989730835,
|
|
"epoch": 1.057788003638504,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004898223420856298,
|
|
"loss": 6.3795,
|
|
"mean_token_accuracy": 0.12782718241214752,
|
|
"num_tokens": 21395928.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 6.61450834274292,
|
|
"epoch": 1.0583230777462678,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004898109699778686,
|
|
"loss": 6.382,
|
|
"mean_token_accuracy": 0.12396855279803276,
|
|
"num_tokens": 21406391.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 6.618608283996582,
|
|
"epoch": 1.0588581518540319,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000489799591667471,
|
|
"loss": 6.4321,
|
|
"mean_token_accuracy": 0.12423042431473733,
|
|
"num_tokens": 21417859.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 6.57124514579773,
|
|
"epoch": 1.0593932259617957,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004897882071547651,
|
|
"loss": 6.2836,
|
|
"mean_token_accuracy": 0.13253685906529428,
|
|
"num_tokens": 21428284.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 6.554050493240356,
|
|
"epoch": 1.0599283000695596,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004897768164400801,
|
|
"loss": 6.4153,
|
|
"mean_token_accuracy": 0.12158615291118621,
|
|
"num_tokens": 21439610.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 6.622523307800293,
|
|
"epoch": 1.0604633741773235,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004897654195237446,
|
|
"loss": 6.4444,
|
|
"mean_token_accuracy": 0.12294576540589333,
|
|
"num_tokens": 21449319.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 6.648335218429565,
|
|
"epoch": 1.0609984482850874,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004897540164060879,
|
|
"loss": 6.4308,
|
|
"mean_token_accuracy": 0.13007963448762894,
|
|
"num_tokens": 21459851.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 6.570676851272583,
|
|
"epoch": 1.0615335223928515,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004897426070874392,
|
|
"loss": 6.3842,
|
|
"mean_token_accuracy": 0.13101765438914298,
|
|
"num_tokens": 21469717.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 6.627567148208618,
|
|
"epoch": 1.0620685965006154,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004897311915681278,
|
|
"loss": 6.4709,
|
|
"mean_token_accuracy": 0.12203726097941399,
|
|
"num_tokens": 21480815.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 6.661324882507325,
|
|
"epoch": 1.0626036706083792,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004897197698484834,
|
|
"loss": 6.3836,
|
|
"mean_token_accuracy": 0.12534951865673066,
|
|
"num_tokens": 21492000.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 6.592737197875977,
|
|
"epoch": 1.0631387447161431,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004897083419288358,
|
|
"loss": 6.3525,
|
|
"mean_token_accuracy": 0.12510298043489457,
|
|
"num_tokens": 21502006.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 6.580988597869873,
|
|
"epoch": 1.0636738188239072,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000489696907809515,
|
|
"loss": 6.4117,
|
|
"mean_token_accuracy": 0.133916924148798,
|
|
"num_tokens": 21513066.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 6.591636514663696,
|
|
"epoch": 1.064208892931671,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004896854674908512,
|
|
"loss": 6.3856,
|
|
"mean_token_accuracy": 0.12307220920920373,
|
|
"num_tokens": 21524853.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 6.584508752822876,
|
|
"epoch": 1.064743967039435,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004896740209731746,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.12847256138920785,
|
|
"num_tokens": 21536497.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 6.545827436447143,
|
|
"epoch": 1.0652790411471988,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004896625682568159,
|
|
"loss": 6.3312,
|
|
"mean_token_accuracy": 0.1304571323096752,
|
|
"num_tokens": 21546213.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 6.5336925983428955,
|
|
"epoch": 1.0658141152549627,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004896511093421057,
|
|
"loss": 6.3062,
|
|
"mean_token_accuracy": 0.1359667584300041,
|
|
"num_tokens": 21556990.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 6.550822591781616,
|
|
"epoch": 1.0663491893627268,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004896396442293749,
|
|
"loss": 6.3353,
|
|
"mean_token_accuracy": 0.12950969487428665,
|
|
"num_tokens": 21567567.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 6.617183589935303,
|
|
"epoch": 1.0668842634704907,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004896281729189544,
|
|
"loss": 6.3509,
|
|
"mean_token_accuracy": 0.1268716983497143,
|
|
"num_tokens": 21577457.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 6.575533866882324,
|
|
"epoch": 1.0674193375782546,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004896166954111758,
|
|
"loss": 6.3518,
|
|
"mean_token_accuracy": 0.13707511276006698,
|
|
"num_tokens": 21588173.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 6.588746452331543,
|
|
"epoch": 1.0679544116860185,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048960521170637,
|
|
"loss": 6.3887,
|
|
"mean_token_accuracy": 0.12590450868010522,
|
|
"num_tokens": 21599154.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 6.571729278564453,
|
|
"epoch": 1.0684894857937826,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004895937218048692,
|
|
"loss": 6.4491,
|
|
"mean_token_accuracy": 0.12288791760802269,
|
|
"num_tokens": 21610134.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 6.5704535961151125,
|
|
"epoch": 1.0690245599015464,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004895822257070046,
|
|
"loss": 6.309,
|
|
"mean_token_accuracy": 0.12900600507855414,
|
|
"num_tokens": 21619989.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 6.536028575897217,
|
|
"epoch": 1.0695596340093103,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004895707234131084,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.13373802676796914,
|
|
"num_tokens": 21632707.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 6.564278316497803,
|
|
"epoch": 1.0700947081170742,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004895592149235128,
|
|
"loss": 6.3165,
|
|
"mean_token_accuracy": 0.13225629180669785,
|
|
"num_tokens": 21643001.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 6.630655241012573,
|
|
"epoch": 1.070629782224838,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048954770023855,
|
|
"loss": 6.3931,
|
|
"mean_token_accuracy": 0.12363598346710206,
|
|
"num_tokens": 21653425.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 6.645706844329834,
|
|
"epoch": 1.0711648563326022,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004895361793585525,
|
|
"loss": 6.4374,
|
|
"mean_token_accuracy": 0.12584138736128808,
|
|
"num_tokens": 21664212.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 6.593456697463989,
|
|
"epoch": 1.071699930440366,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004895246522838529,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.12775168418884278,
|
|
"num_tokens": 21675564.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 6.606023073196411,
|
|
"epoch": 1.07223500454813,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004895131190147842,
|
|
"loss": 6.4104,
|
|
"mean_token_accuracy": 0.12989913076162338,
|
|
"num_tokens": 21686225.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 6.614732122421264,
|
|
"epoch": 1.0727700786558938,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004895015795516793,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.13152774646878243,
|
|
"num_tokens": 21697479.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 6.662593936920166,
|
|
"epoch": 1.0733051527636577,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004894900338948714,
|
|
"loss": 6.4396,
|
|
"mean_token_accuracy": 0.12273435294628143,
|
|
"num_tokens": 21708496.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 6.58849720954895,
|
|
"epoch": 1.0738402268714218,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004894784820446939,
|
|
"loss": 6.2962,
|
|
"mean_token_accuracy": 0.1348871633410454,
|
|
"num_tokens": 21718290.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 6.56478476524353,
|
|
"epoch": 1.0743753009791857,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004894669240014804,
|
|
"loss": 6.3174,
|
|
"mean_token_accuracy": 0.12889463528990747,
|
|
"num_tokens": 21729185.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 6.566952323913574,
|
|
"epoch": 1.0749103750869495,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004894553597655646,
|
|
"loss": 6.3927,
|
|
"mean_token_accuracy": 0.12326682358980179,
|
|
"num_tokens": 21740787.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 6.655819940567016,
|
|
"epoch": 1.0754454491947134,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004894437893372804,
|
|
"loss": 6.4227,
|
|
"mean_token_accuracy": 0.1281476229429245,
|
|
"num_tokens": 21751804.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 6.729038047790527,
|
|
"epoch": 1.0759805233024773,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000489432212716962,
|
|
"loss": 6.3641,
|
|
"mean_token_accuracy": 0.1265849031507969,
|
|
"num_tokens": 21762730.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 6.587001895904541,
|
|
"epoch": 1.0765155974102414,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004894206299049436,
|
|
"loss": 6.391,
|
|
"mean_token_accuracy": 0.12952957078814506,
|
|
"num_tokens": 21773470.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 6.606532955169678,
|
|
"epoch": 1.0770506715180053,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004894090409015595,
|
|
"loss": 6.3892,
|
|
"mean_token_accuracy": 0.12596526369452477,
|
|
"num_tokens": 21783385.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 6.511558389663696,
|
|
"epoch": 1.0775857456257691,
|
|
"grad_norm": 7.78125,
|
|
"learning_rate": 0.0004893974457071445,
|
|
"loss": 6.4006,
|
|
"mean_token_accuracy": 0.12640529945492746,
|
|
"num_tokens": 21794857.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 6.646017694473267,
|
|
"epoch": 1.078120819733533,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004893858443220335,
|
|
"loss": 6.3921,
|
|
"mean_token_accuracy": 0.12531595304608345,
|
|
"num_tokens": 21804296.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 6.655510187149048,
|
|
"epoch": 1.0786558938412971,
|
|
"grad_norm": 7.34375,
|
|
"learning_rate": 0.0004893742367465613,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.12708523720502854,
|
|
"num_tokens": 21815899.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 6.662460279464722,
|
|
"epoch": 1.079190967949061,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004893626229810631,
|
|
"loss": 6.3835,
|
|
"mean_token_accuracy": 0.12776194885373116,
|
|
"num_tokens": 21825964.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 6.656799983978272,
|
|
"epoch": 1.0797260420568249,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004893510030258743,
|
|
"loss": 6.4491,
|
|
"mean_token_accuracy": 0.1254180334508419,
|
|
"num_tokens": 21836656.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 6.644039535522461,
|
|
"epoch": 1.0802611161645888,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004893393768813305,
|
|
"loss": 6.437,
|
|
"mean_token_accuracy": 0.1265450619161129,
|
|
"num_tokens": 21847658.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 6.653659963607788,
|
|
"epoch": 1.0807961902723526,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004893277445477673,
|
|
"loss": 6.4235,
|
|
"mean_token_accuracy": 0.12204527482390404,
|
|
"num_tokens": 21858338.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 6.574535751342774,
|
|
"epoch": 1.0813312643801167,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004893161060255206,
|
|
"loss": 6.291,
|
|
"mean_token_accuracy": 0.1317730188369751,
|
|
"num_tokens": 21870656.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 6.6015997409820555,
|
|
"epoch": 1.0818663384878806,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004893044613149263,
|
|
"loss": 6.3978,
|
|
"mean_token_accuracy": 0.13066271543502808,
|
|
"num_tokens": 21881806.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 6.533165979385376,
|
|
"epoch": 1.0824014125956445,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004892928104163209,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.12961009442806243,
|
|
"num_tokens": 21892277.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 6.499065113067627,
|
|
"epoch": 1.0829364867034084,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004892811533300407,
|
|
"loss": 6.3304,
|
|
"mean_token_accuracy": 0.12804820537567138,
|
|
"num_tokens": 21903509.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 6.629013204574585,
|
|
"epoch": 1.0834715608111725,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004892694900564223,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.12302088886499404,
|
|
"num_tokens": 21914308.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 6.572379779815674,
|
|
"epoch": 1.0840066349189363,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004892578205958025,
|
|
"loss": 6.3208,
|
|
"mean_token_accuracy": 0.1363232910633087,
|
|
"num_tokens": 21924302.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 6.557709884643555,
|
|
"epoch": 1.0845417090267002,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004892461449485182,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.1192793071269989,
|
|
"num_tokens": 21935066.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 6.571900272369385,
|
|
"epoch": 1.085076783134464,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004892344631149066,
|
|
"loss": 6.2866,
|
|
"mean_token_accuracy": 0.13518054634332657,
|
|
"num_tokens": 21945798.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 6.541820859909057,
|
|
"epoch": 1.085611857242228,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000489222775095305,
|
|
"loss": 6.3896,
|
|
"mean_token_accuracy": 0.12823085263371467,
|
|
"num_tokens": 21955667.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 6.534240627288819,
|
|
"epoch": 1.086146931349992,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004892110808900509,
|
|
"loss": 6.3838,
|
|
"mean_token_accuracy": 0.12837862819433213,
|
|
"num_tokens": 21966107.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 6.578744316101075,
|
|
"epoch": 1.086682005457756,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004891993804994818,
|
|
"loss": 6.3729,
|
|
"mean_token_accuracy": 0.13036210760474204,
|
|
"num_tokens": 21976408.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 6.70277099609375,
|
|
"epoch": 1.0872170795655198,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004891876739239358,
|
|
"loss": 6.3618,
|
|
"mean_token_accuracy": 0.12976597771048545,
|
|
"num_tokens": 21986481.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 6.663537120819091,
|
|
"epoch": 1.0877521536732837,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004891759611637508,
|
|
"loss": 6.416,
|
|
"mean_token_accuracy": 0.12483003661036492,
|
|
"num_tokens": 21997554.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 6.666103315353394,
|
|
"epoch": 1.0882872277810476,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000489164242219265,
|
|
"loss": 6.4746,
|
|
"mean_token_accuracy": 0.12223276570439338,
|
|
"num_tokens": 22009048.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 6.6567144870758055,
|
|
"epoch": 1.0888223018888117,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004891525170908169,
|
|
"loss": 6.4723,
|
|
"mean_token_accuracy": 0.12457619905471802,
|
|
"num_tokens": 22020625.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 6.641097497940064,
|
|
"epoch": 1.0893573759965756,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004891407857787448,
|
|
"loss": 6.349,
|
|
"mean_token_accuracy": 0.12083503529429436,
|
|
"num_tokens": 22032298.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 6.5712422847747805,
|
|
"epoch": 1.0898924501043394,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004891290482833876,
|
|
"loss": 6.3644,
|
|
"mean_token_accuracy": 0.12857181802392006,
|
|
"num_tokens": 22043693.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 6.592135095596314,
|
|
"epoch": 1.0904275242121033,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004891173046050844,
|
|
"loss": 6.4055,
|
|
"mean_token_accuracy": 0.13251589015126228,
|
|
"num_tokens": 22054373.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 6.5286545753479,
|
|
"epoch": 1.0909625983198672,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000489105554744174,
|
|
"loss": 6.3702,
|
|
"mean_token_accuracy": 0.12707970514893532,
|
|
"num_tokens": 22065039.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 6.616340780258179,
|
|
"epoch": 1.0914976724276313,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004890937987009958,
|
|
"loss": 6.4068,
|
|
"mean_token_accuracy": 0.12774839326739312,
|
|
"num_tokens": 22077003.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 6.661441898345947,
|
|
"epoch": 1.0920327465353952,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004890820364758892,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.1249889500439167,
|
|
"num_tokens": 22088558.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 6.66536431312561,
|
|
"epoch": 1.092567820643159,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000489070268069194,
|
|
"loss": 6.3759,
|
|
"mean_token_accuracy": 0.12962212786078453,
|
|
"num_tokens": 22097777.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 6.619532918930053,
|
|
"epoch": 1.093102894750923,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004890584934812498,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.12662954479455948,
|
|
"num_tokens": 22107803.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 6.526411151885986,
|
|
"epoch": 1.093637968858687,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004890467127123967,
|
|
"loss": 6.3021,
|
|
"mean_token_accuracy": 0.13266127556562424,
|
|
"num_tokens": 22117965.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 6.605463743209839,
|
|
"epoch": 1.094173042966451,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004890349257629749,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.12901197746396065,
|
|
"num_tokens": 22127759.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 6.6216710090637205,
|
|
"epoch": 1.0947081170742148,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004890231326333246,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.1223428912460804,
|
|
"num_tokens": 22138477.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 6.616352605819702,
|
|
"epoch": 1.0952431911819787,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004890113333237865,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.12796907275915145,
|
|
"num_tokens": 22149568.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 6.64321870803833,
|
|
"epoch": 1.0957782652897425,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004889995278347012,
|
|
"loss": 6.347,
|
|
"mean_token_accuracy": 0.12704193517565726,
|
|
"num_tokens": 22159949.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 6.565390157699585,
|
|
"epoch": 1.0963133393975066,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 6.3849,
|
|
"mean_token_accuracy": 0.12592787444591522,
|
|
"num_tokens": 22170115.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 6.579483222961426,
|
|
"epoch": 1.0968484135052705,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004889758983192528,
|
|
"loss": 6.4042,
|
|
"mean_token_accuracy": 0.1301763251423836,
|
|
"num_tokens": 22181323.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 6.56703815460205,
|
|
"epoch": 1.0973834876130344,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004889640742935719,
|
|
"loss": 6.3245,
|
|
"mean_token_accuracy": 0.12476136386394501,
|
|
"num_tokens": 22192078.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 6.648708009719849,
|
|
"epoch": 1.0979185617207983,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004889522440897085,
|
|
"loss": 6.4202,
|
|
"mean_token_accuracy": 0.12632420733571054,
|
|
"num_tokens": 22203211.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 6.604081630706787,
|
|
"epoch": 1.0984536358285624,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004889404077080041,
|
|
"loss": 6.327,
|
|
"mean_token_accuracy": 0.12216935753822326,
|
|
"num_tokens": 22213487.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 6.657914781570435,
|
|
"epoch": 1.0989887099363262,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004889285651488005,
|
|
"loss": 6.387,
|
|
"mean_token_accuracy": 0.12401374354958535,
|
|
"num_tokens": 22223717.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 6.600181579589844,
|
|
"epoch": 1.0995237840440901,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004889167164124396,
|
|
"loss": 6.3649,
|
|
"mean_token_accuracy": 0.13022887334227562,
|
|
"num_tokens": 22235141.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 6.630714845657349,
|
|
"epoch": 1.100058858151854,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004889048614992636,
|
|
"loss": 6.4352,
|
|
"mean_token_accuracy": 0.11634738221764565,
|
|
"num_tokens": 22246601.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 6.645396900177002,
|
|
"epoch": 1.1005939322596179,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004888930004096148,
|
|
"loss": 6.3683,
|
|
"mean_token_accuracy": 0.12525427788496019,
|
|
"num_tokens": 22257206.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 6.6107457160949705,
|
|
"epoch": 1.101129006367382,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004888811331438356,
|
|
"loss": 6.4418,
|
|
"mean_token_accuracy": 0.12160066962242126,
|
|
"num_tokens": 22267799.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 6.606397485733032,
|
|
"epoch": 1.1016640804751459,
|
|
"grad_norm": 5.15625,
|
|
"learning_rate": 0.0004888692597022689,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.12350900247693061,
|
|
"num_tokens": 22279368.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 6.566845941543579,
|
|
"epoch": 1.1021991545829097,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004888573800852572,
|
|
"loss": 6.2237,
|
|
"mean_token_accuracy": 0.13400836586952208,
|
|
"num_tokens": 22289998.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 6.556099796295166,
|
|
"epoch": 1.1027342286906736,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004888454942931438,
|
|
"loss": 6.3621,
|
|
"mean_token_accuracy": 0.13843812346458434,
|
|
"num_tokens": 22300058.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 6.605271577835083,
|
|
"epoch": 1.1032693027984375,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004888336023262718,
|
|
"loss": 6.4576,
|
|
"mean_token_accuracy": 0.12336159273982047,
|
|
"num_tokens": 22310962.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 6.632205390930176,
|
|
"epoch": 1.1038043769062016,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004888217041849846,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.12985207065939902,
|
|
"num_tokens": 22321526.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 6.6243726253509525,
|
|
"epoch": 1.1043394510139655,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004888097998696256,
|
|
"loss": 6.4115,
|
|
"mean_token_accuracy": 0.13042085766792297,
|
|
"num_tokens": 22332558.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 6.603054523468018,
|
|
"epoch": 1.1048745251217293,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004887978893805387,
|
|
"loss": 6.3712,
|
|
"mean_token_accuracy": 0.1283302277326584,
|
|
"num_tokens": 22342392.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 6.6153223514556885,
|
|
"epoch": 1.1054095992294932,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004887859727180679,
|
|
"loss": 6.4149,
|
|
"mean_token_accuracy": 0.12070412263274193,
|
|
"num_tokens": 22353089.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 6.595716142654419,
|
|
"epoch": 1.105944673337257,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.0004887740498825572,
|
|
"loss": 6.3403,
|
|
"mean_token_accuracy": 0.12909127920866012,
|
|
"num_tokens": 22364314.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 6.525272035598755,
|
|
"epoch": 1.1064797474450212,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.0004887621208743507,
|
|
"loss": 6.3615,
|
|
"mean_token_accuracy": 0.13097418546676637,
|
|
"num_tokens": 22374985.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 6.5705639839172365,
|
|
"epoch": 1.107014821552785,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004887501856937932,
|
|
"loss": 6.2735,
|
|
"mean_token_accuracy": 0.13664461746811868,
|
|
"num_tokens": 22385618.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 6.680104827880859,
|
|
"epoch": 1.107549895660549,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000488738244341229,
|
|
"loss": 6.3839,
|
|
"mean_token_accuracy": 0.13233611062169076,
|
|
"num_tokens": 22395871.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 6.594969797134399,
|
|
"epoch": 1.1080849697683128,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000488726296817003,
|
|
"loss": 6.4269,
|
|
"mean_token_accuracy": 0.12546478137373923,
|
|
"num_tokens": 22406707.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 6.579285478591919,
|
|
"epoch": 1.108620043876077,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004887143431214602,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.1295640639960766,
|
|
"num_tokens": 22417543.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 6.534362745285034,
|
|
"epoch": 1.1091551179838408,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004887023832549459,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.13080845177173614,
|
|
"num_tokens": 22428283.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 6.561671733856201,
|
|
"epoch": 1.1096901920916047,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004886904172178052,
|
|
"loss": 6.3404,
|
|
"mean_token_accuracy": 0.1269926555454731,
|
|
"num_tokens": 22439860.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 6.64477276802063,
|
|
"epoch": 1.1102252661993686,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004886784450103838,
|
|
"loss": 6.404,
|
|
"mean_token_accuracy": 0.13213484808802606,
|
|
"num_tokens": 22451250.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 6.621029949188232,
|
|
"epoch": 1.1107603403071324,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004886664666330273,
|
|
"loss": 6.3197,
|
|
"mean_token_accuracy": 0.12892655432224273,
|
|
"num_tokens": 22461112.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 6.620653581619263,
|
|
"epoch": 1.1112954144148965,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004886544820860816,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.13428678885102271,
|
|
"num_tokens": 22471368.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 6.593320989608765,
|
|
"epoch": 1.1118304885226604,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004886424913698927,
|
|
"loss": 6.3669,
|
|
"mean_token_accuracy": 0.12603677213191986,
|
|
"num_tokens": 22482011.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 6.531304836273193,
|
|
"epoch": 1.1123655626304243,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004886304944848069,
|
|
"loss": 6.3249,
|
|
"mean_token_accuracy": 0.13783786222338676,
|
|
"num_tokens": 22493648.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 6.640232563018799,
|
|
"epoch": 1.1129006367381882,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004886184914311706,
|
|
"loss": 6.4476,
|
|
"mean_token_accuracy": 0.11930759251117706,
|
|
"num_tokens": 22505577.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 6.6428056240081785,
|
|
"epoch": 1.1134357108459523,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004886064822093305,
|
|
"loss": 6.4195,
|
|
"mean_token_accuracy": 0.12181178033351898,
|
|
"num_tokens": 22515546.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 6.578192329406738,
|
|
"epoch": 1.1139707849537162,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004885944668196332,
|
|
"loss": 6.3138,
|
|
"mean_token_accuracy": 0.1319662280380726,
|
|
"num_tokens": 22526710.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 6.6135190486907955,
|
|
"epoch": 1.11450585906148,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004885824452624254,
|
|
"loss": 6.4374,
|
|
"mean_token_accuracy": 0.11792274415493012,
|
|
"num_tokens": 22537809.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 6.622402667999268,
|
|
"epoch": 1.115040933169244,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004885704175380548,
|
|
"loss": 6.4042,
|
|
"mean_token_accuracy": 0.12123099416494369,
|
|
"num_tokens": 22549301.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 6.6769884586334225,
|
|
"epoch": 1.1155760072770078,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 0.0004885583836468683,
|
|
"loss": 6.3303,
|
|
"mean_token_accuracy": 0.13196219727396966,
|
|
"num_tokens": 22560483.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 6.599582767486572,
|
|
"epoch": 1.1161110813847719,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004885463435892136,
|
|
"loss": 6.4035,
|
|
"mean_token_accuracy": 0.1265159696340561,
|
|
"num_tokens": 22570524.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 6.589896488189697,
|
|
"epoch": 1.1166461554925358,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000488534297365438,
|
|
"loss": 6.4059,
|
|
"mean_token_accuracy": 0.12564171403646468,
|
|
"num_tokens": 22581120.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 6.655992078781128,
|
|
"epoch": 1.1171812296002996,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004885222449758899,
|
|
"loss": 6.4118,
|
|
"mean_token_accuracy": 0.12271245792508126,
|
|
"num_tokens": 22592658.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 6.668973445892334,
|
|
"epoch": 1.1177163037080635,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004885101864209167,
|
|
"loss": 6.3644,
|
|
"mean_token_accuracy": 0.12713511735200883,
|
|
"num_tokens": 22603497.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 6.606515979766845,
|
|
"epoch": 1.1182513778158274,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000488498121700867,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.13579276204109192,
|
|
"num_tokens": 22612916.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 6.542640018463135,
|
|
"epoch": 1.1187864519235915,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004884860508160891,
|
|
"loss": 6.4072,
|
|
"mean_token_accuracy": 0.12952672243118285,
|
|
"num_tokens": 22625345.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 6.547324085235596,
|
|
"epoch": 1.1193215260313554,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004884739737669314,
|
|
"loss": 6.2989,
|
|
"mean_token_accuracy": 0.13511206805706025,
|
|
"num_tokens": 22637000.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 6.6149977684021,
|
|
"epoch": 1.1198566001391193,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004884618905537427,
|
|
"loss": 6.3108,
|
|
"mean_token_accuracy": 0.1349319562315941,
|
|
"num_tokens": 22647025.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 6.568778562545776,
|
|
"epoch": 1.1203916742468831,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004884498011768719,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.13271428719162942,
|
|
"num_tokens": 22657253.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 6.50206880569458,
|
|
"epoch": 1.120926748354647,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000488437705636668,
|
|
"loss": 6.3387,
|
|
"mean_token_accuracy": 0.1264503516256809,
|
|
"num_tokens": 22668432.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 6.574464559555054,
|
|
"epoch": 1.121461822462411,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004884256039334805,
|
|
"loss": 6.4163,
|
|
"mean_token_accuracy": 0.12530939951539039,
|
|
"num_tokens": 22678538.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 6.613846254348755,
|
|
"epoch": 1.121996896570175,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004884134960676586,
|
|
"loss": 6.3533,
|
|
"mean_token_accuracy": 0.12585252597928048,
|
|
"num_tokens": 22688994.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 6.66150279045105,
|
|
"epoch": 1.1225319706779389,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000488401382039552,
|
|
"loss": 6.4045,
|
|
"mean_token_accuracy": 0.1315431110560894,
|
|
"num_tokens": 22699584.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 6.586054182052612,
|
|
"epoch": 1.1230670447857027,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004883892618495104,
|
|
"loss": 6.3237,
|
|
"mean_token_accuracy": 0.12506790682673455,
|
|
"num_tokens": 22710093.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 6.54372091293335,
|
|
"epoch": 1.1236021188934668,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000488377135497884,
|
|
"loss": 6.389,
|
|
"mean_token_accuracy": 0.13032764345407485,
|
|
"num_tokens": 22720533.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 6.552872276306152,
|
|
"epoch": 1.1241371930012307,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004883650029850226,
|
|
"loss": 6.3004,
|
|
"mean_token_accuracy": 0.1326032653450966,
|
|
"num_tokens": 22731010.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 6.562661457061767,
|
|
"epoch": 1.1246722671089946,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004883528643112769,
|
|
"loss": 6.3849,
|
|
"mean_token_accuracy": 0.12769578397274017,
|
|
"num_tokens": 22743045.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 6.543094444274902,
|
|
"epoch": 1.1252073412167585,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004883407194769972,
|
|
"loss": 6.3658,
|
|
"mean_token_accuracy": 0.12816039398312568,
|
|
"num_tokens": 22753746.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 6.6191871643066404,
|
|
"epoch": 1.1257424153245223,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004883285684825342,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.13266870230436326,
|
|
"num_tokens": 22765264.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 6.674008798599243,
|
|
"epoch": 1.1262774894322864,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004883164113282386,
|
|
"loss": 6.386,
|
|
"mean_token_accuracy": 0.1327463336288929,
|
|
"num_tokens": 22775727.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 6.627488136291504,
|
|
"epoch": 1.1268125635400503,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004883042480144618,
|
|
"loss": 6.3888,
|
|
"mean_token_accuracy": 0.12605418637394905,
|
|
"num_tokens": 22787228.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 6.707489776611328,
|
|
"epoch": 1.1273476376478142,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004882920785415547,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.12728470787405968,
|
|
"num_tokens": 22797467.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 6.6242834568023685,
|
|
"epoch": 1.127882711755578,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004882799029098689,
|
|
"loss": 6.3947,
|
|
"mean_token_accuracy": 0.12601481676101683,
|
|
"num_tokens": 22808281.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 6.613295841217041,
|
|
"epoch": 1.1284177858633422,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048826772111975583,
|
|
"loss": 6.4402,
|
|
"mean_token_accuracy": 0.1277705155313015,
|
|
"num_tokens": 22819387.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 6.557784986495972,
|
|
"epoch": 1.128952859971106,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048825553317156717,
|
|
"loss": 6.3985,
|
|
"mean_token_accuracy": 0.12802883014082908,
|
|
"num_tokens": 22829649.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 6.531251573562622,
|
|
"epoch": 1.12948793407887,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004882433390656551,
|
|
"loss": 6.3771,
|
|
"mean_token_accuracy": 0.13570220544934272,
|
|
"num_tokens": 22840667.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 6.582296466827392,
|
|
"epoch": 1.1300230081866338,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004882311388023715,
|
|
"loss": 6.3438,
|
|
"mean_token_accuracy": 0.13229678571224213,
|
|
"num_tokens": 22852461.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 6.660343647003174,
|
|
"epoch": 1.1305580822943977,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004882189323820688,
|
|
"loss": 6.4062,
|
|
"mean_token_accuracy": 0.12644702941179276,
|
|
"num_tokens": 22862781.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 6.689817905426025,
|
|
"epoch": 1.1310931564021618,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00048820671980509935,
|
|
"loss": 6.447,
|
|
"mean_token_accuracy": 0.12604032903909684,
|
|
"num_tokens": 22873393.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 6.673664236068726,
|
|
"epoch": 1.1316282305099257,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048819450107181583,
|
|
"loss": 6.405,
|
|
"mean_token_accuracy": 0.12774647176265716,
|
|
"num_tokens": 22883931.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 6.643437004089355,
|
|
"epoch": 1.1321633046176895,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004881822761825711,
|
|
"loss": 6.3606,
|
|
"mean_token_accuracy": 0.12672000154852867,
|
|
"num_tokens": 22894829.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 6.576650190353393,
|
|
"epoch": 1.1326983787254534,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.000488170045137718,
|
|
"loss": 6.4128,
|
|
"mean_token_accuracy": 0.12564155831933022,
|
|
"num_tokens": 22906059.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 6.61072793006897,
|
|
"epoch": 1.1332334528332173,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004881578079376099,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.12437209784984589,
|
|
"num_tokens": 22917834.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 6.602422142028809,
|
|
"epoch": 1.1337685269409814,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048814556458259996,
|
|
"loss": 6.3032,
|
|
"mean_token_accuracy": 0.13898573443293571,
|
|
"num_tokens": 22929157.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 6.699093055725098,
|
|
"epoch": 1.1343036010487453,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004881333150730419,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.12713947594165803,
|
|
"num_tokens": 22939396.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 6.633609819412231,
|
|
"epoch": 1.1348386751565092,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048812105940928917,
|
|
"loss": 6.4059,
|
|
"mean_token_accuracy": 0.12925138995051383,
|
|
"num_tokens": 22950253.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 6.593989610671997,
|
|
"epoch": 1.135373749264273,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048810879759169593,
|
|
"loss": 6.3921,
|
|
"mean_token_accuracy": 0.13002119585871696,
|
|
"num_tokens": 22960417.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 6.500380373001098,
|
|
"epoch": 1.135908823372037,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000488096529620616,
|
|
"loss": 6.4093,
|
|
"mean_token_accuracy": 0.12384607344865799,
|
|
"num_tokens": 22971763.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 6.6615125179290775,
|
|
"epoch": 1.136443897479801,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00048808425549640383,
|
|
"loss": 6.4073,
|
|
"mean_token_accuracy": 0.12944543585181237,
|
|
"num_tokens": 22981571.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 6.675753545761109,
|
|
"epoch": 1.136978971587565,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048807197521941366,
|
|
"loss": 6.3671,
|
|
"mean_token_accuracy": 0.13062579929828644,
|
|
"num_tokens": 22991644.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 6.570114517211914,
|
|
"epoch": 1.1375140456953288,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004880596887900002,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.13275415301322938,
|
|
"num_tokens": 23001557.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 6.569275569915772,
|
|
"epoch": 1.1380491198030926,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048804739620851806,
|
|
"loss": 6.4096,
|
|
"mean_token_accuracy": 0.1243378646671772,
|
|
"num_tokens": 23012715.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 6.604267311096192,
|
|
"epoch": 1.1385841939108567,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048803509747532235,
|
|
"loss": 6.394,
|
|
"mean_token_accuracy": 0.1274212308228016,
|
|
"num_tokens": 23023016.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 6.6237279891967775,
|
|
"epoch": 1.1391192680186206,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004880227925907682,
|
|
"loss": 6.4135,
|
|
"mean_token_accuracy": 0.12478863894939422,
|
|
"num_tokens": 23033511.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 6.658384037017822,
|
|
"epoch": 1.1396543421263845,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004880104815552108,
|
|
"loss": 6.4015,
|
|
"mean_token_accuracy": 0.13616229668259622,
|
|
"num_tokens": 23045149.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 6.564808702468872,
|
|
"epoch": 1.1401894162341484,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004879981643690056,
|
|
"loss": 6.3508,
|
|
"mean_token_accuracy": 0.13405006006360054,
|
|
"num_tokens": 23054489.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 6.6384093284606935,
|
|
"epoch": 1.1407244903419125,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048798584103250847,
|
|
"loss": 6.4896,
|
|
"mean_token_accuracy": 0.11965025290846824,
|
|
"num_tokens": 23064725.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 6.6000292778015135,
|
|
"epoch": 1.1412595644496764,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000487973511546075,
|
|
"loss": 6.4304,
|
|
"mean_token_accuracy": 0.12639181837439536,
|
|
"num_tokens": 23076473.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 6.651229572296143,
|
|
"epoch": 1.1417946385574402,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004879611759100614,
|
|
"loss": 6.3686,
|
|
"mean_token_accuracy": 0.13827985227108003,
|
|
"num_tokens": 23087449.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 6.659745979309082,
|
|
"epoch": 1.1423297126652041,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004879488341248237,
|
|
"loss": 6.3358,
|
|
"mean_token_accuracy": 0.1292405381798744,
|
|
"num_tokens": 23098284.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 6.608740568161011,
|
|
"epoch": 1.142864786772968,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048793648619071834,
|
|
"loss": 6.3425,
|
|
"mean_token_accuracy": 0.13234004527330398,
|
|
"num_tokens": 23108545.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 6.575946092605591,
|
|
"epoch": 1.143399860880732,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004879241321081019,
|
|
"loss": 6.3228,
|
|
"mean_token_accuracy": 0.1296264797449112,
|
|
"num_tokens": 23118568.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 6.621288585662842,
|
|
"epoch": 1.143934934988496,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.00048791177187733104,
|
|
"loss": 6.4104,
|
|
"mean_token_accuracy": 0.12180029302835464,
|
|
"num_tokens": 23129189.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 6.672067070007325,
|
|
"epoch": 1.1444700090962598,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004878994054987627,
|
|
"loss": 6.4369,
|
|
"mean_token_accuracy": 0.1265236847102642,
|
|
"num_tokens": 23140238.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 6.587863540649414,
|
|
"epoch": 1.1450050832040237,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004878870329727539,
|
|
"loss": 6.3232,
|
|
"mean_token_accuracy": 0.13250792399048805,
|
|
"num_tokens": 23149567.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 6.5830559730529785,
|
|
"epoch": 1.1455401573117876,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000487874654299662,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.12958085983991624,
|
|
"num_tokens": 23159208.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 6.543132019042969,
|
|
"epoch": 1.1460752314195517,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048786226947984435,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.12850967571139335,
|
|
"num_tokens": 23169092.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 6.562094211578369,
|
|
"epoch": 1.1466103055273156,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004878498785136586,
|
|
"loss": 6.3701,
|
|
"mean_token_accuracy": 0.13058268800377845,
|
|
"num_tokens": 23180385.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 6.6576474666595455,
|
|
"epoch": 1.1471453796350795,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048783748140146245,
|
|
"loss": 6.3759,
|
|
"mean_token_accuracy": 0.12697793394327164,
|
|
"num_tokens": 23191180.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 6.6301532745361325,
|
|
"epoch": 1.1476804537428433,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000487825078143614,
|
|
"loss": 6.3474,
|
|
"mean_token_accuracy": 0.13232842609286308,
|
|
"num_tokens": 23200920.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 6.616117000579834,
|
|
"epoch": 1.1482155278506072,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004878126687404713,
|
|
"loss": 6.3574,
|
|
"mean_token_accuracy": 0.13337452784180642,
|
|
"num_tokens": 23211140.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 6.566322898864746,
|
|
"epoch": 1.1487506019583713,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004878002531923927,
|
|
"loss": 6.414,
|
|
"mean_token_accuracy": 0.12017728760838509,
|
|
"num_tokens": 23222039.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 6.643358373641968,
|
|
"epoch": 1.1492856760661352,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048778783149973674,
|
|
"loss": 6.4396,
|
|
"mean_token_accuracy": 0.12307033240795136,
|
|
"num_tokens": 23232502.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 6.716522645950318,
|
|
"epoch": 1.149820750173899,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048777540366286195,
|
|
"loss": 6.3625,
|
|
"mean_token_accuracy": 0.12469939589500427,
|
|
"num_tokens": 23243172.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 6.707009792327881,
|
|
"epoch": 1.150355824281663,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004877629696821273,
|
|
"loss": 6.4163,
|
|
"mean_token_accuracy": 0.12468718886375427,
|
|
"num_tokens": 23254558.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 6.701622581481933,
|
|
"epoch": 1.1508908983894268,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048775052955789185,
|
|
"loss": 6.4411,
|
|
"mean_token_accuracy": 0.12828221768140793,
|
|
"num_tokens": 23266283.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 6.531945371627808,
|
|
"epoch": 1.151425972497191,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004877380832905147,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.13032052889466286,
|
|
"num_tokens": 23277823.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 6.521464061737061,
|
|
"epoch": 1.1519610466049548,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.00048772563088035533,
|
|
"loss": 6.3154,
|
|
"mean_token_accuracy": 0.12795528769493103,
|
|
"num_tokens": 23288159.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 6.571771097183228,
|
|
"epoch": 1.1524961207127187,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004877131723277732,
|
|
"loss": 6.3294,
|
|
"mean_token_accuracy": 0.12732245847582818,
|
|
"num_tokens": 23299379.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 6.620853900909424,
|
|
"epoch": 1.1530311948204826,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004877007076331282,
|
|
"loss": 6.3653,
|
|
"mean_token_accuracy": 0.12556742504239082,
|
|
"num_tokens": 23310572.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 6.638435411453247,
|
|
"epoch": 1.1535662689282467,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004876882367967801,
|
|
"loss": 6.3685,
|
|
"mean_token_accuracy": 0.13028644844889642,
|
|
"num_tokens": 23320782.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 6.582970190048218,
|
|
"epoch": 1.1541013430360105,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048767575981908907,
|
|
"loss": 6.4278,
|
|
"mean_token_accuracy": 0.12447980940341949,
|
|
"num_tokens": 23331427.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 6.636680555343628,
|
|
"epoch": 1.1546364171437744,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048766327670041534,
|
|
"loss": 6.532,
|
|
"mean_token_accuracy": 0.11941971704363823,
|
|
"num_tokens": 23344250.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 6.686970233917236,
|
|
"epoch": 1.1551714912515383,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004876507874411194,
|
|
"loss": 6.3996,
|
|
"mean_token_accuracy": 0.1299537844955921,
|
|
"num_tokens": 23354404.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 6.617187023162842,
|
|
"epoch": 1.1557065653593024,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048763829204156187,
|
|
"loss": 6.4039,
|
|
"mean_token_accuracy": 0.11933726742863655,
|
|
"num_tokens": 23364634.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 6.502858734130859,
|
|
"epoch": 1.1562416394670663,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048762579050210344,
|
|
"loss": 6.2606,
|
|
"mean_token_accuracy": 0.13445552960038185,
|
|
"num_tokens": 23375816.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 6.626778936386108,
|
|
"epoch": 1.1567767135748301,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00048761328282310534,
|
|
"loss": 6.3972,
|
|
"mean_token_accuracy": 0.12917689681053163,
|
|
"num_tokens": 23386583.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 6.550615930557251,
|
|
"epoch": 1.157311787682594,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048760076900492846,
|
|
"loss": 6.3157,
|
|
"mean_token_accuracy": 0.13703981265425683,
|
|
"num_tokens": 23396826.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 6.581752967834473,
|
|
"epoch": 1.157846861790358,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004875882490479343,
|
|
"loss": 6.4222,
|
|
"mean_token_accuracy": 0.12861482873559,
|
|
"num_tokens": 23408661.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 6.586452674865723,
|
|
"epoch": 1.158381935898122,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048757572295248425,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.12771003544330597,
|
|
"num_tokens": 23419308.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 6.55066819190979,
|
|
"epoch": 1.1589170100058859,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004875631907189402,
|
|
"loss": 6.3361,
|
|
"mean_token_accuracy": 0.1366964891552925,
|
|
"num_tokens": 23430043.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 6.522685241699219,
|
|
"epoch": 1.1594520841136498,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004875506523476638,
|
|
"loss": 6.2606,
|
|
"mean_token_accuracy": 0.1345066875219345,
|
|
"num_tokens": 23441246.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 6.6081029891967775,
|
|
"epoch": 1.1599871582214136,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048753810783901716,
|
|
"loss": 6.4176,
|
|
"mean_token_accuracy": 0.1228659138083458,
|
|
"num_tokens": 23452250.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 6.604149436950683,
|
|
"epoch": 1.1605222323291775,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00048752555719336257,
|
|
"loss": 6.3823,
|
|
"mean_token_accuracy": 0.1303229622542858,
|
|
"num_tokens": 23464174.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 6.560730218887329,
|
|
"epoch": 1.1610573064369416,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004875130004110623,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.131521575152874,
|
|
"num_tokens": 23475159.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 6.563075828552246,
|
|
"epoch": 1.1615923805447055,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.00048750043749247907,
|
|
"loss": 6.3166,
|
|
"mean_token_accuracy": 0.13398068472743035,
|
|
"num_tokens": 23486210.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 6.582678699493409,
|
|
"epoch": 1.1621274546524694,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004874878684379756,
|
|
"loss": 6.4425,
|
|
"mean_token_accuracy": 0.12680857703089715,
|
|
"num_tokens": 23497122.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 6.545470142364502,
|
|
"epoch": 1.1626625287602332,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004874752932479148,
|
|
"loss": 6.2502,
|
|
"mean_token_accuracy": 0.1373693734407425,
|
|
"num_tokens": 23507765.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 6.651904487609864,
|
|
"epoch": 1.1631976028679971,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048746271192265974,
|
|
"loss": 6.3421,
|
|
"mean_token_accuracy": 0.1307779908180237,
|
|
"num_tokens": 23517686.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 6.558163738250732,
|
|
"epoch": 1.1637326769757612,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004874501244625737,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.12777699157595634,
|
|
"num_tokens": 23528325.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 6.571179628372192,
|
|
"epoch": 1.164267751083525,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004874375308680202,
|
|
"loss": 6.4075,
|
|
"mean_token_accuracy": 0.12609270066022873,
|
|
"num_tokens": 23540006.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 6.655467510223389,
|
|
"epoch": 1.164802825191289,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048742493113936274,
|
|
"loss": 6.3347,
|
|
"mean_token_accuracy": 0.12938966676592828,
|
|
"num_tokens": 23550419.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 6.691969966888427,
|
|
"epoch": 1.1653378992990528,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004874123252769653,
|
|
"loss": 6.45,
|
|
"mean_token_accuracy": 0.12153846248984337,
|
|
"num_tokens": 23561227.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 6.654784536361694,
|
|
"epoch": 1.1658729734068167,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048739971328119194,
|
|
"loss": 6.3608,
|
|
"mean_token_accuracy": 0.12869727611541748,
|
|
"num_tokens": 23571357.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 6.593526411056518,
|
|
"epoch": 1.1664080475145808,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004873870951524066,
|
|
"loss": 6.3986,
|
|
"mean_token_accuracy": 0.1263137772679329,
|
|
"num_tokens": 23581875.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 6.58023099899292,
|
|
"epoch": 1.1669431216223447,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048737447089097373,
|
|
"loss": 6.4696,
|
|
"mean_token_accuracy": 0.12290235683321953,
|
|
"num_tokens": 23594251.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 6.611230707168579,
|
|
"epoch": 1.1674781957301086,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004873618404972579,
|
|
"loss": 6.3918,
|
|
"mean_token_accuracy": 0.12422449067234993,
|
|
"num_tokens": 23605159.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 6.6689088344573975,
|
|
"epoch": 1.1680132698378725,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.00048734920397162376,
|
|
"loss": 6.3356,
|
|
"mean_token_accuracy": 0.1333016961812973,
|
|
"num_tokens": 23615737.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 6.592845249176025,
|
|
"epoch": 1.1685483439456366,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004873365613144361,
|
|
"loss": 6.352,
|
|
"mean_token_accuracy": 0.12838603630661966,
|
|
"num_tokens": 23626207.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 6.589870357513428,
|
|
"epoch": 1.1690834180534004,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004873239125260602,
|
|
"loss": 6.3924,
|
|
"mean_token_accuracy": 0.1289132535457611,
|
|
"num_tokens": 23637900.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 6.651250553131104,
|
|
"epoch": 1.1696184921611643,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048731125760686106,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.1328061528503895,
|
|
"num_tokens": 23647867.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 6.662811326980591,
|
|
"epoch": 1.1701535662689282,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048729859655720424,
|
|
"loss": 6.3678,
|
|
"mean_token_accuracy": 0.12671908512711524,
|
|
"num_tokens": 23658055.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 6.548589468002319,
|
|
"epoch": 1.1706886403766923,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004872859293774553,
|
|
"loss": 6.3515,
|
|
"mean_token_accuracy": 0.12935460954904557,
|
|
"num_tokens": 23669458.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 6.552815532684326,
|
|
"epoch": 1.1712237144844562,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.00048727325606797995,
|
|
"loss": 6.3774,
|
|
"mean_token_accuracy": 0.12226021885871888,
|
|
"num_tokens": 23679702.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 6.627586698532104,
|
|
"epoch": 1.17175878859222,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004872605766291441,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.12570433542132378,
|
|
"num_tokens": 23690844.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 6.537343597412109,
|
|
"epoch": 1.172293862699984,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000487247891061314,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.12790419906377792,
|
|
"num_tokens": 23701484.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 6.67474398612976,
|
|
"epoch": 1.1728289368077478,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004872351993648559,
|
|
"loss": 6.3889,
|
|
"mean_token_accuracy": 0.12645611688494682,
|
|
"num_tokens": 23711452.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 6.588062715530396,
|
|
"epoch": 1.173364010915512,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048722250154013613,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.12199438139796256,
|
|
"num_tokens": 23723514.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 6.6275921821594235,
|
|
"epoch": 1.1738990850232758,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004872097975875216,
|
|
"loss": 6.405,
|
|
"mean_token_accuracy": 0.12808311581611634,
|
|
"num_tokens": 23733722.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 6.681855058670044,
|
|
"epoch": 1.1744341591310397,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004871970875073789,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.12543651163578035,
|
|
"num_tokens": 23743403.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 6.646767663955688,
|
|
"epoch": 1.1749692332388035,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004871843713000751,
|
|
"loss": 6.3503,
|
|
"mean_token_accuracy": 0.12466617599129677,
|
|
"num_tokens": 23754558.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 6.661968851089478,
|
|
"epoch": 1.1755043073465674,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048717164896597737,
|
|
"loss": 6.3952,
|
|
"mean_token_accuracy": 0.12986711263656617,
|
|
"num_tokens": 23766346.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 6.601209402084351,
|
|
"epoch": 1.1760393814543315,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004871589205054532,
|
|
"loss": 6.3714,
|
|
"mean_token_accuracy": 0.13791783154010773,
|
|
"num_tokens": 23776851.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 6.610412359237671,
|
|
"epoch": 1.1765744555620954,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048714618591886997,
|
|
"loss": 6.4398,
|
|
"mean_token_accuracy": 0.12396790236234664,
|
|
"num_tokens": 23787350.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 6.538012742996216,
|
|
"epoch": 1.1771095296698593,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004871334452065954,
|
|
"loss": 6.2849,
|
|
"mean_token_accuracy": 0.12836700007319451,
|
|
"num_tokens": 23797738.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 6.599735832214355,
|
|
"epoch": 1.1776446037776231,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004871206983689974,
|
|
"loss": 6.3028,
|
|
"mean_token_accuracy": 0.13486284464597703,
|
|
"num_tokens": 23809516.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 6.65482087135315,
|
|
"epoch": 1.178179677885387,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000487107945406444,
|
|
"loss": 6.3701,
|
|
"mean_token_accuracy": 0.13080040067434312,
|
|
"num_tokens": 23819850.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 6.607937145233154,
|
|
"epoch": 1.1787147519931511,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004870951863193036,
|
|
"loss": 6.3597,
|
|
"mean_token_accuracy": 0.13374439626932144,
|
|
"num_tokens": 23829891.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 6.523252391815186,
|
|
"epoch": 1.179249826100915,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004870824211079444,
|
|
"loss": 6.3163,
|
|
"mean_token_accuracy": 0.1344559371471405,
|
|
"num_tokens": 23840816.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 6.618854188919068,
|
|
"epoch": 1.1797849002086789,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048706964977273515,
|
|
"loss": 6.4156,
|
|
"mean_token_accuracy": 0.12290649190545082,
|
|
"num_tokens": 23852595.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 6.681303024291992,
|
|
"epoch": 1.1803199743164428,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048705687231404455,
|
|
"loss": 6.4103,
|
|
"mean_token_accuracy": 0.12458204254508018,
|
|
"num_tokens": 23863048.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 6.6757519245147705,
|
|
"epoch": 1.1808550484242066,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048704408873224156,
|
|
"loss": 6.3804,
|
|
"mean_token_accuracy": 0.130190596729517,
|
|
"num_tokens": 23873499.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 6.595027875900269,
|
|
"epoch": 1.1813901225319707,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048703129902769526,
|
|
"loss": 6.305,
|
|
"mean_token_accuracy": 0.13430339694023133,
|
|
"num_tokens": 23885129.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 6.666780185699463,
|
|
"epoch": 1.1819251966397346,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004870185032007751,
|
|
"loss": 6.4152,
|
|
"mean_token_accuracy": 0.12456584721803665,
|
|
"num_tokens": 23895538.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 6.617560958862304,
|
|
"epoch": 1.1824602707474985,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004870057012518504,
|
|
"loss": 6.4379,
|
|
"mean_token_accuracy": 0.12211228385567666,
|
|
"num_tokens": 23907341.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 6.551357364654541,
|
|
"epoch": 1.1829953448552624,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048699289318129087,
|
|
"loss": 6.2787,
|
|
"mean_token_accuracy": 0.13694006204605103,
|
|
"num_tokens": 23918501.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 6.653029346466065,
|
|
"epoch": 1.1835304189630265,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004869800789894663,
|
|
"loss": 6.3677,
|
|
"mean_token_accuracy": 0.12978087961673737,
|
|
"num_tokens": 23929204.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 6.632968091964722,
|
|
"epoch": 1.1840654930707903,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004869672586767468,
|
|
"loss": 6.4225,
|
|
"mean_token_accuracy": 0.12734040170907973,
|
|
"num_tokens": 23939855.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 6.637135362625122,
|
|
"epoch": 1.1846005671785542,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004869544322435024,
|
|
"loss": 6.3427,
|
|
"mean_token_accuracy": 0.1291130594909191,
|
|
"num_tokens": 23949871.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 6.6302248477935795,
|
|
"epoch": 1.185135641286318,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004869415996901036,
|
|
"loss": 6.4512,
|
|
"mean_token_accuracy": 0.12094607204198837,
|
|
"num_tokens": 23961650.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 6.676426124572754,
|
|
"epoch": 1.1856707153940822,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004869287610169209,
|
|
"loss": 6.4478,
|
|
"mean_token_accuracy": 0.12562597095966338,
|
|
"num_tokens": 23973103.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 6.654819202423096,
|
|
"epoch": 1.186205789501846,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.000486915916224325,
|
|
"loss": 6.385,
|
|
"mean_token_accuracy": 0.1296301566064358,
|
|
"num_tokens": 23982972.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 6.592878293991089,
|
|
"epoch": 1.18674086360961,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004869030653126868,
|
|
"loss": 6.2614,
|
|
"mean_token_accuracy": 0.13468108847737312,
|
|
"num_tokens": 23993044.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 6.6300498962402346,
|
|
"epoch": 1.1872759377173738,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004868902082823774,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.1301009513437748,
|
|
"num_tokens": 24003871.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 6.595417213439942,
|
|
"epoch": 1.1878110118251377,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004868773451337679,
|
|
"loss": 6.3817,
|
|
"mean_token_accuracy": 0.12345974296331405,
|
|
"num_tokens": 24014613.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 6.604805326461792,
|
|
"epoch": 1.1883460859329018,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048686447586722995,
|
|
"loss": 6.3793,
|
|
"mean_token_accuracy": 0.130336894094944,
|
|
"num_tokens": 24024172.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 6.637345170974731,
|
|
"epoch": 1.1888811600406657,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048685160048313506,
|
|
"loss": 6.5175,
|
|
"mean_token_accuracy": 0.12139771580696106,
|
|
"num_tokens": 24035301.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 6.710483884811401,
|
|
"epoch": 1.1894162341484296,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048683871898185486,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.1363987222313881,
|
|
"num_tokens": 24045661.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 6.582315444946289,
|
|
"epoch": 1.1899513082561934,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048682583136376145,
|
|
"loss": 6.3668,
|
|
"mean_token_accuracy": 0.12603660821914672,
|
|
"num_tokens": 24057027.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 6.597838354110718,
|
|
"epoch": 1.1904863823639573,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004868129376292269,
|
|
"loss": 6.4618,
|
|
"mean_token_accuracy": 0.1248090460896492,
|
|
"num_tokens": 24068322.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 6.633081293106079,
|
|
"epoch": 1.1910214564717214,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048680003777862356,
|
|
"loss": 6.3207,
|
|
"mean_token_accuracy": 0.1326053723692894,
|
|
"num_tokens": 24078506.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 6.653125905990601,
|
|
"epoch": 1.1915565305794853,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048678713181232394,
|
|
"loss": 6.3315,
|
|
"mean_token_accuracy": 0.12817228808999062,
|
|
"num_tokens": 24090296.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 6.5576629638671875,
|
|
"epoch": 1.1920916046872492,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048677421973070063,
|
|
"loss": 6.3476,
|
|
"mean_token_accuracy": 0.12494271770119666,
|
|
"num_tokens": 24101478.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 6.59868016242981,
|
|
"epoch": 1.192626678795013,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.00048676130153412644,
|
|
"loss": 6.3896,
|
|
"mean_token_accuracy": 0.12669438794255256,
|
|
"num_tokens": 24112552.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 6.575451040267945,
|
|
"epoch": 1.193161752902777,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004867483772229745,
|
|
"loss": 6.2877,
|
|
"mean_token_accuracy": 0.132377078384161,
|
|
"num_tokens": 24124210.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 6.666009473800659,
|
|
"epoch": 1.193696827010541,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004867354467976178,
|
|
"loss": 6.3657,
|
|
"mean_token_accuracy": 0.1264978066086769,
|
|
"num_tokens": 24133525.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 6.622276496887207,
|
|
"epoch": 1.194231901118305,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048672251025842994,
|
|
"loss": 6.4283,
|
|
"mean_token_accuracy": 0.12235869392752648,
|
|
"num_tokens": 24145400.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 6.581037616729736,
|
|
"epoch": 1.1947669752260688,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004867095676057843,
|
|
"loss": 6.4043,
|
|
"mean_token_accuracy": 0.12346582114696503,
|
|
"num_tokens": 24155596.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 6.660838317871094,
|
|
"epoch": 1.1953020493338327,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048669661884005467,
|
|
"loss": 6.411,
|
|
"mean_token_accuracy": 0.11990564540028573,
|
|
"num_tokens": 24166683.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 6.6620251655578615,
|
|
"epoch": 1.1958371234415965,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.00048668366396161503,
|
|
"loss": 6.3484,
|
|
"mean_token_accuracy": 0.1324770301580429,
|
|
"num_tokens": 24177649.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 6.6482642650604244,
|
|
"epoch": 1.1963721975493606,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004866707029708392,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.13680849149823188,
|
|
"num_tokens": 24188522.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 6.629755258560181,
|
|
"epoch": 1.1969072716571245,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004866577358681015,
|
|
"loss": 6.351,
|
|
"mean_token_accuracy": 0.12546053379774094,
|
|
"num_tokens": 24199285.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 6.555999279022217,
|
|
"epoch": 1.1974423457648884,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004866447626537765,
|
|
"loss": 6.315,
|
|
"mean_token_accuracy": 0.1288013204932213,
|
|
"num_tokens": 24210929.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 6.597998905181885,
|
|
"epoch": 1.1979774198726523,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004866317833282387,
|
|
"loss": 6.3896,
|
|
"mean_token_accuracy": 0.13132332861423493,
|
|
"num_tokens": 24221394.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 6.6404284000396725,
|
|
"epoch": 1.1985124939804164,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048661879789186295,
|
|
"loss": 6.3409,
|
|
"mean_token_accuracy": 0.13481015786528588,
|
|
"num_tokens": 24230297.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 6.588724660873413,
|
|
"epoch": 1.1990475680881802,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.00048660580634502415,
|
|
"loss": 6.4806,
|
|
"mean_token_accuracy": 0.12437879964709282,
|
|
"num_tokens": 24241505.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 6.604456233978271,
|
|
"epoch": 1.1995826421959441,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048659280868809744,
|
|
"loss": 6.3351,
|
|
"mean_token_accuracy": 0.13336351290345191,
|
|
"num_tokens": 24252638.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 6.589144515991211,
|
|
"epoch": 1.200117716303708,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000486579804921458,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.13022335022687911,
|
|
"num_tokens": 24263156.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 6.539801502227784,
|
|
"epoch": 1.200652790411472,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048656679504548145,
|
|
"loss": 6.2507,
|
|
"mean_token_accuracy": 0.13899135142564772,
|
|
"num_tokens": 24274384.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 6.652301454544068,
|
|
"epoch": 1.201187864519236,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004865537790605435,
|
|
"loss": 6.4635,
|
|
"mean_token_accuracy": 0.1245289646089077,
|
|
"num_tokens": 24285159.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 6.666200160980225,
|
|
"epoch": 1.2017229386269999,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004865407569670198,
|
|
"loss": 6.42,
|
|
"mean_token_accuracy": 0.12417516931891441,
|
|
"num_tokens": 24296202.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 6.625790357589722,
|
|
"epoch": 1.2022580127347637,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004865277287652866,
|
|
"loss": 6.352,
|
|
"mean_token_accuracy": 0.1277849294245243,
|
|
"num_tokens": 24306691.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 6.56063323020935,
|
|
"epoch": 1.2027930868425276,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004865146944557199,
|
|
"loss": 6.3749,
|
|
"mean_token_accuracy": 0.1308102548122406,
|
|
"num_tokens": 24317499.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 6.608167600631714,
|
|
"epoch": 1.2033281609502917,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004865016540386961,
|
|
"loss": 6.3711,
|
|
"mean_token_accuracy": 0.12457039803266526,
|
|
"num_tokens": 24328096.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 6.64035701751709,
|
|
"epoch": 1.2038632350580556,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048648860751459173,
|
|
"loss": 6.3564,
|
|
"mean_token_accuracy": 0.12415970861911774,
|
|
"num_tokens": 24338188.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 6.611950922012329,
|
|
"epoch": 1.2043983091658195,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048647555488378355,
|
|
"loss": 6.3912,
|
|
"mean_token_accuracy": 0.1370738387107849,
|
|
"num_tokens": 24348578.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 6.581535959243775,
|
|
"epoch": 1.2049333832735833,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004864624961466485,
|
|
"loss": 6.3799,
|
|
"mean_token_accuracy": 0.13450479954481126,
|
|
"num_tokens": 24358807.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 6.5819176197052,
|
|
"epoch": 1.2054684573813472,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004864494313035635,
|
|
"loss": 6.3885,
|
|
"mean_token_accuracy": 0.12351802438497543,
|
|
"num_tokens": 24369074.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 6.627604293823242,
|
|
"epoch": 1.2060035314891113,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.000486436360354906,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.13293164372444152,
|
|
"num_tokens": 24380655.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 6.652128982543945,
|
|
"epoch": 1.2065386055968752,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.00048642328330105323,
|
|
"loss": 6.3561,
|
|
"mean_token_accuracy": 0.12492936700582505,
|
|
"num_tokens": 24391701.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 6.520333623886108,
|
|
"epoch": 1.207073679704639,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.00048641020014238286,
|
|
"loss": 6.4191,
|
|
"mean_token_accuracy": 0.12641558945178985,
|
|
"num_tokens": 24403690.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 6.633807373046875,
|
|
"epoch": 1.207608753812403,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004863971108792727,
|
|
"loss": 6.4001,
|
|
"mean_token_accuracy": 0.12829528376460075,
|
|
"num_tokens": 24414670.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 6.6214869022369385,
|
|
"epoch": 1.2081438279201668,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00048638401551210063,
|
|
"loss": 6.4542,
|
|
"mean_token_accuracy": 0.11909786760807037,
|
|
"num_tokens": 24425237.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 6.663760662078857,
|
|
"epoch": 1.208678902027931,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.00048637091404124484,
|
|
"loss": 6.406,
|
|
"mean_token_accuracy": 0.12547834888100623,
|
|
"num_tokens": 24437142.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 6.62527379989624,
|
|
"epoch": 1.2092139761356948,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004863578064670837,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.13008212223649024,
|
|
"num_tokens": 24448819.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 6.538669776916504,
|
|
"epoch": 1.2097490502434587,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00048634469278999545,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.1367510162293911,
|
|
"num_tokens": 24459392.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 6.646054792404175,
|
|
"epoch": 1.2102841243512226,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048633157301035895,
|
|
"loss": 6.3562,
|
|
"mean_token_accuracy": 0.12632530331611633,
|
|
"num_tokens": 24470298.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 6.655997180938721,
|
|
"epoch": 1.2108191984589864,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.000486318447128553,
|
|
"loss": 6.3254,
|
|
"mean_token_accuracy": 0.1312053196132183,
|
|
"num_tokens": 24480477.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 6.636211729049682,
|
|
"epoch": 1.2113542725667505,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004863053151449566,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.11806419044733048,
|
|
"num_tokens": 24491890.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 6.632932996749878,
|
|
"epoch": 1.2118893466745144,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048629217705994883,
|
|
"loss": 6.3732,
|
|
"mean_token_accuracy": 0.1282190166413784,
|
|
"num_tokens": 24502583.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 6.654068040847778,
|
|
"epoch": 1.2124244207822783,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004862790328739091,
|
|
"loss": 6.4514,
|
|
"mean_token_accuracy": 0.12212303355336189,
|
|
"num_tokens": 24514491.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 6.579974269866943,
|
|
"epoch": 1.2129594948900422,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048626588258721717,
|
|
"loss": 6.2886,
|
|
"mean_token_accuracy": 0.13765399754047394,
|
|
"num_tokens": 24524788.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 6.581331968307495,
|
|
"epoch": 1.2134945689978063,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004862527262002524,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.12508592531085014,
|
|
"num_tokens": 24535699.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 6.566686964035034,
|
|
"epoch": 1.2140296431055702,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048623956371339494,
|
|
"loss": 6.3331,
|
|
"mean_token_accuracy": 0.1295009195804596,
|
|
"num_tokens": 24547339.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 6.619598388671875,
|
|
"epoch": 1.214564717213334,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048622639512702477,
|
|
"loss": 6.4613,
|
|
"mean_token_accuracy": 0.12075447812676429,
|
|
"num_tokens": 24558778.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 6.62404055595398,
|
|
"epoch": 1.215099791321098,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048621322044152207,
|
|
"loss": 6.3716,
|
|
"mean_token_accuracy": 0.12780714333057402,
|
|
"num_tokens": 24569032.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 6.6212615966796875,
|
|
"epoch": 1.215634865428862,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00048620003965726727,
|
|
"loss": 6.4434,
|
|
"mean_token_accuracy": 0.11491233259439468,
|
|
"num_tokens": 24581356.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 6.623212194442749,
|
|
"epoch": 1.2161699395366259,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048618685277464116,
|
|
"loss": 6.3361,
|
|
"mean_token_accuracy": 0.1290602743625641,
|
|
"num_tokens": 24591809.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 6.535800123214722,
|
|
"epoch": 1.2167050136443898,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.00048617365979402417,
|
|
"loss": 6.2591,
|
|
"mean_token_accuracy": 0.13375867754220963,
|
|
"num_tokens": 24603492.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 6.5800666332244875,
|
|
"epoch": 1.2172400877521536,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004861604607157975,
|
|
"loss": 6.4183,
|
|
"mean_token_accuracy": 0.1260806754231453,
|
|
"num_tokens": 24614837.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 6.626326656341552,
|
|
"epoch": 1.2177751618599175,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004861472555403423,
|
|
"loss": 6.4094,
|
|
"mean_token_accuracy": 0.1283113591372967,
|
|
"num_tokens": 24624714.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 6.6635106086730955,
|
|
"epoch": 1.2183102359676816,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048613404426803964,
|
|
"loss": 6.4257,
|
|
"mean_token_accuracy": 0.12523268461227416,
|
|
"num_tokens": 24635758.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 6.6075873374938965,
|
|
"epoch": 1.2188453100754455,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048612082689927116,
|
|
"loss": 6.4171,
|
|
"mean_token_accuracy": 0.12908233627676963,
|
|
"num_tokens": 24645362.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 6.578433609008789,
|
|
"epoch": 1.2193803841832094,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004861076034344185,
|
|
"loss": 6.4222,
|
|
"mean_token_accuracy": 0.12911440283060074,
|
|
"num_tokens": 24656898.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 6.581374979019165,
|
|
"epoch": 1.2199154582909733,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004860943738738634,
|
|
"loss": 6.3527,
|
|
"mean_token_accuracy": 0.12961121499538422,
|
|
"num_tokens": 24668191.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 6.678846454620361,
|
|
"epoch": 1.2204505323987371,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048608113821798786,
|
|
"loss": 6.3577,
|
|
"mean_token_accuracy": 0.13085444122552872,
|
|
"num_tokens": 24678034.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 6.614822483062744,
|
|
"epoch": 1.2209856065065012,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004860678964671743,
|
|
"loss": 6.4172,
|
|
"mean_token_accuracy": 0.1289056733250618,
|
|
"num_tokens": 24689062.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 6.621836090087891,
|
|
"epoch": 1.221520680614265,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048605464862180474,
|
|
"loss": 6.3867,
|
|
"mean_token_accuracy": 0.12268839031457901,
|
|
"num_tokens": 24699787.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 6.671064138412476,
|
|
"epoch": 1.222055754722029,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004860413946822619,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.12742336764931678,
|
|
"num_tokens": 24711233.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 6.616682338714599,
|
|
"epoch": 1.2225908288297929,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004860281346489284,
|
|
"loss": 6.3754,
|
|
"mean_token_accuracy": 0.12015426009893418,
|
|
"num_tokens": 24722414.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 6.601643037796021,
|
|
"epoch": 1.2231259029375567,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004860148685221873,
|
|
"loss": 6.3891,
|
|
"mean_token_accuracy": 0.12472359091043472,
|
|
"num_tokens": 24733093.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 6.599857425689697,
|
|
"epoch": 1.2236609770453208,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048600159630242135,
|
|
"loss": 6.3454,
|
|
"mean_token_accuracy": 0.12773827463388443,
|
|
"num_tokens": 24743195.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 6.6567943572998045,
|
|
"epoch": 1.2241960511530847,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048598831799001406,
|
|
"loss": 6.36,
|
|
"mean_token_accuracy": 0.1282051384449005,
|
|
"num_tokens": 24753680.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 6.644123315811157,
|
|
"epoch": 1.2247311252608486,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004859750335853488,
|
|
"loss": 6.326,
|
|
"mean_token_accuracy": 0.13350456207990646,
|
|
"num_tokens": 24764135.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 6.545890665054321,
|
|
"epoch": 1.2252661993686125,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.000485961743088809,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.1422355905175209,
|
|
"num_tokens": 24775740.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 6.60781421661377,
|
|
"epoch": 1.2258012734763766,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 0.0004859484465007784,
|
|
"loss": 6.4264,
|
|
"mean_token_accuracy": 0.12363039553165436,
|
|
"num_tokens": 24786169.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 6.596254777908325,
|
|
"epoch": 1.2263363475841405,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048593514382164123,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.12756835222244262,
|
|
"num_tokens": 24796218.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 6.674440526962281,
|
|
"epoch": 1.2268714216919043,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004859218350517814,
|
|
"loss": 6.4544,
|
|
"mean_token_accuracy": 0.12406684979796409,
|
|
"num_tokens": 24806957.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 6.673728513717651,
|
|
"epoch": 1.2274064957996682,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004859085201915831,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.12553686127066613,
|
|
"num_tokens": 24818761.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 6.625372266769409,
|
|
"epoch": 1.227941569907432,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004858951992414311,
|
|
"loss": 6.3138,
|
|
"mean_token_accuracy": 0.1337747246026993,
|
|
"num_tokens": 24829163.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 6.594692897796631,
|
|
"epoch": 1.2284766440151962,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004858818722017097,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.12981459870934486,
|
|
"num_tokens": 24839334.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 6.547637319564819,
|
|
"epoch": 1.22901171812296,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048586853907280395,
|
|
"loss": 6.3692,
|
|
"mean_token_accuracy": 0.13247340619564058,
|
|
"num_tokens": 24850312.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 6.567716598510742,
|
|
"epoch": 1.229546792230724,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004858551998550987,
|
|
"loss": 6.314,
|
|
"mean_token_accuracy": 0.13830785751342772,
|
|
"num_tokens": 24861835.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 6.670967864990234,
|
|
"epoch": 1.2300818663384878,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048584185454897925,
|
|
"loss": 6.3953,
|
|
"mean_token_accuracy": 0.12824348881840705,
|
|
"num_tokens": 24872489.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 6.613324785232544,
|
|
"epoch": 1.230616940446252,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004858285031548309,
|
|
"loss": 6.3707,
|
|
"mean_token_accuracy": 0.12727928161621094,
|
|
"num_tokens": 24882553.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 6.632563734054566,
|
|
"epoch": 1.2311520145540158,
|
|
"grad_norm": 5.21875,
|
|
"learning_rate": 0.0004858151456730391,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.13223066329956054,
|
|
"num_tokens": 24894386.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 6.615245580673218,
|
|
"epoch": 1.2316870886617797,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.00048580178210398954,
|
|
"loss": 6.3741,
|
|
"mean_token_accuracy": 0.12721855491399764,
|
|
"num_tokens": 24905049.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 6.591728639602661,
|
|
"epoch": 1.2322221627695435,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048578841244806823,
|
|
"loss": 6.3377,
|
|
"mean_token_accuracy": 0.1317742109298706,
|
|
"num_tokens": 24914831.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 6.593009042739868,
|
|
"epoch": 1.2327572368773074,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.00048577503670566116,
|
|
"loss": 6.403,
|
|
"mean_token_accuracy": 0.1299585483968258,
|
|
"num_tokens": 24925668.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 6.585937356948852,
|
|
"epoch": 1.2332923109850715,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048576165487715443,
|
|
"loss": 6.3559,
|
|
"mean_token_accuracy": 0.12618065252900124,
|
|
"num_tokens": 24935983.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 6.553822183609009,
|
|
"epoch": 1.2338273850928354,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048574826696293455,
|
|
"loss": 6.3373,
|
|
"mean_token_accuracy": 0.131469988822937,
|
|
"num_tokens": 24946673.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 6.577428245544434,
|
|
"epoch": 1.2343624592005993,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048573487296338814,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.1372582957148552,
|
|
"num_tokens": 24957075.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 6.616323709487915,
|
|
"epoch": 1.2348975333083632,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048572147287890183,
|
|
"loss": 6.4242,
|
|
"mean_token_accuracy": 0.125131606310606,
|
|
"num_tokens": 24967261.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 6.5523268699646,
|
|
"epoch": 1.235432607416127,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048570806670986263,
|
|
"loss": 6.3502,
|
|
"mean_token_accuracy": 0.13004705533385277,
|
|
"num_tokens": 24978097.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 6.618932151794434,
|
|
"epoch": 1.2359676815238911,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048569465445665754,
|
|
"loss": 6.3832,
|
|
"mean_token_accuracy": 0.12783001661300658,
|
|
"num_tokens": 24987932.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 6.591936445236206,
|
|
"epoch": 1.236502755631655,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048568123611967396,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.12940168827772142,
|
|
"num_tokens": 24998919.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 6.569975519180298,
|
|
"epoch": 1.237037829739419,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004856678116992993,
|
|
"loss": 6.3358,
|
|
"mean_token_accuracy": 0.12842285856604577,
|
|
"num_tokens": 25010545.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 6.608821249008178,
|
|
"epoch": 1.2375729038471828,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004856543811959212,
|
|
"loss": 6.302,
|
|
"mean_token_accuracy": 0.1399930827319622,
|
|
"num_tokens": 25021133.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 6.56930980682373,
|
|
"epoch": 1.2381079779549466,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004856409446099274,
|
|
"loss": 6.3197,
|
|
"mean_token_accuracy": 0.12747450470924376,
|
|
"num_tokens": 25031838.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 6.588279676437378,
|
|
"epoch": 1.2386430520627107,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048562750194170595,
|
|
"loss": 6.3742,
|
|
"mean_token_accuracy": 0.12537180930376052,
|
|
"num_tokens": 25042737.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 6.639550447463989,
|
|
"epoch": 1.2391781261704746,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.000485614053191645,
|
|
"loss": 6.4671,
|
|
"mean_token_accuracy": 0.12725185677409173,
|
|
"num_tokens": 25054442.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 6.559206533432007,
|
|
"epoch": 1.2397132002782385,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004856005983601328,
|
|
"loss": 6.1875,
|
|
"mean_token_accuracy": 0.14291266798973085,
|
|
"num_tokens": 25065509.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 6.646664428710937,
|
|
"epoch": 1.2402482743860024,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048558713744755794,
|
|
"loss": 6.4376,
|
|
"mean_token_accuracy": 0.12133636623620987,
|
|
"num_tokens": 25077306.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 6.572434616088867,
|
|
"epoch": 1.2407833484937665,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004855736704543091,
|
|
"loss": 6.3548,
|
|
"mean_token_accuracy": 0.1318959653377533,
|
|
"num_tokens": 25088230.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 6.6829441547393795,
|
|
"epoch": 1.2413184226015304,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004855601973807751,
|
|
"loss": 6.464,
|
|
"mean_token_accuracy": 0.11949804276227952,
|
|
"num_tokens": 25099658.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 6.6502237796783445,
|
|
"epoch": 1.2418534967092942,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048554671822734495,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.1285843014717102,
|
|
"num_tokens": 25110512.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 6.621615076065064,
|
|
"epoch": 1.2423885708170581,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048553323299440807,
|
|
"loss": 6.3742,
|
|
"mean_token_accuracy": 0.13122225254774095,
|
|
"num_tokens": 25120193.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 6.571666193008423,
|
|
"epoch": 1.242923644924822,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048551974168235346,
|
|
"loss": 6.3723,
|
|
"mean_token_accuracy": 0.126374314725399,
|
|
"num_tokens": 25131752.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 6.601293992996216,
|
|
"epoch": 1.243458719032586,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000485506244291571,
|
|
"loss": 6.3674,
|
|
"mean_token_accuracy": 0.13281625136733055,
|
|
"num_tokens": 25141541.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 6.563148069381714,
|
|
"epoch": 1.24399379314035,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004854927408224503,
|
|
"loss": 6.366,
|
|
"mean_token_accuracy": 0.1274819552898407,
|
|
"num_tokens": 25152219.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 6.688095664978027,
|
|
"epoch": 1.2445288672481138,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.00048547923127538126,
|
|
"loss": 6.3944,
|
|
"mean_token_accuracy": 0.12603169530630112,
|
|
"num_tokens": 25163030.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 6.6026605606079105,
|
|
"epoch": 1.2450639413558777,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048546571565075396,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.1284670613706112,
|
|
"num_tokens": 25174637.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 6.566499662399292,
|
|
"epoch": 1.2455990154636418,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004854521939489587,
|
|
"loss": 6.2678,
|
|
"mean_token_accuracy": 0.1353589192032814,
|
|
"num_tokens": 25185067.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 6.567450046539307,
|
|
"epoch": 1.2461340895714057,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048543866617038604,
|
|
"loss": 6.3108,
|
|
"mean_token_accuracy": 0.1296251483261585,
|
|
"num_tokens": 25195046.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 6.585061979293823,
|
|
"epoch": 1.2466691636791696,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048542513231542635,
|
|
"loss": 6.3901,
|
|
"mean_token_accuracy": 0.12518625929951668,
|
|
"num_tokens": 25206265.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 6.642643547058105,
|
|
"epoch": 1.2472042377869335,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004854115923844705,
|
|
"loss": 6.3852,
|
|
"mean_token_accuracy": 0.125561436265707,
|
|
"num_tokens": 25217690.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 6.6429284572601315,
|
|
"epoch": 1.2477393118946973,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004853980463779096,
|
|
"loss": 6.4077,
|
|
"mean_token_accuracy": 0.12148850858211517,
|
|
"num_tokens": 25228229.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 6.559851503372192,
|
|
"epoch": 1.2482743860024614,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004853844942961346,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.13018380254507064,
|
|
"num_tokens": 25240073.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 6.59410662651062,
|
|
"epoch": 1.2488094601102253,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000485370936139537,
|
|
"loss": 6.386,
|
|
"mean_token_accuracy": 0.13106369376182556,
|
|
"num_tokens": 25251915.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 6.573438024520874,
|
|
"epoch": 1.2493445342179892,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000485357371908508,
|
|
"loss": 6.357,
|
|
"mean_token_accuracy": 0.12828725948929787,
|
|
"num_tokens": 25262932.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 6.526694059371948,
|
|
"epoch": 1.249879608325753,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004853438016034396,
|
|
"loss": 6.4159,
|
|
"mean_token_accuracy": 0.1260906420648098,
|
|
"num_tokens": 25274693.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 6.600314474105835,
|
|
"epoch": 1.250414682433517,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048533022522472344,
|
|
"loss": 6.3037,
|
|
"mean_token_accuracy": 0.1329547218978405,
|
|
"num_tokens": 25285359.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 6.612820816040039,
|
|
"epoch": 1.250949756541281,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048531664277275154,
|
|
"loss": 6.3324,
|
|
"mean_token_accuracy": 0.1268061652779579,
|
|
"num_tokens": 25296730.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 6.593801736831665,
|
|
"epoch": 1.251484830649045,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004853030542479162,
|
|
"loss": 6.3768,
|
|
"mean_token_accuracy": 0.13358341604471208,
|
|
"num_tokens": 25306422.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 6.623576259613037,
|
|
"epoch": 1.2520199047568088,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004852894596506096,
|
|
"loss": 6.3846,
|
|
"mean_token_accuracy": 0.1288984887301922,
|
|
"num_tokens": 25317980.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 6.585350036621094,
|
|
"epoch": 1.2525549788645727,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004852758589812245,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.1335228957235813,
|
|
"num_tokens": 25329905.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 6.632127046585083,
|
|
"epoch": 1.2530900529723366,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048526225224015355,
|
|
"loss": 6.3939,
|
|
"mean_token_accuracy": 0.12271509766578674,
|
|
"num_tokens": 25340759.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 6.6104100227355955,
|
|
"epoch": 1.2536251270801007,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004852486394277896,
|
|
"loss": 6.4022,
|
|
"mean_token_accuracy": 0.12256303057074547,
|
|
"num_tokens": 25351124.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 6.685027933120727,
|
|
"epoch": 1.2541602011878645,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048523502054452565,
|
|
"loss": 6.3413,
|
|
"mean_token_accuracy": 0.12788822278380393,
|
|
"num_tokens": 25361337.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 6.689016199111938,
|
|
"epoch": 1.2546952752956284,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048522139559075507,
|
|
"loss": 6.376,
|
|
"mean_token_accuracy": 0.13317637890577316,
|
|
"num_tokens": 25371893.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 6.49555516242981,
|
|
"epoch": 1.2552303494033923,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004852077645668712,
|
|
"loss": 6.2666,
|
|
"mean_token_accuracy": 0.1358470655977726,
|
|
"num_tokens": 25383365.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 6.536110162734985,
|
|
"epoch": 1.2557654235111562,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004851941274732678,
|
|
"loss": 6.3586,
|
|
"mean_token_accuracy": 0.12989744246006013,
|
|
"num_tokens": 25393211.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 6.507546663284302,
|
|
"epoch": 1.2563004976189203,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004851804843103384,
|
|
"loss": 6.2152,
|
|
"mean_token_accuracy": 0.1300113767385483,
|
|
"num_tokens": 25404828.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 6.622454690933227,
|
|
"epoch": 1.2568355717266841,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00048516683507847705,
|
|
"loss": 6.3673,
|
|
"mean_token_accuracy": 0.13234002515673637,
|
|
"num_tokens": 25416016.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 6.601455879211426,
|
|
"epoch": 1.257370645834448,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004851531797780779,
|
|
"loss": 6.327,
|
|
"mean_token_accuracy": 0.12935493439435958,
|
|
"num_tokens": 25426173.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 6.589295482635498,
|
|
"epoch": 1.2579057199422121,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004851395184095352,
|
|
"loss": 6.2896,
|
|
"mean_token_accuracy": 0.1359050452709198,
|
|
"num_tokens": 25437507.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 6.596389102935791,
|
|
"epoch": 1.258440794049976,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004851258509732434,
|
|
"loss": 6.3583,
|
|
"mean_token_accuracy": 0.12319867387413978,
|
|
"num_tokens": 25448201.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 6.6106836795806885,
|
|
"epoch": 1.2589758681577399,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048511217746959723,
|
|
"loss": 6.3987,
|
|
"mean_token_accuracy": 0.12544824481010436,
|
|
"num_tokens": 25458640.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 6.607550859451294,
|
|
"epoch": 1.2595109422655038,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.00048509849789899146,
|
|
"loss": 6.3903,
|
|
"mean_token_accuracy": 0.13483730852603912,
|
|
"num_tokens": 25469474.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 6.618516874313355,
|
|
"epoch": 1.2600460163732676,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000485084812261821,
|
|
"loss": 6.4554,
|
|
"mean_token_accuracy": 0.1234629549086094,
|
|
"num_tokens": 25479565.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 6.649857091903686,
|
|
"epoch": 1.2605810904810317,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004850711205584812,
|
|
"loss": 6.3192,
|
|
"mean_token_accuracy": 0.13465046957135202,
|
|
"num_tokens": 25490142.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 6.60956449508667,
|
|
"epoch": 1.2611161645887956,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048505742278936726,
|
|
"loss": 6.4171,
|
|
"mean_token_accuracy": 0.12825653478503227,
|
|
"num_tokens": 25500824.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 6.623470592498779,
|
|
"epoch": 1.2616512386965595,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00048504371895487474,
|
|
"loss": 6.3587,
|
|
"mean_token_accuracy": 0.1301652304828167,
|
|
"num_tokens": 25511251.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 6.647195100784302,
|
|
"epoch": 1.2621863128043234,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.00048503000905539945,
|
|
"loss": 6.3402,
|
|
"mean_token_accuracy": 0.12572886496782304,
|
|
"num_tokens": 25521368.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 6.5971965312957765,
|
|
"epoch": 1.2627213869120872,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048501629309133707,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.12626405507326127,
|
|
"num_tokens": 25532486.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 6.5415112495422365,
|
|
"epoch": 1.2632564610198513,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004850025710630838,
|
|
"loss": 6.3588,
|
|
"mean_token_accuracy": 0.13551745787262917,
|
|
"num_tokens": 25542867.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 6.530777549743652,
|
|
"epoch": 1.2637915351276152,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048498884297103575,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.12811006009578704,
|
|
"num_tokens": 25553564.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 6.622891569137574,
|
|
"epoch": 1.264326609235379,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004849751088155894,
|
|
"loss": 6.331,
|
|
"mean_token_accuracy": 0.12764688655734063,
|
|
"num_tokens": 25564017.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 6.584018230438232,
|
|
"epoch": 1.264861683343143,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004849613685971413,
|
|
"loss": 6.2618,
|
|
"mean_token_accuracy": 0.13237593099474906,
|
|
"num_tokens": 25575125.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 6.587107801437378,
|
|
"epoch": 1.2653967574509069,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004849476223160882,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.1258866973221302,
|
|
"num_tokens": 25586405.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 6.591556358337402,
|
|
"epoch": 1.265931831558671,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004849338699728269,
|
|
"loss": 6.3696,
|
|
"mean_token_accuracy": 0.12388554513454438,
|
|
"num_tokens": 25597494.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 6.596306848526001,
|
|
"epoch": 1.2664669056664348,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00048492011156775467,
|
|
"loss": 6.328,
|
|
"mean_token_accuracy": 0.13468450382351876,
|
|
"num_tokens": 25608425.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 6.6159019947052,
|
|
"epoch": 1.2670019797741987,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004849063471012688,
|
|
"loss": 6.3633,
|
|
"mean_token_accuracy": 0.12473512068390846,
|
|
"num_tokens": 25619411.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 6.595540714263916,
|
|
"epoch": 1.2675370538819626,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004848925765737665,
|
|
"loss": 6.3818,
|
|
"mean_token_accuracy": 0.12260571494698524,
|
|
"num_tokens": 25630477.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 6.625878715515137,
|
|
"epoch": 1.2680721279897265,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048487879998564565,
|
|
"loss": 6.316,
|
|
"mean_token_accuracy": 0.12914120480418206,
|
|
"num_tokens": 25640129.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 6.605212068557739,
|
|
"epoch": 1.2686072020974906,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048486501733730386,
|
|
"loss": 6.394,
|
|
"mean_token_accuracy": 0.1322409100830555,
|
|
"num_tokens": 25650592.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 6.565747308731079,
|
|
"epoch": 1.2691422762052544,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048485122862913934,
|
|
"loss": 6.2969,
|
|
"mean_token_accuracy": 0.13743074908852576,
|
|
"num_tokens": 25660408.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 6.592240619659424,
|
|
"epoch": 1.2696773503130183,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048483743386154994,
|
|
"loss": 6.4075,
|
|
"mean_token_accuracy": 0.1282390721142292,
|
|
"num_tokens": 25671563.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 6.616723823547363,
|
|
"epoch": 1.2702124244207824,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048482363303493415,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.12819777727127074,
|
|
"num_tokens": 25682474.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 6.684830236434936,
|
|
"epoch": 1.270747498528546,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004848098261496905,
|
|
"loss": 6.3529,
|
|
"mean_token_accuracy": 0.12945090234279633,
|
|
"num_tokens": 25692594.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 6.478584671020508,
|
|
"epoch": 1.2712825726363102,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004847960132062175,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.14128711596131324,
|
|
"num_tokens": 25703724.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 6.604314708709717,
|
|
"epoch": 1.271817646744074,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004847821942049142,
|
|
"loss": 6.4986,
|
|
"mean_token_accuracy": 0.11871818527579307,
|
|
"num_tokens": 25714911.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 6.715882968902588,
|
|
"epoch": 1.272352720851838,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00048476836914617945,
|
|
"loss": 6.3523,
|
|
"mean_token_accuracy": 0.13008263409137727,
|
|
"num_tokens": 25725098.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 6.638854217529297,
|
|
"epoch": 1.272887794959602,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048475453803041254,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.12206205874681472,
|
|
"num_tokens": 25735099.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 6.552611875534057,
|
|
"epoch": 1.273422869067366,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004847407008580128,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.13125536516308783,
|
|
"num_tokens": 25746852.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 6.568732595443725,
|
|
"epoch": 1.2739579431751298,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048472685762937983,
|
|
"loss": 6.393,
|
|
"mean_token_accuracy": 0.1326376549899578,
|
|
"num_tokens": 25758579.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 6.575577163696289,
|
|
"epoch": 1.2744930172828937,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048471300834491325,
|
|
"loss": 6.3753,
|
|
"mean_token_accuracy": 0.12422654181718826,
|
|
"num_tokens": 25769965.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 6.636907291412354,
|
|
"epoch": 1.2750280913906575,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004846991530050132,
|
|
"loss": 6.3759,
|
|
"mean_token_accuracy": 0.1286887437105179,
|
|
"num_tokens": 25780264.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 6.598765516281128,
|
|
"epoch": 1.2755631654984216,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004846852916100794,
|
|
"loss": 6.3177,
|
|
"mean_token_accuracy": 0.12898892611265184,
|
|
"num_tokens": 25791228.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 6.591907978057861,
|
|
"epoch": 1.2760982396061855,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004846714241605123,
|
|
"loss": 6.2923,
|
|
"mean_token_accuracy": 0.13126567080616952,
|
|
"num_tokens": 25802428.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 6.634409666061401,
|
|
"epoch": 1.2766333137139494,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048465755065671233,
|
|
"loss": 6.3683,
|
|
"mean_token_accuracy": 0.12842002362012864,
|
|
"num_tokens": 25814220.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 6.557821607589721,
|
|
"epoch": 1.2771683878217133,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048464367109908005,
|
|
"loss": 6.3747,
|
|
"mean_token_accuracy": 0.1295553684234619,
|
|
"num_tokens": 25824382.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 6.516737222671509,
|
|
"epoch": 1.2777034619294771,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004846297854880162,
|
|
"loss": 6.3126,
|
|
"mean_token_accuracy": 0.13260903656482698,
|
|
"num_tokens": 25834896.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 6.658901119232178,
|
|
"epoch": 1.2782385360372412,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048461589382392176,
|
|
"loss": 6.4175,
|
|
"mean_token_accuracy": 0.12118547409772873,
|
|
"num_tokens": 25847300.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 6.643686723709107,
|
|
"epoch": 1.2787736101450051,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004846019961071978,
|
|
"loss": 6.3608,
|
|
"mean_token_accuracy": 0.1277372010052204,
|
|
"num_tokens": 25858599.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 6.575046014785767,
|
|
"epoch": 1.279308684252769,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004845880923382457,
|
|
"loss": 6.3167,
|
|
"mean_token_accuracy": 0.13413082361221312,
|
|
"num_tokens": 25869135.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 6.548751401901245,
|
|
"epoch": 1.2798437583605329,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00048457418251746695,
|
|
"loss": 6.3203,
|
|
"mean_token_accuracy": 0.13610622137784958,
|
|
"num_tokens": 25879234.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 6.6187419414520265,
|
|
"epoch": 1.2803788324682968,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004845602666452629,
|
|
"loss": 6.3686,
|
|
"mean_token_accuracy": 0.1346176564693451,
|
|
"num_tokens": 25888230.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 6.595930528640747,
|
|
"epoch": 1.2809139065760609,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004845463447220358,
|
|
"loss": 6.3664,
|
|
"mean_token_accuracy": 0.13885386064648628,
|
|
"num_tokens": 25899429.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 6.558820152282715,
|
|
"epoch": 1.2814489806838247,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004845324167481874,
|
|
"loss": 6.2616,
|
|
"mean_token_accuracy": 0.13504811078310014,
|
|
"num_tokens": 25911042.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 6.638614559173584,
|
|
"epoch": 1.2819840547915886,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004845184827241199,
|
|
"loss": 6.319,
|
|
"mean_token_accuracy": 0.1340831160545349,
|
|
"num_tokens": 25921466.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 6.612584924697876,
|
|
"epoch": 1.2825191288993525,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004845045426502357,
|
|
"loss": 6.4304,
|
|
"mean_token_accuracy": 0.12037662118673324,
|
|
"num_tokens": 25931059.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 6.61162691116333,
|
|
"epoch": 1.2830542030071164,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048449059652693724,
|
|
"loss": 6.3422,
|
|
"mean_token_accuracy": 0.12955860793590546,
|
|
"num_tokens": 25941669.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 6.592455291748047,
|
|
"epoch": 1.2835892771148805,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004844766443546272,
|
|
"loss": 6.354,
|
|
"mean_token_accuracy": 0.13435404375195503,
|
|
"num_tokens": 25952066.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 6.589900875091553,
|
|
"epoch": 1.2841243512226443,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004844626861337085,
|
|
"loss": 6.2721,
|
|
"mean_token_accuracy": 0.13439391627907754,
|
|
"num_tokens": 25962388.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.2841243512226443,
|
|
"eval_entropy": 6.390221093607077,
|
|
"eval_loss": 6.48252010345459,
|
|
"eval_mean_token_accuracy": 0.13040220448671969,
|
|
"eval_num_tokens": 25962388.0,
|
|
"eval_runtime": 22.8412,
|
|
"eval_samples_per_second": 1299.364,
|
|
"eval_steps_per_second": 162.426,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 6.496599102020264,
|
|
"epoch": 1.2846594253304082,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004844487218645843,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.12779598981142043,
|
|
"num_tokens": 25973865.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 6.535670518875122,
|
|
"epoch": 1.2851944994381723,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004844347515476575,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.12979554012417793,
|
|
"num_tokens": 25985113.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 6.58581657409668,
|
|
"epoch": 1.285729573545936,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048442077518333175,
|
|
"loss": 6.2258,
|
|
"mean_token_accuracy": 0.14415694922208785,
|
|
"num_tokens": 25995980.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 6.523624420166016,
|
|
"epoch": 1.2862646476537,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048440679277201063,
|
|
"loss": 6.3504,
|
|
"mean_token_accuracy": 0.13102689981460572,
|
|
"num_tokens": 26006362.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 6.6001598834991455,
|
|
"epoch": 1.286799721761464,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048439280431409774,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.13095032572746276,
|
|
"num_tokens": 26016623.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 6.564063215255738,
|
|
"epoch": 1.2873347958692278,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048437880980999694,
|
|
"loss": 6.2171,
|
|
"mean_token_accuracy": 0.13957177698612214,
|
|
"num_tokens": 26027202.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 6.563328266143799,
|
|
"epoch": 1.287869869976992,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004843648092601125,
|
|
"loss": 6.3264,
|
|
"mean_token_accuracy": 0.12523544654250146,
|
|
"num_tokens": 26037330.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 6.605491733551025,
|
|
"epoch": 1.2884049440847558,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004843508026648487,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.13024578839540482,
|
|
"num_tokens": 26047661.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 6.67367262840271,
|
|
"epoch": 1.2889400181925197,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004843367900246098,
|
|
"loss": 6.422,
|
|
"mean_token_accuracy": 0.12344651594758034,
|
|
"num_tokens": 26058582.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 6.592609167098999,
|
|
"epoch": 1.2894750923002836,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048432277133980055,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.12009303420782089,
|
|
"num_tokens": 26069117.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 6.580240678787232,
|
|
"epoch": 1.2900101664080474,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048430874661082565,
|
|
"loss": 6.3382,
|
|
"mean_token_accuracy": 0.13450202122330665,
|
|
"num_tokens": 26079327.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 6.6148916721344,
|
|
"epoch": 1.2905452405158115,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048429471583809016,
|
|
"loss": 6.3684,
|
|
"mean_token_accuracy": 0.1255665585398674,
|
|
"num_tokens": 26090709.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 6.682782411575317,
|
|
"epoch": 1.2910803146235754,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004842806790219991,
|
|
"loss": 6.3586,
|
|
"mean_token_accuracy": 0.12445581406354904,
|
|
"num_tokens": 26101570.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 6.589714670181275,
|
|
"epoch": 1.2916153887313393,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048426663616295783,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.1342082478106022,
|
|
"num_tokens": 26112827.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 6.577224397659302,
|
|
"epoch": 1.2921504628391032,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048425258726137187,
|
|
"loss": 6.395,
|
|
"mean_token_accuracy": 0.12190400063991547,
|
|
"num_tokens": 26124141.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 6.581721830368042,
|
|
"epoch": 1.292685536946867,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048423853231764684,
|
|
"loss": 6.3509,
|
|
"mean_token_accuracy": 0.12956209033727645,
|
|
"num_tokens": 26135372.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 6.560742568969727,
|
|
"epoch": 1.2932206110546312,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048422447133218867,
|
|
"loss": 6.3144,
|
|
"mean_token_accuracy": 0.12703603878617287,
|
|
"num_tokens": 26145933.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 6.614239501953125,
|
|
"epoch": 1.293755685162395,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048421040430540323,
|
|
"loss": 6.3864,
|
|
"mean_token_accuracy": 0.1296641081571579,
|
|
"num_tokens": 26155948.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 6.5700726985931395,
|
|
"epoch": 1.294290759270159,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004841963312376967,
|
|
"loss": 6.2985,
|
|
"mean_token_accuracy": 0.1366102308034897,
|
|
"num_tokens": 26166410.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 6.563685083389283,
|
|
"epoch": 1.2948258333779228,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048418225212947566,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.12744559943675995,
|
|
"num_tokens": 26177334.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 6.685234832763672,
|
|
"epoch": 1.2953609074856867,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004841681669811464,
|
|
"loss": 6.3901,
|
|
"mean_token_accuracy": 0.11985235661268234,
|
|
"num_tokens": 26187987.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 6.5804449081420895,
|
|
"epoch": 1.2958959815934508,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004841540757931157,
|
|
"loss": 6.3562,
|
|
"mean_token_accuracy": 0.12461261823773384,
|
|
"num_tokens": 26198600.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 6.559697198867798,
|
|
"epoch": 1.2964310557012146,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004841399785657904,
|
|
"loss": 6.3884,
|
|
"mean_token_accuracy": 0.1280129984021187,
|
|
"num_tokens": 26210977.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 6.624713611602783,
|
|
"epoch": 1.2969661298089785,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048412587529957774,
|
|
"loss": 6.3376,
|
|
"mean_token_accuracy": 0.12946136817336082,
|
|
"num_tokens": 26220813.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 6.656932353973389,
|
|
"epoch": 1.2975012039167424,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004841117659948848,
|
|
"loss": 6.3855,
|
|
"mean_token_accuracy": 0.1332462102174759,
|
|
"num_tokens": 26232042.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 6.603672075271606,
|
|
"epoch": 1.2980362780245063,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048409765065211884,
|
|
"loss": 6.3813,
|
|
"mean_token_accuracy": 0.12884095311164856,
|
|
"num_tokens": 26242968.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 6.611974287033081,
|
|
"epoch": 1.2985713521322704,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048408352927168774,
|
|
"loss": 6.3603,
|
|
"mean_token_accuracy": 0.13033699095249177,
|
|
"num_tokens": 26252751.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 6.614048290252685,
|
|
"epoch": 1.2991064262400343,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004840694018539991,
|
|
"loss": 6.4322,
|
|
"mean_token_accuracy": 0.122306989133358,
|
|
"num_tokens": 26263270.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 6.624433326721191,
|
|
"epoch": 1.2996415003477981,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048405526839946086,
|
|
"loss": 6.44,
|
|
"mean_token_accuracy": 0.12507982924580574,
|
|
"num_tokens": 26274279.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 6.636956024169922,
|
|
"epoch": 1.3001765744555622,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048404112890848105,
|
|
"loss": 6.4293,
|
|
"mean_token_accuracy": 0.1284723997116089,
|
|
"num_tokens": 26286020.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 6.635603284835815,
|
|
"epoch": 1.3007116485633259,
|
|
"grad_norm": 5.0,
|
|
"learning_rate": 0.00048402698338146803,
|
|
"loss": 6.3466,
|
|
"mean_token_accuracy": 0.13098725825548171,
|
|
"num_tokens": 26296798.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 6.542436122894287,
|
|
"epoch": 1.30124672267109,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004840128318188303,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.13343275263905524,
|
|
"num_tokens": 26306952.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 6.652034282684326,
|
|
"epoch": 1.3017817967788539,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048399867422097644,
|
|
"loss": 6.408,
|
|
"mean_token_accuracy": 0.1271870918571949,
|
|
"num_tokens": 26317686.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 6.6125720024108885,
|
|
"epoch": 1.3023168708866177,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048398451058831514,
|
|
"loss": 6.3944,
|
|
"mean_token_accuracy": 0.12852074056863785,
|
|
"num_tokens": 26327997.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 6.587728977203369,
|
|
"epoch": 1.3028519449943818,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048397034092125554,
|
|
"loss": 6.3767,
|
|
"mean_token_accuracy": 0.12798827961087228,
|
|
"num_tokens": 26340227.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 6.7405383586883545,
|
|
"epoch": 1.3033870191021457,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048395616522020667,
|
|
"loss": 6.4862,
|
|
"mean_token_accuracy": 0.12577992230653762,
|
|
"num_tokens": 26350549.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 6.648358154296875,
|
|
"epoch": 1.3039220932099096,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004839419834855779,
|
|
"loss": 6.3876,
|
|
"mean_token_accuracy": 0.12537632808089255,
|
|
"num_tokens": 26361822.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 6.539509344100952,
|
|
"epoch": 1.3044571673176735,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004839277957177787,
|
|
"loss": 6.3956,
|
|
"mean_token_accuracy": 0.12865559458732606,
|
|
"num_tokens": 26372720.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 6.5293957710266115,
|
|
"epoch": 1.3049922414254373,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004839136019172188,
|
|
"loss": 6.3668,
|
|
"mean_token_accuracy": 0.13241078928112984,
|
|
"num_tokens": 26383092.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 6.560792398452759,
|
|
"epoch": 1.3055273155332014,
|
|
"grad_norm": 4.75,
|
|
"learning_rate": 0.000483899402084308,
|
|
"loss": 6.3007,
|
|
"mean_token_accuracy": 0.13902270272374154,
|
|
"num_tokens": 26395188.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 6.597141218185425,
|
|
"epoch": 1.3060623896409653,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004838851962194563,
|
|
"loss": 6.4134,
|
|
"mean_token_accuracy": 0.1312008999288082,
|
|
"num_tokens": 26406338.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 6.577714490890503,
|
|
"epoch": 1.3065974637487292,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004838709843230739,
|
|
"loss": 6.3525,
|
|
"mean_token_accuracy": 0.12637813463807107,
|
|
"num_tokens": 26416983.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 6.608711528778076,
|
|
"epoch": 1.307132537856493,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004838567663955712,
|
|
"loss": 6.3009,
|
|
"mean_token_accuracy": 0.13467254340648652,
|
|
"num_tokens": 26426966.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 6.590001583099365,
|
|
"epoch": 1.307667611964257,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004838425424373587,
|
|
"loss": 6.2829,
|
|
"mean_token_accuracy": 0.12638806477189063,
|
|
"num_tokens": 26437711.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 6.5735279560089115,
|
|
"epoch": 1.308202686072021,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004838283124488472,
|
|
"loss": 6.4247,
|
|
"mean_token_accuracy": 0.12698045521974563,
|
|
"num_tokens": 26448657.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 6.616390895843506,
|
|
"epoch": 1.308737760179785,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048381407643044737,
|
|
"loss": 6.3208,
|
|
"mean_token_accuracy": 0.1337103560566902,
|
|
"num_tokens": 26459363.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 6.59645037651062,
|
|
"epoch": 1.3092728342875488,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004837998343825705,
|
|
"loss": 6.3359,
|
|
"mean_token_accuracy": 0.1320387527346611,
|
|
"num_tokens": 26470149.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 6.580993700027466,
|
|
"epoch": 1.3098079083953127,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048378558630562783,
|
|
"loss": 6.3093,
|
|
"mean_token_accuracy": 0.13702225163578988,
|
|
"num_tokens": 26480424.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 6.572839689254761,
|
|
"epoch": 1.3103429825030766,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004837713322000306,
|
|
"loss": 6.3279,
|
|
"mean_token_accuracy": 0.1231299638748169,
|
|
"num_tokens": 26490312.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 6.540719795227051,
|
|
"epoch": 1.3108780566108407,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004837570720661905,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.13570182770490646,
|
|
"num_tokens": 26501119.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 6.663457536697388,
|
|
"epoch": 1.3114131307186045,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048374280590451934,
|
|
"loss": 6.3842,
|
|
"mean_token_accuracy": 0.13131397739052772,
|
|
"num_tokens": 26512438.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 6.585407161712647,
|
|
"epoch": 1.3119482048263684,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048372853371542895,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.12171675786375999,
|
|
"num_tokens": 26523930.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 6.584746026992798,
|
|
"epoch": 1.3124832789341323,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004837142554993315,
|
|
"loss": 6.4436,
|
|
"mean_token_accuracy": 0.12544663846492768,
|
|
"num_tokens": 26534937.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 6.533714437484742,
|
|
"epoch": 1.3130183530418962,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004836999712566392,
|
|
"loss": 6.2394,
|
|
"mean_token_accuracy": 0.13478765413165092,
|
|
"num_tokens": 26544555.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 6.646992158889771,
|
|
"epoch": 1.3135534271496603,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048368568098776463,
|
|
"loss": 6.3917,
|
|
"mean_token_accuracy": 0.1362927794456482,
|
|
"num_tokens": 26556144.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 6.64198112487793,
|
|
"epoch": 1.3140885012574242,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004836713846931203,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.12436373457312584,
|
|
"num_tokens": 26567350.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 6.587950038909912,
|
|
"epoch": 1.314623575365188,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048365708237311904,
|
|
"loss": 6.3311,
|
|
"mean_token_accuracy": 0.1277921825647354,
|
|
"num_tokens": 26579486.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 6.564188385009766,
|
|
"epoch": 1.3151586494729521,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004836427740281739,
|
|
"loss": 6.343,
|
|
"mean_token_accuracy": 0.12910154461860657,
|
|
"num_tokens": 26589665.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 6.576068115234375,
|
|
"epoch": 1.3156937235807158,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048362845965869793,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.12906171530485153,
|
|
"num_tokens": 26600187.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 6.599110078811646,
|
|
"epoch": 1.31622879768848,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004836141392651046,
|
|
"loss": 6.3308,
|
|
"mean_token_accuracy": 0.12769033014774323,
|
|
"num_tokens": 26612155.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 6.62664566040039,
|
|
"epoch": 1.3167638717962438,
|
|
"grad_norm": 6.1875,
|
|
"learning_rate": 0.00048359981284780727,
|
|
"loss": 6.3682,
|
|
"mean_token_accuracy": 0.12384458854794503,
|
|
"num_tokens": 26623077.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 6.556846046447754,
|
|
"epoch": 1.3172989459040076,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004835854804072196,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.13607168793678284,
|
|
"num_tokens": 26632979.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 6.573035192489624,
|
|
"epoch": 1.3178340200117717,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048357114194375555,
|
|
"loss": 6.3895,
|
|
"mean_token_accuracy": 0.12178433611989022,
|
|
"num_tokens": 26644377.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 6.565471172332764,
|
|
"epoch": 1.3183690941195356,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000483556797457829,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.1216041162610054,
|
|
"num_tokens": 26655538.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 6.612661981582642,
|
|
"epoch": 1.3189041682272995,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048354244694985435,
|
|
"loss": 6.3562,
|
|
"mean_token_accuracy": 0.12305040657520294,
|
|
"num_tokens": 26668011.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 6.614315509796143,
|
|
"epoch": 1.3194392423350634,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004835280904202457,
|
|
"loss": 6.375,
|
|
"mean_token_accuracy": 0.12892489656805992,
|
|
"num_tokens": 26678996.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 6.638817262649536,
|
|
"epoch": 1.3199743164428273,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004835137278694178,
|
|
"loss": 6.318,
|
|
"mean_token_accuracy": 0.13275674283504485,
|
|
"num_tokens": 26689041.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 6.620911312103272,
|
|
"epoch": 1.3205093905505914,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004834993592977854,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.1369181126356125,
|
|
"num_tokens": 26699459.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 6.5905602931976315,
|
|
"epoch": 1.3210444646583552,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004834849847057632,
|
|
"loss": 6.4444,
|
|
"mean_token_accuracy": 0.12739473357796668,
|
|
"num_tokens": 26711663.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 6.611017751693725,
|
|
"epoch": 1.321579538766119,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048347060409376644,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.12200290784239769,
|
|
"num_tokens": 26722960.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 6.633477735519409,
|
|
"epoch": 1.322114612873883,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048345621746221024,
|
|
"loss": 6.3298,
|
|
"mean_token_accuracy": 0.13550143092870712,
|
|
"num_tokens": 26733274.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 6.624108552932739,
|
|
"epoch": 1.3226496869816469,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048344182481151003,
|
|
"loss": 6.3803,
|
|
"mean_token_accuracy": 0.12166006118059158,
|
|
"num_tokens": 26743906.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 6.559338617324829,
|
|
"epoch": 1.323184761089411,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048342742614208145,
|
|
"loss": 6.3772,
|
|
"mean_token_accuracy": 0.12531487196683883,
|
|
"num_tokens": 26755093.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 6.571753692626953,
|
|
"epoch": 1.3237198351971748,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004834130214543402,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.12853367775678634,
|
|
"num_tokens": 26765614.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 6.608676147460938,
|
|
"epoch": 1.3242549093049387,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048339861074870227,
|
|
"loss": 6.3448,
|
|
"mean_token_accuracy": 0.1282157063484192,
|
|
"num_tokens": 26778078.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 6.626034688949585,
|
|
"epoch": 1.3247899834127026,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048338419402558375,
|
|
"loss": 6.3756,
|
|
"mean_token_accuracy": 0.1281701035797596,
|
|
"num_tokens": 26788707.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 6.587012529373169,
|
|
"epoch": 1.3253250575204665,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004833697712854009,
|
|
"loss": 6.3266,
|
|
"mean_token_accuracy": 0.13063182756304742,
|
|
"num_tokens": 26798650.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 6.545049715042114,
|
|
"epoch": 1.3258601316282306,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048335534252857016,
|
|
"loss": 6.3805,
|
|
"mean_token_accuracy": 0.13052365705370902,
|
|
"num_tokens": 26809822.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 6.58240704536438,
|
|
"epoch": 1.3263952057359945,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004833409077555082,
|
|
"loss": 6.3463,
|
|
"mean_token_accuracy": 0.1254808261990547,
|
|
"num_tokens": 26821061.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 6.6582318305969235,
|
|
"epoch": 1.3269302798437583,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.00048332646696663177,
|
|
"loss": 6.407,
|
|
"mean_token_accuracy": 0.1231968306005001,
|
|
"num_tokens": 26832020.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 6.696759796142578,
|
|
"epoch": 1.3274653539515222,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004833120201623579,
|
|
"loss": 6.381,
|
|
"mean_token_accuracy": 0.12439499422907829,
|
|
"num_tokens": 26844287.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 6.523725986480713,
|
|
"epoch": 1.328000428059286,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048329756734310375,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.13768120482563972,
|
|
"num_tokens": 26855790.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 6.537848472595215,
|
|
"epoch": 1.3285355021670502,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048328310850928656,
|
|
"loss": 6.3764,
|
|
"mean_token_accuracy": 0.13103343099355697,
|
|
"num_tokens": 26867391.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 6.588693284988404,
|
|
"epoch": 1.329070576274814,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048326864366132397,
|
|
"loss": 6.3828,
|
|
"mean_token_accuracy": 0.13175043165683747,
|
|
"num_tokens": 26879173.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 6.616425943374634,
|
|
"epoch": 1.329605650382578,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004832541727996335,
|
|
"loss": 6.2718,
|
|
"mean_token_accuracy": 0.13868370428681373,
|
|
"num_tokens": 26889839.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 6.5418168067932125,
|
|
"epoch": 1.330140724490342,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000483239695924633,
|
|
"loss": 6.3353,
|
|
"mean_token_accuracy": 0.1352730169892311,
|
|
"num_tokens": 26900217.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 6.565599632263184,
|
|
"epoch": 1.330675798598106,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048322521303674064,
|
|
"loss": 6.3739,
|
|
"mean_token_accuracy": 0.1279870606958866,
|
|
"num_tokens": 26911366.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 6.619361162185669,
|
|
"epoch": 1.3312108727058698,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048321072413637454,
|
|
"loss": 6.385,
|
|
"mean_token_accuracy": 0.12501162439584732,
|
|
"num_tokens": 26922135.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 6.585391473770142,
|
|
"epoch": 1.3317459468136337,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004831962292239529,
|
|
"loss": 6.3169,
|
|
"mean_token_accuracy": 0.13367662131786345,
|
|
"num_tokens": 26932502.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 6.574379014968872,
|
|
"epoch": 1.3322810209213976,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048318172829989447,
|
|
"loss": 6.3794,
|
|
"mean_token_accuracy": 0.13536484241485597,
|
|
"num_tokens": 26944607.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 6.629435062408447,
|
|
"epoch": 1.3328160950291617,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004831672213646179,
|
|
"loss": 6.3973,
|
|
"mean_token_accuracy": 0.12481540963053703,
|
|
"num_tokens": 26955205.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 6.570341920852661,
|
|
"epoch": 1.3333511691369255,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004831527084185421,
|
|
"loss": 6.2658,
|
|
"mean_token_accuracy": 0.13952928259968758,
|
|
"num_tokens": 26965558.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 6.554873085021972,
|
|
"epoch": 1.3338862432446894,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000483138189462086,
|
|
"loss": 6.3542,
|
|
"mean_token_accuracy": 0.12495403513312339,
|
|
"num_tokens": 26976176.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 6.592781829833984,
|
|
"epoch": 1.3344213173524533,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048312366449566895,
|
|
"loss": 6.3918,
|
|
"mean_token_accuracy": 0.13018057197332383,
|
|
"num_tokens": 26987099.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 6.579855346679688,
|
|
"epoch": 1.3349563914602172,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004831091335197104,
|
|
"loss": 6.3462,
|
|
"mean_token_accuracy": 0.13035789281129836,
|
|
"num_tokens": 26998122.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 6.547423696517944,
|
|
"epoch": 1.3354914655679813,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004830945965346298,
|
|
"loss": 6.3081,
|
|
"mean_token_accuracy": 0.13053423389792443,
|
|
"num_tokens": 27009427.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 6.6564727306365965,
|
|
"epoch": 1.3360265396757451,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000483080053540847,
|
|
"loss": 6.4419,
|
|
"mean_token_accuracy": 0.12713983058929443,
|
|
"num_tokens": 27020701.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 6.637810945510864,
|
|
"epoch": 1.336561613783509,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004830655045387818,
|
|
"loss": 6.4197,
|
|
"mean_token_accuracy": 0.1186198964715004,
|
|
"num_tokens": 27033215.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 6.589784765243531,
|
|
"epoch": 1.337096687891273,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048305094952885453,
|
|
"loss": 6.3834,
|
|
"mean_token_accuracy": 0.12432724684476852,
|
|
"num_tokens": 27043846.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 6.597361898422241,
|
|
"epoch": 1.3376317619990368,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004830363885114853,
|
|
"loss": 6.3557,
|
|
"mean_token_accuracy": 0.1265014812350273,
|
|
"num_tokens": 27054783.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 6.600591659545898,
|
|
"epoch": 1.3381668361068009,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004830218214870946,
|
|
"loss": 6.3724,
|
|
"mean_token_accuracy": 0.1325926035642624,
|
|
"num_tokens": 27066051.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 6.624477815628052,
|
|
"epoch": 1.3387019102145647,
|
|
"grad_norm": 6.5,
|
|
"learning_rate": 0.0004830072484561029,
|
|
"loss": 6.3835,
|
|
"mean_token_accuracy": 0.1292451150715351,
|
|
"num_tokens": 27078210.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 6.61891360282898,
|
|
"epoch": 1.3392369843223286,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004829926694189312,
|
|
"loss": 6.4121,
|
|
"mean_token_accuracy": 0.12096209973096847,
|
|
"num_tokens": 27089693.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 6.622095584869385,
|
|
"epoch": 1.3397720584300925,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004829780843760005,
|
|
"loss": 6.3897,
|
|
"mean_token_accuracy": 0.12635833844542504,
|
|
"num_tokens": 27099856.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 6.63506121635437,
|
|
"epoch": 1.3403071325378564,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004829634933277317,
|
|
"loss": 6.3873,
|
|
"mean_token_accuracy": 0.12386054396629334,
|
|
"num_tokens": 27110218.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 6.625727653503418,
|
|
"epoch": 1.3408422066456205,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048294889627454636,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.1346342645585537,
|
|
"num_tokens": 27120911.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 6.5528974533081055,
|
|
"epoch": 1.3413772807533844,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048293429321686585,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.13078240528702736,
|
|
"num_tokens": 27130964.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 6.550209426879883,
|
|
"epoch": 1.3419123548611482,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048291968415511174,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.13092748299241067,
|
|
"num_tokens": 27141641.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 6.626099395751953,
|
|
"epoch": 1.3424474289689121,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048290506908970607,
|
|
"loss": 6.4168,
|
|
"mean_token_accuracy": 0.12614600136876106,
|
|
"num_tokens": 27152591.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 6.666768598556518,
|
|
"epoch": 1.342982503076676,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004828904480210707,
|
|
"loss": 6.4706,
|
|
"mean_token_accuracy": 0.123383067548275,
|
|
"num_tokens": 27163839.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 6.641320657730103,
|
|
"epoch": 1.34351757718444,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004828758209496278,
|
|
"loss": 6.3585,
|
|
"mean_token_accuracy": 0.1279606707394123,
|
|
"num_tokens": 27174480.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 6.5603704929351805,
|
|
"epoch": 1.344052651292204,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048286118787579983,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.12910617887973785,
|
|
"num_tokens": 27184546.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 6.56231803894043,
|
|
"epoch": 1.3445877253999678,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048284654880000933,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.1368211105465889,
|
|
"num_tokens": 27195093.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 6.568918895721436,
|
|
"epoch": 1.345122799507732,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048283190372267886,
|
|
"loss": 6.3935,
|
|
"mean_token_accuracy": 0.13006186336278916,
|
|
"num_tokens": 27206416.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 6.61799693107605,
|
|
"epoch": 1.3456578736154958,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004828172526442314,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.1300834983587265,
|
|
"num_tokens": 27215533.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 6.623281192779541,
|
|
"epoch": 1.3461929477232597,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048280259556509,
|
|
"loss": 6.3468,
|
|
"mean_token_accuracy": 0.13039425238966942,
|
|
"num_tokens": 27225985.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 6.565938711166382,
|
|
"epoch": 1.3467280218310236,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004827879324856778,
|
|
"loss": 6.3517,
|
|
"mean_token_accuracy": 0.12926654145121574,
|
|
"num_tokens": 27235967.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 6.577709770202636,
|
|
"epoch": 1.3472630959387875,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048277326340641835,
|
|
"loss": 6.2763,
|
|
"mean_token_accuracy": 0.12951302751898766,
|
|
"num_tokens": 27246854.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 6.572338104248047,
|
|
"epoch": 1.3477981700465516,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000482758588327735,
|
|
"loss": 6.4001,
|
|
"mean_token_accuracy": 0.12966013476252555,
|
|
"num_tokens": 27256640.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 6.568337106704712,
|
|
"epoch": 1.3483332441543154,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004827439072500516,
|
|
"loss": 6.3693,
|
|
"mean_token_accuracy": 0.1308149516582489,
|
|
"num_tokens": 27266907.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 6.620267105102539,
|
|
"epoch": 1.3488683182620793,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048272922017379217,
|
|
"loss": 6.3317,
|
|
"mean_token_accuracy": 0.1307833433151245,
|
|
"num_tokens": 27277089.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 6.627926874160766,
|
|
"epoch": 1.3494033923698432,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004827145270993807,
|
|
"loss": 6.3394,
|
|
"mean_token_accuracy": 0.12991833537817002,
|
|
"num_tokens": 27286781.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 6.585339832305908,
|
|
"epoch": 1.349938466477607,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004826998280272414,
|
|
"loss": 6.3501,
|
|
"mean_token_accuracy": 0.13416332229971886,
|
|
"num_tokens": 27298011.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 6.564283943176269,
|
|
"epoch": 1.3504735405853712,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048268512295779873,
|
|
"loss": 6.385,
|
|
"mean_token_accuracy": 0.1316216245293617,
|
|
"num_tokens": 27309052.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 6.571522521972656,
|
|
"epoch": 1.351008614693135,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004826704118914773,
|
|
"loss": 6.3042,
|
|
"mean_token_accuracy": 0.13217932134866714,
|
|
"num_tokens": 27319945.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 6.5877281665802006,
|
|
"epoch": 1.351543688800899,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000482655694828702,
|
|
"loss": 6.3359,
|
|
"mean_token_accuracy": 0.1368803173303604,
|
|
"num_tokens": 27330543.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 6.612066173553467,
|
|
"epoch": 1.3520787629086628,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004826409717698976,
|
|
"loss": 6.3892,
|
|
"mean_token_accuracy": 0.12858008369803428,
|
|
"num_tokens": 27341957.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 6.595304107666015,
|
|
"epoch": 1.3526138370164267,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048262624271548936,
|
|
"loss": 6.3067,
|
|
"mean_token_accuracy": 0.13112107515335084,
|
|
"num_tokens": 27351506.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 6.6177770614624025,
|
|
"epoch": 1.3531489111241908,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048261150766590257,
|
|
"loss": 6.3076,
|
|
"mean_token_accuracy": 0.1281954102218151,
|
|
"num_tokens": 27362208.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 6.605959463119507,
|
|
"epoch": 1.3536839852319547,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048259676662156263,
|
|
"loss": 6.3339,
|
|
"mean_token_accuracy": 0.13110242784023285,
|
|
"num_tokens": 27372890.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 6.540311479568482,
|
|
"epoch": 1.3542190593397185,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004825820195828952,
|
|
"loss": 6.271,
|
|
"mean_token_accuracy": 0.1387062557041645,
|
|
"num_tokens": 27382879.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 6.519589185714722,
|
|
"epoch": 1.3547541334474824,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004825672665503262,
|
|
"loss": 6.3092,
|
|
"mean_token_accuracy": 0.13326845392584802,
|
|
"num_tokens": 27393878.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 6.586039400100708,
|
|
"epoch": 1.3552892075552463,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004825525075242815,
|
|
"loss": 6.4122,
|
|
"mean_token_accuracy": 0.12758183032274245,
|
|
"num_tokens": 27404928.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 6.633420610427857,
|
|
"epoch": 1.3558242816630104,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004825377425051873,
|
|
"loss": 6.3288,
|
|
"mean_token_accuracy": 0.12901380732655526,
|
|
"num_tokens": 27417473.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 6.643004465103149,
|
|
"epoch": 1.3563593557707743,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048252297149346997,
|
|
"loss": 6.4087,
|
|
"mean_token_accuracy": 0.12803613692522048,
|
|
"num_tokens": 27428378.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 6.5344377040863035,
|
|
"epoch": 1.3568944298785381,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048250819448955595,
|
|
"loss": 6.3608,
|
|
"mean_token_accuracy": 0.13350652530789375,
|
|
"num_tokens": 27438815.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 6.620766830444336,
|
|
"epoch": 1.357429503986302,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000482493411493872,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.12947804257273673,
|
|
"num_tokens": 27449295.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 6.579486465454101,
|
|
"epoch": 1.357964578094066,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000482478622506845,
|
|
"loss": 6.2669,
|
|
"mean_token_accuracy": 0.13803085759282113,
|
|
"num_tokens": 27459357.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 6.61570258140564,
|
|
"epoch": 1.35849965220183,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004824638275289019,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.13059483245015144,
|
|
"num_tokens": 27469405.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 6.619598150253296,
|
|
"epoch": 1.3590347263095939,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004824490265604699,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.13048040643334388,
|
|
"num_tokens": 27478818.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 6.601237964630127,
|
|
"epoch": 1.3595698004173578,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004824342196019764,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.13243394419550897,
|
|
"num_tokens": 27488631.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 6.595383882522583,
|
|
"epoch": 1.3601048745251219,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048241940665384904,
|
|
"loss": 6.3663,
|
|
"mean_token_accuracy": 0.1266361244022846,
|
|
"num_tokens": 27500895.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 6.592416715621948,
|
|
"epoch": 1.3606399486328857,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004824045877165154,
|
|
"loss": 6.3935,
|
|
"mean_token_accuracy": 0.1242723323404789,
|
|
"num_tokens": 27512578.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 6.608439874649048,
|
|
"epoch": 1.3611750227406496,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00048238976279040344,
|
|
"loss": 6.3366,
|
|
"mean_token_accuracy": 0.12849029004573823,
|
|
"num_tokens": 27523448.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 6.5693199634552,
|
|
"epoch": 1.3617100968484135,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004823749318759413,
|
|
"loss": 6.4164,
|
|
"mean_token_accuracy": 0.12786906361579894,
|
|
"num_tokens": 27534919.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 6.515962362289429,
|
|
"epoch": 1.3622451709561774,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000482360094973557,
|
|
"loss": 6.2237,
|
|
"mean_token_accuracy": 0.1343452215194702,
|
|
"num_tokens": 27545603.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 6.61792778968811,
|
|
"epoch": 1.3627802450639415,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004823452520836792,
|
|
"loss": 6.3766,
|
|
"mean_token_accuracy": 0.1248759537935257,
|
|
"num_tokens": 27556868.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 6.687754726409912,
|
|
"epoch": 1.3633153191717053,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00048233040320673634,
|
|
"loss": 6.4844,
|
|
"mean_token_accuracy": 0.12039017677307129,
|
|
"num_tokens": 27567200.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 6.57903151512146,
|
|
"epoch": 1.3638503932794692,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048231554834315716,
|
|
"loss": 6.2985,
|
|
"mean_token_accuracy": 0.13346220403909684,
|
|
"num_tokens": 27577759.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 6.601617813110352,
|
|
"epoch": 1.364385467387233,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004823006874933708,
|
|
"loss": 6.4142,
|
|
"mean_token_accuracy": 0.1205790437757969,
|
|
"num_tokens": 27588935.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 6.614251899719238,
|
|
"epoch": 1.364920541494997,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004822858206578061,
|
|
"loss": 6.3382,
|
|
"mean_token_accuracy": 0.12518487870693207,
|
|
"num_tokens": 27600306.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 6.63030424118042,
|
|
"epoch": 1.365455615602761,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048227094783689244,
|
|
"loss": 6.394,
|
|
"mean_token_accuracy": 0.1275814175605774,
|
|
"num_tokens": 27612322.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 6.648936557769775,
|
|
"epoch": 1.365990689710525,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004822560690310594,
|
|
"loss": 6.3488,
|
|
"mean_token_accuracy": 0.13583381846547127,
|
|
"num_tokens": 27623812.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 6.558746480941773,
|
|
"epoch": 1.3665257638182888,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048224118424073644,
|
|
"loss": 6.2346,
|
|
"mean_token_accuracy": 0.13194585591554642,
|
|
"num_tokens": 27633848.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 6.554841423034668,
|
|
"epoch": 1.3670608379260527,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048222629346635336,
|
|
"loss": 6.3488,
|
|
"mean_token_accuracy": 0.13625205904245377,
|
|
"num_tokens": 27644641.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 6.561163997650146,
|
|
"epoch": 1.3675959120338166,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048221139670834025,
|
|
"loss": 6.3259,
|
|
"mean_token_accuracy": 0.13467152640223504,
|
|
"num_tokens": 27655552.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 6.5596569061279295,
|
|
"epoch": 1.3681309861415807,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004821964939671272,
|
|
"loss": 6.3263,
|
|
"mean_token_accuracy": 0.13799864649772645,
|
|
"num_tokens": 27666396.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 6.644745874404907,
|
|
"epoch": 1.3686660602493446,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004821815852431444,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.13380141332745552,
|
|
"num_tokens": 27676522.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 6.56404070854187,
|
|
"epoch": 1.3692011343571084,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048216667053682243,
|
|
"loss": 6.3135,
|
|
"mean_token_accuracy": 0.1311247631907463,
|
|
"num_tokens": 27687088.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 6.582688570022583,
|
|
"epoch": 1.3697362084648723,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048215174984859207,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.13514762818813325,
|
|
"num_tokens": 27697587.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 6.525529861450195,
|
|
"epoch": 1.3702712825726362,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000482136823178884,
|
|
"loss": 6.2543,
|
|
"mean_token_accuracy": 0.1358187973499298,
|
|
"num_tokens": 27708345.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 6.670403385162354,
|
|
"epoch": 1.3708063566804003,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004821218905281292,
|
|
"loss": 6.4555,
|
|
"mean_token_accuracy": 0.12325085550546647,
|
|
"num_tokens": 27719592.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 6.620159435272217,
|
|
"epoch": 1.3713414307881642,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000482106951896759,
|
|
"loss": 6.3546,
|
|
"mean_token_accuracy": 0.12938541024923325,
|
|
"num_tokens": 27730071.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 6.57355146408081,
|
|
"epoch": 1.371876504895928,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048209200728520466,
|
|
"loss": 6.3719,
|
|
"mean_token_accuracy": 0.12745627611875535,
|
|
"num_tokens": 27740514.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 6.620172834396362,
|
|
"epoch": 1.372411579003692,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048207705669389765,
|
|
"loss": 6.39,
|
|
"mean_token_accuracy": 0.12893705070018768,
|
|
"num_tokens": 27752088.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 6.708187437057495,
|
|
"epoch": 1.3729466531114558,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048206210012326976,
|
|
"loss": 6.4054,
|
|
"mean_token_accuracy": 0.12661417871713637,
|
|
"num_tokens": 27763401.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 6.670238971710205,
|
|
"epoch": 1.37348172721922,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048204713757375283,
|
|
"loss": 6.3297,
|
|
"mean_token_accuracy": 0.1316835328936577,
|
|
"num_tokens": 27773665.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 6.581043910980225,
|
|
"epoch": 1.3740168013269838,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004820321690457789,
|
|
"loss": 6.355,
|
|
"mean_token_accuracy": 0.1313697040081024,
|
|
"num_tokens": 27785474.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 6.592387914657593,
|
|
"epoch": 1.3745518754347477,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048201719453978023,
|
|
"loss": 6.3809,
|
|
"mean_token_accuracy": 0.12963244542479516,
|
|
"num_tokens": 27796520.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 6.688526439666748,
|
|
"epoch": 1.3750869495425118,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004820022140561891,
|
|
"loss": 6.4398,
|
|
"mean_token_accuracy": 0.12583799585700034,
|
|
"num_tokens": 27807559.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 6.668413877487183,
|
|
"epoch": 1.3756220236502756,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004819872275954381,
|
|
"loss": 6.3889,
|
|
"mean_token_accuracy": 0.12827387154102327,
|
|
"num_tokens": 27818208.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 6.614689493179322,
|
|
"epoch": 1.3761570977580395,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048197223515796,
|
|
"loss": 6.2723,
|
|
"mean_token_accuracy": 0.13356864601373672,
|
|
"num_tokens": 27828238.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 6.6167707443237305,
|
|
"epoch": 1.3766921718658034,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004819572367441877,
|
|
"loss": 6.3731,
|
|
"mean_token_accuracy": 0.13847080767154693,
|
|
"num_tokens": 27837885.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 6.5865741729736325,
|
|
"epoch": 1.3772272459735673,
|
|
"grad_norm": 11.5,
|
|
"learning_rate": 0.0004819422323545543,
|
|
"loss": 6.2727,
|
|
"mean_token_accuracy": 0.1372750759124756,
|
|
"num_tokens": 27847425.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 6.53502926826477,
|
|
"epoch": 1.3777623200813314,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000481927221989493,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.12697343453764914,
|
|
"num_tokens": 27859606.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 6.658491897583008,
|
|
"epoch": 1.3782973941890952,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004819122056494373,
|
|
"loss": 6.4114,
|
|
"mean_token_accuracy": 0.12896035313606263,
|
|
"num_tokens": 27871651.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 6.66093635559082,
|
|
"epoch": 1.3788324682968591,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.00048189718333482064,
|
|
"loss": 6.358,
|
|
"mean_token_accuracy": 0.12694099694490432,
|
|
"num_tokens": 27883138.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 6.738395357131958,
|
|
"epoch": 1.379367542404623,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000481882155046077,
|
|
"loss": 6.3991,
|
|
"mean_token_accuracy": 0.1284925326704979,
|
|
"num_tokens": 27893597.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 6.611962938308716,
|
|
"epoch": 1.3799026165123869,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048186712078364006,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.13274351134896278,
|
|
"num_tokens": 27904249.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 6.533528184890747,
|
|
"epoch": 1.380437690620151,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048185208054794414,
|
|
"loss": 6.3593,
|
|
"mean_token_accuracy": 0.12732080221176148,
|
|
"num_tokens": 27914713.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 6.572548866271973,
|
|
"epoch": 1.3809727647279149,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004818370343394235,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.13676211312413217,
|
|
"num_tokens": 27926257.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 6.64458384513855,
|
|
"epoch": 1.3815078388356787,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004818219821585125,
|
|
"loss": 6.3412,
|
|
"mean_token_accuracy": 0.13467023223638536,
|
|
"num_tokens": 27936839.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 6.692562866210937,
|
|
"epoch": 1.3820429129434426,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00048180692400564586,
|
|
"loss": 6.4241,
|
|
"mean_token_accuracy": 0.12410069778561592,
|
|
"num_tokens": 27946318.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 6.720388555526734,
|
|
"epoch": 1.3825779870512065,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048179185988125834,
|
|
"loss": 6.4459,
|
|
"mean_token_accuracy": 0.1252230815589428,
|
|
"num_tokens": 27956990.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 6.669422721862793,
|
|
"epoch": 1.3831130611589706,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000481776789785785,
|
|
"loss": 6.3693,
|
|
"mean_token_accuracy": 0.12451653853058815,
|
|
"num_tokens": 27968187.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 6.647035694122314,
|
|
"epoch": 1.3836481352667345,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048176171371966083,
|
|
"loss": 6.4067,
|
|
"mean_token_accuracy": 0.13051214665174485,
|
|
"num_tokens": 27978337.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 6.6763252258300785,
|
|
"epoch": 1.3841832093744983,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004817466316833212,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.12042975053191185,
|
|
"num_tokens": 27988681.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 6.593517208099366,
|
|
"epoch": 1.3847182834822622,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004817315436772017,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.13919395804405213,
|
|
"num_tokens": 27999233.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 6.621525669097901,
|
|
"epoch": 1.385253357590026,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004817164497017379,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.12791991606354713,
|
|
"num_tokens": 28010242.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 6.584107303619385,
|
|
"epoch": 1.3857884316977902,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004817013497573656,
|
|
"loss": 6.3744,
|
|
"mean_token_accuracy": 0.1282438851892948,
|
|
"num_tokens": 28020424.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 6.673630714416504,
|
|
"epoch": 1.386323505805554,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.000481686243844521,
|
|
"loss": 6.3471,
|
|
"mean_token_accuracy": 0.12757782638072968,
|
|
"num_tokens": 28030287.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 6.664624214172363,
|
|
"epoch": 1.386858579913318,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048167113196364,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.13078064545989038,
|
|
"num_tokens": 28039997.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 6.591899871826172,
|
|
"epoch": 1.387393654021082,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004816560141151593,
|
|
"loss": 6.3371,
|
|
"mean_token_accuracy": 0.12622947618365288,
|
|
"num_tokens": 28051381.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 6.580440187454224,
|
|
"epoch": 1.3879287281288457,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004816408902995151,
|
|
"loss": 6.3176,
|
|
"mean_token_accuracy": 0.12461889162659645,
|
|
"num_tokens": 28063603.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 6.596974945068359,
|
|
"epoch": 1.3884638022366098,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004816257605171442,
|
|
"loss": 6.2905,
|
|
"mean_token_accuracy": 0.1363251030445099,
|
|
"num_tokens": 28073942.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 6.5933913230896,
|
|
"epoch": 1.3889988763443737,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.00048161062476848363,
|
|
"loss": 6.3395,
|
|
"mean_token_accuracy": 0.1304040066897869,
|
|
"num_tokens": 28083837.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 6.552693700790405,
|
|
"epoch": 1.3895339504521376,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004815954830539702,
|
|
"loss": 6.285,
|
|
"mean_token_accuracy": 0.12951438948512078,
|
|
"num_tokens": 28094150.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 6.577668046951294,
|
|
"epoch": 1.3900690245599017,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048158033537404126,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.13384350165724754,
|
|
"num_tokens": 28106345.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 6.6146971702575685,
|
|
"epoch": 1.3906040986676655,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048156518172913417,
|
|
"loss": 6.2686,
|
|
"mean_token_accuracy": 0.1282735824584961,
|
|
"num_tokens": 28116858.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 6.592422389984131,
|
|
"epoch": 1.3911391727754294,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004815500221196865,
|
|
"loss": 6.4411,
|
|
"mean_token_accuracy": 0.1247103713452816,
|
|
"num_tokens": 28128390.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 6.562520170211792,
|
|
"epoch": 1.3916742468831933,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.00048153485654613587,
|
|
"loss": 6.2916,
|
|
"mean_token_accuracy": 0.13480843007564544,
|
|
"num_tokens": 28139421.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 6.628579950332641,
|
|
"epoch": 1.3922093209909572,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048151968500892043,
|
|
"loss": 6.3663,
|
|
"mean_token_accuracy": 0.13195326849818229,
|
|
"num_tokens": 28151076.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 6.736280298233032,
|
|
"epoch": 1.3927443950987213,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048150450750847795,
|
|
"loss": 6.4838,
|
|
"mean_token_accuracy": 0.1264195993542671,
|
|
"num_tokens": 28162079.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 6.624205017089844,
|
|
"epoch": 1.3932794692064852,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000481489324045247,
|
|
"loss": 6.3978,
|
|
"mean_token_accuracy": 0.12501806691288947,
|
|
"num_tokens": 28174442.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 6.583037090301514,
|
|
"epoch": 1.393814543314249,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048147413461966564,
|
|
"loss": 6.2814,
|
|
"mean_token_accuracy": 0.13096126466989516,
|
|
"num_tokens": 28184643.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 6.509779596328736,
|
|
"epoch": 1.394349617422013,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048145893923217276,
|
|
"loss": 6.3026,
|
|
"mean_token_accuracy": 0.13648300170898436,
|
|
"num_tokens": 28194021.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 6.6351330280303955,
|
|
"epoch": 1.3948846915297768,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004814437378832071,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.12254319339990616,
|
|
"num_tokens": 28204750.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 6.713905620574951,
|
|
"epoch": 1.3954197656375409,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004814285305732074,
|
|
"loss": 6.4425,
|
|
"mean_token_accuracy": 0.12344540283083916,
|
|
"num_tokens": 28216499.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 6.671940326690674,
|
|
"epoch": 1.3959548397453048,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048141331730261293,
|
|
"loss": 6.3623,
|
|
"mean_token_accuracy": 0.1292126715183258,
|
|
"num_tokens": 28226573.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 6.593534851074219,
|
|
"epoch": 1.3964899138530686,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000481398098071863,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.13186879456043243,
|
|
"num_tokens": 28236688.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 6.586943054199219,
|
|
"epoch": 1.3970249879608325,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048138287288139686,
|
|
"loss": 6.3871,
|
|
"mean_token_accuracy": 0.12688189446926118,
|
|
"num_tokens": 28247477.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 6.5892548084259035,
|
|
"epoch": 1.3975600620685964,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004813676417316543,
|
|
"loss": 6.3688,
|
|
"mean_token_accuracy": 0.12888751700520515,
|
|
"num_tokens": 28258286.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 6.704712629318237,
|
|
"epoch": 1.3980951361763605,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004813524046230751,
|
|
"loss": 6.4949,
|
|
"mean_token_accuracy": 0.1232834629714489,
|
|
"num_tokens": 28268587.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 6.729250717163086,
|
|
"epoch": 1.3986302102841244,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00048133716155609926,
|
|
"loss": 6.4084,
|
|
"mean_token_accuracy": 0.12168680354952813,
|
|
"num_tokens": 28279352.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 6.6169415473937985,
|
|
"epoch": 1.3991652843918883,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004813219125311668,
|
|
"loss": 6.3157,
|
|
"mean_token_accuracy": 0.1302192322909832,
|
|
"num_tokens": 28290114.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 6.597529935836792,
|
|
"epoch": 1.3997003584996521,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048130665754871814,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.1209537997841835,
|
|
"num_tokens": 28301845.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 6.680888223648071,
|
|
"epoch": 1.400235432607416,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048129139660919374,
|
|
"loss": 6.384,
|
|
"mean_token_accuracy": 0.12530855163931848,
|
|
"num_tokens": 28313162.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 6.626790380477905,
|
|
"epoch": 1.40077050671518,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048127612971303425,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.1309482030570507,
|
|
"num_tokens": 28323888.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 6.5893645763397215,
|
|
"epoch": 1.401305580822944,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004812608568606805,
|
|
"loss": 6.377,
|
|
"mean_token_accuracy": 0.12815819457173347,
|
|
"num_tokens": 28333735.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 6.621941804885864,
|
|
"epoch": 1.4018406549307079,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004812455780525735,
|
|
"loss": 6.3617,
|
|
"mean_token_accuracy": 0.12557571679353713,
|
|
"num_tokens": 28343947.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 6.640798091888428,
|
|
"epoch": 1.402375729038472,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004812302932891544,
|
|
"loss": 6.4296,
|
|
"mean_token_accuracy": 0.12175943478941917,
|
|
"num_tokens": 28354635.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 6.6373186111450195,
|
|
"epoch": 1.4029108031462356,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004812150025708646,
|
|
"loss": 6.3621,
|
|
"mean_token_accuracy": 0.12661642208695412,
|
|
"num_tokens": 28365392.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 6.64743185043335,
|
|
"epoch": 1.4034458772539997,
|
|
"grad_norm": 6.375,
|
|
"learning_rate": 0.00048119970589814557,
|
|
"loss": 6.3661,
|
|
"mean_token_accuracy": 0.12275204285979271,
|
|
"num_tokens": 28376527.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 6.616475629806518,
|
|
"epoch": 1.4039809513617636,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004811844032714389,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.13551399856805801,
|
|
"num_tokens": 28387178.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 6.58491530418396,
|
|
"epoch": 1.4045160254695275,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048116909469118663,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.13240195885300637,
|
|
"num_tokens": 28397578.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 6.617512989044189,
|
|
"epoch": 1.4050510995772916,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004811537801578308,
|
|
"loss": 6.3925,
|
|
"mean_token_accuracy": 0.12425144463777542,
|
|
"num_tokens": 28408933.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 6.592165422439575,
|
|
"epoch": 1.4055861736850555,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048113845967181346,
|
|
"loss": 6.3777,
|
|
"mean_token_accuracy": 0.12327618971467018,
|
|
"num_tokens": 28421906.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 6.6013805866241455,
|
|
"epoch": 1.4061212477928193,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000481123133233577,
|
|
"loss": 6.3131,
|
|
"mean_token_accuracy": 0.13026589453220366,
|
|
"num_tokens": 28432677.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 6.606744003295899,
|
|
"epoch": 1.4066563219005832,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048110780084356414,
|
|
"loss": 6.4197,
|
|
"mean_token_accuracy": 0.1275110200047493,
|
|
"num_tokens": 28443795.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 6.589348840713501,
|
|
"epoch": 1.407191396008347,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004810924625022174,
|
|
"loss": 6.3913,
|
|
"mean_token_accuracy": 0.12912026047706604,
|
|
"num_tokens": 28455727.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 6.6983531475067135,
|
|
"epoch": 1.4077264701161112,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004810771182099799,
|
|
"loss": 6.4284,
|
|
"mean_token_accuracy": 0.12160902246832847,
|
|
"num_tokens": 28467554.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 6.7027562141418455,
|
|
"epoch": 1.408261544223875,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004810617679672945,
|
|
"loss": 6.4021,
|
|
"mean_token_accuracy": 0.1304725468158722,
|
|
"num_tokens": 28479268.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 6.677223873138428,
|
|
"epoch": 1.408796618331639,
|
|
"grad_norm": 6.5625,
|
|
"learning_rate": 0.00048104641177460443,
|
|
"loss": 6.4063,
|
|
"mean_token_accuracy": 0.12386099174618721,
|
|
"num_tokens": 28489887.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 6.551987886428833,
|
|
"epoch": 1.4093316924394028,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004810310496323533,
|
|
"loss": 6.2927,
|
|
"mean_token_accuracy": 0.13378867208957673,
|
|
"num_tokens": 28500736.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 6.558706378936767,
|
|
"epoch": 1.4098667665471667,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.00048101568154098446,
|
|
"loss": 6.2682,
|
|
"mean_token_accuracy": 0.1404990591108799,
|
|
"num_tokens": 28511458.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 6.66455078125,
|
|
"epoch": 1.4104018406549308,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048100030750094185,
|
|
"loss": 6.3987,
|
|
"mean_token_accuracy": 0.12589067593216896,
|
|
"num_tokens": 28522354.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 6.555455827713013,
|
|
"epoch": 1.4109369147626947,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004809849275126693,
|
|
"loss": 6.2614,
|
|
"mean_token_accuracy": 0.13627382293343543,
|
|
"num_tokens": 28533061.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 6.5754310131073,
|
|
"epoch": 1.4114719888704585,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048096954157661085,
|
|
"loss": 6.3924,
|
|
"mean_token_accuracy": 0.1316654436290264,
|
|
"num_tokens": 28544230.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 6.613294839859009,
|
|
"epoch": 1.4120070629782224,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048095414969321086,
|
|
"loss": 6.3924,
|
|
"mean_token_accuracy": 0.13182601183652878,
|
|
"num_tokens": 28555461.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 6.644679880142212,
|
|
"epoch": 1.4125421370859863,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048093875186291376,
|
|
"loss": 6.2965,
|
|
"mean_token_accuracy": 0.13477271869778634,
|
|
"num_tokens": 28565992.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 6.6228475093841555,
|
|
"epoch": 1.4130772111937504,
|
|
"grad_norm": 6.03125,
|
|
"learning_rate": 0.00048092334808616413,
|
|
"loss": 6.2934,
|
|
"mean_token_accuracy": 0.13527860194444657,
|
|
"num_tokens": 28575802.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 6.580503511428833,
|
|
"epoch": 1.4136122853015143,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004809079383634067,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.13500296846032142,
|
|
"num_tokens": 28586982.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 6.603396081924439,
|
|
"epoch": 1.4141473594092782,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048089252269508656,
|
|
"loss": 6.3904,
|
|
"mean_token_accuracy": 0.12892565801739692,
|
|
"num_tokens": 28598267.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 6.641662168502807,
|
|
"epoch": 1.414682433517042,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048087710108164874,
|
|
"loss": 6.3417,
|
|
"mean_token_accuracy": 0.1294536255300045,
|
|
"num_tokens": 28608213.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 6.601648187637329,
|
|
"epoch": 1.415217507624806,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004808616735235385,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.1245055764913559,
|
|
"num_tokens": 28619674.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 6.62523717880249,
|
|
"epoch": 1.41575258173257,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004808462400212014,
|
|
"loss": 6.2724,
|
|
"mean_token_accuracy": 0.1302603393793106,
|
|
"num_tokens": 28630824.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 6.591723203659058,
|
|
"epoch": 1.416287655840334,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048083080057508313,
|
|
"loss": 6.3908,
|
|
"mean_token_accuracy": 0.12700947895646095,
|
|
"num_tokens": 28642270.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 6.602076721191406,
|
|
"epoch": 1.4168227299480978,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.00048081535518562933,
|
|
"loss": 6.3972,
|
|
"mean_token_accuracy": 0.12245190143585205,
|
|
"num_tokens": 28653649.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 6.564943265914917,
|
|
"epoch": 1.4173578040558619,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000480799903853286,
|
|
"loss": 6.2562,
|
|
"mean_token_accuracy": 0.12602358609437941,
|
|
"num_tokens": 28664044.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 6.617947673797607,
|
|
"epoch": 1.4178928781636255,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004807844465784995,
|
|
"loss": 6.3541,
|
|
"mean_token_accuracy": 0.13284602165222167,
|
|
"num_tokens": 28675394.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 6.612474155426026,
|
|
"epoch": 1.4184279522713896,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.00048076898336171596,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.13681749477982522,
|
|
"num_tokens": 28686292.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 6.584032297134399,
|
|
"epoch": 1.4189630263791535,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048075351420338196,
|
|
"loss": 6.3764,
|
|
"mean_token_accuracy": 0.1290843293070793,
|
|
"num_tokens": 28696928.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 6.570753574371338,
|
|
"epoch": 1.4194981004869174,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004807380391039441,
|
|
"loss": 6.3873,
|
|
"mean_token_accuracy": 0.12882263883948325,
|
|
"num_tokens": 28707986.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 6.682375240325928,
|
|
"epoch": 1.4200331745946815,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.00048072255806384936,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.12932803407311438,
|
|
"num_tokens": 28719296.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 6.626744413375855,
|
|
"epoch": 1.4205682487024454,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004807070710835447,
|
|
"loss": 6.2523,
|
|
"mean_token_accuracy": 0.13302616253495217,
|
|
"num_tokens": 28729523.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 6.661232042312622,
|
|
"epoch": 1.4211033228102092,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004806915781634771,
|
|
"loss": 6.3596,
|
|
"mean_token_accuracy": 0.12430754005908966,
|
|
"num_tokens": 28739026.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 6.613552522659302,
|
|
"epoch": 1.4216383969179731,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004806760793040942,
|
|
"loss": 6.4424,
|
|
"mean_token_accuracy": 0.1248494639992714,
|
|
"num_tokens": 28749513.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 6.654860591888427,
|
|
"epoch": 1.422173471025737,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048066057450584334,
|
|
"loss": 6.3509,
|
|
"mean_token_accuracy": 0.1307549335062504,
|
|
"num_tokens": 28760722.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 6.654392576217651,
|
|
"epoch": 1.422708545133501,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004806450637691723,
|
|
"loss": 6.2863,
|
|
"mean_token_accuracy": 0.14401507303118705,
|
|
"num_tokens": 28771235.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 6.6081953048706055,
|
|
"epoch": 1.423243619241265,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048062954709452907,
|
|
"loss": 6.311,
|
|
"mean_token_accuracy": 0.13087828755378722,
|
|
"num_tokens": 28782642.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 6.626807165145874,
|
|
"epoch": 1.4237786933490288,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004806140244823615,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.12405307367444038,
|
|
"num_tokens": 28793628.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 6.670015144348144,
|
|
"epoch": 1.4243137674567927,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048059849593311776,
|
|
"loss": 6.3931,
|
|
"mean_token_accuracy": 0.12888944670557975,
|
|
"num_tokens": 28804034.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 6.628258180618286,
|
|
"epoch": 1.4248488415645566,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004805829614472464,
|
|
"loss": 6.3194,
|
|
"mean_token_accuracy": 0.1301094688475132,
|
|
"num_tokens": 28814679.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 6.576900959014893,
|
|
"epoch": 1.4253839156723207,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048056742102519593,
|
|
"loss": 6.3567,
|
|
"mean_token_accuracy": 0.12895792871713638,
|
|
"num_tokens": 28825130.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 6.636476755142212,
|
|
"epoch": 1.4259189897800846,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048055187466741506,
|
|
"loss": 6.3732,
|
|
"mean_token_accuracy": 0.12868118211627005,
|
|
"num_tokens": 28835500.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 6.597569847106934,
|
|
"epoch": 1.4264540638878485,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004805363223743527,
|
|
"loss": 6.3274,
|
|
"mean_token_accuracy": 0.12981122508645057,
|
|
"num_tokens": 28845794.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 6.6778244972229,
|
|
"epoch": 1.4269891379956123,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004805207641464579,
|
|
"loss": 6.3308,
|
|
"mean_token_accuracy": 0.12735342979431152,
|
|
"num_tokens": 28856326.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 6.581173372268677,
|
|
"epoch": 1.4275242121033762,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004805051999841799,
|
|
"loss": 6.3424,
|
|
"mean_token_accuracy": 0.1278283827006817,
|
|
"num_tokens": 28867592.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 6.642857408523559,
|
|
"epoch": 1.4280592862111403,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004804896298879682,
|
|
"loss": 6.4574,
|
|
"mean_token_accuracy": 0.12210951149463653,
|
|
"num_tokens": 28880352.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 6.6689189910888675,
|
|
"epoch": 1.4285943603189042,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004804740538582723,
|
|
"loss": 6.3572,
|
|
"mean_token_accuracy": 0.1292126402258873,
|
|
"num_tokens": 28892012.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 6.676041507720948,
|
|
"epoch": 1.429129434426668,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004804584718955419,
|
|
"loss": 6.2927,
|
|
"mean_token_accuracy": 0.1330079071223736,
|
|
"num_tokens": 28902247.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 6.569883012771607,
|
|
"epoch": 1.429664508534432,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000480442884000227,
|
|
"loss": 6.42,
|
|
"mean_token_accuracy": 0.12373564317822457,
|
|
"num_tokens": 28913222.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 6.581786155700684,
|
|
"epoch": 1.4301995826421958,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004804272901727778,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.13108997717499732,
|
|
"num_tokens": 28924038.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 6.641871213912964,
|
|
"epoch": 1.43073465674996,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048041169041364437,
|
|
"loss": 6.3669,
|
|
"mean_token_accuracy": 0.13162143304944038,
|
|
"num_tokens": 28934448.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 6.629097509384155,
|
|
"epoch": 1.4312697308577238,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048039608472327724,
|
|
"loss": 6.3334,
|
|
"mean_token_accuracy": 0.13491066992282869,
|
|
"num_tokens": 28945175.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 6.586024236679077,
|
|
"epoch": 1.4318048049654877,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048038047310212706,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.13406300395727158,
|
|
"num_tokens": 28955116.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 6.587283611297607,
|
|
"epoch": 1.4323398790732518,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048036485555064454,
|
|
"loss": 6.3888,
|
|
"mean_token_accuracy": 0.12584230303764343,
|
|
"num_tokens": 28966999.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 6.580404567718506,
|
|
"epoch": 1.4328749531810157,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00048034923206928065,
|
|
"loss": 6.3525,
|
|
"mean_token_accuracy": 0.12539274096488953,
|
|
"num_tokens": 28977388.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 6.614728784561157,
|
|
"epoch": 1.4334100272887795,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048033360265848664,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.13612739443778993,
|
|
"num_tokens": 28987792.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 6.705612421035767,
|
|
"epoch": 1.4339451013965434,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048031796731871364,
|
|
"loss": 6.4048,
|
|
"mean_token_accuracy": 0.1264493465423584,
|
|
"num_tokens": 28998319.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 6.594354677200317,
|
|
"epoch": 1.4344801755043073,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048030232605041323,
|
|
"loss": 6.3813,
|
|
"mean_token_accuracy": 0.1269213505089283,
|
|
"num_tokens": 29007942.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 6.616457796096801,
|
|
"epoch": 1.4350152496120714,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004802866788540369,
|
|
"loss": 6.3303,
|
|
"mean_token_accuracy": 0.1318454623222351,
|
|
"num_tokens": 29018217.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 6.616905975341797,
|
|
"epoch": 1.4355503237198353,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004802710257300367,
|
|
"loss": 6.3681,
|
|
"mean_token_accuracy": 0.131587353348732,
|
|
"num_tokens": 29028472.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 6.612511110305786,
|
|
"epoch": 1.4360853978275991,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004802553666788644,
|
|
"loss": 6.3363,
|
|
"mean_token_accuracy": 0.13199962675571442,
|
|
"num_tokens": 29040553.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 6.662797737121582,
|
|
"epoch": 1.436620471935363,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048023970170097226,
|
|
"loss": 6.3631,
|
|
"mean_token_accuracy": 0.12540305629372597,
|
|
"num_tokens": 29050142.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 6.556989574432373,
|
|
"epoch": 1.437155546043127,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048022403079681254,
|
|
"loss": 6.3039,
|
|
"mean_token_accuracy": 0.12678081840276717,
|
|
"num_tokens": 29061762.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 6.580306100845337,
|
|
"epoch": 1.437690620150891,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048020835396683775,
|
|
"loss": 6.3768,
|
|
"mean_token_accuracy": 0.1283114917576313,
|
|
"num_tokens": 29072095.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 6.653733015060425,
|
|
"epoch": 1.4382256942586549,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048019267121150066,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.12650077268481255,
|
|
"num_tokens": 29082561.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 6.635895013809204,
|
|
"epoch": 1.4387607683664188,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048017698253125397,
|
|
"loss": 6.3331,
|
|
"mean_token_accuracy": 0.13035061061382294,
|
|
"num_tokens": 29093813.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 6.641666412353516,
|
|
"epoch": 1.4392958424741826,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004801612879265507,
|
|
"loss": 6.3233,
|
|
"mean_token_accuracy": 0.1321027010679245,
|
|
"num_tokens": 29104064.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 6.6342226505279545,
|
|
"epoch": 1.4398309165819465,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004801455873978442,
|
|
"loss": 6.3689,
|
|
"mean_token_accuracy": 0.124077807366848,
|
|
"num_tokens": 29115086.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 6.63504810333252,
|
|
"epoch": 1.4403659906897106,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.0004801298809455876,
|
|
"loss": 6.3229,
|
|
"mean_token_accuracy": 0.1360506758093834,
|
|
"num_tokens": 29125536.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 6.631965684890747,
|
|
"epoch": 1.4409010647974745,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004801141685702345,
|
|
"loss": 6.3905,
|
|
"mean_token_accuracy": 0.12729595750570297,
|
|
"num_tokens": 29137007.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 6.605051040649414,
|
|
"epoch": 1.4414361389052384,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048009845027223864,
|
|
"loss": 6.4037,
|
|
"mean_token_accuracy": 0.12139849811792373,
|
|
"num_tokens": 29147072.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 6.655103874206543,
|
|
"epoch": 1.4419712130130022,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048008272605205377,
|
|
"loss": 6.3599,
|
|
"mean_token_accuracy": 0.12759798988699914,
|
|
"num_tokens": 29157803.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 6.657844066619873,
|
|
"epoch": 1.4425062871207661,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048006699591013417,
|
|
"loss": 6.3337,
|
|
"mean_token_accuracy": 0.13097915574908256,
|
|
"num_tokens": 29168173.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 6.700314474105835,
|
|
"epoch": 1.4430413612285302,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004800512598469337,
|
|
"loss": 6.4079,
|
|
"mean_token_accuracy": 0.11870727464556693,
|
|
"num_tokens": 29179377.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 6.631547689437866,
|
|
"epoch": 1.443576435336294,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.000480035517862907,
|
|
"loss": 6.3832,
|
|
"mean_token_accuracy": 0.12728108689188958,
|
|
"num_tokens": 29190909.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 6.598265933990478,
|
|
"epoch": 1.444111509444058,
|
|
"grad_norm": 5.34375,
|
|
"learning_rate": 0.00048001976995850856,
|
|
"loss": 6.3109,
|
|
"mean_token_accuracy": 0.1336888037621975,
|
|
"num_tokens": 29200977.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 6.663753652572632,
|
|
"epoch": 1.4446465835518219,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048000401613419296,
|
|
"loss": 6.3514,
|
|
"mean_token_accuracy": 0.12178457602858543,
|
|
"num_tokens": 29210702.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 6.650463724136353,
|
|
"epoch": 1.4451816576595857,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047998825639041534,
|
|
"loss": 6.4377,
|
|
"mean_token_accuracy": 0.11991989985108376,
|
|
"num_tokens": 29221338.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 6.640734720230102,
|
|
"epoch": 1.4457167317673498,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004799724907276306,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.13895482644438745,
|
|
"num_tokens": 29232091.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 6.5429215908050535,
|
|
"epoch": 1.4462518058751137,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004799567191462939,
|
|
"loss": 6.2816,
|
|
"mean_token_accuracy": 0.13796550109982492,
|
|
"num_tokens": 29241903.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 6.5800317287445065,
|
|
"epoch": 1.4467868799828776,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047994094164686074,
|
|
"loss": 6.3996,
|
|
"mean_token_accuracy": 0.1311745338141918,
|
|
"num_tokens": 29253414.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 6.654065895080566,
|
|
"epoch": 1.4473219540906417,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004799251582297868,
|
|
"loss": 6.3006,
|
|
"mean_token_accuracy": 0.13667644932866096,
|
|
"num_tokens": 29264066.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 6.622067832946778,
|
|
"epoch": 1.4478570281984056,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047990936889552767,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.1318219169974327,
|
|
"num_tokens": 29274915.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 6.598536777496338,
|
|
"epoch": 1.4483921023061694,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004798935736445392,
|
|
"loss": 6.3594,
|
|
"mean_token_accuracy": 0.125430978089571,
|
|
"num_tokens": 29287345.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 6.560144901275635,
|
|
"epoch": 1.4489271764139333,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004798777724772777,
|
|
"loss": 6.2967,
|
|
"mean_token_accuracy": 0.1364574022591114,
|
|
"num_tokens": 29297432.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 6.568680238723755,
|
|
"epoch": 1.4494622505216972,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047986196539419936,
|
|
"loss": 6.2537,
|
|
"mean_token_accuracy": 0.13462310805916786,
|
|
"num_tokens": 29307534.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 6.568902778625488,
|
|
"epoch": 1.4499973246294613,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004798461523957604,
|
|
"loss": 6.317,
|
|
"mean_token_accuracy": 0.13380780816078186,
|
|
"num_tokens": 29319412.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 6.548745107650757,
|
|
"epoch": 1.4505323987372252,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00047983033348241767,
|
|
"loss": 6.2833,
|
|
"mean_token_accuracy": 0.14111633971333504,
|
|
"num_tokens": 29330477.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 6.553199720382691,
|
|
"epoch": 1.451067472844989,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004798145086546278,
|
|
"loss": 6.3255,
|
|
"mean_token_accuracy": 0.12989205121994019,
|
|
"num_tokens": 29341481.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 6.585090160369873,
|
|
"epoch": 1.451602546952753,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004797986779128478,
|
|
"loss": 6.323,
|
|
"mean_token_accuracy": 0.13386962488293647,
|
|
"num_tokens": 29353273.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 6.644768762588501,
|
|
"epoch": 1.4521376210605168,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004797828412575348,
|
|
"loss": 6.3442,
|
|
"mean_token_accuracy": 0.13034061715006828,
|
|
"num_tokens": 29364108.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 6.542171669006348,
|
|
"epoch": 1.452672695168281,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00047976699868914594,
|
|
"loss": 6.3086,
|
|
"mean_token_accuracy": 0.13721685633063316,
|
|
"num_tokens": 29375272.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 6.5679466247558596,
|
|
"epoch": 1.4532077692760448,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004797511502081388,
|
|
"loss": 6.3311,
|
|
"mean_token_accuracy": 0.12930863946676255,
|
|
"num_tokens": 29385749.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 6.542065858840942,
|
|
"epoch": 1.4537428433838087,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000479735295814971,
|
|
"loss": 6.2673,
|
|
"mean_token_accuracy": 0.1342756226658821,
|
|
"num_tokens": 29396430.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 6.59383544921875,
|
|
"epoch": 1.4542779174915725,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00047971943551010035,
|
|
"loss": 6.3458,
|
|
"mean_token_accuracy": 0.1268498755991459,
|
|
"num_tokens": 29407020.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 6.6234365940094,
|
|
"epoch": 1.4548129915993364,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047970356929398467,
|
|
"loss": 6.3245,
|
|
"mean_token_accuracy": 0.12958935126662255,
|
|
"num_tokens": 29418428.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 6.664284801483154,
|
|
"epoch": 1.4553480657071005,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004796876971670822,
|
|
"loss": 6.4256,
|
|
"mean_token_accuracy": 0.12959252223372458,
|
|
"num_tokens": 29430611.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 6.611420392990112,
|
|
"epoch": 1.4558831398148644,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004796718191298512,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.12276019901037216,
|
|
"num_tokens": 29441545.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 6.6315406322479244,
|
|
"epoch": 1.4564182139226283,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004796559351827503,
|
|
"loss": 6.4105,
|
|
"mean_token_accuracy": 0.13150686472654344,
|
|
"num_tokens": 29452529.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 6.589520215988159,
|
|
"epoch": 1.4569532880303921,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000479640045326238,
|
|
"loss": 6.3226,
|
|
"mean_token_accuracy": 0.1352757267653942,
|
|
"num_tokens": 29463860.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 6.6948230266571045,
|
|
"epoch": 1.457488362138156,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004796241495607731,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.1279860816895962,
|
|
"num_tokens": 29475004.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 6.6320289134979244,
|
|
"epoch": 1.4580234362459201,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004796082478868146,
|
|
"loss": 6.4539,
|
|
"mean_token_accuracy": 0.12037836760282516,
|
|
"num_tokens": 29485921.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 6.616090536117554,
|
|
"epoch": 1.458558510353684,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047959234030482185,
|
|
"loss": 6.3177,
|
|
"mean_token_accuracy": 0.1393793612718582,
|
|
"num_tokens": 29495729.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 6.646595239639282,
|
|
"epoch": 1.4590935844614479,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004795764268152538,
|
|
"loss": 6.3783,
|
|
"mean_token_accuracy": 0.12391913235187531,
|
|
"num_tokens": 29506051.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 6.60456395149231,
|
|
"epoch": 1.4596286585692118,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004795605074185704,
|
|
"loss": 6.3366,
|
|
"mean_token_accuracy": 0.13117534592747687,
|
|
"num_tokens": 29516234.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 6.629216003417969,
|
|
"epoch": 1.4601637326769756,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00047954458211523095,
|
|
"loss": 6.3389,
|
|
"mean_token_accuracy": 0.1297903150320053,
|
|
"num_tokens": 29527649.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 6.646526670455932,
|
|
"epoch": 1.4606988067847397,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00047952865090569545,
|
|
"loss": 6.3742,
|
|
"mean_token_accuracy": 0.12276733964681626,
|
|
"num_tokens": 29539150.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 6.55916919708252,
|
|
"epoch": 1.4612338808925036,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.00047951271379042393,
|
|
"loss": 6.2597,
|
|
"mean_token_accuracy": 0.13759431019425392,
|
|
"num_tokens": 29550058.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 6.487969970703125,
|
|
"epoch": 1.4617689550002675,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004794967707698765,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.139717698097229,
|
|
"num_tokens": 29560377.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 6.494484090805054,
|
|
"epoch": 1.4623040291080316,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004794808218445136,
|
|
"loss": 6.2292,
|
|
"mean_token_accuracy": 0.1431405395269394,
|
|
"num_tokens": 29571378.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 6.625008058547974,
|
|
"epoch": 1.4628391032157955,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047946486701479576,
|
|
"loss": 6.3685,
|
|
"mean_token_accuracy": 0.1323017656803131,
|
|
"num_tokens": 29582187.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 6.6289266586303714,
|
|
"epoch": 1.4633741773235593,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004794489062811835,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.12977574542164802,
|
|
"num_tokens": 29592982.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 6.670866966247559,
|
|
"epoch": 1.4639092514313232,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004794329396441378,
|
|
"loss": 6.3352,
|
|
"mean_token_accuracy": 0.12650619074702263,
|
|
"num_tokens": 29603639.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 6.5958539009094235,
|
|
"epoch": 1.464444325539087,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047941696710411975,
|
|
"loss": 6.2834,
|
|
"mean_token_accuracy": 0.14019595980644226,
|
|
"num_tokens": 29615103.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 6.575524711608887,
|
|
"epoch": 1.4649793996468512,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004794009886615904,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.13210229724645614,
|
|
"num_tokens": 29626184.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 6.568060350418091,
|
|
"epoch": 1.465514473754615,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00047938500431701135,
|
|
"loss": 6.3369,
|
|
"mean_token_accuracy": 0.14109130799770356,
|
|
"num_tokens": 29637615.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 6.595815896987915,
|
|
"epoch": 1.466049547862379,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000479369014070844,
|
|
"loss": 6.3621,
|
|
"mean_token_accuracy": 0.12747201919555665,
|
|
"num_tokens": 29648648.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 6.630737686157227,
|
|
"epoch": 1.4665846219701428,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047935301792355003,
|
|
"loss": 6.3144,
|
|
"mean_token_accuracy": 0.1336219772696495,
|
|
"num_tokens": 29660542.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 6.631790065765381,
|
|
"epoch": 1.4671196960779067,
|
|
"grad_norm": 5.75,
|
|
"learning_rate": 0.0004793370158755914,
|
|
"loss": 6.3754,
|
|
"mean_token_accuracy": 0.12961311042308807,
|
|
"num_tokens": 29670342.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 6.564358329772949,
|
|
"epoch": 1.4676547701856708,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00047932100792743014,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.13451576307415963,
|
|
"num_tokens": 29681191.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 6.617118215560913,
|
|
"epoch": 1.4681898442934347,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047930499407952855,
|
|
"loss": 6.2727,
|
|
"mean_token_accuracy": 0.1415800467133522,
|
|
"num_tokens": 29691299.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 6.568503713607788,
|
|
"epoch": 1.4687249184011986,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047928897433234893,
|
|
"loss": 6.3212,
|
|
"mean_token_accuracy": 0.12720755115151405,
|
|
"num_tokens": 29702125.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 6.564566707611084,
|
|
"epoch": 1.4692599925089624,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004792729486863539,
|
|
"loss": 6.3613,
|
|
"mean_token_accuracy": 0.12829102352261543,
|
|
"num_tokens": 29712679.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 6.593156528472901,
|
|
"epoch": 1.4697950666167263,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004792569171420061,
|
|
"loss": 6.2944,
|
|
"mean_token_accuracy": 0.1369052104651928,
|
|
"num_tokens": 29723833.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 6.644722938537598,
|
|
"epoch": 1.4703301407244904,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004792408796997687,
|
|
"loss": 6.3929,
|
|
"mean_token_accuracy": 0.1305772230029106,
|
|
"num_tokens": 29734646.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 6.6128322124481205,
|
|
"epoch": 1.4708652148322543,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004792248363601044,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.12973850443959237,
|
|
"num_tokens": 29745129.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 6.615543937683105,
|
|
"epoch": 1.4714002889400182,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004792087871234767,
|
|
"loss": 6.3403,
|
|
"mean_token_accuracy": 0.12748255282640458,
|
|
"num_tokens": 29756308.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 6.600061750411987,
|
|
"epoch": 1.471935363047782,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.000479192731990349,
|
|
"loss": 6.3528,
|
|
"mean_token_accuracy": 0.12515979558229445,
|
|
"num_tokens": 29767835.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 6.624160385131836,
|
|
"epoch": 1.472470437155546,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004791766709611849,
|
|
"loss": 6.372,
|
|
"mean_token_accuracy": 0.13510562404990195,
|
|
"num_tokens": 29778776.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 6.704435586929321,
|
|
"epoch": 1.47300551126331,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000479160604036448,
|
|
"loss": 6.3997,
|
|
"mean_token_accuracy": 0.12569476887583733,
|
|
"num_tokens": 29788800.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 6.587053871154785,
|
|
"epoch": 1.473540585371074,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004791445312166025,
|
|
"loss": 6.2922,
|
|
"mean_token_accuracy": 0.13508957326412202,
|
|
"num_tokens": 29799375.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 6.652836465835572,
|
|
"epoch": 1.4740756594788378,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004791284525021122,
|
|
"loss": 6.433,
|
|
"mean_token_accuracy": 0.12284208834171295,
|
|
"num_tokens": 29811267.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 6.6526227474212645,
|
|
"epoch": 1.4746107335866017,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004791123678934416,
|
|
"loss": 6.3607,
|
|
"mean_token_accuracy": 0.1288243919610977,
|
|
"num_tokens": 29821616.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 6.600805139541626,
|
|
"epoch": 1.4751458076943655,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004790962773910551,
|
|
"loss": 6.3381,
|
|
"mean_token_accuracy": 0.12973368018865586,
|
|
"num_tokens": 29832233.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 6.647430658340454,
|
|
"epoch": 1.4756808818021296,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047908018099541717,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.129634353518486,
|
|
"num_tokens": 29843465.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 6.575530338287353,
|
|
"epoch": 1.4762159559098935,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004790640787069927,
|
|
"loss": 6.2038,
|
|
"mean_token_accuracy": 0.13620911538600922,
|
|
"num_tokens": 29854123.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 6.639060020446777,
|
|
"epoch": 1.4767510300176574,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004790479705262467,
|
|
"loss": 6.4158,
|
|
"mean_token_accuracy": 0.12202998027205467,
|
|
"num_tokens": 29864831.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 6.58926100730896,
|
|
"epoch": 1.4772861041254215,
|
|
"grad_norm": 5.71875,
|
|
"learning_rate": 0.0004790318564536441,
|
|
"loss": 6.2817,
|
|
"mean_token_accuracy": 0.1287100851535797,
|
|
"num_tokens": 29876273.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 6.59377703666687,
|
|
"epoch": 1.4778211782331854,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047901573648965047,
|
|
"loss": 6.3044,
|
|
"mean_token_accuracy": 0.12934348061680795,
|
|
"num_tokens": 29886560.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 6.602173662185669,
|
|
"epoch": 1.4783562523409493,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000478999610634731,
|
|
"loss": 6.2982,
|
|
"mean_token_accuracy": 0.13478929847478865,
|
|
"num_tokens": 29896916.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 6.543396806716919,
|
|
"epoch": 1.4788913264487131,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004789834788893515,
|
|
"loss": 6.3441,
|
|
"mean_token_accuracy": 0.13018305376172065,
|
|
"num_tokens": 29907288.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 6.559595537185669,
|
|
"epoch": 1.479426400556477,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004789673412539777,
|
|
"loss": 6.2856,
|
|
"mean_token_accuracy": 0.1346842236816883,
|
|
"num_tokens": 29918194.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 6.6217114448547365,
|
|
"epoch": 1.479961474664241,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00047895119772907566,
|
|
"loss": 6.3199,
|
|
"mean_token_accuracy": 0.1316944681107998,
|
|
"num_tokens": 29928521.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 6.6027075290679935,
|
|
"epoch": 1.480496548772005,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004789350483151113,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.1292131632566452,
|
|
"num_tokens": 29938885.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 6.623860597610474,
|
|
"epoch": 1.4810316228797689,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004789188930125512,
|
|
"loss": 6.3554,
|
|
"mean_token_accuracy": 0.134634181112051,
|
|
"num_tokens": 29948921.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 6.564037656784057,
|
|
"epoch": 1.4815666969875327,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004789027318218616,
|
|
"loss": 6.2584,
|
|
"mean_token_accuracy": 0.13995078653097154,
|
|
"num_tokens": 29959633.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 6.572698593139648,
|
|
"epoch": 1.4821017710952966,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004788865647435093,
|
|
"loss": 6.2934,
|
|
"mean_token_accuracy": 0.12565670982003213,
|
|
"num_tokens": 29970639.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 6.636254930496216,
|
|
"epoch": 1.4826368452030607,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004788703917779612,
|
|
"loss": 6.411,
|
|
"mean_token_accuracy": 0.13015194609761238,
|
|
"num_tokens": 29981752.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 6.648344659805298,
|
|
"epoch": 1.4831719193108246,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004788542129256841,
|
|
"loss": 6.2602,
|
|
"mean_token_accuracy": 0.135259310901165,
|
|
"num_tokens": 29991037.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 6.5955588817596436,
|
|
"epoch": 1.4837069934185885,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047883802818714526,
|
|
"loss": 6.3482,
|
|
"mean_token_accuracy": 0.12274064496159554,
|
|
"num_tokens": 30001980.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 6.599097204208374,
|
|
"epoch": 1.4842420675263523,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.000478821837562812,
|
|
"loss": 6.3392,
|
|
"mean_token_accuracy": 0.1303992360830307,
|
|
"num_tokens": 30013377.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 6.6240747451782225,
|
|
"epoch": 1.4847771416341162,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004788056410531518,
|
|
"loss": 6.3764,
|
|
"mean_token_accuracy": 0.13373826295137406,
|
|
"num_tokens": 30023909.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 6.576505994796753,
|
|
"epoch": 1.4853122157418803,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004787894386586324,
|
|
"loss": 6.2899,
|
|
"mean_token_accuracy": 0.13181793913245202,
|
|
"num_tokens": 30034069.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 6.483772802352905,
|
|
"epoch": 1.4858472898496442,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047877323037972153,
|
|
"loss": 6.2916,
|
|
"mean_token_accuracy": 0.13526618108153343,
|
|
"num_tokens": 30043940.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 6.568648815155029,
|
|
"epoch": 1.486382363957408,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.0004787570162168874,
|
|
"loss": 6.27,
|
|
"mean_token_accuracy": 0.1395317204296589,
|
|
"num_tokens": 30054985.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 6.640033817291259,
|
|
"epoch": 1.486917438065172,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047874079617059783,
|
|
"loss": 6.3021,
|
|
"mean_token_accuracy": 0.13225460350513457,
|
|
"num_tokens": 30065675.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 6.630600643157959,
|
|
"epoch": 1.4874525121729358,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.0004787245702413216,
|
|
"loss": 6.2756,
|
|
"mean_token_accuracy": 0.1356930173933506,
|
|
"num_tokens": 30075305.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 6.651743412017822,
|
|
"epoch": 1.4879875862807,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047870833842952697,
|
|
"loss": 6.3579,
|
|
"mean_token_accuracy": 0.13344189748167992,
|
|
"num_tokens": 30087309.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 6.6250523090362545,
|
|
"epoch": 1.4885226603884638,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004786921007356827,
|
|
"loss": 6.2855,
|
|
"mean_token_accuracy": 0.1302078738808632,
|
|
"num_tokens": 30097262.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 6.623433637619018,
|
|
"epoch": 1.4890577344962277,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047867585716025767,
|
|
"loss": 6.3652,
|
|
"mean_token_accuracy": 0.1293804571032524,
|
|
"num_tokens": 30107067.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 6.634920501708985,
|
|
"epoch": 1.4895928086039918,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004786596077037209,
|
|
"loss": 6.3717,
|
|
"mean_token_accuracy": 0.1273067183792591,
|
|
"num_tokens": 30117115.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 6.659192323684692,
|
|
"epoch": 1.4901278827117554,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00047864335236654144,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.12927939891815185,
|
|
"num_tokens": 30127202.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 6.554332447052002,
|
|
"epoch": 1.4906629568195195,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004786270911491889,
|
|
"loss": 6.3217,
|
|
"mean_token_accuracy": 0.1261875458061695,
|
|
"num_tokens": 30138608.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 6.675147199630738,
|
|
"epoch": 1.4911980309272834,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004786108240521327,
|
|
"loss": 6.3469,
|
|
"mean_token_accuracy": 0.13276014477014542,
|
|
"num_tokens": 30148500.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 6.567157316207886,
|
|
"epoch": 1.4917331050350473,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.00047859455107584256,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.13627972155809404,
|
|
"num_tokens": 30159062.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 6.548661994934082,
|
|
"epoch": 1.4922681791428114,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00047857827222078835,
|
|
"loss": 6.3285,
|
|
"mean_token_accuracy": 0.1331160306930542,
|
|
"num_tokens": 30170468.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 6.47429666519165,
|
|
"epoch": 1.4928032532505753,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004785619874874402,
|
|
"loss": 6.2148,
|
|
"mean_token_accuracy": 0.1333200976252556,
|
|
"num_tokens": 30180944.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 6.517950010299683,
|
|
"epoch": 1.4933383273583392,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004785456968762682,
|
|
"loss": 6.2218,
|
|
"mean_token_accuracy": 0.1382657043635845,
|
|
"num_tokens": 30191614.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 6.5833228588104244,
|
|
"epoch": 1.493873401466103,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047852940038774276,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.1384717918932438,
|
|
"num_tokens": 30202035.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 6.547524356842041,
|
|
"epoch": 1.494408475573867,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047851309802233457,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.13306165784597396,
|
|
"num_tokens": 30213205.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 6.651522827148438,
|
|
"epoch": 1.494943549681631,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004784967897805143,
|
|
"loss": 6.3413,
|
|
"mean_token_accuracy": 0.13160361349582672,
|
|
"num_tokens": 30223971.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 6.596083545684815,
|
|
"epoch": 1.495478623789395,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004784804756627528,
|
|
"loss": 6.3319,
|
|
"mean_token_accuracy": 0.12845104485750197,
|
|
"num_tokens": 30235346.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 6.57200517654419,
|
|
"epoch": 1.4960136978971588,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00047846415566952106,
|
|
"loss": 6.2858,
|
|
"mean_token_accuracy": 0.13229528367519378,
|
|
"num_tokens": 30246033.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 6.581707906723023,
|
|
"epoch": 1.4965487720049226,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047844782980129057,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.12570826932787896,
|
|
"num_tokens": 30258208.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 6.6168437004089355,
|
|
"epoch": 1.4970838461126865,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047843149805853254,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.1313864417374134,
|
|
"num_tokens": 30268824.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 6.6648204803466795,
|
|
"epoch": 1.4976189202204506,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004784151604417185,
|
|
"loss": 6.4106,
|
|
"mean_token_accuracy": 0.12392248064279557,
|
|
"num_tokens": 30280078.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 6.602230739593506,
|
|
"epoch": 1.4981539943282145,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00047839881695132034,
|
|
"loss": 6.2763,
|
|
"mean_token_accuracy": 0.14022136330604554,
|
|
"num_tokens": 30290939.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 6.573500061035157,
|
|
"epoch": 1.4986890684359784,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00047838246758780996,
|
|
"loss": 6.3197,
|
|
"mean_token_accuracy": 0.13605999946594238,
|
|
"num_tokens": 30301198.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 6.5753639221191404,
|
|
"epoch": 1.4992241425437423,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004783661123516593,
|
|
"loss": 6.3051,
|
|
"mean_token_accuracy": 0.13538139089941978,
|
|
"num_tokens": 30312021.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 6.565383529663086,
|
|
"epoch": 1.4997592166515061,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004783497512433408,
|
|
"loss": 6.3109,
|
|
"mean_token_accuracy": 0.13328961357474328,
|
|
"num_tokens": 30323335.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 6.582949590682984,
|
|
"epoch": 1.5002942907592702,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004783333842633268,
|
|
"loss": 6.3446,
|
|
"mean_token_accuracy": 0.13472514376044273,
|
|
"num_tokens": 30334389.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 6.530483388900757,
|
|
"epoch": 1.500829364867034,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047831701141208994,
|
|
"loss": 6.286,
|
|
"mean_token_accuracy": 0.12667075768113137,
|
|
"num_tokens": 30345407.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 6.579833316802978,
|
|
"epoch": 1.501364438974798,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047830063269010286,
|
|
"loss": 6.3142,
|
|
"mean_token_accuracy": 0.12763669341802597,
|
|
"num_tokens": 30356718.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 6.583492612838745,
|
|
"epoch": 1.501899513082562,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047828424809783865,
|
|
"loss": 6.2758,
|
|
"mean_token_accuracy": 0.13159737810492517,
|
|
"num_tokens": 30367617.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 6.596625137329101,
|
|
"epoch": 1.5024345871903257,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004782678576357703,
|
|
"loss": 6.3141,
|
|
"mean_token_accuracy": 0.13055066093802453,
|
|
"num_tokens": 30377923.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 6.601361322402954,
|
|
"epoch": 1.5029696612980898,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004782514613043711,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.13799530416727065,
|
|
"num_tokens": 30388719.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 6.592846059799195,
|
|
"epoch": 1.5035047354058537,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00047823505910411465,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.13297346085309983,
|
|
"num_tokens": 30400191.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 6.568882751464844,
|
|
"epoch": 1.5040398095136176,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047821865103547437,
|
|
"loss": 6.3375,
|
|
"mean_token_accuracy": 0.1311485081911087,
|
|
"num_tokens": 30410267.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 6.598819255828857,
|
|
"epoch": 1.5045748836213817,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000478202237098924,
|
|
"loss": 6.3506,
|
|
"mean_token_accuracy": 0.12971964254975318,
|
|
"num_tokens": 30420852.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 6.685174560546875,
|
|
"epoch": 1.5051099577291454,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004781858172949376,
|
|
"loss": 6.409,
|
|
"mean_token_accuracy": 0.12761326357722283,
|
|
"num_tokens": 30432214.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 6.710468721389771,
|
|
"epoch": 1.5056450318369095,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004781693916239894,
|
|
"loss": 6.3952,
|
|
"mean_token_accuracy": 0.1244383580982685,
|
|
"num_tokens": 30443919.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 6.658488655090332,
|
|
"epoch": 1.5061801059446733,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.00047815296008655347,
|
|
"loss": 6.4681,
|
|
"mean_token_accuracy": 0.12101376503705978,
|
|
"num_tokens": 30453930.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 6.584766626358032,
|
|
"epoch": 1.5067151800524372,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047813652268310436,
|
|
"loss": 6.3452,
|
|
"mean_token_accuracy": 0.12030079290270805,
|
|
"num_tokens": 30464612.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 6.6458807468414305,
|
|
"epoch": 1.5072502541602013,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047812007941411673,
|
|
"loss": 6.2887,
|
|
"mean_token_accuracy": 0.13165187761187552,
|
|
"num_tokens": 30474819.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 6.627662658691406,
|
|
"epoch": 1.507785328267965,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047810363028006535,
|
|
"loss": 6.2832,
|
|
"mean_token_accuracy": 0.13824990913271903,
|
|
"num_tokens": 30485481.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 6.596781206130982,
|
|
"epoch": 1.508320402375729,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004780871752814252,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.13541302606463432,
|
|
"num_tokens": 30496321.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 6.586533069610596,
|
|
"epoch": 1.508855476483493,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004780707144186714,
|
|
"loss": 6.4085,
|
|
"mean_token_accuracy": 0.12751608714461327,
|
|
"num_tokens": 30507578.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 6.674954652786255,
|
|
"epoch": 1.5093905505912568,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047805424769227923,
|
|
"loss": 6.3474,
|
|
"mean_token_accuracy": 0.12699943259358407,
|
|
"num_tokens": 30518328.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 6.569561767578125,
|
|
"epoch": 1.509925624699021,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047803777510272425,
|
|
"loss": 6.3236,
|
|
"mean_token_accuracy": 0.1304946683347225,
|
|
"num_tokens": 30528555.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 6.550884056091308,
|
|
"epoch": 1.5104606988067846,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000478021296650482,
|
|
"loss": 6.2629,
|
|
"mean_token_accuracy": 0.13676863610744477,
|
|
"num_tokens": 30540217.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 6.674431180953979,
|
|
"epoch": 1.5109957729145487,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004780048123360283,
|
|
"loss": 6.3821,
|
|
"mean_token_accuracy": 0.13404778763651848,
|
|
"num_tokens": 30550937.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 6.673206233978272,
|
|
"epoch": 1.5115308470223126,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047798832215983916,
|
|
"loss": 6.364,
|
|
"mean_token_accuracy": 0.12827351987361907,
|
|
"num_tokens": 30562248.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 6.666020441055298,
|
|
"epoch": 1.5120659211300764,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004779718261223908,
|
|
"loss": 6.3612,
|
|
"mean_token_accuracy": 0.1355786368250847,
|
|
"num_tokens": 30573362.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 6.591891860961914,
|
|
"epoch": 1.5126009952378405,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047795532422415947,
|
|
"loss": 6.3489,
|
|
"mean_token_accuracy": 0.1280567467212677,
|
|
"num_tokens": 30584052.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 6.56154499053955,
|
|
"epoch": 1.5131360693456044,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004779388164656217,
|
|
"loss": 6.3769,
|
|
"mean_token_accuracy": 0.12667953446507454,
|
|
"num_tokens": 30594630.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 6.621571063995361,
|
|
"epoch": 1.5136711434533683,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047792230284725415,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.12962086722254754,
|
|
"num_tokens": 30605625.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 6.600331592559814,
|
|
"epoch": 1.5142062175611322,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047790578336953356,
|
|
"loss": 6.3088,
|
|
"mean_token_accuracy": 0.136430624127388,
|
|
"num_tokens": 30616520.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 6.602639198303223,
|
|
"epoch": 1.514741291668896,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.000477889258032937,
|
|
"loss": 6.2943,
|
|
"mean_token_accuracy": 0.139606498926878,
|
|
"num_tokens": 30627372.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 6.595419311523438,
|
|
"epoch": 1.5152763657766601,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047787272683794157,
|
|
"loss": 6.2826,
|
|
"mean_token_accuracy": 0.1395291917026043,
|
|
"num_tokens": 30636974.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 6.595134973526001,
|
|
"epoch": 1.515811439884424,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004778561897850247,
|
|
"loss": 6.3552,
|
|
"mean_token_accuracy": 0.1332934506237507,
|
|
"num_tokens": 30648202.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 6.550025224685669,
|
|
"epoch": 1.516346513992188,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047783964687466384,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.1284328430891037,
|
|
"num_tokens": 30657981.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 6.619314289093017,
|
|
"epoch": 1.516881588099952,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.00047782309810733676,
|
|
"loss": 6.3502,
|
|
"mean_token_accuracy": 0.12546662390232086,
|
|
"num_tokens": 30668496.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 6.609033727645874,
|
|
"epoch": 1.5174166622077156,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047780654348352115,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.13610913529992102,
|
|
"num_tokens": 30678868.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 6.615397691726685,
|
|
"epoch": 1.5179517363154797,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047778998300369516,
|
|
"loss": 6.3896,
|
|
"mean_token_accuracy": 0.13218894526362418,
|
|
"num_tokens": 30690066.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 6.54673490524292,
|
|
"epoch": 1.5184868104232436,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004777734166683368,
|
|
"loss": 6.2704,
|
|
"mean_token_accuracy": 0.13186497017741203,
|
|
"num_tokens": 30700624.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 6.552410840988159,
|
|
"epoch": 1.5190218845310075,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047775684447792457,
|
|
"loss": 6.2742,
|
|
"mean_token_accuracy": 0.13776695355772972,
|
|
"num_tokens": 30711183.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 6.601855754852295,
|
|
"epoch": 1.5195569586387716,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000477740266432937,
|
|
"loss": 6.303,
|
|
"mean_token_accuracy": 0.13699688166379928,
|
|
"num_tokens": 30721446.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 6.653039741516113,
|
|
"epoch": 1.5200920327465353,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047772368253385267,
|
|
"loss": 6.3446,
|
|
"mean_token_accuracy": 0.12485012114048004,
|
|
"num_tokens": 30731901.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 6.617021942138672,
|
|
"epoch": 1.5206271068542994,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004777070927811505,
|
|
"loss": 6.3257,
|
|
"mean_token_accuracy": 0.1319168470799923,
|
|
"num_tokens": 30741701.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 6.5978494644165036,
|
|
"epoch": 1.5211621809620632,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047769049717530956,
|
|
"loss": 6.3137,
|
|
"mean_token_accuracy": 0.12779575064778328,
|
|
"num_tokens": 30751594.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 6.5777191638946535,
|
|
"epoch": 1.5216972550698271,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047767389571680896,
|
|
"loss": 6.3952,
|
|
"mean_token_accuracy": 0.12199783921241761,
|
|
"num_tokens": 30764418.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 6.671735191345215,
|
|
"epoch": 1.5222323291775912,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004776572884061281,
|
|
"loss": 6.3296,
|
|
"mean_token_accuracy": 0.1350166030228138,
|
|
"num_tokens": 30773976.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 6.641802787780762,
|
|
"epoch": 1.5227674032853549,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004776406752437465,
|
|
"loss": 6.3444,
|
|
"mean_token_accuracy": 0.1340843990445137,
|
|
"num_tokens": 30784210.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 6.566564273834229,
|
|
"epoch": 1.523302477393119,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004776240562301438,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.12034794166684151,
|
|
"num_tokens": 30794322.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 6.63122296333313,
|
|
"epoch": 1.5238375515008828,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004776074313658001,
|
|
"loss": 6.3564,
|
|
"mean_token_accuracy": 0.13436343222856523,
|
|
"num_tokens": 30805264.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 6.57757077217102,
|
|
"epoch": 1.5243726256086467,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004775908006511952,
|
|
"loss": 6.3185,
|
|
"mean_token_accuracy": 0.13051761463284492,
|
|
"num_tokens": 30815909.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 6.6450457096099855,
|
|
"epoch": 1.5249076997164108,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004775741640868095,
|
|
"loss": 6.3037,
|
|
"mean_token_accuracy": 0.13252366557717324,
|
|
"num_tokens": 30826867.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 6.6083581924438475,
|
|
"epoch": 1.5254427738241747,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047755752167312314,
|
|
"loss": 6.3022,
|
|
"mean_token_accuracy": 0.12474930360913276,
|
|
"num_tokens": 30837696.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 6.5610746383667,
|
|
"epoch": 1.5259778479319386,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004775408734106169,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.1336665481328964,
|
|
"num_tokens": 30848155.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 6.541180276870728,
|
|
"epoch": 1.5265129220397025,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047752421929977143,
|
|
"loss": 6.2181,
|
|
"mean_token_accuracy": 0.1366681531071663,
|
|
"num_tokens": 30857804.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 6.626170015335083,
|
|
"epoch": 1.5270479961474663,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004775075593410675,
|
|
"loss": 6.322,
|
|
"mean_token_accuracy": 0.13398007303476334,
|
|
"num_tokens": 30867290.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 6.613441228866577,
|
|
"epoch": 1.5275830702552304,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00047749089353498625,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.131116596609354,
|
|
"num_tokens": 30877634.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 6.612349653244019,
|
|
"epoch": 1.5281181443629943,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.000477474221882009,
|
|
"loss": 6.3605,
|
|
"mean_token_accuracy": 0.13117219507694244,
|
|
"num_tokens": 30889176.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 6.610392045974732,
|
|
"epoch": 1.5286532184707582,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004774575443826169,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.13066302984952927,
|
|
"num_tokens": 30899516.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 6.627958297729492,
|
|
"epoch": 1.5291882925785223,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004774408610372918,
|
|
"loss": 6.3624,
|
|
"mean_token_accuracy": 0.13004181310534477,
|
|
"num_tokens": 30910155.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 6.6603750705719,
|
|
"epoch": 1.529723366686286,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004774241718465152,
|
|
"loss": 6.3924,
|
|
"mean_token_accuracy": 0.12566164508461952,
|
|
"num_tokens": 30921486.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 6.64437255859375,
|
|
"epoch": 1.53025844079405,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004774074768107691,
|
|
"loss": 6.3322,
|
|
"mean_token_accuracy": 0.13147373571991922,
|
|
"num_tokens": 30932361.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 6.585672616958618,
|
|
"epoch": 1.530793514901814,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00047739077593053554,
|
|
"loss": 6.3131,
|
|
"mean_token_accuracy": 0.13156911507248878,
|
|
"num_tokens": 30943033.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 6.578750419616699,
|
|
"epoch": 1.5313285890095778,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00047737406920629675,
|
|
"loss": 6.2953,
|
|
"mean_token_accuracy": 0.1385014072060585,
|
|
"num_tokens": 30953094.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 6.559763240814209,
|
|
"epoch": 1.531863663117342,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047735735663853514,
|
|
"loss": 6.3469,
|
|
"mean_token_accuracy": 0.12932962477207183,
|
|
"num_tokens": 30964604.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 6.652671384811401,
|
|
"epoch": 1.5323987372251056,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004773406382277334,
|
|
"loss": 6.3833,
|
|
"mean_token_accuracy": 0.1271856114268303,
|
|
"num_tokens": 30975681.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 6.6918689727783205,
|
|
"epoch": 1.5329338113328697,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004773239139743741,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.12816953882575036,
|
|
"num_tokens": 30986319.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 6.637636518478393,
|
|
"epoch": 1.5334688854406335,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004773071838789402,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.13024308085441588,
|
|
"num_tokens": 30997077.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 6.57767539024353,
|
|
"epoch": 1.5340039595483974,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004772904479419148,
|
|
"loss": 6.2355,
|
|
"mean_token_accuracy": 0.13092122748494148,
|
|
"num_tokens": 31007485.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 6.582985496520996,
|
|
"epoch": 1.5345390336561615,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004772737061637811,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.13817652463912963,
|
|
"num_tokens": 31017827.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 6.593803977966308,
|
|
"epoch": 1.5350741077639252,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047725695854502267,
|
|
"loss": 6.3592,
|
|
"mean_token_accuracy": 0.13093263730406762,
|
|
"num_tokens": 31028167.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 6.592303085327148,
|
|
"epoch": 1.5356091818716893,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.00047724020508612287,
|
|
"loss": 6.2985,
|
|
"mean_token_accuracy": 0.1356341652572155,
|
|
"num_tokens": 31038941.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 6.63203501701355,
|
|
"epoch": 1.5361442559794531,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047722344578756564,
|
|
"loss": 6.3103,
|
|
"mean_token_accuracy": 0.1268148973584175,
|
|
"num_tokens": 31049949.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 6.637924575805664,
|
|
"epoch": 1.536679330087217,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00047720668064983476,
|
|
"loss": 6.3126,
|
|
"mean_token_accuracy": 0.13545114919543266,
|
|
"num_tokens": 31059299.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 6.5864652633667,
|
|
"epoch": 1.5372144041949811,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004771899096734145,
|
|
"loss": 6.4159,
|
|
"mean_token_accuracy": 0.12512890696525575,
|
|
"num_tokens": 31070508.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 6.485046339035034,
|
|
"epoch": 1.5377494783027448,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047717313285878886,
|
|
"loss": 6.2844,
|
|
"mean_token_accuracy": 0.13554516434669495,
|
|
"num_tokens": 31082354.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 6.713227844238281,
|
|
"epoch": 1.5382845524105089,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047715635020644247,
|
|
"loss": 6.4572,
|
|
"mean_token_accuracy": 0.12149391025304794,
|
|
"num_tokens": 31093496.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 6.675244522094727,
|
|
"epoch": 1.5388196265182728,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.00047713956171685994,
|
|
"loss": 6.2768,
|
|
"mean_token_accuracy": 0.1361006423830986,
|
|
"num_tokens": 31104289.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 6.534764957427979,
|
|
"epoch": 1.5393547006260366,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.000477122767390526,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.14380293637514113,
|
|
"num_tokens": 31114998.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 6.549643659591675,
|
|
"epoch": 1.5398897747338007,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047710596722792543,
|
|
"loss": 6.3265,
|
|
"mean_token_accuracy": 0.1263222172856331,
|
|
"num_tokens": 31127393.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 6.522597217559815,
|
|
"epoch": 1.5404248488415646,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004770891612295435,
|
|
"loss": 6.1652,
|
|
"mean_token_accuracy": 0.14330109134316443,
|
|
"num_tokens": 31137484.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 6.592005252838135,
|
|
"epoch": 1.5409599229493285,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004770723493958654,
|
|
"loss": 6.3887,
|
|
"mean_token_accuracy": 0.12686755806207656,
|
|
"num_tokens": 31147863.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 6.533912897109985,
|
|
"epoch": 1.5414949970570924,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004770555317273767,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.13427213877439498,
|
|
"num_tokens": 31159018.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 6.601826095581055,
|
|
"epoch": 1.5420300711648562,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00047703870822456287,
|
|
"loss": 6.2914,
|
|
"mean_token_accuracy": 0.1306685209274292,
|
|
"num_tokens": 31170673.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 6.512188291549682,
|
|
"epoch": 1.5425651452726203,
|
|
"grad_norm": 5.375,
|
|
"learning_rate": 0.0004770218788879097,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.1431228093802929,
|
|
"num_tokens": 31181165.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 6.508229207992554,
|
|
"epoch": 1.5431002193803842,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004770050437179033,
|
|
"loss": 6.2974,
|
|
"mean_token_accuracy": 0.13542182371020317,
|
|
"num_tokens": 31192976.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 6.633187961578369,
|
|
"epoch": 1.543635293488148,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004769882027150295,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.12985335141420365,
|
|
"num_tokens": 31203979.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 6.607591533660889,
|
|
"epoch": 1.5441703675959122,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047697135587977473,
|
|
"loss": 6.2481,
|
|
"mean_token_accuracy": 0.13489941731095315,
|
|
"num_tokens": 31214972.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 6.600766801834107,
|
|
"epoch": 1.5447054417036759,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047695450321262546,
|
|
"loss": 6.3697,
|
|
"mean_token_accuracy": 0.13742295131087304,
|
|
"num_tokens": 31224726.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 6.619610738754273,
|
|
"epoch": 1.54524051581144,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004769376447140683,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.13607348799705504,
|
|
"num_tokens": 31235761.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 6.610139513015747,
|
|
"epoch": 1.5457755899192038,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047692078038459015,
|
|
"loss": 6.3571,
|
|
"mean_token_accuracy": 0.13551222607493402,
|
|
"num_tokens": 31246221.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 6.583718204498291,
|
|
"epoch": 1.5463106640269677,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004769039102246777,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.1308446191251278,
|
|
"num_tokens": 31257364.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 6.598931455612183,
|
|
"epoch": 1.5468457381347318,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.00047688703423481827,
|
|
"loss": 6.3178,
|
|
"mean_token_accuracy": 0.12803043723106383,
|
|
"num_tokens": 31268343.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 6.596816492080689,
|
|
"epoch": 1.5473808122424955,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047687015241549896,
|
|
"loss": 6.3556,
|
|
"mean_token_accuracy": 0.13014432713389396,
|
|
"num_tokens": 31278335.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 6.620870876312256,
|
|
"epoch": 1.5479158863502596,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004768532647672075,
|
|
"loss": 6.2802,
|
|
"mean_token_accuracy": 0.12716290652751921,
|
|
"num_tokens": 31288537.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 6.535238313674927,
|
|
"epoch": 1.5484509604580234,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004768363712904314,
|
|
"loss": 6.2899,
|
|
"mean_token_accuracy": 0.14087557494640351,
|
|
"num_tokens": 31299353.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 6.649505710601806,
|
|
"epoch": 1.5489860345657873,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004768194719856584,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.12458242252469062,
|
|
"num_tokens": 31309655.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 6.612591314315796,
|
|
"epoch": 1.5495211086735514,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004768025668533765,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.1365545831620693,
|
|
"num_tokens": 31321008.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 6.554720067977906,
|
|
"epoch": 1.550056182781315,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047678565589407383,
|
|
"loss": 6.2526,
|
|
"mean_token_accuracy": 0.13562536463141442,
|
|
"num_tokens": 31331978.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 6.599108648300171,
|
|
"epoch": 1.5505912568890792,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004767687391082387,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.13647982701659203,
|
|
"num_tokens": 31341703.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 6.595365524291992,
|
|
"epoch": 1.551126330996843,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047675181649635965,
|
|
"loss": 6.3435,
|
|
"mean_token_accuracy": 0.13550451546907424,
|
|
"num_tokens": 31352787.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 6.561582374572754,
|
|
"epoch": 1.551661405104607,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047673488805892515,
|
|
"loss": 6.3304,
|
|
"mean_token_accuracy": 0.1311231903731823,
|
|
"num_tokens": 31363702.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 6.572860336303711,
|
|
"epoch": 1.552196479212371,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00047671795379642415,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.1268619939684868,
|
|
"num_tokens": 31374719.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 6.658960151672363,
|
|
"epoch": 1.5527315533201347,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004767010137093456,
|
|
"loss": 6.4251,
|
|
"mean_token_accuracy": 0.12287965789437294,
|
|
"num_tokens": 31386289.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 6.599834346771241,
|
|
"epoch": 1.5532666274278988,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047668406779817864,
|
|
"loss": 6.2351,
|
|
"mean_token_accuracy": 0.13514427468180656,
|
|
"num_tokens": 31397103.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 6.595873498916626,
|
|
"epoch": 1.5538017015356627,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004766671160634125,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.13780971318483354,
|
|
"num_tokens": 31408715.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 6.637453937530518,
|
|
"epoch": 1.5543367756434265,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004766501585055367,
|
|
"loss": 6.3702,
|
|
"mean_token_accuracy": 0.12579223066568374,
|
|
"num_tokens": 31420365.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 6.5931297779083256,
|
|
"epoch": 1.5548718497511906,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.000476633195125041,
|
|
"loss": 6.2838,
|
|
"mean_token_accuracy": 0.13136679083108901,
|
|
"num_tokens": 31431635.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 6.630488348007202,
|
|
"epoch": 1.5554069238589545,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00047661622592241507,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.13207176178693772,
|
|
"num_tokens": 31442513.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 6.615256357192993,
|
|
"epoch": 1.5559419979667184,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004765992508981489,
|
|
"loss": 6.3491,
|
|
"mean_token_accuracy": 0.12018114104866981,
|
|
"num_tokens": 31453726.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 6.654684686660767,
|
|
"epoch": 1.5564770720744823,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004765822700527328,
|
|
"loss": 6.2755,
|
|
"mean_token_accuracy": 0.13515690490603446,
|
|
"num_tokens": 31463980.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 6.62519941329956,
|
|
"epoch": 1.5570121461822461,
|
|
"grad_norm": 5.84375,
|
|
"learning_rate": 0.0004765652833866569,
|
|
"loss": 6.3963,
|
|
"mean_token_accuracy": 0.1226954534649849,
|
|
"num_tokens": 31474615.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 6.53183274269104,
|
|
"epoch": 1.5575472202900102,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004765482909004118,
|
|
"loss": 6.2612,
|
|
"mean_token_accuracy": 0.13954779729247094,
|
|
"num_tokens": 31485283.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 6.568670701980591,
|
|
"epoch": 1.5580822943977741,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004765312925944881,
|
|
"loss": 6.3147,
|
|
"mean_token_accuracy": 0.1254294402897358,
|
|
"num_tokens": 31496997.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 6.674722623825073,
|
|
"epoch": 1.558617368505538,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047651428846937673,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.13286553472280502,
|
|
"num_tokens": 31507585.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 6.634952211380005,
|
|
"epoch": 1.559152442613302,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047649727852556854,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.13332946524024009,
|
|
"num_tokens": 31517078.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 6.484353256225586,
|
|
"epoch": 1.5596875167210658,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004764802627635547,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.13877461850643158,
|
|
"num_tokens": 31528576.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 6.650916910171508,
|
|
"epoch": 1.5602225908288299,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004764632411838266,
|
|
"loss": 6.3509,
|
|
"mean_token_accuracy": 0.12712524607777595,
|
|
"num_tokens": 31540095.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 6.618455600738526,
|
|
"epoch": 1.5607576649365937,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047644621378687573,
|
|
"loss": 6.2568,
|
|
"mean_token_accuracy": 0.13074170500040055,
|
|
"num_tokens": 31550980.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 6.39392614364624,
|
|
"epoch": 1.5612927390443576,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00047642918057319377,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.15051754489541053,
|
|
"num_tokens": 31561842.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 6.589424324035645,
|
|
"epoch": 1.5618278131521217,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004764121415432725,
|
|
"loss": 6.4183,
|
|
"mean_token_accuracy": 0.12579916715621947,
|
|
"num_tokens": 31572798.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 6.593762922286987,
|
|
"epoch": 1.5623628872598854,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004763950966976039,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.12810579016804696,
|
|
"num_tokens": 31584774.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 6.59525580406189,
|
|
"epoch": 1.5628979613676495,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004763780460366803,
|
|
"loss": 6.2816,
|
|
"mean_token_accuracy": 0.1284186452627182,
|
|
"num_tokens": 31596197.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 6.628557825088501,
|
|
"epoch": 1.5634330354754133,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004763609895609939,
|
|
"loss": 6.3495,
|
|
"mean_token_accuracy": 0.12698548808693885,
|
|
"num_tokens": 31607455.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 6.679028797149658,
|
|
"epoch": 1.5639681095831772,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047634392727103714,
|
|
"loss": 6.3833,
|
|
"mean_token_accuracy": 0.1267906002700329,
|
|
"num_tokens": 31618995.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 6.541309070587158,
|
|
"epoch": 1.5645031836909413,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004763268591673028,
|
|
"loss": 6.2321,
|
|
"mean_token_accuracy": 0.13662346079945564,
|
|
"num_tokens": 31629984.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 6.563742160797119,
|
|
"epoch": 1.565038257798705,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004763097852502837,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.1362563520669937,
|
|
"num_tokens": 31641362.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 6.6136754035949705,
|
|
"epoch": 1.565573331906469,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.00047629270552047284,
|
|
"loss": 6.434,
|
|
"mean_token_accuracy": 0.11938761994242668,
|
|
"num_tokens": 31652650.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 6.597079467773438,
|
|
"epoch": 1.566108406014233,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00047627561997836337,
|
|
"loss": 6.3351,
|
|
"mean_token_accuracy": 0.12390407547354698,
|
|
"num_tokens": 31664201.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 6.614897632598877,
|
|
"epoch": 1.5666434801219968,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004762585286244487,
|
|
"loss": 6.3126,
|
|
"mean_token_accuracy": 0.13390533849596978,
|
|
"num_tokens": 31674480.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 6.585116529464722,
|
|
"epoch": 1.567178554229761,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00047624143145922227,
|
|
"loss": 6.3128,
|
|
"mean_token_accuracy": 0.13245998173952103,
|
|
"num_tokens": 31685377.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 6.632396936416626,
|
|
"epoch": 1.5677136283375246,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047622432848317775,
|
|
"loss": 6.3056,
|
|
"mean_token_accuracy": 0.13168206736445426,
|
|
"num_tokens": 31695199.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 6.617273759841919,
|
|
"epoch": 1.5682487024452887,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004762072196968091,
|
|
"loss": 6.3352,
|
|
"mean_token_accuracy": 0.1323869712650776,
|
|
"num_tokens": 31705528.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 6.509475374221802,
|
|
"epoch": 1.5687837765530526,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004761901051006102,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.137880327552557,
|
|
"num_tokens": 31718156.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 6.530184888839722,
|
|
"epoch": 1.5693188506608164,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00047617298469507534,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.1315704807639122,
|
|
"num_tokens": 31729783.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 6.587510347366333,
|
|
"epoch": 1.5698539247685805,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004761558584806988,
|
|
"loss": 6.2887,
|
|
"mean_token_accuracy": 0.13561197146773338,
|
|
"num_tokens": 31740796.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 6.714927101135254,
|
|
"epoch": 1.5703889988763444,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004761387264579751,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.1286628656089306,
|
|
"num_tokens": 31750559.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 6.5851012706756595,
|
|
"epoch": 1.5709240729841083,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004761215886273989,
|
|
"loss": 6.2491,
|
|
"mean_token_accuracy": 0.13372278064489365,
|
|
"num_tokens": 31761559.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 6.557302951812744,
|
|
"epoch": 1.5714591470918722,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00047610444498946507,
|
|
"loss": 6.2388,
|
|
"mean_token_accuracy": 0.13366507813334466,
|
|
"num_tokens": 31771677.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 6.607733917236328,
|
|
"epoch": 1.571994221199636,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004760872955446688,
|
|
"loss": 6.3926,
|
|
"mean_token_accuracy": 0.12398634850978851,
|
|
"num_tokens": 31783028.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 6.586536598205567,
|
|
"epoch": 1.5725292953074002,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047607014029350504,
|
|
"loss": 6.3455,
|
|
"mean_token_accuracy": 0.13382895141839982,
|
|
"num_tokens": 31793110.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 6.566289329528809,
|
|
"epoch": 1.573064369415164,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047605297923646923,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.13202153593301774,
|
|
"num_tokens": 31804193.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 6.5647545337677,
|
|
"epoch": 1.573599443522928,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047603581237405684,
|
|
"loss": 6.3135,
|
|
"mean_token_accuracy": 0.13706985041499137,
|
|
"num_tokens": 31815752.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 6.621603059768677,
|
|
"epoch": 1.574134517630692,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047601863970676367,
|
|
"loss": 6.3859,
|
|
"mean_token_accuracy": 0.12783994004130364,
|
|
"num_tokens": 31825936.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 6.611870193481446,
|
|
"epoch": 1.5746695917384557,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00047600146123508554,
|
|
"loss": 6.2858,
|
|
"mean_token_accuracy": 0.12577598989009858,
|
|
"num_tokens": 31836601.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 6.48514609336853,
|
|
"epoch": 1.5752046658462198,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047598427695951846,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.14532327204942702,
|
|
"num_tokens": 31846476.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 6.508503866195679,
|
|
"epoch": 1.5757397399539836,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00047596708688055857,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.14378889948129653,
|
|
"num_tokens": 31856151.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 6.655289554595948,
|
|
"epoch": 1.5762748140617475,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004759498909987023,
|
|
"loss": 6.3822,
|
|
"mean_token_accuracy": 0.12285813465714454,
|
|
"num_tokens": 31867419.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 6.630120420455933,
|
|
"epoch": 1.5768098881695116,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004759326893144462,
|
|
"loss": 6.3805,
|
|
"mean_token_accuracy": 0.12796944230794907,
|
|
"num_tokens": 31878036.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 6.582902574539185,
|
|
"epoch": 1.5773449622772753,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000475915481828287,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.12752599716186525,
|
|
"num_tokens": 31887919.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 6.528231382369995,
|
|
"epoch": 1.5778800363850394,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00047589826854072133,
|
|
"loss": 6.3169,
|
|
"mean_token_accuracy": 0.1306762307882309,
|
|
"num_tokens": 31898962.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 6.631040048599243,
|
|
"epoch": 1.5784151104928033,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047588104945224654,
|
|
"loss": 6.4203,
|
|
"mean_token_accuracy": 0.1277483507990837,
|
|
"num_tokens": 31911027.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 6.693498992919922,
|
|
"epoch": 1.5789501846005671,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004758638245633595,
|
|
"loss": 6.3491,
|
|
"mean_token_accuracy": 0.13183382153511047,
|
|
"num_tokens": 31921226.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 6.59174370765686,
|
|
"epoch": 1.5794852587083312,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004758465938745579,
|
|
"loss": 6.2908,
|
|
"mean_token_accuracy": 0.13105081021785736,
|
|
"num_tokens": 31932848.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 6.547547340393066,
|
|
"epoch": 1.5800203328160949,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047582935738633915,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.1314263053238392,
|
|
"num_tokens": 31943757.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 6.605871152877808,
|
|
"epoch": 1.580555406923859,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004758121150992009,
|
|
"loss": 6.3729,
|
|
"mean_token_accuracy": 0.1265105903148651,
|
|
"num_tokens": 31954391.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 6.596248817443848,
|
|
"epoch": 1.5810904810316229,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047579486701364093,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.12978238463401795,
|
|
"num_tokens": 31964497.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 6.63506669998169,
|
|
"epoch": 1.5816255551393867,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.0004757776131301575,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.12468324452638627,
|
|
"num_tokens": 31974466.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 6.664370441436768,
|
|
"epoch": 1.5821606292471508,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004757603534492487,
|
|
"loss": 6.3659,
|
|
"mean_token_accuracy": 0.12907677814364432,
|
|
"num_tokens": 31985890.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 6.633312702178955,
|
|
"epoch": 1.5826957033549145,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004757430879714128,
|
|
"loss": 6.461,
|
|
"mean_token_accuracy": 0.12869332060217858,
|
|
"num_tokens": 31996865.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 6.551844215393066,
|
|
"epoch": 1.5832307774626786,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004757258166971485,
|
|
"loss": 6.2053,
|
|
"mean_token_accuracy": 0.14229926690459252,
|
|
"num_tokens": 32008121.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 6.6514777660369875,
|
|
"epoch": 1.5837658515704425,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004757085396269545,
|
|
"loss": 6.4085,
|
|
"mean_token_accuracy": 0.12366401329636574,
|
|
"num_tokens": 32020552.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 6.649660444259643,
|
|
"epoch": 1.5843009256782064,
|
|
"grad_norm": 8.25,
|
|
"learning_rate": 0.00047569125676132963,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.12904865220189093,
|
|
"num_tokens": 32032361.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 6.654403305053711,
|
|
"epoch": 1.5848359997859705,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047567396810077286,
|
|
"loss": 6.3651,
|
|
"mean_token_accuracy": 0.12120763063430787,
|
|
"num_tokens": 32043233.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 6.632879114151001,
|
|
"epoch": 1.5853710738937343,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047565667364578344,
|
|
"loss": 6.2929,
|
|
"mean_token_accuracy": 0.13683302700519562,
|
|
"num_tokens": 32054273.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 6.615459775924682,
|
|
"epoch": 1.5859061480014982,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004756393733968608,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.13609257936477662,
|
|
"num_tokens": 32064200.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 6.514322566986084,
|
|
"epoch": 1.586441222109262,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004756220673545045,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.13050827756524086,
|
|
"num_tokens": 32074823.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 6.550486612319946,
|
|
"epoch": 1.586976296217026,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047560475551921416,
|
|
"loss": 6.3741,
|
|
"mean_token_accuracy": 0.13203538805246354,
|
|
"num_tokens": 32085333.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 6.679742860794067,
|
|
"epoch": 1.58751137032479,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004755874378914897,
|
|
"loss": 6.3527,
|
|
"mean_token_accuracy": 0.1274569056928158,
|
|
"num_tokens": 32095827.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 6.6661763191223145,
|
|
"epoch": 1.588046444432554,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004755701144718311,
|
|
"loss": 6.3494,
|
|
"mean_token_accuracy": 0.1311432473361492,
|
|
"num_tokens": 32106949.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 6.617701816558838,
|
|
"epoch": 1.5885815185403178,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047555278526073867,
|
|
"loss": 6.2965,
|
|
"mean_token_accuracy": 0.13490767031908035,
|
|
"num_tokens": 32118269.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 6.575267791748047,
|
|
"epoch": 1.589116592648082,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004755354502587127,
|
|
"loss": 6.3174,
|
|
"mean_token_accuracy": 0.1294573001563549,
|
|
"num_tokens": 32128406.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 6.590138053894043,
|
|
"epoch": 1.5896516667558456,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.00047551810946625385,
|
|
"loss": 6.3501,
|
|
"mean_token_accuracy": 0.13134751915931703,
|
|
"num_tokens": 32140112.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 6.635708141326904,
|
|
"epoch": 1.5901867408636097,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047550076288386276,
|
|
"loss": 6.2723,
|
|
"mean_token_accuracy": 0.14180956929922103,
|
|
"num_tokens": 32150010.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 6.646892404556274,
|
|
"epoch": 1.5907218149713735,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004754834105120403,
|
|
"loss": 6.3789,
|
|
"mean_token_accuracy": 0.12848537862300874,
|
|
"num_tokens": 32160694.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 6.622180604934693,
|
|
"epoch": 1.5912568890791374,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00047546605235128755,
|
|
"loss": 6.3954,
|
|
"mean_token_accuracy": 0.12833331078290938,
|
|
"num_tokens": 32171947.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 6.701618194580078,
|
|
"epoch": 1.5917919631869015,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004754486884021057,
|
|
"loss": 6.3702,
|
|
"mean_token_accuracy": 0.1309874251484871,
|
|
"num_tokens": 32182849.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 6.634417009353638,
|
|
"epoch": 1.5923270372946652,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004754313186649961,
|
|
"loss": 6.3577,
|
|
"mean_token_accuracy": 0.1309151455760002,
|
|
"num_tokens": 32192871.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 6.63468713760376,
|
|
"epoch": 1.5928621114024293,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.00047541394314046037,
|
|
"loss": 6.3951,
|
|
"mean_token_accuracy": 0.12587238401174544,
|
|
"num_tokens": 32203289.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 6.637603616714477,
|
|
"epoch": 1.5933971855101932,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004753965618290002,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.1338638797402382,
|
|
"num_tokens": 32213238.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 6.586855220794678,
|
|
"epoch": 1.593932259617957,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004753791747311175,
|
|
"loss": 6.2749,
|
|
"mean_token_accuracy": 0.13351626470685005,
|
|
"num_tokens": 32223384.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 6.626897621154785,
|
|
"epoch": 1.5944673337257211,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047536178184731426,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.13031843081116676,
|
|
"num_tokens": 32235358.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 6.733929061889649,
|
|
"epoch": 1.5950024078334848,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004753443831780927,
|
|
"loss": 6.3881,
|
|
"mean_token_accuracy": 0.12627255618572236,
|
|
"num_tokens": 32246459.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 6.677834606170654,
|
|
"epoch": 1.595537481941249,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004753269787239552,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.132364159822464,
|
|
"num_tokens": 32257798.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 6.632442617416382,
|
|
"epoch": 1.5960725560490128,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047530956848540435,
|
|
"loss": 6.3148,
|
|
"mean_token_accuracy": 0.13264451622962953,
|
|
"num_tokens": 32268118.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 6.499905633926391,
|
|
"epoch": 1.5966076301567766,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004752921524629429,
|
|
"loss": 6.2589,
|
|
"mean_token_accuracy": 0.13095818608999252,
|
|
"num_tokens": 32279676.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 6.568278074264526,
|
|
"epoch": 1.5971427042645407,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004752747306570737,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.13241808935999871,
|
|
"num_tokens": 32290613.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 6.6734068393707275,
|
|
"epoch": 1.5976777783723044,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00047525730306829977,
|
|
"loss": 6.3255,
|
|
"mean_token_accuracy": 0.12900790944695473,
|
|
"num_tokens": 32300873.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 6.629452085494995,
|
|
"epoch": 1.5982128524800685,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004752398696971244,
|
|
"loss": 6.3434,
|
|
"mean_token_accuracy": 0.1297914333641529,
|
|
"num_tokens": 32312326.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 6.666079187393189,
|
|
"epoch": 1.5987479265878324,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047522243054405085,
|
|
"loss": 6.3117,
|
|
"mean_token_accuracy": 0.12396792843937873,
|
|
"num_tokens": 32324322.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 6.624876499176025,
|
|
"epoch": 1.5992830006955963,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004752049856095828,
|
|
"loss": 6.2966,
|
|
"mean_token_accuracy": 0.13041224628686904,
|
|
"num_tokens": 32334397.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 6.578952217102051,
|
|
"epoch": 1.5998180748033604,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047518753489422393,
|
|
"loss": 6.2908,
|
|
"mean_token_accuracy": 0.13576632663607596,
|
|
"num_tokens": 32345131.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 6.5346184253692625,
|
|
"epoch": 1.6003531489111242,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047517007839847816,
|
|
"loss": 6.261,
|
|
"mean_token_accuracy": 0.13239944726228714,
|
|
"num_tokens": 32355520.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 6.618630504608154,
|
|
"epoch": 1.6008882230188881,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004751526161228494,
|
|
"loss": 6.3812,
|
|
"mean_token_accuracy": 0.13626265674829482,
|
|
"num_tokens": 32366695.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 6.569707775115967,
|
|
"epoch": 1.601423297126652,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000475135148067842,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.1304539032280445,
|
|
"num_tokens": 32377467.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 6.6673486709594725,
|
|
"epoch": 1.6019583712344159,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047511767423396033,
|
|
"loss": 6.3145,
|
|
"mean_token_accuracy": 0.13318536207079887,
|
|
"num_tokens": 32388021.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 6.58619704246521,
|
|
"epoch": 1.60249344534218,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000475100194621709,
|
|
"loss": 6.3075,
|
|
"mean_token_accuracy": 0.13175821155309678,
|
|
"num_tokens": 32398105.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 6.622416019439697,
|
|
"epoch": 1.6030285194499438,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004750827092315926,
|
|
"loss": 6.4079,
|
|
"mean_token_accuracy": 0.13028636425733567,
|
|
"num_tokens": 32409876.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 6.63068995475769,
|
|
"epoch": 1.6035635935577077,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047506521806411613,
|
|
"loss": 6.3055,
|
|
"mean_token_accuracy": 0.13789043202996254,
|
|
"num_tokens": 32420283.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 6.645041561126709,
|
|
"epoch": 1.6040986676654718,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047504772111978463,
|
|
"loss": 6.3878,
|
|
"mean_token_accuracy": 0.12090407237410546,
|
|
"num_tokens": 32431164.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 6.629057741165161,
|
|
"epoch": 1.6046337417732355,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004750302183991032,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.13134497553110122,
|
|
"num_tokens": 32442253.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 6.611510181427002,
|
|
"epoch": 1.6051688158809996,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004750127099025774,
|
|
"loss": 6.4009,
|
|
"mean_token_accuracy": 0.13296333476901054,
|
|
"num_tokens": 32452800.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.6051688158809996,
|
|
"eval_entropy": 6.497136345578011,
|
|
"eval_loss": 6.438198089599609,
|
|
"eval_mean_token_accuracy": 0.13348102208849474,
|
|
"eval_num_tokens": 32452800.0,
|
|
"eval_runtime": 22.8069,
|
|
"eval_samples_per_second": 1301.315,
|
|
"eval_steps_per_second": 162.67,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 6.7039392471313475,
|
|
"epoch": 1.6057038899887635,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004749951956307126,
|
|
"loss": 6.3586,
|
|
"mean_token_accuracy": 0.12454131469130517,
|
|
"num_tokens": 32462890.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 6.630990362167358,
|
|
"epoch": 1.6062389640965273,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004749776755840148,
|
|
"loss": 6.3163,
|
|
"mean_token_accuracy": 0.13767746984958648,
|
|
"num_tokens": 32473422.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 6.592038583755493,
|
|
"epoch": 1.6067740382042914,
|
|
"grad_norm": 5.875,
|
|
"learning_rate": 0.00047496014976298957,
|
|
"loss": 6.3494,
|
|
"mean_token_accuracy": 0.12856539264321326,
|
|
"num_tokens": 32483980.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 6.647782468795777,
|
|
"epoch": 1.607309112312055,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004749426181681432,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.12655933424830437,
|
|
"num_tokens": 32494905.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 6.64284315109253,
|
|
"epoch": 1.6078441864198192,
|
|
"grad_norm": 8.5625,
|
|
"learning_rate": 0.00047492508079998173,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.12563200816512107,
|
|
"num_tokens": 32505799.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 6.61481237411499,
|
|
"epoch": 1.608379260527583,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004749075376590117,
|
|
"loss": 6.3602,
|
|
"mean_token_accuracy": 0.12689877450466155,
|
|
"num_tokens": 32516328.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 6.633776998519897,
|
|
"epoch": 1.608914334635347,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004748899887457396,
|
|
"loss": 6.3638,
|
|
"mean_token_accuracy": 0.1328594595193863,
|
|
"num_tokens": 32526335.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 6.624560260772705,
|
|
"epoch": 1.609449408743111,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047487243406067227,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.13055480495095254,
|
|
"num_tokens": 32536896.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 6.612313318252563,
|
|
"epoch": 1.6099844828508747,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004748548736043164,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.132292677462101,
|
|
"num_tokens": 32547604.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 6.682834005355835,
|
|
"epoch": 1.6105195569586388,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00047483730737717914,
|
|
"loss": 6.362,
|
|
"mean_token_accuracy": 0.12497605234384537,
|
|
"num_tokens": 32558539.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 6.6648775100708,
|
|
"epoch": 1.6110546310664027,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004748197353797677,
|
|
"loss": 6.4393,
|
|
"mean_token_accuracy": 0.12241820469498635,
|
|
"num_tokens": 32569787.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 6.62459077835083,
|
|
"epoch": 1.6115897051741666,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004748021576125895,
|
|
"loss": 6.3694,
|
|
"mean_token_accuracy": 0.1310337647795677,
|
|
"num_tokens": 32580146.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 6.647180843353271,
|
|
"epoch": 1.6121247792819307,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004747845740761521,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.1317858375608921,
|
|
"num_tokens": 32591243.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 6.634462547302246,
|
|
"epoch": 1.6126598533896943,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004747669847709631,
|
|
"loss": 6.3831,
|
|
"mean_token_accuracy": 0.12935088202357292,
|
|
"num_tokens": 32602424.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 6.6950843334198,
|
|
"epoch": 1.6131949274974584,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004747493896975306,
|
|
"loss": 6.4308,
|
|
"mean_token_accuracy": 0.12338371276855468,
|
|
"num_tokens": 32613703.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 6.657159423828125,
|
|
"epoch": 1.6137300016052223,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004747317888563625,
|
|
"loss": 6.3954,
|
|
"mean_token_accuracy": 0.12457507327198983,
|
|
"num_tokens": 32624371.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 6.621936988830567,
|
|
"epoch": 1.6142650757129862,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.00047471418224796704,
|
|
"loss": 6.3247,
|
|
"mean_token_accuracy": 0.13022591471672057,
|
|
"num_tokens": 32634039.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 6.614598655700684,
|
|
"epoch": 1.6148001498207503,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004746965698728526,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.1345980040729046,
|
|
"num_tokens": 32644644.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 6.653465270996094,
|
|
"epoch": 1.6153352239285141,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00047467895173152787,
|
|
"loss": 6.3393,
|
|
"mean_token_accuracy": 0.13484947979450226,
|
|
"num_tokens": 32655961.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 6.60253381729126,
|
|
"epoch": 1.615870298036278,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047466132782450146,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.14157851189374923,
|
|
"num_tokens": 32665506.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 6.563534545898437,
|
|
"epoch": 1.616405372144042,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047464369815228215,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.1310724548995495,
|
|
"num_tokens": 32676278.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 6.602992582321167,
|
|
"epoch": 1.6169404462518058,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004746260627153792,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.13006754517555236,
|
|
"num_tokens": 32686835.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 6.681662654876709,
|
|
"epoch": 1.6174755203595699,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00047460842151430166,
|
|
"loss": 6.4241,
|
|
"mean_token_accuracy": 0.127652844786644,
|
|
"num_tokens": 32696856.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 6.653195905685425,
|
|
"epoch": 1.6180105944673338,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.00047459077454955914,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.12848575934767723,
|
|
"num_tokens": 32707514.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 6.667760992050171,
|
|
"epoch": 1.6185456685750976,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00047457312182166094,
|
|
"loss": 6.4196,
|
|
"mean_token_accuracy": 0.12824680805206298,
|
|
"num_tokens": 32718934.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 6.653951930999756,
|
|
"epoch": 1.6190807426828617,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004745554633311169,
|
|
"loss": 6.3265,
|
|
"mean_token_accuracy": 0.12734292075037956,
|
|
"num_tokens": 32729249.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 6.625629186630249,
|
|
"epoch": 1.6196158167906254,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047453779907843686,
|
|
"loss": 6.3807,
|
|
"mean_token_accuracy": 0.12749914154410363,
|
|
"num_tokens": 32739948.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 6.6512809753417965,
|
|
"epoch": 1.6201508908983895,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047452012906413105,
|
|
"loss": 6.3711,
|
|
"mean_token_accuracy": 0.12841144502162932,
|
|
"num_tokens": 32751482.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 6.61352276802063,
|
|
"epoch": 1.6206859650061534,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00047450245328870943,
|
|
"loss": 6.2248,
|
|
"mean_token_accuracy": 0.14227624535560607,
|
|
"num_tokens": 32761260.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 6.633208894729615,
|
|
"epoch": 1.6212210391139172,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047448477175268255,
|
|
"loss": 6.339,
|
|
"mean_token_accuracy": 0.13111163824796676,
|
|
"num_tokens": 32772684.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 6.474795198440551,
|
|
"epoch": 1.6217561132216813,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047446708445656095,
|
|
"loss": 6.1548,
|
|
"mean_token_accuracy": 0.14719875231385232,
|
|
"num_tokens": 32784022.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 6.608185720443726,
|
|
"epoch": 1.622291187329445,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004744493914008552,
|
|
"loss": 6.2698,
|
|
"mean_token_accuracy": 0.13183990344405175,
|
|
"num_tokens": 32794104.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 6.666050767898559,
|
|
"epoch": 1.622826261437209,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004744316925860764,
|
|
"loss": 6.273,
|
|
"mean_token_accuracy": 0.13637425899505615,
|
|
"num_tokens": 32804038.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 6.573110342025757,
|
|
"epoch": 1.623361335544973,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004744139880127355,
|
|
"loss": 6.342,
|
|
"mean_token_accuracy": 0.1315135180950165,
|
|
"num_tokens": 32815620.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 6.572382307052612,
|
|
"epoch": 1.6238964096527368,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047439627768134366,
|
|
"loss": 6.2519,
|
|
"mean_token_accuracy": 0.14027094691991807,
|
|
"num_tokens": 32826353.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 6.616070699691773,
|
|
"epoch": 1.624431483760501,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004743785615924124,
|
|
"loss": 6.3697,
|
|
"mean_token_accuracy": 0.12889265790581703,
|
|
"num_tokens": 32836582.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 6.618151473999023,
|
|
"epoch": 1.6249665578682646,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004743608397464531,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.13237857446074486,
|
|
"num_tokens": 32848073.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 6.653196954727173,
|
|
"epoch": 1.6255016319760287,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047434311214397765,
|
|
"loss": 6.3613,
|
|
"mean_token_accuracy": 0.12775565162301064,
|
|
"num_tokens": 32857839.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 6.549168252944947,
|
|
"epoch": 1.6260367060837926,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047432537878549786,
|
|
"loss": 6.2901,
|
|
"mean_token_accuracy": 0.1413236103951931,
|
|
"num_tokens": 32868087.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 6.606210708618164,
|
|
"epoch": 1.6265717801915565,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047430763967152564,
|
|
"loss": 6.3534,
|
|
"mean_token_accuracy": 0.12719216346740722,
|
|
"num_tokens": 32880622.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 6.681926012039185,
|
|
"epoch": 1.6271068542993206,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047428989480257337,
|
|
"loss": 6.3395,
|
|
"mean_token_accuracy": 0.12695611864328385,
|
|
"num_tokens": 32891405.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 6.662096929550171,
|
|
"epoch": 1.6276419284070842,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004742721441791535,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.13617558479309083,
|
|
"num_tokens": 32900487.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 6.536318731307984,
|
|
"epoch": 1.6281770025148483,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004742543878017784,
|
|
"loss": 6.2526,
|
|
"mean_token_accuracy": 0.14222714751958848,
|
|
"num_tokens": 32912139.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 6.604346084594726,
|
|
"epoch": 1.6287120766226122,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047423662567096085,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.12800935059785842,
|
|
"num_tokens": 32922972.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 6.622891473770141,
|
|
"epoch": 1.629247150730376,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047421885778721376,
|
|
"loss": 6.2765,
|
|
"mean_token_accuracy": 0.13566811829805375,
|
|
"num_tokens": 32932609.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 6.555486679077148,
|
|
"epoch": 1.6297822248381402,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047420108415105006,
|
|
"loss": 6.2945,
|
|
"mean_token_accuracy": 0.14234523251652717,
|
|
"num_tokens": 32942706.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 6.582446670532226,
|
|
"epoch": 1.630317298945904,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00047418330476298317,
|
|
"loss": 6.2957,
|
|
"mean_token_accuracy": 0.13032932505011557,
|
|
"num_tokens": 32952240.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 6.616906023025512,
|
|
"epoch": 1.630852373053668,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004741655196235262,
|
|
"loss": 6.3554,
|
|
"mean_token_accuracy": 0.12885645627975464,
|
|
"num_tokens": 32963249.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 6.635798215866089,
|
|
"epoch": 1.6313874471614318,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047414772873319294,
|
|
"loss": 6.3303,
|
|
"mean_token_accuracy": 0.13535914197564125,
|
|
"num_tokens": 32974004.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 6.673778009414673,
|
|
"epoch": 1.6319225212691957,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000474129932092497,
|
|
"loss": 6.3168,
|
|
"mean_token_accuracy": 0.1309266485273838,
|
|
"num_tokens": 32985236.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 6.675806856155395,
|
|
"epoch": 1.6324575953769598,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004741121297019522,
|
|
"loss": 6.3604,
|
|
"mean_token_accuracy": 0.12881071865558624,
|
|
"num_tokens": 32995155.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 6.68417329788208,
|
|
"epoch": 1.6329926694847237,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.00047409432156207264,
|
|
"loss": 6.3462,
|
|
"mean_token_accuracy": 0.1371862508356571,
|
|
"num_tokens": 33007562.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 6.594800090789795,
|
|
"epoch": 1.6335277435924875,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00047407650767337256,
|
|
"loss": 6.3095,
|
|
"mean_token_accuracy": 0.1269940122961998,
|
|
"num_tokens": 33018653.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 6.650726938247681,
|
|
"epoch": 1.6340628177002516,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004740586880363663,
|
|
"loss": 6.4303,
|
|
"mean_token_accuracy": 0.12319175526499748,
|
|
"num_tokens": 33029470.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 6.646920776367187,
|
|
"epoch": 1.6345978918080153,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047404086265156835,
|
|
"loss": 6.2794,
|
|
"mean_token_accuracy": 0.13674794062972068,
|
|
"num_tokens": 33039597.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 6.5994054794311525,
|
|
"epoch": 1.6351329659157794,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004740230315194935,
|
|
"loss": 6.3177,
|
|
"mean_token_accuracy": 0.13071761801838874,
|
|
"num_tokens": 33050984.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 6.59453821182251,
|
|
"epoch": 1.6356680400235433,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00047400519464065656,
|
|
"loss": 6.3696,
|
|
"mean_token_accuracy": 0.13218805193901062,
|
|
"num_tokens": 33062250.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 6.647855472564697,
|
|
"epoch": 1.6362031141313071,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004739873520155726,
|
|
"loss": 6.4036,
|
|
"mean_token_accuracy": 0.13088377118110656,
|
|
"num_tokens": 33072129.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 6.6347808837890625,
|
|
"epoch": 1.6367381882390712,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004739695036447568,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.13105602338910102,
|
|
"num_tokens": 33082475.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 6.57205023765564,
|
|
"epoch": 1.637273262346835,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00047395164952872455,
|
|
"loss": 6.2993,
|
|
"mean_token_accuracy": 0.14202253818511962,
|
|
"num_tokens": 33093791.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 6.634311819076538,
|
|
"epoch": 1.637808336454599,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004739337896679914,
|
|
"loss": 6.2832,
|
|
"mean_token_accuracy": 0.139603790640831,
|
|
"num_tokens": 33104231.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 6.596739149093628,
|
|
"epoch": 1.6383434105623629,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047391592406307296,
|
|
"loss": 6.2887,
|
|
"mean_token_accuracy": 0.12891674265265465,
|
|
"num_tokens": 33115118.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 6.59426326751709,
|
|
"epoch": 1.6388784846701268,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004738980527144852,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.13312907591462136,
|
|
"num_tokens": 33126154.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 6.599968576431275,
|
|
"epoch": 1.6394135587778909,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004738801756227441,
|
|
"loss": 6.3504,
|
|
"mean_token_accuracy": 0.13169101178646087,
|
|
"num_tokens": 33137342.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 6.536832523345947,
|
|
"epoch": 1.6399486328856545,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00047386229278836595,
|
|
"loss": 6.3242,
|
|
"mean_token_accuracy": 0.13218657150864602,
|
|
"num_tokens": 33147661.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 6.648887014389038,
|
|
"epoch": 1.6404837069934186,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047384440421186695,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.1300333596765995,
|
|
"num_tokens": 33157106.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 6.657330560684204,
|
|
"epoch": 1.6410187811011825,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004738265098937638,
|
|
"loss": 6.3404,
|
|
"mean_token_accuracy": 0.13192059919238092,
|
|
"num_tokens": 33169451.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 6.657918310165405,
|
|
"epoch": 1.6415538552089464,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000473808609834573,
|
|
"loss": 6.3568,
|
|
"mean_token_accuracy": 0.12858274728059768,
|
|
"num_tokens": 33180799.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 6.6730410099029545,
|
|
"epoch": 1.6420889293167105,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047379070403481165,
|
|
"loss": 6.4238,
|
|
"mean_token_accuracy": 0.12632434144616128,
|
|
"num_tokens": 33191948.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 6.595246315002441,
|
|
"epoch": 1.6426240034244743,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00047377279249499656,
|
|
"loss": 6.3284,
|
|
"mean_token_accuracy": 0.12742524072527886,
|
|
"num_tokens": 33203536.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 6.6604820728302006,
|
|
"epoch": 1.6431590775322382,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004737548752156451,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.1314496412873268,
|
|
"num_tokens": 33214526.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 6.593611383438111,
|
|
"epoch": 1.643694151640002,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004737369521972745,
|
|
"loss": 6.3051,
|
|
"mean_token_accuracy": 0.1356895625591278,
|
|
"num_tokens": 33226560.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 6.5674488067626955,
|
|
"epoch": 1.644229225747766,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00047371902344040234,
|
|
"loss": 6.3123,
|
|
"mean_token_accuracy": 0.13007354065775872,
|
|
"num_tokens": 33237441.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 6.599070930480957,
|
|
"epoch": 1.64476429985553,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047370108894554633,
|
|
"loss": 6.2704,
|
|
"mean_token_accuracy": 0.13252194002270698,
|
|
"num_tokens": 33248229.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 6.553744983673096,
|
|
"epoch": 1.645299373963294,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004736831487132243,
|
|
"loss": 6.2215,
|
|
"mean_token_accuracy": 0.14548372998833656,
|
|
"num_tokens": 33258992.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 6.562128067016602,
|
|
"epoch": 1.6458344480710578,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004736652027439542,
|
|
"loss": 6.2573,
|
|
"mean_token_accuracy": 0.13460740223526954,
|
|
"num_tokens": 33269583.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 6.618464994430542,
|
|
"epoch": 1.646369522178822,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047364725103825437,
|
|
"loss": 6.3746,
|
|
"mean_token_accuracy": 0.12685413733124734,
|
|
"num_tokens": 33280236.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 6.594023418426514,
|
|
"epoch": 1.6469045962865856,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000473629293596643,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.13143166452646254,
|
|
"num_tokens": 33291327.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 6.622612428665161,
|
|
"epoch": 1.6474396703943497,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00047361133041963873,
|
|
"loss": 6.3674,
|
|
"mean_token_accuracy": 0.12954002022743225,
|
|
"num_tokens": 33302125.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 6.598691320419311,
|
|
"epoch": 1.6479747445021136,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004735933615077602,
|
|
"loss": 6.3198,
|
|
"mean_token_accuracy": 0.12793680876493455,
|
|
"num_tokens": 33312576.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 6.612389659881591,
|
|
"epoch": 1.6485098186098774,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047357538686152627,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.13181447014212608,
|
|
"num_tokens": 33322821.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 6.633521556854248,
|
|
"epoch": 1.6490448927176415,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00047355740648145596,
|
|
"loss": 6.348,
|
|
"mean_token_accuracy": 0.12862193435430527,
|
|
"num_tokens": 33333951.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 6.649112033843994,
|
|
"epoch": 1.6495799668254052,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004735394203680684,
|
|
"loss": 6.2938,
|
|
"mean_token_accuracy": 0.1329148754477501,
|
|
"num_tokens": 33344739.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 6.661335039138794,
|
|
"epoch": 1.6501150409331693,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047352142852188304,
|
|
"loss": 6.256,
|
|
"mean_token_accuracy": 0.13395226001739502,
|
|
"num_tokens": 33354956.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 6.493580007553101,
|
|
"epoch": 1.6506501150409332,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004735034309434193,
|
|
"loss": 6.2397,
|
|
"mean_token_accuracy": 0.1374268114566803,
|
|
"num_tokens": 33364809.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 6.599809646606445,
|
|
"epoch": 1.651185189148697,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004734854276331968,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.13576392754912375,
|
|
"num_tokens": 33375324.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 6.664802312850952,
|
|
"epoch": 1.6517202632564612,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047346741859173564,
|
|
"loss": 6.413,
|
|
"mean_token_accuracy": 0.12761991694569588,
|
|
"num_tokens": 33385963.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 6.689538908004761,
|
|
"epoch": 1.6522553373642248,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004734494038195555,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.12837739959359168,
|
|
"num_tokens": 33395927.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 6.627625942230225,
|
|
"epoch": 1.652790411471989,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004734313833171768,
|
|
"loss": 6.3162,
|
|
"mean_token_accuracy": 0.1345876343548298,
|
|
"num_tokens": 33406294.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 6.585708665847778,
|
|
"epoch": 1.6533254855797528,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004734133570851198,
|
|
"loss": 6.2815,
|
|
"mean_token_accuracy": 0.13808462917804717,
|
|
"num_tokens": 33416995.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 6.516575145721435,
|
|
"epoch": 1.6538605596875167,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004733953251239049,
|
|
"loss": 6.2313,
|
|
"mean_token_accuracy": 0.13732824847102165,
|
|
"num_tokens": 33428087.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 6.629632759094238,
|
|
"epoch": 1.6543956337952808,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004733772874340529,
|
|
"loss": 6.4062,
|
|
"mean_token_accuracy": 0.12961470559239388,
|
|
"num_tokens": 33439151.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 6.624176073074341,
|
|
"epoch": 1.6549307079030444,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004733592440160846,
|
|
"loss": 6.2992,
|
|
"mean_token_accuracy": 0.13723560497164727,
|
|
"num_tokens": 33449257.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 6.574230623245239,
|
|
"epoch": 1.6554657820108085,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00047334119487052104,
|
|
"loss": 6.2703,
|
|
"mean_token_accuracy": 0.1331109032034874,
|
|
"num_tokens": 33460472.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 6.597341680526734,
|
|
"epoch": 1.6560008561185724,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047332313999788334,
|
|
"loss": 6.2822,
|
|
"mean_token_accuracy": 0.12963220328092576,
|
|
"num_tokens": 33470193.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 6.486804389953614,
|
|
"epoch": 1.6565359302263363,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00047330507939869284,
|
|
"loss": 6.2173,
|
|
"mean_token_accuracy": 0.13749109506607055,
|
|
"num_tokens": 33481098.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 6.640764951705933,
|
|
"epoch": 1.6570710043341004,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000473287013073471,
|
|
"loss": 6.3098,
|
|
"mean_token_accuracy": 0.1328273668885231,
|
|
"num_tokens": 33492514.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 6.631761741638184,
|
|
"epoch": 1.6576060784418643,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004732689410227396,
|
|
"loss": 6.2967,
|
|
"mean_token_accuracy": 0.13085147142410278,
|
|
"num_tokens": 33504254.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 6.605322170257568,
|
|
"epoch": 1.6581411525496281,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004732508632470203,
|
|
"loss": 6.3036,
|
|
"mean_token_accuracy": 0.12817856520414353,
|
|
"num_tokens": 33515101.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 6.587841892242432,
|
|
"epoch": 1.658676226657392,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004732327797468352,
|
|
"loss": 6.2965,
|
|
"mean_token_accuracy": 0.13031181544065476,
|
|
"num_tokens": 33525052.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 6.6165220737457275,
|
|
"epoch": 1.6592113007651559,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004732146905227065,
|
|
"loss": 6.4595,
|
|
"mean_token_accuracy": 0.12015106230974197,
|
|
"num_tokens": 33536841.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 6.6230329990386965,
|
|
"epoch": 1.65974637487292,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004731965955751564,
|
|
"loss": 6.3429,
|
|
"mean_token_accuracy": 0.12911240085959436,
|
|
"num_tokens": 33547292.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 6.6358482837677,
|
|
"epoch": 1.6602814489806839,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004731784949047075,
|
|
"loss": 6.2679,
|
|
"mean_token_accuracy": 0.13079825341701506,
|
|
"num_tokens": 33557674.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 6.6476973533630375,
|
|
"epoch": 1.6608165230884477,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004731603885118824,
|
|
"loss": 6.3619,
|
|
"mean_token_accuracy": 0.12732397243380547,
|
|
"num_tokens": 33568396.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 6.650739908218384,
|
|
"epoch": 1.6613515971962118,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004731422763972039,
|
|
"loss": 6.4109,
|
|
"mean_token_accuracy": 0.12701910063624383,
|
|
"num_tokens": 33579688.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 6.659929180145264,
|
|
"epoch": 1.6618866713039755,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00047312415856119505,
|
|
"loss": 6.4215,
|
|
"mean_token_accuracy": 0.12725574970245362,
|
|
"num_tokens": 33591550.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 6.7010422706604,
|
|
"epoch": 1.6624217454117396,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047310603500437895,
|
|
"loss": 6.3404,
|
|
"mean_token_accuracy": 0.13577439785003662,
|
|
"num_tokens": 33600792.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 6.606597566604615,
|
|
"epoch": 1.6629568195195035,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047308790572727895,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.1334552951157093,
|
|
"num_tokens": 33611873.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 6.5518897533416744,
|
|
"epoch": 1.6634918936272673,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004730697707304184,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.12786948606371878,
|
|
"num_tokens": 33622960.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 6.63243293762207,
|
|
"epoch": 1.6640269677350314,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004730516300143211,
|
|
"loss": 6.411,
|
|
"mean_token_accuracy": 0.13002867698669435,
|
|
"num_tokens": 33635391.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 6.688350534439087,
|
|
"epoch": 1.664562041842795,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004730334835795109,
|
|
"loss": 6.3383,
|
|
"mean_token_accuracy": 0.12779011204838753,
|
|
"num_tokens": 33647942.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 6.666274452209473,
|
|
"epoch": 1.6650971159505592,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004730153314265116,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.13125099763274192,
|
|
"num_tokens": 33658425.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 6.588416194915771,
|
|
"epoch": 1.665632190058323,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004729971735558475,
|
|
"loss": 6.2922,
|
|
"mean_token_accuracy": 0.13702479973435402,
|
|
"num_tokens": 33669645.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 6.653393840789795,
|
|
"epoch": 1.666167264166087,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004729790099680428,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.12628820389509202,
|
|
"num_tokens": 33680415.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 6.606220054626465,
|
|
"epoch": 1.666702338273851,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000472960840663622,
|
|
"loss": 6.3983,
|
|
"mean_token_accuracy": 0.12569784373044968,
|
|
"num_tokens": 33691425.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 6.579849672317505,
|
|
"epoch": 1.6672374123816147,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004729426656431097,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.1358106829226017,
|
|
"num_tokens": 33703845.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 6.684722995758056,
|
|
"epoch": 1.6677724864893788,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004729244849070308,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.1314408779144287,
|
|
"num_tokens": 33714737.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 6.592172145843506,
|
|
"epoch": 1.6683075605971427,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047290629845591026,
|
|
"loss": 6.2655,
|
|
"mean_token_accuracy": 0.13266967087984086,
|
|
"num_tokens": 33725042.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 6.5786230087280275,
|
|
"epoch": 1.6688426347049066,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000472888106290273,
|
|
"loss": 6.3179,
|
|
"mean_token_accuracy": 0.1289871871471405,
|
|
"num_tokens": 33736306.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 6.707979774475097,
|
|
"epoch": 1.6693777088126707,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047286990841064467,
|
|
"loss": 6.3722,
|
|
"mean_token_accuracy": 0.12232113480567933,
|
|
"num_tokens": 33747327.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 6.603635787963867,
|
|
"epoch": 1.6699127829204343,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004728517048175504,
|
|
"loss": 6.2945,
|
|
"mean_token_accuracy": 0.1330920048058033,
|
|
"num_tokens": 33757723.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 6.474155712127685,
|
|
"epoch": 1.6704478570281984,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000472833495511516,
|
|
"loss": 6.2641,
|
|
"mean_token_accuracy": 0.1339734673500061,
|
|
"num_tokens": 33769958.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 6.584074306488037,
|
|
"epoch": 1.6709829311359623,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00047281528049306727,
|
|
"loss": 6.2855,
|
|
"mean_token_accuracy": 0.1338521271944046,
|
|
"num_tokens": 33780107.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 6.605830526351928,
|
|
"epoch": 1.6715180052437262,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004727970597627301,
|
|
"loss": 6.3305,
|
|
"mean_token_accuracy": 0.1283121168613434,
|
|
"num_tokens": 33791023.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 6.576494312286377,
|
|
"epoch": 1.6720530793514903,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004727788333210305,
|
|
"loss": 6.3289,
|
|
"mean_token_accuracy": 0.1364523097872734,
|
|
"num_tokens": 33801195.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 6.584420967102051,
|
|
"epoch": 1.6725881534592542,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000472760601168495,
|
|
"loss": 6.3015,
|
|
"mean_token_accuracy": 0.13910519927740098,
|
|
"num_tokens": 33812957.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 6.61924786567688,
|
|
"epoch": 1.673123227567018,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047274236330564995,
|
|
"loss": 6.3448,
|
|
"mean_token_accuracy": 0.1288554809987545,
|
|
"num_tokens": 33823874.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 6.610079956054688,
|
|
"epoch": 1.673658301674782,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004727241197330219,
|
|
"loss": 6.2991,
|
|
"mean_token_accuracy": 0.13549968153238295,
|
|
"num_tokens": 33834284.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 6.6640490055084225,
|
|
"epoch": 1.6741933757825458,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004727058704511376,
|
|
"loss": 6.3541,
|
|
"mean_token_accuracy": 0.12749727070331573,
|
|
"num_tokens": 33845544.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 6.658020162582398,
|
|
"epoch": 1.67472844989031,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004726876154605242,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.12860184386372567,
|
|
"num_tokens": 33855420.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 6.613762712478637,
|
|
"epoch": 1.6752635239980738,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004726693547617086,
|
|
"loss": 6.2352,
|
|
"mean_token_accuracy": 0.13463180810213088,
|
|
"num_tokens": 33864904.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 6.586810636520386,
|
|
"epoch": 1.6757985981058376,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047265108835521825,
|
|
"loss": 6.2891,
|
|
"mean_token_accuracy": 0.1301662303507328,
|
|
"num_tokens": 33875139.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 6.588503408432007,
|
|
"epoch": 1.6763336722136017,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004726328162415804,
|
|
"loss": 6.3138,
|
|
"mean_token_accuracy": 0.12985033988952638,
|
|
"num_tokens": 33886401.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 6.63114972114563,
|
|
"epoch": 1.6768687463213654,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00047261453842132277,
|
|
"loss": 6.33,
|
|
"mean_token_accuracy": 0.13734885305166245,
|
|
"num_tokens": 33896382.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 6.624880361557007,
|
|
"epoch": 1.6774038204291295,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.00047259625489497317,
|
|
"loss": 6.302,
|
|
"mean_token_accuracy": 0.13409410268068314,
|
|
"num_tokens": 33906403.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 6.494806337356567,
|
|
"epoch": 1.6779388945368934,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00047257796566305946,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.13780235052108764,
|
|
"num_tokens": 33916992.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 6.6446911811828615,
|
|
"epoch": 1.6784739686446573,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004725596707261097,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.12677459195256233,
|
|
"num_tokens": 33927599.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 6.708520984649658,
|
|
"epoch": 1.6790090427524214,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004725413700846522,
|
|
"loss": 6.4039,
|
|
"mean_token_accuracy": 0.1242218941450119,
|
|
"num_tokens": 33938957.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 6.595543384552002,
|
|
"epoch": 1.679544116860185,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047252306373921543,
|
|
"loss": 6.3095,
|
|
"mean_token_accuracy": 0.13570107370615006,
|
|
"num_tokens": 33950169.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 6.598382759094238,
|
|
"epoch": 1.680079190967949,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00047250475169032804,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.1289659895002842,
|
|
"num_tokens": 33960800.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 6.625497150421142,
|
|
"epoch": 1.680614265075713,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004724864339385185,
|
|
"loss": 6.3893,
|
|
"mean_token_accuracy": 0.1255663387477398,
|
|
"num_tokens": 33973060.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 6.644721031188965,
|
|
"epoch": 1.6811493391834769,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004724681104843161,
|
|
"loss": 6.3924,
|
|
"mean_token_accuracy": 0.1254941590130329,
|
|
"num_tokens": 33983185.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 6.658469772338867,
|
|
"epoch": 1.681684413291241,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004724497813282497,
|
|
"loss": 6.3269,
|
|
"mean_token_accuracy": 0.13494203835725785,
|
|
"num_tokens": 33993373.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 6.552082824707031,
|
|
"epoch": 1.6822194873990046,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004724314464708486,
|
|
"loss": 6.2509,
|
|
"mean_token_accuracy": 0.14298256933689119,
|
|
"num_tokens": 34005793.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 6.577910232543945,
|
|
"epoch": 1.6827545615067687,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004724131059126423,
|
|
"loss": 6.3941,
|
|
"mean_token_accuracy": 0.12339521944522858,
|
|
"num_tokens": 34016415.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 6.579348611831665,
|
|
"epoch": 1.6832896356145326,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047239475965416016,
|
|
"loss": 6.2482,
|
|
"mean_token_accuracy": 0.13493065014481545,
|
|
"num_tokens": 34026859.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 6.687756061553955,
|
|
"epoch": 1.6838247097222965,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047237640769593224,
|
|
"loss": 6.1855,
|
|
"mean_token_accuracy": 0.1511477179825306,
|
|
"num_tokens": 34037942.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 6.6067070960998535,
|
|
"epoch": 1.6843597838300606,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004723580500384882,
|
|
"loss": 6.2779,
|
|
"mean_token_accuracy": 0.13254965990781784,
|
|
"num_tokens": 34048659.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 6.522604370117188,
|
|
"epoch": 1.6848948579378242,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047233968668235817,
|
|
"loss": 6.2661,
|
|
"mean_token_accuracy": 0.1351561240851879,
|
|
"num_tokens": 34059961.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 6.598905229568482,
|
|
"epoch": 1.6854299320455883,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047232131762807244,
|
|
"loss": 6.3113,
|
|
"mean_token_accuracy": 0.13467268720269204,
|
|
"num_tokens": 34069978.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 6.635032796859742,
|
|
"epoch": 1.6859650061533522,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004723029428761614,
|
|
"loss": 6.3342,
|
|
"mean_token_accuracy": 0.13094720765948295,
|
|
"num_tokens": 34080301.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 6.570935201644898,
|
|
"epoch": 1.686500080261116,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047228456242715564,
|
|
"loss": 6.3102,
|
|
"mean_token_accuracy": 0.13536394760012627,
|
|
"num_tokens": 34092376.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 6.611394309997559,
|
|
"epoch": 1.6870351543688802,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004722661762815858,
|
|
"loss": 6.2943,
|
|
"mean_token_accuracy": 0.13419599682092667,
|
|
"num_tokens": 34102761.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 6.562061357498169,
|
|
"epoch": 1.687570228476644,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004722477844399829,
|
|
"loss": 6.3021,
|
|
"mean_token_accuracy": 0.12383381500840188,
|
|
"num_tokens": 34113370.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 6.612930107116699,
|
|
"epoch": 1.688105302584408,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004722293869028779,
|
|
"loss": 6.3157,
|
|
"mean_token_accuracy": 0.13814915269613265,
|
|
"num_tokens": 34125038.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 6.654970741271972,
|
|
"epoch": 1.6886403766921718,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004722109836708021,
|
|
"loss": 6.3401,
|
|
"mean_token_accuracy": 0.12763590440154077,
|
|
"num_tokens": 34135595.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 6.5883739471435545,
|
|
"epoch": 1.6891754507999357,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047219257474428685,
|
|
"loss": 6.3381,
|
|
"mean_token_accuracy": 0.12380890101194382,
|
|
"num_tokens": 34146755.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 6.473936605453491,
|
|
"epoch": 1.6897105249076998,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047217416012386367,
|
|
"loss": 6.1814,
|
|
"mean_token_accuracy": 0.14478894472122192,
|
|
"num_tokens": 34158465.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 6.585050439834594,
|
|
"epoch": 1.6902455990154637,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004721557398100644,
|
|
"loss": 6.2891,
|
|
"mean_token_accuracy": 0.13352150321006775,
|
|
"num_tokens": 34170007.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 6.632531833648682,
|
|
"epoch": 1.6907806731232276,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00047213731380342077,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.1267198570072651,
|
|
"num_tokens": 34181595.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 6.636486053466797,
|
|
"epoch": 1.6913157472309917,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000472118882104465,
|
|
"loss": 6.3378,
|
|
"mean_token_accuracy": 0.1303263157606125,
|
|
"num_tokens": 34191791.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 6.658541679382324,
|
|
"epoch": 1.6918508213387553,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00047210044471372915,
|
|
"loss": 6.2521,
|
|
"mean_token_accuracy": 0.13072575405240058,
|
|
"num_tokens": 34202636.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 6.6955639839172365,
|
|
"epoch": 1.6923858954465194,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004720820016317456,
|
|
"loss": 6.3849,
|
|
"mean_token_accuracy": 0.12349523305892944,
|
|
"num_tokens": 34213333.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 6.6826465129852295,
|
|
"epoch": 1.6929209695542833,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000472063552859047,
|
|
"loss": 6.3194,
|
|
"mean_token_accuracy": 0.13126217499375342,
|
|
"num_tokens": 34223679.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 6.598942375183105,
|
|
"epoch": 1.6934560436620472,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047204509839616604,
|
|
"loss": 6.4525,
|
|
"mean_token_accuracy": 0.1224810004234314,
|
|
"num_tokens": 34234528.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 6.623500537872315,
|
|
"epoch": 1.6939911177698113,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004720266382436355,
|
|
"loss": 6.2642,
|
|
"mean_token_accuracy": 0.1318439446389675,
|
|
"num_tokens": 34246203.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 6.623016738891602,
|
|
"epoch": 1.694526191877575,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00047200817240198846,
|
|
"loss": 6.269,
|
|
"mean_token_accuracy": 0.13091511502861977,
|
|
"num_tokens": 34257231.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 6.615456914901733,
|
|
"epoch": 1.695061265985339,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00047198970087175817,
|
|
"loss": 6.29,
|
|
"mean_token_accuracy": 0.13009563833475113,
|
|
"num_tokens": 34268900.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 6.643181371688843,
|
|
"epoch": 1.695596340093103,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004719712236534779,
|
|
"loss": 6.3813,
|
|
"mean_token_accuracy": 0.1250915087759495,
|
|
"num_tokens": 34279343.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 6.653273200988769,
|
|
"epoch": 1.6961314142008668,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004719527407476812,
|
|
"loss": 6.3153,
|
|
"mean_token_accuracy": 0.13341137617826462,
|
|
"num_tokens": 34291952.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 6.641414642333984,
|
|
"epoch": 1.6966664883086309,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00047193425215490186,
|
|
"loss": 6.3348,
|
|
"mean_token_accuracy": 0.12323536872863769,
|
|
"num_tokens": 34302516.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 6.611573028564453,
|
|
"epoch": 1.6972015624163945,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.00047191575787567373,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.13148811608552932,
|
|
"num_tokens": 34313094.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 6.650350570678711,
|
|
"epoch": 1.6977366365241586,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004718972579105306,
|
|
"loss": 6.4024,
|
|
"mean_token_accuracy": 0.12756735160946847,
|
|
"num_tokens": 34324803.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 6.607530546188355,
|
|
"epoch": 1.6982717106319225,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004718787522600069,
|
|
"loss": 6.3517,
|
|
"mean_token_accuracy": 0.12115450650453567,
|
|
"num_tokens": 34336386.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 6.632864379882813,
|
|
"epoch": 1.6988067847396864,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004718602409246369,
|
|
"loss": 6.357,
|
|
"mean_token_accuracy": 0.1266083911061287,
|
|
"num_tokens": 34347085.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 6.619017648696899,
|
|
"epoch": 1.6993418588474505,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00047184172390495505,
|
|
"loss": 6.2834,
|
|
"mean_token_accuracy": 0.13709528222680092,
|
|
"num_tokens": 34358146.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 6.624742317199707,
|
|
"epoch": 1.6998769329552141,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004718232012014961,
|
|
"loss": 6.3241,
|
|
"mean_token_accuracy": 0.1306489624083042,
|
|
"num_tokens": 34370403.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 6.620585155487061,
|
|
"epoch": 1.7004120070629782,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00047180467281479496,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.1309751771390438,
|
|
"num_tokens": 34381130.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 6.583881473541259,
|
|
"epoch": 1.7009470811707421,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004717861387453865,
|
|
"loss": 6.3534,
|
|
"mean_token_accuracy": 0.1292177639901638,
|
|
"num_tokens": 34391610.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 6.611362171173096,
|
|
"epoch": 1.701482155278506,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004717675989938059,
|
|
"loss": 6.3207,
|
|
"mean_token_accuracy": 0.1319234013557434,
|
|
"num_tokens": 34402262.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 6.611799716949463,
|
|
"epoch": 1.70201722938627,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047174905356058857,
|
|
"loss": 6.3419,
|
|
"mean_token_accuracy": 0.1307123251259327,
|
|
"num_tokens": 34412707.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 6.606465291976929,
|
|
"epoch": 1.702552303494034,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.00047173050244626993,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.13719049021601676,
|
|
"num_tokens": 34423203.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 6.602627277374268,
|
|
"epoch": 1.7030873776017978,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004717119456513857,
|
|
"loss": 6.3425,
|
|
"mean_token_accuracy": 0.12976966202259063,
|
|
"num_tokens": 34433279.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 6.598700332641601,
|
|
"epoch": 1.7036224517095617,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047169338317647164,
|
|
"loss": 6.3912,
|
|
"mean_token_accuracy": 0.1284857951104641,
|
|
"num_tokens": 34444601.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 6.658487844467163,
|
|
"epoch": 1.7041575258173256,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047167481502206383,
|
|
"loss": 6.328,
|
|
"mean_token_accuracy": 0.13193465769290924,
|
|
"num_tokens": 34455103.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 6.580682754516602,
|
|
"epoch": 1.7046925999250897,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047165624118869834,
|
|
"loss": 6.3537,
|
|
"mean_token_accuracy": 0.12659695595502854,
|
|
"num_tokens": 34465835.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 6.678673124313354,
|
|
"epoch": 1.7052276740328536,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004716376616769115,
|
|
"loss": 6.3759,
|
|
"mean_token_accuracy": 0.129863403737545,
|
|
"num_tokens": 34476602.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 6.672983264923095,
|
|
"epoch": 1.7057627481406175,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004716190764872399,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.13224006816744804,
|
|
"num_tokens": 34488026.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 6.631501626968384,
|
|
"epoch": 1.7062978222483816,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047160048562022006,
|
|
"loss": 6.3704,
|
|
"mean_token_accuracy": 0.13688023015856743,
|
|
"num_tokens": 34497837.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 6.566190099716186,
|
|
"epoch": 1.7068328963561452,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004715818890763888,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.13337550982832908,
|
|
"num_tokens": 34507727.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 6.619547319412232,
|
|
"epoch": 1.7073679704639093,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047156328685628307,
|
|
"loss": 6.2918,
|
|
"mean_token_accuracy": 0.1299712784588337,
|
|
"num_tokens": 34518595.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 6.578174686431884,
|
|
"epoch": 1.7079030445716732,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004715446789604401,
|
|
"loss": 6.2444,
|
|
"mean_token_accuracy": 0.13805535882711412,
|
|
"num_tokens": 34529415.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 6.625114059448242,
|
|
"epoch": 1.708438118679437,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004715260653893972,
|
|
"loss": 6.2756,
|
|
"mean_token_accuracy": 0.14068608582019806,
|
|
"num_tokens": 34539593.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 6.6397308826446535,
|
|
"epoch": 1.7089731927872012,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004715074461436917,
|
|
"loss": 6.3215,
|
|
"mean_token_accuracy": 0.1266191601753235,
|
|
"num_tokens": 34549441.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 6.629886245727539,
|
|
"epoch": 1.7095082668949648,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047148882122386126,
|
|
"loss": 6.2483,
|
|
"mean_token_accuracy": 0.13213597759604453,
|
|
"num_tokens": 34560211.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 6.6736321449279785,
|
|
"epoch": 1.710043341002729,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047147019063044387,
|
|
"loss": 6.3635,
|
|
"mean_token_accuracy": 0.12661591917276382,
|
|
"num_tokens": 34570479.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 6.651476621627808,
|
|
"epoch": 1.7105784151104928,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00047145155436397726,
|
|
"loss": 6.359,
|
|
"mean_token_accuracy": 0.13111006766557692,
|
|
"num_tokens": 34581382.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 6.574719190597534,
|
|
"epoch": 1.7111134892182567,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004714329124249996,
|
|
"loss": 6.2739,
|
|
"mean_token_accuracy": 0.1396162748336792,
|
|
"num_tokens": 34592131.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 6.624205017089844,
|
|
"epoch": 1.7116485633260208,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004714142648140492,
|
|
"loss": 6.3696,
|
|
"mean_token_accuracy": 0.13238141685724258,
|
|
"num_tokens": 34604407.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 6.596266269683838,
|
|
"epoch": 1.7121836374337844,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004713956115316645,
|
|
"loss": 6.238,
|
|
"mean_token_accuracy": 0.129188697040081,
|
|
"num_tokens": 34614842.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 6.550742769241333,
|
|
"epoch": 1.7127187115415485,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004713769525783841,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.1379176914691925,
|
|
"num_tokens": 34625991.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 6.60060682296753,
|
|
"epoch": 1.7132537856493124,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004713582879547469,
|
|
"loss": 6.3742,
|
|
"mean_token_accuracy": 0.13335420265793801,
|
|
"num_tokens": 34637317.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 6.659848642349243,
|
|
"epoch": 1.7137888597570763,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004713396176612916,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.12434218674898148,
|
|
"num_tokens": 34648282.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 6.647034311294556,
|
|
"epoch": 1.7143239338648404,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004713209416985575,
|
|
"loss": 6.307,
|
|
"mean_token_accuracy": 0.1285879209637642,
|
|
"num_tokens": 34658638.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 6.58911018371582,
|
|
"epoch": 1.714859007972604,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00047130226006708375,
|
|
"loss": 6.3392,
|
|
"mean_token_accuracy": 0.127749053388834,
|
|
"num_tokens": 34669308.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 6.5781384944915775,
|
|
"epoch": 1.7153940820803681,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00047128357276740986,
|
|
"loss": 6.3167,
|
|
"mean_token_accuracy": 0.12773392498493194,
|
|
"num_tokens": 34679513.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 6.654141902923584,
|
|
"epoch": 1.715929156188132,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004712648798000754,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.13225141167640686,
|
|
"num_tokens": 34690736.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 6.660310983657837,
|
|
"epoch": 1.716464230295896,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047124618116562003,
|
|
"loss": 6.3125,
|
|
"mean_token_accuracy": 0.13196858987212182,
|
|
"num_tokens": 34701272.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 6.5591541767120365,
|
|
"epoch": 1.71699930440366,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004712274768645839,
|
|
"loss": 6.2451,
|
|
"mean_token_accuracy": 0.13934627473354338,
|
|
"num_tokens": 34712486.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 6.624559450149536,
|
|
"epoch": 1.7175343785114239,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00047120876689750685,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.1335703045129776,
|
|
"num_tokens": 34721979.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 6.564228582382202,
|
|
"epoch": 1.7180694526191878,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004711900512649292,
|
|
"loss": 6.3022,
|
|
"mean_token_accuracy": 0.134153850376606,
|
|
"num_tokens": 34733496.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 6.644364356994629,
|
|
"epoch": 1.7186045267269516,
|
|
"grad_norm": 15.25,
|
|
"learning_rate": 0.0004711713299673914,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.13654060885310174,
|
|
"num_tokens": 34744223.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 6.654580879211426,
|
|
"epoch": 1.7191396008347155,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047115260300543407,
|
|
"loss": 6.3914,
|
|
"mean_token_accuracy": 0.12722784131765366,
|
|
"num_tokens": 34754931.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 6.594193696975708,
|
|
"epoch": 1.7196746749424796,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004711338703795978,
|
|
"loss": 6.226,
|
|
"mean_token_accuracy": 0.13471216559410096,
|
|
"num_tokens": 34766285.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 6.610436344146729,
|
|
"epoch": 1.7202097490502435,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004711151320904237,
|
|
"loss": 6.3167,
|
|
"mean_token_accuracy": 0.13399520069360732,
|
|
"num_tokens": 34776979.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 6.663286113739014,
|
|
"epoch": 1.7207448231580074,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004710963881384527,
|
|
"loss": 6.4084,
|
|
"mean_token_accuracy": 0.1243788629770279,
|
|
"num_tokens": 34787466.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 6.702347707748413,
|
|
"epoch": 1.7212798972657715,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000471077638524226,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.13149091154336928,
|
|
"num_tokens": 34797664.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 6.603410053253174,
|
|
"epoch": 1.7218149713735351,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.00047105888324828506,
|
|
"loss": 6.2707,
|
|
"mean_token_accuracy": 0.1454118326306343,
|
|
"num_tokens": 34809082.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 6.630747318267822,
|
|
"epoch": 1.7223500454812992,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00047104012231117143,
|
|
"loss": 6.3126,
|
|
"mean_token_accuracy": 0.1354602113366127,
|
|
"num_tokens": 34820223.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 6.495922565460205,
|
|
"epoch": 1.722885119589063,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047102135571342683,
|
|
"loss": 6.2185,
|
|
"mean_token_accuracy": 0.13407095074653624,
|
|
"num_tokens": 34830428.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 6.55476188659668,
|
|
"epoch": 1.723420193696827,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00047100258345559307,
|
|
"loss": 6.3677,
|
|
"mean_token_accuracy": 0.12560501992702483,
|
|
"num_tokens": 34842787.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 6.638940238952637,
|
|
"epoch": 1.723955267804591,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004709838055382123,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.1272047095000744,
|
|
"num_tokens": 34854323.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 6.5924476146697994,
|
|
"epoch": 1.7244903419123547,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004709650219618266,
|
|
"loss": 6.268,
|
|
"mean_token_accuracy": 0.13460715487599373,
|
|
"num_tokens": 34865279.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 6.597858572006226,
|
|
"epoch": 1.7250254160201188,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004709462327269785,
|
|
"loss": 6.286,
|
|
"mean_token_accuracy": 0.13176569864153861,
|
|
"num_tokens": 34875951.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 6.580719614028931,
|
|
"epoch": 1.7255604901278827,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004709274378342105,
|
|
"loss": 6.3067,
|
|
"mean_token_accuracy": 0.137729399651289,
|
|
"num_tokens": 34885815.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 6.581804275512695,
|
|
"epoch": 1.7260955642356466,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047090863728406517,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.12767457589507103,
|
|
"num_tokens": 34897158.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 6.632544279098511,
|
|
"epoch": 1.7266306383434107,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004708898310770856,
|
|
"loss": 6.3505,
|
|
"mean_token_accuracy": 0.13180675208568574,
|
|
"num_tokens": 34907815.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 6.61566801071167,
|
|
"epoch": 1.7271657124511743,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004708710192138146,
|
|
"loss": 6.3099,
|
|
"mean_token_accuracy": 0.13764499500393867,
|
|
"num_tokens": 34918820.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 6.655914688110352,
|
|
"epoch": 1.7277007865589384,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004708522016947954,
|
|
"loss": 6.3724,
|
|
"mean_token_accuracy": 0.13163803815841674,
|
|
"num_tokens": 34929998.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 6.585067224502564,
|
|
"epoch": 1.7282358606667023,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004708333785205715,
|
|
"loss": 6.2847,
|
|
"mean_token_accuracy": 0.14070848226547242,
|
|
"num_tokens": 34940989.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 6.660203456878662,
|
|
"epoch": 1.7287709347744662,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004708145496916862,
|
|
"loss": 6.3214,
|
|
"mean_token_accuracy": 0.13103776723146437,
|
|
"num_tokens": 34952433.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 6.690386152267456,
|
|
"epoch": 1.7293060088822303,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00047079571520868344,
|
|
"loss": 6.351,
|
|
"mean_token_accuracy": 0.12799755558371545,
|
|
"num_tokens": 34963074.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 6.616890954971313,
|
|
"epoch": 1.729841082989994,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00047077687507210674,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.13581970557570458,
|
|
"num_tokens": 34974315.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 6.580818748474121,
|
|
"epoch": 1.730376157097758,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004707580292825004,
|
|
"loss": 6.2443,
|
|
"mean_token_accuracy": 0.14814614802598952,
|
|
"num_tokens": 34985059.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 6.59804949760437,
|
|
"epoch": 1.730911231205522,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004707391778404085,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.12103285118937493,
|
|
"num_tokens": 34996156.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 6.640845489501953,
|
|
"epoch": 1.7314463053132858,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004707203207463752,
|
|
"loss": 6.3215,
|
|
"mean_token_accuracy": 0.13638050705194474,
|
|
"num_tokens": 35007410.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 6.649735450744629,
|
|
"epoch": 1.73198137942105,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004707014580009453,
|
|
"loss": 6.2993,
|
|
"mean_token_accuracy": 0.13719501122832298,
|
|
"num_tokens": 35018492.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 6.630956029891967,
|
|
"epoch": 1.7325164535288138,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004706825896046632,
|
|
"loss": 6.345,
|
|
"mean_token_accuracy": 0.13211160004138947,
|
|
"num_tokens": 35029923.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 6.579127073287964,
|
|
"epoch": 1.7330515276365777,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047066371555807386,
|
|
"loss": 6.2845,
|
|
"mean_token_accuracy": 0.13117245882749556,
|
|
"num_tokens": 35040370.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 6.61843900680542,
|
|
"epoch": 1.7335866017443415,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004706448358617222,
|
|
"loss": 6.3412,
|
|
"mean_token_accuracy": 0.1296013116836548,
|
|
"num_tokens": 35051414.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 6.7188023090362545,
|
|
"epoch": 1.7341216758521054,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047062595051615343,
|
|
"loss": 6.2802,
|
|
"mean_token_accuracy": 0.13661740198731423,
|
|
"num_tokens": 35061015.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 6.643433427810669,
|
|
"epoch": 1.7346567499598695,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004706070595219128,
|
|
"loss": 6.3614,
|
|
"mean_token_accuracy": 0.1311680093407631,
|
|
"num_tokens": 35071757.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 6.5616559982299805,
|
|
"epoch": 1.7351918240676334,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047058816287954587,
|
|
"loss": 6.3401,
|
|
"mean_token_accuracy": 0.13369180783629417,
|
|
"num_tokens": 35082912.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 6.620582866668701,
|
|
"epoch": 1.7357268981753973,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00047056926058959813,
|
|
"loss": 6.3022,
|
|
"mean_token_accuracy": 0.141063379496336,
|
|
"num_tokens": 35094103.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 6.613072681427002,
|
|
"epoch": 1.7362619722831614,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004705503526526155,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.1402138851583004,
|
|
"num_tokens": 35105960.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 6.5840822696685795,
|
|
"epoch": 1.736797046390925,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047053143906914405,
|
|
"loss": 6.2783,
|
|
"mean_token_accuracy": 0.14029459282755852,
|
|
"num_tokens": 35116482.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 6.641913890838623,
|
|
"epoch": 1.7373321204986891,
|
|
"grad_norm": 6.71875,
|
|
"learning_rate": 0.00047051251983972966,
|
|
"loss": 6.3551,
|
|
"mean_token_accuracy": 0.1294461227953434,
|
|
"num_tokens": 35127976.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 6.631348466873169,
|
|
"epoch": 1.737867194606453,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004704935949649187,
|
|
"loss": 6.3678,
|
|
"mean_token_accuracy": 0.13159794807434083,
|
|
"num_tokens": 35137712.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 6.55814003944397,
|
|
"epoch": 1.7384022687142169,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004704746644452577,
|
|
"loss": 6.2464,
|
|
"mean_token_accuracy": 0.13908153250813485,
|
|
"num_tokens": 35148524.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 6.628344964981079,
|
|
"epoch": 1.738937342821981,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00047045572828129323,
|
|
"loss": 6.3429,
|
|
"mean_token_accuracy": 0.13093504682183266,
|
|
"num_tokens": 35159080.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 6.515056419372558,
|
|
"epoch": 1.7394724169297446,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000470436786473572,
|
|
"loss": 6.2248,
|
|
"mean_token_accuracy": 0.13515454828739165,
|
|
"num_tokens": 35169993.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 6.594348382949829,
|
|
"epoch": 1.7400074910375087,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004704178390226411,
|
|
"loss": 6.273,
|
|
"mean_token_accuracy": 0.13104352727532387,
|
|
"num_tokens": 35181413.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 6.590282011032104,
|
|
"epoch": 1.7405425651452726,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047039888592904753,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.13633189499378204,
|
|
"num_tokens": 35191600.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 6.596925830841064,
|
|
"epoch": 1.7410776392530365,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047037992719333864,
|
|
"loss": 6.2978,
|
|
"mean_token_accuracy": 0.12924458235502242,
|
|
"num_tokens": 35202535.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 6.601422643661499,
|
|
"epoch": 1.7416127133608006,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047036096281606176,
|
|
"loss": 6.2992,
|
|
"mean_token_accuracy": 0.13108343929052352,
|
|
"num_tokens": 35214798.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 6.591292810440064,
|
|
"epoch": 1.7421477874685642,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047034199279776456,
|
|
"loss": 6.2738,
|
|
"mean_token_accuracy": 0.13685359433293343,
|
|
"num_tokens": 35224870.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 6.621234607696533,
|
|
"epoch": 1.7426828615763283,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004703230171389948,
|
|
"loss": 6.2732,
|
|
"mean_token_accuracy": 0.13399977684020997,
|
|
"num_tokens": 35235408.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 6.555628871917724,
|
|
"epoch": 1.7432179356840922,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047030403584030024,
|
|
"loss": 6.3017,
|
|
"mean_token_accuracy": 0.13622151389718057,
|
|
"num_tokens": 35246310.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 6.593136310577393,
|
|
"epoch": 1.743753009791856,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004702850489022292,
|
|
"loss": 6.3233,
|
|
"mean_token_accuracy": 0.13240843489766121,
|
|
"num_tokens": 35257027.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 6.689269924163819,
|
|
"epoch": 1.7442880838996202,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047026605632532976,
|
|
"loss": 6.3089,
|
|
"mean_token_accuracy": 0.13237227126955986,
|
|
"num_tokens": 35267397.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 6.610038328170776,
|
|
"epoch": 1.7448231580073839,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.00047024705811015045,
|
|
"loss": 6.2412,
|
|
"mean_token_accuracy": 0.136200849711895,
|
|
"num_tokens": 35278775.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 6.577280569076538,
|
|
"epoch": 1.745358232115148,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004702280542572397,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.14345884546637536,
|
|
"num_tokens": 35288818.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 6.582151079177857,
|
|
"epoch": 1.7458933062229118,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004702090447671464,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.12940049692988395,
|
|
"num_tokens": 35299385.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 6.637843465805053,
|
|
"epoch": 1.7464283803306757,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004701900296404193,
|
|
"loss": 6.2633,
|
|
"mean_token_accuracy": 0.14055221304297447,
|
|
"num_tokens": 35310626.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 6.654524040222168,
|
|
"epoch": 1.7469634544384398,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004701710088776075,
|
|
"loss": 6.3541,
|
|
"mean_token_accuracy": 0.1261627681553364,
|
|
"num_tokens": 35321615.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 6.6335982322692875,
|
|
"epoch": 1.7474985285462037,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047015198247926025,
|
|
"loss": 6.367,
|
|
"mean_token_accuracy": 0.13256216272711754,
|
|
"num_tokens": 35332012.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 6.645944356918335,
|
|
"epoch": 1.7480336026539676,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000470132950445927,
|
|
"loss": 6.3711,
|
|
"mean_token_accuracy": 0.1241213247179985,
|
|
"num_tokens": 35342153.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 6.65523509979248,
|
|
"epoch": 1.7485686767617317,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004701139127781571,
|
|
"loss": 6.3055,
|
|
"mean_token_accuracy": 0.13350063115358352,
|
|
"num_tokens": 35352858.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 6.634918880462647,
|
|
"epoch": 1.7491037508694953,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004700948694765005,
|
|
"loss": 6.2367,
|
|
"mean_token_accuracy": 0.138949416577816,
|
|
"num_tokens": 35363489.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 6.629547452926635,
|
|
"epoch": 1.7496388249772594,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004700758205415069,
|
|
"loss": 6.4216,
|
|
"mean_token_accuracy": 0.12814826890826225,
|
|
"num_tokens": 35375816.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 6.636178684234619,
|
|
"epoch": 1.7501738990850233,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047005676597372645,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.12719852849841118,
|
|
"num_tokens": 35386708.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 6.644186019897461,
|
|
"epoch": 1.7507089731927872,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00047003770577370925,
|
|
"loss": 6.3681,
|
|
"mean_token_accuracy": 0.12734269797801973,
|
|
"num_tokens": 35397734.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 6.720634269714355,
|
|
"epoch": 1.7512440473005513,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00047001863994200574,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.13564276322722435,
|
|
"num_tokens": 35408870.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 6.580907869338989,
|
|
"epoch": 1.751779121408315,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004699995684791664,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.13107749074697495,
|
|
"num_tokens": 35419498.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 6.524800825119018,
|
|
"epoch": 1.752314195516079,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00046998049138574177,
|
|
"loss": 6.2721,
|
|
"mean_token_accuracy": 0.13551856130361556,
|
|
"num_tokens": 35430690.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 6.544882154464721,
|
|
"epoch": 1.752849269623843,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000469961408662283,
|
|
"loss": 6.2322,
|
|
"mean_token_accuracy": 0.14030840247869492,
|
|
"num_tokens": 35441007.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 6.604276037216186,
|
|
"epoch": 1.7533843437316068,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.000469942320309341,
|
|
"loss": 6.2996,
|
|
"mean_token_accuracy": 0.1404838003218174,
|
|
"num_tokens": 35453202.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 6.589113855361939,
|
|
"epoch": 1.7539194178393709,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046992322632746677,
|
|
"loss": 6.2978,
|
|
"mean_token_accuracy": 0.1385349527001381,
|
|
"num_tokens": 35463303.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 6.625360536575317,
|
|
"epoch": 1.7544544919471345,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.00046990412671721186,
|
|
"loss": 6.3079,
|
|
"mean_token_accuracy": 0.13750702142715454,
|
|
"num_tokens": 35474104.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 6.60996036529541,
|
|
"epoch": 1.7549895660548986,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004698850214791276,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.1309199295938015,
|
|
"num_tokens": 35486412.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 6.562714862823486,
|
|
"epoch": 1.7555246401626625,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004698659106137658,
|
|
"loss": 6.3103,
|
|
"mean_token_accuracy": 0.13035363256931304,
|
|
"num_tokens": 35497505.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 6.665454387664795,
|
|
"epoch": 1.7560597142704264,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004698467941216782,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.13559577092528344,
|
|
"num_tokens": 35508397.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 6.6934761047363285,
|
|
"epoch": 1.7565947883781905,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00046982767200341675,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.12500149458646775,
|
|
"num_tokens": 35520261.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 6.644599962234497,
|
|
"epoch": 1.7571298624859542,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00046980854425953365,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.12976839914917945,
|
|
"num_tokens": 35531816.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 6.6425474166870115,
|
|
"epoch": 1.7576649365937183,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004697894108905813,
|
|
"loss": 6.3509,
|
|
"mean_token_accuracy": 0.12998742535710334,
|
|
"num_tokens": 35542233.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 6.614479112625122,
|
|
"epoch": 1.7582000107014821,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00046977027189711197,
|
|
"loss": 6.2911,
|
|
"mean_token_accuracy": 0.13618450984358788,
|
|
"num_tokens": 35552881.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 6.612358522415161,
|
|
"epoch": 1.758735084809246,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004697511272796785,
|
|
"loss": 6.2511,
|
|
"mean_token_accuracy": 0.13425956815481185,
|
|
"num_tokens": 35562392.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 6.618925285339356,
|
|
"epoch": 1.75927015891701,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004697319770388335,
|
|
"loss": 6.3262,
|
|
"mean_token_accuracy": 0.1242551252245903,
|
|
"num_tokens": 35574587.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 6.585968255996704,
|
|
"epoch": 1.759805233024774,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004697128211751301,
|
|
"loss": 6.1986,
|
|
"mean_token_accuracy": 0.13545156866312028,
|
|
"num_tokens": 35585178.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 6.546419286727906,
|
|
"epoch": 1.7603403071325379,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004696936596891213,
|
|
"loss": 6.2681,
|
|
"mean_token_accuracy": 0.1320943646132946,
|
|
"num_tokens": 35595501.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 6.600337076187134,
|
|
"epoch": 1.7608753812403017,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004696744925813605,
|
|
"loss": 6.2882,
|
|
"mean_token_accuracy": 0.12996454536914825,
|
|
"num_tokens": 35606794.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 6.627634525299072,
|
|
"epoch": 1.7614104553480656,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004696553198524011,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.13083907440304757,
|
|
"num_tokens": 35618732.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 6.615886974334717,
|
|
"epoch": 1.7619455294558297,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004696361415027966,
|
|
"loss": 6.2468,
|
|
"mean_token_accuracy": 0.13505003079771996,
|
|
"num_tokens": 35629802.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 6.6018777847290036,
|
|
"epoch": 1.7624806035635936,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004696169575331009,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.12601472139358522,
|
|
"num_tokens": 35640826.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 6.6303651332855225,
|
|
"epoch": 1.7630156776713575,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000469597767943868,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.13192034363746644,
|
|
"num_tokens": 35651613.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 6.624626731872558,
|
|
"epoch": 1.7635507517791216,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004695785727356517,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.13552088737487794,
|
|
"num_tokens": 35662334.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 6.657793188095093,
|
|
"epoch": 1.7640858258868852,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004695593719090066,
|
|
"loss": 6.3476,
|
|
"mean_token_accuracy": 0.12990945652127267,
|
|
"num_tokens": 35673466.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 6.583916568756104,
|
|
"epoch": 1.7646208999946493,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004695401654644869,
|
|
"loss": 6.3076,
|
|
"mean_token_accuracy": 0.13364871814846993,
|
|
"num_tokens": 35684708.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 6.533912324905396,
|
|
"epoch": 1.7651559741024132,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00046952095340264727,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.1350885309278965,
|
|
"num_tokens": 35694888.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 6.66177978515625,
|
|
"epoch": 1.765691048210177,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00046950173572404255,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.13110286891460418,
|
|
"num_tokens": 35704844.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 6.629522085189819,
|
|
"epoch": 1.7662261223179412,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004694825124292275,
|
|
"loss": 6.3334,
|
|
"mean_token_accuracy": 0.1319143742322922,
|
|
"num_tokens": 35715468.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 6.569692325592041,
|
|
"epoch": 1.7667611964257048,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004694632835187572,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.13306174874305726,
|
|
"num_tokens": 35725542.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 6.599575996398926,
|
|
"epoch": 1.767296270533469,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.00046944404899318685,
|
|
"loss": 6.2585,
|
|
"mean_token_accuracy": 0.13644295260310174,
|
|
"num_tokens": 35737032.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 6.664855861663819,
|
|
"epoch": 1.7678313446412328,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000469424808853072,
|
|
"loss": 6.2822,
|
|
"mean_token_accuracy": 0.1355866640806198,
|
|
"num_tokens": 35747742.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 6.586109590530396,
|
|
"epoch": 1.7683664187489967,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004694055630989681,
|
|
"loss": 6.2647,
|
|
"mean_token_accuracy": 0.13411461114883422,
|
|
"num_tokens": 35757795.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 6.5574501037597654,
|
|
"epoch": 1.7689014928567608,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004693863117314308,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.14302469938993453,
|
|
"num_tokens": 35767962.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 6.577033233642578,
|
|
"epoch": 1.7694365669645244,
|
|
"grad_norm": 5.71875,
|
|
"learning_rate": 0.0004693670547510161,
|
|
"loss": 6.3686,
|
|
"mean_token_accuracy": 0.12652606293559074,
|
|
"num_tokens": 35778564.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 6.672263336181641,
|
|
"epoch": 1.7699716410722885,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00046934779215828006,
|
|
"loss": 6.2802,
|
|
"mean_token_accuracy": 0.13933001458644867,
|
|
"num_tokens": 35788417.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 6.606206703186035,
|
|
"epoch": 1.7705067151800524,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004693285239537788,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.1313735492527485,
|
|
"num_tokens": 35799724.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 6.642638397216797,
|
|
"epoch": 1.7710417892878163,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00046930925013806873,
|
|
"loss": 6.2535,
|
|
"mean_token_accuracy": 0.13537903055548667,
|
|
"num_tokens": 35810306.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 6.650364398956299,
|
|
"epoch": 1.7715768633955804,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004692899707117064,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.1335926964879036,
|
|
"num_tokens": 35821103.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 6.584615850448609,
|
|
"epoch": 1.772111937503344,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004692706856752484,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.13890458792448043,
|
|
"num_tokens": 35832271.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 6.5764007568359375,
|
|
"epoch": 1.7726470116111082,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00046925139502925167,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.13056388571858407,
|
|
"num_tokens": 35843875.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 6.6337854862213135,
|
|
"epoch": 1.773182085718872,
|
|
"grad_norm": 3.890625,
|
|
"learning_rate": 0.0004692320987742732,
|
|
"loss": 6.3281,
|
|
"mean_token_accuracy": 0.13335452377796173,
|
|
"num_tokens": 35854085.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 6.721234703063965,
|
|
"epoch": 1.773717159826636,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004692127969108702,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.1313113674521446,
|
|
"num_tokens": 35864777.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 6.655748462677002,
|
|
"epoch": 1.7742522339344,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004691934894396,
|
|
"loss": 6.3551,
|
|
"mean_token_accuracy": 0.12990280613303185,
|
|
"num_tokens": 35876822.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 6.639148426055908,
|
|
"epoch": 1.774787308042164,
|
|
"grad_norm": 4.75,
|
|
"learning_rate": 0.00046917417636102,
|
|
"loss": 6.2779,
|
|
"mean_token_accuracy": 0.13540241941809655,
|
|
"num_tokens": 35886997.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 6.622691535949707,
|
|
"epoch": 1.7753223821499278,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000469154857675688,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.13177612349390982,
|
|
"num_tokens": 35897871.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 6.577442455291748,
|
|
"epoch": 1.7758574562576916,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004691355333841617,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.1441633000969887,
|
|
"num_tokens": 35908791.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 6.64111442565918,
|
|
"epoch": 1.7763925303654555,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004691162034869993,
|
|
"loss": 6.357,
|
|
"mean_token_accuracy": 0.13071720078587531,
|
|
"num_tokens": 35919436.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 6.688005352020264,
|
|
"epoch": 1.7769276044732196,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004690968679847586,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.13329437375068665,
|
|
"num_tokens": 35929851.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 6.637648582458496,
|
|
"epoch": 1.7774626785809835,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004690775268779983,
|
|
"loss": 6.285,
|
|
"mean_token_accuracy": 0.1351489692926407,
|
|
"num_tokens": 35940271.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 6.587462043762207,
|
|
"epoch": 1.7779977526887474,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004690581801672765,
|
|
"loss": 6.3897,
|
|
"mean_token_accuracy": 0.1269778937101364,
|
|
"num_tokens": 35951460.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 6.563213443756103,
|
|
"epoch": 1.7785328267965115,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00046903882785315215,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.13399467915296553,
|
|
"num_tokens": 35961530.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 6.591010856628418,
|
|
"epoch": 1.7790679009042751,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004690194699361839,
|
|
"loss": 6.2432,
|
|
"mean_token_accuracy": 0.14185749143362045,
|
|
"num_tokens": 35971085.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 6.604857349395752,
|
|
"epoch": 1.7796029750120392,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.00046900010641693073,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.12479043304920197,
|
|
"num_tokens": 35981393.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 6.63058066368103,
|
|
"epoch": 1.7801380491198031,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004689807372959517,
|
|
"loss": 6.2787,
|
|
"mean_token_accuracy": 0.13293046578764917,
|
|
"num_tokens": 35992847.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 6.564885044097901,
|
|
"epoch": 1.780673123227567,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00046896136257380615,
|
|
"loss": 6.3168,
|
|
"mean_token_accuracy": 0.132865971326828,
|
|
"num_tokens": 36002991.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 6.56801700592041,
|
|
"epoch": 1.781208197335331,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00046894198225105356,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.13603267967700958,
|
|
"num_tokens": 36015140.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 6.568941593170166,
|
|
"epoch": 1.7817432714430947,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004689225963282534,
|
|
"loss": 6.2142,
|
|
"mean_token_accuracy": 0.1376933515071869,
|
|
"num_tokens": 36026014.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 6.661668157577514,
|
|
"epoch": 1.7822783455508588,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004689032048059656,
|
|
"loss": 6.3827,
|
|
"mean_token_accuracy": 0.13067136332392693,
|
|
"num_tokens": 36035926.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 6.608845472335815,
|
|
"epoch": 1.7828134196586227,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00046888380768475,
|
|
"loss": 6.2836,
|
|
"mean_token_accuracy": 0.1349094606935978,
|
|
"num_tokens": 36046406.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 6.587793445587158,
|
|
"epoch": 1.7833484937663866,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004688644049651667,
|
|
"loss": 6.2335,
|
|
"mean_token_accuracy": 0.13360365629196166,
|
|
"num_tokens": 36056440.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 6.604903841018677,
|
|
"epoch": 1.7838835678741507,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00046884499664777586,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.13076087534427644,
|
|
"num_tokens": 36067244.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 6.609608364105225,
|
|
"epoch": 1.7844186419819144,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004688255827331381,
|
|
"loss": 6.2287,
|
|
"mean_token_accuracy": 0.13767247647047043,
|
|
"num_tokens": 36078110.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 6.600276088714599,
|
|
"epoch": 1.7849537160896785,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004688061632218137,
|
|
"loss": 6.3111,
|
|
"mean_token_accuracy": 0.13210405558347701,
|
|
"num_tokens": 36088805.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 6.585881996154785,
|
|
"epoch": 1.7854887901974423,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00046878673811436375,
|
|
"loss": 6.2867,
|
|
"mean_token_accuracy": 0.1401722937822342,
|
|
"num_tokens": 36098619.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 6.668530130386353,
|
|
"epoch": 1.7860238643052062,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004687673074113489,
|
|
"loss": 6.3554,
|
|
"mean_token_accuracy": 0.1354214258491993,
|
|
"num_tokens": 36110604.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 6.717661142349243,
|
|
"epoch": 1.7865589384129703,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004687478711133303,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.13070405200123786,
|
|
"num_tokens": 36121669.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 6.512844133377075,
|
|
"epoch": 1.787094012520734,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004687284292208691,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.14433105066418647,
|
|
"num_tokens": 36132165.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 6.542000246047974,
|
|
"epoch": 1.787629086628498,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00046870898173452676,
|
|
"loss": 6.2867,
|
|
"mean_token_accuracy": 0.13366685509681703,
|
|
"num_tokens": 36142830.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 6.5658944606781,
|
|
"epoch": 1.788164160736262,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004686895286548648,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.1351202718913555,
|
|
"num_tokens": 36153812.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 6.5656684875488285,
|
|
"epoch": 1.7886992348440258,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00046867006998244494,
|
|
"loss": 6.3257,
|
|
"mean_token_accuracy": 0.13076186850667,
|
|
"num_tokens": 36163599.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 6.580621957778931,
|
|
"epoch": 1.78923430895179,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00046865060571782896,
|
|
"loss": 6.3296,
|
|
"mean_token_accuracy": 0.1297022894024849,
|
|
"num_tokens": 36173815.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 6.769290494918823,
|
|
"epoch": 1.7897693830595538,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00046863113586157894,
|
|
"loss": 6.4053,
|
|
"mean_token_accuracy": 0.1256492741405964,
|
|
"num_tokens": 36186131.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 6.633991622924805,
|
|
"epoch": 1.7903044571673177,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004686116604142572,
|
|
"loss": 6.2618,
|
|
"mean_token_accuracy": 0.1349225454032421,
|
|
"num_tokens": 36196084.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 6.543641996383667,
|
|
"epoch": 1.7908395312750816,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004685921793764259,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.13962459713220596,
|
|
"num_tokens": 36206948.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 6.608253479003906,
|
|
"epoch": 1.7913746053828454,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004685726927486476,
|
|
"loss": 6.37,
|
|
"mean_token_accuracy": 0.12911229878664016,
|
|
"num_tokens": 36217202.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 6.686311292648315,
|
|
"epoch": 1.7919096794906095,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046855320053148505,
|
|
"loss": 6.4015,
|
|
"mean_token_accuracy": 0.1246464267373085,
|
|
"num_tokens": 36227914.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 6.715205907821655,
|
|
"epoch": 1.7924447535983734,
|
|
"grad_norm": 8.4375,
|
|
"learning_rate": 0.000468533702725501,
|
|
"loss": 6.3541,
|
|
"mean_token_accuracy": 0.13168523758649825,
|
|
"num_tokens": 36239344.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 6.6749412536621096,
|
|
"epoch": 1.7929798277061373,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00046851419933125843,
|
|
"loss": 6.3766,
|
|
"mean_token_accuracy": 0.13080505803227424,
|
|
"num_tokens": 36250438.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 6.629966354370117,
|
|
"epoch": 1.7935149018139014,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004684946903493206,
|
|
"loss": 6.3271,
|
|
"mean_token_accuracy": 0.12688625156879424,
|
|
"num_tokens": 36260545.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 6.513330602645874,
|
|
"epoch": 1.794049975921665,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004684751757802508,
|
|
"loss": 6.2241,
|
|
"mean_token_accuracy": 0.13600071594119073,
|
|
"num_tokens": 36272577.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 6.584756660461426,
|
|
"epoch": 1.7945850500294291,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046845565562461243,
|
|
"loss": 6.2649,
|
|
"mean_token_accuracy": 0.1377692051231861,
|
|
"num_tokens": 36284161.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 6.607342672348023,
|
|
"epoch": 1.795120124137193,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00046843612988296926,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.12932114228606223,
|
|
"num_tokens": 36294910.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 6.63202748298645,
|
|
"epoch": 1.795655198244957,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004684165985558849,
|
|
"loss": 6.2505,
|
|
"mean_token_accuracy": 0.13275219798088073,
|
|
"num_tokens": 36305388.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 6.619568729400635,
|
|
"epoch": 1.796190272352721,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004683970616439236,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.1427262581884861,
|
|
"num_tokens": 36316696.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 6.568006086349487,
|
|
"epoch": 1.7967253464604847,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004683775191476492,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.1415497839450836,
|
|
"num_tokens": 36327246.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 6.685283041000366,
|
|
"epoch": 1.7972604205682488,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004683579710676262,
|
|
"loss": 6.374,
|
|
"mean_token_accuracy": 0.1248635970056057,
|
|
"num_tokens": 36338089.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 6.606064081192017,
|
|
"epoch": 1.7977954946760126,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00046833841740441886,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.13408589139580726,
|
|
"num_tokens": 36350285.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 6.663595247268677,
|
|
"epoch": 1.7983305687837765,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004683188581585919,
|
|
"loss": 6.307,
|
|
"mean_token_accuracy": 0.13034658655524253,
|
|
"num_tokens": 36360431.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 6.662921953201294,
|
|
"epoch": 1.7988656428915406,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004682992933307101,
|
|
"loss": 6.2694,
|
|
"mean_token_accuracy": 0.13253438025712966,
|
|
"num_tokens": 36371257.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 6.558261060714722,
|
|
"epoch": 1.7994007169993043,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.00046827972292133835,
|
|
"loss": 6.2381,
|
|
"mean_token_accuracy": 0.13622535914182662,
|
|
"num_tokens": 36382613.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 6.64785361289978,
|
|
"epoch": 1.7999357911070684,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004682601469310418,
|
|
"loss": 6.3268,
|
|
"mean_token_accuracy": 0.12922666743397712,
|
|
"num_tokens": 36393799.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 6.594283676147461,
|
|
"epoch": 1.8004708652148322,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00046824056536038565,
|
|
"loss": 6.2947,
|
|
"mean_token_accuracy": 0.13629090785980225,
|
|
"num_tokens": 36403914.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 6.528755378723145,
|
|
"epoch": 1.8010059393225961,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004682209782099353,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.133383172750473,
|
|
"num_tokens": 36415022.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 6.595521259307861,
|
|
"epoch": 1.8015410134303602,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00046820138548025634,
|
|
"loss": 6.2142,
|
|
"mean_token_accuracy": 0.14095254987478256,
|
|
"num_tokens": 36426155.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 6.647051000595093,
|
|
"epoch": 1.8020760875381239,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.00046818178717191464,
|
|
"loss": 6.3062,
|
|
"mean_token_accuracy": 0.13143352866172792,
|
|
"num_tokens": 36437345.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 6.612011909484863,
|
|
"epoch": 1.802611161645888,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004681621832854759,
|
|
"loss": 6.3085,
|
|
"mean_token_accuracy": 0.13487469404935837,
|
|
"num_tokens": 36448634.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 6.573487329483032,
|
|
"epoch": 1.8031462357536518,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00046814257382150627,
|
|
"loss": 6.2626,
|
|
"mean_token_accuracy": 0.14112870171666145,
|
|
"num_tokens": 36458870.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 6.634332942962646,
|
|
"epoch": 1.8036813098614157,
|
|
"grad_norm": 6.75,
|
|
"learning_rate": 0.00046812295878057193,
|
|
"loss": 6.4008,
|
|
"mean_token_accuracy": 0.1273484483361244,
|
|
"num_tokens": 36469865.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 6.598207807540893,
|
|
"epoch": 1.8042163839691798,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004681033381632393,
|
|
"loss": 6.2783,
|
|
"mean_token_accuracy": 0.13211158961057662,
|
|
"num_tokens": 36480502.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 6.649739360809326,
|
|
"epoch": 1.8047514580769437,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004680837119700749,
|
|
"loss": 6.3006,
|
|
"mean_token_accuracy": 0.13394420370459556,
|
|
"num_tokens": 36492356.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 6.537524700164795,
|
|
"epoch": 1.8052865321847076,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.00046806408020164553,
|
|
"loss": 6.2793,
|
|
"mean_token_accuracy": 0.13545331507921218,
|
|
"num_tokens": 36504659.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 6.546615362167358,
|
|
"epoch": 1.8058216062924715,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00046804444285851796,
|
|
"loss": 6.2728,
|
|
"mean_token_accuracy": 0.13199991285800933,
|
|
"num_tokens": 36516042.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 6.649050855636597,
|
|
"epoch": 1.8063566804002353,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.00046802479994125916,
|
|
"loss": 6.3728,
|
|
"mean_token_accuracy": 0.12917319685220718,
|
|
"num_tokens": 36527417.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 6.657395696640014,
|
|
"epoch": 1.8068917545079994,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004680051514504364,
|
|
"loss": 6.3019,
|
|
"mean_token_accuracy": 0.13716157525777817,
|
|
"num_tokens": 36538182.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 6.615043306350708,
|
|
"epoch": 1.8074268286157633,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004679854973866171,
|
|
"loss": 6.3559,
|
|
"mean_token_accuracy": 0.13190600350499154,
|
|
"num_tokens": 36549835.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 6.552302551269531,
|
|
"epoch": 1.8079619027235272,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.00046796583775036857,
|
|
"loss": 6.2873,
|
|
"mean_token_accuracy": 0.14080114141106606,
|
|
"num_tokens": 36560238.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 6.668530988693237,
|
|
"epoch": 1.8084969768312913,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00046794617254225865,
|
|
"loss": 6.2956,
|
|
"mean_token_accuracy": 0.13277275189757348,
|
|
"num_tokens": 36571267.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 6.594847631454468,
|
|
"epoch": 1.809032050939055,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004679265017628551,
|
|
"loss": 6.367,
|
|
"mean_token_accuracy": 0.13326788023114206,
|
|
"num_tokens": 36582174.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 6.632411623001099,
|
|
"epoch": 1.809567125046819,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004679068254127259,
|
|
"loss": 6.3245,
|
|
"mean_token_accuracy": 0.12731056809425353,
|
|
"num_tokens": 36593054.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 6.645024967193604,
|
|
"epoch": 1.810102199154583,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.00046788714349243923,
|
|
"loss": 6.3267,
|
|
"mean_token_accuracy": 0.13425510972738267,
|
|
"num_tokens": 36603962.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 6.704790782928467,
|
|
"epoch": 1.8106372732623468,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004678674560025634,
|
|
"loss": 6.3072,
|
|
"mean_token_accuracy": 0.1331163689494133,
|
|
"num_tokens": 36616003.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 6.6815580368042,
|
|
"epoch": 1.811172347370111,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004678477629436669,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.125041913241148,
|
|
"num_tokens": 36627189.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 6.641905403137207,
|
|
"epoch": 1.8117074214778746,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004678280643163184,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.12457984536886216,
|
|
"num_tokens": 36637756.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 6.579206562042236,
|
|
"epoch": 1.8122424955856387,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004678083601210865,
|
|
"loss": 6.3466,
|
|
"mean_token_accuracy": 0.13508816957473754,
|
|
"num_tokens": 36648946.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 6.67406005859375,
|
|
"epoch": 1.8127775696934025,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004677886503585404,
|
|
"loss": 6.3648,
|
|
"mean_token_accuracy": 0.13107882738113402,
|
|
"num_tokens": 36660184.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 6.705534029006958,
|
|
"epoch": 1.8133126438011664,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00046776893502924904,
|
|
"loss": 6.4133,
|
|
"mean_token_accuracy": 0.12986828610301018,
|
|
"num_tokens": 36671346.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 6.698011684417724,
|
|
"epoch": 1.8138477179089305,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004677492141337818,
|
|
"loss": 6.3059,
|
|
"mean_token_accuracy": 0.13024382218718528,
|
|
"num_tokens": 36682917.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 6.618733072280884,
|
|
"epoch": 1.8143827920166942,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004677294876727081,
|
|
"loss": 6.3597,
|
|
"mean_token_accuracy": 0.12282465919852256,
|
|
"num_tokens": 36693577.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 6.65786828994751,
|
|
"epoch": 1.8149178661244583,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004677097556465975,
|
|
"loss": 6.3368,
|
|
"mean_token_accuracy": 0.13316798210144043,
|
|
"num_tokens": 36704915.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 6.665150547027588,
|
|
"epoch": 1.8154529402322221,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00046769001805601983,
|
|
"loss": 6.4354,
|
|
"mean_token_accuracy": 0.12380209863185883,
|
|
"num_tokens": 36716086.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 6.610789155960083,
|
|
"epoch": 1.815988014339986,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00046767027490154494,
|
|
"loss": 6.2742,
|
|
"mean_token_accuracy": 0.13092861473560333,
|
|
"num_tokens": 36726110.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 6.668860626220703,
|
|
"epoch": 1.8165230884477501,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00046765052618374296,
|
|
"loss": 6.2596,
|
|
"mean_token_accuracy": 0.1359055981040001,
|
|
"num_tokens": 36735846.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 6.623946809768677,
|
|
"epoch": 1.8170581625555138,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000467630771903184,
|
|
"loss": 6.3443,
|
|
"mean_token_accuracy": 0.13512761667370796,
|
|
"num_tokens": 36746851.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 6.646110582351684,
|
|
"epoch": 1.8175932366632779,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004676110120604387,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.13240315094590188,
|
|
"num_tokens": 36758032.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 6.658700895309448,
|
|
"epoch": 1.8181283107710418,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.0004675912466560775,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.13368158414959908,
|
|
"num_tokens": 36768939.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 6.645512533187866,
|
|
"epoch": 1.8186633848788056,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00046757147569067106,
|
|
"loss": 6.3756,
|
|
"mean_token_accuracy": 0.12750740870833396,
|
|
"num_tokens": 36780338.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 6.6122660636901855,
|
|
"epoch": 1.8191984589865697,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004675516991647903,
|
|
"loss": 6.2358,
|
|
"mean_token_accuracy": 0.13005613684654235,
|
|
"num_tokens": 36791384.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 6.590920686721802,
|
|
"epoch": 1.8197335330943336,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00046753191707900636,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.1296996295452118,
|
|
"num_tokens": 36802460.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 6.6155530452728275,
|
|
"epoch": 1.8202686072020975,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00046751212943389026,
|
|
"loss": 6.3712,
|
|
"mean_token_accuracy": 0.1270579494535923,
|
|
"num_tokens": 36813599.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 6.621894121170044,
|
|
"epoch": 1.8208036813098614,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004674923362300135,
|
|
"loss": 6.2596,
|
|
"mean_token_accuracy": 0.13139134123921395,
|
|
"num_tokens": 36823100.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 6.695833158493042,
|
|
"epoch": 1.8213387554176252,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00046747253746794767,
|
|
"loss": 6.3894,
|
|
"mean_token_accuracy": 0.12691818177700043,
|
|
"num_tokens": 36834245.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 6.629623889923096,
|
|
"epoch": 1.8218738295253893,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00046745273314826425,
|
|
"loss": 6.252,
|
|
"mean_token_accuracy": 0.13720860332250595,
|
|
"num_tokens": 36844126.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 6.553670454025268,
|
|
"epoch": 1.8224089036331532,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004674329232715353,
|
|
"loss": 6.2419,
|
|
"mean_token_accuracy": 0.14087960198521615,
|
|
"num_tokens": 36855451.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 6.625223588943482,
|
|
"epoch": 1.822943977740917,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.0004674131078383327,
|
|
"loss": 6.3232,
|
|
"mean_token_accuracy": 0.12838400155305862,
|
|
"num_tokens": 36864994.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 6.6084020137786865,
|
|
"epoch": 1.8234790518486812,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004673932868492286,
|
|
"loss": 6.2873,
|
|
"mean_token_accuracy": 0.1326562114059925,
|
|
"num_tokens": 36875131.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 6.636068868637085,
|
|
"epoch": 1.8240141259564449,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046737346030479546,
|
|
"loss": 6.3502,
|
|
"mean_token_accuracy": 0.12886129468679428,
|
|
"num_tokens": 36884789.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 6.563739871978759,
|
|
"epoch": 1.824549200064209,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.00046735362820560564,
|
|
"loss": 6.2315,
|
|
"mean_token_accuracy": 0.1337413877248764,
|
|
"num_tokens": 36895199.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 6.637328720092773,
|
|
"epoch": 1.8250842741719728,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004673337905522318,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.13146366998553277,
|
|
"num_tokens": 36906495.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 6.585487651824951,
|
|
"epoch": 1.8256193482797367,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046731394734524686,
|
|
"loss": 6.3038,
|
|
"mean_token_accuracy": 0.12943502962589265,
|
|
"num_tokens": 36916907.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 6.54070634841919,
|
|
"epoch": 1.8261544223875008,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00046729409858522363,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.13321856558322906,
|
|
"num_tokens": 36927872.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 6.568526744842529,
|
|
"epoch": 1.8266894964952645,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004672742442727354,
|
|
"loss": 6.3191,
|
|
"mean_token_accuracy": 0.13578804954886436,
|
|
"num_tokens": 36938575.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 6.552577066421509,
|
|
"epoch": 1.8272245706030286,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.00046725438440835536,
|
|
"loss": 6.1837,
|
|
"mean_token_accuracy": 0.14711219295859337,
|
|
"num_tokens": 36949179.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 6.610858535766601,
|
|
"epoch": 1.8277596447107924,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000467234518992657,
|
|
"loss": 6.2451,
|
|
"mean_token_accuracy": 0.13843801394104957,
|
|
"num_tokens": 36959164.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 6.632494115829468,
|
|
"epoch": 1.8282947188185563,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00046721464802621383,
|
|
"loss": 6.3867,
|
|
"mean_token_accuracy": 0.13117994591593743,
|
|
"num_tokens": 36969091.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 6.596967983245849,
|
|
"epoch": 1.8288297929263204,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00046719477150959984,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.13205136954784394,
|
|
"num_tokens": 36980481.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 6.649194431304932,
|
|
"epoch": 1.829364867034084,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00046717488944338873,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.1364925391972065,
|
|
"num_tokens": 36991349.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 6.658361291885376,
|
|
"epoch": 1.8298999411418482,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046715500182815473,
|
|
"loss": 6.3885,
|
|
"mean_token_accuracy": 0.13224469870328903,
|
|
"num_tokens": 37002803.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 6.665770483016968,
|
|
"epoch": 1.830435015249612,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046713510866447204,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.13392111510038376,
|
|
"num_tokens": 37013578.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 6.580105543136597,
|
|
"epoch": 1.830970089357376,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004671152099529152,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.13564569875597954,
|
|
"num_tokens": 37024012.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 6.534465026855469,
|
|
"epoch": 1.83150516346514,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00046709530569405855,
|
|
"loss": 6.2294,
|
|
"mean_token_accuracy": 0.13694893419742585,
|
|
"num_tokens": 37034149.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 6.5556529521942135,
|
|
"epoch": 1.8320402375729037,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004670753958884769,
|
|
"loss": 6.2354,
|
|
"mean_token_accuracy": 0.13454676195979118,
|
|
"num_tokens": 37045669.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 6.623359203338623,
|
|
"epoch": 1.8325753116806678,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00046705548053674524,
|
|
"loss": 6.3271,
|
|
"mean_token_accuracy": 0.13318384066224098,
|
|
"num_tokens": 37056611.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 6.603987693786621,
|
|
"epoch": 1.8331103857884317,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00046703555963943855,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.13181695640087127,
|
|
"num_tokens": 37067387.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 6.692294311523438,
|
|
"epoch": 1.8336454598961955,
|
|
"grad_norm": 8.0625,
|
|
"learning_rate": 0.00046701563319713214,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.12348829060792924,
|
|
"num_tokens": 37078151.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 6.678979969024658,
|
|
"epoch": 1.8341805340039596,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00046699570121040126,
|
|
"loss": 6.3498,
|
|
"mean_token_accuracy": 0.13332833498716354,
|
|
"num_tokens": 37088219.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 6.617359018325805,
|
|
"epoch": 1.8347156081117235,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004669757636798215,
|
|
"loss": 6.2115,
|
|
"mean_token_accuracy": 0.13718561083078384,
|
|
"num_tokens": 37098769.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 6.64462251663208,
|
|
"epoch": 1.8352506822194874,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004669558206059684,
|
|
"loss": 6.3564,
|
|
"mean_token_accuracy": 0.12303334027528763,
|
|
"num_tokens": 37110716.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 6.635640716552734,
|
|
"epoch": 1.8357857563272513,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004669358719894181,
|
|
"loss": 6.2616,
|
|
"mean_token_accuracy": 0.1336287148296833,
|
|
"num_tokens": 37122785.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 6.591304636001587,
|
|
"epoch": 1.8363208304350152,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004669159178307465,
|
|
"loss": 6.2821,
|
|
"mean_token_accuracy": 0.13385289981961251,
|
|
"num_tokens": 37133308.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 6.5352874279022215,
|
|
"epoch": 1.8368559045427792,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004668959581305296,
|
|
"loss": 6.2387,
|
|
"mean_token_accuracy": 0.13802679926156997,
|
|
"num_tokens": 37143916.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 6.63859338760376,
|
|
"epoch": 1.8373909786505431,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046687599288934394,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.13396358042955397,
|
|
"num_tokens": 37154335.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 6.587702941894531,
|
|
"epoch": 1.837926052758307,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000466856022107766,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.1303239643573761,
|
|
"num_tokens": 37164116.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 6.614885330200195,
|
|
"epoch": 1.838461126866071,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00046683604578637235,
|
|
"loss": 6.3644,
|
|
"mean_token_accuracy": 0.13217984288930892,
|
|
"num_tokens": 37175407.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 6.577514028549194,
|
|
"epoch": 1.8389962009738348,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00046681606392573975,
|
|
"loss": 6.2535,
|
|
"mean_token_accuracy": 0.1303245522081852,
|
|
"num_tokens": 37185339.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 6.659743976593018,
|
|
"epoch": 1.8395312750815989,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004667960765264454,
|
|
"loss": 6.3569,
|
|
"mean_token_accuracy": 0.12978954389691352,
|
|
"num_tokens": 37195145.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 6.60614161491394,
|
|
"epoch": 1.8400663491893627,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004667760835890662,
|
|
"loss": 6.3644,
|
|
"mean_token_accuracy": 0.1255668170750141,
|
|
"num_tokens": 37206454.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 6.599306583404541,
|
|
"epoch": 1.8406014232971266,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.00046675608511417957,
|
|
"loss": 6.2659,
|
|
"mean_token_accuracy": 0.1350914493203163,
|
|
"num_tokens": 37216646.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 6.541911697387695,
|
|
"epoch": 1.8411364974048907,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00046673608110236293,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.13526492118835448,
|
|
"num_tokens": 37227368.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 6.624236297607422,
|
|
"epoch": 1.8416715715126544,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004667160715541939,
|
|
"loss": 6.3533,
|
|
"mean_token_accuracy": 0.13322544544935228,
|
|
"num_tokens": 37238150.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 6.6048534393310545,
|
|
"epoch": 1.8422066456204185,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00046669605647025014,
|
|
"loss": 6.311,
|
|
"mean_token_accuracy": 0.13024024292826653,
|
|
"num_tokens": 37249534.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 6.666620063781738,
|
|
"epoch": 1.8427417197281823,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004666760358511098,
|
|
"loss": 6.3874,
|
|
"mean_token_accuracy": 0.134862569719553,
|
|
"num_tokens": 37260633.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 6.675939464569092,
|
|
"epoch": 1.8432767938359462,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00046665600969735086,
|
|
"loss": 6.351,
|
|
"mean_token_accuracy": 0.1244233176112175,
|
|
"num_tokens": 37271978.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 6.567233610153198,
|
|
"epoch": 1.8438118679437103,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004666359780095515,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.13469780310988427,
|
|
"num_tokens": 37284130.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 6.610420036315918,
|
|
"epoch": 1.844346942051474,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004666159407882902,
|
|
"loss": 6.3675,
|
|
"mean_token_accuracy": 0.12647682130336763,
|
|
"num_tokens": 37295648.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 6.627671623229981,
|
|
"epoch": 1.844882016159238,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004665958980341456,
|
|
"loss": 6.3366,
|
|
"mean_token_accuracy": 0.13092027232050896,
|
|
"num_tokens": 37306715.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 6.629836320877075,
|
|
"epoch": 1.845417090267002,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00046657584974769636,
|
|
"loss": 6.356,
|
|
"mean_token_accuracy": 0.13126768544316292,
|
|
"num_tokens": 37317605.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 6.625104999542236,
|
|
"epoch": 1.8459521643747658,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004665557959295213,
|
|
"loss": 6.2675,
|
|
"mean_token_accuracy": 0.13975381702184678,
|
|
"num_tokens": 37328898.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 6.6089941501617435,
|
|
"epoch": 1.84648723848253,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00046653573658019963,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.13710161820054054,
|
|
"num_tokens": 37340108.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 6.642422723770141,
|
|
"epoch": 1.8470223125902936,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00046651567170031053,
|
|
"loss": 6.3709,
|
|
"mean_token_accuracy": 0.135176370292902,
|
|
"num_tokens": 37351773.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 6.594505453109742,
|
|
"epoch": 1.8475573866980577,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004664956012904332,
|
|
"loss": 6.2825,
|
|
"mean_token_accuracy": 0.1348278932273388,
|
|
"num_tokens": 37362748.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 6.573114633560181,
|
|
"epoch": 1.8480924608058216,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004664755253511474,
|
|
"loss": 6.3622,
|
|
"mean_token_accuracy": 0.1318984553217888,
|
|
"num_tokens": 37373487.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 6.593974876403808,
|
|
"epoch": 1.8486275349135854,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004664554438830326,
|
|
"loss": 6.217,
|
|
"mean_token_accuracy": 0.13720255047082902,
|
|
"num_tokens": 37383302.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 6.608273935317993,
|
|
"epoch": 1.8491626090213495,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004664353568866689,
|
|
"loss": 6.2602,
|
|
"mean_token_accuracy": 0.13239469677209853,
|
|
"num_tokens": 37393085.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 6.7005657196044925,
|
|
"epoch": 1.8496976831291134,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.000466415264362636,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.1315258599817753,
|
|
"num_tokens": 37403774.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 6.667989206314087,
|
|
"epoch": 1.8502327572368773,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046639516631151435,
|
|
"loss": 6.3166,
|
|
"mean_token_accuracy": 0.1402564041316509,
|
|
"num_tokens": 37414356.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 6.56283392906189,
|
|
"epoch": 1.8507678313446412,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00046637506273388416,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.13335509076714516,
|
|
"num_tokens": 37426381.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 6.645048046112061,
|
|
"epoch": 1.851302905452405,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00046635495363032595,
|
|
"loss": 6.2896,
|
|
"mean_token_accuracy": 0.1335553079843521,
|
|
"num_tokens": 37436259.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 6.657007789611816,
|
|
"epoch": 1.8518379795601692,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.00046633483900142026,
|
|
"loss": 6.2713,
|
|
"mean_token_accuracy": 0.13850347697734833,
|
|
"num_tokens": 37447498.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 6.633471298217773,
|
|
"epoch": 1.852373053667933,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000466314718847748,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.1331757090985775,
|
|
"num_tokens": 37457323.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 6.627668142318726,
|
|
"epoch": 1.852908127775697,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004662945931698901,
|
|
"loss": 6.2954,
|
|
"mean_token_accuracy": 0.13209863379597664,
|
|
"num_tokens": 37468121.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 6.643212032318115,
|
|
"epoch": 1.853443201883461,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00046627446196842784,
|
|
"loss": 6.3447,
|
|
"mean_token_accuracy": 0.12525903955101966,
|
|
"num_tokens": 37479205.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 6.6700186252594,
|
|
"epoch": 1.8539782759912247,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004662543252439422,
|
|
"loss": 6.4445,
|
|
"mean_token_accuracy": 0.12689207196235658,
|
|
"num_tokens": 37491015.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 6.676544189453125,
|
|
"epoch": 1.8545133500989888,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00046623418299701494,
|
|
"loss": 6.374,
|
|
"mean_token_accuracy": 0.1245142474770546,
|
|
"num_tokens": 37503078.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 6.670204734802246,
|
|
"epoch": 1.8550484242067526,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.0004662140352282274,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.1376691021025181,
|
|
"num_tokens": 37514623.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 6.598353576660156,
|
|
"epoch": 1.8555834983145165,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00046619388193816155,
|
|
"loss": 6.2818,
|
|
"mean_token_accuracy": 0.1332160823047161,
|
|
"num_tokens": 37525618.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 6.6285497665405275,
|
|
"epoch": 1.8561185724222806,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046617372312739917,
|
|
"loss": 6.3584,
|
|
"mean_token_accuracy": 0.13104381486773492,
|
|
"num_tokens": 37536023.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 6.672425699234009,
|
|
"epoch": 1.8566536465300443,
|
|
"grad_norm": 6.1875,
|
|
"learning_rate": 0.0004661535587965224,
|
|
"loss": 6.3438,
|
|
"mean_token_accuracy": 0.12977855876088143,
|
|
"num_tokens": 37545886.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 6.625645685195923,
|
|
"epoch": 1.8571887206378084,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00046613338894611347,
|
|
"loss": 6.2716,
|
|
"mean_token_accuracy": 0.12767500057816505,
|
|
"num_tokens": 37557587.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 6.574593210220337,
|
|
"epoch": 1.8577237947455723,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004661132135767548,
|
|
"loss": 6.2147,
|
|
"mean_token_accuracy": 0.14355370700359343,
|
|
"num_tokens": 37569379.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 6.682255506515503,
|
|
"epoch": 1.8582588688533361,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000466093032689029,
|
|
"loss": 6.3746,
|
|
"mean_token_accuracy": 0.12823841720819473,
|
|
"num_tokens": 37580478.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 6.579362201690674,
|
|
"epoch": 1.8587939429611002,
|
|
"grad_norm": 23.75,
|
|
"learning_rate": 0.0004660728462835187,
|
|
"loss": 6.3044,
|
|
"mean_token_accuracy": 0.13725776448845864,
|
|
"num_tokens": 37591506.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 6.54266767501831,
|
|
"epoch": 1.8593290170688639,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004660526543608068,
|
|
"loss": 6.1488,
|
|
"mean_token_accuracy": 0.14388667270541192,
|
|
"num_tokens": 37602074.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 6.654793310165405,
|
|
"epoch": 1.859864091176628,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004660324569214763,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.1255615808069706,
|
|
"num_tokens": 37612180.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 6.629324245452881,
|
|
"epoch": 1.8603991652843919,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004660122539661106,
|
|
"loss": 6.3276,
|
|
"mean_token_accuracy": 0.1313563294708729,
|
|
"num_tokens": 37622588.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 6.671821403503418,
|
|
"epoch": 1.8609342393921557,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004659920454952928,
|
|
"loss": 6.2979,
|
|
"mean_token_accuracy": 0.1334337666630745,
|
|
"num_tokens": 37634323.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 6.68469762802124,
|
|
"epoch": 1.8614693134999198,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004659718315096065,
|
|
"loss": 6.369,
|
|
"mean_token_accuracy": 0.12719584181904792,
|
|
"num_tokens": 37645816.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 6.724806833267212,
|
|
"epoch": 1.8620043876076835,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00046595161200963545,
|
|
"loss": 6.3605,
|
|
"mean_token_accuracy": 0.12854044660925865,
|
|
"num_tokens": 37656143.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 6.629797124862671,
|
|
"epoch": 1.8625394617154476,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.00046593138699596343,
|
|
"loss": 6.2589,
|
|
"mean_token_accuracy": 0.12791704535484313,
|
|
"num_tokens": 37665959.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 6.553432559967041,
|
|
"epoch": 1.8630745358232115,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.00046591115646917443,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.12191513404250146,
|
|
"num_tokens": 37677176.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 6.575576734542847,
|
|
"epoch": 1.8636096099309754,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004658909204298526,
|
|
"loss": 6.3328,
|
|
"mean_token_accuracy": 0.13491981402039527,
|
|
"num_tokens": 37687740.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 6.590323495864868,
|
|
"epoch": 1.8641446840387395,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004658706788785823,
|
|
"loss": 6.2717,
|
|
"mean_token_accuracy": 0.13880357071757315,
|
|
"num_tokens": 37698536.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 6.663274526596069,
|
|
"epoch": 1.8646797581465033,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00046585043181594793,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.1336245618760586,
|
|
"num_tokens": 37708795.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 6.684688520431519,
|
|
"epoch": 1.8652148322542672,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00046583017924253426,
|
|
"loss": 6.3217,
|
|
"mean_token_accuracy": 0.13615410551428794,
|
|
"num_tokens": 37719136.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 6.729979848861694,
|
|
"epoch": 1.8657499063620313,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004658099211589259,
|
|
"loss": 6.4068,
|
|
"mean_token_accuracy": 0.13240860402584076,
|
|
"num_tokens": 37730513.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 6.630531358718872,
|
|
"epoch": 1.866284980469795,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00046578965756570787,
|
|
"loss": 6.3318,
|
|
"mean_token_accuracy": 0.12876324951648713,
|
|
"num_tokens": 37741811.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 6.536631631851196,
|
|
"epoch": 1.866820054577559,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00046576938846346527,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.13851544559001921,
|
|
"num_tokens": 37752213.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 6.486163806915283,
|
|
"epoch": 1.867355128685323,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046574911385278343,
|
|
"loss": 6.1366,
|
|
"mean_token_accuracy": 0.1502847321331501,
|
|
"num_tokens": 37763253.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 6.614396381378174,
|
|
"epoch": 1.8678902027930868,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046572883373424776,
|
|
"loss": 6.3554,
|
|
"mean_token_accuracy": 0.12787273675203323,
|
|
"num_tokens": 37775087.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 6.666113376617432,
|
|
"epoch": 1.868425276900851,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00046570854810844373,
|
|
"loss": 6.3463,
|
|
"mean_token_accuracy": 0.12702058106660843,
|
|
"num_tokens": 37786119.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 6.655316925048828,
|
|
"epoch": 1.8689603510086146,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00046568825697595724,
|
|
"loss": 6.34,
|
|
"mean_token_accuracy": 0.1301281288266182,
|
|
"num_tokens": 37797482.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 6.636830997467041,
|
|
"epoch": 1.8694954251163787,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004656679603373741,
|
|
"loss": 6.28,
|
|
"mean_token_accuracy": 0.13358325362205506,
|
|
"num_tokens": 37808067.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 6.665271615982055,
|
|
"epoch": 1.8700304992241426,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004656476581932804,
|
|
"loss": 6.4135,
|
|
"mean_token_accuracy": 0.12461074516177177,
|
|
"num_tokens": 37819762.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 6.572727346420288,
|
|
"epoch": 1.8705655733319064,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004656273505442624,
|
|
"loss": 6.3036,
|
|
"mean_token_accuracy": 0.13804551661014558,
|
|
"num_tokens": 37829510.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 6.620176839828491,
|
|
"epoch": 1.8711006474396705,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00046560703739090633,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.13087524324655533,
|
|
"num_tokens": 37839431.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 6.70141019821167,
|
|
"epoch": 1.8716357215474342,
|
|
"grad_norm": 5.34375,
|
|
"learning_rate": 0.00046558671873379886,
|
|
"loss": 6.3723,
|
|
"mean_token_accuracy": 0.12219800576567649,
|
|
"num_tokens": 37850531.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 6.710987281799317,
|
|
"epoch": 1.8721707956551983,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004655663945735268,
|
|
"loss": 6.3895,
|
|
"mean_token_accuracy": 0.1254601500928402,
|
|
"num_tokens": 37861964.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 6.540854406356812,
|
|
"epoch": 1.8727058697629622,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004655460649106768,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.1462603121995926,
|
|
"num_tokens": 37873598.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 6.65954270362854,
|
|
"epoch": 1.873240943870726,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00046552572974583597,
|
|
"loss": 6.3463,
|
|
"mean_token_accuracy": 0.12698510214686393,
|
|
"num_tokens": 37884643.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 6.605120086669922,
|
|
"epoch": 1.8737760179784901,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004655053890795914,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.1272936172783375,
|
|
"num_tokens": 37896566.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 6.677714109420776,
|
|
"epoch": 1.8743110920862538,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00046548504291253054,
|
|
"loss": 6.3818,
|
|
"mean_token_accuracy": 0.12922848090529443,
|
|
"num_tokens": 37907424.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 6.683991384506226,
|
|
"epoch": 1.874846166194018,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004654646912452408,
|
|
"loss": 6.329,
|
|
"mean_token_accuracy": 0.1327470749616623,
|
|
"num_tokens": 37917318.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 6.622165250778198,
|
|
"epoch": 1.8753812403017818,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004654443340783099,
|
|
"loss": 6.2914,
|
|
"mean_token_accuracy": 0.13647771179676055,
|
|
"num_tokens": 37928521.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 6.619613790512085,
|
|
"epoch": 1.8759163144095456,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00046542397141232554,
|
|
"loss": 6.352,
|
|
"mean_token_accuracy": 0.13352775126695632,
|
|
"num_tokens": 37939930.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 6.61543836593628,
|
|
"epoch": 1.8764513885173097,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004654036032478759,
|
|
"loss": 6.2823,
|
|
"mean_token_accuracy": 0.13499080762267113,
|
|
"num_tokens": 37949690.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 6.623438119888306,
|
|
"epoch": 1.8769864626250736,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.00046538322958554885,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.14001342058181762,
|
|
"num_tokens": 37962162.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 6.70307469367981,
|
|
"epoch": 1.8775215367328375,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004653628504259329,
|
|
"loss": 6.3204,
|
|
"mean_token_accuracy": 0.13058942854404448,
|
|
"num_tokens": 37972707.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 6.586777830123902,
|
|
"epoch": 1.8780566108406014,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00046534246576961633,
|
|
"loss": 6.2543,
|
|
"mean_token_accuracy": 0.13928712010383607,
|
|
"num_tokens": 37983101.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 6.496839761734009,
|
|
"epoch": 1.8785916849483653,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00046532207561718775,
|
|
"loss": 6.2153,
|
|
"mean_token_accuracy": 0.13958105370402335,
|
|
"num_tokens": 37994025.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 6.598912715911865,
|
|
"epoch": 1.8791267590561294,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00046530167996923613,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.1276422955095768,
|
|
"num_tokens": 38004761.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 6.686553001403809,
|
|
"epoch": 1.8796618331638932,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004652812788263501,
|
|
"loss": 6.3388,
|
|
"mean_token_accuracy": 0.13515076488256456,
|
|
"num_tokens": 38015129.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 6.645777082443237,
|
|
"epoch": 1.8801969072716571,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.00046526087218911894,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.1359887018799782,
|
|
"num_tokens": 38025501.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 6.63254828453064,
|
|
"epoch": 1.8807319813794212,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046524046005813185,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.13127582967281343,
|
|
"num_tokens": 38034912.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 6.60418004989624,
|
|
"epoch": 1.8812670554871849,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004652200424339782,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.13427453190088273,
|
|
"num_tokens": 38045417.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 6.647205400466919,
|
|
"epoch": 1.881802129594949,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004651996193172475,
|
|
"loss": 6.3994,
|
|
"mean_token_accuracy": 0.12675082087516784,
|
|
"num_tokens": 38057033.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 6.671993827819824,
|
|
"epoch": 1.8823372037027128,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004651791907085296,
|
|
"loss": 6.3198,
|
|
"mean_token_accuracy": 0.13641978651285172,
|
|
"num_tokens": 38067804.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 6.6601917266845705,
|
|
"epoch": 1.8828722778104767,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004651587566084143,
|
|
"loss": 6.3002,
|
|
"mean_token_accuracy": 0.14057500138878823,
|
|
"num_tokens": 38079246.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 6.671951246261597,
|
|
"epoch": 1.8834073519182408,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00046513831701749155,
|
|
"loss": 6.4507,
|
|
"mean_token_accuracy": 0.1259689025580883,
|
|
"num_tokens": 38090628.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 6.590282011032104,
|
|
"epoch": 1.8839424260260045,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00046511787193635165,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.13838147595524788,
|
|
"num_tokens": 38100848.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 6.68871545791626,
|
|
"epoch": 1.8844775001337686,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00046509742136558493,
|
|
"loss": 6.2716,
|
|
"mean_token_accuracy": 0.1335602141916752,
|
|
"num_tokens": 38110732.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 6.601482772827149,
|
|
"epoch": 1.8850125742415325,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00046507696530578185,
|
|
"loss": 6.2608,
|
|
"mean_token_accuracy": 0.14348884373903276,
|
|
"num_tokens": 38121002.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 6.6228508949279785,
|
|
"epoch": 1.8855476483492963,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004650565037575331,
|
|
"loss": 6.319,
|
|
"mean_token_accuracy": 0.1325066864490509,
|
|
"num_tokens": 38132294.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 6.5808309555053714,
|
|
"epoch": 1.8860827224570604,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00046503603672142955,
|
|
"loss": 6.2387,
|
|
"mean_token_accuracy": 0.1357392393052578,
|
|
"num_tokens": 38142962.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 6.658428621292114,
|
|
"epoch": 1.886617796564824,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004650155641980621,
|
|
"loss": 6.3505,
|
|
"mean_token_accuracy": 0.13111490234732628,
|
|
"num_tokens": 38153737.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 6.659497594833374,
|
|
"epoch": 1.8871528706725882,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00046499508618802195,
|
|
"loss": 6.3208,
|
|
"mean_token_accuracy": 0.13113079071044922,
|
|
"num_tokens": 38163897.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 6.583869504928589,
|
|
"epoch": 1.887687944780352,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004649746026919004,
|
|
"loss": 6.2805,
|
|
"mean_token_accuracy": 0.14177790358662606,
|
|
"num_tokens": 38175123.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 6.579678010940552,
|
|
"epoch": 1.888223018888116,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00046495411371028886,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.13888279870152473,
|
|
"num_tokens": 38186100.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 6.682177734375,
|
|
"epoch": 1.88875809299588,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046493361924377903,
|
|
"loss": 6.3221,
|
|
"mean_token_accuracy": 0.1338127762079239,
|
|
"num_tokens": 38196385.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 6.544964599609375,
|
|
"epoch": 1.8892931671036437,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004649131192929626,
|
|
"loss": 6.2715,
|
|
"mean_token_accuracy": 0.13190760165452958,
|
|
"num_tokens": 38207260.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 6.549527883529663,
|
|
"epoch": 1.8898282412114078,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004648926138584315,
|
|
"loss": 6.1825,
|
|
"mean_token_accuracy": 0.14460922330617904,
|
|
"num_tokens": 38217537.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 6.668672180175781,
|
|
"epoch": 1.8903633153191717,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00046487210294077794,
|
|
"loss": 6.2938,
|
|
"mean_token_accuracy": 0.12837572395801544,
|
|
"num_tokens": 38228956.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 6.525818729400635,
|
|
"epoch": 1.8908983894269356,
|
|
"grad_norm": 6.53125,
|
|
"learning_rate": 0.00046485158654059405,
|
|
"loss": 6.2281,
|
|
"mean_token_accuracy": 0.13550452440977095,
|
|
"num_tokens": 38240236.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 6.656255483627319,
|
|
"epoch": 1.8914334635346997,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004648310646584723,
|
|
"loss": 6.3568,
|
|
"mean_token_accuracy": 0.1327085316181183,
|
|
"num_tokens": 38251739.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 6.656518983840942,
|
|
"epoch": 1.8919685376424635,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00046481053729500516,
|
|
"loss": 6.2959,
|
|
"mean_token_accuracy": 0.12752566784620284,
|
|
"num_tokens": 38262090.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 6.667726182937622,
|
|
"epoch": 1.8925036117502274,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004647900044507855,
|
|
"loss": 6.3038,
|
|
"mean_token_accuracy": 0.13256197348237037,
|
|
"num_tokens": 38272770.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 6.595956087112427,
|
|
"epoch": 1.8930386858579913,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004647694661264061,
|
|
"loss": 6.2613,
|
|
"mean_token_accuracy": 0.13470710515975953,
|
|
"num_tokens": 38283449.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 6.591614627838135,
|
|
"epoch": 1.8935737599657552,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00046474892232246,
|
|
"loss": 6.3039,
|
|
"mean_token_accuracy": 0.13666461184620857,
|
|
"num_tokens": 38293831.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 6.582961320877075,
|
|
"epoch": 1.8941088340735193,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00046472837303954053,
|
|
"loss": 6.2507,
|
|
"mean_token_accuracy": 0.13238801658153534,
|
|
"num_tokens": 38304782.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 6.638685703277588,
|
|
"epoch": 1.8946439081812831,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00046470781827824087,
|
|
"loss": 6.3149,
|
|
"mean_token_accuracy": 0.13763461112976075,
|
|
"num_tokens": 38316547.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 6.651870679855347,
|
|
"epoch": 1.895178982289047,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00046468725803915464,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.13055257350206376,
|
|
"num_tokens": 38329488.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 6.5717504024505615,
|
|
"epoch": 1.8957140563968111,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00046466669232287543,
|
|
"loss": 6.1969,
|
|
"mean_token_accuracy": 0.14302201718091964,
|
|
"num_tokens": 38341290.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 6.603822660446167,
|
|
"epoch": 1.8962491305045748,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004646461211299973,
|
|
"loss": 6.3188,
|
|
"mean_token_accuracy": 0.1284906543791294,
|
|
"num_tokens": 38352445.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 6.610106372833252,
|
|
"epoch": 1.8967842046123389,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004646255444611139,
|
|
"loss": 6.3322,
|
|
"mean_token_accuracy": 0.1338462047278881,
|
|
"num_tokens": 38363825.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 6.616929960250855,
|
|
"epoch": 1.8973192787201028,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00046460496231681957,
|
|
"loss": 6.3982,
|
|
"mean_token_accuracy": 0.13163574114441873,
|
|
"num_tokens": 38375454.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 6.593948030471802,
|
|
"epoch": 1.8978543528278666,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.00046458437469770866,
|
|
"loss": 6.3243,
|
|
"mean_token_accuracy": 0.1351953186094761,
|
|
"num_tokens": 38385938.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 6.604735565185547,
|
|
"epoch": 1.8983894269356307,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00046456378160437555,
|
|
"loss": 6.2608,
|
|
"mean_token_accuracy": 0.13992209136486053,
|
|
"num_tokens": 38396143.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 6.557766103744507,
|
|
"epoch": 1.8989245010433944,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004645431830374149,
|
|
"loss": 6.3471,
|
|
"mean_token_accuracy": 0.1251856081187725,
|
|
"num_tokens": 38407445.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 6.653984689712525,
|
|
"epoch": 1.8994595751511585,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00046452257899742144,
|
|
"loss": 6.3627,
|
|
"mean_token_accuracy": 0.12066067457199096,
|
|
"num_tokens": 38418438.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 6.620872831344604,
|
|
"epoch": 1.8999946492589224,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00046450196948499015,
|
|
"loss": 6.239,
|
|
"mean_token_accuracy": 0.13421217799186708,
|
|
"num_tokens": 38428821.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 6.623964929580689,
|
|
"epoch": 1.9005297233666862,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004644813545007161,
|
|
"loss": 6.2262,
|
|
"mean_token_accuracy": 0.13535997793078422,
|
|
"num_tokens": 38439560.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 6.597965145111084,
|
|
"epoch": 1.9010647974744503,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004644607340451946,
|
|
"loss": 6.3152,
|
|
"mean_token_accuracy": 0.13745911940932273,
|
|
"num_tokens": 38449724.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 6.64752345085144,
|
|
"epoch": 1.901599871582214,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.00046444010811902105,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.13298168852925302,
|
|
"num_tokens": 38459833.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 6.607278203964233,
|
|
"epoch": 1.902134945689978,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00046441947672279095,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.13985922560095787,
|
|
"num_tokens": 38470682.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 6.610258722305298,
|
|
"epoch": 1.902670019797742,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004643988398571001,
|
|
"loss": 6.3025,
|
|
"mean_token_accuracy": 0.1318335175514221,
|
|
"num_tokens": 38481362.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 6.598448276519775,
|
|
"epoch": 1.9032050939055059,
|
|
"grad_norm": 5.0,
|
|
"learning_rate": 0.0004643781975225444,
|
|
"loss": 6.2848,
|
|
"mean_token_accuracy": 0.1404268704354763,
|
|
"num_tokens": 38492941.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 6.672146987915039,
|
|
"epoch": 1.90374016801327,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00046435754971971976,
|
|
"loss": 6.3126,
|
|
"mean_token_accuracy": 0.1294758602976799,
|
|
"num_tokens": 38503823.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 6.609655427932739,
|
|
"epoch": 1.9042752421210336,
|
|
"grad_norm": 7.4375,
|
|
"learning_rate": 0.00046433689644922256,
|
|
"loss": 6.2438,
|
|
"mean_token_accuracy": 0.13945200368762017,
|
|
"num_tokens": 38514482.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 6.614125680923462,
|
|
"epoch": 1.9048103162287977,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00046431623771164897,
|
|
"loss": 6.3117,
|
|
"mean_token_accuracy": 0.13540274500846863,
|
|
"num_tokens": 38525580.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 6.635672664642334,
|
|
"epoch": 1.9053453903365616,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004642955735075958,
|
|
"loss": 6.3058,
|
|
"mean_token_accuracy": 0.13719252049922942,
|
|
"num_tokens": 38537025.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 6.643199014663696,
|
|
"epoch": 1.9058804644443255,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046427490383765943,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.13464637100696564,
|
|
"num_tokens": 38548974.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 6.604790925979614,
|
|
"epoch": 1.9064155385520896,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004642542287024368,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.1389023132622242,
|
|
"num_tokens": 38559971.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 6.64806752204895,
|
|
"epoch": 1.9069506126598534,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.000464233548102525,
|
|
"loss": 6.2642,
|
|
"mean_token_accuracy": 0.1332742042839527,
|
|
"num_tokens": 38570326.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 6.606299161911011,
|
|
"epoch": 1.9074856867676173,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000464212862038521,
|
|
"loss": 6.2812,
|
|
"mean_token_accuracy": 0.1327664889395237,
|
|
"num_tokens": 38580799.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 6.511040115356446,
|
|
"epoch": 1.9080207608753812,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00046419217051102223,
|
|
"loss": 6.3552,
|
|
"mean_token_accuracy": 0.12950172945857047,
|
|
"num_tokens": 38591136.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 6.590004873275757,
|
|
"epoch": 1.908555834983145,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004641714735206261,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.13618991598486901,
|
|
"num_tokens": 38602600.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 6.669078302383423,
|
|
"epoch": 1.9090909090909092,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046415077106793024,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.13270080015063285,
|
|
"num_tokens": 38612641.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 6.632688856124878,
|
|
"epoch": 1.909625983198673,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004641300631535325,
|
|
"loss": 6.2603,
|
|
"mean_token_accuracy": 0.13681951761245728,
|
|
"num_tokens": 38622873.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 6.5671014308929445,
|
|
"epoch": 1.910161057306437,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004641093497780307,
|
|
"loss": 6.2929,
|
|
"mean_token_accuracy": 0.13879813402891159,
|
|
"num_tokens": 38633523.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 6.608433103561401,
|
|
"epoch": 1.910696131414201,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004640886309420231,
|
|
"loss": 6.3059,
|
|
"mean_token_accuracy": 0.12590662464499475,
|
|
"num_tokens": 38645635.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 6.6866131782531735,
|
|
"epoch": 1.9112312055219647,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004640679066461078,
|
|
"loss": 6.2645,
|
|
"mean_token_accuracy": 0.13954178243875504,
|
|
"num_tokens": 38656293.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 6.625728559494019,
|
|
"epoch": 1.9117662796297288,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004640471768908832,
|
|
"loss": 6.3788,
|
|
"mean_token_accuracy": 0.1237617440521717,
|
|
"num_tokens": 38667307.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 6.63565411567688,
|
|
"epoch": 1.9123013537374927,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004640264416769481,
|
|
"loss": 6.2597,
|
|
"mean_token_accuracy": 0.13812418282032013,
|
|
"num_tokens": 38677775.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 6.574324083328247,
|
|
"epoch": 1.9128364278452565,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00046400570100490086,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.133269814401865,
|
|
"num_tokens": 38688652.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 6.693653583526611,
|
|
"epoch": 1.9133715019530206,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00046398495487534066,
|
|
"loss": 6.3292,
|
|
"mean_token_accuracy": 0.12704226300120353,
|
|
"num_tokens": 38698694.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 6.69752140045166,
|
|
"epoch": 1.9139065760607843,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004639642032888664,
|
|
"loss": 6.3323,
|
|
"mean_token_accuracy": 0.1328016772866249,
|
|
"num_tokens": 38709864.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 6.606888484954834,
|
|
"epoch": 1.9144416501685484,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004639434462460774,
|
|
"loss": 6.3345,
|
|
"mean_token_accuracy": 0.1275869481265545,
|
|
"num_tokens": 38721034.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 6.6645567417144775,
|
|
"epoch": 1.9149767242763123,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00046392268374757285,
|
|
"loss": 6.337,
|
|
"mean_token_accuracy": 0.12819663137197496,
|
|
"num_tokens": 38731874.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 6.594719648361206,
|
|
"epoch": 1.9155117983840761,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004639019157939524,
|
|
"loss": 6.2803,
|
|
"mean_token_accuracy": 0.13650997206568719,
|
|
"num_tokens": 38742447.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 6.628026628494263,
|
|
"epoch": 1.9160468724918402,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004638811423858157,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.1366233415901661,
|
|
"num_tokens": 38754117.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 6.627432346343994,
|
|
"epoch": 1.916581946599604,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00046386036352376255,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.12385469004511833,
|
|
"num_tokens": 38765057.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 6.607076406478882,
|
|
"epoch": 1.917117020707368,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046383957920839285,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.1392330765724182,
|
|
"num_tokens": 38775938.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 6.5342999458312985,
|
|
"epoch": 1.9176520948151319,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00046381878944030697,
|
|
"loss": 6.2054,
|
|
"mean_token_accuracy": 0.13657856956124306,
|
|
"num_tokens": 38787013.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 6.5868042469024655,
|
|
"epoch": 1.9181871689228958,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000463797994220105,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.136510668694973,
|
|
"num_tokens": 38798412.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 6.619282865524292,
|
|
"epoch": 1.9187222430306599,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00046377719354838756,
|
|
"loss": 6.331,
|
|
"mean_token_accuracy": 0.12793270274996757,
|
|
"num_tokens": 38809983.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 6.664031648635865,
|
|
"epoch": 1.9192573171384235,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046375638742575506,
|
|
"loss": 6.3183,
|
|
"mean_token_accuracy": 0.13364638313651084,
|
|
"num_tokens": 38820418.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 6.655880117416382,
|
|
"epoch": 1.9197923912461876,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004637355758528085,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.13363831266760826,
|
|
"num_tokens": 38831482.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 6.698722314834595,
|
|
"epoch": 1.9203274653539515,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004637147588301486,
|
|
"loss": 6.3174,
|
|
"mean_token_accuracy": 0.1279696963727474,
|
|
"num_tokens": 38842110.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 6.580570077896118,
|
|
"epoch": 1.9208625394617154,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00046369393635837657,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.13577533811330794,
|
|
"num_tokens": 38852861.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 6.561133956909179,
|
|
"epoch": 1.9213976135694795,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00046367310843809374,
|
|
"loss": 6.3396,
|
|
"mean_token_accuracy": 0.12695899605751038,
|
|
"num_tokens": 38864067.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 6.5936907768249515,
|
|
"epoch": 1.9219326876772433,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00046365227506990137,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.1335115022957325,
|
|
"num_tokens": 38875363.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 6.680049991607666,
|
|
"epoch": 1.9224677617850072,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004636314362544011,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.13562106788158418,
|
|
"num_tokens": 38886414.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 6.686338090896607,
|
|
"epoch": 1.923002835892771,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00046361059199219457,
|
|
"loss": 6.3738,
|
|
"mean_token_accuracy": 0.1290262259542942,
|
|
"num_tokens": 38897708.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 6.549062442779541,
|
|
"epoch": 1.923537910000535,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004635897422838837,
|
|
"loss": 6.2472,
|
|
"mean_token_accuracy": 0.13593280091881751,
|
|
"num_tokens": 38908683.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 6.494812965393066,
|
|
"epoch": 1.924072984108299,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00046356888713007055,
|
|
"loss": 6.2078,
|
|
"mean_token_accuracy": 0.143157659471035,
|
|
"num_tokens": 38919279.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 6.603155660629272,
|
|
"epoch": 1.924608058216063,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046354802653135723,
|
|
"loss": 6.3226,
|
|
"mean_token_accuracy": 0.12940333560109138,
|
|
"num_tokens": 38929353.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 6.630473041534424,
|
|
"epoch": 1.9251431323238268,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004635271604883462,
|
|
"loss": 6.2765,
|
|
"mean_token_accuracy": 0.13454302698373793,
|
|
"num_tokens": 38939296.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 6.601442956924439,
|
|
"epoch": 1.925678206431591,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00046350628900163987,
|
|
"loss": 6.2911,
|
|
"mean_token_accuracy": 0.1352592244744301,
|
|
"num_tokens": 38950149.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 6.6375023365020756,
|
|
"epoch": 1.9262132805393546,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000463485412071841,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.1311757579445839,
|
|
"num_tokens": 38961052.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.9262132805393546,
|
|
"eval_entropy": 6.453076730712726,
|
|
"eval_loss": 6.403806686401367,
|
|
"eval_mean_token_accuracy": 0.13643358242133197,
|
|
"eval_num_tokens": 38961052.0,
|
|
"eval_runtime": 22.8229,
|
|
"eval_samples_per_second": 1300.404,
|
|
"eval_steps_per_second": 162.556,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 6.6405754566192625,
|
|
"epoch": 1.9267483546471187,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046346452969955214,
|
|
"loss": 6.3406,
|
|
"mean_token_accuracy": 0.13284966051578523,
|
|
"num_tokens": 38972344.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 6.592107248306275,
|
|
"epoch": 1.9272834287548826,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004634436418853767,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.12557595670223237,
|
|
"num_tokens": 38982877.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 6.601504850387573,
|
|
"epoch": 1.9278185028626464,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046342274862991745,
|
|
"loss": 6.2759,
|
|
"mean_token_accuracy": 0.13484299555420876,
|
|
"num_tokens": 38994322.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 6.647946739196778,
|
|
"epoch": 1.9283535769704105,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00046340184993377793,
|
|
"loss": 6.2439,
|
|
"mean_token_accuracy": 0.13622480779886245,
|
|
"num_tokens": 39003447.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 6.6276712894439695,
|
|
"epoch": 1.9288886510781742,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00046338094579756136,
|
|
"loss": 6.2896,
|
|
"mean_token_accuracy": 0.1311311513185501,
|
|
"num_tokens": 39013760.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 6.436968040466309,
|
|
"epoch": 1.9294237251859383,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00046336003622187143,
|
|
"loss": 6.0986,
|
|
"mean_token_accuracy": 0.14645204469561576,
|
|
"num_tokens": 39025559.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 6.535755586624146,
|
|
"epoch": 1.9299587992937022,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.000463339121207312,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.13236603438854216,
|
|
"num_tokens": 39036004.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 6.582877111434937,
|
|
"epoch": 1.930493873401466,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004633182007544868,
|
|
"loss": 6.3238,
|
|
"mean_token_accuracy": 0.13297565579414367,
|
|
"num_tokens": 39047251.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 6.6302838802337645,
|
|
"epoch": 1.9310289475092302,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00046329727486400015,
|
|
"loss": 6.3534,
|
|
"mean_token_accuracy": 0.12752459943294525,
|
|
"num_tokens": 39057255.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 6.669422578811646,
|
|
"epoch": 1.9315640216169938,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004632763435364561,
|
|
"loss": 6.3494,
|
|
"mean_token_accuracy": 0.13096485659480095,
|
|
"num_tokens": 39068186.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 6.611477470397949,
|
|
"epoch": 1.932099095724758,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00046325540677245907,
|
|
"loss": 6.2501,
|
|
"mean_token_accuracy": 0.13380171209573746,
|
|
"num_tokens": 39079173.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 6.613319826126099,
|
|
"epoch": 1.9326341698325218,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00046323446457261365,
|
|
"loss": 6.3407,
|
|
"mean_token_accuracy": 0.1311669684946537,
|
|
"num_tokens": 39089939.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 6.577937936782837,
|
|
"epoch": 1.9331692439402857,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004632135169375245,
|
|
"loss": 6.3168,
|
|
"mean_token_accuracy": 0.13481636196374894,
|
|
"num_tokens": 39100464.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 6.657149410247802,
|
|
"epoch": 1.9337043180480498,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004631925638677965,
|
|
"loss": 6.2709,
|
|
"mean_token_accuracy": 0.1347548857331276,
|
|
"num_tokens": 39111161.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 6.6402815818786625,
|
|
"epoch": 1.9342393921558134,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00046317160536403463,
|
|
"loss": 6.2936,
|
|
"mean_token_accuracy": 0.14163879081606864,
|
|
"num_tokens": 39122469.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 6.60252742767334,
|
|
"epoch": 1.9347744662635775,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046315064142684416,
|
|
"loss": 6.2361,
|
|
"mean_token_accuracy": 0.14239733964204787,
|
|
"num_tokens": 39131871.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 6.590932703018188,
|
|
"epoch": 1.9353095403713414,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004631296720568304,
|
|
"loss": 6.3001,
|
|
"mean_token_accuracy": 0.13025425747036934,
|
|
"num_tokens": 39143061.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 6.543646669387817,
|
|
"epoch": 1.9358446144791053,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004631086972545987,
|
|
"loss": 6.2945,
|
|
"mean_token_accuracy": 0.14120843261480331,
|
|
"num_tokens": 39152452.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 6.527207136154175,
|
|
"epoch": 1.9363796885868694,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004630877170207548,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.13757711350917817,
|
|
"num_tokens": 39163196.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 6.55150351524353,
|
|
"epoch": 1.9369147626946333,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004630667313559045,
|
|
"loss": 6.2538,
|
|
"mean_token_accuracy": 0.1307540327310562,
|
|
"num_tokens": 39173958.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 6.617849922180175,
|
|
"epoch": 1.9374498368023971,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00046304574026065376,
|
|
"loss": 6.2672,
|
|
"mean_token_accuracy": 0.13959050178527832,
|
|
"num_tokens": 39184483.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 6.530823278427124,
|
|
"epoch": 1.937984910910161,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004630247437356087,
|
|
"loss": 6.3261,
|
|
"mean_token_accuracy": 0.13107125833630562,
|
|
"num_tokens": 39196500.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 6.642915153503418,
|
|
"epoch": 1.9385199850179249,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00046300374178137566,
|
|
"loss": 6.369,
|
|
"mean_token_accuracy": 0.1297813333570957,
|
|
"num_tokens": 39207492.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 6.652480554580689,
|
|
"epoch": 1.939055059125689,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004629827343985609,
|
|
"loss": 6.2879,
|
|
"mean_token_accuracy": 0.13619059696793556,
|
|
"num_tokens": 39218204.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 6.648185873031617,
|
|
"epoch": 1.9395901332334529,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00046296172158777116,
|
|
"loss": 6.3358,
|
|
"mean_token_accuracy": 0.12842862084507942,
|
|
"num_tokens": 39229646.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 6.618672943115234,
|
|
"epoch": 1.9401252073412167,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004629407033496131,
|
|
"loss": 6.2827,
|
|
"mean_token_accuracy": 0.13143716678023337,
|
|
"num_tokens": 39240151.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 6.629973554611206,
|
|
"epoch": 1.9406602814489808,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004629196796846936,
|
|
"loss": 6.3402,
|
|
"mean_token_accuracy": 0.1362326741218567,
|
|
"num_tokens": 39251571.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 6.6370221138000485,
|
|
"epoch": 1.9411953555567445,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046289865059361983,
|
|
"loss": 6.2862,
|
|
"mean_token_accuracy": 0.13274998143315314,
|
|
"num_tokens": 39262937.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 6.650292253494262,
|
|
"epoch": 1.9417304296645086,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046287761607699887,
|
|
"loss": 6.3747,
|
|
"mean_token_accuracy": 0.1311851494014263,
|
|
"num_tokens": 39274354.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 6.6335042953491214,
|
|
"epoch": 1.9422655037722725,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004628565761354382,
|
|
"loss": 6.259,
|
|
"mean_token_accuracy": 0.13824965432286263,
|
|
"num_tokens": 39284314.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 6.567974519729614,
|
|
"epoch": 1.9428005778800364,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00046283553076954527,
|
|
"loss": 6.272,
|
|
"mean_token_accuracy": 0.13405769392848016,
|
|
"num_tokens": 39295516.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 6.605622720718384,
|
|
"epoch": 1.9433356519878004,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004628144799799277,
|
|
"loss": 6.2892,
|
|
"mean_token_accuracy": 0.13282298892736435,
|
|
"num_tokens": 39307221.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 6.603948450088501,
|
|
"epoch": 1.943870726095564,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004627934237671935,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.13060752749443055,
|
|
"num_tokens": 39318448.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 6.574307537078857,
|
|
"epoch": 1.9444058002033282,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00046277236213195064,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.14082662910223007,
|
|
"num_tokens": 39329384.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 6.601798391342163,
|
|
"epoch": 1.944940874311092,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.00046275129507480705,
|
|
"loss": 6.3398,
|
|
"mean_token_accuracy": 0.13390476182103156,
|
|
"num_tokens": 39340342.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 6.497661828994751,
|
|
"epoch": 1.945475948418856,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004627302225963713,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.14248088151216506,
|
|
"num_tokens": 39350825.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 6.6758880615234375,
|
|
"epoch": 1.94601102252662,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00046270914469725174,
|
|
"loss": 6.3564,
|
|
"mean_token_accuracy": 0.1259928524494171,
|
|
"num_tokens": 39361986.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 6.653494787216187,
|
|
"epoch": 1.9465460966343837,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00046268806137805704,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.13453317061066628,
|
|
"num_tokens": 39372440.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 6.611294078826904,
|
|
"epoch": 1.9470811707421478,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004626669726393958,
|
|
"loss": 6.2769,
|
|
"mean_token_accuracy": 0.14468842446804048,
|
|
"num_tokens": 39383455.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 6.522170209884644,
|
|
"epoch": 1.9476162448499117,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004626458784818772,
|
|
"loss": 6.297,
|
|
"mean_token_accuracy": 0.13090599775314332,
|
|
"num_tokens": 39393511.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 6.549947023391724,
|
|
"epoch": 1.9481513189576756,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.00046262477890611026,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.135219606757164,
|
|
"num_tokens": 39404049.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 6.638777446746826,
|
|
"epoch": 1.9486863930654397,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00046260367391270414,
|
|
"loss": 6.2929,
|
|
"mean_token_accuracy": 0.13686663135886193,
|
|
"num_tokens": 39414771.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 6.587277030944824,
|
|
"epoch": 1.9492214671732033,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046258256350226835,
|
|
"loss": 6.2525,
|
|
"mean_token_accuracy": 0.13928669169545174,
|
|
"num_tokens": 39424869.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 6.55087628364563,
|
|
"epoch": 1.9497565412809674,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004625614476754123,
|
|
"loss": 6.3366,
|
|
"mean_token_accuracy": 0.13307763785123825,
|
|
"num_tokens": 39435442.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 6.626724815368652,
|
|
"epoch": 1.9502916153887313,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00046254032643274596,
|
|
"loss": 6.2832,
|
|
"mean_token_accuracy": 0.1386459544301033,
|
|
"num_tokens": 39446704.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 6.587406253814697,
|
|
"epoch": 1.9508266894964952,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046251919977487887,
|
|
"loss": 6.2904,
|
|
"mean_token_accuracy": 0.14100923240184784,
|
|
"num_tokens": 39458079.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 6.628858613967895,
|
|
"epoch": 1.9513617636042593,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00046249806770242135,
|
|
"loss": 6.2989,
|
|
"mean_token_accuracy": 0.1409958079457283,
|
|
"num_tokens": 39469867.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 6.581766891479492,
|
|
"epoch": 1.9518968377120232,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004624769302159834,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.13066913709044456,
|
|
"num_tokens": 39481138.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 6.58373384475708,
|
|
"epoch": 1.952431911819787,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004624557873161755,
|
|
"loss": 6.2426,
|
|
"mean_token_accuracy": 0.13671674355864524,
|
|
"num_tokens": 39492066.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 6.6335718631744385,
|
|
"epoch": 1.952966985927551,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004624346390036081,
|
|
"loss": 6.3403,
|
|
"mean_token_accuracy": 0.12580371722579003,
|
|
"num_tokens": 39502576.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 6.609574604034424,
|
|
"epoch": 1.9535020600353148,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004624134852788918,
|
|
"loss": 6.2585,
|
|
"mean_token_accuracy": 0.13199134543538094,
|
|
"num_tokens": 39513373.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 6.651701784133911,
|
|
"epoch": 1.954037134143079,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004623923261426374,
|
|
"loss": 6.3231,
|
|
"mean_token_accuracy": 0.12971585392951965,
|
|
"num_tokens": 39523970.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 6.57604832649231,
|
|
"epoch": 1.9545722082508428,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000462371161595456,
|
|
"loss": 6.3212,
|
|
"mean_token_accuracy": 0.13403116464614867,
|
|
"num_tokens": 39533893.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 6.576398515701294,
|
|
"epoch": 1.9551072823586066,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004623499916379586,
|
|
"loss": 6.2624,
|
|
"mean_token_accuracy": 0.1302025869488716,
|
|
"num_tokens": 39544276.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 6.642313623428345,
|
|
"epoch": 1.9556423564663707,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004623288162707565,
|
|
"loss": 6.2775,
|
|
"mean_token_accuracy": 0.13979310318827629,
|
|
"num_tokens": 39554443.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 6.604557847976684,
|
|
"epoch": 1.9561774305741344,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046230763549446116,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.1334226794540882,
|
|
"num_tokens": 39564508.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 6.614166593551635,
|
|
"epoch": 1.9567125046818985,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004622864493096842,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.12620873898267745,
|
|
"num_tokens": 39574757.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 6.645195436477661,
|
|
"epoch": 1.9572475787896624,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00046226525771703733,
|
|
"loss": 6.3751,
|
|
"mean_token_accuracy": 0.12469575107097626,
|
|
"num_tokens": 39585911.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 6.675882863998413,
|
|
"epoch": 1.9577826528974263,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004622440607171324,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.12905604168772697,
|
|
"num_tokens": 39597443.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 6.655953645706177,
|
|
"epoch": 1.9583177270051904,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046222285831058155,
|
|
"loss": 6.3357,
|
|
"mean_token_accuracy": 0.13277479335665704,
|
|
"num_tokens": 39608693.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 6.593850421905517,
|
|
"epoch": 1.958852801112954,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000462201650497997,
|
|
"loss": 6.3235,
|
|
"mean_token_accuracy": 0.13438228219747544,
|
|
"num_tokens": 39620002.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 6.614213562011718,
|
|
"epoch": 1.9593878752207181,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00046218043727999105,
|
|
"loss": 6.2821,
|
|
"mean_token_accuracy": 0.14223418906331062,
|
|
"num_tokens": 39629856.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 6.532969331741333,
|
|
"epoch": 1.959922949328482,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046215921865717637,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.14119271710515022,
|
|
"num_tokens": 39640418.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 6.661060953140259,
|
|
"epoch": 1.9604580234362459,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004621379946301655,
|
|
"loss": 6.3633,
|
|
"mean_token_accuracy": 0.12533408850431443,
|
|
"num_tokens": 39652871.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 6.672148609161377,
|
|
"epoch": 1.96099309754401,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004621167651995713,
|
|
"loss": 6.2875,
|
|
"mean_token_accuracy": 0.1315033219754696,
|
|
"num_tokens": 39663864.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 6.622793531417846,
|
|
"epoch": 1.9615281716517736,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004620955303660068,
|
|
"loss": 6.2897,
|
|
"mean_token_accuracy": 0.13778938055038453,
|
|
"num_tokens": 39675835.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 6.625301504135132,
|
|
"epoch": 1.9620632457595377,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00046207429013008525,
|
|
"loss": 6.3113,
|
|
"mean_token_accuracy": 0.12885296791791917,
|
|
"num_tokens": 39686799.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 6.684085893630981,
|
|
"epoch": 1.9625983198673016,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00046205304449241976,
|
|
"loss": 6.2703,
|
|
"mean_token_accuracy": 0.13376201316714287,
|
|
"num_tokens": 39697564.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 6.612188339233398,
|
|
"epoch": 1.9631333939750655,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004620317934536239,
|
|
"loss": 6.3022,
|
|
"mean_token_accuracy": 0.1300494357943535,
|
|
"num_tokens": 39708064.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 6.541477823257447,
|
|
"epoch": 1.9636684680828296,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004620105370143112,
|
|
"loss": 6.183,
|
|
"mean_token_accuracy": 0.14265059381723405,
|
|
"num_tokens": 39718076.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 6.593139362335205,
|
|
"epoch": 1.9642035421905932,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004619892751750957,
|
|
"loss": 6.277,
|
|
"mean_token_accuracy": 0.13124811053276061,
|
|
"num_tokens": 39729532.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 6.664540815353393,
|
|
"epoch": 1.9647386162983573,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00046196800793659116,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.13447292596101762,
|
|
"num_tokens": 39740372.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 6.628764820098877,
|
|
"epoch": 1.9652736904061212,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004619467352994115,
|
|
"loss": 6.1547,
|
|
"mean_token_accuracy": 0.14195441901683808,
|
|
"num_tokens": 39751283.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 6.653083753585816,
|
|
"epoch": 1.965808764513885,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004619254572641712,
|
|
"loss": 6.371,
|
|
"mean_token_accuracy": 0.13150099590420722,
|
|
"num_tokens": 39763295.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 6.523511028289795,
|
|
"epoch": 1.9663438386216492,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00046190417383148465,
|
|
"loss": 6.2842,
|
|
"mean_token_accuracy": 0.13487935960292816,
|
|
"num_tokens": 39773849.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 6.449695491790772,
|
|
"epoch": 1.966878912729413,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004618828850019663,
|
|
"loss": 6.1015,
|
|
"mean_token_accuracy": 0.14321984872221946,
|
|
"num_tokens": 39784366.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 6.626819467544555,
|
|
"epoch": 1.967413986837177,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00046186159077623093,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.13259550407528878,
|
|
"num_tokens": 39794226.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 6.607760572433472,
|
|
"epoch": 1.9679490609449408,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004618402911548933,
|
|
"loss": 6.2428,
|
|
"mean_token_accuracy": 0.13623574674129485,
|
|
"num_tokens": 39805557.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 6.60635781288147,
|
|
"epoch": 1.9684841350527047,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004618189861385686,
|
|
"loss": 6.2321,
|
|
"mean_token_accuracy": 0.14006453901529312,
|
|
"num_tokens": 39816090.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 6.596402645111084,
|
|
"epoch": 1.9690192091604688,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004617976757278719,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.12973579317331313,
|
|
"num_tokens": 39826662.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 6.6736939430236815,
|
|
"epoch": 1.9695542832682327,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00046177635992341855,
|
|
"loss": 6.32,
|
|
"mean_token_accuracy": 0.12867724522948265,
|
|
"num_tokens": 39837805.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 6.678556060791015,
|
|
"epoch": 1.9700893573759966,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004617550387258241,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.12540676444768906,
|
|
"num_tokens": 39848052.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 6.650353050231933,
|
|
"epoch": 1.9706244314837607,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004617337121357041,
|
|
"loss": 6.3243,
|
|
"mean_token_accuracy": 0.13391705974936485,
|
|
"num_tokens": 39859448.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 6.626171684265136,
|
|
"epoch": 1.9711595055915243,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004617123801536744,
|
|
"loss": 6.2684,
|
|
"mean_token_accuracy": 0.13142177313566208,
|
|
"num_tokens": 39870053.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 6.635379076004028,
|
|
"epoch": 1.9716945796992884,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000461691042780351,
|
|
"loss": 6.3705,
|
|
"mean_token_accuracy": 0.1277768172323704,
|
|
"num_tokens": 39881547.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 6.606582403182983,
|
|
"epoch": 1.9722296538070523,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00046166970001635,
|
|
"loss": 6.3416,
|
|
"mean_token_accuracy": 0.13397602811455728,
|
|
"num_tokens": 39892974.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 6.6238696575164795,
|
|
"epoch": 1.9727647279148162,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046164835186228757,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.1359258197247982,
|
|
"num_tokens": 39904210.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 6.6285560131073,
|
|
"epoch": 1.9732998020225803,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00046162699831878026,
|
|
"loss": 6.2719,
|
|
"mean_token_accuracy": 0.13358834758400917,
|
|
"num_tokens": 39915464.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 6.609404230117798,
|
|
"epoch": 1.973834876130344,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004616056393864446,
|
|
"loss": 6.3159,
|
|
"mean_token_accuracy": 0.13424640744924546,
|
|
"num_tokens": 39927117.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 6.675488901138306,
|
|
"epoch": 1.974369950238108,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004615842750658972,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.13805598840117456,
|
|
"num_tokens": 39937363.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 6.571225547790528,
|
|
"epoch": 1.974905024345872,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004615629053577552,
|
|
"loss": 6.1757,
|
|
"mean_token_accuracy": 0.14515014737844467,
|
|
"num_tokens": 39948934.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 6.5612458229064945,
|
|
"epoch": 1.9754400984536358,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004615415302626355,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.13592228442430496,
|
|
"num_tokens": 39959435.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 6.611463117599487,
|
|
"epoch": 1.9759751725613999,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.00046152014978115535,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.1358589008450508,
|
|
"num_tokens": 39969006.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 6.607724380493164,
|
|
"epoch": 1.9765102466691635,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000461498763913932,
|
|
"loss": 6.2338,
|
|
"mean_token_accuracy": 0.13482216149568557,
|
|
"num_tokens": 39979264.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 6.697569465637207,
|
|
"epoch": 1.9770453207769276,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00046147737266158314,
|
|
"loss": 6.3937,
|
|
"mean_token_accuracy": 0.12744224742054938,
|
|
"num_tokens": 39989791.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 6.626405334472656,
|
|
"epoch": 1.9775803948846915,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004614559760247263,
|
|
"loss": 6.24,
|
|
"mean_token_accuracy": 0.13352037444710732,
|
|
"num_tokens": 39999591.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 6.5957612037658695,
|
|
"epoch": 1.9781154689924554,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004614345740039794,
|
|
"loss": 6.389,
|
|
"mean_token_accuracy": 0.1325157456099987,
|
|
"num_tokens": 40010811.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 6.6041535377502445,
|
|
"epoch": 1.9786505431002195,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00046141316659996037,
|
|
"loss": 6.331,
|
|
"mean_token_accuracy": 0.13099640011787414,
|
|
"num_tokens": 40022190.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 6.678543186187744,
|
|
"epoch": 1.9791856172079834,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.00046139175381328725,
|
|
"loss": 6.2893,
|
|
"mean_token_accuracy": 0.13157772794365882,
|
|
"num_tokens": 40033905.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 6.724796724319458,
|
|
"epoch": 1.9797206913157472,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004613703356445786,
|
|
"loss": 6.3604,
|
|
"mean_token_accuracy": 0.1307512827217579,
|
|
"num_tokens": 40044923.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 6.645975351333618,
|
|
"epoch": 1.9802557654235111,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004613489120944526,
|
|
"loss": 6.2569,
|
|
"mean_token_accuracy": 0.1349247321486473,
|
|
"num_tokens": 40054988.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 6.602586364746093,
|
|
"epoch": 1.980790839531275,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004613274831635279,
|
|
"loss": 6.3452,
|
|
"mean_token_accuracy": 0.12847888544201852,
|
|
"num_tokens": 40065565.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 6.6099285125732425,
|
|
"epoch": 1.981325913639039,
|
|
"grad_norm": 11.8125,
|
|
"learning_rate": 0.00046130604885242333,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.13375270441174508,
|
|
"num_tokens": 40076282.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 6.615926885604859,
|
|
"epoch": 1.981860987746803,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004612846091617578,
|
|
"loss": 6.2642,
|
|
"mean_token_accuracy": 0.14098501950502396,
|
|
"num_tokens": 40087546.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 6.6281575679779055,
|
|
"epoch": 1.9823960618545668,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004612631640921504,
|
|
"loss": 6.3348,
|
|
"mean_token_accuracy": 0.13378945663571357,
|
|
"num_tokens": 40097937.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 6.658842420578003,
|
|
"epoch": 1.982931135962331,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00046124171364422025,
|
|
"loss": 6.2887,
|
|
"mean_token_accuracy": 0.13760803490877152,
|
|
"num_tokens": 40108639.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 6.587354040145874,
|
|
"epoch": 1.9834662100700946,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004612202578185868,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.13681902587413788,
|
|
"num_tokens": 40119533.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 6.643749809265136,
|
|
"epoch": 1.9840012841778587,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004611987966158695,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.13220566660165786,
|
|
"num_tokens": 40131176.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 6.605323314666748,
|
|
"epoch": 1.9845363582856226,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046117733003668825,
|
|
"loss": 6.283,
|
|
"mean_token_accuracy": 0.13294972628355026,
|
|
"num_tokens": 40143293.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 6.607056427001953,
|
|
"epoch": 1.9850714323933865,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004611558580816628,
|
|
"loss": 6.2436,
|
|
"mean_token_accuracy": 0.130212265253067,
|
|
"num_tokens": 40155312.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 6.6404517650604244,
|
|
"epoch": 1.9856065065011506,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000461134380751413,
|
|
"loss": 6.2947,
|
|
"mean_token_accuracy": 0.1354106195271015,
|
|
"num_tokens": 40166261.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 6.593300628662109,
|
|
"epoch": 1.9861415806089142,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00046111289804655906,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.13961956650018692,
|
|
"num_tokens": 40176641.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 6.625611734390259,
|
|
"epoch": 1.9866766547166783,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004610914099677214,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.13404286056756973,
|
|
"num_tokens": 40187784.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 6.57705545425415,
|
|
"epoch": 1.9872117288244422,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004610699165155204,
|
|
"loss": 6.3237,
|
|
"mean_token_accuracy": 0.12904028967022896,
|
|
"num_tokens": 40198219.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 6.580019283294678,
|
|
"epoch": 1.987746802932206,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00046104841769057677,
|
|
"loss": 6.2947,
|
|
"mean_token_accuracy": 0.1307603269815445,
|
|
"num_tokens": 40208589.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 6.650794601440429,
|
|
"epoch": 1.9882818770399702,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004610269134935112,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.13587681204080582,
|
|
"num_tokens": 40219587.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 6.595871639251709,
|
|
"epoch": 1.9888169511477338,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004610054039249446,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.13774412199854852,
|
|
"num_tokens": 40230681.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 6.514229822158813,
|
|
"epoch": 1.989352025255498,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00046098388898549816,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.14184198081493377,
|
|
"num_tokens": 40241356.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 6.647546005249024,
|
|
"epoch": 1.9898870993632618,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00046096236867579306,
|
|
"loss": 6.29,
|
|
"mean_token_accuracy": 0.13567113801836966,
|
|
"num_tokens": 40251652.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 6.596577262878418,
|
|
"epoch": 1.9904221734710257,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00046094084299645065,
|
|
"loss": 6.2521,
|
|
"mean_token_accuracy": 0.12917528972029685,
|
|
"num_tokens": 40262819.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 6.567748403549194,
|
|
"epoch": 1.9909572475787898,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00046091931194809253,
|
|
"loss": 6.3495,
|
|
"mean_token_accuracy": 0.12601519823074342,
|
|
"num_tokens": 40274314.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 6.654333257675171,
|
|
"epoch": 1.9914923216865534,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004608977755313404,
|
|
"loss": 6.308,
|
|
"mean_token_accuracy": 0.13219375237822534,
|
|
"num_tokens": 40284733.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 6.594553136825562,
|
|
"epoch": 1.9920273957943175,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004608762337468162,
|
|
"loss": 6.2743,
|
|
"mean_token_accuracy": 0.13736194595694542,
|
|
"num_tokens": 40295484.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 6.607972860336304,
|
|
"epoch": 1.9925624699020814,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004608546865951418,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.13534663170576094,
|
|
"num_tokens": 40305470.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 6.666028213500977,
|
|
"epoch": 1.9930975440098453,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00046083313407693945,
|
|
"loss": 6.3767,
|
|
"mean_token_accuracy": 0.12920014038681985,
|
|
"num_tokens": 40316055.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 6.642501354217529,
|
|
"epoch": 1.9936326181176094,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004608115761928315,
|
|
"loss": 6.2715,
|
|
"mean_token_accuracy": 0.1358068458735943,
|
|
"num_tokens": 40326689.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 6.535877132415772,
|
|
"epoch": 1.9941676922253733,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00046079001294344036,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.13622386306524276,
|
|
"num_tokens": 40338511.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 6.594684410095215,
|
|
"epoch": 1.9947027663331371,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004607684443293887,
|
|
"loss": 6.2694,
|
|
"mean_token_accuracy": 0.12647117003798486,
|
|
"num_tokens": 40350395.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 6.645154142379761,
|
|
"epoch": 1.995237840440901,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004607468703512993,
|
|
"loss": 6.2547,
|
|
"mean_token_accuracy": 0.14212493151426314,
|
|
"num_tokens": 40360166.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 6.5726580142974855,
|
|
"epoch": 1.995772914548665,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.00046072529100979514,
|
|
"loss": 6.2956,
|
|
"mean_token_accuracy": 0.12961820885539055,
|
|
"num_tokens": 40370655.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 6.618028211593628,
|
|
"epoch": 1.996307988656429,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004607037063054993,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.1380405068397522,
|
|
"num_tokens": 40381502.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 6.708159780502319,
|
|
"epoch": 1.9968430627641929,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000460682116239035,
|
|
"loss": 6.3294,
|
|
"mean_token_accuracy": 0.12856414839625357,
|
|
"num_tokens": 40391815.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 6.614266347885132,
|
|
"epoch": 1.9973781368719568,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00046066052081102576,
|
|
"loss": 6.296,
|
|
"mean_token_accuracy": 0.13519723564386368,
|
|
"num_tokens": 40403306.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 6.603552770614624,
|
|
"epoch": 1.9979132109797209,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00046063892002209505,
|
|
"loss": 6.2329,
|
|
"mean_token_accuracy": 0.14253919571638107,
|
|
"num_tokens": 40414210.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 6.508784532546997,
|
|
"epoch": 1.9984482850874845,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004606173138728666,
|
|
"loss": 6.2335,
|
|
"mean_token_accuracy": 0.14333124309778214,
|
|
"num_tokens": 40424368.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 6.592488765716553,
|
|
"epoch": 1.9989833591952486,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004605957023639643,
|
|
"loss": 6.3106,
|
|
"mean_token_accuracy": 0.1314486160874367,
|
|
"num_tokens": 40436252.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 6.660682964324951,
|
|
"epoch": 1.9995184333030125,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00046057408549601223,
|
|
"loss": 6.2976,
|
|
"mean_token_accuracy": 0.13354944363236426,
|
|
"num_tokens": 40447256.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 6.6441013548109265,
|
|
"epoch": 2.0,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004605524632696344,
|
|
"loss": 6.2516,
|
|
"mean_token_accuracy": 0.13674567639827728,
|
|
"num_tokens": 40456516.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 6.627287721633911,
|
|
"epoch": 2.000535074107764,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004605308356854553,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.13583022654056548,
|
|
"num_tokens": 40467563.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 6.614476299285888,
|
|
"epoch": 2.0010701482155278,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004605092027440994,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.13973827064037322,
|
|
"num_tokens": 40478202.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 6.6228007793426515,
|
|
"epoch": 2.001605222323292,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004604875644461914,
|
|
"loss": 6.224,
|
|
"mean_token_accuracy": 0.13292253091931344,
|
|
"num_tokens": 40489677.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 6.597926664352417,
|
|
"epoch": 2.0021402964310555,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00046046592079235595,
|
|
"loss": 6.2529,
|
|
"mean_token_accuracy": 0.13624285608530046,
|
|
"num_tokens": 40500694.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 6.587586259841919,
|
|
"epoch": 2.0026753705388196,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004604442717832181,
|
|
"loss": 6.2255,
|
|
"mean_token_accuracy": 0.13825805783271788,
|
|
"num_tokens": 40511539.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 6.6088159561157225,
|
|
"epoch": 2.0032104446465837,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000460422617419403,
|
|
"loss": 6.2103,
|
|
"mean_token_accuracy": 0.13499139472842217,
|
|
"num_tokens": 40521906.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 6.61983470916748,
|
|
"epoch": 2.0037455187543474,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046040095770153594,
|
|
"loss": 6.2425,
|
|
"mean_token_accuracy": 0.1344665728509426,
|
|
"num_tokens": 40531454.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 6.659852933883667,
|
|
"epoch": 2.0042805928621115,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004603792926302422,
|
|
"loss": 6.2835,
|
|
"mean_token_accuracy": 0.13003234192728996,
|
|
"num_tokens": 40541497.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 6.671592426300049,
|
|
"epoch": 2.004815666969875,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004603576222061475,
|
|
"loss": 6.2758,
|
|
"mean_token_accuracy": 0.13341319784522057,
|
|
"num_tokens": 40552576.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 6.630139446258545,
|
|
"epoch": 2.005350741077639,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004603359464298774,
|
|
"loss": 6.2259,
|
|
"mean_token_accuracy": 0.13670521825551987,
|
|
"num_tokens": 40562906.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 6.561100625991822,
|
|
"epoch": 2.0058858151854033,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046031426530205796,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.1423003762960434,
|
|
"num_tokens": 40574510.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 6.490091133117676,
|
|
"epoch": 2.006420889293167,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004602925788233152,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.14576459154486657,
|
|
"num_tokens": 40586170.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 6.631974506378174,
|
|
"epoch": 2.006955963400931,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00046027088699427516,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.12929682210087776,
|
|
"num_tokens": 40597613.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 6.702176713943482,
|
|
"epoch": 2.007491037508695,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00046024918981556434,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.13489426597952842,
|
|
"num_tokens": 40608366.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 6.613981056213379,
|
|
"epoch": 2.008026111616459,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004602274872878092,
|
|
"loss": 6.2338,
|
|
"mean_token_accuracy": 0.138826072961092,
|
|
"num_tokens": 40618616.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 6.512788581848144,
|
|
"epoch": 2.008561185724223,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00046020577941163635,
|
|
"loss": 6.1176,
|
|
"mean_token_accuracy": 0.13982770442962647,
|
|
"num_tokens": 40628342.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 6.586994981765747,
|
|
"epoch": 2.0090962598319866,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00046018406618767273,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.13579508438706397,
|
|
"num_tokens": 40638644.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 6.579953908920288,
|
|
"epoch": 2.0096313339397507,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004601623476165451,
|
|
"loss": 6.2062,
|
|
"mean_token_accuracy": 0.14031298458576202,
|
|
"num_tokens": 40649945.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 6.644200325012207,
|
|
"epoch": 2.010166408047515,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00046014062369888084,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.1303163379430771,
|
|
"num_tokens": 40660896.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 6.667866802215576,
|
|
"epoch": 2.0107014821552784,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000460118894435307,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.1304280385375023,
|
|
"num_tokens": 40672072.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 6.6651770114898685,
|
|
"epoch": 2.0112365562630425,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004600971598264511,
|
|
"loss": 6.3174,
|
|
"mean_token_accuracy": 0.13128310069441795,
|
|
"num_tokens": 40682622.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 6.547537040710449,
|
|
"epoch": 2.011771630370806,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004600754198729407,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.13864753469824792,
|
|
"num_tokens": 40693127.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 6.588384389877319,
|
|
"epoch": 2.0123067044785703,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046005367457540366,
|
|
"loss": 6.2411,
|
|
"mean_token_accuracy": 0.13582852631807327,
|
|
"num_tokens": 40705009.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 6.6885009765625,
|
|
"epoch": 2.0128417785863344,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046003192393446763,
|
|
"loss": 6.2631,
|
|
"mean_token_accuracy": 0.1358159601688385,
|
|
"num_tokens": 40716498.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 6.650737190246582,
|
|
"epoch": 2.013376852694098,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004600101679507609,
|
|
"loss": 6.2412,
|
|
"mean_token_accuracy": 0.14250265657901764,
|
|
"num_tokens": 40727802.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 6.566486549377442,
|
|
"epoch": 2.013911926801862,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004599884066249115,
|
|
"loss": 6.2862,
|
|
"mean_token_accuracy": 0.1371168352663517,
|
|
"num_tokens": 40738866.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 6.6057147026062015,
|
|
"epoch": 2.014447000909626,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004599666399575479,
|
|
"loss": 6.2526,
|
|
"mean_token_accuracy": 0.13330088332295417,
|
|
"num_tokens": 40750214.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 6.64248218536377,
|
|
"epoch": 2.01498207501739,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004599448679492986,
|
|
"loss": 6.2329,
|
|
"mean_token_accuracy": 0.14242857918143273,
|
|
"num_tokens": 40759830.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 6.614819431304932,
|
|
"epoch": 2.015517149125154,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004599230906007921,
|
|
"loss": 6.2856,
|
|
"mean_token_accuracy": 0.13269748911261559,
|
|
"num_tokens": 40770007.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 6.58149561882019,
|
|
"epoch": 2.0160522232329177,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004599013079126575,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.13410270735621452,
|
|
"num_tokens": 40781495.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 6.666657876968384,
|
|
"epoch": 2.0165872973406818,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004598795198855235,
|
|
"loss": 6.1779,
|
|
"mean_token_accuracy": 0.13792298957705498,
|
|
"num_tokens": 40792875.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 6.6696741580963135,
|
|
"epoch": 2.0171223714484454,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004598577265200193,
|
|
"loss": 6.3084,
|
|
"mean_token_accuracy": 0.1269318588078022,
|
|
"num_tokens": 40804484.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 6.540780401229858,
|
|
"epoch": 2.0176574455562095,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004598359278167744,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.1362209364771843,
|
|
"num_tokens": 40814692.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 6.568814897537232,
|
|
"epoch": 2.0181925196639736,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00045981412377641795,
|
|
"loss": 6.1995,
|
|
"mean_token_accuracy": 0.139553514868021,
|
|
"num_tokens": 40825443.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 6.637061357498169,
|
|
"epoch": 2.0187275937717373,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00045979231439957966,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.13438811972737313,
|
|
"num_tokens": 40836699.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 6.63066987991333,
|
|
"epoch": 2.0192626678795014,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004597704996868893,
|
|
"loss": 6.245,
|
|
"mean_token_accuracy": 0.13515519946813584,
|
|
"num_tokens": 40846736.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 6.650888872146607,
|
|
"epoch": 2.019797741987265,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004597486796389766,
|
|
"loss": 6.3287,
|
|
"mean_token_accuracy": 0.13836793452501298,
|
|
"num_tokens": 40858362.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 6.611936330795288,
|
|
"epoch": 2.020332816095029,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00045972685425647186,
|
|
"loss": 6.241,
|
|
"mean_token_accuracy": 0.13694039285182952,
|
|
"num_tokens": 40869346.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 6.6427289009094235,
|
|
"epoch": 2.0208678902027932,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004597050235400051,
|
|
"loss": 6.322,
|
|
"mean_token_accuracy": 0.13093021884560585,
|
|
"num_tokens": 40880003.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 6.668729305267334,
|
|
"epoch": 2.021402964310557,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00045968318749020675,
|
|
"loss": 6.2614,
|
|
"mean_token_accuracy": 0.1340502120554447,
|
|
"num_tokens": 40891515.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 6.626113748550415,
|
|
"epoch": 2.021938038418321,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004596613461077073,
|
|
"loss": 6.2307,
|
|
"mean_token_accuracy": 0.13299428075551986,
|
|
"num_tokens": 40902024.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 6.583237934112549,
|
|
"epoch": 2.022473112526085,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00045963949939313754,
|
|
"loss": 6.2284,
|
|
"mean_token_accuracy": 0.13834994807839393,
|
|
"num_tokens": 40912160.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 6.621576118469238,
|
|
"epoch": 2.0230081866338487,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000459617647347128,
|
|
"loss": 6.2944,
|
|
"mean_token_accuracy": 0.12755901068449021,
|
|
"num_tokens": 40922516.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 6.580006456375122,
|
|
"epoch": 2.023543260741613,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.00045959578997031,
|
|
"loss": 6.2899,
|
|
"mean_token_accuracy": 0.12750839069485664,
|
|
"num_tokens": 40934148.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 6.686640644073487,
|
|
"epoch": 2.0240783348493765,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00045957392726331443,
|
|
"loss": 6.2247,
|
|
"mean_token_accuracy": 0.1364900916814804,
|
|
"num_tokens": 40944409.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 6.661095190048218,
|
|
"epoch": 2.0246134089571406,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00045955205922677264,
|
|
"loss": 6.2689,
|
|
"mean_token_accuracy": 0.1354162074625492,
|
|
"num_tokens": 40955133.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 6.644590425491333,
|
|
"epoch": 2.0251484830649047,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004595301858613161,
|
|
"loss": 6.3392,
|
|
"mean_token_accuracy": 0.13647802770137787,
|
|
"num_tokens": 40965508.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 6.658960390090942,
|
|
"epoch": 2.0256835571726683,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004595083071675763,
|
|
"loss": 6.3052,
|
|
"mean_token_accuracy": 0.1384161077439785,
|
|
"num_tokens": 40975931.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 6.631773185729981,
|
|
"epoch": 2.0262186312804324,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00045948642314618514,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.13521615862846376,
|
|
"num_tokens": 40985797.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 6.550546264648437,
|
|
"epoch": 2.026753705388196,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004594645337977744,
|
|
"loss": 6.2508,
|
|
"mean_token_accuracy": 0.13349076136946678,
|
|
"num_tokens": 40996501.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 6.585389471054077,
|
|
"epoch": 2.02728877949596,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004594426391229762,
|
|
"loss": 6.2326,
|
|
"mean_token_accuracy": 0.13476013168692588,
|
|
"num_tokens": 41005970.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 6.568695974349976,
|
|
"epoch": 2.0278238536037243,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004594207391224227,
|
|
"loss": 6.2015,
|
|
"mean_token_accuracy": 0.13638953641057014,
|
|
"num_tokens": 41017208.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 6.6429369926452635,
|
|
"epoch": 2.028358927711488,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00045939883379674624,
|
|
"loss": 6.3636,
|
|
"mean_token_accuracy": 0.1305374749004841,
|
|
"num_tokens": 41028435.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 6.627215051651001,
|
|
"epoch": 2.028894001819252,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00045937692314657936,
|
|
"loss": 6.2416,
|
|
"mean_token_accuracy": 0.1376147210597992,
|
|
"num_tokens": 41039256.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 6.630423593521118,
|
|
"epoch": 2.0294290759270157,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004593550071725548,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.13307126015424728,
|
|
"num_tokens": 41050527.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 6.6238585948944095,
|
|
"epoch": 2.02996415003478,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00045933308587530527,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.13456388637423516,
|
|
"num_tokens": 41062259.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 6.580452966690063,
|
|
"epoch": 2.030499224142544,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004593111592554638,
|
|
"loss": 6.2883,
|
|
"mean_token_accuracy": 0.13668508902192117,
|
|
"num_tokens": 41073011.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 6.556156349182129,
|
|
"epoch": 2.0310342982503076,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004592892273136635,
|
|
"loss": 6.1886,
|
|
"mean_token_accuracy": 0.14138735383749007,
|
|
"num_tokens": 41083482.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 6.5967793464660645,
|
|
"epoch": 2.0315693723580717,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00045926729005053764,
|
|
"loss": 6.2183,
|
|
"mean_token_accuracy": 0.14028257727622986,
|
|
"num_tokens": 41094028.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 6.592178678512573,
|
|
"epoch": 2.0321044464658353,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004592453474667197,
|
|
"loss": 6.2261,
|
|
"mean_token_accuracy": 0.13519903272390366,
|
|
"num_tokens": 41106346.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 6.648704385757446,
|
|
"epoch": 2.0326395205735994,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004592233995628432,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.1365912824869156,
|
|
"num_tokens": 41116130.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 6.571787309646607,
|
|
"epoch": 2.0331745946813635,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000459201446339542,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.14098722264170646,
|
|
"num_tokens": 41127103.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 6.541314029693604,
|
|
"epoch": 2.033709668789127,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004591794877974499,
|
|
"loss": 6.2238,
|
|
"mean_token_accuracy": 0.133497653901577,
|
|
"num_tokens": 41138258.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 6.636067342758179,
|
|
"epoch": 2.0342447428968913,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00045915752393720094,
|
|
"loss": 6.26,
|
|
"mean_token_accuracy": 0.13875531330704688,
|
|
"num_tokens": 41148859.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 6.59470567703247,
|
|
"epoch": 2.034779817004655,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00045913555475942937,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.13544606417417526,
|
|
"num_tokens": 41158614.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 6.563582181930542,
|
|
"epoch": 2.035314891112419,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004591135802647695,
|
|
"loss": 6.2404,
|
|
"mean_token_accuracy": 0.14283828511834146,
|
|
"num_tokens": 41170215.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 6.595398044586181,
|
|
"epoch": 2.035849965220183,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004590916004538559,
|
|
"loss": 6.2309,
|
|
"mean_token_accuracy": 0.1368607796728611,
|
|
"num_tokens": 41180784.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 6.6088591575622555,
|
|
"epoch": 2.036385039327947,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.00045906961532732316,
|
|
"loss": 6.257,
|
|
"mean_token_accuracy": 0.13261247649788857,
|
|
"num_tokens": 41191305.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 6.623996162414551,
|
|
"epoch": 2.036920113435711,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004590476248858062,
|
|
"loss": 6.2846,
|
|
"mean_token_accuracy": 0.13123485520482064,
|
|
"num_tokens": 41202388.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 6.5996400833129885,
|
|
"epoch": 2.037455187543475,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004590256291299399,
|
|
"loss": 6.2246,
|
|
"mean_token_accuracy": 0.13849703818559647,
|
|
"num_tokens": 41212136.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 6.589424467086792,
|
|
"epoch": 2.0379902616512386,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00045900362806035945,
|
|
"loss": 6.2583,
|
|
"mean_token_accuracy": 0.13227000907063485,
|
|
"num_tokens": 41223390.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 6.580247163772583,
|
|
"epoch": 2.0385253357590027,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00045898162167770006,
|
|
"loss": 6.2814,
|
|
"mean_token_accuracy": 0.1399260088801384,
|
|
"num_tokens": 41234775.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 6.5931233882904055,
|
|
"epoch": 2.0390604098667664,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004589596099825973,
|
|
"loss": 6.2167,
|
|
"mean_token_accuracy": 0.13984185308218003,
|
|
"num_tokens": 41245627.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 6.595823574066162,
|
|
"epoch": 2.0395954839745305,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00045893759297568654,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.13242710381746292,
|
|
"num_tokens": 41255441.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 6.545255136489868,
|
|
"epoch": 2.0401305580822946,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004589155706576036,
|
|
"loss": 6.196,
|
|
"mean_token_accuracy": 0.1331594817340374,
|
|
"num_tokens": 41268686.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 6.68111400604248,
|
|
"epoch": 2.0406656321900583,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00045889354302898445,
|
|
"loss": 6.2967,
|
|
"mean_token_accuracy": 0.13213636800646783,
|
|
"num_tokens": 41279384.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 6.6709002494812015,
|
|
"epoch": 2.0412007062978224,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004588715100904651,
|
|
"loss": 6.291,
|
|
"mean_token_accuracy": 0.12930534034967422,
|
|
"num_tokens": 41289923.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 6.540483999252319,
|
|
"epoch": 2.041735780405586,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004588494718426818,
|
|
"loss": 6.2217,
|
|
"mean_token_accuracy": 0.14160189405083656,
|
|
"num_tokens": 41300486.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 6.5193297386169435,
|
|
"epoch": 2.04227085451335,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004588274282862708,
|
|
"loss": 6.1944,
|
|
"mean_token_accuracy": 0.1371292568743229,
|
|
"num_tokens": 41310507.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 6.611303043365479,
|
|
"epoch": 2.042805928621114,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00045880537942186855,
|
|
"loss": 6.2516,
|
|
"mean_token_accuracy": 0.1415947675704956,
|
|
"num_tokens": 41321284.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 6.578255558013916,
|
|
"epoch": 2.043341002728878,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004587833252501118,
|
|
"loss": 6.1688,
|
|
"mean_token_accuracy": 0.1430806778371334,
|
|
"num_tokens": 41332037.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 6.530525064468383,
|
|
"epoch": 2.043876076836642,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004587612657716374,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.13531340211629866,
|
|
"num_tokens": 41343480.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 6.646954679489136,
|
|
"epoch": 2.0444111509444056,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004587392009870824,
|
|
"loss": 6.2756,
|
|
"mean_token_accuracy": 0.13181781023740768,
|
|
"num_tokens": 41353656.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 6.634633016586304,
|
|
"epoch": 2.0449462250521697,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004587171308970836,
|
|
"loss": 6.2211,
|
|
"mean_token_accuracy": 0.1344899781048298,
|
|
"num_tokens": 41363640.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 6.646233654022216,
|
|
"epoch": 2.045481299159934,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00045869505550227857,
|
|
"loss": 6.2446,
|
|
"mean_token_accuracy": 0.13082142993807794,
|
|
"num_tokens": 41374194.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 6.627936363220215,
|
|
"epoch": 2.0460163732676975,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004586729748033046,
|
|
"loss": 6.2229,
|
|
"mean_token_accuracy": 0.14047310501337051,
|
|
"num_tokens": 41384968.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 6.605069875717163,
|
|
"epoch": 2.0465514473754616,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00045865088880079924,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.14400119036436082,
|
|
"num_tokens": 41395117.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 6.584554386138916,
|
|
"epoch": 2.0470865214832252,
|
|
"grad_norm": 7.25,
|
|
"learning_rate": 0.0004586287974954004,
|
|
"loss": 6.2484,
|
|
"mean_token_accuracy": 0.13384103029966354,
|
|
"num_tokens": 41406366.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 6.648293399810791,
|
|
"epoch": 2.0476215955909893,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004586067008877457,
|
|
"loss": 6.2498,
|
|
"mean_token_accuracy": 0.13591982871294023,
|
|
"num_tokens": 41417388.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 6.58433837890625,
|
|
"epoch": 2.0481566696987534,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004585845989784734,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.13956477865576744,
|
|
"num_tokens": 41428085.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 6.634393739700317,
|
|
"epoch": 2.048691743806517,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00045856249176822155,
|
|
"loss": 6.2949,
|
|
"mean_token_accuracy": 0.13241263329982758,
|
|
"num_tokens": 41439117.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 6.5859733581542965,
|
|
"epoch": 2.049226817914281,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00045854037925762857,
|
|
"loss": 6.266,
|
|
"mean_token_accuracy": 0.13188693076372146,
|
|
"num_tokens": 41450042.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 6.607028865814209,
|
|
"epoch": 2.049761892022045,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00045851826144733296,
|
|
"loss": 6.1676,
|
|
"mean_token_accuracy": 0.1433619126677513,
|
|
"num_tokens": 41460554.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 6.67827525138855,
|
|
"epoch": 2.050296966129809,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00045849613833797326,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.13457248210906983,
|
|
"num_tokens": 41471403.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 6.619464588165283,
|
|
"epoch": 2.050832040237573,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00045847400993018835,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.13308603912591935,
|
|
"num_tokens": 41482098.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 6.579060792922974,
|
|
"epoch": 2.0513671143453367,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00045845187622461724,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.13776277974247933,
|
|
"num_tokens": 41493126.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 6.6635666847229,
|
|
"epoch": 2.051902188453101,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000458429737221899,
|
|
"loss": 6.337,
|
|
"mean_token_accuracy": 0.1318577580153942,
|
|
"num_tokens": 41504242.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 6.611014318466187,
|
|
"epoch": 2.052437262560865,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004584075929226728,
|
|
"loss": 6.2363,
|
|
"mean_token_accuracy": 0.1369643911719322,
|
|
"num_tokens": 41515368.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 6.573815107345581,
|
|
"epoch": 2.0529723366686286,
|
|
"grad_norm": 5.21875,
|
|
"learning_rate": 0.0004583854433275782,
|
|
"loss": 6.2615,
|
|
"mean_token_accuracy": 0.13503768816590309,
|
|
"num_tokens": 41525939.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 6.566453838348389,
|
|
"epoch": 2.0535074107763926,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00045836328843725465,
|
|
"loss": 6.2925,
|
|
"mean_token_accuracy": 0.1302167408168316,
|
|
"num_tokens": 41536505.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 6.603198719024658,
|
|
"epoch": 2.0540424848841563,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045834112825234193,
|
|
"loss": 6.2046,
|
|
"mean_token_accuracy": 0.13947994485497475,
|
|
"num_tokens": 41546293.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 6.607600545883178,
|
|
"epoch": 2.0545775589919204,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00045831896277347985,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.13982907459139823,
|
|
"num_tokens": 41556596.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 6.6009012222290036,
|
|
"epoch": 2.0551126330996845,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004582967920013085,
|
|
"loss": 6.2602,
|
|
"mean_token_accuracy": 0.13696323409676553,
|
|
"num_tokens": 41566732.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 6.607040929794311,
|
|
"epoch": 2.055647707207448,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00045827461593646806,
|
|
"loss": 6.2694,
|
|
"mean_token_accuracy": 0.13118503615260124,
|
|
"num_tokens": 41577777.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 6.606495761871338,
|
|
"epoch": 2.0561827813152123,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004582524345795989,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.1392368994653225,
|
|
"num_tokens": 41587978.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 6.593067264556884,
|
|
"epoch": 2.056717855422976,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004582302479313413,
|
|
"loss": 6.22,
|
|
"mean_token_accuracy": 0.1374417893588543,
|
|
"num_tokens": 41598977.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 6.621930980682373,
|
|
"epoch": 2.05725292953074,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004582080559923362,
|
|
"loss": 6.2737,
|
|
"mean_token_accuracy": 0.1264662839472294,
|
|
"num_tokens": 41609664.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 6.6291344165802,
|
|
"epoch": 2.057788003638504,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004581858587632241,
|
|
"loss": 6.2723,
|
|
"mean_token_accuracy": 0.13098785355687143,
|
|
"num_tokens": 41619427.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 6.631173801422119,
|
|
"epoch": 2.0583230777462678,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004581636562446461,
|
|
"loss": 6.2472,
|
|
"mean_token_accuracy": 0.13138061687350272,
|
|
"num_tokens": 41629551.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 6.595761394500732,
|
|
"epoch": 2.058858151854032,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004581414484372433,
|
|
"loss": 6.2614,
|
|
"mean_token_accuracy": 0.13145191147923468,
|
|
"num_tokens": 41640183.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 6.582157182693481,
|
|
"epoch": 2.0593932259617955,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004581192353416569,
|
|
"loss": 6.2488,
|
|
"mean_token_accuracy": 0.13547784984111785,
|
|
"num_tokens": 41651934.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 6.505010938644409,
|
|
"epoch": 2.0599283000695596,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004580970169585283,
|
|
"loss": 6.1283,
|
|
"mean_token_accuracy": 0.15469877794384956,
|
|
"num_tokens": 41662418.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 6.511779165267944,
|
|
"epoch": 2.0604633741773237,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00045807479328849906,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.13851948082447052,
|
|
"num_tokens": 41673419.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 6.538329458236694,
|
|
"epoch": 2.0609984482850874,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00045805256433221087,
|
|
"loss": 6.1779,
|
|
"mean_token_accuracy": 0.14701486378908157,
|
|
"num_tokens": 41684132.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 6.621984672546387,
|
|
"epoch": 2.0615335223928515,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004580303300903056,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.13402581289410592,
|
|
"num_tokens": 41695051.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 6.658152914047241,
|
|
"epoch": 2.062068596500615,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00045800809056342534,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.13628610074520112,
|
|
"num_tokens": 41705986.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 6.643789196014405,
|
|
"epoch": 2.0626036706083792,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00045798584575221213,
|
|
"loss": 6.2706,
|
|
"mean_token_accuracy": 0.13433527573943138,
|
|
"num_tokens": 41717082.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 6.636149454116821,
|
|
"epoch": 2.0631387447161433,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004579635956573084,
|
|
"loss": 6.282,
|
|
"mean_token_accuracy": 0.13608639687299728,
|
|
"num_tokens": 41728783.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 6.574067783355713,
|
|
"epoch": 2.063673818823907,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.00045794134027935646,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.13533465266227723,
|
|
"num_tokens": 41740452.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 6.6245763301849365,
|
|
"epoch": 2.064208892931671,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004579190796189991,
|
|
"loss": 6.2116,
|
|
"mean_token_accuracy": 0.14122342318296432,
|
|
"num_tokens": 41750966.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 6.636345052719117,
|
|
"epoch": 2.064743967039435,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000457896813676879,
|
|
"loss": 6.1933,
|
|
"mean_token_accuracy": 0.13933002799749375,
|
|
"num_tokens": 41762174.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 6.587269926071167,
|
|
"epoch": 2.065279041147199,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00045787454245363907,
|
|
"loss": 6.3015,
|
|
"mean_token_accuracy": 0.1271741971373558,
|
|
"num_tokens": 41773396.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 6.572438669204712,
|
|
"epoch": 2.065814115254963,
|
|
"grad_norm": 5.625,
|
|
"learning_rate": 0.0004578522659499225,
|
|
"loss": 6.2453,
|
|
"mean_token_accuracy": 0.1405311867594719,
|
|
"num_tokens": 41783833.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 6.552950239181518,
|
|
"epoch": 2.0663491893627266,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00045782998416637235,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.1436617910861969,
|
|
"num_tokens": 41795363.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 6.651199913024902,
|
|
"epoch": 2.0668842634704907,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004578076971036321,
|
|
"loss": 6.2798,
|
|
"mean_token_accuracy": 0.1340879701077938,
|
|
"num_tokens": 41807575.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 6.560057926177978,
|
|
"epoch": 2.067419337578255,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004577854047623454,
|
|
"loss": 6.1932,
|
|
"mean_token_accuracy": 0.13973165452480316,
|
|
"num_tokens": 41818496.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 6.6407918453216555,
|
|
"epoch": 2.0679544116860185,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004577631071431557,
|
|
"loss": 6.2244,
|
|
"mean_token_accuracy": 0.13823178708553313,
|
|
"num_tokens": 41829106.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 6.568043804168701,
|
|
"epoch": 2.0684894857937826,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00045774080424670704,
|
|
"loss": 6.1956,
|
|
"mean_token_accuracy": 0.14299218654632567,
|
|
"num_tokens": 41838095.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 6.536950588226318,
|
|
"epoch": 2.069024559901546,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004577184960736433,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.12904291599988937,
|
|
"num_tokens": 41847980.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 6.6340498447418215,
|
|
"epoch": 2.0695596340093103,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00045769618262460864,
|
|
"loss": 6.2782,
|
|
"mean_token_accuracy": 0.13629768863320352,
|
|
"num_tokens": 41858625.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 6.632993555068969,
|
|
"epoch": 2.0700947081170744,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004576738639002475,
|
|
"loss": 6.2615,
|
|
"mean_token_accuracy": 0.13038470819592476,
|
|
"num_tokens": 41870939.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 6.648717927932739,
|
|
"epoch": 2.070629782224838,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004576515399012041,
|
|
"loss": 6.3021,
|
|
"mean_token_accuracy": 0.13237005323171616,
|
|
"num_tokens": 41882356.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 6.589583539962769,
|
|
"epoch": 2.071164856332602,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004576292106281231,
|
|
"loss": 6.2623,
|
|
"mean_token_accuracy": 0.1374188743531704,
|
|
"num_tokens": 41892306.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 6.604954624176026,
|
|
"epoch": 2.071699930440366,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00045760687608164933,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.13321260511875152,
|
|
"num_tokens": 41902450.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 6.563578987121582,
|
|
"epoch": 2.07223500454813,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004575845362624278,
|
|
"loss": 6.22,
|
|
"mean_token_accuracy": 0.138578549772501,
|
|
"num_tokens": 41913319.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 6.618473720550537,
|
|
"epoch": 2.072770078655894,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00045756219117110337,
|
|
"loss": 6.2505,
|
|
"mean_token_accuracy": 0.13525751903653144,
|
|
"num_tokens": 41923598.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 6.63307409286499,
|
|
"epoch": 2.0733051527636577,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00045753984080832127,
|
|
"loss": 6.2457,
|
|
"mean_token_accuracy": 0.13612314388155938,
|
|
"num_tokens": 41934482.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 6.6050714492797855,
|
|
"epoch": 2.0738402268714218,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000457517485174727,
|
|
"loss": 6.2188,
|
|
"mean_token_accuracy": 0.12968629747629165,
|
|
"num_tokens": 41945994.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 6.643345069885254,
|
|
"epoch": 2.0743753009791854,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045749512427096595,
|
|
"loss": 6.2601,
|
|
"mean_token_accuracy": 0.13657110780477524,
|
|
"num_tokens": 41956564.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 6.5427813053131105,
|
|
"epoch": 2.0749103750869495,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045747275809768386,
|
|
"loss": 6.2384,
|
|
"mean_token_accuracy": 0.1406050868332386,
|
|
"num_tokens": 41966847.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 6.608779239654541,
|
|
"epoch": 2.0754454491947136,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004574503866555265,
|
|
"loss": 6.2974,
|
|
"mean_token_accuracy": 0.1283829130232334,
|
|
"num_tokens": 41977752.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 6.618145513534546,
|
|
"epoch": 2.0759805233024773,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045742800994513983,
|
|
"loss": 6.2482,
|
|
"mean_token_accuracy": 0.1395014278590679,
|
|
"num_tokens": 41987837.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 6.594688796997071,
|
|
"epoch": 2.0765155974102414,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00045740562796717005,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.13240207657217978,
|
|
"num_tokens": 41997988.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 6.503649282455444,
|
|
"epoch": 2.077050671518005,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004573832407222634,
|
|
"loss": 6.1679,
|
|
"mean_token_accuracy": 0.14166393727064133,
|
|
"num_tokens": 42009643.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 6.604776906967163,
|
|
"epoch": 2.077585745625769,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004573608482110663,
|
|
"loss": 6.2278,
|
|
"mean_token_accuracy": 0.1366498164832592,
|
|
"num_tokens": 42019972.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 6.6183586597442625,
|
|
"epoch": 2.0781208197335332,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00045733845043422535,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.141374521702528,
|
|
"num_tokens": 42030536.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 6.5975884914398195,
|
|
"epoch": 2.078655893841297,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004573160473923872,
|
|
"loss": 6.2216,
|
|
"mean_token_accuracy": 0.13035545796155928,
|
|
"num_tokens": 42041217.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 6.4605405807495115,
|
|
"epoch": 2.079190967949061,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004572936390861988,
|
|
"loss": 6.124,
|
|
"mean_token_accuracy": 0.13937411829829216,
|
|
"num_tokens": 42051346.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 6.694436836242676,
|
|
"epoch": 2.0797260420568247,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004572712255163072,
|
|
"loss": 6.3084,
|
|
"mean_token_accuracy": 0.13127609714865685,
|
|
"num_tokens": 42062718.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 6.640197038650513,
|
|
"epoch": 2.0802611161645888,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004572488066833596,
|
|
"loss": 6.2165,
|
|
"mean_token_accuracy": 0.13187195137143135,
|
|
"num_tokens": 42073587.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 6.614070463180542,
|
|
"epoch": 2.080796190272353,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00045722638258800335,
|
|
"loss": 6.2508,
|
|
"mean_token_accuracy": 0.14042752087116242,
|
|
"num_tokens": 42083763.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 6.5697469234466555,
|
|
"epoch": 2.0813312643801165,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004572039532308858,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.13458342626690864,
|
|
"num_tokens": 42094062.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 6.596635246276856,
|
|
"epoch": 2.0818663384878806,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004571815186126549,
|
|
"loss": 6.2687,
|
|
"mean_token_accuracy": 0.1320091664791107,
|
|
"num_tokens": 42106136.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 6.604555892944336,
|
|
"epoch": 2.0824014125956447,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00045715907873395805,
|
|
"loss": 6.2596,
|
|
"mean_token_accuracy": 0.128982724994421,
|
|
"num_tokens": 42116309.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 6.564693450927734,
|
|
"epoch": 2.0829364867034084,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004571366335954435,
|
|
"loss": 6.2735,
|
|
"mean_token_accuracy": 0.13488733246922494,
|
|
"num_tokens": 42127747.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 6.536147499084473,
|
|
"epoch": 2.0834715608111725,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004571141831977592,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.1493422731757164,
|
|
"num_tokens": 42137992.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 6.632700252532959,
|
|
"epoch": 2.084006634918936,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004570917275415535,
|
|
"loss": 6.1794,
|
|
"mean_token_accuracy": 0.13866008520126344,
|
|
"num_tokens": 42148833.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 6.518670463562012,
|
|
"epoch": 2.0845417090267,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004570692666274747,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.14080480113625526,
|
|
"num_tokens": 42159276.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 6.6284136295318605,
|
|
"epoch": 2.0850767831344643,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004570468004561715,
|
|
"loss": 6.2976,
|
|
"mean_token_accuracy": 0.13880984336137772,
|
|
"num_tokens": 42171541.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 6.621776866912842,
|
|
"epoch": 2.085611857242228,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00045702432902829245,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.1405622258782387,
|
|
"num_tokens": 42182888.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 6.585399866104126,
|
|
"epoch": 2.086146931349992,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004570018523444865,
|
|
"loss": 6.1823,
|
|
"mean_token_accuracy": 0.14482903108000755,
|
|
"num_tokens": 42193405.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 6.596245956420899,
|
|
"epoch": 2.0866820054577557,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045697937040540263,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.13755371049046516,
|
|
"num_tokens": 42203355.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 6.558695697784424,
|
|
"epoch": 2.08721707956552,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045695688321169,
|
|
"loss": 6.2248,
|
|
"mean_token_accuracy": 0.12791117504239083,
|
|
"num_tokens": 42213191.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 6.593454265594483,
|
|
"epoch": 2.087752153673284,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00045693439076399797,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.13074761480093003,
|
|
"num_tokens": 42223357.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 6.6586517810821535,
|
|
"epoch": 2.0882872277810476,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00045691189306297595,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.13833891823887826,
|
|
"num_tokens": 42234917.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 6.659210824966431,
|
|
"epoch": 2.0888223018888117,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045688939010927353,
|
|
"loss": 6.2866,
|
|
"mean_token_accuracy": 0.13251255974173545,
|
|
"num_tokens": 42245977.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 6.573454570770264,
|
|
"epoch": 2.0893573759965753,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004568668819035406,
|
|
"loss": 6.2218,
|
|
"mean_token_accuracy": 0.13001953214406967,
|
|
"num_tokens": 42257523.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 6.666018342971801,
|
|
"epoch": 2.0898924501043394,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00045684436844642694,
|
|
"loss": 6.2683,
|
|
"mean_token_accuracy": 0.1347210392355919,
|
|
"num_tokens": 42267727.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 6.667880296707153,
|
|
"epoch": 2.0904275242121035,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004568218497385828,
|
|
"loss": 6.2332,
|
|
"mean_token_accuracy": 0.13361469358205796,
|
|
"num_tokens": 42278201.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 6.64308500289917,
|
|
"epoch": 2.090962598319867,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004567993257806582,
|
|
"loss": 6.3148,
|
|
"mean_token_accuracy": 0.13311177492141724,
|
|
"num_tokens": 42288695.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 6.602832365036011,
|
|
"epoch": 2.0914976724276313,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004567767965733036,
|
|
"loss": 6.3136,
|
|
"mean_token_accuracy": 0.13641746193170548,
|
|
"num_tokens": 42299418.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 6.580172348022461,
|
|
"epoch": 2.092032746535395,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00045675426211716963,
|
|
"loss": 6.1891,
|
|
"mean_token_accuracy": 0.1353619709610939,
|
|
"num_tokens": 42310901.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 6.671511650085449,
|
|
"epoch": 2.092567820643159,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004567317224129069,
|
|
"loss": 6.1978,
|
|
"mean_token_accuracy": 0.1423824317753315,
|
|
"num_tokens": 42320055.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 6.635959959030151,
|
|
"epoch": 2.093102894750923,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004567091774611661,
|
|
"loss": 6.3443,
|
|
"mean_token_accuracy": 0.13496016785502435,
|
|
"num_tokens": 42330393.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 6.537560749053955,
|
|
"epoch": 2.093637968858687,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.00045668662726259846,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.1394476994872093,
|
|
"num_tokens": 42341384.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 6.595864248275757,
|
|
"epoch": 2.094173042966451,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00045666407181785496,
|
|
"loss": 6.1716,
|
|
"mean_token_accuracy": 0.14574610367417334,
|
|
"num_tokens": 42352351.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 6.505797719955444,
|
|
"epoch": 2.094708117074215,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004566415111275869,
|
|
"loss": 6.1845,
|
|
"mean_token_accuracy": 0.13964219242334366,
|
|
"num_tokens": 42363912.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 6.568895387649536,
|
|
"epoch": 2.0952431911819787,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004566189451924457,
|
|
"loss": 6.2532,
|
|
"mean_token_accuracy": 0.1361321896314621,
|
|
"num_tokens": 42374638.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 6.547950792312622,
|
|
"epoch": 2.0957782652897428,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045659637401308296,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.14705153554677963,
|
|
"num_tokens": 42385976.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 6.6166352272033695,
|
|
"epoch": 2.0963133393975064,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004565737975901505,
|
|
"loss": 6.2421,
|
|
"mean_token_accuracy": 0.13263367787003516,
|
|
"num_tokens": 42395714.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 6.577794313430786,
|
|
"epoch": 2.0968484135052705,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004565512159243001,
|
|
"loss": 6.159,
|
|
"mean_token_accuracy": 0.14172261357307434,
|
|
"num_tokens": 42406027.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 6.628651762008667,
|
|
"epoch": 2.0973834876130346,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004565286290161839,
|
|
"loss": 6.2959,
|
|
"mean_token_accuracy": 0.129336217045784,
|
|
"num_tokens": 42417756.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 6.659178161621094,
|
|
"epoch": 2.0979185617207983,
|
|
"grad_norm": 4.75,
|
|
"learning_rate": 0.00045650603686645403,
|
|
"loss": 6.2898,
|
|
"mean_token_accuracy": 0.13429513275623323,
|
|
"num_tokens": 42429321.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 6.575289869308472,
|
|
"epoch": 2.0984536358285624,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045648343947576284,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.14917002767324447,
|
|
"num_tokens": 42440003.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 6.638622379302978,
|
|
"epoch": 2.098988709936326,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004564608368447628,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.13776830360293388,
|
|
"num_tokens": 42450743.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 6.525564575195313,
|
|
"epoch": 2.09952378404409,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004564382289741067,
|
|
"loss": 6.2397,
|
|
"mean_token_accuracy": 0.13522262647747993,
|
|
"num_tokens": 42460885.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 6.547997379302979,
|
|
"epoch": 2.1000588581518542,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00045641561586444706,
|
|
"loss": 6.2177,
|
|
"mean_token_accuracy": 0.1409442350268364,
|
|
"num_tokens": 42470854.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 6.542618083953857,
|
|
"epoch": 2.100593932259618,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00045639299751643714,
|
|
"loss": 6.2817,
|
|
"mean_token_accuracy": 0.1311788462102413,
|
|
"num_tokens": 42482392.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 6.638660955429077,
|
|
"epoch": 2.101129006367382,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00045637037393072996,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.1298483803868294,
|
|
"num_tokens": 42494156.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 6.586408090591431,
|
|
"epoch": 2.1016640804751456,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004563477451079786,
|
|
"loss": 6.2377,
|
|
"mean_token_accuracy": 0.1400507554411888,
|
|
"num_tokens": 42505185.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 6.5411529541015625,
|
|
"epoch": 2.1021991545829097,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00045632511104883657,
|
|
"loss": 6.1912,
|
|
"mean_token_accuracy": 0.13459663912653924,
|
|
"num_tokens": 42516415.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 6.63468599319458,
|
|
"epoch": 2.102734228690674,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004563024717539575,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.1398872308433056,
|
|
"num_tokens": 42526945.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 6.668132162094116,
|
|
"epoch": 2.1032693027984375,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00045627982722399506,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.13298046886920928,
|
|
"num_tokens": 42537629.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 6.52944712638855,
|
|
"epoch": 2.1038043769062016,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00045625717745960306,
|
|
"loss": 6.2478,
|
|
"mean_token_accuracy": 0.14338910356163978,
|
|
"num_tokens": 42547952.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 6.540002727508545,
|
|
"epoch": 2.1043394510139652,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045623452246143547,
|
|
"loss": 6.2194,
|
|
"mean_token_accuracy": 0.13670600950717926,
|
|
"num_tokens": 42559026.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 6.639871120452881,
|
|
"epoch": 2.1048745251217293,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004562118622301466,
|
|
"loss": 6.2898,
|
|
"mean_token_accuracy": 0.13217105194926262,
|
|
"num_tokens": 42570046.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 6.670265150070191,
|
|
"epoch": 2.1054095992294934,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004561891967663906,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.1299501046538353,
|
|
"num_tokens": 42580440.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 6.63663501739502,
|
|
"epoch": 2.105944673337257,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00045616652607082203,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.1320934496819973,
|
|
"num_tokens": 42591872.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 6.579199552536011,
|
|
"epoch": 2.106479747445021,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004561438501440955,
|
|
"loss": 6.1552,
|
|
"mean_token_accuracy": 0.13399756476283073,
|
|
"num_tokens": 42602843.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 6.559487152099609,
|
|
"epoch": 2.107014821552785,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004561211689868657,
|
|
"loss": 6.2679,
|
|
"mean_token_accuracy": 0.14079473912715912,
|
|
"num_tokens": 42613476.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 6.525128173828125,
|
|
"epoch": 2.107549895660549,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045609848259978766,
|
|
"loss": 6.1359,
|
|
"mean_token_accuracy": 0.1485744059085846,
|
|
"num_tokens": 42624059.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 6.612544393539428,
|
|
"epoch": 2.108084969768313,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004560757909835164,
|
|
"loss": 6.3026,
|
|
"mean_token_accuracy": 0.13164251521229745,
|
|
"num_tokens": 42633980.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 6.645945692062378,
|
|
"epoch": 2.1086200438760767,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00045605309413870697,
|
|
"loss": 6.3138,
|
|
"mean_token_accuracy": 0.13203021883964539,
|
|
"num_tokens": 42645504.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 6.6313639163970945,
|
|
"epoch": 2.109155117983841,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004560303920660151,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.13372128009796141,
|
|
"num_tokens": 42655403.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 6.661088275909424,
|
|
"epoch": 2.1096901920916045,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045600768476609596,
|
|
"loss": 6.2827,
|
|
"mean_token_accuracy": 0.13641247972846032,
|
|
"num_tokens": 42666236.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 6.605567550659179,
|
|
"epoch": 2.1102252661993686,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00045598497223960533,
|
|
"loss": 6.3622,
|
|
"mean_token_accuracy": 0.1304132327437401,
|
|
"num_tokens": 42677365.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 6.595529985427857,
|
|
"epoch": 2.1107603403071327,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00045596225448719913,
|
|
"loss": 6.234,
|
|
"mean_token_accuracy": 0.14006053507328034,
|
|
"num_tokens": 42688518.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 6.653754377365113,
|
|
"epoch": 2.1112954144148963,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045593953150953326,
|
|
"loss": 6.2545,
|
|
"mean_token_accuracy": 0.13705209493637086,
|
|
"num_tokens": 42699877.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 6.587026500701905,
|
|
"epoch": 2.1118304885226604,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004559168033072638,
|
|
"loss": 6.2235,
|
|
"mean_token_accuracy": 0.1423036828637123,
|
|
"num_tokens": 42710191.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 6.570167970657349,
|
|
"epoch": 2.1123655626304245,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00045589406988104717,
|
|
"loss": 6.3151,
|
|
"mean_token_accuracy": 0.13141437247395515,
|
|
"num_tokens": 42720874.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 6.595329856872558,
|
|
"epoch": 2.112900636738188,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004558713312315396,
|
|
"loss": 6.2689,
|
|
"mean_token_accuracy": 0.13679243102669716,
|
|
"num_tokens": 42731783.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 6.610166120529175,
|
|
"epoch": 2.1134357108459523,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004558485873593978,
|
|
"loss": 6.2356,
|
|
"mean_token_accuracy": 0.13728932067751884,
|
|
"num_tokens": 42741602.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 6.710304641723633,
|
|
"epoch": 2.113970784953716,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00045582583826527835,
|
|
"loss": 6.2289,
|
|
"mean_token_accuracy": 0.14166050851345063,
|
|
"num_tokens": 42751249.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 6.593657302856445,
|
|
"epoch": 2.11450585906148,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004558030839498383,
|
|
"loss": 6.228,
|
|
"mean_token_accuracy": 0.13720010966062546,
|
|
"num_tokens": 42762083.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 6.523158168792724,
|
|
"epoch": 2.115040933169244,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004557803244137347,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.14905437976121902,
|
|
"num_tokens": 42773443.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 6.584961175918579,
|
|
"epoch": 2.115576007277008,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004557575596576245,
|
|
"loss": 6.2929,
|
|
"mean_token_accuracy": 0.13414834216237068,
|
|
"num_tokens": 42784126.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 6.601247310638428,
|
|
"epoch": 2.116111081384772,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045573478968216526,
|
|
"loss": 6.1827,
|
|
"mean_token_accuracy": 0.14093563184142113,
|
|
"num_tokens": 42795472.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 6.56029257774353,
|
|
"epoch": 2.1166461554925355,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045571201448801424,
|
|
"loss": 6.2287,
|
|
"mean_token_accuracy": 0.14368945062160493,
|
|
"num_tokens": 42805279.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 6.531841707229614,
|
|
"epoch": 2.1171812296002996,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004556892340758293,
|
|
"loss": 6.2606,
|
|
"mean_token_accuracy": 0.13446766063570975,
|
|
"num_tokens": 42815680.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 6.6385585308074955,
|
|
"epoch": 2.1177163037080637,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004556664484462681,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.13052476197481155,
|
|
"num_tokens": 42826724.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 6.668669891357422,
|
|
"epoch": 2.1182513778158274,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045564365759998856,
|
|
"loss": 6.2436,
|
|
"mean_token_accuracy": 0.13629350140690805,
|
|
"num_tokens": 42837875.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 6.602033424377441,
|
|
"epoch": 2.1187864519235915,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004556208615376488,
|
|
"loss": 6.236,
|
|
"mean_token_accuracy": 0.13456250056624414,
|
|
"num_tokens": 42848714.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 6.564524221420288,
|
|
"epoch": 2.119321526031355,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004555980602599071,
|
|
"loss": 6.287,
|
|
"mean_token_accuracy": 0.1357819400727749,
|
|
"num_tokens": 42859764.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 6.5792591094970705,
|
|
"epoch": 2.1198566001391193,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004555752537674217,
|
|
"loss": 6.1431,
|
|
"mean_token_accuracy": 0.13949351757764816,
|
|
"num_tokens": 42870346.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 6.548667907714844,
|
|
"epoch": 2.1203916742468834,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004555524420608513,
|
|
"loss": 6.2442,
|
|
"mean_token_accuracy": 0.1416882246732712,
|
|
"num_tokens": 42882706.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 6.520541095733643,
|
|
"epoch": 2.120926748354647,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045552962514085443,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.14233649522066116,
|
|
"num_tokens": 42893611.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 6.646184968948364,
|
|
"epoch": 2.121461822462411,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045550680300809003,
|
|
"loss": 6.2005,
|
|
"mean_token_accuracy": 0.13649763092398642,
|
|
"num_tokens": 42904034.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 6.580163383483887,
|
|
"epoch": 2.1219968965701748,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045548397566321706,
|
|
"loss": 6.2395,
|
|
"mean_token_accuracy": 0.13381608948111534,
|
|
"num_tokens": 42915530.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 6.558029127120972,
|
|
"epoch": 2.122531970677939,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004554611431068947,
|
|
"loss": 6.2317,
|
|
"mean_token_accuracy": 0.13710232973098754,
|
|
"num_tokens": 42926696.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 6.577070713043213,
|
|
"epoch": 2.123067044785703,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004554383053397822,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.14172173514962197,
|
|
"num_tokens": 42936985.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 6.653017377853393,
|
|
"epoch": 2.1236021188934666,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00045541546236253896,
|
|
"loss": 6.2078,
|
|
"mean_token_accuracy": 0.14061302319169044,
|
|
"num_tokens": 42947996.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 6.562133550643921,
|
|
"epoch": 2.1241371930012307,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.00045539261417582456,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.140869802236557,
|
|
"num_tokens": 42959669.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 6.4858794689178465,
|
|
"epoch": 2.124672267108995,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045536976078029874,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.14621758311986924,
|
|
"num_tokens": 42969687.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 6.594363260269165,
|
|
"epoch": 2.1252073412167585,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004553469021766215,
|
|
"loss": 6.2822,
|
|
"mean_token_accuracy": 0.12778127044439316,
|
|
"num_tokens": 42980752.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 6.671602201461792,
|
|
"epoch": 2.1257424153245226,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00045532403836545286,
|
|
"loss": 6.3429,
|
|
"mean_token_accuracy": 0.13322691172361373,
|
|
"num_tokens": 42991949.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 6.598054456710815,
|
|
"epoch": 2.1262774894322862,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004553011693474528,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.1461856409907341,
|
|
"num_tokens": 43002689.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 6.609069204330444,
|
|
"epoch": 2.1268125635400503,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004552782951232819,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.13533738479018212,
|
|
"num_tokens": 43012939.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 6.602839803695678,
|
|
"epoch": 2.1273476376478144,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00045525541569360053,
|
|
"loss": 6.2158,
|
|
"mean_token_accuracy": 0.13694751337170602,
|
|
"num_tokens": 43023887.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 6.495054149627686,
|
|
"epoch": 2.127882711755578,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004552325310590694,
|
|
"loss": 6.1434,
|
|
"mean_token_accuracy": 0.13924660235643388,
|
|
"num_tokens": 43034554.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 6.5834801197052,
|
|
"epoch": 2.128417785863342,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004552096412203492,
|
|
"loss": 6.2998,
|
|
"mean_token_accuracy": 0.13441743403673173,
|
|
"num_tokens": 43046322.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 6.642183589935303,
|
|
"epoch": 2.128952859971106,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000455186746178101,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.1421908676624298,
|
|
"num_tokens": 43055981.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 6.700017309188842,
|
|
"epoch": 2.12948793407887,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00045516384593298584,
|
|
"loss": 6.2524,
|
|
"mean_token_accuracy": 0.12821802645921707,
|
|
"num_tokens": 43067217.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 6.648524904251099,
|
|
"epoch": 2.130023008186634,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00045514094048566486,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.13673778101801873,
|
|
"num_tokens": 43078312.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 6.426058435440064,
|
|
"epoch": 2.1305580822943977,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00045511802983679955,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.1545651763677597,
|
|
"num_tokens": 43090210.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 6.5579427719116214,
|
|
"epoch": 2.131093156402162,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004550951139870515,
|
|
"loss": 6.1899,
|
|
"mean_token_accuracy": 0.13597036451101302,
|
|
"num_tokens": 43101282.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 6.618681621551514,
|
|
"epoch": 2.1316282305099254,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00045507219293708227,
|
|
"loss": 6.3199,
|
|
"mean_token_accuracy": 0.12866441458463668,
|
|
"num_tokens": 43112856.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 6.571073532104492,
|
|
"epoch": 2.1321633046176895,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00045504926668755384,
|
|
"loss": 6.1731,
|
|
"mean_token_accuracy": 0.14310084134340287,
|
|
"num_tokens": 43123898.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 6.5852282524108885,
|
|
"epoch": 2.1326983787254536,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004550263352391281,
|
|
"loss": 6.2318,
|
|
"mean_token_accuracy": 0.14241430088877677,
|
|
"num_tokens": 43134651.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 6.573841667175293,
|
|
"epoch": 2.1332334528332173,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004550033985924672,
|
|
"loss": 6.2669,
|
|
"mean_token_accuracy": 0.13783082291483878,
|
|
"num_tokens": 43145385.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 6.63946304321289,
|
|
"epoch": 2.1337685269409814,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004549804567482335,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.136797234416008,
|
|
"num_tokens": 43157356.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 6.667788648605347,
|
|
"epoch": 2.134303601048745,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00045495750970708944,
|
|
"loss": 6.2545,
|
|
"mean_token_accuracy": 0.14129154980182648,
|
|
"num_tokens": 43168289.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 6.547308921813965,
|
|
"epoch": 2.134838675156509,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00045493455746969746,
|
|
"loss": 6.1887,
|
|
"mean_token_accuracy": 0.14103937596082688,
|
|
"num_tokens": 43177796.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 6.500805997848511,
|
|
"epoch": 2.1353737492642733,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004549116000367205,
|
|
"loss": 6.2011,
|
|
"mean_token_accuracy": 0.14314061030745506,
|
|
"num_tokens": 43188846.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 6.6554749488830565,
|
|
"epoch": 2.135908823372037,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00045488863740882133,
|
|
"loss": 6.2958,
|
|
"mean_token_accuracy": 0.13791427314281463,
|
|
"num_tokens": 43199852.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 6.577768707275391,
|
|
"epoch": 2.136443897479801,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00045486566958666307,
|
|
"loss": 6.2024,
|
|
"mean_token_accuracy": 0.13826452568173409,
|
|
"num_tokens": 43210591.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 6.576674461364746,
|
|
"epoch": 2.136978971587565,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045484269657090887,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.13490024507045745,
|
|
"num_tokens": 43221760.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 6.602348566055298,
|
|
"epoch": 2.1375140456953288,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00045481971836222205,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.12968283221125604,
|
|
"num_tokens": 43233693.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 6.612666749954224,
|
|
"epoch": 2.138049119803093,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00045479673496126615,
|
|
"loss": 6.2735,
|
|
"mean_token_accuracy": 0.13571649864315988,
|
|
"num_tokens": 43244565.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 6.527144193649292,
|
|
"epoch": 2.1385841939108565,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 0.00045477374636870485,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.1402919739484787,
|
|
"num_tokens": 43254913.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 6.652837181091309,
|
|
"epoch": 2.1391192680186206,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00045475075258520175,
|
|
"loss": 6.2453,
|
|
"mean_token_accuracy": 0.13735177367925644,
|
|
"num_tokens": 43265525.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 6.634648752212525,
|
|
"epoch": 2.1396543421263843,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004547277536114211,
|
|
"loss": 6.3205,
|
|
"mean_token_accuracy": 0.13027699068188667,
|
|
"num_tokens": 43276954.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 6.590658569335938,
|
|
"epoch": 2.1401894162341484,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004547047494480267,
|
|
"loss": 6.2183,
|
|
"mean_token_accuracy": 0.14129220843315124,
|
|
"num_tokens": 43287491.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 6.567471361160278,
|
|
"epoch": 2.1407244903419125,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004546817400956829,
|
|
"loss": 6.2679,
|
|
"mean_token_accuracy": 0.1343812607228756,
|
|
"num_tokens": 43298341.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 6.503889656066894,
|
|
"epoch": 2.141259564449676,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00045465872555505417,
|
|
"loss": 6.2063,
|
|
"mean_token_accuracy": 0.14123483896255493,
|
|
"num_tokens": 43309450.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 6.652082920074463,
|
|
"epoch": 2.1417946385574402,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000454635705826805,
|
|
"loss": 6.2303,
|
|
"mean_token_accuracy": 0.13314618319272994,
|
|
"num_tokens": 43320126.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 6.667106294631958,
|
|
"epoch": 2.1423297126652043,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004546126809116,
|
|
"loss": 6.3153,
|
|
"mean_token_accuracy": 0.12874586060643195,
|
|
"num_tokens": 43331347.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 6.567958402633667,
|
|
"epoch": 2.142864786772968,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004545896508101041,
|
|
"loss": 6.2242,
|
|
"mean_token_accuracy": 0.1406198963522911,
|
|
"num_tokens": 43341351.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 6.610765790939331,
|
|
"epoch": 2.143399860880732,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004545666155229823,
|
|
"loss": 6.2948,
|
|
"mean_token_accuracy": 0.13321691676974295,
|
|
"num_tokens": 43352471.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 6.616747665405273,
|
|
"epoch": 2.1439349349884957,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00045454357505089965,
|
|
"loss": 6.1738,
|
|
"mean_token_accuracy": 0.13594428300857545,
|
|
"num_tokens": 43363041.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 6.571103763580322,
|
|
"epoch": 2.14447000909626,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004545205293945215,
|
|
"loss": 6.2088,
|
|
"mean_token_accuracy": 0.1360207110643387,
|
|
"num_tokens": 43375034.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 6.615240812301636,
|
|
"epoch": 2.145005083204024,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004544974785545134,
|
|
"loss": 6.3276,
|
|
"mean_token_accuracy": 0.12840238735079765,
|
|
"num_tokens": 43386110.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 6.5785605907440186,
|
|
"epoch": 2.1455401573117876,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004544744225315407,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.1399793043732643,
|
|
"num_tokens": 43396150.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 6.555577993392944,
|
|
"epoch": 2.1460752314195517,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004544513613262693,
|
|
"loss": 6.2538,
|
|
"mean_token_accuracy": 0.1358305223286152,
|
|
"num_tokens": 43407237.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 6.5300150394439695,
|
|
"epoch": 2.1466103055273154,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004544282949393652,
|
|
"loss": 6.1475,
|
|
"mean_token_accuracy": 0.1429210811853409,
|
|
"num_tokens": 43417626.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 6.580790233612061,
|
|
"epoch": 2.1471453796350795,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004544052233714941,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.1394651398062706,
|
|
"num_tokens": 43427368.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 6.532987260818482,
|
|
"epoch": 2.1476804537428436,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00045438214662332245,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.13770126029849053,
|
|
"num_tokens": 43438159.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 6.5826249599456785,
|
|
"epoch": 2.148215527850607,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00045435906469551657,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.1385325774550438,
|
|
"num_tokens": 43447403.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 6.556477451324463,
|
|
"epoch": 2.1487506019583713,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00045433597758874286,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.15006787776947023,
|
|
"num_tokens": 43457713.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 6.567327547073364,
|
|
"epoch": 2.149285676066135,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000454312885303668,
|
|
"loss": 6.2667,
|
|
"mean_token_accuracy": 0.13713714331388474,
|
|
"num_tokens": 43468520.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 6.632494163513184,
|
|
"epoch": 2.149820750173899,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00045428978784095873,
|
|
"loss": 6.2878,
|
|
"mean_token_accuracy": 0.13077297061681747,
|
|
"num_tokens": 43480501.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 6.682619047164917,
|
|
"epoch": 2.150355824281663,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00045426668520128204,
|
|
"loss": 6.2516,
|
|
"mean_token_accuracy": 0.1356627568602562,
|
|
"num_tokens": 43491297.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 6.631320858001709,
|
|
"epoch": 2.150890898389427,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004542435773853051,
|
|
"loss": 6.2569,
|
|
"mean_token_accuracy": 0.13558914884924889,
|
|
"num_tokens": 43501212.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 6.53989896774292,
|
|
"epoch": 2.151425972497191,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000454220464393695,
|
|
"loss": 6.2759,
|
|
"mean_token_accuracy": 0.13101306781172753,
|
|
"num_tokens": 43511136.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 6.613527059555054,
|
|
"epoch": 2.1519610466049546,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004541973462271192,
|
|
"loss": 6.3004,
|
|
"mean_token_accuracy": 0.13350855335593223,
|
|
"num_tokens": 43522006.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 6.620876598358154,
|
|
"epoch": 2.1524961207127187,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004541742228862451,
|
|
"loss": 6.2176,
|
|
"mean_token_accuracy": 0.14102254509925843,
|
|
"num_tokens": 43532746.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 6.51152720451355,
|
|
"epoch": 2.1530311948204828,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00045415109437174064,
|
|
"loss": 6.2421,
|
|
"mean_token_accuracy": 0.13935872092843055,
|
|
"num_tokens": 43543707.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 6.532021999359131,
|
|
"epoch": 2.1535662689282464,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00045412796068427337,
|
|
"loss": 6.2363,
|
|
"mean_token_accuracy": 0.1310371808707714,
|
|
"num_tokens": 43555029.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 6.613600397109986,
|
|
"epoch": 2.1541013430360105,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00045410482182451153,
|
|
"loss": 6.2723,
|
|
"mean_token_accuracy": 0.1307027131319046,
|
|
"num_tokens": 43565639.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 6.5654387950897215,
|
|
"epoch": 2.1546364171437746,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00045408167779312306,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.14522920027375222,
|
|
"num_tokens": 43576333.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 6.591990518569946,
|
|
"epoch": 2.1551714912515383,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00045405852859077626,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.13329390659928322,
|
|
"num_tokens": 43587012.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 6.575863265991211,
|
|
"epoch": 2.1557065653593024,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045403537421813975,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.1413382962346077,
|
|
"num_tokens": 43597779.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 6.56874189376831,
|
|
"epoch": 2.156241639467066,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00045401221467588184,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.13611011877655982,
|
|
"num_tokens": 43608631.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 6.564034175872803,
|
|
"epoch": 2.15677671357483,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004539890499646714,
|
|
"loss": 6.1866,
|
|
"mean_token_accuracy": 0.1426114782691002,
|
|
"num_tokens": 43620254.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 6.566227626800537,
|
|
"epoch": 2.1573117876825942,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004539658800851773,
|
|
"loss": 6.1638,
|
|
"mean_token_accuracy": 0.13967948108911515,
|
|
"num_tokens": 43630986.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 6.522751998901367,
|
|
"epoch": 2.157846861790358,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004539427050380686,
|
|
"loss": 6.1497,
|
|
"mean_token_accuracy": 0.13614366129040717,
|
|
"num_tokens": 43641260.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 6.528595495223999,
|
|
"epoch": 2.158381935898122,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045391952482401444,
|
|
"loss": 6.3068,
|
|
"mean_token_accuracy": 0.1336046002805233,
|
|
"num_tokens": 43652093.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 6.573609399795532,
|
|
"epoch": 2.1589170100058857,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00045389633944368406,
|
|
"loss": 6.2243,
|
|
"mean_token_accuracy": 0.13741191029548644,
|
|
"num_tokens": 43662799.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 6.563785123825073,
|
|
"epoch": 2.1594520841136498,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004538731488977471,
|
|
"loss": 6.1694,
|
|
"mean_token_accuracy": 0.13669373616576194,
|
|
"num_tokens": 43674198.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 6.581851816177368,
|
|
"epoch": 2.159987158221414,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004538499531868731,
|
|
"loss": 6.2196,
|
|
"mean_token_accuracy": 0.14030924513936044,
|
|
"num_tokens": 43684841.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 6.6294575214385985,
|
|
"epoch": 2.1605222323291775,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00045382675231173174,
|
|
"loss": 6.307,
|
|
"mean_token_accuracy": 0.12898236364126206,
|
|
"num_tokens": 43695903.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 6.597292852401734,
|
|
"epoch": 2.1610573064369416,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004538035462729931,
|
|
"loss": 6.2057,
|
|
"mean_token_accuracy": 0.13727677762508392,
|
|
"num_tokens": 43706740.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 6.585876321792602,
|
|
"epoch": 2.1615923805447053,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004537803350713273,
|
|
"loss": 6.1863,
|
|
"mean_token_accuracy": 0.13955402001738548,
|
|
"num_tokens": 43717124.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 6.552768659591675,
|
|
"epoch": 2.1621274546524694,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004537571187074043,
|
|
"loss": 6.1693,
|
|
"mean_token_accuracy": 0.1418169267475605,
|
|
"num_tokens": 43727346.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 6.640131092071533,
|
|
"epoch": 2.1626625287602335,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00045373389718189464,
|
|
"loss": 6.3419,
|
|
"mean_token_accuracy": 0.12521408051252364,
|
|
"num_tokens": 43738297.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 6.6138440608978275,
|
|
"epoch": 2.163197602867997,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004537106704954689,
|
|
"loss": 6.2331,
|
|
"mean_token_accuracy": 0.13427724912762642,
|
|
"num_tokens": 43749543.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 6.635886335372925,
|
|
"epoch": 2.163732676975761,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00045368743864879755,
|
|
"loss": 6.2214,
|
|
"mean_token_accuracy": 0.1402733728289604,
|
|
"num_tokens": 43760324.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 6.6271484851837155,
|
|
"epoch": 2.164267751083525,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00045366420164255156,
|
|
"loss": 6.2763,
|
|
"mean_token_accuracy": 0.13219456374645233,
|
|
"num_tokens": 43770391.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 6.522807455062866,
|
|
"epoch": 2.164802825191289,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004536409594774019,
|
|
"loss": 6.1933,
|
|
"mean_token_accuracy": 0.13223286718130112,
|
|
"num_tokens": 43781516.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 6.5333081722259525,
|
|
"epoch": 2.165337899299053,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00045361771215401953,
|
|
"loss": 6.2296,
|
|
"mean_token_accuracy": 0.14509074464440347,
|
|
"num_tokens": 43794152.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 6.64941930770874,
|
|
"epoch": 2.1658729734068167,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00045359445967307595,
|
|
"loss": 6.2172,
|
|
"mean_token_accuracy": 0.14311170801520348,
|
|
"num_tokens": 43805712.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 6.693462896347046,
|
|
"epoch": 2.166408047514581,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004535712020352423,
|
|
"loss": 6.2856,
|
|
"mean_token_accuracy": 0.1299527995288372,
|
|
"num_tokens": 43816985.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 6.553119134902954,
|
|
"epoch": 2.166943121622345,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004535479392411904,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.137317306548357,
|
|
"num_tokens": 43828048.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 6.543961429595948,
|
|
"epoch": 2.1674781957301086,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00045352467129159183,
|
|
"loss": 6.2359,
|
|
"mean_token_accuracy": 0.13402119725942613,
|
|
"num_tokens": 43838507.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 6.535673427581787,
|
|
"epoch": 2.1680132698378727,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00045350139818711846,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.14233728349208832,
|
|
"num_tokens": 43849328.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 6.562674951553345,
|
|
"epoch": 2.1685483439456363,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004534781199284423,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.13256120011210443,
|
|
"num_tokens": 43860311.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 6.6427960872650145,
|
|
"epoch": 2.1690834180534004,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004534548365162354,
|
|
"loss": 6.3046,
|
|
"mean_token_accuracy": 0.13149307742714883,
|
|
"num_tokens": 43871167.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 6.572381496429443,
|
|
"epoch": 2.169618492161164,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00045343154795117024,
|
|
"loss": 6.1949,
|
|
"mean_token_accuracy": 0.14235295429825784,
|
|
"num_tokens": 43882332.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 6.593906497955322,
|
|
"epoch": 2.170153566268928,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004534082542339192,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.1371185638010502,
|
|
"num_tokens": 43892971.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 6.495148658752441,
|
|
"epoch": 2.1706886403766923,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045338495536515497,
|
|
"loss": 6.2432,
|
|
"mean_token_accuracy": 0.14178172945976258,
|
|
"num_tokens": 43904305.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 6.416570949554443,
|
|
"epoch": 2.171223714484456,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004533616513455502,
|
|
"loss": 6.1849,
|
|
"mean_token_accuracy": 0.13799539655447007,
|
|
"num_tokens": 43914431.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 6.6083173751831055,
|
|
"epoch": 2.17175878859222,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00045333834217577775,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.1429225467145443,
|
|
"num_tokens": 43925350.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 6.5853283405303955,
|
|
"epoch": 2.172293862699984,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00045331502785651075,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.13435436487197877,
|
|
"num_tokens": 43936194.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 6.606304264068603,
|
|
"epoch": 2.172828936807748,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004532917083884224,
|
|
"loss": 6.2384,
|
|
"mean_token_accuracy": 0.1382653869688511,
|
|
"num_tokens": 43946692.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 6.569739532470703,
|
|
"epoch": 2.173364010915512,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000453268383772186,
|
|
"loss": 6.2099,
|
|
"mean_token_accuracy": 0.13581094965338708,
|
|
"num_tokens": 43957493.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 6.600575542449951,
|
|
"epoch": 2.1738990850232756,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00045324505400847506,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.13378666937351227,
|
|
"num_tokens": 43970203.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 6.604616022109985,
|
|
"epoch": 2.1744341591310397,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00045322171909796327,
|
|
"loss": 6.2071,
|
|
"mean_token_accuracy": 0.13666222244501114,
|
|
"num_tokens": 43980778.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 6.596654748916626,
|
|
"epoch": 2.1749692332388038,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045319837904132435,
|
|
"loss": 6.2259,
|
|
"mean_token_accuracy": 0.14115234836935997,
|
|
"num_tokens": 43992239.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 6.610764646530152,
|
|
"epoch": 2.1755043073465674,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004531750338392323,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.1386513441801071,
|
|
"num_tokens": 44001882.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 6.520384931564331,
|
|
"epoch": 2.1760393814543315,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004531516834923611,
|
|
"loss": 6.2218,
|
|
"mean_token_accuracy": 0.13213175013661385,
|
|
"num_tokens": 44013192.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 6.672077274322509,
|
|
"epoch": 2.176574455562095,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004531283280013852,
|
|
"loss": 6.2669,
|
|
"mean_token_accuracy": 0.1311400391161442,
|
|
"num_tokens": 44023072.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 6.679711866378784,
|
|
"epoch": 2.1771095296698593,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00045310496736697875,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.13929223790764808,
|
|
"num_tokens": 44034238.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 6.5589159488677975,
|
|
"epoch": 2.1776446037776234,
|
|
"grad_norm": 16.0,
|
|
"learning_rate": 0.00045308160158981646,
|
|
"loss": 6.2368,
|
|
"mean_token_accuracy": 0.1385028451681137,
|
|
"num_tokens": 44044392.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 6.577165651321411,
|
|
"epoch": 2.178179677885387,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000453058230670573,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.1324876882135868,
|
|
"num_tokens": 44056129.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 6.542128705978394,
|
|
"epoch": 2.178714751993151,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00045303485460992303,
|
|
"loss": 6.2092,
|
|
"mean_token_accuracy": 0.14428236037492753,
|
|
"num_tokens": 44067600.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 6.58773832321167,
|
|
"epoch": 2.1792498261009148,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.00045301147340854177,
|
|
"loss": 6.1177,
|
|
"mean_token_accuracy": 0.1481347404420376,
|
|
"num_tokens": 44077373.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 6.582125616073609,
|
|
"epoch": 2.179784900208679,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00045298808706710416,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.136127108335495,
|
|
"num_tokens": 44087422.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 6.608782339096069,
|
|
"epoch": 2.180319974316443,
|
|
"grad_norm": 6.03125,
|
|
"learning_rate": 0.00045296469558628555,
|
|
"loss": 6.2741,
|
|
"mean_token_accuracy": 0.1320221520960331,
|
|
"num_tokens": 44098524.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 6.554975748062134,
|
|
"epoch": 2.1808550484242066,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045294129896676134,
|
|
"loss": 6.1774,
|
|
"mean_token_accuracy": 0.14473088085651398,
|
|
"num_tokens": 44108340.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 6.573651933670044,
|
|
"epoch": 2.1813901225319707,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004529178972092071,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.132859718054533,
|
|
"num_tokens": 44118985.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 6.653313302993775,
|
|
"epoch": 2.1819251966397344,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00045289449031429873,
|
|
"loss": 6.2468,
|
|
"mean_token_accuracy": 0.13791687935590743,
|
|
"num_tokens": 44129126.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 6.6461302757263185,
|
|
"epoch": 2.1824602707474985,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00045287107828271184,
|
|
"loss": 6.243,
|
|
"mean_token_accuracy": 0.1388023763895035,
|
|
"num_tokens": 44139731.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 6.59973258972168,
|
|
"epoch": 2.1829953448552626,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004528476611151226,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.13669243827462196,
|
|
"num_tokens": 44149924.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 6.52322678565979,
|
|
"epoch": 2.1835304189630262,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004528242388122071,
|
|
"loss": 6.2047,
|
|
"mean_token_accuracy": 0.13386249244213105,
|
|
"num_tokens": 44161155.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 6.597751140594482,
|
|
"epoch": 2.1840654930707903,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004528008113746417,
|
|
"loss": 6.254,
|
|
"mean_token_accuracy": 0.13706667572259904,
|
|
"num_tokens": 44171563.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 6.567836332321167,
|
|
"epoch": 2.1846005671785544,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00045277737880310284,
|
|
"loss": 6.1699,
|
|
"mean_token_accuracy": 0.13824426308274268,
|
|
"num_tokens": 44182719.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 6.583373022079468,
|
|
"epoch": 2.185135641286318,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045275394109826715,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.14230660796165467,
|
|
"num_tokens": 44192214.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 6.55186448097229,
|
|
"epoch": 2.185670715394082,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00045273049826081145,
|
|
"loss": 6.2175,
|
|
"mean_token_accuracy": 0.13366278260946274,
|
|
"num_tokens": 44204074.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 6.611530017852783,
|
|
"epoch": 2.186205789501846,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004527070502914125,
|
|
"loss": 6.3724,
|
|
"mean_token_accuracy": 0.1308964490890503,
|
|
"num_tokens": 44214402.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 6.662555122375489,
|
|
"epoch": 2.18674086360961,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004526835971907475,
|
|
"loss": 6.243,
|
|
"mean_token_accuracy": 0.1345195949077606,
|
|
"num_tokens": 44224479.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 6.5980236530303955,
|
|
"epoch": 2.187275937717374,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00045266013895949356,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.13219650238752365,
|
|
"num_tokens": 44234069.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 6.610879230499267,
|
|
"epoch": 2.1878110118251377,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004526366755983281,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.13069274127483368,
|
|
"num_tokens": 44244978.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 6.605560255050659,
|
|
"epoch": 2.188346085932902,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004526132071079286,
|
|
"loss": 6.2301,
|
|
"mean_token_accuracy": 0.1396063208580017,
|
|
"num_tokens": 44255657.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 6.524712181091308,
|
|
"epoch": 2.1888811600406655,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00045258973348897267,
|
|
"loss": 6.1997,
|
|
"mean_token_accuracy": 0.13705252036452292,
|
|
"num_tokens": 44267370.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 6.517517757415772,
|
|
"epoch": 2.1894162341484296,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004525662547421382,
|
|
"loss": 6.2284,
|
|
"mean_token_accuracy": 0.13603501617908478,
|
|
"num_tokens": 44277855.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 6.635191488265991,
|
|
"epoch": 2.1899513082561937,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000452542770868103,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.13610289096832276,
|
|
"num_tokens": 44288233.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 6.614072227478028,
|
|
"epoch": 2.1904863823639573,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00045251928186754533,
|
|
"loss": 6.2594,
|
|
"mean_token_accuracy": 0.14411043450236322,
|
|
"num_tokens": 44298054.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 6.607892274856567,
|
|
"epoch": 2.1910214564717214,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004524957877411432,
|
|
"loss": 6.2177,
|
|
"mean_token_accuracy": 0.13948602452874184,
|
|
"num_tokens": 44309435.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 6.6357465267181395,
|
|
"epoch": 2.191556530579485,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004524722884895753,
|
|
"loss": 6.2913,
|
|
"mean_token_accuracy": 0.13606009557843207,
|
|
"num_tokens": 44320502.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 6.531925868988037,
|
|
"epoch": 2.192091604687249,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00045244878411352,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.14880633652210234,
|
|
"num_tokens": 44330911.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 6.6444549560546875,
|
|
"epoch": 2.1926266787950133,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004524252746136559,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.1326467677950859,
|
|
"num_tokens": 44342159.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 6.6098878383636475,
|
|
"epoch": 2.193161752902777,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00045240175999066194,
|
|
"loss": 6.1877,
|
|
"mean_token_accuracy": 0.14018870741128922,
|
|
"num_tokens": 44352293.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 6.590828275680542,
|
|
"epoch": 2.193696827010541,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00045237824024521714,
|
|
"loss": 6.3493,
|
|
"mean_token_accuracy": 0.13741861805319786,
|
|
"num_tokens": 44362321.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 6.600882244110108,
|
|
"epoch": 2.1942319011183047,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004523547153780005,
|
|
"loss": 6.207,
|
|
"mean_token_accuracy": 0.13784217983484268,
|
|
"num_tokens": 44372682.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 6.627217435836792,
|
|
"epoch": 2.194766975226069,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004523311853896915,
|
|
"loss": 6.2339,
|
|
"mean_token_accuracy": 0.14101556614041327,
|
|
"num_tokens": 44383482.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 6.529561281204224,
|
|
"epoch": 2.195302049333833,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00045230765028096925,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.15929336175322534,
|
|
"num_tokens": 44395333.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 6.595133686065674,
|
|
"epoch": 2.1958371234415965,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00045228411005251366,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.13142997100949289,
|
|
"num_tokens": 44406210.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 6.576221179962158,
|
|
"epoch": 2.1963721975493606,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004522605647050043,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.1340940348803997,
|
|
"num_tokens": 44415834.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 6.732267904281616,
|
|
"epoch": 2.1969072716571247,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00045223701423912103,
|
|
"loss": 6.3514,
|
|
"mean_token_accuracy": 0.13144610300660134,
|
|
"num_tokens": 44427902.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 6.66651725769043,
|
|
"epoch": 2.1974423457648884,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00045221345865554386,
|
|
"loss": 6.1581,
|
|
"mean_token_accuracy": 0.14375145509839057,
|
|
"num_tokens": 44437406.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 6.56536226272583,
|
|
"epoch": 2.1979774198726525,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00045218989795495294,
|
|
"loss": 6.174,
|
|
"mean_token_accuracy": 0.14052731394767762,
|
|
"num_tokens": 44446889.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 6.549853515625,
|
|
"epoch": 2.198512493980416,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00045216633213802866,
|
|
"loss": 6.2552,
|
|
"mean_token_accuracy": 0.1328713685274124,
|
|
"num_tokens": 44457132.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 6.5789573192596436,
|
|
"epoch": 2.1990475680881802,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00045214276120545137,
|
|
"loss": 6.2733,
|
|
"mean_token_accuracy": 0.13562775626778603,
|
|
"num_tokens": 44468006.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 6.588794088363647,
|
|
"epoch": 2.199582642195944,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004521191851579019,
|
|
"loss": 6.2005,
|
|
"mean_token_accuracy": 0.13432316109538078,
|
|
"num_tokens": 44478650.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 6.498971223831177,
|
|
"epoch": 2.200117716303708,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004520956039960607,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.13360520601272582,
|
|
"num_tokens": 44489842.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 6.52718563079834,
|
|
"epoch": 2.200652790411472,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045207201772060887,
|
|
"loss": 6.1858,
|
|
"mean_token_accuracy": 0.14044702276587487,
|
|
"num_tokens": 44500444.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 6.576969051361084,
|
|
"epoch": 2.2011878645192358,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004520484263322274,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.1412016600370407,
|
|
"num_tokens": 44510711.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 6.600472021102905,
|
|
"epoch": 2.201722938627,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004520248298315975,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.14031925201416015,
|
|
"num_tokens": 44522343.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 6.5167388916015625,
|
|
"epoch": 2.202258012734764,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045200122821940057,
|
|
"loss": 6.2459,
|
|
"mean_token_accuracy": 0.1338384784758091,
|
|
"num_tokens": 44533218.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 6.643731784820557,
|
|
"epoch": 2.2027930868425276,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00045197762149631795,
|
|
"loss": 6.2787,
|
|
"mean_token_accuracy": 0.13989424481987953,
|
|
"num_tokens": 44543406.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 6.666849803924561,
|
|
"epoch": 2.2033281609502917,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00045195400966303146,
|
|
"loss": 6.3033,
|
|
"mean_token_accuracy": 0.1391474649310112,
|
|
"num_tokens": 44555329.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 6.647317409515381,
|
|
"epoch": 2.2038632350580554,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004519303927202228,
|
|
"loss": 6.3037,
|
|
"mean_token_accuracy": 0.13623926043510437,
|
|
"num_tokens": 44565191.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 6.546984386444092,
|
|
"epoch": 2.2043983091658195,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00045190677066857384,
|
|
"loss": 6.1784,
|
|
"mean_token_accuracy": 0.15021046847105027,
|
|
"num_tokens": 44576374.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 6.543681240081787,
|
|
"epoch": 2.2049333832735836,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004518831435087668,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.14416999518871307,
|
|
"num_tokens": 44586533.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 6.5041008472442625,
|
|
"epoch": 2.2054684573813472,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004518595112414838,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.14975323155522346,
|
|
"num_tokens": 44596753.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 6.633648443222046,
|
|
"epoch": 2.2060035314891113,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004518358738674073,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.1309145286679268,
|
|
"num_tokens": 44607632.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 6.619381999969482,
|
|
"epoch": 2.206538605596875,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004518122313872198,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.13560301959514617,
|
|
"num_tokens": 44618786.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 6.579495096206665,
|
|
"epoch": 2.207073679704639,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00045178858380160396,
|
|
"loss": 6.2087,
|
|
"mean_token_accuracy": 0.13541341125965117,
|
|
"num_tokens": 44628760.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 6.583818435668945,
|
|
"epoch": 2.207608753812403,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004517649311112426,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.13615447655320168,
|
|
"num_tokens": 44641206.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 6.6077642917633055,
|
|
"epoch": 2.208143827920167,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004517412733168187,
|
|
"loss": 6.2202,
|
|
"mean_token_accuracy": 0.14037453681230544,
|
|
"num_tokens": 44651923.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 6.589768362045288,
|
|
"epoch": 2.208678902027931,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00045171761041901533,
|
|
"loss": 6.1953,
|
|
"mean_token_accuracy": 0.13628434911370277,
|
|
"num_tokens": 44662375.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 6.476265907287598,
|
|
"epoch": 2.2092139761356946,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004516939424185158,
|
|
"loss": 6.149,
|
|
"mean_token_accuracy": 0.14235980063676834,
|
|
"num_tokens": 44673201.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 6.550486850738525,
|
|
"epoch": 2.2097490502434587,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004516702693160035,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.13487618118524553,
|
|
"num_tokens": 44684300.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 6.621839380264282,
|
|
"epoch": 2.210284124351223,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004516465911121621,
|
|
"loss": 6.2508,
|
|
"mean_token_accuracy": 0.1372546449303627,
|
|
"num_tokens": 44694603.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 6.621879577636719,
|
|
"epoch": 2.2108191984589864,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004516229078076751,
|
|
"loss": 6.235,
|
|
"mean_token_accuracy": 0.14090180546045303,
|
|
"num_tokens": 44704461.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 6.574653148651123,
|
|
"epoch": 2.2113542725667505,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004515992194032265,
|
|
"loss": 6.3196,
|
|
"mean_token_accuracy": 0.13438495770096778,
|
|
"num_tokens": 44715784.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 6.573662662506104,
|
|
"epoch": 2.211889346674514,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045157552589950023,
|
|
"loss": 6.1799,
|
|
"mean_token_accuracy": 0.14029885083436966,
|
|
"num_tokens": 44726025.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 6.513232278823852,
|
|
"epoch": 2.2124244207822783,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004515518272971805,
|
|
"loss": 6.1367,
|
|
"mean_token_accuracy": 0.15541271194815637,
|
|
"num_tokens": 44736602.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 6.573304605484009,
|
|
"epoch": 2.2129594948900424,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004515281235969515,
|
|
"loss": 6.3031,
|
|
"mean_token_accuracy": 0.1314288333058357,
|
|
"num_tokens": 44746260.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 6.562344884872436,
|
|
"epoch": 2.213494568997806,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004515044147994978,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.13978503420948982,
|
|
"num_tokens": 44756894.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 6.623016309738159,
|
|
"epoch": 2.21402964310557,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004514807009055039,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.1358432151377201,
|
|
"num_tokens": 44768483.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 6.584512948989868,
|
|
"epoch": 2.2145647172133343,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00045145698191565456,
|
|
"loss": 6.1906,
|
|
"mean_token_accuracy": 0.13653227910399438,
|
|
"num_tokens": 44778843.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 6.576665735244751,
|
|
"epoch": 2.215099791321098,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00045143325783063466,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.14021056592464448,
|
|
"num_tokens": 44788659.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 6.596614980697632,
|
|
"epoch": 2.215634865428862,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004514095286511293,
|
|
"loss": 6.2489,
|
|
"mean_token_accuracy": 0.13831923753023148,
|
|
"num_tokens": 44799730.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 6.582507085800171,
|
|
"epoch": 2.2161699395366257,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004513857943778235,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.14641110375523567,
|
|
"num_tokens": 44811679.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 6.606428432464599,
|
|
"epoch": 2.2167050136443898,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004513620550114027,
|
|
"loss": 6.2232,
|
|
"mean_token_accuracy": 0.13752431869506837,
|
|
"num_tokens": 44821996.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 6.6189656257629395,
|
|
"epoch": 2.217240087752154,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00045133831055255234,
|
|
"loss": 6.2629,
|
|
"mean_token_accuracy": 0.1383106604218483,
|
|
"num_tokens": 44833713.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 6.59858980178833,
|
|
"epoch": 2.2177751618599175,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004513145610019581,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.1427071288228035,
|
|
"num_tokens": 44844751.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 6.616464281082154,
|
|
"epoch": 2.2183102359676816,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00045129080636030554,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.13303786441683768,
|
|
"num_tokens": 44856089.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 6.583980751037598,
|
|
"epoch": 2.2188453100754453,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004512670466282808,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.136950009316206,
|
|
"num_tokens": 44867313.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 6.611618185043335,
|
|
"epoch": 2.2193803841832094,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00045124328180656993,
|
|
"loss": 6.2264,
|
|
"mean_token_accuracy": 0.13527941778302194,
|
|
"num_tokens": 44878430.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 6.5980141162872314,
|
|
"epoch": 2.2199154582909735,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045121951189585897,
|
|
"loss": 6.157,
|
|
"mean_token_accuracy": 0.13870189264416694,
|
|
"num_tokens": 44888746.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 6.574773550033569,
|
|
"epoch": 2.220450532398737,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00045119573689683445,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.13028892278671264,
|
|
"num_tokens": 44899412.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 6.5714301586151125,
|
|
"epoch": 2.2209856065065012,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00045117195681018273,
|
|
"loss": 6.214,
|
|
"mean_token_accuracy": 0.1353364259004593,
|
|
"num_tokens": 44910362.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 6.572721815109253,
|
|
"epoch": 2.221520680614265,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004511481716365905,
|
|
"loss": 6.1855,
|
|
"mean_token_accuracy": 0.13480910956859588,
|
|
"num_tokens": 44920552.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 6.553461790084839,
|
|
"epoch": 2.222055754722029,
|
|
"grad_norm": 5.46875,
|
|
"learning_rate": 0.0004511243813767446,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.1313568703830242,
|
|
"num_tokens": 44932090.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 6.6229747295379635,
|
|
"epoch": 2.222590828829793,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000451100586031332,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.1328655958175659,
|
|
"num_tokens": 44944122.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 6.620243978500366,
|
|
"epoch": 2.2231259029375567,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.00045107678560103953,
|
|
"loss": 6.2539,
|
|
"mean_token_accuracy": 0.13433120846748353,
|
|
"num_tokens": 44955104.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 6.575278806686401,
|
|
"epoch": 2.223660977045321,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00045105298008655485,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.13889905139803888,
|
|
"num_tokens": 44965495.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 6.554048633575439,
|
|
"epoch": 2.2241960511530845,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00045102916948856493,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.13465714752674102,
|
|
"num_tokens": 44976627.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 6.629545021057129,
|
|
"epoch": 2.2247311252608486,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004510053538077576,
|
|
"loss": 6.2918,
|
|
"mean_token_accuracy": 0.1343181885778904,
|
|
"num_tokens": 44987955.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 6.686997938156128,
|
|
"epoch": 2.2252661993686127,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004509815330448203,
|
|
"loss": 6.2435,
|
|
"mean_token_accuracy": 0.135974407941103,
|
|
"num_tokens": 44998124.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 6.660250186920166,
|
|
"epoch": 2.2258012734763764,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000450957707200441,
|
|
"loss": 6.2633,
|
|
"mean_token_accuracy": 0.1334424674510956,
|
|
"num_tokens": 45007881.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 6.606856346130371,
|
|
"epoch": 2.2263363475841405,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004509338762753076,
|
|
"loss": 6.2148,
|
|
"mean_token_accuracy": 0.14261817187070847,
|
|
"num_tokens": 45018994.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 6.569690847396851,
|
|
"epoch": 2.2268714216919046,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004509100402701083,
|
|
"loss": 6.2883,
|
|
"mean_token_accuracy": 0.1362292967736721,
|
|
"num_tokens": 45030109.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 6.450086259841919,
|
|
"epoch": 2.227406495799668,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00045088619918553136,
|
|
"loss": 6.1713,
|
|
"mean_token_accuracy": 0.1497543826699257,
|
|
"num_tokens": 45039872.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 6.6232834815979,
|
|
"epoch": 2.2279415699074323,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004508623530222651,
|
|
"loss": 6.1737,
|
|
"mean_token_accuracy": 0.14561225324869156,
|
|
"num_tokens": 45049216.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 6.541246128082276,
|
|
"epoch": 2.228476644015196,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00045083850178099805,
|
|
"loss": 6.1428,
|
|
"mean_token_accuracy": 0.1506657913327217,
|
|
"num_tokens": 45059191.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 6.524127388000489,
|
|
"epoch": 2.22901171812296,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000450814645462419,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.14425912126898766,
|
|
"num_tokens": 45069212.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 6.549907112121582,
|
|
"epoch": 2.229546792230724,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.00045079078406721676,
|
|
"loss": 6.1813,
|
|
"mean_token_accuracy": 0.13748989701271058,
|
|
"num_tokens": 45080248.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 6.593059825897217,
|
|
"epoch": 2.230081866338488,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00045076691759608035,
|
|
"loss": 6.2023,
|
|
"mean_token_accuracy": 0.13422387540340425,
|
|
"num_tokens": 45091315.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 6.590615463256836,
|
|
"epoch": 2.230616940446252,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00045074304604969886,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.14029399380087854,
|
|
"num_tokens": 45102674.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 6.567454385757446,
|
|
"epoch": 2.2311520145540156,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00045071916942876163,
|
|
"loss": 6.2092,
|
|
"mean_token_accuracy": 0.13777123019099236,
|
|
"num_tokens": 45113171.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 6.563689374923706,
|
|
"epoch": 2.2316870886617797,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004506952877339581,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.1405326656997204,
|
|
"num_tokens": 45122912.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 6.636022567749023,
|
|
"epoch": 2.2322221627695438,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004506714009659778,
|
|
"loss": 6.2388,
|
|
"mean_token_accuracy": 0.14083116948604585,
|
|
"num_tokens": 45133839.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 6.566247224807739,
|
|
"epoch": 2.2327572368773074,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004506475091255105,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.14455747455358506,
|
|
"num_tokens": 45144914.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 6.544160842895508,
|
|
"epoch": 2.2332923109850715,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000450623612213246,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.1406594380736351,
|
|
"num_tokens": 45155194.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 6.592961597442627,
|
|
"epoch": 2.233827385092835,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045059971022987446,
|
|
"loss": 6.342,
|
|
"mean_token_accuracy": 0.13420788422226906,
|
|
"num_tokens": 45166771.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 6.605739641189575,
|
|
"epoch": 2.2343624592005993,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00045057580317608585,
|
|
"loss": 6.179,
|
|
"mean_token_accuracy": 0.13810787051916124,
|
|
"num_tokens": 45177236.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 6.581020355224609,
|
|
"epoch": 2.2348975333083634,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00045055189105257064,
|
|
"loss": 6.2195,
|
|
"mean_token_accuracy": 0.13225647583603858,
|
|
"num_tokens": 45187382.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 6.580011320114136,
|
|
"epoch": 2.235432607416127,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00045052797386001936,
|
|
"loss": 6.2238,
|
|
"mean_token_accuracy": 0.1431779831647873,
|
|
"num_tokens": 45197287.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 6.6294886589050295,
|
|
"epoch": 2.235967681523891,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004505040515991224,
|
|
"loss": 6.2053,
|
|
"mean_token_accuracy": 0.14543160870671273,
|
|
"num_tokens": 45208737.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 6.611729669570923,
|
|
"epoch": 2.236502755631655,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00045048012427057057,
|
|
"loss": 6.3028,
|
|
"mean_token_accuracy": 0.13180789947509766,
|
|
"num_tokens": 45219586.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 6.631686019897461,
|
|
"epoch": 2.237037829739419,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004504561918750549,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.12554254606366158,
|
|
"num_tokens": 45230730.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 6.625497627258301,
|
|
"epoch": 2.237572903847183,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004504322544132663,
|
|
"loss": 6.1292,
|
|
"mean_token_accuracy": 0.1503148064017296,
|
|
"num_tokens": 45241330.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 6.4672304630279545,
|
|
"epoch": 2.2381079779549466,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000450408311885896,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.13956911340355874,
|
|
"num_tokens": 45251439.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 6.496202993392944,
|
|
"epoch": 2.2386430520627107,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045038436429363537,
|
|
"loss": 6.0405,
|
|
"mean_token_accuracy": 0.14421598315238954,
|
|
"num_tokens": 45262078.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 6.613201379776001,
|
|
"epoch": 2.2391781261704744,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045036041163717586,
|
|
"loss": 6.2563,
|
|
"mean_token_accuracy": 0.13553860560059547,
|
|
"num_tokens": 45272466.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 6.592843151092529,
|
|
"epoch": 2.2397132002782385,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004503364539172091,
|
|
"loss": 6.1742,
|
|
"mean_token_accuracy": 0.142956680059433,
|
|
"num_tokens": 45281830.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 6.492534399032593,
|
|
"epoch": 2.2402482743860026,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004503124911344268,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.1290408693253994,
|
|
"num_tokens": 45293026.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 6.630679941177368,
|
|
"epoch": 2.2407833484937663,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045028852328952106,
|
|
"loss": 6.2251,
|
|
"mean_token_accuracy": 0.13686614111065865,
|
|
"num_tokens": 45303532.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 6.489639377593994,
|
|
"epoch": 2.2413184226015304,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004502645503831838,
|
|
"loss": 6.1003,
|
|
"mean_token_accuracy": 0.14967215061187744,
|
|
"num_tokens": 45314448.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 6.552432727813721,
|
|
"epoch": 2.241853496709294,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045024057241610727,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.1330533280968666,
|
|
"num_tokens": 45323194.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 6.583135604858398,
|
|
"epoch": 2.242388570817058,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004502165893889839,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.1538370095193386,
|
|
"num_tokens": 45333464.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 6.565091228485107,
|
|
"epoch": 2.242923644924822,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004501926013025061,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.13789451196789743,
|
|
"num_tokens": 45344364.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 6.606811666488648,
|
|
"epoch": 2.243458719032586,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045016860815736646,
|
|
"loss": 6.1899,
|
|
"mean_token_accuracy": 0.14026373326778413,
|
|
"num_tokens": 45355202.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 6.552300643920899,
|
|
"epoch": 2.24399379314035,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004501446099542579,
|
|
"loss": 6.1326,
|
|
"mean_token_accuracy": 0.14296514987945558,
|
|
"num_tokens": 45365696.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 6.499941158294678,
|
|
"epoch": 2.244528867248114,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004501206066938734,
|
|
"loss": 6.1584,
|
|
"mean_token_accuracy": 0.13991134762763976,
|
|
"num_tokens": 45376609.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 6.633443403244018,
|
|
"epoch": 2.2450639413558777,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045009659837690606,
|
|
"loss": 6.3047,
|
|
"mean_token_accuracy": 0.124668949842453,
|
|
"num_tokens": 45386158.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 6.6999983310699465,
|
|
"epoch": 2.245599015463642,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000450072585004049,
|
|
"loss": 6.2946,
|
|
"mean_token_accuracy": 0.13415922820568085,
|
|
"num_tokens": 45396824.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 6.612515497207641,
|
|
"epoch": 2.2461340895714055,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004500485665759955,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.1379229672253132,
|
|
"num_tokens": 45407219.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 6.567481470108032,
|
|
"epoch": 2.2466691636791696,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004500245430934394,
|
|
"loss": 6.2783,
|
|
"mean_token_accuracy": 0.1265104778110981,
|
|
"num_tokens": 45418572.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 6.555287456512451,
|
|
"epoch": 2.2472042377869337,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00045000051455707413,
|
|
"loss": 6.1645,
|
|
"mean_token_accuracy": 0.1386981040239334,
|
|
"num_tokens": 45429643.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.2472042377869337,
|
|
"eval_entropy": 6.423131566548926,
|
|
"eval_loss": 6.357901096343994,
|
|
"eval_mean_token_accuracy": 0.13938838401332376,
|
|
"eval_num_tokens": 45429643.0,
|
|
"eval_runtime": 22.8553,
|
|
"eval_samples_per_second": 1298.558,
|
|
"eval_steps_per_second": 162.325,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 6.620022916793824,
|
|
"epoch": 2.2477393118946973,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004499764809675937,
|
|
"loss": 6.1813,
|
|
"mean_token_accuracy": 0.14135412126779556,
|
|
"num_tokens": 45440183.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 6.576360464096069,
|
|
"epoch": 2.2482743860024614,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004499524423256918,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.13582171127200127,
|
|
"num_tokens": 45451252.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 6.533924770355225,
|
|
"epoch": 2.248809460110225,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00044992839863206284,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.13770029693841934,
|
|
"num_tokens": 45462336.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 6.550244235992432,
|
|
"epoch": 2.249344534217989,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00044990434988740095,
|
|
"loss": 6.2146,
|
|
"mean_token_accuracy": 0.1370294488966465,
|
|
"num_tokens": 45472526.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 6.626816368103027,
|
|
"epoch": 2.2498796083257533,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004498802960924005,
|
|
"loss": 6.2769,
|
|
"mean_token_accuracy": 0.13138353526592256,
|
|
"num_tokens": 45483281.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 6.655478668212891,
|
|
"epoch": 2.250414682433517,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004498562372477561,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.14250532016158104,
|
|
"num_tokens": 45494258.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 6.611414527893066,
|
|
"epoch": 2.250949756541281,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004498321733541624,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.1360429860651493,
|
|
"num_tokens": 45504233.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 6.557222557067871,
|
|
"epoch": 2.2514848306490447,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00044980810441231424,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.1419654168188572,
|
|
"num_tokens": 45513902.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 6.589977216720581,
|
|
"epoch": 2.252019904756809,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004497840304229066,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.14096261635422708,
|
|
"num_tokens": 45524111.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 6.583997964859009,
|
|
"epoch": 2.252554978864573,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00044975995138663466,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.13745391741394997,
|
|
"num_tokens": 45534816.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 6.595811462402343,
|
|
"epoch": 2.2530900529723366,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00044973586730419373,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.14393639117479323,
|
|
"num_tokens": 45546012.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 6.52909836769104,
|
|
"epoch": 2.2536251270801007,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004497117781762792,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.14106843918561934,
|
|
"num_tokens": 45555402.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 6.539710140228271,
|
|
"epoch": 2.2541602011878643,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004496876840035866,
|
|
"loss": 6.2263,
|
|
"mean_token_accuracy": 0.1385742872953415,
|
|
"num_tokens": 45565537.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 6.593047857284546,
|
|
"epoch": 2.2546952752956284,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00044966358478681163,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.14454827904701234,
|
|
"num_tokens": 45576449.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 6.676673936843872,
|
|
"epoch": 2.2552303494033925,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004496394805266502,
|
|
"loss": 6.2339,
|
|
"mean_token_accuracy": 0.13167814761400223,
|
|
"num_tokens": 45586477.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 6.5287150859832765,
|
|
"epoch": 2.255765423511156,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00044961537122379844,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.13794239684939386,
|
|
"num_tokens": 45597279.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 6.591759061813354,
|
|
"epoch": 2.2563004976189203,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004495912568789522,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.13251241147518159,
|
|
"num_tokens": 45608216.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 6.584631633758545,
|
|
"epoch": 2.2568355717266844,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00044956713749280805,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.14192432165145874,
|
|
"num_tokens": 45620665.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 6.629117012023926,
|
|
"epoch": 2.257370645834448,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00044954301306606234,
|
|
"loss": 6.2242,
|
|
"mean_token_accuracy": 0.13804905340075493,
|
|
"num_tokens": 45631635.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 6.470837497711182,
|
|
"epoch": 2.257905719942212,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00044951888359941156,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.14540730714797973,
|
|
"num_tokens": 45642507.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 6.521148300170898,
|
|
"epoch": 2.2584407940499758,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00044949474909355264,
|
|
"loss": 6.2093,
|
|
"mean_token_accuracy": 0.13597728908061982,
|
|
"num_tokens": 45653123.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 6.6253598690032955,
|
|
"epoch": 2.25897586815774,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.00044947060954918233,
|
|
"loss": 6.1932,
|
|
"mean_token_accuracy": 0.14091432690620423,
|
|
"num_tokens": 45663228.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 6.61837477684021,
|
|
"epoch": 2.2595109422655035,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004494464649669976,
|
|
"loss": 6.2153,
|
|
"mean_token_accuracy": 0.14023588523268699,
|
|
"num_tokens": 45673389.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 6.541274976730347,
|
|
"epoch": 2.2600460163732676,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00044942231534769587,
|
|
"loss": 6.1985,
|
|
"mean_token_accuracy": 0.1389498233795166,
|
|
"num_tokens": 45684803.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 6.531466293334961,
|
|
"epoch": 2.2605810904810317,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00044939816069197415,
|
|
"loss": 6.2412,
|
|
"mean_token_accuracy": 0.1405462309718132,
|
|
"num_tokens": 45695164.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 6.611288118362427,
|
|
"epoch": 2.2611161645887954,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00044937400100053017,
|
|
"loss": 6.2576,
|
|
"mean_token_accuracy": 0.14161428362131118,
|
|
"num_tokens": 45706169.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 6.676942682266235,
|
|
"epoch": 2.2616512386965595,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004493498362740613,
|
|
"loss": 6.326,
|
|
"mean_token_accuracy": 0.12880936935544013,
|
|
"num_tokens": 45717299.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 6.5807562351226805,
|
|
"epoch": 2.2621863128043236,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00044932566651326546,
|
|
"loss": 6.1945,
|
|
"mean_token_accuracy": 0.14285514876246452,
|
|
"num_tokens": 45728815.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 6.589425325393677,
|
|
"epoch": 2.2627213869120872,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004493014917188405,
|
|
"loss": 6.2606,
|
|
"mean_token_accuracy": 0.1398294411599636,
|
|
"num_tokens": 45740293.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 6.594993734359742,
|
|
"epoch": 2.2632564610198513,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00044927731189148447,
|
|
"loss": 6.1967,
|
|
"mean_token_accuracy": 0.1392090402543545,
|
|
"num_tokens": 45751243.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 6.483538627624512,
|
|
"epoch": 2.263791535127615,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00044925312703189546,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.13829605653882027,
|
|
"num_tokens": 45762477.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 6.590510320663452,
|
|
"epoch": 2.264326609235379,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000449228937140772,
|
|
"loss": 6.205,
|
|
"mean_token_accuracy": 0.1428476646542549,
|
|
"num_tokens": 45772929.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 6.575795316696167,
|
|
"epoch": 2.264861683343143,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00044920474221881243,
|
|
"loss": 6.203,
|
|
"mean_token_accuracy": 0.14052318781614304,
|
|
"num_tokens": 45782999.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 6.481068277359009,
|
|
"epoch": 2.265396757450907,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00044918054226671545,
|
|
"loss": 6.2107,
|
|
"mean_token_accuracy": 0.1428921103477478,
|
|
"num_tokens": 45793020.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 6.597474384307861,
|
|
"epoch": 2.265931831558671,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00044915633728517975,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.14650665000081062,
|
|
"num_tokens": 45803020.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 6.575968647003174,
|
|
"epoch": 2.2664669056664346,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004491321272749042,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.14052460119128227,
|
|
"num_tokens": 45812700.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 6.573241758346557,
|
|
"epoch": 2.2670019797741987,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00044910791223658805,
|
|
"loss": 6.2613,
|
|
"mean_token_accuracy": 0.13801420405507087,
|
|
"num_tokens": 45823097.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 6.579110813140869,
|
|
"epoch": 2.267537053881963,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00044908369217093035,
|
|
"loss": 6.1725,
|
|
"mean_token_accuracy": 0.13683705776929855,
|
|
"num_tokens": 45832935.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 6.619824552536011,
|
|
"epoch": 2.2680721279897265,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.00044905946707863057,
|
|
"loss": 6.3095,
|
|
"mean_token_accuracy": 0.12927604466676712,
|
|
"num_tokens": 45844296.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 6.5791614055633545,
|
|
"epoch": 2.2686072020974906,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004490352369603881,
|
|
"loss": 6.228,
|
|
"mean_token_accuracy": 0.13591959774494172,
|
|
"num_tokens": 45854942.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 6.610316610336303,
|
|
"epoch": 2.2691422762052547,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00044901100181690256,
|
|
"loss": 6.2958,
|
|
"mean_token_accuracy": 0.13932087197899817,
|
|
"num_tokens": 45866427.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 6.628189611434936,
|
|
"epoch": 2.2696773503130183,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00044898676164887387,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.13814638927578926,
|
|
"num_tokens": 45877955.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 6.597223234176636,
|
|
"epoch": 2.2702124244207824,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00044896251645700185,
|
|
"loss": 6.1116,
|
|
"mean_token_accuracy": 0.15180970579385758,
|
|
"num_tokens": 45888668.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 6.520671606063843,
|
|
"epoch": 2.270747498528546,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004489382662419866,
|
|
"loss": 6.2087,
|
|
"mean_token_accuracy": 0.13952710703015328,
|
|
"num_tokens": 45898819.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 6.5697835922241214,
|
|
"epoch": 2.27128257263631,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004489140110045283,
|
|
"loss": 6.2464,
|
|
"mean_token_accuracy": 0.13808191418647767,
|
|
"num_tokens": 45909390.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 6.590308475494385,
|
|
"epoch": 2.271817646744074,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004488897507453275,
|
|
"loss": 6.1892,
|
|
"mean_token_accuracy": 0.13915675804018973,
|
|
"num_tokens": 45919697.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 6.634515380859375,
|
|
"epoch": 2.272352720851838,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00044886548546508453,
|
|
"loss": 6.2568,
|
|
"mean_token_accuracy": 0.14091005325317382,
|
|
"num_tokens": 45929458.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 6.525170946121216,
|
|
"epoch": 2.272887794959602,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004488412151645001,
|
|
"loss": 6.1294,
|
|
"mean_token_accuracy": 0.1411816358566284,
|
|
"num_tokens": 45939373.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 6.464337015151978,
|
|
"epoch": 2.2734228690673657,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00044881693984427504,
|
|
"loss": 6.2058,
|
|
"mean_token_accuracy": 0.13582992777228356,
|
|
"num_tokens": 45949954.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 6.591743230819702,
|
|
"epoch": 2.27395794317513,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004487926595051102,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.1373317539691925,
|
|
"num_tokens": 45960147.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 6.6388387203216555,
|
|
"epoch": 2.274493017282894,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004487683741477068,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.14041801542043686,
|
|
"num_tokens": 45970718.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 6.572554302215576,
|
|
"epoch": 2.2750280913906575,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000448744083772766,
|
|
"loss": 6.2101,
|
|
"mean_token_accuracy": 0.13963003382086753,
|
|
"num_tokens": 45981631.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 6.623730230331421,
|
|
"epoch": 2.2755631654984216,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00044871978838098917,
|
|
"loss": 6.2673,
|
|
"mean_token_accuracy": 0.13465490490198134,
|
|
"num_tokens": 45992295.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 6.657938861846924,
|
|
"epoch": 2.2760982396061853,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004486954879730778,
|
|
"loss": 6.242,
|
|
"mean_token_accuracy": 0.13363970965147018,
|
|
"num_tokens": 46002222.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 6.574161243438721,
|
|
"epoch": 2.2766333137139494,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004486711825497337,
|
|
"loss": 6.1176,
|
|
"mean_token_accuracy": 0.15163662880659104,
|
|
"num_tokens": 46012393.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 6.522473955154419,
|
|
"epoch": 2.2771683878217135,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00044864687211165863,
|
|
"loss": 6.1987,
|
|
"mean_token_accuracy": 0.14101213738322257,
|
|
"num_tokens": 46022095.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 6.575163269042969,
|
|
"epoch": 2.277703461929477,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00044862255665955447,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.1374075561761856,
|
|
"num_tokens": 46032973.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 6.595778274536133,
|
|
"epoch": 2.2782385360372412,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004485982361941234,
|
|
"loss": 6.1991,
|
|
"mean_token_accuracy": 0.1403585970401764,
|
|
"num_tokens": 46043430.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 6.53571195602417,
|
|
"epoch": 2.278773610145005,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004485739107160677,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.14040687531232834,
|
|
"num_tokens": 46054580.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 6.54841890335083,
|
|
"epoch": 2.279308684252769,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00044854958022608974,
|
|
"loss": 6.2237,
|
|
"mean_token_accuracy": 0.1450565740466118,
|
|
"num_tokens": 46064898.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 6.566688776016235,
|
|
"epoch": 2.279843758360533,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00044852524472489196,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.1373706966638565,
|
|
"num_tokens": 46075985.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 6.618686389923096,
|
|
"epoch": 2.2803788324682968,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004485009042131771,
|
|
"loss": 6.2914,
|
|
"mean_token_accuracy": 0.13356651216745377,
|
|
"num_tokens": 46087544.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 6.621676015853882,
|
|
"epoch": 2.280913906576061,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00044847655869164813,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.1345014527440071,
|
|
"num_tokens": 46097613.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 6.505275249481201,
|
|
"epoch": 2.281448980683825,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004484522081610078,
|
|
"loss": 6.1338,
|
|
"mean_token_accuracy": 0.15520013868808746,
|
|
"num_tokens": 46107728.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 6.510373735427857,
|
|
"epoch": 2.2819840547915886,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00044842785262195936,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.13722736835479737,
|
|
"num_tokens": 46118309.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 6.5600972175598145,
|
|
"epoch": 2.2825191288993527,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.00044840349207520604,
|
|
"loss": 6.202,
|
|
"mean_token_accuracy": 0.14572459682822228,
|
|
"num_tokens": 46128425.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 6.633022499084473,
|
|
"epoch": 2.2830542030071164,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004483791265214513,
|
|
"loss": 6.3188,
|
|
"mean_token_accuracy": 0.13185100480914116,
|
|
"num_tokens": 46139506.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 6.610679674148559,
|
|
"epoch": 2.2835892771148805,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00044835475596139855,
|
|
"loss": 6.2155,
|
|
"mean_token_accuracy": 0.13927485570311546,
|
|
"num_tokens": 46151226.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 6.6427360534667965,
|
|
"epoch": 2.284124351222644,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004483303803957516,
|
|
"loss": 6.2596,
|
|
"mean_token_accuracy": 0.1356756642460823,
|
|
"num_tokens": 46162749.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 6.61524453163147,
|
|
"epoch": 2.2846594253304082,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004483059998252144,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.14033842757344245,
|
|
"num_tokens": 46174802.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 6.614740324020386,
|
|
"epoch": 2.2851944994381723,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00044828161425049067,
|
|
"loss": 6.1944,
|
|
"mean_token_accuracy": 0.140848508477211,
|
|
"num_tokens": 46185579.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 6.6383952617645265,
|
|
"epoch": 2.285729573545936,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00044825722367228477,
|
|
"loss": 6.3055,
|
|
"mean_token_accuracy": 0.13319142088294028,
|
|
"num_tokens": 46196399.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 6.623202085494995,
|
|
"epoch": 2.2862646476537,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00044823282809130084,
|
|
"loss": 6.2317,
|
|
"mean_token_accuracy": 0.13208706676959991,
|
|
"num_tokens": 46206931.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 6.571099281311035,
|
|
"epoch": 2.286799721761464,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00044820842750824334,
|
|
"loss": 6.2175,
|
|
"mean_token_accuracy": 0.1428168386220932,
|
|
"num_tokens": 46217327.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 6.574071884155273,
|
|
"epoch": 2.287334795869228,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00044818402192381684,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.13855075389146804,
|
|
"num_tokens": 46227981.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 6.573427438735962,
|
|
"epoch": 2.287869869976992,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00044815961133872606,
|
|
"loss": 6.274,
|
|
"mean_token_accuracy": 0.13296961188316345,
|
|
"num_tokens": 46238500.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 6.503869915008545,
|
|
"epoch": 2.2884049440847556,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044813519575367586,
|
|
"loss": 6.1411,
|
|
"mean_token_accuracy": 0.14513339549303056,
|
|
"num_tokens": 46249530.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 6.5638597965240475,
|
|
"epoch": 2.2889400181925197,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004481107751693711,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.13861719146370888,
|
|
"num_tokens": 46260272.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 6.5337118148803714,
|
|
"epoch": 2.2894750923002833,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004480863495865171,
|
|
"loss": 6.1874,
|
|
"mean_token_accuracy": 0.13893595933914185,
|
|
"num_tokens": 46271805.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 6.5811597347259525,
|
|
"epoch": 2.2900101664080474,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004480619190058191,
|
|
"loss": 6.236,
|
|
"mean_token_accuracy": 0.13779565393924714,
|
|
"num_tokens": 46282211.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 6.497325372695923,
|
|
"epoch": 2.2905452405158115,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00044803748342798247,
|
|
"loss": 6.1478,
|
|
"mean_token_accuracy": 0.14273095726966858,
|
|
"num_tokens": 46292287.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 6.542933225631714,
|
|
"epoch": 2.291080314623575,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00044801304285371286,
|
|
"loss": 6.2652,
|
|
"mean_token_accuracy": 0.13633257374167443,
|
|
"num_tokens": 46302978.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 6.569995403289795,
|
|
"epoch": 2.2916153887313393,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004479885972837159,
|
|
"loss": 6.2403,
|
|
"mean_token_accuracy": 0.1396270513534546,
|
|
"num_tokens": 46313958.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 6.65785174369812,
|
|
"epoch": 2.2921504628391034,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004479641467186975,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.13433297201991082,
|
|
"num_tokens": 46325262.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 6.59770565032959,
|
|
"epoch": 2.292685536946867,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044793969115936375,
|
|
"loss": 6.275,
|
|
"mean_token_accuracy": 0.13918232619762422,
|
|
"num_tokens": 46336773.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 6.5203145980834964,
|
|
"epoch": 2.293220611054631,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004479152306064207,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.13982990235090256,
|
|
"num_tokens": 46346616.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 6.534423875808716,
|
|
"epoch": 2.293755685162395,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004478907650605745,
|
|
"loss": 6.2321,
|
|
"mean_token_accuracy": 0.13900470435619355,
|
|
"num_tokens": 46358564.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 6.598055171966553,
|
|
"epoch": 2.294290759270159,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00044786629452253196,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.1487185224890709,
|
|
"num_tokens": 46369207.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 6.600506734848023,
|
|
"epoch": 2.294825833377923,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004478418189929994,
|
|
"loss": 6.1943,
|
|
"mean_token_accuracy": 0.14107945635914804,
|
|
"num_tokens": 46379382.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 6.503506278991699,
|
|
"epoch": 2.2953609074856867,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.00044781733847268357,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.1306885652244091,
|
|
"num_tokens": 46390738.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 6.518324327468872,
|
|
"epoch": 2.2958959815934508,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00044779285296229137,
|
|
"loss": 6.1139,
|
|
"mean_token_accuracy": 0.1453678496181965,
|
|
"num_tokens": 46401740.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 6.640698528289795,
|
|
"epoch": 2.2964310557012144,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00044776836246252985,
|
|
"loss": 6.1631,
|
|
"mean_token_accuracy": 0.1414472371339798,
|
|
"num_tokens": 46412009.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 6.618959283828735,
|
|
"epoch": 2.2969661298089785,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004477438669741061,
|
|
"loss": 6.2604,
|
|
"mean_token_accuracy": 0.13677583038806915,
|
|
"num_tokens": 46422550.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 6.630204534530639,
|
|
"epoch": 2.2975012039167426,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004477193664977275,
|
|
"loss": 6.2435,
|
|
"mean_token_accuracy": 0.13979279696941377,
|
|
"num_tokens": 46432797.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 6.485927724838257,
|
|
"epoch": 2.2980362780245063,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004476948610341015,
|
|
"loss": 6.0733,
|
|
"mean_token_accuracy": 0.1477263778448105,
|
|
"num_tokens": 46444638.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 6.556946563720703,
|
|
"epoch": 2.2985713521322704,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00044767035058393564,
|
|
"loss": 6.1582,
|
|
"mean_token_accuracy": 0.1421547129750252,
|
|
"num_tokens": 46455404.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 6.527092933654785,
|
|
"epoch": 2.2991064262400345,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00044764583514793766,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.13768905103206636,
|
|
"num_tokens": 46466821.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 6.60277795791626,
|
|
"epoch": 2.299641500347798,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004476213147268154,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.13924731761217118,
|
|
"num_tokens": 46477222.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 6.5981849193572994,
|
|
"epoch": 2.3001765744555622,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00044759678932127693,
|
|
"loss": 6.1796,
|
|
"mean_token_accuracy": 0.1414933241903782,
|
|
"num_tokens": 46488596.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 6.587899684906006,
|
|
"epoch": 2.300711648563326,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00044757225893203047,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.13643549382686615,
|
|
"num_tokens": 46499799.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 6.604064321517944,
|
|
"epoch": 2.30124672267109,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004475477235597843,
|
|
"loss": 6.27,
|
|
"mean_token_accuracy": 0.1425755187869072,
|
|
"num_tokens": 46511077.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 6.6288646221160885,
|
|
"epoch": 2.3017817967788536,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004475231832052469,
|
|
"loss": 6.2969,
|
|
"mean_token_accuracy": 0.1315444938838482,
|
|
"num_tokens": 46523517.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 6.591297769546509,
|
|
"epoch": 2.3023168708866177,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004474986378691267,
|
|
"loss": 6.1979,
|
|
"mean_token_accuracy": 0.14165833219885826,
|
|
"num_tokens": 46533198.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 6.580213022232056,
|
|
"epoch": 2.302851944994382,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00044747408755213265,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.13396124839782714,
|
|
"num_tokens": 46544659.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 6.537385749816894,
|
|
"epoch": 2.3033870191021455,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00044744953225497354,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.13289897963404657,
|
|
"num_tokens": 46555897.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 6.577791023254394,
|
|
"epoch": 2.3039220932099096,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00044742497197835845,
|
|
"loss": 6.1978,
|
|
"mean_token_accuracy": 0.1402841880917549,
|
|
"num_tokens": 46565695.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 6.648237037658691,
|
|
"epoch": 2.3044571673176737,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004474004067229965,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.1321396015584469,
|
|
"num_tokens": 46576620.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 6.676483821868897,
|
|
"epoch": 2.3049922414254373,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000447375836489597,
|
|
"loss": 6.2991,
|
|
"mean_token_accuracy": 0.1328316994011402,
|
|
"num_tokens": 46588264.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 6.612703657150268,
|
|
"epoch": 2.3055273155332014,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00044735126127886944,
|
|
"loss": 6.2106,
|
|
"mean_token_accuracy": 0.13663850203156472,
|
|
"num_tokens": 46600180.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 6.576396799087524,
|
|
"epoch": 2.306062389640965,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004473266810915235,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.1415916457772255,
|
|
"num_tokens": 46610391.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 6.585912847518921,
|
|
"epoch": 2.306597463748729,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004473020959282688,
|
|
"loss": 6.2763,
|
|
"mean_token_accuracy": 0.13886235430836677,
|
|
"num_tokens": 46622955.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 6.614183568954468,
|
|
"epoch": 2.3071325378564933,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00044727750578981535,
|
|
"loss": 6.2477,
|
|
"mean_token_accuracy": 0.13635684698820114,
|
|
"num_tokens": 46632361.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 6.5604596614837645,
|
|
"epoch": 2.307667611964257,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004472529106768731,
|
|
"loss": 6.1995,
|
|
"mean_token_accuracy": 0.13886631280183792,
|
|
"num_tokens": 46642693.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 6.560416555404663,
|
|
"epoch": 2.308202686072021,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004472283105901522,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.14183820337057113,
|
|
"num_tokens": 46653251.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 6.648093509674072,
|
|
"epoch": 2.3087377601797847,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004472037055303631,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.1323258750140667,
|
|
"num_tokens": 46664751.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 6.525610828399659,
|
|
"epoch": 2.309272834287549,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004471790954982162,
|
|
"loss": 6.2088,
|
|
"mean_token_accuracy": 0.13264587223529817,
|
|
"num_tokens": 46676825.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 6.562147712707519,
|
|
"epoch": 2.309807908395313,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004471544804944221,
|
|
"loss": 6.1724,
|
|
"mean_token_accuracy": 0.14485999941825867,
|
|
"num_tokens": 46687202.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 6.600687742233276,
|
|
"epoch": 2.3103429825030766,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004471298605196916,
|
|
"loss": 6.3018,
|
|
"mean_token_accuracy": 0.13413620367646217,
|
|
"num_tokens": 46697687.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 6.52313003540039,
|
|
"epoch": 2.3108780566108407,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.00044710523557473544,
|
|
"loss": 6.172,
|
|
"mean_token_accuracy": 0.14281018674373627,
|
|
"num_tokens": 46709088.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 6.584764575958252,
|
|
"epoch": 2.3114131307186048,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00044708060566026487,
|
|
"loss": 6.2539,
|
|
"mean_token_accuracy": 0.13895513191819192,
|
|
"num_tokens": 46721675.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 6.643505001068116,
|
|
"epoch": 2.3119482048263684,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000447055970776991,
|
|
"loss": 6.2442,
|
|
"mean_token_accuracy": 0.14027330353856088,
|
|
"num_tokens": 46731854.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 6.597783994674683,
|
|
"epoch": 2.3124832789341325,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00044703133092562514,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.1349008060991764,
|
|
"num_tokens": 46742815.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 6.534633731842041,
|
|
"epoch": 2.313018353041896,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00044700668610687884,
|
|
"loss": 6.2096,
|
|
"mean_token_accuracy": 0.14512321650981902,
|
|
"num_tokens": 46753012.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 6.533611059188843,
|
|
"epoch": 2.3135534271496603,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00044698203632146353,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.1395387500524521,
|
|
"num_tokens": 46763701.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 6.654627084732056,
|
|
"epoch": 2.314088501257424,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004469573815700911,
|
|
"loss": 6.2621,
|
|
"mean_token_accuracy": 0.13091326355934144,
|
|
"num_tokens": 46775407.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 6.5231317520141605,
|
|
"epoch": 2.314623575365188,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00044693272185347357,
|
|
"loss": 6.1464,
|
|
"mean_token_accuracy": 0.1422886461019516,
|
|
"num_tokens": 46786282.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 6.534490346908569,
|
|
"epoch": 2.315158649472952,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004469080571723228,
|
|
"loss": 6.2462,
|
|
"mean_token_accuracy": 0.1348537966609001,
|
|
"num_tokens": 46796768.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 6.56196780204773,
|
|
"epoch": 2.315693723580716,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00044688338752735095,
|
|
"loss": 6.1442,
|
|
"mean_token_accuracy": 0.14024894684553146,
|
|
"num_tokens": 46806538.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 6.580567502975464,
|
|
"epoch": 2.31622879768848,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004468587129192705,
|
|
"loss": 6.1372,
|
|
"mean_token_accuracy": 0.1493992656469345,
|
|
"num_tokens": 46816692.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 6.532517719268799,
|
|
"epoch": 2.316763871796244,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00044683403334879384,
|
|
"loss": 6.2277,
|
|
"mean_token_accuracy": 0.14620931595563888,
|
|
"num_tokens": 46827551.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 6.5661383152008055,
|
|
"epoch": 2.3172989459040076,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004468093488166337,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.1294407866895199,
|
|
"num_tokens": 46840168.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 6.6199544906616214,
|
|
"epoch": 2.3178340200117717,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00044678465932350273,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.14295195713639258,
|
|
"num_tokens": 46851086.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 6.546455240249633,
|
|
"epoch": 2.3183690941195354,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00044675996487011373,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.14708448871970176,
|
|
"num_tokens": 46861830.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 6.598917484283447,
|
|
"epoch": 2.3189041682272995,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00044673526545718,
|
|
"loss": 6.2282,
|
|
"mean_token_accuracy": 0.14443652778863908,
|
|
"num_tokens": 46871348.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 6.561430597305298,
|
|
"epoch": 2.3194392423350636,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004467105610854146,
|
|
"loss": 6.213,
|
|
"mean_token_accuracy": 0.1380787596106529,
|
|
"num_tokens": 46882737.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 6.609207582473755,
|
|
"epoch": 2.3199743164428273,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00044668585175553085,
|
|
"loss": 6.2763,
|
|
"mean_token_accuracy": 0.12967987656593322,
|
|
"num_tokens": 46893616.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 6.643645715713501,
|
|
"epoch": 2.3205093905505914,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004466611374682423,
|
|
"loss": 6.2084,
|
|
"mean_token_accuracy": 0.13792625591158866,
|
|
"num_tokens": 46904546.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 6.5849833488464355,
|
|
"epoch": 2.321044464658355,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00044663641822426244,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.13933669701218604,
|
|
"num_tokens": 46915513.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 6.649220991134643,
|
|
"epoch": 2.321579538766119,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00044661169402430517,
|
|
"loss": 6.2608,
|
|
"mean_token_accuracy": 0.13652921542525293,
|
|
"num_tokens": 46925535.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 6.517515373229981,
|
|
"epoch": 2.322114612873883,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00044658696486908443,
|
|
"loss": 6.2373,
|
|
"mean_token_accuracy": 0.14068458154797553,
|
|
"num_tokens": 46936222.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 6.52279052734375,
|
|
"epoch": 2.322649686981647,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004465622307593141,
|
|
"loss": 6.145,
|
|
"mean_token_accuracy": 0.14815887808799744,
|
|
"num_tokens": 46946855.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 6.566970777511597,
|
|
"epoch": 2.323184761089411,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00044653749169570845,
|
|
"loss": 6.2183,
|
|
"mean_token_accuracy": 0.13804322332143784,
|
|
"num_tokens": 46958246.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 6.495046091079712,
|
|
"epoch": 2.3237198351971746,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00044651274767898186,
|
|
"loss": 6.2191,
|
|
"mean_token_accuracy": 0.13895852267742156,
|
|
"num_tokens": 46969237.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 6.643564367294312,
|
|
"epoch": 2.3242549093049387,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004464879987098488,
|
|
"loss": 6.2831,
|
|
"mean_token_accuracy": 0.13591848462820053,
|
|
"num_tokens": 46979897.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 6.677999019622803,
|
|
"epoch": 2.324789983412703,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004464632447890238,
|
|
"loss": 6.1801,
|
|
"mean_token_accuracy": 0.14328082352876664,
|
|
"num_tokens": 46989833.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 6.508643865585327,
|
|
"epoch": 2.3253250575204665,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00044643848591722183,
|
|
"loss": 6.1749,
|
|
"mean_token_accuracy": 0.14676769822835922,
|
|
"num_tokens": 46999822.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 6.485074806213379,
|
|
"epoch": 2.3258601316282306,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00044641372209515764,
|
|
"loss": 6.1663,
|
|
"mean_token_accuracy": 0.14787330478429794,
|
|
"num_tokens": 47010176.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 6.5251851081848145,
|
|
"epoch": 2.3263952057359942,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004463889533235462,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.14453841149806976,
|
|
"num_tokens": 47020184.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 6.587107706069946,
|
|
"epoch": 2.3269302798437583,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00044636417960310294,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.13539543747901917,
|
|
"num_tokens": 47032066.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 6.619333982467651,
|
|
"epoch": 2.3274653539515224,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004463394009345431,
|
|
"loss": 6.2967,
|
|
"mean_token_accuracy": 0.13160070925951003,
|
|
"num_tokens": 47043571.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 6.639884614944458,
|
|
"epoch": 2.328000428059286,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00044631461731858195,
|
|
"loss": 6.2149,
|
|
"mean_token_accuracy": 0.1373543359339237,
|
|
"num_tokens": 47053813.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 6.619365787506103,
|
|
"epoch": 2.32853550216705,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00044628982875593546,
|
|
"loss": 6.2434,
|
|
"mean_token_accuracy": 0.13876141980290413,
|
|
"num_tokens": 47063671.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 6.512105989456177,
|
|
"epoch": 2.3290705762748143,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00044626503524731917,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.14519273042678832,
|
|
"num_tokens": 47073537.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 6.517653369903565,
|
|
"epoch": 2.329605650382578,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004462402367934491,
|
|
"loss": 6.2143,
|
|
"mean_token_accuracy": 0.13717902079224586,
|
|
"num_tokens": 47084272.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 6.5984447479248045,
|
|
"epoch": 2.330140724490342,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004462154333950412,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.1337424099445343,
|
|
"num_tokens": 47095198.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 6.692504072189331,
|
|
"epoch": 2.3306757985981057,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004461906250528117,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.1337990716099739,
|
|
"num_tokens": 47106540.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 6.611970090866089,
|
|
"epoch": 2.33121087270587,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000446165811767477,
|
|
"loss": 6.2641,
|
|
"mean_token_accuracy": 0.14458328932523729,
|
|
"num_tokens": 47117301.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 6.5499590873718265,
|
|
"epoch": 2.3317459468136335,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004461409935397536,
|
|
"loss": 6.2403,
|
|
"mean_token_accuracy": 0.1353599414229393,
|
|
"num_tokens": 47127058.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 6.557889366149903,
|
|
"epoch": 2.3322810209213976,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00044611617037035794,
|
|
"loss": 6.1879,
|
|
"mean_token_accuracy": 0.13895585834980012,
|
|
"num_tokens": 47137182.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 6.6298394203186035,
|
|
"epoch": 2.3328160950291617,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000446091342260007,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.1329098030924797,
|
|
"num_tokens": 47148591.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 6.618223810195923,
|
|
"epoch": 2.3333511691369253,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00044606650920941753,
|
|
"loss": 6.1936,
|
|
"mean_token_accuracy": 0.14223768785595894,
|
|
"num_tokens": 47159014.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 6.585618686676026,
|
|
"epoch": 2.3338862432446894,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004460416712193067,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.14067996218800544,
|
|
"num_tokens": 47168760.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 6.498009538650512,
|
|
"epoch": 2.3344213173524535,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004460168282903916,
|
|
"loss": 6.2277,
|
|
"mean_token_accuracy": 0.13544398546218872,
|
|
"num_tokens": 47180902.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 6.476215553283692,
|
|
"epoch": 2.334956391460217,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00044599198042338963,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.14449657797813414,
|
|
"num_tokens": 47190458.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 6.580565977096557,
|
|
"epoch": 2.3354914655679813,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.00044596712761901824,
|
|
"loss": 6.2797,
|
|
"mean_token_accuracy": 0.13567885309457778,
|
|
"num_tokens": 47201099.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 6.525856399536133,
|
|
"epoch": 2.336026539675745,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004459422698779951,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.14438913762569427,
|
|
"num_tokens": 47211284.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 6.5691187381744385,
|
|
"epoch": 2.336561613783509,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004459174072010379,
|
|
"loss": 6.2829,
|
|
"mean_token_accuracy": 0.1352905422449112,
|
|
"num_tokens": 47222875.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 6.569251298904419,
|
|
"epoch": 2.337096687891273,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004458925395888646,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.13289797380566598,
|
|
"num_tokens": 47234238.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 6.586571311950683,
|
|
"epoch": 2.3376317619990368,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00044586766704219326,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.13420825824141502,
|
|
"num_tokens": 47244634.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 6.6197274684906,
|
|
"epoch": 2.338166836106801,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000445842789561742,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.13469713926315308,
|
|
"num_tokens": 47256538.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 6.511069679260254,
|
|
"epoch": 2.3387019102145645,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004458179071482292,
|
|
"loss": 6.0932,
|
|
"mean_token_accuracy": 0.1486232414841652,
|
|
"num_tokens": 47266373.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 6.559872341156006,
|
|
"epoch": 2.3392369843223286,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00044579301980237333,
|
|
"loss": 6.2792,
|
|
"mean_token_accuracy": 0.13349660411477088,
|
|
"num_tokens": 47276441.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 6.6282378196716305,
|
|
"epoch": 2.3397720584300927,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004457681275248931,
|
|
"loss": 6.2481,
|
|
"mean_token_accuracy": 0.13909940272569657,
|
|
"num_tokens": 47287299.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 6.527365398406983,
|
|
"epoch": 2.3403071325378564,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00044574323031650715,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.1385004475712776,
|
|
"num_tokens": 47298007.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 6.515253067016602,
|
|
"epoch": 2.3408422066456205,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004457183281779343,
|
|
"loss": 6.1011,
|
|
"mean_token_accuracy": 0.15069910362362862,
|
|
"num_tokens": 47309729.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 6.571058511734009,
|
|
"epoch": 2.3413772807533846,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044569342110989385,
|
|
"loss": 6.1791,
|
|
"mean_token_accuracy": 0.13877325803041457,
|
|
"num_tokens": 47319050.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 6.6047882556915285,
|
|
"epoch": 2.3419123548611482,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004456685091131048,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.1351003184914589,
|
|
"num_tokens": 47330365.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 6.689036273956299,
|
|
"epoch": 2.3424474289689123,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00044564359218828654,
|
|
"loss": 6.2266,
|
|
"mean_token_accuracy": 0.14099057614803315,
|
|
"num_tokens": 47341225.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 6.5713941097259525,
|
|
"epoch": 2.342982503076676,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00044561867033615854,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.14578369855880738,
|
|
"num_tokens": 47352996.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 6.446670579910278,
|
|
"epoch": 2.34351757718444,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004455937435574404,
|
|
"loss": 6.1362,
|
|
"mean_token_accuracy": 0.14041250795125962,
|
|
"num_tokens": 47363577.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 6.605824947357178,
|
|
"epoch": 2.3440526512922037,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00044556881185285185,
|
|
"loss": 6.3321,
|
|
"mean_token_accuracy": 0.129665108025074,
|
|
"num_tokens": 47374389.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 6.572376441955567,
|
|
"epoch": 2.344587725399968,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00044554387522311286,
|
|
"loss": 6.1663,
|
|
"mean_token_accuracy": 0.1425795316696167,
|
|
"num_tokens": 47385624.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 6.611634969711304,
|
|
"epoch": 2.345122799507732,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004455189336689435,
|
|
"loss": 6.2619,
|
|
"mean_token_accuracy": 0.13393474146723747,
|
|
"num_tokens": 47396611.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 6.610867595672607,
|
|
"epoch": 2.3456578736154956,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00044549398719106374,
|
|
"loss": 6.2366,
|
|
"mean_token_accuracy": 0.13768574520945548,
|
|
"num_tokens": 47406693.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 6.557671213150025,
|
|
"epoch": 2.3461929477232597,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004454690357901942,
|
|
"loss": 6.1646,
|
|
"mean_token_accuracy": 0.14326710477471352,
|
|
"num_tokens": 47417528.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 6.594715595245361,
|
|
"epoch": 2.346728021831024,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004454440794670552,
|
|
"loss": 6.2928,
|
|
"mean_token_accuracy": 0.13789374753832817,
|
|
"num_tokens": 47430032.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 6.614400148391724,
|
|
"epoch": 2.3472630959387875,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00044541911822236724,
|
|
"loss": 6.2974,
|
|
"mean_token_accuracy": 0.13252754732966424,
|
|
"num_tokens": 47441002.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 6.611999940872193,
|
|
"epoch": 2.3477981700465516,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004453941520568513,
|
|
"loss": 6.1507,
|
|
"mean_token_accuracy": 0.14790167436003684,
|
|
"num_tokens": 47451716.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 6.558821678161621,
|
|
"epoch": 2.348333244154315,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004453691809712281,
|
|
"loss": 6.1945,
|
|
"mean_token_accuracy": 0.1407183215022087,
|
|
"num_tokens": 47463039.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 6.514092111587525,
|
|
"epoch": 2.3488683182620793,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00044534420496621877,
|
|
"loss": 6.1365,
|
|
"mean_token_accuracy": 0.14654235541820526,
|
|
"num_tokens": 47473836.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 6.588634252548218,
|
|
"epoch": 2.3494033923698434,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00044531922404254445,
|
|
"loss": 6.2141,
|
|
"mean_token_accuracy": 0.13827887177467346,
|
|
"num_tokens": 47485103.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 6.494474744796753,
|
|
"epoch": 2.349938466477607,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004452942382009265,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.14684780240058898,
|
|
"num_tokens": 47495509.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 6.579980707168579,
|
|
"epoch": 2.350473540585371,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004452692474420863,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.1431807890534401,
|
|
"num_tokens": 47506062.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 6.529388475418091,
|
|
"epoch": 2.351008614693135,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004452442517667455,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.14681631624698638,
|
|
"num_tokens": 47515632.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 6.493258953094482,
|
|
"epoch": 2.351543688800899,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004452192511756259,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.1439495027065277,
|
|
"num_tokens": 47525412.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 6.58870677947998,
|
|
"epoch": 2.352078762908663,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00044519424566944935,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.14056721478700637,
|
|
"num_tokens": 47536094.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 6.538588953018189,
|
|
"epoch": 2.3526138370164267,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00044516923524893777,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.13619512245059012,
|
|
"num_tokens": 47546893.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 6.562430953979492,
|
|
"epoch": 2.353148911124191,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00044514421991481354,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.1418699011206627,
|
|
"num_tokens": 47557117.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 6.577167415618897,
|
|
"epoch": 2.3536839852319544,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00044511919966779885,
|
|
"loss": 6.1572,
|
|
"mean_token_accuracy": 0.1403982751071453,
|
|
"num_tokens": 47567878.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 6.587763786315918,
|
|
"epoch": 2.3542190593397185,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00044509417450861615,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.13388620540499688,
|
|
"num_tokens": 47578185.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 6.641248655319214,
|
|
"epoch": 2.3547541334474826,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004450691444379881,
|
|
"loss": 6.3366,
|
|
"mean_token_accuracy": 0.12986918911337852,
|
|
"num_tokens": 47590042.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 6.622638845443726,
|
|
"epoch": 2.3552892075552463,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00044504410945663735,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.1412392072379589,
|
|
"num_tokens": 47601225.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 6.569279336929322,
|
|
"epoch": 2.3558242816630104,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00044501906956528686,
|
|
"loss": 6.2453,
|
|
"mean_token_accuracy": 0.1346086621284485,
|
|
"num_tokens": 47612596.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 6.625122785568237,
|
|
"epoch": 2.356359355770774,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004449940247646596,
|
|
"loss": 6.282,
|
|
"mean_token_accuracy": 0.1375691555440426,
|
|
"num_tokens": 47623156.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 6.565970706939697,
|
|
"epoch": 2.356894429878538,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00044496897505547886,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.13626671209931374,
|
|
"num_tokens": 47633743.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 6.591253185272217,
|
|
"epoch": 2.3574295039863022,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004449439204384677,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.13712609857320784,
|
|
"num_tokens": 47643914.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 6.589194059371948,
|
|
"epoch": 2.357964578094066,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00044491886091434983,
|
|
"loss": 6.2427,
|
|
"mean_token_accuracy": 0.1385965682566166,
|
|
"num_tokens": 47655187.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 6.616750574111938,
|
|
"epoch": 2.35849965220183,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004448937964838487,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.13423595428466797,
|
|
"num_tokens": 47667193.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 6.591698360443115,
|
|
"epoch": 2.359034726309594,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004448687271476881,
|
|
"loss": 6.2475,
|
|
"mean_token_accuracy": 0.13862593472003937,
|
|
"num_tokens": 47678116.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 6.581958436965943,
|
|
"epoch": 2.3595698004173578,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004448436529065918,
|
|
"loss": 6.2215,
|
|
"mean_token_accuracy": 0.13761291429400443,
|
|
"num_tokens": 47689883.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 6.57611312866211,
|
|
"epoch": 2.360104874525122,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004448185737612839,
|
|
"loss": 6.2233,
|
|
"mean_token_accuracy": 0.13863909989595413,
|
|
"num_tokens": 47699939.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 6.515372467041016,
|
|
"epoch": 2.3606399486328855,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00044479348971248863,
|
|
"loss": 6.1797,
|
|
"mean_token_accuracy": 0.1442003756761551,
|
|
"num_tokens": 47710477.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 6.600262403488159,
|
|
"epoch": 2.3611750227406496,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004447684007609301,
|
|
"loss": 6.2284,
|
|
"mean_token_accuracy": 0.13676860183477402,
|
|
"num_tokens": 47720548.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 6.629921579360962,
|
|
"epoch": 2.3617100968484133,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00044474330690733293,
|
|
"loss": 6.2125,
|
|
"mean_token_accuracy": 0.13679243996739388,
|
|
"num_tokens": 47732135.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 6.575686645507813,
|
|
"epoch": 2.3622451709561774,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004447182081524216,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.13673500940203667,
|
|
"num_tokens": 47742934.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 6.559023666381836,
|
|
"epoch": 2.3627802450639415,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00044469310449692085,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.13671469911932946,
|
|
"num_tokens": 47754586.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 6.638344621658325,
|
|
"epoch": 2.363315319171705,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.00044466799594155556,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.13339167088270187,
|
|
"num_tokens": 47765564.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 6.568977499008179,
|
|
"epoch": 2.363850393279469,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00044464288248705075,
|
|
"loss": 6.1843,
|
|
"mean_token_accuracy": 0.14318932220339775,
|
|
"num_tokens": 47776191.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 6.639568090438843,
|
|
"epoch": 2.3643854673872333,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00044461776413413153,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.1301228404045105,
|
|
"num_tokens": 47787193.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 6.639419746398926,
|
|
"epoch": 2.364920541494997,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004445926408835232,
|
|
"loss": 6.2702,
|
|
"mean_token_accuracy": 0.13113785088062285,
|
|
"num_tokens": 47798576.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 6.506872653961182,
|
|
"epoch": 2.365455615602761,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004445675127359511,
|
|
"loss": 6.1213,
|
|
"mean_token_accuracy": 0.14751743227243425,
|
|
"num_tokens": 47809519.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 6.5969878196716305,
|
|
"epoch": 2.3659906897105247,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000444542379692141,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.13982801735401154,
|
|
"num_tokens": 47820618.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 6.621946573257446,
|
|
"epoch": 2.366525763818289,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004445172417528186,
|
|
"loss": 6.2885,
|
|
"mean_token_accuracy": 0.135103540122509,
|
|
"num_tokens": 47831756.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 6.601783418655396,
|
|
"epoch": 2.367060837926053,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00044449209891870954,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.1362423576414585,
|
|
"num_tokens": 47841974.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 6.545253467559815,
|
|
"epoch": 2.3675959120338166,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00044446695119053993,
|
|
"loss": 6.1718,
|
|
"mean_token_accuracy": 0.13833274692296982,
|
|
"num_tokens": 47852194.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 6.614467716217041,
|
|
"epoch": 2.3681309861415807,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000444441798569036,
|
|
"loss": 6.3101,
|
|
"mean_token_accuracy": 0.13715747594833375,
|
|
"num_tokens": 47863921.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 6.674740266799927,
|
|
"epoch": 2.3686660602493443,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00044441664105492393,
|
|
"loss": 6.3923,
|
|
"mean_token_accuracy": 0.12698644325137137,
|
|
"num_tokens": 47875520.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 6.626958322525025,
|
|
"epoch": 2.3692011343571084,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004443914786489301,
|
|
"loss": 6.1799,
|
|
"mean_token_accuracy": 0.14149469882249832,
|
|
"num_tokens": 47886047.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 6.48414044380188,
|
|
"epoch": 2.3697362084648725,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00044436631135178113,
|
|
"loss": 6.1092,
|
|
"mean_token_accuracy": 0.14744011163711548,
|
|
"num_tokens": 47896449.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 6.617450475692749,
|
|
"epoch": 2.370271282572636,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00044434113916420377,
|
|
"loss": 6.2698,
|
|
"mean_token_accuracy": 0.13669810369610785,
|
|
"num_tokens": 47908613.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 6.660142087936402,
|
|
"epoch": 2.3708063566804003,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00044431596208692475,
|
|
"loss": 6.3216,
|
|
"mean_token_accuracy": 0.12883925214409828,
|
|
"num_tokens": 47919474.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 6.559785795211792,
|
|
"epoch": 2.3713414307881644,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004442907801206712,
|
|
"loss": 6.1983,
|
|
"mean_token_accuracy": 0.13823748826980592,
|
|
"num_tokens": 47930929.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 6.538672828674317,
|
|
"epoch": 2.371876504895928,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00044426559326617013,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.14677972346544266,
|
|
"num_tokens": 47942050.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 6.620697736740112,
|
|
"epoch": 2.372411579003692,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004442404015241488,
|
|
"loss": 6.3048,
|
|
"mean_token_accuracy": 0.13431683853268622,
|
|
"num_tokens": 47953162.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 6.63784556388855,
|
|
"epoch": 2.372946653111456,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.00044421520489533467,
|
|
"loss": 6.24,
|
|
"mean_token_accuracy": 0.13637386858463288,
|
|
"num_tokens": 47963140.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 6.5145162582397464,
|
|
"epoch": 2.37348172721922,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.00044419000338045527,
|
|
"loss": 6.2949,
|
|
"mean_token_accuracy": 0.1377105548977852,
|
|
"num_tokens": 47975622.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 6.6045502662658695,
|
|
"epoch": 2.3740168013269836,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004441647969802383,
|
|
"loss": 6.2118,
|
|
"mean_token_accuracy": 0.13273803666234016,
|
|
"num_tokens": 47986450.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 6.681471300125122,
|
|
"epoch": 2.3745518754347477,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004441395856954117,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.1293344922363758,
|
|
"num_tokens": 47997441.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 6.589809989929199,
|
|
"epoch": 2.3750869495425118,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00044411436952670325,
|
|
"loss": 6.2162,
|
|
"mean_token_accuracy": 0.13476677238941193,
|
|
"num_tokens": 48008995.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 6.612467241287232,
|
|
"epoch": 2.3756220236502754,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00044408914847484103,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.14459354281425477,
|
|
"num_tokens": 48019975.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 6.60690746307373,
|
|
"epoch": 2.3761570977580395,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004440639225405536,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.13531510531902313,
|
|
"num_tokens": 48031278.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 6.538502931594849,
|
|
"epoch": 2.3766921718658036,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.000444038691724569,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.13921816200017928,
|
|
"num_tokens": 48042050.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 6.500094413757324,
|
|
"epoch": 2.3772272459735673,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00044401345602761605,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.14961424171924592,
|
|
"num_tokens": 48052833.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 6.486407613754272,
|
|
"epoch": 2.3777623200813314,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00044398821545042327,
|
|
"loss": 6.1775,
|
|
"mean_token_accuracy": 0.13931036964058877,
|
|
"num_tokens": 48063425.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 6.578277969360352,
|
|
"epoch": 2.378297394189095,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00044396296999371946,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.1444233775138855,
|
|
"num_tokens": 48074941.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 6.506859683990479,
|
|
"epoch": 2.378832468296859,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00044393771965823376,
|
|
"loss": 6.0113,
|
|
"mean_token_accuracy": 0.14569775238633156,
|
|
"num_tokens": 48085224.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 6.590883827209472,
|
|
"epoch": 2.3793675424046232,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000443912464444695,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.1366701267659664,
|
|
"num_tokens": 48096509.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 6.521537399291992,
|
|
"epoch": 2.379902616512387,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004438872043538327,
|
|
"loss": 6.1885,
|
|
"mean_token_accuracy": 0.13702284097671508,
|
|
"num_tokens": 48106839.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 6.643890285491944,
|
|
"epoch": 2.380437690620151,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000443861939386376,
|
|
"loss": 6.2535,
|
|
"mean_token_accuracy": 0.13631090000271798,
|
|
"num_tokens": 48118209.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 6.609898900985717,
|
|
"epoch": 2.3809727647279146,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004438366695430546,
|
|
"loss": 6.2262,
|
|
"mean_token_accuracy": 0.14026885405182837,
|
|
"num_tokens": 48128651.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 6.597871017456055,
|
|
"epoch": 2.3815078388356787,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00044381139482459805,
|
|
"loss": 6.2547,
|
|
"mean_token_accuracy": 0.13822279274463653,
|
|
"num_tokens": 48139612.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 6.607874965667724,
|
|
"epoch": 2.382042912943443,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00044378611523173615,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.14173949360847474,
|
|
"num_tokens": 48150557.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 6.576299142837525,
|
|
"epoch": 2.3825779870512065,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004437608307651989,
|
|
"loss": 6.115,
|
|
"mean_token_accuracy": 0.1444450043141842,
|
|
"num_tokens": 48160784.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 6.546441745758057,
|
|
"epoch": 2.3831130611589706,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004437355414257165,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.14046984612941743,
|
|
"num_tokens": 48171075.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 6.598555946350098,
|
|
"epoch": 2.3836481352667347,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044371024721401894,
|
|
"loss": 6.2577,
|
|
"mean_token_accuracy": 0.1323731504380703,
|
|
"num_tokens": 48182713.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 6.610416841506958,
|
|
"epoch": 2.3841832093744983,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004436849481308367,
|
|
"loss": 6.1868,
|
|
"mean_token_accuracy": 0.14868704378604888,
|
|
"num_tokens": 48194198.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 6.542577791213989,
|
|
"epoch": 2.3847182834822624,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00044365964417690035,
|
|
"loss": 6.141,
|
|
"mean_token_accuracy": 0.14006274342536926,
|
|
"num_tokens": 48205650.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 6.509784936904907,
|
|
"epoch": 2.385253357590026,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004436343353529404,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.14055607318878174,
|
|
"num_tokens": 48216335.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 6.579950189590454,
|
|
"epoch": 2.38578843169779,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00044360902165968774,
|
|
"loss": 6.1888,
|
|
"mean_token_accuracy": 0.14037863314151763,
|
|
"num_tokens": 48227206.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 6.565878105163574,
|
|
"epoch": 2.386323505805554,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004435837030978733,
|
|
"loss": 6.1946,
|
|
"mean_token_accuracy": 0.14142837077379228,
|
|
"num_tokens": 48237948.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 6.553464031219482,
|
|
"epoch": 2.386858579913318,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004435583796682281,
|
|
"loss": 6.2074,
|
|
"mean_token_accuracy": 0.14942528903484345,
|
|
"num_tokens": 48250086.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 6.584306144714356,
|
|
"epoch": 2.387393654021082,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004435330513714834,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.14200235307216644,
|
|
"num_tokens": 48261004.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 6.536152458190918,
|
|
"epoch": 2.3879287281288457,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004435077182083705,
|
|
"loss": 6.2053,
|
|
"mean_token_accuracy": 0.14087184518575668,
|
|
"num_tokens": 48271314.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 6.496436595916748,
|
|
"epoch": 2.38846380223661,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00044348238017962095,
|
|
"loss": 6.1584,
|
|
"mean_token_accuracy": 0.14190915673971177,
|
|
"num_tokens": 48281899.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 6.562120580673218,
|
|
"epoch": 2.388998876344374,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004434570372859663,
|
|
"loss": 6.2309,
|
|
"mean_token_accuracy": 0.14017684385180473,
|
|
"num_tokens": 48292925.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 6.643316745758057,
|
|
"epoch": 2.3895339504521376,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004434316895281384,
|
|
"loss": 6.2531,
|
|
"mean_token_accuracy": 0.13907974809408188,
|
|
"num_tokens": 48303138.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 6.492652940750122,
|
|
"epoch": 2.3900690245599017,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004434063369068691,
|
|
"loss": 6.1162,
|
|
"mean_token_accuracy": 0.15191553384065629,
|
|
"num_tokens": 48313586.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 6.474801063537598,
|
|
"epoch": 2.3906040986676653,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00044338097942289045,
|
|
"loss": 6.1408,
|
|
"mean_token_accuracy": 0.13968117386102677,
|
|
"num_tokens": 48324756.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 6.573549222946167,
|
|
"epoch": 2.3911391727754294,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004433556170769348,
|
|
"loss": 6.2302,
|
|
"mean_token_accuracy": 0.13398828953504563,
|
|
"num_tokens": 48336012.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 6.6080114364624025,
|
|
"epoch": 2.391674246883193,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004433302498697343,
|
|
"loss": 6.2944,
|
|
"mean_token_accuracy": 0.1341991402208805,
|
|
"num_tokens": 48348923.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 6.602735376358032,
|
|
"epoch": 2.392209320990957,
|
|
"grad_norm": 5.53125,
|
|
"learning_rate": 0.00044330487780202144,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.1544332966208458,
|
|
"num_tokens": 48359708.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 6.589661502838135,
|
|
"epoch": 2.3927443950987213,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00044327950087452895,
|
|
"loss": 6.2059,
|
|
"mean_token_accuracy": 0.1406900852918625,
|
|
"num_tokens": 48370497.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 6.512119483947754,
|
|
"epoch": 2.393279469206485,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004432541190879895,
|
|
"loss": 6.2159,
|
|
"mean_token_accuracy": 0.13363559022545815,
|
|
"num_tokens": 48381020.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 6.509419727325439,
|
|
"epoch": 2.393814543314249,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00044322873244313603,
|
|
"loss": 6.2002,
|
|
"mean_token_accuracy": 0.13928357884287834,
|
|
"num_tokens": 48391696.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 6.536404943466186,
|
|
"epoch": 2.394349617422013,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00044320334094070154,
|
|
"loss": 6.1913,
|
|
"mean_token_accuracy": 0.14056565165519713,
|
|
"num_tokens": 48402403.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 6.571100234985352,
|
|
"epoch": 2.394884691529777,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004431779445814192,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.15164462551474572,
|
|
"num_tokens": 48413579.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 6.650535249710083,
|
|
"epoch": 2.395419765637541,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00044315254336602236,
|
|
"loss": 6.2499,
|
|
"mean_token_accuracy": 0.13543590605258943,
|
|
"num_tokens": 48423814.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 6.614046287536621,
|
|
"epoch": 2.3959548397453045,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00044312713729524443,
|
|
"loss": 6.3367,
|
|
"mean_token_accuracy": 0.13394274264574052,
|
|
"num_tokens": 48433937.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 6.582800006866455,
|
|
"epoch": 2.3964899138530686,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00044310172636981905,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.13738479018211364,
|
|
"num_tokens": 48444397.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 6.56569538116455,
|
|
"epoch": 2.3970249879608327,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004430763105904799,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.14497862830758096,
|
|
"num_tokens": 48454566.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 6.531002950668335,
|
|
"epoch": 2.3975600620685964,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000443050889957961,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.14810080975294113,
|
|
"num_tokens": 48465129.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 6.538532781600952,
|
|
"epoch": 2.3980951361763605,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00044302546447299625,
|
|
"loss": 6.1538,
|
|
"mean_token_accuracy": 0.14122578948736192,
|
|
"num_tokens": 48475793.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 6.5227946758270265,
|
|
"epoch": 2.398630210284124,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004430000341363198,
|
|
"loss": 6.0908,
|
|
"mean_token_accuracy": 0.14892042204737663,
|
|
"num_tokens": 48486543.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 6.614182329177856,
|
|
"epoch": 2.3991652843918883,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004429745989486659,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.1438041627407074,
|
|
"num_tokens": 48498426.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 6.592417669296265,
|
|
"epoch": 2.3997003584996524,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004429491589107691,
|
|
"loss": 6.1411,
|
|
"mean_token_accuracy": 0.14752377644181253,
|
|
"num_tokens": 48508763.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 6.6265510559082035,
|
|
"epoch": 2.400235432607416,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004429237140233639,
|
|
"loss": 6.2495,
|
|
"mean_token_accuracy": 0.1334492914378643,
|
|
"num_tokens": 48519112.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 6.6404191017150875,
|
|
"epoch": 2.40077050671518,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004428982642871852,
|
|
"loss": 6.1956,
|
|
"mean_token_accuracy": 0.14126064628362656,
|
|
"num_tokens": 48530341.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 6.530861711502075,
|
|
"epoch": 2.401305580822944,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004428728097029676,
|
|
"loss": 6.1242,
|
|
"mean_token_accuracy": 0.1427082508802414,
|
|
"num_tokens": 48541962.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 6.5764037609100345,
|
|
"epoch": 2.401840654930708,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00044284735027144624,
|
|
"loss": 6.2842,
|
|
"mean_token_accuracy": 0.12749214544892312,
|
|
"num_tokens": 48554206.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 6.489275550842285,
|
|
"epoch": 2.402375729038472,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004428218859933562,
|
|
"loss": 6.1471,
|
|
"mean_token_accuracy": 0.14041391015052795,
|
|
"num_tokens": 48563919.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 6.492449808120727,
|
|
"epoch": 2.4029108031462356,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00044279641686943277,
|
|
"loss": 6.2723,
|
|
"mean_token_accuracy": 0.14656204655766486,
|
|
"num_tokens": 48575388.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 6.602008867263794,
|
|
"epoch": 2.4034458772539997,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00044277094290041144,
|
|
"loss": 6.2032,
|
|
"mean_token_accuracy": 0.14210669994354247,
|
|
"num_tokens": 48587492.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 6.486867761611938,
|
|
"epoch": 2.4039809513617634,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00044274546408702763,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.15841298252344133,
|
|
"num_tokens": 48598757.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 6.592644596099854,
|
|
"epoch": 2.4045160254695275,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00044271998043001723,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.1432599849998951,
|
|
"num_tokens": 48609912.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 6.607081127166748,
|
|
"epoch": 2.4050510995772916,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004426944919301158,
|
|
"loss": 6.3177,
|
|
"mean_token_accuracy": 0.13574332147836685,
|
|
"num_tokens": 48621614.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 6.535430288314819,
|
|
"epoch": 2.4055861736850552,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00044266899858805964,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.14281328842043878,
|
|
"num_tokens": 48632539.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 6.639069080352783,
|
|
"epoch": 2.4061212477928193,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00044264350040458463,
|
|
"loss": 6.3094,
|
|
"mean_token_accuracy": 0.13739847168326377,
|
|
"num_tokens": 48644157.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 6.63141188621521,
|
|
"epoch": 2.4066563219005834,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00044261799738042713,
|
|
"loss": 6.3047,
|
|
"mean_token_accuracy": 0.13865743950009346,
|
|
"num_tokens": 48654928.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 6.667938995361328,
|
|
"epoch": 2.407191396008347,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004425924895163235,
|
|
"loss": 6.2157,
|
|
"mean_token_accuracy": 0.14891067668795585,
|
|
"num_tokens": 48665183.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 6.5611371994018555,
|
|
"epoch": 2.407726470116111,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00044256697681301034,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.150129434466362,
|
|
"num_tokens": 48675233.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 6.509908771514892,
|
|
"epoch": 2.408261544223875,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004425414592712242,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.1410057030618191,
|
|
"num_tokens": 48685881.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 6.565768766403198,
|
|
"epoch": 2.408796618331639,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00044251593689170196,
|
|
"loss": 6.2573,
|
|
"mean_token_accuracy": 0.1356266789138317,
|
|
"num_tokens": 48696402.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 6.608573532104492,
|
|
"epoch": 2.409331692439403,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00044249040967518063,
|
|
"loss": 6.2501,
|
|
"mean_token_accuracy": 0.1383936047554016,
|
|
"num_tokens": 48708041.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 6.603364324569702,
|
|
"epoch": 2.4098667665471667,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00044246487762239717,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.14465048313140869,
|
|
"num_tokens": 48718836.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 6.559991121292114,
|
|
"epoch": 2.410401840654931,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000442439340734089,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.14216591119766236,
|
|
"num_tokens": 48729115.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 6.5147112846374515,
|
|
"epoch": 2.4109369147626944,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00044241379901099334,
|
|
"loss": 6.1791,
|
|
"mean_token_accuracy": 0.1474498838186264,
|
|
"num_tokens": 48740037.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 6.5272633075714115,
|
|
"epoch": 2.4114719888704585,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00044238825245384775,
|
|
"loss": 6.2319,
|
|
"mean_token_accuracy": 0.13638036847114562,
|
|
"num_tokens": 48750894.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 6.596189880371094,
|
|
"epoch": 2.4120070629782226,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004423627010633899,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.14759288281202315,
|
|
"num_tokens": 48761566.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 6.4535469055175785,
|
|
"epoch": 2.4125421370859863,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00044233714484035765,
|
|
"loss": 6.1069,
|
|
"mean_token_accuracy": 0.1436549171805382,
|
|
"num_tokens": 48772971.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 6.511305809020996,
|
|
"epoch": 2.4130772111937504,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00044231158378548873,
|
|
"loss": 6.1813,
|
|
"mean_token_accuracy": 0.14407134428620338,
|
|
"num_tokens": 48784548.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 6.427939081192017,
|
|
"epoch": 2.4136122853015145,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004422860178995215,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.15126224383711814,
|
|
"num_tokens": 48795228.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 6.582669305801391,
|
|
"epoch": 2.414147359409278,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.00044226044718319383,
|
|
"loss": 6.1653,
|
|
"mean_token_accuracy": 0.14032421708106996,
|
|
"num_tokens": 48806497.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 6.58074107170105,
|
|
"epoch": 2.4146824335170423,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004422348716372444,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.14450195878744126,
|
|
"num_tokens": 48816402.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 6.632004356384277,
|
|
"epoch": 2.415217507624806,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004422092912624115,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.13952990397810935,
|
|
"num_tokens": 48826151.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 6.5028993606567385,
|
|
"epoch": 2.41575258173257,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00044218370605943376,
|
|
"loss": 6.2489,
|
|
"mean_token_accuracy": 0.1427173689007759,
|
|
"num_tokens": 48836458.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 6.518651294708252,
|
|
"epoch": 2.4162876558403337,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00044215811602905003,
|
|
"loss": 6.2024,
|
|
"mean_token_accuracy": 0.14275349974632262,
|
|
"num_tokens": 48845863.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 6.59752402305603,
|
|
"epoch": 2.4168227299480978,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00044213252117199914,
|
|
"loss": 6.2344,
|
|
"mean_token_accuracy": 0.13482951298356055,
|
|
"num_tokens": 48856453.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 6.651044416427612,
|
|
"epoch": 2.417357804055862,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00044210692148902034,
|
|
"loss": 6.1546,
|
|
"mean_token_accuracy": 0.13642938509583474,
|
|
"num_tokens": 48867013.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 6.585464239120483,
|
|
"epoch": 2.4178928781636255,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004420813169808525,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.1357590027153492,
|
|
"num_tokens": 48876455.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 6.520710134506226,
|
|
"epoch": 2.4184279522713896,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004420557076482352,
|
|
"loss": 6.2268,
|
|
"mean_token_accuracy": 0.13314828500151635,
|
|
"num_tokens": 48888223.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 6.537656021118164,
|
|
"epoch": 2.4189630263791537,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00044203009349190784,
|
|
"loss": 6.2129,
|
|
"mean_token_accuracy": 0.14048228561878204,
|
|
"num_tokens": 48899287.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 6.6088722229003904,
|
|
"epoch": 2.4194981004869174,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004420044745126099,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.1346104085445404,
|
|
"num_tokens": 48910740.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 6.542724466323852,
|
|
"epoch": 2.4200331745946815,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00044197885071108127,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.14118960201740266,
|
|
"num_tokens": 48921925.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 6.6059041023254395,
|
|
"epoch": 2.420568248702445,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004419532220880619,
|
|
"loss": 6.3162,
|
|
"mean_token_accuracy": 0.1302391566336155,
|
|
"num_tokens": 48933164.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 6.588613367080688,
|
|
"epoch": 2.4211033228102092,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00044192758864429157,
|
|
"loss": 6.2536,
|
|
"mean_token_accuracy": 0.13726796880364417,
|
|
"num_tokens": 48943285.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 6.544233989715576,
|
|
"epoch": 2.421638396917973,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004419019503805106,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.1372228443622589,
|
|
"num_tokens": 48952852.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 6.572935628890991,
|
|
"epoch": 2.422173471025737,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00044187630729745924,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.13040569499135019,
|
|
"num_tokens": 48964339.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 6.651379251480103,
|
|
"epoch": 2.422708545133501,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00044185065939587805,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.1355573281645775,
|
|
"num_tokens": 48974754.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 6.601839780807495,
|
|
"epoch": 2.4232436192412647,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00044182500667650746,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.14399916678667068,
|
|
"num_tokens": 48985596.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 6.6200426578521725,
|
|
"epoch": 2.423778693349029,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004417993491400882,
|
|
"loss": 6.2728,
|
|
"mean_token_accuracy": 0.13993245959281922,
|
|
"num_tokens": 48997400.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 6.584427309036255,
|
|
"epoch": 2.424313767456793,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00044177368678736126,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.14288668483495712,
|
|
"num_tokens": 49007525.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 6.517870998382568,
|
|
"epoch": 2.4248488415645566,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00044174801961906744,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.1410953991115093,
|
|
"num_tokens": 49018205.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 6.62923641204834,
|
|
"epoch": 2.4253839156723207,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00044172234763594805,
|
|
"loss": 6.2325,
|
|
"mean_token_accuracy": 0.13655352145433425,
|
|
"num_tokens": 49028760.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 6.607015609741211,
|
|
"epoch": 2.4259189897800844,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004416966708387443,
|
|
"loss": 6.1842,
|
|
"mean_token_accuracy": 0.1398657537996769,
|
|
"num_tokens": 49040734.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 6.479090404510498,
|
|
"epoch": 2.4264540638878485,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00044167098922819764,
|
|
"loss": 6.1662,
|
|
"mean_token_accuracy": 0.13426587879657745,
|
|
"num_tokens": 49051474.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 6.497205781936645,
|
|
"epoch": 2.4269891379956126,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00044164530280504954,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.1456982523202896,
|
|
"num_tokens": 49061697.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 6.541453313827515,
|
|
"epoch": 2.427524212103376,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00044161961157004176,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.14687985628843309,
|
|
"num_tokens": 49072124.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 6.607861804962158,
|
|
"epoch": 2.4280592862111403,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000441593915523916,
|
|
"loss": 6.204,
|
|
"mean_token_accuracy": 0.1422594055533409,
|
|
"num_tokens": 49082653.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 6.637756395339966,
|
|
"epoch": 2.428594360318904,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00044156821466741447,
|
|
"loss": 6.3059,
|
|
"mean_token_accuracy": 0.13259934186935424,
|
|
"num_tokens": 49092481.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 6.595689058303833,
|
|
"epoch": 2.429129434426668,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004415425090012792,
|
|
"loss": 6.2953,
|
|
"mean_token_accuracy": 0.13121173679828643,
|
|
"num_tokens": 49103189.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 6.606493282318115,
|
|
"epoch": 2.429664508534432,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00044151679852625226,
|
|
"loss": 6.2442,
|
|
"mean_token_accuracy": 0.1332022301852703,
|
|
"num_tokens": 49114071.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 6.636916971206665,
|
|
"epoch": 2.430199582642196,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004414910832430762,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.14170701801776886,
|
|
"num_tokens": 49125521.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 6.598323249816895,
|
|
"epoch": 2.43073465674996,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004414653631524935,
|
|
"loss": 6.1717,
|
|
"mean_token_accuracy": 0.1399085521697998,
|
|
"num_tokens": 49136162.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 6.601904058456421,
|
|
"epoch": 2.431269730857724,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004414396382552468,
|
|
"loss": 6.1977,
|
|
"mean_token_accuracy": 0.13976423293352128,
|
|
"num_tokens": 49146127.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 6.570015001296997,
|
|
"epoch": 2.4318048049654877,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00044141390855207904,
|
|
"loss": 6.1573,
|
|
"mean_token_accuracy": 0.14458316043019295,
|
|
"num_tokens": 49156619.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 6.541472053527832,
|
|
"epoch": 2.4323398790732518,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00044138817404373295,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.13050250560045243,
|
|
"num_tokens": 49168578.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 6.615605783462525,
|
|
"epoch": 2.4328749531810154,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004413624347309517,
|
|
"loss": 6.2614,
|
|
"mean_token_accuracy": 0.1419189453125,
|
|
"num_tokens": 49178845.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 6.6025710105896,
|
|
"epoch": 2.4334100272887795,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00044133669061447855,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.1384100593626499,
|
|
"num_tokens": 49189067.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 6.626526975631714,
|
|
"epoch": 2.433945101396543,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00044131094169505694,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.13203438222408295,
|
|
"num_tokens": 49200368.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 6.56493124961853,
|
|
"epoch": 2.4344801755043073,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00044128518797343014,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.14148974567651748,
|
|
"num_tokens": 49211630.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 6.5697629928588865,
|
|
"epoch": 2.4350152496120714,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000441259429450342,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.13500226512551308,
|
|
"num_tokens": 49223092.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 6.596406745910644,
|
|
"epoch": 2.435550323719835,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00044123366612653617,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.14174099490046502,
|
|
"num_tokens": 49233963.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 6.674398612976074,
|
|
"epoch": 2.436085397827599,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004412078980027565,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.14314457774162292,
|
|
"num_tokens": 49243834.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 6.525671768188476,
|
|
"epoch": 2.4366204719353632,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004411821250797472,
|
|
"loss": 6.0648,
|
|
"mean_token_accuracy": 0.14632426500320433,
|
|
"num_tokens": 49254274.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 6.518257141113281,
|
|
"epoch": 2.437155546043127,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004411563473582524,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.1456860162317753,
|
|
"num_tokens": 49264734.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 6.577956581115723,
|
|
"epoch": 2.437690620150891,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004411305648390163,
|
|
"loss": 6.1634,
|
|
"mean_token_accuracy": 0.1411969281733036,
|
|
"num_tokens": 49274708.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 6.585747623443604,
|
|
"epoch": 2.4382256942586547,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004411047775227836,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.13971465528011323,
|
|
"num_tokens": 49286318.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 6.639686489105225,
|
|
"epoch": 2.4387607683664188,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00044107898541029885,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.13426866456866265,
|
|
"num_tokens": 49296948.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 6.489386320114136,
|
|
"epoch": 2.439295842474183,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004410531885023066,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.14529868811368943,
|
|
"num_tokens": 49307060.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 6.553091621398925,
|
|
"epoch": 2.4398309165819465,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00044102738679955195,
|
|
"loss": 6.2268,
|
|
"mean_token_accuracy": 0.13407843708992004,
|
|
"num_tokens": 49318449.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 6.57895245552063,
|
|
"epoch": 2.4403659906897106,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004410015803027798,
|
|
"loss": 6.2428,
|
|
"mean_token_accuracy": 0.14007993116974832,
|
|
"num_tokens": 49329567.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 6.638948678970337,
|
|
"epoch": 2.4409010647974743,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00044097576901273535,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.14173311740159988,
|
|
"num_tokens": 49340854.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 6.655818223953247,
|
|
"epoch": 2.4414361389052384,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004409499529301639,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.1364336259663105,
|
|
"num_tokens": 49352749.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 6.63412036895752,
|
|
"epoch": 2.4419712130130025,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004409241320558109,
|
|
"loss": 6.2727,
|
|
"mean_token_accuracy": 0.13245029747486115,
|
|
"num_tokens": 49364703.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 6.553991413116455,
|
|
"epoch": 2.442506287120766,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044089830639042183,
|
|
"loss": 6.1259,
|
|
"mean_token_accuracy": 0.14391778334975242,
|
|
"num_tokens": 49375873.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 6.6160523891448975,
|
|
"epoch": 2.44304136122853,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00044087247593474255,
|
|
"loss": 6.2792,
|
|
"mean_token_accuracy": 0.13565881103277205,
|
|
"num_tokens": 49386578.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 6.611468172073364,
|
|
"epoch": 2.4435764353362943,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004408466406895188,
|
|
"loss": 6.2197,
|
|
"mean_token_accuracy": 0.13757925406098365,
|
|
"num_tokens": 49398394.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 6.537632942199707,
|
|
"epoch": 2.444111509444058,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004408208006554966,
|
|
"loss": 6.1617,
|
|
"mean_token_accuracy": 0.1552607849240303,
|
|
"num_tokens": 49408758.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 6.554506778717041,
|
|
"epoch": 2.444646583551822,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004407949558334221,
|
|
"loss": 6.1896,
|
|
"mean_token_accuracy": 0.14144173115491868,
|
|
"num_tokens": 49420447.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 6.603532171249389,
|
|
"epoch": 2.4451816576595857,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00044076910622404153,
|
|
"loss": 6.2254,
|
|
"mean_token_accuracy": 0.14549217820167543,
|
|
"num_tokens": 49430246.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 6.575584363937378,
|
|
"epoch": 2.44571673176735,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00044074325182810135,
|
|
"loss": 6.1994,
|
|
"mean_token_accuracy": 0.14200471043586732,
|
|
"num_tokens": 49441272.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 6.553707790374756,
|
|
"epoch": 2.4462518058751135,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00044071739264634803,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.13279729560017586,
|
|
"num_tokens": 49452778.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 6.595398235321045,
|
|
"epoch": 2.4467868799828776,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004406915286795283,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.1375604398548603,
|
|
"num_tokens": 49463594.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 6.61736478805542,
|
|
"epoch": 2.4473219540906417,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004406656599283889,
|
|
"loss": 6.2155,
|
|
"mean_token_accuracy": 0.13873564898967744,
|
|
"num_tokens": 49473649.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 6.526067686080933,
|
|
"epoch": 2.4478570281984053,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004406397863936769,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.1451099380850792,
|
|
"num_tokens": 49485112.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 6.561701154708862,
|
|
"epoch": 2.4483921023061694,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004406139080761394,
|
|
"loss": 6.2789,
|
|
"mean_token_accuracy": 0.1371996968984604,
|
|
"num_tokens": 49495455.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 6.598499155044555,
|
|
"epoch": 2.4489271764139335,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004405880249765235,
|
|
"loss": 6.2098,
|
|
"mean_token_accuracy": 0.13983510434627533,
|
|
"num_tokens": 49506495.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 6.584448385238647,
|
|
"epoch": 2.449462250521697,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00044056213709557667,
|
|
"loss": 6.2261,
|
|
"mean_token_accuracy": 0.14070743322372437,
|
|
"num_tokens": 49516384.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 6.502516412734986,
|
|
"epoch": 2.4499973246294613,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00044053624443404646,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.1469280645251274,
|
|
"num_tokens": 49527972.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 6.552877902984619,
|
|
"epoch": 2.450532398737225,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004405103469926803,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.1392278179526329,
|
|
"num_tokens": 49540643.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 6.556387042999267,
|
|
"epoch": 2.451067472844989,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00044048444477222626,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.14588721841573715,
|
|
"num_tokens": 49550968.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 6.573545026779175,
|
|
"epoch": 2.451602546952753,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004404585377734321,
|
|
"loss": 6.1666,
|
|
"mean_token_accuracy": 0.1377850279211998,
|
|
"num_tokens": 49562381.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 6.533356046676635,
|
|
"epoch": 2.452137621060517,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004404326259970459,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.14043846726417542,
|
|
"num_tokens": 49573414.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 6.578101921081543,
|
|
"epoch": 2.452672695168281,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004404067094438159,
|
|
"loss": 6.2592,
|
|
"mean_token_accuracy": 0.14074127599596978,
|
|
"num_tokens": 49583772.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 6.582143974304199,
|
|
"epoch": 2.4532077692760446,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004403807881144903,
|
|
"loss": 6.2506,
|
|
"mean_token_accuracy": 0.13861199021339415,
|
|
"num_tokens": 49594751.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 6.530072021484375,
|
|
"epoch": 2.4537428433838087,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044035486200981786,
|
|
"loss": 6.1496,
|
|
"mean_token_accuracy": 0.13950811699032784,
|
|
"num_tokens": 49605048.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 6.632976245880127,
|
|
"epoch": 2.4542779174915728,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00044032893113054683,
|
|
"loss": 6.2797,
|
|
"mean_token_accuracy": 0.14097194373607635,
|
|
"num_tokens": 49616582.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 6.616191339492798,
|
|
"epoch": 2.4548129915993364,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004403029954774263,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.1374459944665432,
|
|
"num_tokens": 49626974.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 6.5496479034423825,
|
|
"epoch": 2.4553480657071005,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004402770550512049,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.14061234816908835,
|
|
"num_tokens": 49637580.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 6.597954893112183,
|
|
"epoch": 2.455883139814864,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004402511098526318,
|
|
"loss": 6.2412,
|
|
"mean_token_accuracy": 0.13903196081519126,
|
|
"num_tokens": 49648543.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 6.640139245986939,
|
|
"epoch": 2.4564182139226283,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004402251598824561,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.14036984294652938,
|
|
"num_tokens": 49659057.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 6.583414077758789,
|
|
"epoch": 2.4569532880303924,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004401992051414272,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.14044130891561507,
|
|
"num_tokens": 49671226.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 6.581265687942505,
|
|
"epoch": 2.457488362138156,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00044017324563029435,
|
|
"loss": 6.1922,
|
|
"mean_token_accuracy": 0.14174712002277373,
|
|
"num_tokens": 49682063.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 6.515926504135132,
|
|
"epoch": 2.45802343624592,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004401472813498074,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.14585558772087098,
|
|
"num_tokens": 49693768.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 6.609798336029053,
|
|
"epoch": 2.458558510353684,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00044012131230071575,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.1359372153878212,
|
|
"num_tokens": 49703807.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 6.559808301925659,
|
|
"epoch": 2.459093584461448,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004400953384837695,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.13829320147633553,
|
|
"num_tokens": 49714945.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 6.593253660202026,
|
|
"epoch": 2.459628658569212,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004400693598997185,
|
|
"loss": 6.1401,
|
|
"mean_token_accuracy": 0.15091168135404587,
|
|
"num_tokens": 49727267.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 6.611941862106323,
|
|
"epoch": 2.4601637326769756,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00044004337654931293,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.13963893577456474,
|
|
"num_tokens": 49738370.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 6.597040891647339,
|
|
"epoch": 2.4606988067847397,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00044001738843330306,
|
|
"loss": 6.2396,
|
|
"mean_token_accuracy": 0.1354781411588192,
|
|
"num_tokens": 49750113.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 6.567853260040283,
|
|
"epoch": 2.461233880892504,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00043999139555243936,
|
|
"loss": 6.3014,
|
|
"mean_token_accuracy": 0.13081169575452806,
|
|
"num_tokens": 49761163.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 6.609952116012574,
|
|
"epoch": 2.4617689550002675,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004399653979074722,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.13769548237323762,
|
|
"num_tokens": 49771185.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 6.646675777435303,
|
|
"epoch": 2.4623040291080316,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00043993939549915245,
|
|
"loss": 6.211,
|
|
"mean_token_accuracy": 0.14141955673694612,
|
|
"num_tokens": 49781202.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 6.589687013626099,
|
|
"epoch": 2.4628391032157952,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00043991338832823074,
|
|
"loss": 6.1849,
|
|
"mean_token_accuracy": 0.13683156073093414,
|
|
"num_tokens": 49790971.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 6.529941463470459,
|
|
"epoch": 2.4633741773235593,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004398873763954582,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.14026567637920379,
|
|
"num_tokens": 49800942.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 6.491559934616089,
|
|
"epoch": 2.463909251431323,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00043986135970158573,
|
|
"loss": 6.1338,
|
|
"mean_token_accuracy": 0.1408398523926735,
|
|
"num_tokens": 49812043.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 6.465959453582764,
|
|
"epoch": 2.464444325539087,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00043983533824736476,
|
|
"loss": 6.1529,
|
|
"mean_token_accuracy": 0.1559968963265419,
|
|
"num_tokens": 49823045.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 6.615090847015381,
|
|
"epoch": 2.464979399646851,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004398093120335465,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.14355914741754533,
|
|
"num_tokens": 49833014.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 6.576143407821656,
|
|
"epoch": 2.465514473754615,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00043978328106088254,
|
|
"loss": 6.1506,
|
|
"mean_token_accuracy": 0.13887238800525664,
|
|
"num_tokens": 49843171.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 6.542810249328613,
|
|
"epoch": 2.466049547862379,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004397572453301246,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.14906176328659057,
|
|
"num_tokens": 49853772.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 6.568971776962281,
|
|
"epoch": 2.466584621970143,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00043973120484202416,
|
|
"loss": 6.213,
|
|
"mean_token_accuracy": 0.14252916872501373,
|
|
"num_tokens": 49865379.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 6.577012062072754,
|
|
"epoch": 2.4671196960779067,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00043970515959733343,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.14053355604410173,
|
|
"num_tokens": 49876453.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 6.4928388595581055,
|
|
"epoch": 2.467654770185671,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00043967910959680435,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.1498573198914528,
|
|
"num_tokens": 49886675.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 6.533790588378906,
|
|
"epoch": 2.4681898442934345,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004396530548411891,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.1451677292585373,
|
|
"num_tokens": 49896946.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 6.591805267333984,
|
|
"epoch": 2.4687249184011986,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004396269953312401,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.13425560519099236,
|
|
"num_tokens": 49906989.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 6.487037897109985,
|
|
"epoch": 2.4692599925089627,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00043960093106770964,
|
|
"loss": 6.0281,
|
|
"mean_token_accuracy": 0.14676028564572335,
|
|
"num_tokens": 49917861.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 6.52523136138916,
|
|
"epoch": 2.4697950666167263,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00043957486205135047,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.14084675833582877,
|
|
"num_tokens": 49930529.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 6.555235385894775,
|
|
"epoch": 2.4703301407244904,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004395487882829153,
|
|
"loss": 6.1463,
|
|
"mean_token_accuracy": 0.14663565680384635,
|
|
"num_tokens": 49943067.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 6.567328310012817,
|
|
"epoch": 2.470865214832254,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00043952270976315707,
|
|
"loss": 6.1929,
|
|
"mean_token_accuracy": 0.13954328000545502,
|
|
"num_tokens": 49953648.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 6.648578739166259,
|
|
"epoch": 2.471400288940018,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00043949662649282853,
|
|
"loss": 6.2489,
|
|
"mean_token_accuracy": 0.13361161053180695,
|
|
"num_tokens": 49963571.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 6.570921134948731,
|
|
"epoch": 2.4719353630477823,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00043947053847268313,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.14862456321716308,
|
|
"num_tokens": 49974627.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 6.614248991012573,
|
|
"epoch": 2.472470437155546,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000439444445703474,
|
|
"loss": 6.2675,
|
|
"mean_token_accuracy": 0.14131628349423409,
|
|
"num_tokens": 49986659.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 6.5690172672271725,
|
|
"epoch": 2.47300551126331,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00043941834818595464,
|
|
"loss": 6.1883,
|
|
"mean_token_accuracy": 0.14746731668710708,
|
|
"num_tokens": 49997099.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 6.542939949035644,
|
|
"epoch": 2.473540585371074,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00043939224592087864,
|
|
"loss": 6.1984,
|
|
"mean_token_accuracy": 0.1399266578257084,
|
|
"num_tokens": 50008148.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 6.631348943710327,
|
|
"epoch": 2.474075659478838,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00043936613890899955,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.1328575298190117,
|
|
"num_tokens": 50019335.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 6.5282509326934814,
|
|
"epoch": 2.474610733586602,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004393400271510713,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.14660109281539918,
|
|
"num_tokens": 50029513.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 6.583563184738159,
|
|
"epoch": 2.4751458076943655,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00043931391064784786,
|
|
"loss": 6.2535,
|
|
"mean_token_accuracy": 0.13174295499920846,
|
|
"num_tokens": 50039353.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 6.578448915481568,
|
|
"epoch": 2.4756808818021296,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00043928778940008334,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.14084446877241136,
|
|
"num_tokens": 50050260.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 6.523663663864136,
|
|
"epoch": 2.4762159559098933,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00043926166340853203,
|
|
"loss": 6.0934,
|
|
"mean_token_accuracy": 0.13590084090828897,
|
|
"num_tokens": 50061384.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 6.595340919494629,
|
|
"epoch": 2.4767510300176574,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004392355326739483,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.14741005152463912,
|
|
"num_tokens": 50071984.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 6.509817314147949,
|
|
"epoch": 2.4772861041254215,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00043920939719708656,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.14337370842695235,
|
|
"num_tokens": 50083225.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 6.510489463806152,
|
|
"epoch": 2.477821178233185,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004391832569787016,
|
|
"loss": 6.1693,
|
|
"mean_token_accuracy": 0.14521462693810464,
|
|
"num_tokens": 50093240.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 6.5480855941772464,
|
|
"epoch": 2.4783562523409493,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004391571120195481,
|
|
"loss": 6.2127,
|
|
"mean_token_accuracy": 0.14012411311268808,
|
|
"num_tokens": 50103870.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 6.563443279266357,
|
|
"epoch": 2.4788913264487134,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004391309623203811,
|
|
"loss": 6.2341,
|
|
"mean_token_accuracy": 0.13797985538840293,
|
|
"num_tokens": 50115231.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 6.59563250541687,
|
|
"epoch": 2.479426400556477,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004391048078819556,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.14531537741422654,
|
|
"num_tokens": 50125592.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 6.498585033416748,
|
|
"epoch": 2.479961474664241,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004390786487050269,
|
|
"loss": 6.1285,
|
|
"mean_token_accuracy": 0.1453690730035305,
|
|
"num_tokens": 50136713.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 6.56780309677124,
|
|
"epoch": 2.4804965487720048,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004390524847903502,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.14090289250016214,
|
|
"num_tokens": 50148645.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 6.627575254440307,
|
|
"epoch": 2.481031622879769,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004390263161386811,
|
|
"loss": 6.1749,
|
|
"mean_token_accuracy": 0.14132757633924484,
|
|
"num_tokens": 50159973.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 6.59428038597107,
|
|
"epoch": 2.481566696987533,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00043900014275077517,
|
|
"loss": 6.1947,
|
|
"mean_token_accuracy": 0.13869029581546782,
|
|
"num_tokens": 50170591.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 6.571988534927368,
|
|
"epoch": 2.4821017710952966,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00043897396462738817,
|
|
"loss": 6.2157,
|
|
"mean_token_accuracy": 0.14687027484178544,
|
|
"num_tokens": 50182414.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 6.606548690795899,
|
|
"epoch": 2.4826368452030607,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004389477817692759,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.1359868824481964,
|
|
"num_tokens": 50192567.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 6.614966106414795,
|
|
"epoch": 2.4831719193108244,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004389215941771946,
|
|
"loss": 6.2328,
|
|
"mean_token_accuracy": 0.13815125450491905,
|
|
"num_tokens": 50203142.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 6.592585849761963,
|
|
"epoch": 2.4837069934185885,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00043889540185190024,
|
|
"loss": 6.2446,
|
|
"mean_token_accuracy": 0.13127191439270974,
|
|
"num_tokens": 50214854.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 6.605365753173828,
|
|
"epoch": 2.4842420675263526,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004388692047941492,
|
|
"loss": 6.1967,
|
|
"mean_token_accuracy": 0.13766995519399644,
|
|
"num_tokens": 50225999.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 6.638523244857788,
|
|
"epoch": 2.4847771416341162,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004388430030046978,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.13526825830340386,
|
|
"num_tokens": 50236657.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 6.630037450790406,
|
|
"epoch": 2.4853122157418803,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004388167964843029,
|
|
"loss": 6.2158,
|
|
"mean_token_accuracy": 0.13825089111924171,
|
|
"num_tokens": 50246457.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 6.551841497421265,
|
|
"epoch": 2.485847289849644,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004387905852337209,
|
|
"loss": 6.22,
|
|
"mean_token_accuracy": 0.13563032373785971,
|
|
"num_tokens": 50257020.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 6.599992036819458,
|
|
"epoch": 2.486382363957408,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00043876436925370873,
|
|
"loss": 6.1294,
|
|
"mean_token_accuracy": 0.14658360704779624,
|
|
"num_tokens": 50267173.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 6.5490397930145265,
|
|
"epoch": 2.486917438065172,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004387381485450235,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.14085866659879684,
|
|
"num_tokens": 50278352.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 6.573115491867066,
|
|
"epoch": 2.487452512172936,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00043871192310842216,
|
|
"loss": 6.2914,
|
|
"mean_token_accuracy": 0.13282587453722955,
|
|
"num_tokens": 50290301.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 6.659524440765381,
|
|
"epoch": 2.4879875862807,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004386856929446621,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.13170573711395264,
|
|
"num_tokens": 50301707.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 6.615113210678101,
|
|
"epoch": 2.4885226603884636,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004386594580545006,
|
|
"loss": 6.2224,
|
|
"mean_token_accuracy": 0.14283460453152658,
|
|
"num_tokens": 50313334.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 6.570059680938721,
|
|
"epoch": 2.4890577344962277,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004386332184386953,
|
|
"loss": 6.2171,
|
|
"mean_token_accuracy": 0.14413201287388802,
|
|
"num_tokens": 50324228.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 6.464450693130493,
|
|
"epoch": 2.489592808603992,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00043860697409800383,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.14365957379341127,
|
|
"num_tokens": 50335001.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 6.55489296913147,
|
|
"epoch": 2.4901278827117554,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00043858072503318393,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.1411533311009407,
|
|
"num_tokens": 50346415.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 6.582531595230103,
|
|
"epoch": 2.4906629568195195,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043855447124499356,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.13599497452378273,
|
|
"num_tokens": 50357625.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 6.562934446334839,
|
|
"epoch": 2.4911980309272836,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00043852821273419087,
|
|
"loss": 6.1139,
|
|
"mean_token_accuracy": 0.15196037888526917,
|
|
"num_tokens": 50367672.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 6.502917385101318,
|
|
"epoch": 2.4917331050350473,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000438501949501534,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.14414839819073677,
|
|
"num_tokens": 50378220.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 6.5431873321533205,
|
|
"epoch": 2.4922681791428114,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00043847568154778134,
|
|
"loss": 6.0899,
|
|
"mean_token_accuracy": 0.1467802807688713,
|
|
"num_tokens": 50389517.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 6.5760761260986325,
|
|
"epoch": 2.492803253250575,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004384494088736913,
|
|
"loss": 6.1856,
|
|
"mean_token_accuracy": 0.14401412159204482,
|
|
"num_tokens": 50401155.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 6.552769947052002,
|
|
"epoch": 2.493338327358339,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004384231314800226,
|
|
"loss": 6.1825,
|
|
"mean_token_accuracy": 0.14262628555297852,
|
|
"num_tokens": 50412609.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 6.565682697296142,
|
|
"epoch": 2.493873401466103,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004383968493675339,
|
|
"loss": 6.1971,
|
|
"mean_token_accuracy": 0.1379497766494751,
|
|
"num_tokens": 50422665.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 6.618400049209595,
|
|
"epoch": 2.494408475573867,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004383705625369841,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.13191719874739646,
|
|
"num_tokens": 50434012.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 6.615737676620483,
|
|
"epoch": 2.494943549681631,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004383442709891323,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.13519085794687272,
|
|
"num_tokens": 50444270.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 6.525007581710815,
|
|
"epoch": 2.4954786237893947,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00043831797472473763,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.14782456904649735,
|
|
"num_tokens": 50455236.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 6.55296368598938,
|
|
"epoch": 2.4960136978971588,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004382916737445594,
|
|
"loss": 6.2247,
|
|
"mean_token_accuracy": 0.1355710059404373,
|
|
"num_tokens": 50466431.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 6.657807922363281,
|
|
"epoch": 2.496548772004923,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000438265368049357,
|
|
"loss": 6.2698,
|
|
"mean_token_accuracy": 0.13292243778705598,
|
|
"num_tokens": 50477211.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 6.632038927078247,
|
|
"epoch": 2.4970838461126865,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00043823905763989003,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.13709299266338348,
|
|
"num_tokens": 50488668.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 6.547015428543091,
|
|
"epoch": 2.4976189202204506,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00043821274251691823,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.14607506468892098,
|
|
"num_tokens": 50498031.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 6.4287440299987795,
|
|
"epoch": 2.4981539943282143,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00043818642268120153,
|
|
"loss": 6.1329,
|
|
"mean_token_accuracy": 0.14218931272625923,
|
|
"num_tokens": 50508567.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 6.532089710235596,
|
|
"epoch": 2.4986890684359784,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00043816009813349964,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.14911196753382683,
|
|
"num_tokens": 50519057.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 6.644241571426392,
|
|
"epoch": 2.4992241425437425,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000438133768874573,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.14033986553549765,
|
|
"num_tokens": 50530572.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 6.585339307785034,
|
|
"epoch": 2.499759216651506,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00043810743490518155,
|
|
"loss": 6.2148,
|
|
"mean_token_accuracy": 0.1399044945836067,
|
|
"num_tokens": 50541195.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 6.581700468063355,
|
|
"epoch": 2.5002942907592702,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00043808109622608596,
|
|
"loss": 6.3045,
|
|
"mean_token_accuracy": 0.1308658614754677,
|
|
"num_tokens": 50552655.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 6.559261655807495,
|
|
"epoch": 2.500829364867034,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00043805475283804657,
|
|
"loss": 6.2354,
|
|
"mean_token_accuracy": 0.13739247471094132,
|
|
"num_tokens": 50562848.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 6.544573068618774,
|
|
"epoch": 2.501364438974798,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004380284047418241,
|
|
"loss": 6.1825,
|
|
"mean_token_accuracy": 0.1492833361029625,
|
|
"num_tokens": 50572690.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 6.516261243820191,
|
|
"epoch": 2.501899513082562,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004380020519381794,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.14783216491341591,
|
|
"num_tokens": 50583826.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 6.4821141242980955,
|
|
"epoch": 2.5024345871903257,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00043797569442787334,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.14270055368542672,
|
|
"num_tokens": 50595148.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 6.632216501235962,
|
|
"epoch": 2.50296966129809,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000437949332211667,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.13714811876416205,
|
|
"num_tokens": 50606568.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 6.644623136520385,
|
|
"epoch": 2.503504735405854,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00043792296529032156,
|
|
"loss": 6.2313,
|
|
"mean_token_accuracy": 0.13420336470007896,
|
|
"num_tokens": 50618144.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 6.593896198272705,
|
|
"epoch": 2.5040398095136176,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004378965936645984,
|
|
"loss": 6.1569,
|
|
"mean_token_accuracy": 0.14487072080373764,
|
|
"num_tokens": 50629721.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 6.551956033706665,
|
|
"epoch": 2.5045748836213817,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00043787021733525904,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.13993795588612556,
|
|
"num_tokens": 50640482.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 6.608171463012695,
|
|
"epoch": 2.5051099577291454,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000437843836303065,
|
|
"loss": 6.2596,
|
|
"mean_token_accuracy": 0.13669075816869736,
|
|
"num_tokens": 50652261.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 6.5592132091522215,
|
|
"epoch": 2.5056450318369095,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004378174505687781,
|
|
"loss": 6.0343,
|
|
"mean_token_accuracy": 0.14036520048975945,
|
|
"num_tokens": 50662397.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 6.520137977600098,
|
|
"epoch": 2.506180105944673,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004377910601331601,
|
|
"loss": 6.1729,
|
|
"mean_token_accuracy": 0.14021281003952027,
|
|
"num_tokens": 50673494.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 6.457839107513427,
|
|
"epoch": 2.506715180052437,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004377646649969733,
|
|
"loss": 6.119,
|
|
"mean_token_accuracy": 0.14647033289074898,
|
|
"num_tokens": 50683963.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 6.58657922744751,
|
|
"epoch": 2.5072502541602013,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00043773826516097945,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.1407020352780819,
|
|
"num_tokens": 50694449.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 6.596576356887818,
|
|
"epoch": 2.507785328267965,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00043771186062594114,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.14285276010632514,
|
|
"num_tokens": 50705877.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 6.551129531860352,
|
|
"epoch": 2.508320402375729,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00043768545139262076,
|
|
"loss": 6.2064,
|
|
"mean_token_accuracy": 0.14183696657419204,
|
|
"num_tokens": 50716581.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 6.555866861343384,
|
|
"epoch": 2.508855476483493,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004376590374617809,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.1400114804506302,
|
|
"num_tokens": 50727948.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 6.463600730895996,
|
|
"epoch": 2.509390550591257,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00043763261883418396,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.15792732760310174,
|
|
"num_tokens": 50739189.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 6.510007429122925,
|
|
"epoch": 2.509925624699021,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004376061955105932,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.14361271634697914,
|
|
"num_tokens": 50749439.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 6.549712228775024,
|
|
"epoch": 2.5104606988067846,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00043757976749177137,
|
|
"loss": 6.2727,
|
|
"mean_token_accuracy": 0.13862788081169128,
|
|
"num_tokens": 50761463.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 6.594852113723755,
|
|
"epoch": 2.5109957729145487,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004375533347784816,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.13393818959593773,
|
|
"num_tokens": 50771359.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 6.580721521377564,
|
|
"epoch": 2.5115308470223123,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00043752689737148705,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.14026760756969453,
|
|
"num_tokens": 50781669.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 6.605483102798462,
|
|
"epoch": 2.5120659211300764,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00043750045527155126,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.14111865684390068,
|
|
"num_tokens": 50792217.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 6.587331485748291,
|
|
"epoch": 2.5126009952378405,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004374740084794376,
|
|
"loss": 6.2279,
|
|
"mean_token_accuracy": 0.14035352692008018,
|
|
"num_tokens": 50805288.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 6.523919105529785,
|
|
"epoch": 2.513136069345604,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004374475569959098,
|
|
"loss": 6.1656,
|
|
"mean_token_accuracy": 0.14503239542245866,
|
|
"num_tokens": 50815563.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 6.548303270339966,
|
|
"epoch": 2.5136711434533683,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004374211008217316,
|
|
"loss": 6.1743,
|
|
"mean_token_accuracy": 0.14389263466000557,
|
|
"num_tokens": 50826108.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 6.507506895065307,
|
|
"epoch": 2.5142062175611324,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00043739463995766696,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.1433514878153801,
|
|
"num_tokens": 50837180.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 6.513788890838623,
|
|
"epoch": 2.514741291668896,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004373681744044799,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.14458876028656958,
|
|
"num_tokens": 50847430.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 6.580620002746582,
|
|
"epoch": 2.51527636577666,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.00043734170416293467,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.1423148810863495,
|
|
"num_tokens": 50858100.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 6.564510154724121,
|
|
"epoch": 2.5158114398844242,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00043731522923379554,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.13347225934267043,
|
|
"num_tokens": 50868549.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 6.588267469406128,
|
|
"epoch": 2.516346513992188,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004372887496178269,
|
|
"loss": 6.1905,
|
|
"mean_token_accuracy": 0.1401882417500019,
|
|
"num_tokens": 50879522.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 6.545710229873658,
|
|
"epoch": 2.516881588099952,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004372622653157935,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.1400975413620472,
|
|
"num_tokens": 50891139.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 6.552085065841675,
|
|
"epoch": 2.5174166622077156,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004372357763284599,
|
|
"loss": 6.2338,
|
|
"mean_token_accuracy": 0.13401019647717477,
|
|
"num_tokens": 50901267.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 6.5813562870025635,
|
|
"epoch": 2.5179517363154797,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004372092826565911,
|
|
"loss": 6.1309,
|
|
"mean_token_accuracy": 0.1452510364353657,
|
|
"num_tokens": 50912137.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 6.5678050994873045,
|
|
"epoch": 2.5184868104232434,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004371827843009521,
|
|
"loss": 6.2182,
|
|
"mean_token_accuracy": 0.14051555544137956,
|
|
"num_tokens": 50922724.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 6.563961553573608,
|
|
"epoch": 2.5190218845310075,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00043715628126230795,
|
|
"loss": 6.2078,
|
|
"mean_token_accuracy": 0.13902231976389884,
|
|
"num_tokens": 50934617.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 6.592443180084229,
|
|
"epoch": 2.5195569586387716,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004371297735414239,
|
|
"loss": 6.2185,
|
|
"mean_token_accuracy": 0.14081588238477707,
|
|
"num_tokens": 50945179.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 6.5607850551605225,
|
|
"epoch": 2.5200920327465353,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00043710326113906555,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.1405520483851433,
|
|
"num_tokens": 50955383.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 6.625709104537964,
|
|
"epoch": 2.5206271068542994,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004370767440559983,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.14259199053049088,
|
|
"num_tokens": 50966107.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 6.498420333862304,
|
|
"epoch": 2.5211621809620635,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00043705022229298775,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.16112855896353723,
|
|
"num_tokens": 50977042.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 6.505741977691651,
|
|
"epoch": 2.521697255069827,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004370236958507998,
|
|
"loss": 6.2445,
|
|
"mean_token_accuracy": 0.14243893101811408,
|
|
"num_tokens": 50986999.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 6.615095424652099,
|
|
"epoch": 2.522232329177591,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004369971647302005,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.13469621986150743,
|
|
"num_tokens": 50997824.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 6.687608623504639,
|
|
"epoch": 2.522767403285355,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004369706289319558,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.13765193596482278,
|
|
"num_tokens": 51009001.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 6.526150274276733,
|
|
"epoch": 2.523302477393119,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043694408845683185,
|
|
"loss": 6.1842,
|
|
"mean_token_accuracy": 0.14509233236312866,
|
|
"num_tokens": 51019222.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 6.550604009628296,
|
|
"epoch": 2.5238375515008826,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004369175433055952,
|
|
"loss": 6.1686,
|
|
"mean_token_accuracy": 0.13766011446714402,
|
|
"num_tokens": 51029473.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 6.595000076293945,
|
|
"epoch": 2.5243726256086467,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00043689099347901227,
|
|
"loss": 6.1809,
|
|
"mean_token_accuracy": 0.14395889341831208,
|
|
"num_tokens": 51040667.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 6.531175518035889,
|
|
"epoch": 2.524907699716411,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00043686443897784954,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.1464095339179039,
|
|
"num_tokens": 51050386.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 6.548489284515381,
|
|
"epoch": 2.5254427738241745,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000436837879802874,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.14163751751184464,
|
|
"num_tokens": 51060752.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 6.534994220733642,
|
|
"epoch": 2.5259778479319386,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043681131595485234,
|
|
"loss": 6.1892,
|
|
"mean_token_accuracy": 0.14004546478390695,
|
|
"num_tokens": 51072467.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 6.680403184890747,
|
|
"epoch": 2.5265129220397027,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004367847474345517,
|
|
"loss": 6.2784,
|
|
"mean_token_accuracy": 0.1373277485370636,
|
|
"num_tokens": 51083404.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 6.601364374160767,
|
|
"epoch": 2.5270479961474663,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00043675817424273925,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.145694612711668,
|
|
"num_tokens": 51094392.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 6.552385950088501,
|
|
"epoch": 2.5275830702552304,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00043673159638018215,
|
|
"loss": 6.1862,
|
|
"mean_token_accuracy": 0.13883354961872102,
|
|
"num_tokens": 51104706.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 6.561319828033447,
|
|
"epoch": 2.5281181443629945,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000436705013847648,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.1407299146056175,
|
|
"num_tokens": 51114881.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 6.648111295700073,
|
|
"epoch": 2.528653218470758,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004366784266459043,
|
|
"loss": 6.2632,
|
|
"mean_token_accuracy": 0.13806032240390778,
|
|
"num_tokens": 51125705.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 6.5972291946411135,
|
|
"epoch": 2.5291882925785223,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00043665183477571874,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.13478989005088807,
|
|
"num_tokens": 51136460.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 6.5489248752594,
|
|
"epoch": 2.529723366686286,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004366252382378592,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.1456507697701454,
|
|
"num_tokens": 51146206.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 6.557229089736938,
|
|
"epoch": 2.53025844079405,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004365986370330935,
|
|
"loss": 6.2825,
|
|
"mean_token_accuracy": 0.13528637140989302,
|
|
"num_tokens": 51156650.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 6.6003594398498535,
|
|
"epoch": 2.5307935149018137,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00043657203116218994,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.13711861297488212,
|
|
"num_tokens": 51168401.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 6.607922792434692,
|
|
"epoch": 2.531328589009578,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043654542062591674,
|
|
"loss": 6.1986,
|
|
"mean_token_accuracy": 0.13482684418559074,
|
|
"num_tokens": 51178571.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 6.5786622047424315,
|
|
"epoch": 2.531863663117342,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00043651880542504214,
|
|
"loss": 6.2587,
|
|
"mean_token_accuracy": 0.13363634794950485,
|
|
"num_tokens": 51189143.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 6.569158697128296,
|
|
"epoch": 2.5323987372251056,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00043649218556033475,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.13778189942240715,
|
|
"num_tokens": 51200552.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 6.593986463546753,
|
|
"epoch": 2.5329338113328697,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004364655610325632,
|
|
"loss": 6.2162,
|
|
"mean_token_accuracy": 0.13980167210102082,
|
|
"num_tokens": 51210493.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 6.530652141571045,
|
|
"epoch": 2.5334688854406338,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004364389318424962,
|
|
"loss": 6.1834,
|
|
"mean_token_accuracy": 0.14060719236731528,
|
|
"num_tokens": 51220535.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 6.540695285797119,
|
|
"epoch": 2.5340039595483974,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00043641229799090285,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.13430460914969444,
|
|
"num_tokens": 51232078.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 6.565031862258911,
|
|
"epoch": 2.5345390336561615,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000436385659478552,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.1478009007871151,
|
|
"num_tokens": 51242750.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 6.636708450317383,
|
|
"epoch": 2.535074107763925,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00043635901630621293,
|
|
"loss": 6.259,
|
|
"mean_token_accuracy": 0.1354198068380356,
|
|
"num_tokens": 51254295.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 6.586541748046875,
|
|
"epoch": 2.5356091818716893,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00043633236847465497,
|
|
"loss": 6.2131,
|
|
"mean_token_accuracy": 0.140294548869133,
|
|
"num_tokens": 51265060.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 6.5132965564727785,
|
|
"epoch": 2.536144255979453,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004363057159846475,
|
|
"loss": 6.125,
|
|
"mean_token_accuracy": 0.14150992631912232,
|
|
"num_tokens": 51275623.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 6.50688533782959,
|
|
"epoch": 2.536679330087217,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004362790588369602,
|
|
"loss": 6.1062,
|
|
"mean_token_accuracy": 0.15126922428607942,
|
|
"num_tokens": 51285830.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 6.582822942733765,
|
|
"epoch": 2.537214404194981,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004362523970323627,
|
|
"loss": 6.2237,
|
|
"mean_token_accuracy": 0.1409708522260189,
|
|
"num_tokens": 51297047.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 6.608353042602539,
|
|
"epoch": 2.5377494783027448,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00043622573057162484,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.13784098476171494,
|
|
"num_tokens": 51307254.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 6.588401174545288,
|
|
"epoch": 2.538284552410509,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004361990594555167,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.1339943826198578,
|
|
"num_tokens": 51317796.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 6.579130029678344,
|
|
"epoch": 2.538819626518273,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00043617238368480845,
|
|
"loss": 6.3102,
|
|
"mean_token_accuracy": 0.13548193275928497,
|
|
"num_tokens": 51330172.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 6.621174573898315,
|
|
"epoch": 2.5393547006260366,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00043614570326027015,
|
|
"loss": 6.1468,
|
|
"mean_token_accuracy": 0.1509023666381836,
|
|
"num_tokens": 51340844.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 6.5853204250335695,
|
|
"epoch": 2.5398897747338007,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004361190181826724,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.14102248027920722,
|
|
"num_tokens": 51352078.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 6.523656845092773,
|
|
"epoch": 2.540424848841565,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00043609232845278565,
|
|
"loss": 6.2795,
|
|
"mean_token_accuracy": 0.13425008282065393,
|
|
"num_tokens": 51364121.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 6.5692667961120605,
|
|
"epoch": 2.5409599229493285,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004360656340713805,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.15009300261735917,
|
|
"num_tokens": 51375046.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 6.572698163986206,
|
|
"epoch": 2.541494997057092,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004360389350392278,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.13670057356357573,
|
|
"num_tokens": 51386363.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 6.50921630859375,
|
|
"epoch": 2.5420300711648562,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00043601223135709846,
|
|
"loss": 6.1148,
|
|
"mean_token_accuracy": 0.15063474774360658,
|
|
"num_tokens": 51398036.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 6.531105041503906,
|
|
"epoch": 2.5425651452726203,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004359855230257636,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.14176757857203484,
|
|
"num_tokens": 51408769.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 6.567804527282715,
|
|
"epoch": 2.543100219380384,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00043595881004599444,
|
|
"loss": 6.2258,
|
|
"mean_token_accuracy": 0.1369999274611473,
|
|
"num_tokens": 51420315.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 6.570938587188721,
|
|
"epoch": 2.543635293488148,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00043593209241856216,
|
|
"loss": 6.1617,
|
|
"mean_token_accuracy": 0.14906059205532074,
|
|
"num_tokens": 51432283.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 6.6053540229797365,
|
|
"epoch": 2.544170367595912,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00043590537014423833,
|
|
"loss": 6.1883,
|
|
"mean_token_accuracy": 0.14526057839393616,
|
|
"num_tokens": 51443151.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 6.47984471321106,
|
|
"epoch": 2.544705441703676,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004358786432237946,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.1451314426958561,
|
|
"num_tokens": 51453964.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 6.548235988616943,
|
|
"epoch": 2.54524051581144,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004358519116580026,
|
|
"loss": 6.1571,
|
|
"mean_token_accuracy": 0.14378248602151872,
|
|
"num_tokens": 51464236.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 6.444574451446533,
|
|
"epoch": 2.545775589919204,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004358251754476344,
|
|
"loss": 6.1317,
|
|
"mean_token_accuracy": 0.1523175820708275,
|
|
"num_tokens": 51474388.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 6.512021398544311,
|
|
"epoch": 2.5463106640269677,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004357984345934617,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.13515693321824074,
|
|
"num_tokens": 51485209.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 6.566023588180542,
|
|
"epoch": 2.546845738134732,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004357716890962568,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.1465166389942169,
|
|
"num_tokens": 51495993.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 6.539640426635742,
|
|
"epoch": 2.5473808122424955,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000435744938956792,
|
|
"loss": 6.13,
|
|
"mean_token_accuracy": 0.14474419504404068,
|
|
"num_tokens": 51506282.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 6.542548274993896,
|
|
"epoch": 2.5479158863502596,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00043571818417583976,
|
|
"loss": 6.262,
|
|
"mean_token_accuracy": 0.1375872403383255,
|
|
"num_tokens": 51517728.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 6.572766590118408,
|
|
"epoch": 2.548450960458023,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004356914247541724,
|
|
"loss": 6.1778,
|
|
"mean_token_accuracy": 0.13943342864513397,
|
|
"num_tokens": 51528769.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 6.566153812408447,
|
|
"epoch": 2.5489860345657873,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00043566466069256283,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.14363037198781967,
|
|
"num_tokens": 51540148.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 6.58780083656311,
|
|
"epoch": 2.5495211086735514,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004356378919917837,
|
|
"loss": 6.1592,
|
|
"mean_token_accuracy": 0.1439876526594162,
|
|
"num_tokens": 51550657.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 6.5809732437133786,
|
|
"epoch": 2.550056182781315,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004356111186526081,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.14554023891687393,
|
|
"num_tokens": 51560399.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 6.584104871749878,
|
|
"epoch": 2.550591256889079,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043558434067580894,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.1396302103996277,
|
|
"num_tokens": 51571463.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 6.577657413482666,
|
|
"epoch": 2.5511263309968433,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00043555755806215946,
|
|
"loss": 6.1206,
|
|
"mean_token_accuracy": 0.14839429706335067,
|
|
"num_tokens": 51583136.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 6.537318325042724,
|
|
"epoch": 2.551661405104607,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00043553077081243314,
|
|
"loss": 6.2404,
|
|
"mean_token_accuracy": 0.13799526765942574,
|
|
"num_tokens": 51594397.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 6.535944890975952,
|
|
"epoch": 2.552196479212371,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004355039789274034,
|
|
"loss": 6.2912,
|
|
"mean_token_accuracy": 0.13698622658848764,
|
|
"num_tokens": 51605788.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 6.595166540145874,
|
|
"epoch": 2.5527315533201347,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004354771824078437,
|
|
"loss": 6.1906,
|
|
"mean_token_accuracy": 0.1375291496515274,
|
|
"num_tokens": 51615693.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 6.522503995895386,
|
|
"epoch": 2.553266627427899,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00043545038125452793,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.14652308970689773,
|
|
"num_tokens": 51626607.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 6.535194253921508,
|
|
"epoch": 2.5538017015356624,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00043542357546823003,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.14471736922860146,
|
|
"num_tokens": 51636905.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 6.544647693634033,
|
|
"epoch": 2.5543367756434265,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00043539676504972393,
|
|
"loss": 6.1801,
|
|
"mean_token_accuracy": 0.14050254747271537,
|
|
"num_tokens": 51648142.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 6.607646799087524,
|
|
"epoch": 2.5548718497511906,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004353699499997837,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.1354542165994644,
|
|
"num_tokens": 51659583.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 6.553555345535278,
|
|
"epoch": 2.5554069238589543,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004353431303191837,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.13480132147669793,
|
|
"num_tokens": 51670582.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 6.667104434967041,
|
|
"epoch": 2.5559419979667184,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00043531630600869846,
|
|
"loss": 6.2632,
|
|
"mean_token_accuracy": 0.13191739693284035,
|
|
"num_tokens": 51680773.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 6.616030836105347,
|
|
"epoch": 2.5564770720744825,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004352894770691024,
|
|
"loss": 6.2103,
|
|
"mean_token_accuracy": 0.14156819880008698,
|
|
"num_tokens": 51690680.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 6.563816261291504,
|
|
"epoch": 2.557012146182246,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004352626435011701,
|
|
"loss": 6.1762,
|
|
"mean_token_accuracy": 0.14677293598651886,
|
|
"num_tokens": 51700910.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 6.565460157394409,
|
|
"epoch": 2.5575472202900102,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00043523580530567654,
|
|
"loss": 6.1863,
|
|
"mean_token_accuracy": 0.14103823378682137,
|
|
"num_tokens": 51712331.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 6.508602094650269,
|
|
"epoch": 2.5580822943977743,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004352089624833966,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.14670649021863938,
|
|
"num_tokens": 51722805.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 6.549962425231934,
|
|
"epoch": 2.558617368505538,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00043518211503510535,
|
|
"loss": 6.1745,
|
|
"mean_token_accuracy": 0.14431192129850387,
|
|
"num_tokens": 51733909.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 6.550505495071411,
|
|
"epoch": 2.559152442613302,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00043515526296157813,
|
|
"loss": 6.2348,
|
|
"mean_token_accuracy": 0.1330706663429737,
|
|
"num_tokens": 51745062.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 6.594059467315674,
|
|
"epoch": 2.5596875167210658,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004351284062635901,
|
|
"loss": 6.258,
|
|
"mean_token_accuracy": 0.13754986524581908,
|
|
"num_tokens": 51756235.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 6.612155389785767,
|
|
"epoch": 2.56022259082883,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000435101544941917,
|
|
"loss": 6.1792,
|
|
"mean_token_accuracy": 0.14121299982070923,
|
|
"num_tokens": 51765689.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 6.5233465194702145,
|
|
"epoch": 2.5607576649365935,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004350746789973341,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.14829456210136413,
|
|
"num_tokens": 51777090.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 6.542276668548584,
|
|
"epoch": 2.5612927390443576,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004350478084306174,
|
|
"loss": 6.2213,
|
|
"mean_token_accuracy": 0.136881535500288,
|
|
"num_tokens": 51787360.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 6.531747722625733,
|
|
"epoch": 2.5618278131521217,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004350209332425428,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.1445350505411625,
|
|
"num_tokens": 51799075.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 6.462994718551636,
|
|
"epoch": 2.5623628872598854,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00043499405343388613,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.1600067473948002,
|
|
"num_tokens": 51810024.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 6.5702996253967285,
|
|
"epoch": 2.5628979613676495,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004349671690054238,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.13680429905653,
|
|
"num_tokens": 51820710.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 6.558108377456665,
|
|
"epoch": 2.5634330354754136,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00043494027995793176,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.1402980923652649,
|
|
"num_tokens": 51831451.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 6.431221437454224,
|
|
"epoch": 2.5639681095831772,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004349133862921867,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.15267557501792908,
|
|
"num_tokens": 51841483.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 6.569863748550415,
|
|
"epoch": 2.5645031836909413,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00043488648800896516,
|
|
"loss": 6.1442,
|
|
"mean_token_accuracy": 0.1451101556420326,
|
|
"num_tokens": 51852838.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 6.500291252136231,
|
|
"epoch": 2.565038257798705,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004348595851090436,
|
|
"loss": 6.1832,
|
|
"mean_token_accuracy": 0.1431698225438595,
|
|
"num_tokens": 51863851.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 6.493624925613403,
|
|
"epoch": 2.565573331906469,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00043483267759319907,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.14460720047354697,
|
|
"num_tokens": 51874380.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 6.616022300720215,
|
|
"epoch": 2.5661084060142327,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004348057654622084,
|
|
"loss": 6.1557,
|
|
"mean_token_accuracy": 0.13882671147584916,
|
|
"num_tokens": 51884594.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 6.639428567886353,
|
|
"epoch": 2.566643480121997,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004347788487168487,
|
|
"loss": 6.2649,
|
|
"mean_token_accuracy": 0.13798629641532897,
|
|
"num_tokens": 51897679.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 6.605780410766601,
|
|
"epoch": 2.567178554229761,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004347519273578972,
|
|
"loss": 6.3064,
|
|
"mean_token_accuracy": 0.1348626807332039,
|
|
"num_tokens": 51907501.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 6.568436527252198,
|
|
"epoch": 2.5677136283375246,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00043472500138613124,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.13716496527194977,
|
|
"num_tokens": 51917732.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 6.601845788955688,
|
|
"epoch": 2.5682487024452887,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004346980708023284,
|
|
"loss": 6.2643,
|
|
"mean_token_accuracy": 0.13747099563479423,
|
|
"num_tokens": 51929038.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.5682487024452887,
|
|
"eval_entropy": 6.3842873251984384,
|
|
"eval_loss": 6.29932975769043,
|
|
"eval_mean_token_accuracy": 0.14311343311229244,
|
|
"eval_num_tokens": 51929038.0,
|
|
"eval_runtime": 22.8141,
|
|
"eval_samples_per_second": 1300.909,
|
|
"eval_steps_per_second": 162.619,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 6.619065046310425,
|
|
"epoch": 2.568783776553053,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004346711356072661,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.1335938774049282,
|
|
"num_tokens": 51939481.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 6.662156581878662,
|
|
"epoch": 2.5693188506608164,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004346441958017222,
|
|
"loss": 6.2531,
|
|
"mean_token_accuracy": 0.13729004561901093,
|
|
"num_tokens": 51951393.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 6.646235084533691,
|
|
"epoch": 2.5698539247685805,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004346172513864746,
|
|
"loss": 6.2844,
|
|
"mean_token_accuracy": 0.1319551944732666,
|
|
"num_tokens": 51962897.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 6.611423969268799,
|
|
"epoch": 2.5703889988763446,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00043459030236230137,
|
|
"loss": 6.198,
|
|
"mean_token_accuracy": 0.14238701462745668,
|
|
"num_tokens": 51974443.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 6.5468724250793455,
|
|
"epoch": 2.5709240729841083,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004345633487299805,
|
|
"loss": 6.2111,
|
|
"mean_token_accuracy": 0.14234139323234557,
|
|
"num_tokens": 51985158.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 6.6647895812988285,
|
|
"epoch": 2.571459147091872,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00043453639049029035,
|
|
"loss": 6.3044,
|
|
"mean_token_accuracy": 0.13237544447183608,
|
|
"num_tokens": 51994956.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 6.620481348037719,
|
|
"epoch": 2.571994221199636,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00043450942764400937,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.1436376191675663,
|
|
"num_tokens": 52004922.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 6.508921146392822,
|
|
"epoch": 2.5725292953074,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004344824601919161,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.15018639713525772,
|
|
"num_tokens": 52014684.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 6.562528133392334,
|
|
"epoch": 2.573064369415164,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00043445548813478914,
|
|
"loss": 6.1526,
|
|
"mean_token_accuracy": 0.14551526829600334,
|
|
"num_tokens": 52025283.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 6.595951557159424,
|
|
"epoch": 2.573599443522928,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004344285114734074,
|
|
"loss": 6.2641,
|
|
"mean_token_accuracy": 0.13992835953831673,
|
|
"num_tokens": 52036513.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 6.627249526977539,
|
|
"epoch": 2.574134517630692,
|
|
"grad_norm": 4.84375,
|
|
"learning_rate": 0.00043440153020854987,
|
|
"loss": 6.1386,
|
|
"mean_token_accuracy": 0.14859954118728638,
|
|
"num_tokens": 52047230.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 6.6056671142578125,
|
|
"epoch": 2.5746695917384557,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004343745443409954,
|
|
"loss": 6.2129,
|
|
"mean_token_accuracy": 0.14009647890925409,
|
|
"num_tokens": 52058889.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 6.541915941238403,
|
|
"epoch": 2.5752046658462198,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00043434755387152354,
|
|
"loss": 6.1234,
|
|
"mean_token_accuracy": 0.1441617116332054,
|
|
"num_tokens": 52068478.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 6.51550555229187,
|
|
"epoch": 2.575739739953984,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004343205588009133,
|
|
"loss": 6.1813,
|
|
"mean_token_accuracy": 0.14157261699438095,
|
|
"num_tokens": 52079756.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 6.596438884735107,
|
|
"epoch": 2.5762748140617475,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00043429355912994437,
|
|
"loss": 6.1667,
|
|
"mean_token_accuracy": 0.13893031626939772,
|
|
"num_tokens": 52090452.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 6.558697319030761,
|
|
"epoch": 2.5768098881695116,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004342665548593964,
|
|
"loss": 6.1102,
|
|
"mean_token_accuracy": 0.14269472360610963,
|
|
"num_tokens": 52101134.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 6.582512044906617,
|
|
"epoch": 2.5773449622772753,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004342395459900489,
|
|
"loss": 6.1418,
|
|
"mean_token_accuracy": 0.1382672294974327,
|
|
"num_tokens": 52111529.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 6.46117205619812,
|
|
"epoch": 2.5778800363850394,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.00043421253252268194,
|
|
"loss": 6.1357,
|
|
"mean_token_accuracy": 0.13808883130550384,
|
|
"num_tokens": 52122779.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 6.532436752319336,
|
|
"epoch": 2.578415110492803,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004341855144580754,
|
|
"loss": 6.134,
|
|
"mean_token_accuracy": 0.13865361958742142,
|
|
"num_tokens": 52134140.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 6.595927000045776,
|
|
"epoch": 2.578950184600567,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00043415849179700956,
|
|
"loss": 6.1634,
|
|
"mean_token_accuracy": 0.13834074884653091,
|
|
"num_tokens": 52146033.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 6.541924905776978,
|
|
"epoch": 2.5794852587083312,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004341314645402647,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.13868132010102271,
|
|
"num_tokens": 52157516.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 6.554893350601196,
|
|
"epoch": 2.580020332816095,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004341044326886211,
|
|
"loss": 6.1855,
|
|
"mean_token_accuracy": 0.1470040574669838,
|
|
"num_tokens": 52167523.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 6.4754222393035885,
|
|
"epoch": 2.580555406923859,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004340773962428593,
|
|
"loss": 6.0881,
|
|
"mean_token_accuracy": 0.14982061758637427,
|
|
"num_tokens": 52178235.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 6.525172376632691,
|
|
"epoch": 2.581090481031623,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00043405035520376013,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.1495649039745331,
|
|
"num_tokens": 52188586.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 6.610724210739136,
|
|
"epoch": 2.5816255551393867,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004340233095721043,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.1461607962846756,
|
|
"num_tokens": 52199081.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 6.570985603332519,
|
|
"epoch": 2.582160629247151,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004339962593486727,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.14181596040725708,
|
|
"num_tokens": 52210324.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 6.557026958465576,
|
|
"epoch": 2.5826957033549145,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00043396920453424656,
|
|
"loss": 6.215,
|
|
"mean_token_accuracy": 0.1348014973104,
|
|
"num_tokens": 52221973.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 6.503771877288818,
|
|
"epoch": 2.5832307774626786,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00043394214512960683,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.14250057190656662,
|
|
"num_tokens": 52232560.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 6.564362335205078,
|
|
"epoch": 2.5837658515704423,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004339150811355351,
|
|
"loss": 6.0824,
|
|
"mean_token_accuracy": 0.1478087306022644,
|
|
"num_tokens": 52243416.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 6.5455397605896,
|
|
"epoch": 2.5843009256782064,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004338880125528127,
|
|
"loss": 6.1833,
|
|
"mean_token_accuracy": 0.1434246927499771,
|
|
"num_tokens": 52254213.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 6.463933610916138,
|
|
"epoch": 2.5848359997859705,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00043386093938222126,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.14180535823106766,
|
|
"num_tokens": 52265381.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 6.532451057434082,
|
|
"epoch": 2.585371073893734,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004338338616245425,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.1486621916294098,
|
|
"num_tokens": 52276407.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 6.572145795822143,
|
|
"epoch": 2.585906148001498,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00043380677928055834,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.13917866423726083,
|
|
"num_tokens": 52286484.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 6.559039449691772,
|
|
"epoch": 2.5864412221092623,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00043377969235105075,
|
|
"loss": 6.1222,
|
|
"mean_token_accuracy": 0.14802854508161545,
|
|
"num_tokens": 52297674.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 6.604058408737183,
|
|
"epoch": 2.586976296217026,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004337526008368018,
|
|
"loss": 6.315,
|
|
"mean_token_accuracy": 0.1287540890276432,
|
|
"num_tokens": 52309100.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 6.5949077129364015,
|
|
"epoch": 2.58751137032479,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004337255047385938,
|
|
"loss": 6.2613,
|
|
"mean_token_accuracy": 0.13583641424775122,
|
|
"num_tokens": 52320002.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 6.6120912551879885,
|
|
"epoch": 2.588046444432554,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00043369840405720923,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.1449574500322342,
|
|
"num_tokens": 52330073.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 6.572416973114014,
|
|
"epoch": 2.588581518540318,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043367129879343054,
|
|
"loss": 6.1698,
|
|
"mean_token_accuracy": 0.14355989173054695,
|
|
"num_tokens": 52340472.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 6.4900984287261965,
|
|
"epoch": 2.589116592648082,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00043364418894804033,
|
|
"loss": 6.2165,
|
|
"mean_token_accuracy": 0.13661001175642012,
|
|
"num_tokens": 52350654.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 6.536292505264282,
|
|
"epoch": 2.5896516667558456,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00043361707452182146,
|
|
"loss": 6.1212,
|
|
"mean_token_accuracy": 0.139813232421875,
|
|
"num_tokens": 52361412.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 6.596290826797485,
|
|
"epoch": 2.5901867408636097,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00043358995551555693,
|
|
"loss": 6.1381,
|
|
"mean_token_accuracy": 0.146058152616024,
|
|
"num_tokens": 52372030.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 6.566216468811035,
|
|
"epoch": 2.5907218149713733,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00043356283193002966,
|
|
"loss": 6.1998,
|
|
"mean_token_accuracy": 0.14162807613611222,
|
|
"num_tokens": 52382965.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 6.5201421737670895,
|
|
"epoch": 2.5912568890791374,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004335357037660229,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.15539595633745193,
|
|
"num_tokens": 52393959.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 6.5839173793792725,
|
|
"epoch": 2.5917919631869015,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00043350857102432,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.14018062502145767,
|
|
"num_tokens": 52405142.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 6.551693105697632,
|
|
"epoch": 2.592327037294665,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004334814337057043,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.13564291447401047,
|
|
"num_tokens": 52415927.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 6.574957275390625,
|
|
"epoch": 2.5928621114024293,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00043345429181095957,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.1411016196012497,
|
|
"num_tokens": 52426475.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 6.559908199310303,
|
|
"epoch": 2.5933971855101934,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00043342714534086945,
|
|
"loss": 6.1533,
|
|
"mean_token_accuracy": 0.14289586916565894,
|
|
"num_tokens": 52437239.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 6.5464733123779295,
|
|
"epoch": 2.593932259617957,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004333999942962177,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.13552225530147552,
|
|
"num_tokens": 52447323.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 6.6362371921539305,
|
|
"epoch": 2.594467333725721,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00043337283867778836,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.14295388087630273,
|
|
"num_tokens": 52458465.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 6.56463508605957,
|
|
"epoch": 2.595002407833485,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00043334567848636563,
|
|
"loss": 6.2027,
|
|
"mean_token_accuracy": 0.13894245773553848,
|
|
"num_tokens": 52468809.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 6.5825786113739015,
|
|
"epoch": 2.595537481941249,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00043331851372273365,
|
|
"loss": 6.2163,
|
|
"mean_token_accuracy": 0.13440893739461898,
|
|
"num_tokens": 52479456.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 6.545080709457397,
|
|
"epoch": 2.5960725560490125,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00043329134438767683,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.14299445152282714,
|
|
"num_tokens": 52490146.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 6.566885614395142,
|
|
"epoch": 2.5966076301567766,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004332641704819797,
|
|
"loss": 6.2284,
|
|
"mean_token_accuracy": 0.13397061675786973,
|
|
"num_tokens": 52499875.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 6.513084411621094,
|
|
"epoch": 2.5971427042645407,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00043323699200642686,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.14407797902822495,
|
|
"num_tokens": 52510297.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 6.436622571945191,
|
|
"epoch": 2.5976777783723044,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004332098089618031,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.15865793004631995,
|
|
"num_tokens": 52523111.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 6.509023523330688,
|
|
"epoch": 2.5982128524800685,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00043318262134889334,
|
|
"loss": 6.1707,
|
|
"mean_token_accuracy": 0.1511079676449299,
|
|
"num_tokens": 52534097.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 6.5538372039794925,
|
|
"epoch": 2.5987479265878326,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004331554291684827,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.14593381732702254,
|
|
"num_tokens": 52544985.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 6.615003299713135,
|
|
"epoch": 2.5992830006955963,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004331282324213561,
|
|
"loss": 6.2027,
|
|
"mean_token_accuracy": 0.14589604288339614,
|
|
"num_tokens": 52555772.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 6.517669153213501,
|
|
"epoch": 2.5998180748033604,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004331010311082992,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.1334726519882679,
|
|
"num_tokens": 52566578.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 6.549510335922241,
|
|
"epoch": 2.6003531489111245,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043307382523009717,
|
|
"loss": 6.2591,
|
|
"mean_token_accuracy": 0.13483854234218598,
|
|
"num_tokens": 52578551.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 6.577581310272217,
|
|
"epoch": 2.600888223018888,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004330466147875356,
|
|
"loss": 6.1682,
|
|
"mean_token_accuracy": 0.1450027756392956,
|
|
"num_tokens": 52589225.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 6.58490252494812,
|
|
"epoch": 2.6014232971266518,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043301939978140024,
|
|
"loss": 6.1115,
|
|
"mean_token_accuracy": 0.1467117577791214,
|
|
"num_tokens": 52599572.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 6.639813804626465,
|
|
"epoch": 2.601958371234416,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00043299218021247693,
|
|
"loss": 6.2025,
|
|
"mean_token_accuracy": 0.14008743166923524,
|
|
"num_tokens": 52610562.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 6.592208814620972,
|
|
"epoch": 2.60249344534218,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004329649560815517,
|
|
"loss": 6.2626,
|
|
"mean_token_accuracy": 0.13796344697475432,
|
|
"num_tokens": 52621078.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 6.522030210494995,
|
|
"epoch": 2.6030285194499436,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004329377273894104,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.14876777678728104,
|
|
"num_tokens": 52632336.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 6.505379962921142,
|
|
"epoch": 2.6035635935577077,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004329104941368396,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.15157392472028733,
|
|
"num_tokens": 52643701.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 6.5069550514221195,
|
|
"epoch": 2.604098667665472,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004328832563246254,
|
|
"loss": 6.0984,
|
|
"mean_token_accuracy": 0.15870848000049592,
|
|
"num_tokens": 52654052.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 6.461515617370606,
|
|
"epoch": 2.6046337417732355,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00043285601395355426,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.1519724413752556,
|
|
"num_tokens": 52665033.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 6.548370027542115,
|
|
"epoch": 2.6051688158809996,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00043282876702441296,
|
|
"loss": 6.2085,
|
|
"mean_token_accuracy": 0.14245531782507898,
|
|
"num_tokens": 52674726.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 6.566390037536621,
|
|
"epoch": 2.6057038899887637,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00043280151553798824,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.14566671699285508,
|
|
"num_tokens": 52687221.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 6.606517601013183,
|
|
"epoch": 2.6062389640965273,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004327742594950669,
|
|
"loss": 6.2141,
|
|
"mean_token_accuracy": 0.14511393308639525,
|
|
"num_tokens": 52697902.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 6.567224216461182,
|
|
"epoch": 2.6067740382042914,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000432746998896436,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.14172334223985672,
|
|
"num_tokens": 52707845.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 6.463049030303955,
|
|
"epoch": 2.607309112312055,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004327197337428827,
|
|
"loss": 6.1062,
|
|
"mean_token_accuracy": 0.1432230919599533,
|
|
"num_tokens": 52719254.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 6.538470029830933,
|
|
"epoch": 2.607844186419819,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004326924640351942,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.13925740644335746,
|
|
"num_tokens": 52729765.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 6.588010835647583,
|
|
"epoch": 2.608379260527583,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00043266518977415797,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.13960155919194223,
|
|
"num_tokens": 52740997.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 6.632661151885986,
|
|
"epoch": 2.608914334635347,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004326379109605615,
|
|
"loss": 6.3379,
|
|
"mean_token_accuracy": 0.13341037333011627,
|
|
"num_tokens": 52753107.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 6.520866727828979,
|
|
"epoch": 2.609449408743111,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004326106275951926,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.13766885325312614,
|
|
"num_tokens": 52765453.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 6.564418983459473,
|
|
"epoch": 2.6099844828508747,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004325833396788389,
|
|
"loss": 6.1888,
|
|
"mean_token_accuracy": 0.14648929834365845,
|
|
"num_tokens": 52776145.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 6.5781529426574705,
|
|
"epoch": 2.610519556958639,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004325560472122884,
|
|
"loss": 6.2156,
|
|
"mean_token_accuracy": 0.13451072424650193,
|
|
"num_tokens": 52788404.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 6.593848466873169,
|
|
"epoch": 2.611054631066403,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004325287501963293,
|
|
"loss": 6.2092,
|
|
"mean_token_accuracy": 0.14748505726456643,
|
|
"num_tokens": 52800481.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 6.585141229629516,
|
|
"epoch": 2.6115897051741666,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004325014486317495,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.14090005159378052,
|
|
"num_tokens": 52811539.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 6.647451305389405,
|
|
"epoch": 2.6121247792819307,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004324741425193376,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.14929482936859131,
|
|
"num_tokens": 52822330.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 6.596120357513428,
|
|
"epoch": 2.6126598533896943,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000432446831859882,
|
|
"loss": 6.1632,
|
|
"mean_token_accuracy": 0.13988590538501738,
|
|
"num_tokens": 52832447.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 6.488139915466308,
|
|
"epoch": 2.6131949274974584,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004324195166541712,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.1443193018436432,
|
|
"num_tokens": 52843089.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 6.625485944747925,
|
|
"epoch": 2.613730001605222,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000432392196902994,
|
|
"loss": 6.2089,
|
|
"mean_token_accuracy": 0.14264900162816047,
|
|
"num_tokens": 52854235.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 6.600734758377075,
|
|
"epoch": 2.614265075712986,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004323648726071392,
|
|
"loss": 6.2348,
|
|
"mean_token_accuracy": 0.1405814193189144,
|
|
"num_tokens": 52864693.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 6.554009819030762,
|
|
"epoch": 2.6148001498207503,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00043233754376739583,
|
|
"loss": 6.2545,
|
|
"mean_token_accuracy": 0.1336046800017357,
|
|
"num_tokens": 52876410.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 6.599989652633667,
|
|
"epoch": 2.615335223928514,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00043231021038455297,
|
|
"loss": 6.2103,
|
|
"mean_token_accuracy": 0.1422418661415577,
|
|
"num_tokens": 52887416.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 6.588643789291382,
|
|
"epoch": 2.615870298036278,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043228287245939995,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.13978185504674911,
|
|
"num_tokens": 52899191.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 6.581878423690796,
|
|
"epoch": 2.616405372144042,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000432255529992726,
|
|
"loss": 6.2217,
|
|
"mean_token_accuracy": 0.1377883732318878,
|
|
"num_tokens": 52910479.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 6.620970916748047,
|
|
"epoch": 2.6169404462518058,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00043222818298532074,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.14118027463555335,
|
|
"num_tokens": 52921121.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 6.536572790145874,
|
|
"epoch": 2.61747552035957,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00043220083143797385,
|
|
"loss": 6.1936,
|
|
"mean_token_accuracy": 0.13265490755438805,
|
|
"num_tokens": 52931604.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 6.481448650360107,
|
|
"epoch": 2.618010594467334,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000432173475351475,
|
|
"loss": 6.1507,
|
|
"mean_token_accuracy": 0.14148655235767366,
|
|
"num_tokens": 52942200.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 6.56163272857666,
|
|
"epoch": 2.6185456685750976,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004321461147266141,
|
|
"loss": 6.1984,
|
|
"mean_token_accuracy": 0.13918397352099418,
|
|
"num_tokens": 52954350.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 6.61436972618103,
|
|
"epoch": 2.6190807426828617,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00043211874956418134,
|
|
"loss": 6.1787,
|
|
"mean_token_accuracy": 0.153399658203125,
|
|
"num_tokens": 52965683.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 6.5595556735992435,
|
|
"epoch": 2.6196158167906254,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004320913798649667,
|
|
"loss": 6.1822,
|
|
"mean_token_accuracy": 0.1431018218398094,
|
|
"num_tokens": 52975463.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 6.511537885665893,
|
|
"epoch": 2.6201508908983895,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004320640056297605,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.141774470359087,
|
|
"num_tokens": 52986115.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 6.578539133071899,
|
|
"epoch": 2.620685965006153,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004320366268593532,
|
|
"loss": 6.1616,
|
|
"mean_token_accuracy": 0.14293137937784195,
|
|
"num_tokens": 52995770.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 6.540454244613647,
|
|
"epoch": 2.6212210391139172,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00043200924355453544,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.13992016538977622,
|
|
"num_tokens": 53006490.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 6.518912076950073,
|
|
"epoch": 2.6217561132216813,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004319818557160978,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.1505638062953949,
|
|
"num_tokens": 53016129.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 6.538277530670166,
|
|
"epoch": 2.622291187329445,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00043195446334483116,
|
|
"loss": 6.1718,
|
|
"mean_token_accuracy": 0.1418795593082905,
|
|
"num_tokens": 53026568.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 6.534890365600586,
|
|
"epoch": 2.622826261437209,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00043192706644152646,
|
|
"loss": 6.1192,
|
|
"mean_token_accuracy": 0.14417702555656434,
|
|
"num_tokens": 53036488.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 6.61812105178833,
|
|
"epoch": 2.623361335544973,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004318996650069747,
|
|
"loss": 6.1944,
|
|
"mean_token_accuracy": 0.14132592156529428,
|
|
"num_tokens": 53047195.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 6.62873477935791,
|
|
"epoch": 2.623896409652737,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004318722590419672,
|
|
"loss": 6.2727,
|
|
"mean_token_accuracy": 0.13309245184063911,
|
|
"num_tokens": 53058602.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 6.632037401199341,
|
|
"epoch": 2.624431483760501,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004318448485472953,
|
|
"loss": 6.2426,
|
|
"mean_token_accuracy": 0.13687872365117074,
|
|
"num_tokens": 53070822.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 6.5243031024932865,
|
|
"epoch": 2.6249665578682646,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00043181743352375035,
|
|
"loss": 6.2049,
|
|
"mean_token_accuracy": 0.1401023432612419,
|
|
"num_tokens": 53082166.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 6.5663680076599125,
|
|
"epoch": 2.6255016319760287,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000431790013972124,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.13709209635853767,
|
|
"num_tokens": 53093688.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 6.603389883041382,
|
|
"epoch": 2.6260367060837924,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004317625898932082,
|
|
"loss": 6.1834,
|
|
"mean_token_accuracy": 0.1456095591187477,
|
|
"num_tokens": 53104793.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 6.591601848602295,
|
|
"epoch": 2.6265717801915565,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004317351612877946,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.1433986909687519,
|
|
"num_tokens": 53115835.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 6.523034477233887,
|
|
"epoch": 2.6271068542993206,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004317077281566751,
|
|
"loss": 6.0578,
|
|
"mean_token_accuracy": 0.14957990497350693,
|
|
"num_tokens": 53127153.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 6.487595558166504,
|
|
"epoch": 2.627641928407084,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043168029050064214,
|
|
"loss": 6.0783,
|
|
"mean_token_accuracy": 0.15035273879766464,
|
|
"num_tokens": 53137323.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 6.565543508529663,
|
|
"epoch": 2.6281770025148483,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00043165284832048773,
|
|
"loss": 6.2396,
|
|
"mean_token_accuracy": 0.1397866800427437,
|
|
"num_tokens": 53146858.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 6.545457220077514,
|
|
"epoch": 2.6287120766226124,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00043162540161700434,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.13699059709906578,
|
|
"num_tokens": 53157225.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 6.603227281570435,
|
|
"epoch": 2.629247150730376,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00043159795039098453,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.1414657674729824,
|
|
"num_tokens": 53167571.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 6.559129858016968,
|
|
"epoch": 2.62978222483814,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004315704946432209,
|
|
"loss": 6.1491,
|
|
"mean_token_accuracy": 0.14764243364334106,
|
|
"num_tokens": 53178562.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 6.6152125835418705,
|
|
"epoch": 2.6303172989459043,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00043154303437450617,
|
|
"loss": 6.2588,
|
|
"mean_token_accuracy": 0.13629103899002076,
|
|
"num_tokens": 53188833.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 6.5509391784667965,
|
|
"epoch": 2.630852373053668,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00043151556958563337,
|
|
"loss": 6.1997,
|
|
"mean_token_accuracy": 0.1414390578866005,
|
|
"num_tokens": 53199596.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 6.590257787704468,
|
|
"epoch": 2.6313874471614316,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004314881002773955,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.1425345718860626,
|
|
"num_tokens": 53209942.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 6.657707834243775,
|
|
"epoch": 2.6319225212691957,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004314606264505857,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.13668931126594544,
|
|
"num_tokens": 53221546.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 6.593166160583496,
|
|
"epoch": 2.63245759537696,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004314331481059973,
|
|
"loss": 6.2211,
|
|
"mean_token_accuracy": 0.13390860930085183,
|
|
"num_tokens": 53232343.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 6.5368577003479,
|
|
"epoch": 2.6329926694847234,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004314056652444237,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.14880850166082382,
|
|
"num_tokens": 53242820.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 6.644289016723633,
|
|
"epoch": 2.6335277435924875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00043137817786665863,
|
|
"loss": 6.1972,
|
|
"mean_token_accuracy": 0.14336780980229377,
|
|
"num_tokens": 53253503.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 6.639523220062256,
|
|
"epoch": 2.6340628177002516,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00043135068597349545,
|
|
"loss": 6.2055,
|
|
"mean_token_accuracy": 0.14338171929121019,
|
|
"num_tokens": 53264160.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 6.575501251220703,
|
|
"epoch": 2.6345978918080153,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004313231895657283,
|
|
"loss": 6.1797,
|
|
"mean_token_accuracy": 0.13615822270512581,
|
|
"num_tokens": 53275002.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 6.513131856918335,
|
|
"epoch": 2.6351329659157794,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00043129568864415103,
|
|
"loss": 6.0687,
|
|
"mean_token_accuracy": 0.14952839612960817,
|
|
"num_tokens": 53284216.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 6.5871141910552975,
|
|
"epoch": 2.6356680400235435,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043126818320955766,
|
|
"loss": 6.1163,
|
|
"mean_token_accuracy": 0.15600992888212203,
|
|
"num_tokens": 53294277.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 6.504469394683838,
|
|
"epoch": 2.636203114131307,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004312406732627425,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.14111925140023232,
|
|
"num_tokens": 53304448.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 6.513329553604126,
|
|
"epoch": 2.6367381882390712,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00043121315880449983,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.13983937427401544,
|
|
"num_tokens": 53315765.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 6.50860104560852,
|
|
"epoch": 2.637273262346835,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00043118563983562415,
|
|
"loss": 6.0397,
|
|
"mean_token_accuracy": 0.154642191529274,
|
|
"num_tokens": 53326529.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 6.5030264377594,
|
|
"epoch": 2.637808336454599,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00043115811635691006,
|
|
"loss": 6.0385,
|
|
"mean_token_accuracy": 0.15429445058107377,
|
|
"num_tokens": 53336132.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 6.464020442962647,
|
|
"epoch": 2.6383434105623627,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004311305883691524,
|
|
"loss": 6.1863,
|
|
"mean_token_accuracy": 0.14697637856006623,
|
|
"num_tokens": 53347284.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 6.540275239944458,
|
|
"epoch": 2.6388784846701268,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004311030558731458,
|
|
"loss": 6.2035,
|
|
"mean_token_accuracy": 0.14316580146551133,
|
|
"num_tokens": 53357872.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 6.6080793857574465,
|
|
"epoch": 2.639413558777891,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00043107551886968545,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.14208291247487068,
|
|
"num_tokens": 53370311.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 6.552876615524292,
|
|
"epoch": 2.6399486328856545,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00043104797735956643,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.1579568311572075,
|
|
"num_tokens": 53380320.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 6.553140258789062,
|
|
"epoch": 2.6404837069934186,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000431020431343584,
|
|
"loss": 6.2837,
|
|
"mean_token_accuracy": 0.13707210421562194,
|
|
"num_tokens": 53391311.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 6.540488338470459,
|
|
"epoch": 2.6410187811011827,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004309928808225335,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.13946278616786004,
|
|
"num_tokens": 53402367.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 6.562510013580322,
|
|
"epoch": 2.6415538552089464,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004309653257972105,
|
|
"loss": 6.1656,
|
|
"mean_token_accuracy": 0.13966550305485725,
|
|
"num_tokens": 53414253.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 6.579259014129638,
|
|
"epoch": 2.6420889293167105,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00043093776626841075,
|
|
"loss": 6.1853,
|
|
"mean_token_accuracy": 0.14716733396053314,
|
|
"num_tokens": 53425727.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 6.568738317489624,
|
|
"epoch": 2.6426240034244746,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00043091020223692974,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.14259096086025239,
|
|
"num_tokens": 53435402.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 6.517737531661988,
|
|
"epoch": 2.643159077532238,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00043088263370356364,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.14859788566827775,
|
|
"num_tokens": 53447421.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 6.555581188201904,
|
|
"epoch": 2.643694151640002,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004308550606691084,
|
|
"loss": 6.0852,
|
|
"mean_token_accuracy": 0.1487600840628147,
|
|
"num_tokens": 53458346.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 6.6077087879180905,
|
|
"epoch": 2.644229225747766,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004308274831343601,
|
|
"loss": 6.2025,
|
|
"mean_token_accuracy": 0.1418262891471386,
|
|
"num_tokens": 53469638.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 6.610241270065307,
|
|
"epoch": 2.64476429985553,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00043079990110011525,
|
|
"loss": 6.2093,
|
|
"mean_token_accuracy": 0.13674848303198814,
|
|
"num_tokens": 53480645.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 6.567220258712768,
|
|
"epoch": 2.6452993739632937,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00043077231456717006,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.14318317770957947,
|
|
"num_tokens": 53491958.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 6.561835718154907,
|
|
"epoch": 2.645834448071058,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00043074472353632124,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.14568044245243073,
|
|
"num_tokens": 53502183.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 6.543507766723633,
|
|
"epoch": 2.646369522178822,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004307171280083653,
|
|
"loss": 6.1174,
|
|
"mean_token_accuracy": 0.1398914024233818,
|
|
"num_tokens": 53513373.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 6.508629989624024,
|
|
"epoch": 2.6469045962865856,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004306895279840992,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.14795607104897499,
|
|
"num_tokens": 53523668.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 6.567703294754028,
|
|
"epoch": 2.6474396703943497,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004306619234643199,
|
|
"loss": 6.1964,
|
|
"mean_token_accuracy": 0.14260121062397957,
|
|
"num_tokens": 53535642.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 6.389489364624024,
|
|
"epoch": 2.647974744502114,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043063431444982447,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.15889847725629808,
|
|
"num_tokens": 53546192.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 6.525236320495606,
|
|
"epoch": 2.6485098186098774,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00043060670094141005,
|
|
"loss": 6.1601,
|
|
"mean_token_accuracy": 0.1420307420194149,
|
|
"num_tokens": 53557375.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 6.598752832412719,
|
|
"epoch": 2.6490448927176415,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00043057908293987404,
|
|
"loss": 6.219,
|
|
"mean_token_accuracy": 0.13861377835273742,
|
|
"num_tokens": 53568434.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 6.586975479125977,
|
|
"epoch": 2.649579966825405,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004305514604460138,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.1466659538447857,
|
|
"num_tokens": 53579095.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 6.540426731109619,
|
|
"epoch": 2.6501150409331693,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000430523833460627,
|
|
"loss": 6.1644,
|
|
"mean_token_accuracy": 0.1426902085542679,
|
|
"num_tokens": 53590082.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 6.546037578582764,
|
|
"epoch": 2.650650115040933,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00043049620198451147,
|
|
"loss": 6.2343,
|
|
"mean_token_accuracy": 0.14279514849185942,
|
|
"num_tokens": 53600421.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 6.47894868850708,
|
|
"epoch": 2.651185189148697,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00043046856601846483,
|
|
"loss": 6.0887,
|
|
"mean_token_accuracy": 0.15048880651593208,
|
|
"num_tokens": 53610994.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 6.629634523391724,
|
|
"epoch": 2.651720263256461,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00043044092556328517,
|
|
"loss": 6.1774,
|
|
"mean_token_accuracy": 0.1425248995423317,
|
|
"num_tokens": 53622205.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 6.56712908744812,
|
|
"epoch": 2.652255337364225,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00043041328061977073,
|
|
"loss": 6.1261,
|
|
"mean_token_accuracy": 0.14087933152914048,
|
|
"num_tokens": 53632440.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 6.488208484649658,
|
|
"epoch": 2.652790411471989,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00043038563118871965,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.1459902010858059,
|
|
"num_tokens": 53642443.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 6.6436046123504635,
|
|
"epoch": 2.653325485579753,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004303579772709303,
|
|
"loss": 6.3186,
|
|
"mean_token_accuracy": 0.13115085139870644,
|
|
"num_tokens": 53653671.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 6.597554540634155,
|
|
"epoch": 2.6538605596875167,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00043033031886720107,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.14809426963329314,
|
|
"num_tokens": 53664874.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 6.589475059509278,
|
|
"epoch": 2.6543956337952808,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004303026559783309,
|
|
"loss": 6.1994,
|
|
"mean_token_accuracy": 0.13460417240858077,
|
|
"num_tokens": 53675623.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 6.60116810798645,
|
|
"epoch": 2.6549307079030444,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004302749886051182,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.1380039393901825,
|
|
"num_tokens": 53685754.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 6.520810937881469,
|
|
"epoch": 2.6554657820108085,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004302473167483621,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.1464005909860134,
|
|
"num_tokens": 53696925.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 6.5272613048553465,
|
|
"epoch": 2.656000856118572,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00043021964040886154,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.14274688810110092,
|
|
"num_tokens": 53708046.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 6.450190830230713,
|
|
"epoch": 2.6565359302263363,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004301919595874156,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.15501822978258134,
|
|
"num_tokens": 53719179.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 6.5482892990112305,
|
|
"epoch": 2.6570710043341004,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004301642742848237,
|
|
"loss": 6.2096,
|
|
"mean_token_accuracy": 0.14222733825445175,
|
|
"num_tokens": 53731523.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 6.615186071395874,
|
|
"epoch": 2.657606078441864,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004301365845018853,
|
|
"loss": 6.2989,
|
|
"mean_token_accuracy": 0.13655554354190827,
|
|
"num_tokens": 53742072.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 6.616942834854126,
|
|
"epoch": 2.658141152549628,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004301088902393996,
|
|
"loss": 6.2317,
|
|
"mean_token_accuracy": 0.13743873983621596,
|
|
"num_tokens": 53754695.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 6.51912407875061,
|
|
"epoch": 2.6586762266573922,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004300811914981666,
|
|
"loss": 6.0635,
|
|
"mean_token_accuracy": 0.15166480764746665,
|
|
"num_tokens": 53764587.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 6.598759889602661,
|
|
"epoch": 2.659211300765156,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000430053488278986,
|
|
"loss": 6.2457,
|
|
"mean_token_accuracy": 0.13377450183033943,
|
|
"num_tokens": 53775609.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 6.519057369232177,
|
|
"epoch": 2.65974637487292,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00043002578058265776,
|
|
"loss": 6.1688,
|
|
"mean_token_accuracy": 0.14544350206851958,
|
|
"num_tokens": 53786495.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 6.5516664505004885,
|
|
"epoch": 2.660281448980684,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004299980684099818,
|
|
"loss": 6.1601,
|
|
"mean_token_accuracy": 0.14316681921482086,
|
|
"num_tokens": 53797058.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 6.612541913986206,
|
|
"epoch": 2.6608165230884477,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00042997035176175834,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.1419295459985733,
|
|
"num_tokens": 53808148.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 6.548106145858765,
|
|
"epoch": 2.661351597196212,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004299426306387879,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.1511787697672844,
|
|
"num_tokens": 53818375.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 6.581113624572754,
|
|
"epoch": 2.6618866713039755,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004299149050418707,
|
|
"loss": 6.2424,
|
|
"mean_token_accuracy": 0.13656440526247024,
|
|
"num_tokens": 53831273.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 6.518377017974854,
|
|
"epoch": 2.6624217454117396,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00042988717497180733,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.1433103121817112,
|
|
"num_tokens": 53842492.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 6.566966438293457,
|
|
"epoch": 2.6629568195195032,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00042985944042939867,
|
|
"loss": 6.1801,
|
|
"mean_token_accuracy": 0.14450253695249557,
|
|
"num_tokens": 53853017.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 6.623194360733033,
|
|
"epoch": 2.6634918936272673,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00042983170141544535,
|
|
"loss": 6.2525,
|
|
"mean_token_accuracy": 0.14528491497039794,
|
|
"num_tokens": 53863606.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 6.545564270019531,
|
|
"epoch": 2.6640269677350314,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004298039579307484,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.14550747126340866,
|
|
"num_tokens": 53874689.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 6.603804874420166,
|
|
"epoch": 2.664562041842795,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000429776209976109,
|
|
"loss": 6.1526,
|
|
"mean_token_accuracy": 0.1457737222313881,
|
|
"num_tokens": 53885247.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 6.522936391830444,
|
|
"epoch": 2.665097115950559,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004297484575523282,
|
|
"loss": 6.2292,
|
|
"mean_token_accuracy": 0.14107502326369287,
|
|
"num_tokens": 53896829.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 6.523618888854981,
|
|
"epoch": 2.6656321900583233,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042972070066020745,
|
|
"loss": 6.1111,
|
|
"mean_token_accuracy": 0.14738998040556908,
|
|
"num_tokens": 53907236.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 6.638113975524902,
|
|
"epoch": 2.666167264166087,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004296929393005482,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.14359449818730355,
|
|
"num_tokens": 53918420.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 6.496638917922974,
|
|
"epoch": 2.666702338273851,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004296651734741521,
|
|
"loss": 6.0941,
|
|
"mean_token_accuracy": 0.1512155666947365,
|
|
"num_tokens": 53928949.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 6.515101432800293,
|
|
"epoch": 2.6672374123816147,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00042963740318182085,
|
|
"loss": 6.211,
|
|
"mean_token_accuracy": 0.13944983333349228,
|
|
"num_tokens": 53939332.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 6.50306544303894,
|
|
"epoch": 2.667772486489379,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004296096284243563,
|
|
"loss": 6.1506,
|
|
"mean_token_accuracy": 0.14198232889175416,
|
|
"num_tokens": 53950703.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 6.656912422180175,
|
|
"epoch": 2.6683075605971425,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004295818492025605,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.13840252086520194,
|
|
"num_tokens": 53964061.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 6.5511839389801025,
|
|
"epoch": 2.6688426347049066,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004295540655172355,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.14662017598748206,
|
|
"num_tokens": 53974980.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 6.468306159973144,
|
|
"epoch": 2.6693777088126707,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004295262773691835,
|
|
"loss": 6.0946,
|
|
"mean_token_accuracy": 0.15195737332105635,
|
|
"num_tokens": 53985437.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 6.552871608734131,
|
|
"epoch": 2.6699127829204343,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00042949848475920706,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.14167244359850883,
|
|
"num_tokens": 53996952.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 6.5842742919921875,
|
|
"epoch": 2.6704478570281984,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004294706876881085,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.14593843817710878,
|
|
"num_tokens": 54007727.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 6.4952045440673825,
|
|
"epoch": 2.6709829311359625,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00042944288615669055,
|
|
"loss": 6.0294,
|
|
"mean_token_accuracy": 0.15579609274864198,
|
|
"num_tokens": 54018275.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 6.519923830032349,
|
|
"epoch": 2.671518005243726,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00042941508016575597,
|
|
"loss": 6.2615,
|
|
"mean_token_accuracy": 0.135496773570776,
|
|
"num_tokens": 54030376.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 6.51620922088623,
|
|
"epoch": 2.6720530793514903,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004293872697161077,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.14426541477441787,
|
|
"num_tokens": 54041487.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 6.568425178527832,
|
|
"epoch": 2.6725881534592544,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00042935945480854866,
|
|
"loss": 6.1252,
|
|
"mean_token_accuracy": 0.1577095627784729,
|
|
"num_tokens": 54051273.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 6.531775331497192,
|
|
"epoch": 2.673123227567018,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004293316354438821,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.14802649915218352,
|
|
"num_tokens": 54061910.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 6.595247459411621,
|
|
"epoch": 2.6736583016747817,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004293038116229112,
|
|
"loss": 6.2252,
|
|
"mean_token_accuracy": 0.1372023954987526,
|
|
"num_tokens": 54072980.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 6.508825254440308,
|
|
"epoch": 2.674193375782546,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004292759833464394,
|
|
"loss": 6.1287,
|
|
"mean_token_accuracy": 0.1509809710085392,
|
|
"num_tokens": 54083027.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 6.450683832168579,
|
|
"epoch": 2.67472844989031,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00042924815061527033,
|
|
"loss": 6.1062,
|
|
"mean_token_accuracy": 0.1436111479997635,
|
|
"num_tokens": 54094068.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 6.55344443321228,
|
|
"epoch": 2.6752635239980735,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004292203134302076,
|
|
"loss": 6.1565,
|
|
"mean_token_accuracy": 0.1409911885857582,
|
|
"num_tokens": 54104683.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 6.59823784828186,
|
|
"epoch": 2.6757985981058376,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000429192471792055,
|
|
"loss": 6.1163,
|
|
"mean_token_accuracy": 0.1399107165634632,
|
|
"num_tokens": 54115357.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 6.577314472198486,
|
|
"epoch": 2.6763336722136017,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004291646257016163,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.14015805199742318,
|
|
"num_tokens": 54126410.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 6.484987735748291,
|
|
"epoch": 2.6768687463213654,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00042913677515969586,
|
|
"loss": 6.0988,
|
|
"mean_token_accuracy": 0.14498216807842254,
|
|
"num_tokens": 54137279.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 6.556871032714843,
|
|
"epoch": 2.6774038204291295,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004291089201670976,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.14583845883607865,
|
|
"num_tokens": 54146521.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 6.616815567016602,
|
|
"epoch": 2.6779388945368936,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00042908106072462595,
|
|
"loss": 6.2216,
|
|
"mean_token_accuracy": 0.1366604045033455,
|
|
"num_tokens": 54157277.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 6.634881925582886,
|
|
"epoch": 2.6784739686446573,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004290531968330853,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.13936708867549896,
|
|
"num_tokens": 54168078.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 6.66855640411377,
|
|
"epoch": 2.6790090427524214,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004290253284932803,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.14373714700341225,
|
|
"num_tokens": 54178567.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 6.540094470977783,
|
|
"epoch": 2.679544116860185,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004289974557060155,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.14421114772558213,
|
|
"num_tokens": 54189485.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 6.621365356445312,
|
|
"epoch": 2.680079190967949,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00042896957847209593,
|
|
"loss": 6.2403,
|
|
"mean_token_accuracy": 0.14293561205267907,
|
|
"num_tokens": 54199351.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 6.579947233200073,
|
|
"epoch": 2.6806142650757128,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004289416967923264,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.13684981167316437,
|
|
"num_tokens": 54209001.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 6.585976505279541,
|
|
"epoch": 2.681149339183477,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00042891381066751186,
|
|
"loss": 6.2181,
|
|
"mean_token_accuracy": 0.14137208387255668,
|
|
"num_tokens": 54219783.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 6.625453805923462,
|
|
"epoch": 2.681684413291241,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00042888592009845776,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.1399910904467106,
|
|
"num_tokens": 54231337.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 6.59433536529541,
|
|
"epoch": 2.6822194873990046,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004288580250859694,
|
|
"loss": 6.2038,
|
|
"mean_token_accuracy": 0.14496433213353158,
|
|
"num_tokens": 54241650.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 6.534805393218994,
|
|
"epoch": 2.6827545615067687,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004288301256308521,
|
|
"loss": 6.1985,
|
|
"mean_token_accuracy": 0.13410138934850693,
|
|
"num_tokens": 54252223.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 6.5412883281707765,
|
|
"epoch": 2.683289635614533,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00042880222173391155,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.14675514698028563,
|
|
"num_tokens": 54262469.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 6.595539236068726,
|
|
"epoch": 2.6838247097222965,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004287743133959535,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.1419118031859398,
|
|
"num_tokens": 54272885.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 6.543181467056274,
|
|
"epoch": 2.6843597838300606,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004287464006177837,
|
|
"loss": 6.1804,
|
|
"mean_token_accuracy": 0.14130209982395173,
|
|
"num_tokens": 54283327.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 6.519068050384521,
|
|
"epoch": 2.6848948579378242,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004287184834002082,
|
|
"loss": 6.134,
|
|
"mean_token_accuracy": 0.1447476901113987,
|
|
"num_tokens": 54294761.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 6.640497875213623,
|
|
"epoch": 2.6854299320455883,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00042869056174403303,
|
|
"loss": 6.1793,
|
|
"mean_token_accuracy": 0.1468206986784935,
|
|
"num_tokens": 54305205.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 6.575417375564575,
|
|
"epoch": 2.685965006153352,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004286626356500647,
|
|
"loss": 6.1982,
|
|
"mean_token_accuracy": 0.14216837286949158,
|
|
"num_tokens": 54315902.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 6.561103820800781,
|
|
"epoch": 2.686500080261116,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004286347051191091,
|
|
"loss": 6.1948,
|
|
"mean_token_accuracy": 0.14694490432739257,
|
|
"num_tokens": 54327345.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 6.61946210861206,
|
|
"epoch": 2.68703515436888,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004286067701519731,
|
|
"loss": 6.2424,
|
|
"mean_token_accuracy": 0.13714828714728355,
|
|
"num_tokens": 54337548.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 6.563602781295776,
|
|
"epoch": 2.687570228476644,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042857883074946324,
|
|
"loss": 6.2177,
|
|
"mean_token_accuracy": 0.13575371503829955,
|
|
"num_tokens": 54348384.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 6.565671157836914,
|
|
"epoch": 2.688105302584408,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004285508869123862,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.142025226354599,
|
|
"num_tokens": 54358245.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 6.485191822052002,
|
|
"epoch": 2.688640376692172,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00042852293864154885,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.1387248583137989,
|
|
"num_tokens": 54370421.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 6.598221921920777,
|
|
"epoch": 2.6891754507999357,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042849498593775827,
|
|
"loss": 6.1124,
|
|
"mean_token_accuracy": 0.14265856072306632,
|
|
"num_tokens": 54381368.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 6.5423788070678714,
|
|
"epoch": 2.6897105249077,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00042846702880182147,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.13631427958607673,
|
|
"num_tokens": 54392226.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 6.554638910293579,
|
|
"epoch": 2.690245599015464,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004284390672345458,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.1379536733031273,
|
|
"num_tokens": 54402295.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 6.611361026763916,
|
|
"epoch": 2.6907806731232276,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004284111012367387,
|
|
"loss": 6.2262,
|
|
"mean_token_accuracy": 0.14042413458228112,
|
|
"num_tokens": 54413808.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 6.594064712524414,
|
|
"epoch": 2.6913157472309917,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00042838313080920755,
|
|
"loss": 6.202,
|
|
"mean_token_accuracy": 0.1426466777920723,
|
|
"num_tokens": 54425048.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 6.638346815109253,
|
|
"epoch": 2.6918508213387553,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042835515595276,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.1353751040995121,
|
|
"num_tokens": 54435908.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 6.497889566421509,
|
|
"epoch": 2.6923858954465194,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004283271766682039,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.1477851890027523,
|
|
"num_tokens": 54447594.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 6.514171123504639,
|
|
"epoch": 2.692920969554283,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004282991929563471,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.14370713979005814,
|
|
"num_tokens": 54458918.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 6.535639142990112,
|
|
"epoch": 2.693456043662047,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004282712048179977,
|
|
"loss": 6.1191,
|
|
"mean_token_accuracy": 0.1475418895483017,
|
|
"num_tokens": 54469423.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 6.604026222229004,
|
|
"epoch": 2.6939911177698113,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004282432122539638,
|
|
"loss": 6.2369,
|
|
"mean_token_accuracy": 0.14293455928564072,
|
|
"num_tokens": 54481895.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 6.597784376144409,
|
|
"epoch": 2.694526191877575,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00042821521526505363,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.13924351334571838,
|
|
"num_tokens": 54492233.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 6.582783937454224,
|
|
"epoch": 2.695061265985339,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004281872138520757,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.15103355571627616,
|
|
"num_tokens": 54502366.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 6.456221961975098,
|
|
"epoch": 2.695596340093103,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00042815920801583845,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.14359703585505484,
|
|
"num_tokens": 54512565.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 6.566391468048096,
|
|
"epoch": 2.6961314142008668,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00042813119775715066,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.14658018723130226,
|
|
"num_tokens": 54522999.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 6.558338689804077,
|
|
"epoch": 2.696666488308631,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00042810318307682095,
|
|
"loss": 6.1554,
|
|
"mean_token_accuracy": 0.14645984023809433,
|
|
"num_tokens": 54533776.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 6.520054483413697,
|
|
"epoch": 2.6972015624163945,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00042807516397565845,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.14013207703828812,
|
|
"num_tokens": 54544972.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 6.531105661392212,
|
|
"epoch": 2.6977366365241586,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004280471404544721,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.14386613816022872,
|
|
"num_tokens": 54556034.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 6.611520004272461,
|
|
"epoch": 2.6982717106319223,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00042801911251407095,
|
|
"loss": 6.114,
|
|
"mean_token_accuracy": 0.14833165109157562,
|
|
"num_tokens": 54566662.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 6.547452163696289,
|
|
"epoch": 2.6988067847396864,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004279910801552645,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.14094368517398834,
|
|
"num_tokens": 54578889.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 6.518944883346558,
|
|
"epoch": 2.6993418588474505,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004279630433788621,
|
|
"loss": 6.262,
|
|
"mean_token_accuracy": 0.13489435464143754,
|
|
"num_tokens": 54590456.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 6.60769510269165,
|
|
"epoch": 2.699876932955214,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004279350021856734,
|
|
"loss": 6.2111,
|
|
"mean_token_accuracy": 0.1349624663591385,
|
|
"num_tokens": 54602327.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 6.661423063278198,
|
|
"epoch": 2.7004120070629782,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00042790695657650787,
|
|
"loss": 6.159,
|
|
"mean_token_accuracy": 0.14148908257484435,
|
|
"num_tokens": 54612999.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 6.503651809692383,
|
|
"epoch": 2.7009470811707423,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042787890655217553,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.14160091951489448,
|
|
"num_tokens": 54624332.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 6.491953754425049,
|
|
"epoch": 2.701482155278506,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00042785085211348624,
|
|
"loss": 6.1253,
|
|
"mean_token_accuracy": 0.14483464062213897,
|
|
"num_tokens": 54635679.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 6.584280633926392,
|
|
"epoch": 2.70201722938627,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00042782279326125005,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.14690318331122398,
|
|
"num_tokens": 54646344.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 6.657462310791016,
|
|
"epoch": 2.702552303494034,
|
|
"grad_norm": 6.96875,
|
|
"learning_rate": 0.00042779472999627724,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.13560424670577048,
|
|
"num_tokens": 54657395.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 6.528586101531983,
|
|
"epoch": 2.703087377601798,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000427766662319378,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.1414429225027561,
|
|
"num_tokens": 54668755.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 6.543591022491455,
|
|
"epoch": 2.7036224517095615,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00042773859023136285,
|
|
"loss": 6.1469,
|
|
"mean_token_accuracy": 0.14058267176151276,
|
|
"num_tokens": 54679170.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 6.5261553764343265,
|
|
"epoch": 2.7041575258173256,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004277105137330424,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.14667425453662872,
|
|
"num_tokens": 54688728.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 6.4883630752563475,
|
|
"epoch": 2.7046925999250897,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00042768243282522735,
|
|
"loss": 6.1737,
|
|
"mean_token_accuracy": 0.14207538664340974,
|
|
"num_tokens": 54700236.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 6.54293384552002,
|
|
"epoch": 2.7052276740328534,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042765434750872847,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.1447503685951233,
|
|
"num_tokens": 54710586.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 6.574968242645264,
|
|
"epoch": 2.7057627481406175,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00042762625778435676,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.1464052364230156,
|
|
"num_tokens": 54721159.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 6.525949096679687,
|
|
"epoch": 2.7062978222483816,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004275981636529233,
|
|
"loss": 6.1775,
|
|
"mean_token_accuracy": 0.1437419645488262,
|
|
"num_tokens": 54731593.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 6.525927972793579,
|
|
"epoch": 2.706832896356145,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004275700651152393,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.14845551177859306,
|
|
"num_tokens": 54742890.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 6.508445835113525,
|
|
"epoch": 2.7073679704639093,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00042754196217211616,
|
|
"loss": 6.1731,
|
|
"mean_token_accuracy": 0.14559964910149575,
|
|
"num_tokens": 54753344.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 6.58334789276123,
|
|
"epoch": 2.7079030445716734,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042751385482436523,
|
|
"loss": 6.2448,
|
|
"mean_token_accuracy": 0.13652830421924592,
|
|
"num_tokens": 54763157.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 6.6253118991851805,
|
|
"epoch": 2.708438118679437,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042748574307279824,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.1460372492671013,
|
|
"num_tokens": 54772515.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 6.524020385742188,
|
|
"epoch": 2.708973192787201,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004274576269182268,
|
|
"loss": 6.1094,
|
|
"mean_token_accuracy": 0.1483628749847412,
|
|
"num_tokens": 54783178.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 6.578008842468262,
|
|
"epoch": 2.709508266894965,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004274295063614629,
|
|
"loss": 6.2294,
|
|
"mean_token_accuracy": 0.13769440203905106,
|
|
"num_tokens": 54794709.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 6.5791514873504635,
|
|
"epoch": 2.710043341002729,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004274013814033184,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.14866385757923126,
|
|
"num_tokens": 54804821.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 6.58971095085144,
|
|
"epoch": 2.7105784151104926,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042737325204460523,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.13538878560066223,
|
|
"num_tokens": 54815291.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 6.364390087127686,
|
|
"epoch": 2.7111134892182567,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000427345118286136,
|
|
"loss": 5.9883,
|
|
"mean_token_accuracy": 0.15534957349300385,
|
|
"num_tokens": 54826891.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 6.598145437240601,
|
|
"epoch": 2.7116485633260208,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004273169801287228,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.14149535074830055,
|
|
"num_tokens": 54837545.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 6.6023521900177,
|
|
"epoch": 2.7121836374337844,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00042728883757317825,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.13578827157616616,
|
|
"num_tokens": 54848028.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 6.572189998626709,
|
|
"epoch": 2.7127187115415485,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042726069062031495,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.13816566541790962,
|
|
"num_tokens": 54858679.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 6.550875234603882,
|
|
"epoch": 2.7132537856493126,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042723253927094565,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.1480478972196579,
|
|
"num_tokens": 54870892.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 6.537986850738525,
|
|
"epoch": 2.7137888597570763,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000427204383525883,
|
|
"loss": 6.0719,
|
|
"mean_token_accuracy": 0.14651345312595368,
|
|
"num_tokens": 54881131.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 6.539002895355225,
|
|
"epoch": 2.7143239338648404,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004271762233859403,
|
|
"loss": 6.1881,
|
|
"mean_token_accuracy": 0.1411701537668705,
|
|
"num_tokens": 54891532.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 6.495243406295776,
|
|
"epoch": 2.714859007972604,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042714805885193046,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.1483546607196331,
|
|
"num_tokens": 54902945.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 6.5329734802246096,
|
|
"epoch": 2.715394082080368,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042711988992466684,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.1415770597755909,
|
|
"num_tokens": 54913943.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 6.603453016281128,
|
|
"epoch": 2.715929156188132,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042709171660496275,
|
|
"loss": 6.2289,
|
|
"mean_token_accuracy": 0.14435778111219405,
|
|
"num_tokens": 54924241.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 6.5637397289276125,
|
|
"epoch": 2.716464230295896,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004270635388936317,
|
|
"loss": 6.1532,
|
|
"mean_token_accuracy": 0.14465492814779282,
|
|
"num_tokens": 54934083.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 6.600241088867188,
|
|
"epoch": 2.71699930440366,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00042703535679148734,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.140153232216835,
|
|
"num_tokens": 54944928.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 6.496172046661377,
|
|
"epoch": 2.7175343785114237,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00042700717029934345,
|
|
"loss": 6.013,
|
|
"mean_token_accuracy": 0.15262067914009095,
|
|
"num_tokens": 54955715.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 6.511968040466309,
|
|
"epoch": 2.7180694526191878,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004269789794180139,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.14448234885931016,
|
|
"num_tokens": 54966149.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 6.529322814941406,
|
|
"epoch": 2.718604526726952,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00042695078414831263,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.14164806753396988,
|
|
"num_tokens": 54976854.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 6.538543033599853,
|
|
"epoch": 2.7191396008347155,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004269225844910538,
|
|
"loss": 6.1827,
|
|
"mean_token_accuracy": 0.14038587212562562,
|
|
"num_tokens": 54987377.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 6.576548862457275,
|
|
"epoch": 2.7196746749424796,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004268943804470518,
|
|
"loss": 6.2224,
|
|
"mean_token_accuracy": 0.13838811740279197,
|
|
"num_tokens": 54999488.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 6.690387725830078,
|
|
"epoch": 2.7202097490502437,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00042686617201712074,
|
|
"loss": 6.2695,
|
|
"mean_token_accuracy": 0.13587075769901275,
|
|
"num_tokens": 55011517.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 6.626272439956665,
|
|
"epoch": 2.7207448231580074,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004268379592020754,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.1450803779065609,
|
|
"num_tokens": 55022133.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 6.493826818466187,
|
|
"epoch": 2.7212798972657715,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00042680974200273036,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.14528268277645112,
|
|
"num_tokens": 55032684.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 6.534641933441162,
|
|
"epoch": 2.721814971373535,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004267815204199003,
|
|
"loss": 6.2311,
|
|
"mean_token_accuracy": 0.14462506845593454,
|
|
"num_tokens": 55042943.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 6.530017137527466,
|
|
"epoch": 2.722350045481299,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004267532944544002,
|
|
"loss": 6.2052,
|
|
"mean_token_accuracy": 0.14035545140504838,
|
|
"num_tokens": 55053805.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 6.505929088592529,
|
|
"epoch": 2.722885119589063,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00042672506410704495,
|
|
"loss": 6.1692,
|
|
"mean_token_accuracy": 0.14253990799188615,
|
|
"num_tokens": 55066611.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 6.5785871028900145,
|
|
"epoch": 2.723420193696827,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004266968293786499,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.13714278042316436,
|
|
"num_tokens": 55077954.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 6.562727689743042,
|
|
"epoch": 2.723955267804591,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004266685902700302,
|
|
"loss": 6.2215,
|
|
"mean_token_accuracy": 0.14759265556931495,
|
|
"num_tokens": 55090296.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 6.62928957939148,
|
|
"epoch": 2.7244903419123547,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004266403467820013,
|
|
"loss": 6.1855,
|
|
"mean_token_accuracy": 0.13954791575670242,
|
|
"num_tokens": 55100664.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 6.505074596405029,
|
|
"epoch": 2.725025416020119,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004266120989153786,
|
|
"loss": 6.0866,
|
|
"mean_token_accuracy": 0.1423269495368004,
|
|
"num_tokens": 55111094.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 6.569557476043701,
|
|
"epoch": 2.725560490127883,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00042658384667097787,
|
|
"loss": 6.2016,
|
|
"mean_token_accuracy": 0.13720061406493186,
|
|
"num_tokens": 55121877.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 6.533632373809814,
|
|
"epoch": 2.7260955642356466,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004265555900496149,
|
|
"loss": 6.1124,
|
|
"mean_token_accuracy": 0.14367010369896888,
|
|
"num_tokens": 55133087.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 6.5266571044921875,
|
|
"epoch": 2.7266306383434107,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00042652732905210555,
|
|
"loss": 6.1905,
|
|
"mean_token_accuracy": 0.13943759948015214,
|
|
"num_tokens": 55144257.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 6.508918619155883,
|
|
"epoch": 2.7271657124511743,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004264990636792659,
|
|
"loss": 6.0654,
|
|
"mean_token_accuracy": 0.15449982583522798,
|
|
"num_tokens": 55154389.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 6.450720596313476,
|
|
"epoch": 2.7277007865589384,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000426470793931912,
|
|
"loss": 6.096,
|
|
"mean_token_accuracy": 0.15466541200876235,
|
|
"num_tokens": 55165734.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 6.430225133895874,
|
|
"epoch": 2.728235860666702,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004264425198108603,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.1523221679031849,
|
|
"num_tokens": 55176448.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 6.5447577953338625,
|
|
"epoch": 2.728770934774466,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042641424131692707,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.14815260469913483,
|
|
"num_tokens": 55187515.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 6.5779022693634035,
|
|
"epoch": 2.7293060088822303,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004263859584509289,
|
|
"loss": 6.2341,
|
|
"mean_token_accuracy": 0.14347974583506584,
|
|
"num_tokens": 55199236.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 6.600110816955566,
|
|
"epoch": 2.729841082989994,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004263576712136825,
|
|
"loss": 6.1825,
|
|
"mean_token_accuracy": 0.14445364475250244,
|
|
"num_tokens": 55210151.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 6.540364980697632,
|
|
"epoch": 2.730376157097758,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00042632937960600454,
|
|
"loss": 6.1576,
|
|
"mean_token_accuracy": 0.14207155480980874,
|
|
"num_tokens": 55221322.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 6.467457723617554,
|
|
"epoch": 2.730911231205522,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00042630108362871205,
|
|
"loss": 6.084,
|
|
"mean_token_accuracy": 0.15477709770202636,
|
|
"num_tokens": 55231901.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 6.5848325252532955,
|
|
"epoch": 2.731446305313286,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00042627278328262203,
|
|
"loss": 6.1401,
|
|
"mean_token_accuracy": 0.14924724102020265,
|
|
"num_tokens": 55243154.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 6.5793235301971436,
|
|
"epoch": 2.73198137942105,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00042624447856855164,
|
|
"loss": 6.1178,
|
|
"mean_token_accuracy": 0.1458869308233261,
|
|
"num_tokens": 55253485.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 6.572154426574707,
|
|
"epoch": 2.732516453528814,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00042621616948731816,
|
|
"loss": 6.2078,
|
|
"mean_token_accuracy": 0.13728644251823424,
|
|
"num_tokens": 55264936.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 6.546516609191895,
|
|
"epoch": 2.7330515276365777,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004261878560397391,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.14645720273256302,
|
|
"num_tokens": 55276138.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 6.55620584487915,
|
|
"epoch": 2.7335866017443413,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00042615953822663195,
|
|
"loss": 6.218,
|
|
"mean_token_accuracy": 0.13871607631444932,
|
|
"num_tokens": 55287398.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 6.638921117782592,
|
|
"epoch": 2.7341216758521054,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00042613121604881426,
|
|
"loss": 6.2458,
|
|
"mean_token_accuracy": 0.1321701377630234,
|
|
"num_tokens": 55298806.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 6.580674457550049,
|
|
"epoch": 2.7346567499598695,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004261028895071041,
|
|
"loss": 6.1408,
|
|
"mean_token_accuracy": 0.14177805557847023,
|
|
"num_tokens": 55309976.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 6.571374750137329,
|
|
"epoch": 2.735191824067633,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00042607455860231916,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.14067357331514357,
|
|
"num_tokens": 55320806.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 6.540859031677246,
|
|
"epoch": 2.7357268981753973,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004260462233352775,
|
|
"loss": 6.1889,
|
|
"mean_token_accuracy": 0.14671343713998794,
|
|
"num_tokens": 55332153.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 6.615581035614014,
|
|
"epoch": 2.7362619722831614,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042601788370679746,
|
|
"loss": 6.1868,
|
|
"mean_token_accuracy": 0.1394096314907074,
|
|
"num_tokens": 55343595.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 6.571436786651612,
|
|
"epoch": 2.736797046390925,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042598953971769723,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.14062318727374076,
|
|
"num_tokens": 55353891.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 6.549102354049682,
|
|
"epoch": 2.737332120498689,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004259611913687952,
|
|
"loss": 6.1182,
|
|
"mean_token_accuracy": 0.14188437908887863,
|
|
"num_tokens": 55364743.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 6.623900318145752,
|
|
"epoch": 2.7378671946064532,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00042593283866091,
|
|
"loss": 6.2171,
|
|
"mean_token_accuracy": 0.13967869728803634,
|
|
"num_tokens": 55375122.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 6.545878601074219,
|
|
"epoch": 2.738402268714217,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042590448159486035,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.13848114088177682,
|
|
"num_tokens": 55387281.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 6.569247627258301,
|
|
"epoch": 2.738937342821981,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00042587612017146496,
|
|
"loss": 6.1935,
|
|
"mean_token_accuracy": 0.13394651263952256,
|
|
"num_tokens": 55397859.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 6.585854530334473,
|
|
"epoch": 2.7394724169297446,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00042584775439154276,
|
|
"loss": 6.1137,
|
|
"mean_token_accuracy": 0.14506488367915155,
|
|
"num_tokens": 55408169.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 6.510363531112671,
|
|
"epoch": 2.7400074910375087,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004258193842559129,
|
|
"loss": 6.0868,
|
|
"mean_token_accuracy": 0.14164062589406967,
|
|
"num_tokens": 55419342.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 6.429851150512695,
|
|
"epoch": 2.7405425651452724,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004257910097653945,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.1502538099884987,
|
|
"num_tokens": 55430271.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 6.595976257324219,
|
|
"epoch": 2.7410776392530365,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004257626309208069,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.14474261850118636,
|
|
"num_tokens": 55441901.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 6.513349151611328,
|
|
"epoch": 2.7416127133608006,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004257342477229695,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.14348843917250634,
|
|
"num_tokens": 55451743.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 6.579008913040161,
|
|
"epoch": 2.7421477874685642,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00042570586017270196,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.1456002935767174,
|
|
"num_tokens": 55462805.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 6.499527168273926,
|
|
"epoch": 2.7426828615763283,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00042567746827082377,
|
|
"loss": 6.2209,
|
|
"mean_token_accuracy": 0.14342751428484918,
|
|
"num_tokens": 55474277.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 6.598701524734497,
|
|
"epoch": 2.7432179356840924,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004256490720181549,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.13803670555353165,
|
|
"num_tokens": 55485257.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 6.468766117095948,
|
|
"epoch": 2.743753009791856,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00042562067141551523,
|
|
"loss": 6.0916,
|
|
"mean_token_accuracy": 0.14202239289879798,
|
|
"num_tokens": 55495835.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 6.578554725646972,
|
|
"epoch": 2.74428808389962,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00042559226646372486,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.13709181547164917,
|
|
"num_tokens": 55506256.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 6.572082376480102,
|
|
"epoch": 2.744823158007384,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000425563857163604,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.15287534520030022,
|
|
"num_tokens": 55516821.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 6.514011335372925,
|
|
"epoch": 2.745358232115148,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00042553544351597286,
|
|
"loss": 6.1658,
|
|
"mean_token_accuracy": 0.13815057203173636,
|
|
"num_tokens": 55527153.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 6.5836457252502445,
|
|
"epoch": 2.7458933062229116,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00042550702552165195,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.13684011697769166,
|
|
"num_tokens": 55538219.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 6.675678157806397,
|
|
"epoch": 2.7464283803306757,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042547860318146183,
|
|
"loss": 6.1883,
|
|
"mean_token_accuracy": 0.13965234383940697,
|
|
"num_tokens": 55548733.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 6.592297697067261,
|
|
"epoch": 2.74696345443844,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00042545017649622314,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.14311980009078978,
|
|
"num_tokens": 55559746.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 6.516272830963135,
|
|
"epoch": 2.7474985285462035,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004254217454667569,
|
|
"loss": 6.1621,
|
|
"mean_token_accuracy": 0.14393166974186897,
|
|
"num_tokens": 55570322.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 6.4252057552337645,
|
|
"epoch": 2.7480336026539676,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004253933100938837,
|
|
"loss": 6.0693,
|
|
"mean_token_accuracy": 0.1464044451713562,
|
|
"num_tokens": 55580715.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 6.611335563659668,
|
|
"epoch": 2.7485686767617317,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004253648703784249,
|
|
"loss": 6.1261,
|
|
"mean_token_accuracy": 0.1467358648777008,
|
|
"num_tokens": 55591685.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 6.592088985443115,
|
|
"epoch": 2.7491037508694953,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004253364263212016,
|
|
"loss": 6.1272,
|
|
"mean_token_accuracy": 0.14339596778154373,
|
|
"num_tokens": 55602288.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 6.536873531341553,
|
|
"epoch": 2.7496388249772594,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004253079779230352,
|
|
"loss": 6.2361,
|
|
"mean_token_accuracy": 0.1388120710849762,
|
|
"num_tokens": 55613011.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 6.5020044326782225,
|
|
"epoch": 2.7501738990850235,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004252795251847469,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.14594679623842238,
|
|
"num_tokens": 55623630.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 6.54440336227417,
|
|
"epoch": 2.750708973192787,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00042525106810715845,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.15465491116046906,
|
|
"num_tokens": 55634764.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 6.596581888198853,
|
|
"epoch": 2.7512440473005513,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00042522260669109157,
|
|
"loss": 6.1568,
|
|
"mean_token_accuracy": 0.14717646911740304,
|
|
"num_tokens": 55645085.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 6.570849132537842,
|
|
"epoch": 2.751779121408315,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000425194140937368,
|
|
"loss": 6.2548,
|
|
"mean_token_accuracy": 0.13317542299628257,
|
|
"num_tokens": 55656249.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 6.6196671485900875,
|
|
"epoch": 2.752314195516079,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00042516567084680977,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.14690053537487985,
|
|
"num_tokens": 55668138.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 6.601205158233642,
|
|
"epoch": 2.7528492696238427,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004251371964202389,
|
|
"loss": 6.1856,
|
|
"mean_token_accuracy": 0.14204964265227318,
|
|
"num_tokens": 55678747.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 6.563790416717529,
|
|
"epoch": 2.753384343731607,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004251087176584775,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.14080666601657868,
|
|
"num_tokens": 55690266.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 6.560403776168823,
|
|
"epoch": 2.753919417839371,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042508023456234805,
|
|
"loss": 6.1444,
|
|
"mean_token_accuracy": 0.1446196712553501,
|
|
"num_tokens": 55700229.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 6.5393352031707765,
|
|
"epoch": 2.7544544919471345,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042505174713267286,
|
|
"loss": 6.1953,
|
|
"mean_token_accuracy": 0.13945085778832436,
|
|
"num_tokens": 55711564.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 6.607245206832886,
|
|
"epoch": 2.7549895660548986,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004250232553702746,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.14838516786694528,
|
|
"num_tokens": 55722618.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 6.527014970779419,
|
|
"epoch": 2.7555246401626627,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004249947592759759,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.15185271054506302,
|
|
"num_tokens": 55732828.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 6.494454050064087,
|
|
"epoch": 2.7560597142704264,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004249662588505996,
|
|
"loss": 6.0826,
|
|
"mean_token_accuracy": 0.14239320605993272,
|
|
"num_tokens": 55742283.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 6.532657623291016,
|
|
"epoch": 2.7565947883781905,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042493775409496867,
|
|
"loss": 6.1653,
|
|
"mean_token_accuracy": 0.1416530653834343,
|
|
"num_tokens": 55752883.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 6.604326057434082,
|
|
"epoch": 2.757129862485954,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004249092450099062,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.14293775111436843,
|
|
"num_tokens": 55762730.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 6.431799840927124,
|
|
"epoch": 2.7576649365937183,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004248807315962353,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.14589868634939193,
|
|
"num_tokens": 55774068.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 6.547713994979858,
|
|
"epoch": 2.758200010701482,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004248522138547793,
|
|
"loss": 6.1837,
|
|
"mean_token_accuracy": 0.13609157353639603,
|
|
"num_tokens": 55784896.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 6.530615568161011,
|
|
"epoch": 2.758735084809246,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004248236917863617,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.1454329915344715,
|
|
"num_tokens": 55796186.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 6.487886524200439,
|
|
"epoch": 2.75927015891701,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042479516539180605,
|
|
"loss": 6.0687,
|
|
"mean_token_accuracy": 0.15311401933431626,
|
|
"num_tokens": 55806439.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 6.53472204208374,
|
|
"epoch": 2.7598052330247738,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000424766634671936,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.1366858370602131,
|
|
"num_tokens": 55817955.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 6.54031195640564,
|
|
"epoch": 2.760340307132538,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00042473809962757553,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.1447063833475113,
|
|
"num_tokens": 55828876.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 6.529758024215698,
|
|
"epoch": 2.760875381240302,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004247095602595485,
|
|
"loss": 6.1114,
|
|
"mean_token_accuracy": 0.14915342554450034,
|
|
"num_tokens": 55839721.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 6.487936544418335,
|
|
"epoch": 2.7614104553480656,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004246810165686788,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.144862849265337,
|
|
"num_tokens": 55850427.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 6.582725763320923,
|
|
"epoch": 2.7619455294558297,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042465246855579093,
|
|
"loss": 6.1917,
|
|
"mean_token_accuracy": 0.139267298579216,
|
|
"num_tokens": 55860245.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 6.587867546081543,
|
|
"epoch": 2.762480603563594,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00042462391622170897,
|
|
"loss": 6.1888,
|
|
"mean_token_accuracy": 0.14452599063515664,
|
|
"num_tokens": 55869957.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 6.556235885620117,
|
|
"epoch": 2.7630156776713575,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004245953595672575,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.13578791469335555,
|
|
"num_tokens": 55881159.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 6.699882888793946,
|
|
"epoch": 2.7635507517791216,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000424566798593261,
|
|
"loss": 6.1871,
|
|
"mean_token_accuracy": 0.13794263154268266,
|
|
"num_tokens": 55891830.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 6.577232837677002,
|
|
"epoch": 2.7640858258868852,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042453823330054427,
|
|
"loss": 6.1892,
|
|
"mean_token_accuracy": 0.13983393162488938,
|
|
"num_tokens": 55901904.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 6.495845222473145,
|
|
"epoch": 2.7646208999946493,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000424509663689932,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.1381370261311531,
|
|
"num_tokens": 55913808.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 6.481015968322754,
|
|
"epoch": 2.765155974102413,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004244810897622492,
|
|
"loss": 6.1394,
|
|
"mean_token_accuracy": 0.1437651574611664,
|
|
"num_tokens": 55924997.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 6.6441210269927975,
|
|
"epoch": 2.765691048210177,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000424452511518321,
|
|
"loss": 6.241,
|
|
"mean_token_accuracy": 0.13912588953971863,
|
|
"num_tokens": 55935623.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 6.593527889251709,
|
|
"epoch": 2.766226122317941,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004244239289589724,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.14090535491704942,
|
|
"num_tokens": 55946733.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 6.5654137134552,
|
|
"epoch": 2.766761196425705,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000424395342085029,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.1396829329431057,
|
|
"num_tokens": 55956158.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 6.595712041854858,
|
|
"epoch": 2.767296270533469,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00042436675089731603,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.1498132437467575,
|
|
"num_tokens": 55966442.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 6.537619018554688,
|
|
"epoch": 2.767831344641233,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004243381553966591,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.14348981976509095,
|
|
"num_tokens": 55977314.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 6.520560026168823,
|
|
"epoch": 2.7683664187489967,
|
|
"grad_norm": 5.34375,
|
|
"learning_rate": 0.00042430955558388396,
|
|
"loss": 6.1014,
|
|
"mean_token_accuracy": 0.14455328211188317,
|
|
"num_tokens": 55987457.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 6.600881433486938,
|
|
"epoch": 2.768901492856761,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00042428095145981634,
|
|
"loss": 6.1177,
|
|
"mean_token_accuracy": 0.1490711972117424,
|
|
"num_tokens": 55998319.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 6.508493947982788,
|
|
"epoch": 2.7694365669645244,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00042425234302528224,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.1453601077198982,
|
|
"num_tokens": 56008654.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 6.537225341796875,
|
|
"epoch": 2.7699716410722885,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004242237302811077,
|
|
"loss": 6.2443,
|
|
"mean_token_accuracy": 0.13631143867969514,
|
|
"num_tokens": 56019793.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 6.612562036514282,
|
|
"epoch": 2.770506715180052,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000424195113228119,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.14320329800248147,
|
|
"num_tokens": 56031051.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 6.598811912536621,
|
|
"epoch": 2.7710417892878163,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004241664918671423,
|
|
"loss": 6.2383,
|
|
"mean_token_accuracy": 0.14300152733922006,
|
|
"num_tokens": 56041210.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 6.520844125747681,
|
|
"epoch": 2.7715768633955804,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000424137866199004,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.14668864086270333,
|
|
"num_tokens": 56051601.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 6.557717418670654,
|
|
"epoch": 2.772111937503344,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004241092362245309,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.15041750967502593,
|
|
"num_tokens": 56062669.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 6.50094051361084,
|
|
"epoch": 2.772647011611108,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00042408060194454956,
|
|
"loss": 6.2225,
|
|
"mean_token_accuracy": 0.14309757947921753,
|
|
"num_tokens": 56074414.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 6.543452358245849,
|
|
"epoch": 2.7731820857188723,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00042405196335988676,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.1424746572971344,
|
|
"num_tokens": 56085428.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 6.584384489059448,
|
|
"epoch": 2.773717159826636,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00042402332047136943,
|
|
"loss": 6.1572,
|
|
"mean_token_accuracy": 0.1392229437828064,
|
|
"num_tokens": 56097403.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 6.495270872116089,
|
|
"epoch": 2.7742522339344,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004239946732798247,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.15233143419027328,
|
|
"num_tokens": 56107781.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 6.445868492126465,
|
|
"epoch": 2.774787308042164,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00042396602178607973,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.15436270385980605,
|
|
"num_tokens": 56118698.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 6.527877855300903,
|
|
"epoch": 2.7753223821499278,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004239373659909618,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.1449520006775856,
|
|
"num_tokens": 56128397.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 6.551731157302856,
|
|
"epoch": 2.7758574562576914,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004239087058952984,
|
|
"loss": 6.1428,
|
|
"mean_token_accuracy": 0.14682915285229683,
|
|
"num_tokens": 56138798.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 6.570207262039185,
|
|
"epoch": 2.7763925303654555,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000423880041499917,
|
|
"loss": 6.0989,
|
|
"mean_token_accuracy": 0.15500355064868926,
|
|
"num_tokens": 56149936.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 6.558843278884888,
|
|
"epoch": 2.7769276044732196,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004238513728056453,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.1426151543855667,
|
|
"num_tokens": 56161433.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 6.54704065322876,
|
|
"epoch": 2.7774626785809833,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00042382269981331116,
|
|
"loss": 6.1702,
|
|
"mean_token_accuracy": 0.1362956166267395,
|
|
"num_tokens": 56172312.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 6.537230157852173,
|
|
"epoch": 2.7779977526887474,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00042379402252374244,
|
|
"loss": 6.1016,
|
|
"mean_token_accuracy": 0.14957149922847748,
|
|
"num_tokens": 56183887.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 6.512060356140137,
|
|
"epoch": 2.7785328267965115,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042376534093776727,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.14736717641353608,
|
|
"num_tokens": 56194172.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 6.5566637992858885,
|
|
"epoch": 2.779067900904275,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004237366550562137,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.13823279067873956,
|
|
"num_tokens": 56204569.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 6.533468914031983,
|
|
"epoch": 2.7796029750120392,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042370796487991013,
|
|
"loss": 6.119,
|
|
"mean_token_accuracy": 0.1467661090195179,
|
|
"num_tokens": 56215875.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 6.602261304855347,
|
|
"epoch": 2.7801380491198033,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00042367927040968514,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.13065228313207627,
|
|
"num_tokens": 56227633.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 6.408648872375489,
|
|
"epoch": 2.780673123227567,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004236505716463669,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.15133264362812043,
|
|
"num_tokens": 56239420.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 6.520856428146362,
|
|
"epoch": 2.781208197335331,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004236218685907844,
|
|
"loss": 6.1346,
|
|
"mean_token_accuracy": 0.1402910128235817,
|
|
"num_tokens": 56250538.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 6.5642866611480715,
|
|
"epoch": 2.7817432714430947,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004235931612437663,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.141983575373888,
|
|
"num_tokens": 56261423.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 6.586930656433106,
|
|
"epoch": 2.782278345550859,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004235644496061416,
|
|
"loss": 6.1943,
|
|
"mean_token_accuracy": 0.14280136525630951,
|
|
"num_tokens": 56272581.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 6.5971152782440186,
|
|
"epoch": 2.7828134196586225,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004235357336787392,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.14308769702911378,
|
|
"num_tokens": 56283703.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 6.634580802917481,
|
|
"epoch": 2.7833484937663866,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042350701346238853,
|
|
"loss": 6.2343,
|
|
"mean_token_accuracy": 0.13882396295666694,
|
|
"num_tokens": 56294657.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 6.546750497817993,
|
|
"epoch": 2.7838835678741507,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004234782889579185,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.14877328425645828,
|
|
"num_tokens": 56305555.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 6.558487415313721,
|
|
"epoch": 2.7844186419819144,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00042344956016615885,
|
|
"loss": 6.217,
|
|
"mean_token_accuracy": 0.14211586937308313,
|
|
"num_tokens": 56316716.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 6.5006208419799805,
|
|
"epoch": 2.7849537160896785,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004234208270879389,
|
|
"loss": 6.0727,
|
|
"mean_token_accuracy": 0.14045752286911012,
|
|
"num_tokens": 56326582.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 6.539473390579223,
|
|
"epoch": 2.7854887901974426,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00042339208972408865,
|
|
"loss": 6.1708,
|
|
"mean_token_accuracy": 0.14863744974136353,
|
|
"num_tokens": 56336687.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 6.501152563095093,
|
|
"epoch": 2.786023864305206,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004233633480754375,
|
|
"loss": 6.0033,
|
|
"mean_token_accuracy": 0.15732960700988768,
|
|
"num_tokens": 56347493.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 6.546044111251831,
|
|
"epoch": 2.7865589384129703,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00042333460214281557,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.14478814005851745,
|
|
"num_tokens": 56359259.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 6.505811071395874,
|
|
"epoch": 2.787094012520734,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042330585192705284,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.14285291582345963,
|
|
"num_tokens": 56370502.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 6.502809190750122,
|
|
"epoch": 2.787629086628498,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00042327709742897944,
|
|
"loss": 6.1435,
|
|
"mean_token_accuracy": 0.1467990204691887,
|
|
"num_tokens": 56381047.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 6.541677665710449,
|
|
"epoch": 2.7881641607362617,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00042324833864942576,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.14868857711553574,
|
|
"num_tokens": 56392304.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 6.52217812538147,
|
|
"epoch": 2.788699234844026,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004232195755892221,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.1518963634967804,
|
|
"num_tokens": 56402480.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 6.503185653686524,
|
|
"epoch": 2.78923430895179,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00042319080824919895,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.1413701742887497,
|
|
"num_tokens": 56413659.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 6.57382230758667,
|
|
"epoch": 2.7897693830595536,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004231620366301871,
|
|
"loss": 6.2318,
|
|
"mean_token_accuracy": 0.13842638432979584,
|
|
"num_tokens": 56425272.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 6.635707187652588,
|
|
"epoch": 2.7903044571673177,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00042313326073301733,
|
|
"loss": 6.1668,
|
|
"mean_token_accuracy": 0.14410255402326583,
|
|
"num_tokens": 56436696.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 6.582508087158203,
|
|
"epoch": 2.7908395312750818,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004231044805585204,
|
|
"loss": 6.1812,
|
|
"mean_token_accuracy": 0.14307481199502944,
|
|
"num_tokens": 56446666.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 6.500238609313965,
|
|
"epoch": 2.7913746053828454,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004230756961075274,
|
|
"loss": 6.1552,
|
|
"mean_token_accuracy": 0.14491480812430382,
|
|
"num_tokens": 56457082.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 6.456539297103882,
|
|
"epoch": 2.7919096794906095,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00042304690738086944,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.14439799264073372,
|
|
"num_tokens": 56468492.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 6.5672468662261965,
|
|
"epoch": 2.7924447535983736,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004230181143793779,
|
|
"loss": 6.1668,
|
|
"mean_token_accuracy": 0.14492122009396552,
|
|
"num_tokens": 56479353.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 6.554325723648072,
|
|
"epoch": 2.7929798277061373,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00042298931710388414,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.14425694271922113,
|
|
"num_tokens": 56490105.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 6.5762628555297855,
|
|
"epoch": 2.7935149018139014,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004229605155552195,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.14124056175351143,
|
|
"num_tokens": 56501528.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 6.588911151885986,
|
|
"epoch": 2.794049975921665,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00042293170973421593,
|
|
"loss": 6.2539,
|
|
"mean_token_accuracy": 0.13497179076075555,
|
|
"num_tokens": 56512952.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 6.623517942428589,
|
|
"epoch": 2.794585050029429,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042290289964170495,
|
|
"loss": 6.1572,
|
|
"mean_token_accuracy": 0.14636044204235077,
|
|
"num_tokens": 56523332.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 6.559038591384888,
|
|
"epoch": 2.795120124137193,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004228740852785185,
|
|
"loss": 6.159,
|
|
"mean_token_accuracy": 0.14455383494496346,
|
|
"num_tokens": 56534777.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 6.511839294433594,
|
|
"epoch": 2.795655198244957,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00042284526664548866,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.13896902799606323,
|
|
"num_tokens": 56545706.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 6.538518476486206,
|
|
"epoch": 2.796190272352721,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00042281644374344754,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.13761672303080558,
|
|
"num_tokens": 56557014.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 6.613624095916748,
|
|
"epoch": 2.7967253464604847,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00042278761657322736,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.14503440409898757,
|
|
"num_tokens": 56569707.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 6.608669233322144,
|
|
"epoch": 2.7972604205682488,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004227587851356605,
|
|
"loss": 6.1092,
|
|
"mean_token_accuracy": 0.14836087673902512,
|
|
"num_tokens": 56579924.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 6.58938775062561,
|
|
"epoch": 2.797795494676013,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004227299494315795,
|
|
"loss": 6.2016,
|
|
"mean_token_accuracy": 0.14550254717469216,
|
|
"num_tokens": 56590301.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 6.593760442733765,
|
|
"epoch": 2.7983305687837765,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042270110946181693,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.14254245236516,
|
|
"num_tokens": 56600717.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 6.595337009429931,
|
|
"epoch": 2.7988656428915406,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042267226522720556,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.14293911904096604,
|
|
"num_tokens": 56611547.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 6.521939134597778,
|
|
"epoch": 2.7994007169993043,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004226434167285784,
|
|
"loss": 6.0733,
|
|
"mean_token_accuracy": 0.14869356900453568,
|
|
"num_tokens": 56622542.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 6.496916341781616,
|
|
"epoch": 2.7999357911070684,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004226145639667683,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.14482851922512055,
|
|
"num_tokens": 56633359.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 6.473493051528931,
|
|
"epoch": 2.800470865214832,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004225857069426083,
|
|
"loss": 6.0304,
|
|
"mean_token_accuracy": 0.15227488577365875,
|
|
"num_tokens": 56644101.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 6.557975912094117,
|
|
"epoch": 2.801005939322596,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00042255684565693183,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.14281883835792542,
|
|
"num_tokens": 56654630.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 6.558210277557373,
|
|
"epoch": 2.80154101343036,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004225279801105722,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.14586687386035918,
|
|
"num_tokens": 56665826.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 6.533395195007325,
|
|
"epoch": 2.802076087538124,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004224991103043628,
|
|
"loss": 6.1519,
|
|
"mean_token_accuracy": 0.14563033431768418,
|
|
"num_tokens": 56676431.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 6.591195201873779,
|
|
"epoch": 2.802611161645888,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00042247023623913745,
|
|
"loss": 6.1399,
|
|
"mean_token_accuracy": 0.14860984683036804,
|
|
"num_tokens": 56687297.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 6.52235689163208,
|
|
"epoch": 2.803146235753652,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004224413579157296,
|
|
"loss": 6.1779,
|
|
"mean_token_accuracy": 0.1498168781399727,
|
|
"num_tokens": 56698392.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 6.548229742050171,
|
|
"epoch": 2.8036813098614157,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004224124753349733,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.1470751740038395,
|
|
"num_tokens": 56710588.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 6.459409570693969,
|
|
"epoch": 2.80421638396918,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004223835884977025,
|
|
"loss": 6.0226,
|
|
"mean_token_accuracy": 0.15141253620386125,
|
|
"num_tokens": 56723143.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 6.54159026145935,
|
|
"epoch": 2.804751458076944,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004223546974047513,
|
|
"loss": 6.1263,
|
|
"mean_token_accuracy": 0.14785472303628922,
|
|
"num_tokens": 56734097.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 6.556371402740479,
|
|
"epoch": 2.8052865321847076,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004223258020569539,
|
|
"loss": 6.1997,
|
|
"mean_token_accuracy": 0.13852703124284743,
|
|
"num_tokens": 56745311.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 6.619455480575562,
|
|
"epoch": 2.8058216062924712,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004222969024551447,
|
|
"loss": 6.2331,
|
|
"mean_token_accuracy": 0.145738585293293,
|
|
"num_tokens": 56755495.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 6.611628484725952,
|
|
"epoch": 2.8063566804002353,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00042226799860015817,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.1510625809431076,
|
|
"num_tokens": 56766107.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 6.511661100387573,
|
|
"epoch": 2.8068917545079994,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004222390904928288,
|
|
"loss": 6.1094,
|
|
"mean_token_accuracy": 0.15050103664398193,
|
|
"num_tokens": 56776877.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 6.575976371765137,
|
|
"epoch": 2.807426828615763,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00042221017813399146,
|
|
"loss": 6.1883,
|
|
"mean_token_accuracy": 0.14673145413398742,
|
|
"num_tokens": 56786439.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 6.548148155212402,
|
|
"epoch": 2.807961902723527,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004221812615244809,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.13965382501482965,
|
|
"num_tokens": 56797433.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 6.619834232330322,
|
|
"epoch": 2.8084969768312913,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00042215234066513203,
|
|
"loss": 6.2147,
|
|
"mean_token_accuracy": 0.13901015669107436,
|
|
"num_tokens": 56808270.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 6.559413719177246,
|
|
"epoch": 2.809032050939055,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00042212341555678,
|
|
"loss": 6.1564,
|
|
"mean_token_accuracy": 0.13976674526929855,
|
|
"num_tokens": 56818590.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 6.5373390197753904,
|
|
"epoch": 2.809567125046819,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004220944862002601,
|
|
"loss": 6.1881,
|
|
"mean_token_accuracy": 0.13808188810944558,
|
|
"num_tokens": 56828799.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 6.576023864746094,
|
|
"epoch": 2.810102199154583,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00042206555259640744,
|
|
"loss": 6.1788,
|
|
"mean_token_accuracy": 0.1402301825582981,
|
|
"num_tokens": 56839409.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 6.469111490249634,
|
|
"epoch": 2.810637273262347,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00042203661474605775,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.1567970797419548,
|
|
"num_tokens": 56849650.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 6.527505159378052,
|
|
"epoch": 2.811172347370111,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004220076726500464,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.13666568398475648,
|
|
"num_tokens": 56860437.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 6.576977729797363,
|
|
"epoch": 2.8117074214778746,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042197872630920927,
|
|
"loss": 6.1481,
|
|
"mean_token_accuracy": 0.14877523332834244,
|
|
"num_tokens": 56870314.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 6.591359663009643,
|
|
"epoch": 2.8122424955856387,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00042194977572438194,
|
|
"loss": 6.1734,
|
|
"mean_token_accuracy": 0.1433998242020607,
|
|
"num_tokens": 56881675.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 6.574231433868408,
|
|
"epoch": 2.8127775696934023,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042192082089640055,
|
|
"loss": 6.232,
|
|
"mean_token_accuracy": 0.13772969990968703,
|
|
"num_tokens": 56893148.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 6.581654167175293,
|
|
"epoch": 2.8133126438011664,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004218918618261011,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.15254155546426773,
|
|
"num_tokens": 56904008.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 6.536041021347046,
|
|
"epoch": 2.8138477179089305,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042186289851431976,
|
|
"loss": 6.1264,
|
|
"mean_token_accuracy": 0.1461220435798168,
|
|
"num_tokens": 56914731.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 6.614019870758057,
|
|
"epoch": 2.814382792016694,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042183393096189285,
|
|
"loss": 6.244,
|
|
"mean_token_accuracy": 0.13986846357583999,
|
|
"num_tokens": 56926037.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 6.435464811325073,
|
|
"epoch": 2.8149178661244583,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042180495916965686,
|
|
"loss": 6.0479,
|
|
"mean_token_accuracy": 0.15360037684440614,
|
|
"num_tokens": 56936456.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 6.532927227020264,
|
|
"epoch": 2.8154529402322224,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004217759831384483,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.14854140877723693,
|
|
"num_tokens": 56947929.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 6.527433395385742,
|
|
"epoch": 2.815988014339986,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042174700286910376,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.1458355501294136,
|
|
"num_tokens": 56958153.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 6.5887534618377686,
|
|
"epoch": 2.81652308844775,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004217180183624602,
|
|
"loss": 6.1743,
|
|
"mean_token_accuracy": 0.14444401115179062,
|
|
"num_tokens": 56968609.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 6.545349740982056,
|
|
"epoch": 2.817058162555514,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004216890296193545,
|
|
"loss": 6.1668,
|
|
"mean_token_accuracy": 0.14618612974882125,
|
|
"num_tokens": 56978434.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 6.501297903060913,
|
|
"epoch": 2.817593236663278,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004216600366406236,
|
|
"loss": 6.1385,
|
|
"mean_token_accuracy": 0.14914523512125016,
|
|
"num_tokens": 56988826.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 6.5244386196136475,
|
|
"epoch": 2.8181283107710415,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00042163103942710487,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.1431665003299713,
|
|
"num_tokens": 57000385.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 6.476370573043823,
|
|
"epoch": 2.8186633848788056,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004216020379796354,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.15840113833546637,
|
|
"num_tokens": 57012137.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 6.537134599685669,
|
|
"epoch": 2.8191984589865697,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00042157303229905277,
|
|
"loss": 6.1964,
|
|
"mean_token_accuracy": 0.1425363078713417,
|
|
"num_tokens": 57022533.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 6.569771718978882,
|
|
"epoch": 2.8197335330943334,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042154402238619434,
|
|
"loss": 6.1971,
|
|
"mean_token_accuracy": 0.13677304461598397,
|
|
"num_tokens": 57034438.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 6.601274108886718,
|
|
"epoch": 2.8202686072020975,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00042151500824189785,
|
|
"loss": 6.2103,
|
|
"mean_token_accuracy": 0.1403756856918335,
|
|
"num_tokens": 57046343.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 6.57053542137146,
|
|
"epoch": 2.8208036813098616,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00042148598986700117,
|
|
"loss": 6.1787,
|
|
"mean_token_accuracy": 0.13869398683309556,
|
|
"num_tokens": 57058269.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 6.5484086036682125,
|
|
"epoch": 2.8213387554176252,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00042145696726234207,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.1469111442565918,
|
|
"num_tokens": 57069192.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 6.583009338378906,
|
|
"epoch": 2.8218738295253893,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004214279404287586,
|
|
"loss": 6.1586,
|
|
"mean_token_accuracy": 0.14601791575551032,
|
|
"num_tokens": 57080021.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 6.506668901443481,
|
|
"epoch": 2.8224089036331534,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004213989093670889,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.14438596591353417,
|
|
"num_tokens": 57090336.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 6.48719425201416,
|
|
"epoch": 2.822943977740917,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004213698740781713,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.14825507402420043,
|
|
"num_tokens": 57101942.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 6.5222900390625,
|
|
"epoch": 2.823479051848681,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004213408345628442,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.14740404039621352,
|
|
"num_tokens": 57112353.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 6.486120796203613,
|
|
"epoch": 2.824014125956445,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.000421311790821946,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.15795335173606873,
|
|
"num_tokens": 57123796.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 6.566050720214844,
|
|
"epoch": 2.824549200064209,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00042128274285631545,
|
|
"loss": 6.1418,
|
|
"mean_token_accuracy": 0.14231483936309813,
|
|
"num_tokens": 57134463.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 6.5165716171264645,
|
|
"epoch": 2.8250842741719726,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00042125369066679124,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.14769949913024902,
|
|
"num_tokens": 57146964.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 6.560316896438598,
|
|
"epoch": 2.8256193482797367,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042122463425421224,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.13410290628671645,
|
|
"num_tokens": 57157322.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 6.489172315597534,
|
|
"epoch": 2.826154422387501,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004211955736194175,
|
|
"loss": 6.0696,
|
|
"mean_token_accuracy": 0.1488802284002304,
|
|
"num_tokens": 57168758.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 6.505826187133789,
|
|
"epoch": 2.8266894964952645,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042116650876324616,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.1497102454304695,
|
|
"num_tokens": 57180322.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 6.534818696975708,
|
|
"epoch": 2.8272245706030286,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004211374396865373,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.1411368243396282,
|
|
"num_tokens": 57190836.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 6.472420120239258,
|
|
"epoch": 2.8277596447107927,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004211083663901305,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.14494197070598602,
|
|
"num_tokens": 57202439.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 6.601978826522827,
|
|
"epoch": 2.8282947188185563,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004210792888748651,
|
|
"loss": 6.2698,
|
|
"mean_token_accuracy": 0.1340482547879219,
|
|
"num_tokens": 57213335.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 6.566740989685059,
|
|
"epoch": 2.8288297929263204,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00042105020714158076,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.13992462754249574,
|
|
"num_tokens": 57223840.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 6.566862964630127,
|
|
"epoch": 2.829364867034084,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042102112119111725,
|
|
"loss": 6.1738,
|
|
"mean_token_accuracy": 0.13998859152197837,
|
|
"num_tokens": 57234702.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 6.450004243850708,
|
|
"epoch": 2.829899941141848,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004209920310243144,
|
|
"loss": 6.1049,
|
|
"mean_token_accuracy": 0.14990269541740417,
|
|
"num_tokens": 57247415.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 6.4817276954650875,
|
|
"epoch": 2.830435015249612,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004209629366420121,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.14815844595432281,
|
|
"num_tokens": 57257768.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 6.579893970489502,
|
|
"epoch": 2.830970089357376,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004209338380450506,
|
|
"loss": 6.2934,
|
|
"mean_token_accuracy": 0.14120492115616798,
|
|
"num_tokens": 57268114.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 6.602554750442505,
|
|
"epoch": 2.83150516346514,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042090473523426994,
|
|
"loss": 6.1972,
|
|
"mean_token_accuracy": 0.13939568176865577,
|
|
"num_tokens": 57278680.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 6.640215873718262,
|
|
"epoch": 2.8320402375729037,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00042087562821051055,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.13254932463169097,
|
|
"num_tokens": 57289823.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 6.552631855010986,
|
|
"epoch": 2.832575311680668,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042084651697461297,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.14295072332024575,
|
|
"num_tokens": 57300137.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 6.538321113586425,
|
|
"epoch": 2.833110385788432,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042081740152741763,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.15230545550584793,
|
|
"num_tokens": 57311160.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 6.530941677093506,
|
|
"epoch": 2.8336454598961955,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004207882818697654,
|
|
"loss": 6.1381,
|
|
"mean_token_accuracy": 0.14437396824359894,
|
|
"num_tokens": 57322708.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 6.523876523971557,
|
|
"epoch": 2.8341805340039596,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000420759158002497,
|
|
"loss": 6.1156,
|
|
"mean_token_accuracy": 0.14913655519485475,
|
|
"num_tokens": 57333788.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 6.575799512863159,
|
|
"epoch": 2.8347156081117237,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00042073002992645337,
|
|
"loss": 6.1335,
|
|
"mean_token_accuracy": 0.14622239023447037,
|
|
"num_tokens": 57344806.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 6.569938135147095,
|
|
"epoch": 2.8352506822194874,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004207008976424756,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.14218514636158944,
|
|
"num_tokens": 57355086.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 6.512008619308472,
|
|
"epoch": 2.835785756327251,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004206717611514049,
|
|
"loss": 6.0407,
|
|
"mean_token_accuracy": 0.15334405303001403,
|
|
"num_tokens": 57364837.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 6.500442218780518,
|
|
"epoch": 2.836320830435015,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004206426204540825,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.14359380006790162,
|
|
"num_tokens": 57376049.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 6.548292255401611,
|
|
"epoch": 2.8368559045427792,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00042061347555135,
|
|
"loss": 6.1742,
|
|
"mean_token_accuracy": 0.1378846175968647,
|
|
"num_tokens": 57387829.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 6.563036489486694,
|
|
"epoch": 2.837390978650543,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004205843264440488,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.15226632207632065,
|
|
"num_tokens": 57397165.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 6.506733417510986,
|
|
"epoch": 2.837926052758307,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00042055517313302064,
|
|
"loss": 6.1173,
|
|
"mean_token_accuracy": 0.1448871985077858,
|
|
"num_tokens": 57408602.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 6.496715021133423,
|
|
"epoch": 2.838461126866071,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004205260156191073,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.15323320403695107,
|
|
"num_tokens": 57419393.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 6.505649900436401,
|
|
"epoch": 2.8389962009738348,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042049685390315074,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.14108188599348068,
|
|
"num_tokens": 57431238.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 6.5632038593292235,
|
|
"epoch": 2.839531275081599,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00042046768798599293,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.15107546299695968,
|
|
"num_tokens": 57442080.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 6.529848241806031,
|
|
"epoch": 2.840066349189363,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004204385178684761,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.1425222709774971,
|
|
"num_tokens": 57452539.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 6.560629224777221,
|
|
"epoch": 2.8406014232971266,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00042040934355144245,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.1397110715508461,
|
|
"num_tokens": 57464936.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 6.546103286743164,
|
|
"epoch": 2.8411364974048907,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004203801650357346,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.14157830327749252,
|
|
"num_tokens": 57477460.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 6.578550052642822,
|
|
"epoch": 2.8416715715126544,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004203509823221947,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.14745037406682968,
|
|
"num_tokens": 57487707.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 6.488901281356812,
|
|
"epoch": 2.8422066456204185,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004203217954116657,
|
|
"loss": 6.1865,
|
|
"mean_token_accuracy": 0.14364331364631652,
|
|
"num_tokens": 57498107.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 6.492470788955688,
|
|
"epoch": 2.842741719728182,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00042029260430499033,
|
|
"loss": 6.0799,
|
|
"mean_token_accuracy": 0.14064841270446776,
|
|
"num_tokens": 57509035.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 6.555630111694336,
|
|
"epoch": 2.8432767938359462,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00042026340900301135,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.1402133248746395,
|
|
"num_tokens": 57521234.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 6.530895185470581,
|
|
"epoch": 2.8438118679437103,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004202342095065719,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.15059569329023362,
|
|
"num_tokens": 57532294.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 6.539517879486084,
|
|
"epoch": 2.844346942051474,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000420205005816515,
|
|
"loss": 6.129,
|
|
"mean_token_accuracy": 0.1504014626145363,
|
|
"num_tokens": 57542047.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 6.44587926864624,
|
|
"epoch": 2.844882016159238,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000420175797933684,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.14565242528915406,
|
|
"num_tokens": 57553254.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 6.522662734985351,
|
|
"epoch": 2.845417090267002,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00042014658585892223,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.15372227728366852,
|
|
"num_tokens": 57564321.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 6.476567268371582,
|
|
"epoch": 2.845952164374766,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042011736959307323,
|
|
"loss": 6.0411,
|
|
"mean_token_accuracy": 0.14456560015678405,
|
|
"num_tokens": 57575018.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 6.471282625198365,
|
|
"epoch": 2.84648723848253,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00042008814913698054,
|
|
"loss": 6.1266,
|
|
"mean_token_accuracy": 0.13975058495998383,
|
|
"num_tokens": 57585698.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 6.493369817733765,
|
|
"epoch": 2.8470223125902936,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004200589244914879,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.15106166303157806,
|
|
"num_tokens": 57595363.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 6.481197786331177,
|
|
"epoch": 2.8475573866980577,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00042002969565743925,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.15511105880141257,
|
|
"num_tokens": 57605908.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 6.462172126770019,
|
|
"epoch": 2.8480924608058213,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004200004626356785,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.15295604318380357,
|
|
"num_tokens": 57616172.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 6.533484601974488,
|
|
"epoch": 2.8486275349135854,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041997122542704974,
|
|
"loss": 6.092,
|
|
"mean_token_accuracy": 0.14885272681713105,
|
|
"num_tokens": 57626770.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 6.5200952053070065,
|
|
"epoch": 2.8491626090213495,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004199419840323972,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.15648696571588516,
|
|
"num_tokens": 57636576.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 6.425666189193725,
|
|
"epoch": 2.849697683129113,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00041991273845256536,
|
|
"loss": 6.1042,
|
|
"mean_token_accuracy": 0.15075935423374176,
|
|
"num_tokens": 57646431.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 6.447622346878052,
|
|
"epoch": 2.8502327572368773,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00041988348868839836,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.14786752462387084,
|
|
"num_tokens": 57657412.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 6.542451333999634,
|
|
"epoch": 2.8507678313446414,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004198542347407412,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.14865738078951835,
|
|
"num_tokens": 57667434.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 6.5194519519805905,
|
|
"epoch": 2.851302905452405,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004198249766104382,
|
|
"loss": 6.146,
|
|
"mean_token_accuracy": 0.14927664250135422,
|
|
"num_tokens": 57677640.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 6.529724168777466,
|
|
"epoch": 2.851837979560169,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004197957142983344,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.1475653976202011,
|
|
"num_tokens": 57687909.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 6.589068794250489,
|
|
"epoch": 2.8523730536679333,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004197664478052747,
|
|
"loss": 6.2644,
|
|
"mean_token_accuracy": 0.13916537463665007,
|
|
"num_tokens": 57700374.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 6.59693021774292,
|
|
"epoch": 2.852908127775697,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004197371771321042,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.14790308773517608,
|
|
"num_tokens": 57711577.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 6.473593091964721,
|
|
"epoch": 2.853443201883461,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00041970790227966804,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.15344537049531937,
|
|
"num_tokens": 57721259.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 6.493796920776367,
|
|
"epoch": 2.8539782759912247,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00041967862324881154,
|
|
"loss": 6.1203,
|
|
"mean_token_accuracy": 0.14557915478944777,
|
|
"num_tokens": 57731499.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 6.57301812171936,
|
|
"epoch": 2.8545133500989888,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004196493400403801,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.14061342179775238,
|
|
"num_tokens": 57742343.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 6.5550885677337645,
|
|
"epoch": 2.8550484242067524,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004196200526552193,
|
|
"loss": 6.1482,
|
|
"mean_token_accuracy": 0.14899497330188752,
|
|
"num_tokens": 57752942.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 6.581289291381836,
|
|
"epoch": 2.8555834983145165,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004195907610941748,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.1460196152329445,
|
|
"num_tokens": 57763623.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 6.497776889801026,
|
|
"epoch": 2.8561185724222806,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004195614653580924,
|
|
"loss": 6.1359,
|
|
"mean_token_accuracy": 0.14459621161222458,
|
|
"num_tokens": 57774538.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 6.494773197174072,
|
|
"epoch": 2.8566536465300443,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041953216544781796,
|
|
"loss": 6.129,
|
|
"mean_token_accuracy": 0.1413637265563011,
|
|
"num_tokens": 57785420.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 6.515912961959839,
|
|
"epoch": 2.8571887206378084,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041950286136419756,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.13585734292864798,
|
|
"num_tokens": 57796488.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 6.628446960449219,
|
|
"epoch": 2.8577237947455725,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041947355310807737,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.14220907911658287,
|
|
"num_tokens": 57806391.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 6.497838068008423,
|
|
"epoch": 2.858258868853336,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041944424068030364,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.1429177589714527,
|
|
"num_tokens": 57817410.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 6.542545652389526,
|
|
"epoch": 2.8587939429611002,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041941492408172277,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.14392782598733903,
|
|
"num_tokens": 57828582.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 6.502765369415283,
|
|
"epoch": 2.859329017068864,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041938560331318124,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.15508327037096023,
|
|
"num_tokens": 57838962.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 6.522745418548584,
|
|
"epoch": 2.859864091176628,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004193562783755257,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.1510725811123848,
|
|
"num_tokens": 57849335.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 6.508123731613159,
|
|
"epoch": 2.8603991652843916,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004193269492696029,
|
|
"loss": 6.1319,
|
|
"mean_token_accuracy": 0.14305149689316748,
|
|
"num_tokens": 57860904.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 6.546517276763916,
|
|
"epoch": 2.8609342393921557,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004192976159962597,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.1412898227572441,
|
|
"num_tokens": 57870861.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 6.478988361358643,
|
|
"epoch": 2.86146931349992,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004192682785563432,
|
|
"loss": 6.1553,
|
|
"mean_token_accuracy": 0.13741284385323524,
|
|
"num_tokens": 57881590.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 6.548636436462402,
|
|
"epoch": 2.8620043876076835,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004192389369507004,
|
|
"loss": 6.1227,
|
|
"mean_token_accuracy": 0.14779388010501862,
|
|
"num_tokens": 57892736.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 6.63283953666687,
|
|
"epoch": 2.8625394617154476,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004192095911801785,
|
|
"loss": 6.1896,
|
|
"mean_token_accuracy": 0.14023101925849915,
|
|
"num_tokens": 57904340.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 6.5642454624176025,
|
|
"epoch": 2.8630745358232117,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000419180241245625,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.14407695233821868,
|
|
"num_tokens": 57916369.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 6.525102996826172,
|
|
"epoch": 2.8636096099309754,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004191508871478873,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.13954001069068908,
|
|
"num_tokens": 57926867.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 6.515405178070068,
|
|
"epoch": 2.8641446840387395,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00041912152888781283,
|
|
"loss": 6.0801,
|
|
"mean_token_accuracy": 0.14303958117961885,
|
|
"num_tokens": 57938408.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 6.584450626373291,
|
|
"epoch": 2.8646797581465036,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041909216646624967,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.1538046568632126,
|
|
"num_tokens": 57948821.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 6.5102966785430905,
|
|
"epoch": 2.865214832254267,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004190627998840453,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.14521811604499818,
|
|
"num_tokens": 57959589.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 6.529639673233032,
|
|
"epoch": 2.8657499063620313,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004190334291420479,
|
|
"loss": 6.1196,
|
|
"mean_token_accuracy": 0.14496074467897416,
|
|
"num_tokens": 57970508.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 6.601312065124512,
|
|
"epoch": 2.866284980469795,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004190040542411055,
|
|
"loss": 6.1158,
|
|
"mean_token_accuracy": 0.1517277792096138,
|
|
"num_tokens": 57980411.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 6.523510885238648,
|
|
"epoch": 2.866820054577559,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00041897467518206614,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.14705872014164925,
|
|
"num_tokens": 57991457.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 6.575181341171264,
|
|
"epoch": 2.8673551286853227,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004189452919657784,
|
|
"loss": 6.1892,
|
|
"mean_token_accuracy": 0.13625505194067955,
|
|
"num_tokens": 58001860.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 6.596246814727783,
|
|
"epoch": 2.867890202793087,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041891590459309055,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.14077902361750602,
|
|
"num_tokens": 58011958.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 6.540633678436279,
|
|
"epoch": 2.868425276900851,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041888651306485117,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.14434419870376586,
|
|
"num_tokens": 58022216.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 6.51785044670105,
|
|
"epoch": 2.8689603510086146,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00041885711738190895,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.1430641457438469,
|
|
"num_tokens": 58032502.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 6.459881067276001,
|
|
"epoch": 2.8694954251163787,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004188277175451126,
|
|
"loss": 6.1572,
|
|
"mean_token_accuracy": 0.14581400901079178,
|
|
"num_tokens": 58043944.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 6.578799915313721,
|
|
"epoch": 2.8700304992241428,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00041879831355531123,
|
|
"loss": 6.2037,
|
|
"mean_token_accuracy": 0.14260607957839966,
|
|
"num_tokens": 58055857.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 6.530503559112549,
|
|
"epoch": 2.8705655733319064,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004187689054133537,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.14971188753843306,
|
|
"num_tokens": 58067070.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 6.495825862884521,
|
|
"epoch": 2.8711006474396705,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004187394931200893,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.1540823757648468,
|
|
"num_tokens": 58077922.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 6.534556293487549,
|
|
"epoch": 2.871635721547434,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004187100766763671,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.14613471031188965,
|
|
"num_tokens": 58089698.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 6.553792810440063,
|
|
"epoch": 2.8721707956551983,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00041868065608303674,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.14809264615178108,
|
|
"num_tokens": 58100640.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 6.53035979270935,
|
|
"epoch": 2.872705869762962,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004186512313409476,
|
|
"loss": 6.1799,
|
|
"mean_token_accuracy": 0.1425020471215248,
|
|
"num_tokens": 58112810.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 6.614489030838013,
|
|
"epoch": 2.873240943870726,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004186218024509493,
|
|
"loss": 6.217,
|
|
"mean_token_accuracy": 0.1399749845266342,
|
|
"num_tokens": 58123818.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 6.5899701595306395,
|
|
"epoch": 2.87377601797849,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00041859236941389175,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.14540104269981385,
|
|
"num_tokens": 58134785.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 6.581728410720825,
|
|
"epoch": 2.874311092086254,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004185629322306246,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.1461853340268135,
|
|
"num_tokens": 58144987.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 6.51855435371399,
|
|
"epoch": 2.874846166194018,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00041853349090199805,
|
|
"loss": 6.098,
|
|
"mean_token_accuracy": 0.14934733659029006,
|
|
"num_tokens": 58155031.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 6.468179845809937,
|
|
"epoch": 2.875381240301782,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000418504045428862,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.1500189259648323,
|
|
"num_tokens": 58165216.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 6.51800012588501,
|
|
"epoch": 2.8759163144095456,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004184745958120669,
|
|
"loss": 6.1478,
|
|
"mean_token_accuracy": 0.1510514460504055,
|
|
"num_tokens": 58176329.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 6.5874213695526125,
|
|
"epoch": 2.8764513885173097,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041844514205246293,
|
|
"loss": 6.1459,
|
|
"mean_token_accuracy": 0.1416185826063156,
|
|
"num_tokens": 58187058.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 6.5409997463226315,
|
|
"epoch": 2.876986462625074,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004184156841509007,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.14460644870996475,
|
|
"num_tokens": 58196579.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 6.456871891021729,
|
|
"epoch": 2.8775215367328375,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00041838622210823076,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.1511030077934265,
|
|
"num_tokens": 58206689.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 6.5443192481994625,
|
|
"epoch": 2.878056610840601,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004183567559253037,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.1469161756336689,
|
|
"num_tokens": 58218093.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 6.5532856464385985,
|
|
"epoch": 2.8785916849483653,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00041832728560297055,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.14168731719255448,
|
|
"num_tokens": 58228587.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 6.4904169082641605,
|
|
"epoch": 2.8791267590561294,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00041829781114208214,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.15421380400657653,
|
|
"num_tokens": 58240500.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 6.490023803710938,
|
|
"epoch": 2.879661833163893,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00041826833254348956,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.14082615524530412,
|
|
"num_tokens": 58252253.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 6.554584217071533,
|
|
"epoch": 2.880196907271657,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00041823884980804406,
|
|
"loss": 6.1784,
|
|
"mean_token_accuracy": 0.1412655808031559,
|
|
"num_tokens": 58263356.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 6.410767126083374,
|
|
"epoch": 2.880731981379421,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041820936293659685,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.149995356798172,
|
|
"num_tokens": 58273270.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 6.548860740661621,
|
|
"epoch": 2.881267055487185,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041817987192999947,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.14403591752052308,
|
|
"num_tokens": 58284669.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 6.614366054534912,
|
|
"epoch": 2.881802129594949,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00041815037678910334,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.14625323116779326,
|
|
"num_tokens": 58294791.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 6.576487064361572,
|
|
"epoch": 2.882337203702713,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004181208775147602,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.14711599051952362,
|
|
"num_tokens": 58305789.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 6.520147228240967,
|
|
"epoch": 2.8828722778104767,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004180913741078218,
|
|
"loss": 6.1525,
|
|
"mean_token_accuracy": 0.1414557933807373,
|
|
"num_tokens": 58317547.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 6.5464863777160645,
|
|
"epoch": 2.883407351918241,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004180618665691402,
|
|
"loss": 6.1073,
|
|
"mean_token_accuracy": 0.1436331830918789,
|
|
"num_tokens": 58328408.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 6.439816045761108,
|
|
"epoch": 2.8839424260260045,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004180323548995672,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.16695494651794435,
|
|
"num_tokens": 58339356.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 6.47957181930542,
|
|
"epoch": 2.8844775001337686,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00041800283909995505,
|
|
"loss": 6.0338,
|
|
"mean_token_accuracy": 0.15543508157134056,
|
|
"num_tokens": 58349016.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 6.534615182876587,
|
|
"epoch": 2.8850125742415322,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004179733191711561,
|
|
"loss": 6.2077,
|
|
"mean_token_accuracy": 0.13543751537799836,
|
|
"num_tokens": 58360188.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 6.584318685531616,
|
|
"epoch": 2.8855476483492963,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00041794379511402263,
|
|
"loss": 6.1576,
|
|
"mean_token_accuracy": 0.13940884917974472,
|
|
"num_tokens": 58370733.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 6.51302170753479,
|
|
"epoch": 2.8860827224570604,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004179142669294071,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.13779421001672745,
|
|
"num_tokens": 58382249.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 6.519924831390381,
|
|
"epoch": 2.886617796564824,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041788473461816224,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.15247844457626342,
|
|
"num_tokens": 58393598.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 6.542453813552856,
|
|
"epoch": 2.887152870672588,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041785519818114073,
|
|
"loss": 6.1325,
|
|
"mean_token_accuracy": 0.14348772615194322,
|
|
"num_tokens": 58403920.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 6.480035829544067,
|
|
"epoch": 2.8876879447803523,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041782565761919546,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.1435514733195305,
|
|
"num_tokens": 58413691.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 6.607816743850708,
|
|
"epoch": 2.888223018888116,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00041779611293317936,
|
|
"loss": 6.1987,
|
|
"mean_token_accuracy": 0.13868182003498078,
|
|
"num_tokens": 58425995.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 6.547822713851929,
|
|
"epoch": 2.88875809299588,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004177665641239456,
|
|
"loss": 6.1249,
|
|
"mean_token_accuracy": 0.13888239860534668,
|
|
"num_tokens": 58435984.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 6.541032600402832,
|
|
"epoch": 2.8892931671036437,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 0.00041773701119234734,
|
|
"loss": 6.1777,
|
|
"mean_token_accuracy": 0.14314846992492675,
|
|
"num_tokens": 58447630.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 2.8892931671036437,
|
|
"eval_entropy": 6.362117066087748,
|
|
"eval_loss": 6.246114253997803,
|
|
"eval_mean_token_accuracy": 0.1478163972710362,
|
|
"eval_num_tokens": 58447630.0,
|
|
"eval_runtime": 22.8096,
|
|
"eval_samples_per_second": 1301.162,
|
|
"eval_steps_per_second": 162.651,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"entropy": 6.602389907836914,
|
|
"epoch": 2.889828241211408,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000417707454139238,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.13884808719158173,
|
|
"num_tokens": 58458055.0,
|
|
"step": 27005
|
|
},
|
|
{
|
|
"entropy": 6.546388339996338,
|
|
"epoch": 2.8903633153191715,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004176778929654709,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.1432637855410576,
|
|
"num_tokens": 58469115.0,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"entropy": 6.516539096832275,
|
|
"epoch": 2.8908983894269356,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004176483276718997,
|
|
"loss": 6.1057,
|
|
"mean_token_accuracy": 0.15183210074901582,
|
|
"num_tokens": 58480038.0,
|
|
"step": 27015
|
|
},
|
|
{
|
|
"entropy": 6.5369891166687015,
|
|
"epoch": 2.8914334635346997,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004176187582593781,
|
|
"loss": 6.1794,
|
|
"mean_token_accuracy": 0.14798381924629211,
|
|
"num_tokens": 58490413.0,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"entropy": 6.535061311721802,
|
|
"epoch": 2.8919685376424633,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004175891847287599,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.14452269598841666,
|
|
"num_tokens": 58500162.0,
|
|
"step": 27025
|
|
},
|
|
{
|
|
"entropy": 6.468069839477539,
|
|
"epoch": 2.8925036117502274,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.000417559607080899,
|
|
"loss": 6.0313,
|
|
"mean_token_accuracy": 0.15732128471136092,
|
|
"num_tokens": 58511174.0,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"entropy": 6.547758436203003,
|
|
"epoch": 2.8930386858579915,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00041753002531664954,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.13952440470457078,
|
|
"num_tokens": 58521891.0,
|
|
"step": 27035
|
|
},
|
|
{
|
|
"entropy": 6.560975122451782,
|
|
"epoch": 2.893573759965755,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004175004394368656,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.14373358637094497,
|
|
"num_tokens": 58532029.0,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"entropy": 6.576901149749756,
|
|
"epoch": 2.8941088340735193,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041747084944240154,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.14375966638326645,
|
|
"num_tokens": 58542568.0,
|
|
"step": 27045
|
|
},
|
|
{
|
|
"entropy": 6.5749718189239506,
|
|
"epoch": 2.8946439081812834,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004174412553341116,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.15005491003394128,
|
|
"num_tokens": 58553396.0,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"entropy": 6.478358936309815,
|
|
"epoch": 2.895178982289047,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004174116571128506,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.14866278767585756,
|
|
"num_tokens": 58564792.0,
|
|
"step": 27055
|
|
},
|
|
{
|
|
"entropy": 6.524820709228516,
|
|
"epoch": 2.895714056396811,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00041738205477947284,
|
|
"loss": 6.1874,
|
|
"mean_token_accuracy": 0.14725350737571716,
|
|
"num_tokens": 58575666.0,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"entropy": 6.519762420654297,
|
|
"epoch": 2.8962491305045748,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00041735244833483325,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.14813049137592316,
|
|
"num_tokens": 58587411.0,
|
|
"step": 27065
|
|
},
|
|
{
|
|
"entropy": 6.514184236526489,
|
|
"epoch": 2.896784204612339,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00041732283777978687,
|
|
"loss": 6.1055,
|
|
"mean_token_accuracy": 0.1437177024781704,
|
|
"num_tokens": 58598283.0,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"entropy": 6.49215784072876,
|
|
"epoch": 2.8973192787201025,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004172932231151885,
|
|
"loss": 6.1035,
|
|
"mean_token_accuracy": 0.15028020590543748,
|
|
"num_tokens": 58608982.0,
|
|
"step": 27075
|
|
},
|
|
{
|
|
"entropy": 6.511564922332764,
|
|
"epoch": 2.8978543528278666,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004172636043418932,
|
|
"loss": 6.144,
|
|
"mean_token_accuracy": 0.14483024850487708,
|
|
"num_tokens": 58619022.0,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"entropy": 6.497292375564575,
|
|
"epoch": 2.8983894269356307,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004172339814607564,
|
|
"loss": 6.0581,
|
|
"mean_token_accuracy": 0.14393431842327117,
|
|
"num_tokens": 58630559.0,
|
|
"step": 27085
|
|
},
|
|
{
|
|
"entropy": 6.549119091033935,
|
|
"epoch": 2.8989245010433944,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004172043544726334,
|
|
"loss": 6.1729,
|
|
"mean_token_accuracy": 0.14365807175636292,
|
|
"num_tokens": 58641346.0,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"entropy": 6.526231050491333,
|
|
"epoch": 2.8994595751511585,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004171747233783796,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.14360417649149895,
|
|
"num_tokens": 58652697.0,
|
|
"step": 27095
|
|
},
|
|
{
|
|
"entropy": 6.566808795928955,
|
|
"epoch": 2.8999946492589226,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004171450881788507,
|
|
"loss": 6.1646,
|
|
"mean_token_accuracy": 0.13571249097585678,
|
|
"num_tokens": 58665574.0,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"entropy": 6.592064094543457,
|
|
"epoch": 2.9005297233666862,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00041711544887490233,
|
|
"loss": 6.1011,
|
|
"mean_token_accuracy": 0.1484016641974449,
|
|
"num_tokens": 58676079.0,
|
|
"step": 27105
|
|
},
|
|
{
|
|
"entropy": 6.50888614654541,
|
|
"epoch": 2.9010647974744503,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004170858054673903,
|
|
"loss": 6.1468,
|
|
"mean_token_accuracy": 0.14541101157665254,
|
|
"num_tokens": 58688465.0,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"entropy": 6.529153966903687,
|
|
"epoch": 2.901599871582214,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004170561579571706,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.1429116703569889,
|
|
"num_tokens": 58698772.0,
|
|
"step": 27115
|
|
},
|
|
{
|
|
"entropy": 6.54620327949524,
|
|
"epoch": 2.902134945689978,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00041702650634509934,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.13781452178955078,
|
|
"num_tokens": 58709505.0,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"entropy": 6.561288595199585,
|
|
"epoch": 2.9026700197977418,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041699685063203263,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.14607461914420128,
|
|
"num_tokens": 58718652.0,
|
|
"step": 27125
|
|
},
|
|
{
|
|
"entropy": 6.5879082679748535,
|
|
"epoch": 2.903205093905506,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00041696719081882685,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.13808235079050063,
|
|
"num_tokens": 58730207.0,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"entropy": 6.550343608856201,
|
|
"epoch": 2.90374016801327,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00041693752690633837,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.1468784287571907,
|
|
"num_tokens": 58741418.0,
|
|
"step": 27135
|
|
},
|
|
{
|
|
"entropy": 6.5386512756347654,
|
|
"epoch": 2.9042752421210336,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004169078588954237,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.13847753629088402,
|
|
"num_tokens": 58753535.0,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"entropy": 6.538966226577759,
|
|
"epoch": 2.9048103162287977,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004168781867869396,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.13957973197102547,
|
|
"num_tokens": 58766220.0,
|
|
"step": 27145
|
|
},
|
|
{
|
|
"entropy": 6.607447004318237,
|
|
"epoch": 2.905345390336562,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00041684851058174284,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.14425073340535163,
|
|
"num_tokens": 58776795.0,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"entropy": 6.575570297241211,
|
|
"epoch": 2.9058804644443255,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004168188302806902,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.14650482833385467,
|
|
"num_tokens": 58787495.0,
|
|
"step": 27155
|
|
},
|
|
{
|
|
"entropy": 6.518732070922852,
|
|
"epoch": 2.9064155385520896,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004167891458846387,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.14203549474477767,
|
|
"num_tokens": 58798518.0,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"entropy": 6.560490512847901,
|
|
"epoch": 2.9069506126598537,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00041675945739444567,
|
|
"loss": 6.1246,
|
|
"mean_token_accuracy": 0.15044992864131929,
|
|
"num_tokens": 58808849.0,
|
|
"step": 27165
|
|
},
|
|
{
|
|
"entropy": 6.5911009311676025,
|
|
"epoch": 2.9074856867676173,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004167297648109682,
|
|
"loss": 6.1317,
|
|
"mean_token_accuracy": 0.14701652228832246,
|
|
"num_tokens": 58821110.0,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"entropy": 6.568964004516602,
|
|
"epoch": 2.908020760875381,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00041670006813506366,
|
|
"loss": 6.1976,
|
|
"mean_token_accuracy": 0.14486606419086456,
|
|
"num_tokens": 58831433.0,
|
|
"step": 27175
|
|
},
|
|
{
|
|
"entropy": 6.575030851364136,
|
|
"epoch": 2.908555834983145,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041667036736758954,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.13637409806251527,
|
|
"num_tokens": 58842031.0,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"entropy": 6.487732601165772,
|
|
"epoch": 2.909090909090909,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041664066250940353,
|
|
"loss": 6.0776,
|
|
"mean_token_accuracy": 0.14899675101041793,
|
|
"num_tokens": 58852767.0,
|
|
"step": 27185
|
|
},
|
|
{
|
|
"entropy": 6.566605043411255,
|
|
"epoch": 2.909625983198673,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00041661095356136326,
|
|
"loss": 6.1489,
|
|
"mean_token_accuracy": 0.145561084151268,
|
|
"num_tokens": 58864147.0,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"entropy": 6.55667634010315,
|
|
"epoch": 2.910161057306437,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041658124052432655,
|
|
"loss": 6.1277,
|
|
"mean_token_accuracy": 0.15169840008020402,
|
|
"num_tokens": 58874059.0,
|
|
"step": 27195
|
|
},
|
|
{
|
|
"entropy": 6.494117403030396,
|
|
"epoch": 2.910696131414201,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004165515233991514,
|
|
"loss": 6.1261,
|
|
"mean_token_accuracy": 0.14528934508562089,
|
|
"num_tokens": 58884433.0,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"entropy": 6.552262020111084,
|
|
"epoch": 2.9112312055219647,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004165218021866961,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.13547866567969322,
|
|
"num_tokens": 58896062.0,
|
|
"step": 27205
|
|
},
|
|
{
|
|
"entropy": 6.536118125915527,
|
|
"epoch": 2.911766279629729,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004164920768878184,
|
|
"loss": 6.1326,
|
|
"mean_token_accuracy": 0.14536064118146896,
|
|
"num_tokens": 58906926.0,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"entropy": 6.549924421310425,
|
|
"epoch": 2.912301353737493,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00041646234750337697,
|
|
"loss": 6.1207,
|
|
"mean_token_accuracy": 0.1431511051952839,
|
|
"num_tokens": 58919230.0,
|
|
"step": 27215
|
|
},
|
|
{
|
|
"entropy": 6.564912176132202,
|
|
"epoch": 2.9128364278452565,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004164326140342302,
|
|
"loss": 6.1755,
|
|
"mean_token_accuracy": 0.1414386585354805,
|
|
"num_tokens": 58929094.0,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"entropy": 6.532775974273681,
|
|
"epoch": 2.9133715019530206,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041640287648123645,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.1489305667579174,
|
|
"num_tokens": 58939952.0,
|
|
"step": 27225
|
|
},
|
|
{
|
|
"entropy": 6.5599359512329105,
|
|
"epoch": 2.9139065760607843,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00041637313484525464,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.1518976256251335,
|
|
"num_tokens": 58950520.0,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"entropy": 6.600883674621582,
|
|
"epoch": 2.9144416501685484,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004163433891271434,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.1392052501440048,
|
|
"num_tokens": 58960578.0,
|
|
"step": 27235
|
|
},
|
|
{
|
|
"entropy": 6.560609436035156,
|
|
"epoch": 2.914976724276312,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00041631363932776154,
|
|
"loss": 6.2171,
|
|
"mean_token_accuracy": 0.14074805453419686,
|
|
"num_tokens": 58972188.0,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"entropy": 6.555400753021241,
|
|
"epoch": 2.915511798384076,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041628388544796835,
|
|
"loss": 6.1201,
|
|
"mean_token_accuracy": 0.15544168502092362,
|
|
"num_tokens": 58982852.0,
|
|
"step": 27245
|
|
},
|
|
{
|
|
"entropy": 6.494577074050904,
|
|
"epoch": 2.9160468724918402,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004162541274886228,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.15355968475341797,
|
|
"num_tokens": 58993713.0,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"entropy": 6.449869966506958,
|
|
"epoch": 2.916581946599604,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00041622436545058405,
|
|
"loss": 6.0418,
|
|
"mean_token_accuracy": 0.14600559026002885,
|
|
"num_tokens": 59004021.0,
|
|
"step": 27255
|
|
},
|
|
{
|
|
"entropy": 6.389255142211914,
|
|
"epoch": 2.917117020707368,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041619459933471174,
|
|
"loss": 6.0404,
|
|
"mean_token_accuracy": 0.16860805898904802,
|
|
"num_tokens": 59016592.0,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"entropy": 6.5751471519470215,
|
|
"epoch": 2.917652094815132,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004161648291418651,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.1499280661344528,
|
|
"num_tokens": 59027116.0,
|
|
"step": 27265
|
|
},
|
|
{
|
|
"entropy": 6.5485083103179935,
|
|
"epoch": 2.9181871689228958,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004161350548729039,
|
|
"loss": 6.1418,
|
|
"mean_token_accuracy": 0.1413179263472557,
|
|
"num_tokens": 59036917.0,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"entropy": 6.500831270217896,
|
|
"epoch": 2.91872224303066,
|
|
"grad_norm": 4.90625,
|
|
"learning_rate": 0.0004161052765286878,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.14654586613178253,
|
|
"num_tokens": 59046588.0,
|
|
"step": 27275
|
|
},
|
|
{
|
|
"entropy": 6.5354170322418215,
|
|
"epoch": 2.9192573171384235,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004160754941100767,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.14758977815508842,
|
|
"num_tokens": 59057710.0,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"entropy": 6.585712480545044,
|
|
"epoch": 2.9197923912461876,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041604570761793054,
|
|
"loss": 6.1989,
|
|
"mean_token_accuracy": 0.1344500318169594,
|
|
"num_tokens": 59068795.0,
|
|
"step": 27285
|
|
},
|
|
{
|
|
"entropy": 6.542792558670044,
|
|
"epoch": 2.9203274653539513,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004160159170531094,
|
|
"loss": 6.1283,
|
|
"mean_token_accuracy": 0.14961691647768022,
|
|
"num_tokens": 59079266.0,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"entropy": 6.505189085006714,
|
|
"epoch": 2.9208625394617154,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004159861224164734,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.13652141764760017,
|
|
"num_tokens": 59088827.0,
|
|
"step": 27295
|
|
},
|
|
{
|
|
"entropy": 6.497051095962524,
|
|
"epoch": 2.9213976135694795,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000415956323708883,
|
|
"loss": 6.1699,
|
|
"mean_token_accuracy": 0.14570963978767396,
|
|
"num_tokens": 59099097.0,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"entropy": 6.623202085494995,
|
|
"epoch": 2.921932687677243,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041592652093119846,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.14955192655324936,
|
|
"num_tokens": 59110175.0,
|
|
"step": 27305
|
|
},
|
|
{
|
|
"entropy": 6.609943866729736,
|
|
"epoch": 2.9224677617850072,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041589671408428055,
|
|
"loss": 6.1677,
|
|
"mean_token_accuracy": 0.1443056084215641,
|
|
"num_tokens": 59121133.0,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"entropy": 6.559341859817505,
|
|
"epoch": 2.9230028358927713,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041586690316898977,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.13829909190535544,
|
|
"num_tokens": 59132750.0,
|
|
"step": 27315
|
|
},
|
|
{
|
|
"entropy": 6.561866092681885,
|
|
"epoch": 2.923537910000535,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00041583708818618693,
|
|
"loss": 6.146,
|
|
"mean_token_accuracy": 0.1492330625653267,
|
|
"num_tokens": 59143488.0,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"entropy": 6.4226541996002195,
|
|
"epoch": 2.924072984108299,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000415807269136733,
|
|
"loss": 6.0624,
|
|
"mean_token_accuracy": 0.1496111460030079,
|
|
"num_tokens": 59154118.0,
|
|
"step": 27325
|
|
},
|
|
{
|
|
"entropy": 6.5389172554016115,
|
|
"epoch": 2.924608058216063,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041577744602148893,
|
|
"loss": 6.1786,
|
|
"mean_token_accuracy": 0.1456573411822319,
|
|
"num_tokens": 59164736.0,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"entropy": 6.531483936309814,
|
|
"epoch": 2.925143132323827,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000415747618841316,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.14324256479740144,
|
|
"num_tokens": 59175895.0,
|
|
"step": 27335
|
|
},
|
|
{
|
|
"entropy": 6.538332414627075,
|
|
"epoch": 2.925678206431591,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004157177875970752,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.1522311195731163,
|
|
"num_tokens": 59186692.0,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"entropy": 6.593583011627198,
|
|
"epoch": 2.9262132805393546,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004156879522896281,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.14875915348529817,
|
|
"num_tokens": 59197731.0,
|
|
"step": 27345
|
|
},
|
|
{
|
|
"entropy": 6.536186790466308,
|
|
"epoch": 2.9267483546471187,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004156581129198362,
|
|
"loss": 6.1283,
|
|
"mean_token_accuracy": 0.1420949801802635,
|
|
"num_tokens": 59209470.0,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"entropy": 6.4622376441955565,
|
|
"epoch": 2.9272834287548823,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000415628269488561,
|
|
"loss": 6.0892,
|
|
"mean_token_accuracy": 0.14847136288881302,
|
|
"num_tokens": 59220085.0,
|
|
"step": 27355
|
|
},
|
|
{
|
|
"entropy": 6.492366743087769,
|
|
"epoch": 2.9278185028626464,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004155984219966643,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.14273576065897942,
|
|
"num_tokens": 59231862.0,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"entropy": 6.50175142288208,
|
|
"epoch": 2.9283535769704105,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041556857044500796,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.13954354152083398,
|
|
"num_tokens": 59242771.0,
|
|
"step": 27365
|
|
},
|
|
{
|
|
"entropy": 6.518511247634888,
|
|
"epoch": 2.928888651078174,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004155387148344538,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.14717973470687867,
|
|
"num_tokens": 59253456.0,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"entropy": 6.526618576049804,
|
|
"epoch": 2.9294237251859383,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00041550885516586405,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.1415664866566658,
|
|
"num_tokens": 59265307.0,
|
|
"step": 27375
|
|
},
|
|
{
|
|
"entropy": 6.502726030349732,
|
|
"epoch": 2.9299587992937024,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00041547899144010086,
|
|
"loss": 6.088,
|
|
"mean_token_accuracy": 0.14544336199760438,
|
|
"num_tokens": 59276920.0,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"entropy": 6.58178825378418,
|
|
"epoch": 2.930493873401466,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041544912365802655,
|
|
"loss": 6.1293,
|
|
"mean_token_accuracy": 0.14250123277306556,
|
|
"num_tokens": 59288370.0,
|
|
"step": 27385
|
|
},
|
|
{
|
|
"entropy": 6.432065868377686,
|
|
"epoch": 2.93102894750923,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004154192518205035,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.15524159222841263,
|
|
"num_tokens": 59299719.0,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"entropy": 6.561090326309204,
|
|
"epoch": 2.931564021616994,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00041538937592839427,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.14323845952749253,
|
|
"num_tokens": 59310409.0,
|
|
"step": 27395
|
|
},
|
|
{
|
|
"entropy": 6.513817501068115,
|
|
"epoch": 2.932099095724758,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041535949598256157,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.14726171642541885,
|
|
"num_tokens": 59321429.0,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"entropy": 6.595257759094238,
|
|
"epoch": 2.9326341698325216,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041532961198386813,
|
|
"loss": 6.1832,
|
|
"mean_token_accuracy": 0.14056679531931876,
|
|
"num_tokens": 59332095.0,
|
|
"step": 27405
|
|
},
|
|
{
|
|
"entropy": 6.528480672836304,
|
|
"epoch": 2.9331692439402857,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004152997239331769,
|
|
"loss": 6.1582,
|
|
"mean_token_accuracy": 0.1406519390642643,
|
|
"num_tokens": 59344002.0,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"entropy": 6.501610851287841,
|
|
"epoch": 2.9337043180480498,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004152698318313509,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.1451256513595581,
|
|
"num_tokens": 59355148.0,
|
|
"step": 27415
|
|
},
|
|
{
|
|
"entropy": 6.485611057281494,
|
|
"epoch": 2.9342393921558134,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004152399356792531,
|
|
"loss": 6.0631,
|
|
"mean_token_accuracy": 0.15028859302401543,
|
|
"num_tokens": 59365916.0,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"entropy": 6.464716815948487,
|
|
"epoch": 2.9347744662635775,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041521003547774694,
|
|
"loss": 6.0796,
|
|
"mean_token_accuracy": 0.1456640660762787,
|
|
"num_tokens": 59376843.0,
|
|
"step": 27425
|
|
},
|
|
{
|
|
"entropy": 6.554827260971069,
|
|
"epoch": 2.9353095403713416,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004151801312276957,
|
|
"loss": 6.2289,
|
|
"mean_token_accuracy": 0.1389165088534355,
|
|
"num_tokens": 59388572.0,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"entropy": 6.593492889404297,
|
|
"epoch": 2.9358446144791053,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004151502229299628,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.13896920755505562,
|
|
"num_tokens": 59399122.0,
|
|
"step": 27435
|
|
},
|
|
{
|
|
"entropy": 6.526142644882202,
|
|
"epoch": 2.9363796885868694,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000415120310585412,
|
|
"loss": 6.0863,
|
|
"mean_token_accuracy": 0.14602885097265245,
|
|
"num_tokens": 59409565.0,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"entropy": 6.51497802734375,
|
|
"epoch": 2.9369147626946335,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004150903941949068,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.15551329106092454,
|
|
"num_tokens": 59420465.0,
|
|
"step": 27445
|
|
},
|
|
{
|
|
"entropy": 6.584837436676025,
|
|
"epoch": 2.937449836802397,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041506047375931127,
|
|
"loss": 6.1751,
|
|
"mean_token_accuracy": 0.1433542288839817,
|
|
"num_tokens": 59431457.0,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"entropy": 6.555227899551392,
|
|
"epoch": 2.937984910910161,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004150305492794892,
|
|
"loss": 6.13,
|
|
"mean_token_accuracy": 0.15279969722032546,
|
|
"num_tokens": 59442257.0,
|
|
"step": 27455
|
|
},
|
|
{
|
|
"entropy": 6.572006940841675,
|
|
"epoch": 2.938519985017925,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004150006207563047,
|
|
"loss": 6.1451,
|
|
"mean_token_accuracy": 0.14554820209741592,
|
|
"num_tokens": 59453634.0,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"entropy": 6.550296592712402,
|
|
"epoch": 2.939055059125689,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00041497068819062197,
|
|
"loss": 6.1881,
|
|
"mean_token_accuracy": 0.1403369501233101,
|
|
"num_tokens": 59463085.0,
|
|
"step": 27465
|
|
},
|
|
{
|
|
"entropy": 6.518547821044922,
|
|
"epoch": 2.9395901332334526,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004149407515833052,
|
|
"loss": 6.0912,
|
|
"mean_token_accuracy": 0.14406699538230897,
|
|
"num_tokens": 59473195.0,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"entropy": 6.536580324172974,
|
|
"epoch": 2.9401252073412167,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000414910810935219,
|
|
"loss": 6.1641,
|
|
"mean_token_accuracy": 0.14478133395314216,
|
|
"num_tokens": 59483669.0,
|
|
"step": 27475
|
|
},
|
|
{
|
|
"entropy": 6.5624762058258055,
|
|
"epoch": 2.940660281448981,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041488086624722777,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.14694832414388656,
|
|
"num_tokens": 59495036.0,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"entropy": 6.531662225723267,
|
|
"epoch": 2.9411953555567445,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00041485091752019613,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.15077586323022843,
|
|
"num_tokens": 59505130.0,
|
|
"step": 27485
|
|
},
|
|
{
|
|
"entropy": 6.45242829322815,
|
|
"epoch": 2.9417304296645086,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00041482096475498894,
|
|
"loss": 6.0039,
|
|
"mean_token_accuracy": 0.158292455971241,
|
|
"num_tokens": 59516275.0,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"entropy": 6.5823609828948975,
|
|
"epoch": 2.9422655037722727,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041479100795247106,
|
|
"loss": 6.194,
|
|
"mean_token_accuracy": 0.14621485844254495,
|
|
"num_tokens": 59526978.0,
|
|
"step": 27495
|
|
},
|
|
{
|
|
"entropy": 6.559683895111084,
|
|
"epoch": 2.9428005778800364,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004147610471135074,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.15046545565128328,
|
|
"num_tokens": 59536771.0,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"entropy": 6.4983540058135985,
|
|
"epoch": 2.9433356519878004,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00041473108223896314,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.14174746125936508,
|
|
"num_tokens": 59548371.0,
|
|
"step": 27505
|
|
},
|
|
{
|
|
"entropy": 6.584409999847412,
|
|
"epoch": 2.943870726095564,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041470111332970354,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.14764641970396042,
|
|
"num_tokens": 59558578.0,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"entropy": 6.4651891708374025,
|
|
"epoch": 2.944405800203328,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000414671140386594,
|
|
"loss": 6.1145,
|
|
"mean_token_accuracy": 0.1466823011636734,
|
|
"num_tokens": 59569023.0,
|
|
"step": 27515
|
|
},
|
|
{
|
|
"entropy": 6.529027366638184,
|
|
"epoch": 2.944940874311092,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004146411634104999,
|
|
"loss": 6.1654,
|
|
"mean_token_accuracy": 0.14905362129211425,
|
|
"num_tokens": 59580296.0,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"entropy": 6.508855247497559,
|
|
"epoch": 2.945475948418856,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041461118240228675,
|
|
"loss": 6.0437,
|
|
"mean_token_accuracy": 0.1487180545926094,
|
|
"num_tokens": 59591298.0,
|
|
"step": 27525
|
|
},
|
|
{
|
|
"entropy": 6.61455717086792,
|
|
"epoch": 2.94601102252662,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041458119736282033,
|
|
"loss": 6.1252,
|
|
"mean_token_accuracy": 0.1434404209256172,
|
|
"num_tokens": 59602575.0,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"entropy": 6.579403734207153,
|
|
"epoch": 2.9465460966343837,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00041455120829296657,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.14118235260248185,
|
|
"num_tokens": 59613287.0,
|
|
"step": 27535
|
|
},
|
|
{
|
|
"entropy": 6.5361552238464355,
|
|
"epoch": 2.947081170742148,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004145212151935911,
|
|
"loss": 6.1802,
|
|
"mean_token_accuracy": 0.14011188447475434,
|
|
"num_tokens": 59623263.0,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"entropy": 6.575955104827881,
|
|
"epoch": 2.947616244849912,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004144912180655603,
|
|
"loss": 6.1568,
|
|
"mean_token_accuracy": 0.14539643377065659,
|
|
"num_tokens": 59634416.0,
|
|
"step": 27545
|
|
},
|
|
{
|
|
"entropy": 6.577270412445069,
|
|
"epoch": 2.9481513189576756,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004144612169097401,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.14369366616010665,
|
|
"num_tokens": 59643866.0,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"entropy": 6.548248052597046,
|
|
"epoch": 2.9486863930654397,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004144312117269969,
|
|
"loss": 6.1191,
|
|
"mean_token_accuracy": 0.14380853474140168,
|
|
"num_tokens": 59654113.0,
|
|
"step": 27555
|
|
},
|
|
{
|
|
"entropy": 6.464841651916504,
|
|
"epoch": 2.9492214671732033,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041440120251819704,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.14206772595643996,
|
|
"num_tokens": 59663837.0,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"entropy": 6.355609273910522,
|
|
"epoch": 2.9497565412809674,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000414371189284207,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.1637068822979927,
|
|
"num_tokens": 59673782.0,
|
|
"step": 27565
|
|
},
|
|
{
|
|
"entropy": 6.490414762496949,
|
|
"epoch": 2.950291615388731,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041434117202589346,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.1495014876127243,
|
|
"num_tokens": 59684775.0,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"entropy": 6.504471492767334,
|
|
"epoch": 2.950826689496495,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004143111507441232,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.152902090549469,
|
|
"num_tokens": 59695193.0,
|
|
"step": 27575
|
|
},
|
|
{
|
|
"entropy": 6.533831691741943,
|
|
"epoch": 2.9513617636042593,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041428112543976303,
|
|
"loss": 6.1093,
|
|
"mean_token_accuracy": 0.1479498937726021,
|
|
"num_tokens": 59705707.0,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"entropy": 6.544313955307007,
|
|
"epoch": 2.951896837712023,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041425109611367987,
|
|
"loss": 6.1714,
|
|
"mean_token_accuracy": 0.14184336364269257,
|
|
"num_tokens": 59715882.0,
|
|
"step": 27585
|
|
},
|
|
{
|
|
"entropy": 6.579050064086914,
|
|
"epoch": 2.952431911819787,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004142210627667409,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.13953597471117973,
|
|
"num_tokens": 59726690.0,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"entropy": 6.5310040473937985,
|
|
"epoch": 2.952966985927551,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041419102539981344,
|
|
"loss": 6.1161,
|
|
"mean_token_accuracy": 0.1418216973543167,
|
|
"num_tokens": 59737052.0,
|
|
"step": 27595
|
|
},
|
|
{
|
|
"entropy": 6.538689661026001,
|
|
"epoch": 2.953502060035315,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004141609840137646,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.14260804504156113,
|
|
"num_tokens": 59747989.0,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"entropy": 6.587896633148193,
|
|
"epoch": 2.954037134143079,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004141309386094619,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.14988439679145812,
|
|
"num_tokens": 59759169.0,
|
|
"step": 27605
|
|
},
|
|
{
|
|
"entropy": 6.548550033569336,
|
|
"epoch": 2.954572208250843,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004141008891877728,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.14452364891767502,
|
|
"num_tokens": 59769837.0,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"entropy": 6.423670911788941,
|
|
"epoch": 2.9551072823586066,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00041407083574956515,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.1507248267531395,
|
|
"num_tokens": 59780671.0,
|
|
"step": 27615
|
|
},
|
|
{
|
|
"entropy": 6.498124122619629,
|
|
"epoch": 2.9556423564663707,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004140407782957067,
|
|
"loss": 6.072,
|
|
"mean_token_accuracy": 0.15708368718624116,
|
|
"num_tokens": 59792006.0,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"entropy": 6.564159631729126,
|
|
"epoch": 2.9561774305741344,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004140107168270653,
|
|
"loss": 6.124,
|
|
"mean_token_accuracy": 0.1428181178867817,
|
|
"num_tokens": 59802627.0,
|
|
"step": 27625
|
|
},
|
|
{
|
|
"entropy": 6.525749588012696,
|
|
"epoch": 2.9567125046818985,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041398065134450897,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.14820274859666824,
|
|
"num_tokens": 59813048.0,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"entropy": 6.510714721679688,
|
|
"epoch": 2.957247578789662,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004139505818489058,
|
|
"loss": 6.1548,
|
|
"mean_token_accuracy": 0.15421977937221526,
|
|
"num_tokens": 59823730.0,
|
|
"step": 27635
|
|
},
|
|
{
|
|
"entropy": 6.590114307403565,
|
|
"epoch": 2.9577826528974263,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00041392050834112415,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.14583321958780288,
|
|
"num_tokens": 59835054.0,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"entropy": 6.625777339935302,
|
|
"epoch": 2.9583177270051904,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004138904308220324,
|
|
"loss": 6.1819,
|
|
"mean_token_accuracy": 0.13680932596325873,
|
|
"num_tokens": 59845641.0,
|
|
"step": 27645
|
|
},
|
|
{
|
|
"entropy": 6.525809621810913,
|
|
"epoch": 2.958852801112954,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041386034929249895,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.14387934803962707,
|
|
"num_tokens": 59856255.0,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"entropy": 6.505270004272461,
|
|
"epoch": 2.959387875220718,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004138302637533924,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.15253653079271318,
|
|
"num_tokens": 59867215.0,
|
|
"step": 27655
|
|
},
|
|
{
|
|
"entropy": 6.530617666244507,
|
|
"epoch": 2.959922949328482,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004138001742055815,
|
|
"loss": 6.1401,
|
|
"mean_token_accuracy": 0.14065187573432922,
|
|
"num_tokens": 59877690.0,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"entropy": 6.521882152557373,
|
|
"epoch": 2.960458023436246,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004137700806499351,
|
|
"loss": 6.1069,
|
|
"mean_token_accuracy": 0.14869894385337828,
|
|
"num_tokens": 59888183.0,
|
|
"step": 27665
|
|
},
|
|
{
|
|
"entropy": 6.521590805053711,
|
|
"epoch": 2.96099309754401,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041373998308732204,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.14743454605340958,
|
|
"num_tokens": 59898573.0,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"entropy": 6.557621335983276,
|
|
"epoch": 2.9615281716517736,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041370988151861153,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.14621955901384354,
|
|
"num_tokens": 59909605.0,
|
|
"step": 27675
|
|
},
|
|
{
|
|
"entropy": 6.501629638671875,
|
|
"epoch": 2.9620632457595377,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00041367977594467263,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.1491008721292019,
|
|
"num_tokens": 59920808.0,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"entropy": 6.518020725250244,
|
|
"epoch": 2.9625983198673014,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041364966636637477,
|
|
"loss": 6.1447,
|
|
"mean_token_accuracy": 0.14664777293801307,
|
|
"num_tokens": 59931302.0,
|
|
"step": 27685
|
|
},
|
|
{
|
|
"entropy": 6.577363109588623,
|
|
"epoch": 2.9631333939750655,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00041361955278458725,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.1464727871119976,
|
|
"num_tokens": 59942542.0,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"entropy": 6.524952459335327,
|
|
"epoch": 2.9636684680828296,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004135894352001796,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.14443745762109755,
|
|
"num_tokens": 59953547.0,
|
|
"step": 27695
|
|
},
|
|
{
|
|
"entropy": 6.5200448513031,
|
|
"epoch": 2.9642035421905932,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004135593136140215,
|
|
"loss": 6.1489,
|
|
"mean_token_accuracy": 0.1462544359266758,
|
|
"num_tokens": 59964828.0,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"entropy": 6.534692287445068,
|
|
"epoch": 2.9647386162983573,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041352918802698265,
|
|
"loss": 6.0933,
|
|
"mean_token_accuracy": 0.1580818846821785,
|
|
"num_tokens": 59974989.0,
|
|
"step": 27705
|
|
},
|
|
{
|
|
"entropy": 6.436513996124267,
|
|
"epoch": 2.9652736904061214,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000413499058439933,
|
|
"loss": 6.0248,
|
|
"mean_token_accuracy": 0.1544252708554268,
|
|
"num_tokens": 59985247.0,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"entropy": 6.520539999008179,
|
|
"epoch": 2.965808764513885,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004134689248537425,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.14445083290338517,
|
|
"num_tokens": 59995145.0,
|
|
"step": 27715
|
|
},
|
|
{
|
|
"entropy": 6.516549396514892,
|
|
"epoch": 2.966343838621649,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041343878726928125,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.15859436690807344,
|
|
"num_tokens": 60006400.0,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"entropy": 6.539439916610718,
|
|
"epoch": 2.9668789127294133,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004134086456874194,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.14860632568597792,
|
|
"num_tokens": 60017408.0,
|
|
"step": 27725
|
|
},
|
|
{
|
|
"entropy": 6.513773012161255,
|
|
"epoch": 2.967413986837177,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041337850010902743,
|
|
"loss": 6.129,
|
|
"mean_token_accuracy": 0.14962378442287444,
|
|
"num_tokens": 60030138.0,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"entropy": 6.472547006607056,
|
|
"epoch": 2.9679490609449406,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041334835053497573,
|
|
"loss": 6.0863,
|
|
"mean_token_accuracy": 0.1429509401321411,
|
|
"num_tokens": 60040966.0,
|
|
"step": 27735
|
|
},
|
|
{
|
|
"entropy": 6.5729821681976315,
|
|
"epoch": 2.9684841350527047,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004133181969661349,
|
|
"loss": 6.1377,
|
|
"mean_token_accuracy": 0.14632326886057853,
|
|
"num_tokens": 60053090.0,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"entropy": 6.590319442749023,
|
|
"epoch": 2.969019209160469,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041328803940337546,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.14039722308516503,
|
|
"num_tokens": 60063967.0,
|
|
"step": 27745
|
|
},
|
|
{
|
|
"entropy": 6.572171211242676,
|
|
"epoch": 2.9695542832682325,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004132578778475683,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.1467112995684147,
|
|
"num_tokens": 60075025.0,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"entropy": 6.578608655929566,
|
|
"epoch": 2.9700893573759966,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004132277122995844,
|
|
"loss": 6.1349,
|
|
"mean_token_accuracy": 0.1458240792155266,
|
|
"num_tokens": 60084530.0,
|
|
"step": 27755
|
|
},
|
|
{
|
|
"entropy": 6.500639343261719,
|
|
"epoch": 2.9706244314837607,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004131975427602948,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.14972144663333892,
|
|
"num_tokens": 60095809.0,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"entropy": 6.510994815826416,
|
|
"epoch": 2.9711595055915243,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004131673692305704,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.153014700114727,
|
|
"num_tokens": 60106559.0,
|
|
"step": 27765
|
|
},
|
|
{
|
|
"entropy": 6.5926484107971195,
|
|
"epoch": 2.9716945796992884,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004131371917112827,
|
|
"loss": 6.1826,
|
|
"mean_token_accuracy": 0.13936410546302797,
|
|
"num_tokens": 60117557.0,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"entropy": 6.591794967651367,
|
|
"epoch": 2.9722296538070525,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004131070102033031,
|
|
"loss": 6.1895,
|
|
"mean_token_accuracy": 0.14284161031246184,
|
|
"num_tokens": 60129211.0,
|
|
"step": 27775
|
|
},
|
|
{
|
|
"entropy": 6.550980520248413,
|
|
"epoch": 2.972764727914816,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00041307682470750293,
|
|
"loss": 6.1107,
|
|
"mean_token_accuracy": 0.1439488187432289,
|
|
"num_tokens": 60139345.0,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"entropy": 6.471018743515015,
|
|
"epoch": 2.9732998020225803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004130466352247538,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.14784197360277176,
|
|
"num_tokens": 60148881.0,
|
|
"step": 27785
|
|
},
|
|
{
|
|
"entropy": 6.463105535507202,
|
|
"epoch": 2.973834876130344,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041301644175592756,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.14570058584213258,
|
|
"num_tokens": 60159660.0,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"entropy": 6.477545976638794,
|
|
"epoch": 2.974369950238108,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041298624430189583,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.15053002536296844,
|
|
"num_tokens": 60170649.0,
|
|
"step": 27795
|
|
},
|
|
{
|
|
"entropy": 6.461702919006347,
|
|
"epoch": 2.9749050243458717,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004129560428635308,
|
|
"loss": 6.0234,
|
|
"mean_token_accuracy": 0.14848674833774567,
|
|
"num_tokens": 60181419.0,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"entropy": 6.512762928009034,
|
|
"epoch": 2.9754400984536358,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004129258374417044,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.13929613307118416,
|
|
"num_tokens": 60192466.0,
|
|
"step": 27805
|
|
},
|
|
{
|
|
"entropy": 6.545342445373535,
|
|
"epoch": 2.9759751725614,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004128956280372888,
|
|
"loss": 6.1221,
|
|
"mean_token_accuracy": 0.148729906976223,
|
|
"num_tokens": 60203081.0,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"entropy": 6.598952388763427,
|
|
"epoch": 2.9765102466691635,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041286541465115635,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.14199379980564117,
|
|
"num_tokens": 60214203.0,
|
|
"step": 27815
|
|
},
|
|
{
|
|
"entropy": 6.507927465438843,
|
|
"epoch": 2.9770453207769276,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004128351972841793,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.15064047574996947,
|
|
"num_tokens": 60224904.0,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"entropy": 6.51802020072937,
|
|
"epoch": 2.9775803948846917,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041280497593723046,
|
|
"loss": 6.1594,
|
|
"mean_token_accuracy": 0.1410234309732914,
|
|
"num_tokens": 60234962.0,
|
|
"step": 27825
|
|
},
|
|
{
|
|
"entropy": 6.468809413909912,
|
|
"epoch": 2.9781154689924554,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041277475061118223,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.15098343640565873,
|
|
"num_tokens": 60245758.0,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"entropy": 6.567389869689942,
|
|
"epoch": 2.9786505431002195,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00041274452130690746,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.14969985336065292,
|
|
"num_tokens": 60256809.0,
|
|
"step": 27835
|
|
},
|
|
{
|
|
"entropy": 6.486528062820435,
|
|
"epoch": 2.9791856172079836,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004127142880252789,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.15000572353601455,
|
|
"num_tokens": 60268031.0,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"entropy": 6.4771942615509035,
|
|
"epoch": 2.9797206913157472,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004126840507671698,
|
|
"loss": 6.227,
|
|
"mean_token_accuracy": 0.1357454314827919,
|
|
"num_tokens": 60278526.0,
|
|
"step": 27845
|
|
},
|
|
{
|
|
"entropy": 6.687369966506958,
|
|
"epoch": 2.980255765423511,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041265380953345293,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.1395222745835781,
|
|
"num_tokens": 60289412.0,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"entropy": 6.500949239730835,
|
|
"epoch": 2.980790839531275,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041262356432500175,
|
|
"loss": 6.0893,
|
|
"mean_token_accuracy": 0.14669547826051713,
|
|
"num_tokens": 60301242.0,
|
|
"step": 27855
|
|
},
|
|
{
|
|
"entropy": 6.500544214248658,
|
|
"epoch": 2.981325913639039,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041259331514268945,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.1506238602101803,
|
|
"num_tokens": 60311625.0,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"entropy": 6.572242403030396,
|
|
"epoch": 2.9818609877468027,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00041256306198738946,
|
|
"loss": 6.1712,
|
|
"mean_token_accuracy": 0.14497398138046264,
|
|
"num_tokens": 60321973.0,
|
|
"step": 27865
|
|
},
|
|
{
|
|
"entropy": 6.597566032409668,
|
|
"epoch": 2.982396061854567,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00041253280485997545,
|
|
"loss": 6.1517,
|
|
"mean_token_accuracy": 0.1441341981291771,
|
|
"num_tokens": 60332445.0,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"entropy": 6.471389102935791,
|
|
"epoch": 2.982931135962331,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000412502543761321,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.15902674570679665,
|
|
"num_tokens": 60342378.0,
|
|
"step": 27875
|
|
},
|
|
{
|
|
"entropy": 6.52194619178772,
|
|
"epoch": 2.9834662100700946,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004124722786922999,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.14575620740652084,
|
|
"num_tokens": 60353502.0,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"entropy": 6.51546630859375,
|
|
"epoch": 2.9840012841778587,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004124420096537861,
|
|
"loss": 6.1133,
|
|
"mean_token_accuracy": 0.14688497111201287,
|
|
"num_tokens": 60364243.0,
|
|
"step": 27885
|
|
},
|
|
{
|
|
"entropy": 6.584137058258056,
|
|
"epoch": 2.984536358285623,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004124117366466536,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.14282932877540588,
|
|
"num_tokens": 60375354.0,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"entropy": 6.495726156234741,
|
|
"epoch": 2.9850714323933865,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00041238145967177647,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.14686105847358705,
|
|
"num_tokens": 60385474.0,
|
|
"step": 27895
|
|
},
|
|
{
|
|
"entropy": 6.487525987625122,
|
|
"epoch": 2.9856065065011506,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004123511787300291,
|
|
"loss": 6.0756,
|
|
"mean_token_accuracy": 0.14707876294851302,
|
|
"num_tokens": 60395339.0,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"entropy": 6.502177143096924,
|
|
"epoch": 2.986141580608914,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004123208938222856,
|
|
"loss": 6.0798,
|
|
"mean_token_accuracy": 0.15350011736154556,
|
|
"num_tokens": 60406202.0,
|
|
"step": 27905
|
|
},
|
|
{
|
|
"entropy": 6.512846946716309,
|
|
"epoch": 2.9866766547166783,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00041229060494942074,
|
|
"loss": 6.0944,
|
|
"mean_token_accuracy": 0.1518133021891117,
|
|
"num_tokens": 60417251.0,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"entropy": 6.525832271575927,
|
|
"epoch": 2.987211728824442,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041226031211230883,
|
|
"loss": 6.1513,
|
|
"mean_token_accuracy": 0.1483101688325405,
|
|
"num_tokens": 60427299.0,
|
|
"step": 27915
|
|
},
|
|
{
|
|
"entropy": 6.556073999404907,
|
|
"epoch": 2.987746802932206,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041223001531182475,
|
|
"loss": 6.1436,
|
|
"mean_token_accuracy": 0.15102572739124298,
|
|
"num_tokens": 60438076.0,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"entropy": 6.490516471862793,
|
|
"epoch": 2.98828187703997,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041219971454884325,
|
|
"loss": 6.0284,
|
|
"mean_token_accuracy": 0.1498180314898491,
|
|
"num_tokens": 60449479.0,
|
|
"step": 27925
|
|
},
|
|
{
|
|
"entropy": 6.608638668060303,
|
|
"epoch": 2.988816951147734,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004121694098242392,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.14239273890852927,
|
|
"num_tokens": 60460664.0,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"entropy": 6.494765043258667,
|
|
"epoch": 2.989352025255498,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004121391011388878,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.1437053620815277,
|
|
"num_tokens": 60470673.0,
|
|
"step": 27935
|
|
},
|
|
{
|
|
"entropy": 6.504600858688354,
|
|
"epoch": 2.989887099363262,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041210878849366414,
|
|
"loss": 6.0981,
|
|
"mean_token_accuracy": 0.14941129088401794,
|
|
"num_tokens": 60481378.0,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"entropy": 6.474779891967773,
|
|
"epoch": 2.9904221734710257,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004120784718894434,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.14837968200445176,
|
|
"num_tokens": 60491264.0,
|
|
"step": 27945
|
|
},
|
|
{
|
|
"entropy": 6.419569587707519,
|
|
"epoch": 2.99095724757879,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004120481513271011,
|
|
"loss": 6.0496,
|
|
"mean_token_accuracy": 0.15500301122665405,
|
|
"num_tokens": 60502053.0,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"entropy": 6.513166093826294,
|
|
"epoch": 2.9914923216865534,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004120178268075127,
|
|
"loss": 6.0992,
|
|
"mean_token_accuracy": 0.15520761758089066,
|
|
"num_tokens": 60511995.0,
|
|
"step": 27955
|
|
},
|
|
{
|
|
"entropy": 6.574575138092041,
|
|
"epoch": 2.9920273957943175,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004119874983315538,
|
|
"loss": 6.1667,
|
|
"mean_token_accuracy": 0.14300660490989686,
|
|
"num_tokens": 60523127.0,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"entropy": 6.543115043640137,
|
|
"epoch": 2.992562469902081,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041195716590010015,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.1459070309996605,
|
|
"num_tokens": 60533448.0,
|
|
"step": 27965
|
|
},
|
|
{
|
|
"entropy": 6.516596794128418,
|
|
"epoch": 2.9930975440098453,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004119268295140275,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.14487022608518602,
|
|
"num_tokens": 60544369.0,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"entropy": 6.486294364929199,
|
|
"epoch": 2.9936326181176094,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000411896489174212,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.14541254341602325,
|
|
"num_tokens": 60555518.0,
|
|
"step": 27975
|
|
},
|
|
{
|
|
"entropy": 6.42024712562561,
|
|
"epoch": 2.994167692225373,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004118661448815295,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.15844773948192598,
|
|
"num_tokens": 60566358.0,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"entropy": 6.499072551727295,
|
|
"epoch": 2.994702766333137,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00041183579663685646,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.15441569164395333,
|
|
"num_tokens": 60577935.0,
|
|
"step": 27985
|
|
},
|
|
{
|
|
"entropy": 6.558824157714843,
|
|
"epoch": 2.9952378404409012,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004118054444410688,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.1410360835492611,
|
|
"num_tokens": 60588690.0,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"entropy": 6.486195707321167,
|
|
"epoch": 2.995772914548665,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041177508829504334,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.15343687534332276,
|
|
"num_tokens": 60599090.0,
|
|
"step": 27995
|
|
},
|
|
{
|
|
"entropy": 6.543155765533447,
|
|
"epoch": 2.996307988656429,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041174472819965636,
|
|
"loss": 6.1314,
|
|
"mean_token_accuracy": 0.144694983959198,
|
|
"num_tokens": 60609166.0,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"entropy": 6.514505290985108,
|
|
"epoch": 2.996843062764193,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041171436415578456,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.14840328618884085,
|
|
"num_tokens": 60619769.0,
|
|
"step": 28005
|
|
},
|
|
{
|
|
"entropy": 6.458199167251587,
|
|
"epoch": 2.9973781368719568,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004116839961643046,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.14158840700984002,
|
|
"num_tokens": 60630984.0,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"entropy": 6.508390474319458,
|
|
"epoch": 2.997913210979721,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00041165362422609366,
|
|
"loss": 6.1787,
|
|
"mean_token_accuracy": 0.1367316834628582,
|
|
"num_tokens": 60642019.0,
|
|
"step": 28015
|
|
},
|
|
{
|
|
"entropy": 6.602724885940551,
|
|
"epoch": 2.9984482850874845,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041162324834202843,
|
|
"loss": 6.179,
|
|
"mean_token_accuracy": 0.14135389029979706,
|
|
"num_tokens": 60653359.0,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"entropy": 6.49225926399231,
|
|
"epoch": 2.9989833591952486,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004115928685129861,
|
|
"loss": 5.9853,
|
|
"mean_token_accuracy": 0.1559699758887291,
|
|
"num_tokens": 60663627.0,
|
|
"step": 28025
|
|
},
|
|
{
|
|
"entropy": 6.47770094871521,
|
|
"epoch": 2.9995184333030123,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00041156248473984383,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.15031695365905762,
|
|
"num_tokens": 60675641.0,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"entropy": 6.476656966739231,
|
|
"epoch": 3.0,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004115320970234791,
|
|
"loss": 6.0709,
|
|
"mean_token_accuracy": 0.15384889973534477,
|
|
"num_tokens": 60684774.0,
|
|
"step": 28035
|
|
},
|
|
{
|
|
"entropy": 6.5345231056213375,
|
|
"epoch": 3.000535074107764,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041150170536476924,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.14800183549523355,
|
|
"num_tokens": 60696477.0,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"entropy": 6.503859186172486,
|
|
"epoch": 3.0010701482155278,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041147130976459175,
|
|
"loss": 5.9925,
|
|
"mean_token_accuracy": 0.15297874212265014,
|
|
"num_tokens": 60709214.0,
|
|
"step": 28045
|
|
},
|
|
{
|
|
"entropy": 6.4738609790802,
|
|
"epoch": 3.001605222323292,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004114409102238245,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.15773222595453262,
|
|
"num_tokens": 60719938.0,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"entropy": 6.3500162124633786,
|
|
"epoch": 3.0021402964310555,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041141050674334495,
|
|
"loss": 5.9335,
|
|
"mean_token_accuracy": 0.1532641187310219,
|
|
"num_tokens": 60730131.0,
|
|
"step": 28055
|
|
},
|
|
{
|
|
"entropy": 6.519957780838013,
|
|
"epoch": 3.0026753705388196,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004113800993240313,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.1546997308731079,
|
|
"num_tokens": 60741652.0,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"entropy": 6.462324953079223,
|
|
"epoch": 3.0032104446465837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041134968796676145,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.15572062730789185,
|
|
"num_tokens": 60752945.0,
|
|
"step": 28065
|
|
},
|
|
{
|
|
"entropy": 6.5231997013092045,
|
|
"epoch": 3.0037455187543474,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041131927267241356,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.15157316327095033,
|
|
"num_tokens": 60762695.0,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"entropy": 6.548785877227783,
|
|
"epoch": 3.0042805928621115,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041128885344186573,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.1533831126987934,
|
|
"num_tokens": 60773158.0,
|
|
"step": 28075
|
|
},
|
|
{
|
|
"entropy": 6.507574033737183,
|
|
"epoch": 3.004815666969875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00041125843027599643,
|
|
"loss": 6.1103,
|
|
"mean_token_accuracy": 0.14755358174443245,
|
|
"num_tokens": 60784171.0,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"entropy": 6.547276782989502,
|
|
"epoch": 3.005350741077639,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00041122800317568414,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.14379548132419587,
|
|
"num_tokens": 60794961.0,
|
|
"step": 28085
|
|
},
|
|
{
|
|
"entropy": 6.584900379180908,
|
|
"epoch": 3.0058858151854033,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004111975721418074,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.14981810599565507,
|
|
"num_tokens": 60805749.0,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"entropy": 6.376362133026123,
|
|
"epoch": 3.006420889293167,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041116713717524484,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.15329998657107352,
|
|
"num_tokens": 60815701.0,
|
|
"step": 28095
|
|
},
|
|
{
|
|
"entropy": 6.529170322418213,
|
|
"epoch": 3.006955963400931,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004111366982768754,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.15083200559020044,
|
|
"num_tokens": 60826656.0,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"entropy": 6.582132577896118,
|
|
"epoch": 3.007491037508695,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00041110625544757786,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.1506844237446785,
|
|
"num_tokens": 60837839.0,
|
|
"step": 28105
|
|
},
|
|
{
|
|
"entropy": 6.529769229888916,
|
|
"epoch": 3.008026111616459,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004110758086882314,
|
|
"loss": 6.0848,
|
|
"mean_token_accuracy": 0.15559505075216293,
|
|
"num_tokens": 60848323.0,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"entropy": 6.447881984710693,
|
|
"epoch": 3.008561185724223,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000411045357999715,
|
|
"loss": 6.0465,
|
|
"mean_token_accuracy": 0.14921341314911843,
|
|
"num_tokens": 60859049.0,
|
|
"step": 28115
|
|
},
|
|
{
|
|
"entropy": 6.579263353347779,
|
|
"epoch": 3.0090962598319866,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004110149033829081,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.14390021190047264,
|
|
"num_tokens": 60870451.0,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"entropy": 6.587803697586059,
|
|
"epoch": 3.0096313339397507,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041098444483868995,
|
|
"loss": 6.1098,
|
|
"mean_token_accuracy": 0.14962228015065193,
|
|
"num_tokens": 60880530.0,
|
|
"step": 28125
|
|
},
|
|
{
|
|
"entropy": 6.48838095664978,
|
|
"epoch": 3.010166408047515,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00041095398236793996,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.14647612422704698,
|
|
"num_tokens": 60892170.0,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"entropy": 6.514112520217895,
|
|
"epoch": 3.0107014821552784,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000410923515971538,
|
|
"loss": 6.0742,
|
|
"mean_token_accuracy": 0.15082032829523087,
|
|
"num_tokens": 60902880.0,
|
|
"step": 28135
|
|
},
|
|
{
|
|
"entropy": 6.538649082183838,
|
|
"epoch": 3.0112365562630425,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004108930456503635,
|
|
"loss": 6.0645,
|
|
"mean_token_accuracy": 0.14953110963106156,
|
|
"num_tokens": 60912860.0,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"entropy": 6.497976064682007,
|
|
"epoch": 3.011771630370806,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041086257140529646,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.14841153621673583,
|
|
"num_tokens": 60923303.0,
|
|
"step": 28145
|
|
},
|
|
{
|
|
"entropy": 6.576100158691406,
|
|
"epoch": 3.0123067044785703,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004108320932372167,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.14393430203199387,
|
|
"num_tokens": 60935077.0,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"entropy": 6.610158681869507,
|
|
"epoch": 3.0128417785863344,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004108016111470044,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.1467101491987705,
|
|
"num_tokens": 60945883.0,
|
|
"step": 28155
|
|
},
|
|
{
|
|
"entropy": 6.507206439971924,
|
|
"epoch": 3.013376852694098,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004107711251355396,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.14518281817436218,
|
|
"num_tokens": 60957714.0,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"entropy": 6.464226198196411,
|
|
"epoch": 3.013911926801862,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004107406352037027,
|
|
"loss": 6.0033,
|
|
"mean_token_accuracy": 0.15091200172901154,
|
|
"num_tokens": 60968570.0,
|
|
"step": 28165
|
|
},
|
|
{
|
|
"entropy": 6.500589036941529,
|
|
"epoch": 3.014447000909626,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000410710141352374,
|
|
"loss": 6.0424,
|
|
"mean_token_accuracy": 0.15126307010650636,
|
|
"num_tokens": 60979079.0,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"entropy": 6.5955366611480715,
|
|
"epoch": 3.01498207501739,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00041067964358243404,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.1483599364757538,
|
|
"num_tokens": 60990308.0,
|
|
"step": 28175
|
|
},
|
|
{
|
|
"entropy": 6.443141984939575,
|
|
"epoch": 3.015517149125154,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004106491418947635,
|
|
"loss": 5.998,
|
|
"mean_token_accuracy": 0.1506257548928261,
|
|
"num_tokens": 61000819.0,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"entropy": 6.4671026229858395,
|
|
"epoch": 3.0160522232329177,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000410618636290243,
|
|
"loss": 6.1176,
|
|
"mean_token_accuracy": 0.1440642587840557,
|
|
"num_tokens": 61011071.0,
|
|
"step": 28185
|
|
},
|
|
{
|
|
"entropy": 6.571323823928833,
|
|
"epoch": 3.0165872973406818,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041058812676975337,
|
|
"loss": 6.0996,
|
|
"mean_token_accuracy": 0.14569891095161439,
|
|
"num_tokens": 61022499.0,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"entropy": 6.518028688430786,
|
|
"epoch": 3.0171223714484454,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004105576133341757,
|
|
"loss": 6.1012,
|
|
"mean_token_accuracy": 0.14910078942775726,
|
|
"num_tokens": 61033250.0,
|
|
"step": 28195
|
|
},
|
|
{
|
|
"entropy": 6.441509962081909,
|
|
"epoch": 3.0176574455562095,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041052709598439095,
|
|
"loss": 6.026,
|
|
"mean_token_accuracy": 0.1587045431137085,
|
|
"num_tokens": 61043222.0,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"entropy": 6.543012237548828,
|
|
"epoch": 3.0181925196639736,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004104965747212804,
|
|
"loss": 6.1276,
|
|
"mean_token_accuracy": 0.14700427353382112,
|
|
"num_tokens": 61054830.0,
|
|
"step": 28205
|
|
},
|
|
{
|
|
"entropy": 6.51511926651001,
|
|
"epoch": 3.0187275937717373,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004104660495457252,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.15078950002789498,
|
|
"num_tokens": 61066385.0,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"entropy": 6.598138236999512,
|
|
"epoch": 3.0192626678795014,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000410435520458607,
|
|
"loss": 6.2231,
|
|
"mean_token_accuracy": 0.13961489126086235,
|
|
"num_tokens": 61077434.0,
|
|
"step": 28215
|
|
},
|
|
{
|
|
"entropy": 6.564669513702393,
|
|
"epoch": 3.019797741987265,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00041040498746080714,
|
|
"loss": 6.1012,
|
|
"mean_token_accuracy": 0.14317450672388077,
|
|
"num_tokens": 61087661.0,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"entropy": 6.580402565002442,
|
|
"epoch": 3.020332816095029,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041037445055320724,
|
|
"loss": 6.1507,
|
|
"mean_token_accuracy": 0.14376429617404937,
|
|
"num_tokens": 61098364.0,
|
|
"step": 28225
|
|
},
|
|
{
|
|
"entropy": 6.498570680618286,
|
|
"epoch": 3.0208678902027932,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041034390973668916,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.14393241032958032,
|
|
"num_tokens": 61109061.0,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"entropy": 6.540396785736084,
|
|
"epoch": 3.021402964310557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004103133650121346,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.15094486773014068,
|
|
"num_tokens": 61119191.0,
|
|
"step": 28235
|
|
},
|
|
{
|
|
"entropy": 6.474926328659057,
|
|
"epoch": 3.021938038418321,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041028281638042576,
|
|
"loss": 6.0696,
|
|
"mean_token_accuracy": 0.15286141335964204,
|
|
"num_tokens": 61130494.0,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"entropy": 6.49192066192627,
|
|
"epoch": 3.022473112526085,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004102522638424445,
|
|
"loss": 6.0502,
|
|
"mean_token_accuracy": 0.15030349493026735,
|
|
"num_tokens": 61141660.0,
|
|
"step": 28245
|
|
},
|
|
{
|
|
"entropy": 6.52507643699646,
|
|
"epoch": 3.0230081866338487,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041022170739907324,
|
|
"loss": 6.0372,
|
|
"mean_token_accuracy": 0.14882655292749405,
|
|
"num_tokens": 61152864.0,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"entropy": 6.512677240371704,
|
|
"epoch": 3.023543260741613,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004101911470511941,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.1465941458940506,
|
|
"num_tokens": 61163877.0,
|
|
"step": 28255
|
|
},
|
|
{
|
|
"entropy": 6.446626138687134,
|
|
"epoch": 3.0240783348493765,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004101605827996896,
|
|
"loss": 5.998,
|
|
"mean_token_accuracy": 0.16263344138860703,
|
|
"num_tokens": 61173771.0,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"entropy": 6.44002251625061,
|
|
"epoch": 3.0246134089571406,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004101300146454423,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.15930144637823104,
|
|
"num_tokens": 61183652.0,
|
|
"step": 28265
|
|
},
|
|
{
|
|
"entropy": 6.456925344467163,
|
|
"epoch": 3.0251484830649047,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041009944258933473,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.15492360442876815,
|
|
"num_tokens": 61195119.0,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"entropy": 6.481824064254761,
|
|
"epoch": 3.0256835571726683,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00041006886663224983,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.14698936864733697,
|
|
"num_tokens": 61206736.0,
|
|
"step": 28275
|
|
},
|
|
{
|
|
"entropy": 6.565949964523315,
|
|
"epoch": 3.0262186312804324,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041003828677507037,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.14655671045184135,
|
|
"num_tokens": 61217064.0,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"entropy": 6.485136461257935,
|
|
"epoch": 3.026753705388196,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041000770301867934,
|
|
"loss": 5.9917,
|
|
"mean_token_accuracy": 0.15919136852025986,
|
|
"num_tokens": 61228520.0,
|
|
"step": 28285
|
|
},
|
|
{
|
|
"entropy": 6.543988943099976,
|
|
"epoch": 3.02728877949596,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004099771153639599,
|
|
"loss": 6.035,
|
|
"mean_token_accuracy": 0.1480492390692234,
|
|
"num_tokens": 61239835.0,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"entropy": 6.496836709976196,
|
|
"epoch": 3.0278238536037243,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004099465238117951,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.14896841645240783,
|
|
"num_tokens": 61250996.0,
|
|
"step": 28295
|
|
},
|
|
{
|
|
"entropy": 6.531451559066772,
|
|
"epoch": 3.028358927711488,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004099159283630685,
|
|
"loss": 6.1256,
|
|
"mean_token_accuracy": 0.1437664344906807,
|
|
"num_tokens": 61261384.0,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"entropy": 6.5096845626831055,
|
|
"epoch": 3.028894001819252,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040988532901866336,
|
|
"loss": 6.0308,
|
|
"mean_token_accuracy": 0.15409209728240966,
|
|
"num_tokens": 61271519.0,
|
|
"step": 28305
|
|
},
|
|
{
|
|
"entropy": 6.500550127029419,
|
|
"epoch": 3.0294290759270157,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004098547257794633,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.159528249502182,
|
|
"num_tokens": 61281769.0,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"entropy": 6.5353985786437985,
|
|
"epoch": 3.02996415003478,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040982411864635206,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.14695898145437242,
|
|
"num_tokens": 61293081.0,
|
|
"step": 28315
|
|
},
|
|
{
|
|
"entropy": 6.4287999153137205,
|
|
"epoch": 3.030499224142544,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004097935076202133,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.15660462230443956,
|
|
"num_tokens": 61303374.0,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"entropy": 6.534010362625122,
|
|
"epoch": 3.0310342982503076,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040976289270193097,
|
|
"loss": 6.0995,
|
|
"mean_token_accuracy": 0.14298609271645546,
|
|
"num_tokens": 61314700.0,
|
|
"step": 28325
|
|
},
|
|
{
|
|
"entropy": 6.524338150024414,
|
|
"epoch": 3.0315693723580717,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040973227389238897,
|
|
"loss": 6.0465,
|
|
"mean_token_accuracy": 0.15674033164978027,
|
|
"num_tokens": 61325463.0,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"entropy": 6.5287909507751465,
|
|
"epoch": 3.0321044464658353,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004097016511924716,
|
|
"loss": 6.0197,
|
|
"mean_token_accuracy": 0.15099039524793625,
|
|
"num_tokens": 61337069.0,
|
|
"step": 28335
|
|
},
|
|
{
|
|
"entropy": 6.506898880004883,
|
|
"epoch": 3.0326395205735994,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004096710246030629,
|
|
"loss": 6.0809,
|
|
"mean_token_accuracy": 0.147159381210804,
|
|
"num_tokens": 61347407.0,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"entropy": 6.4607024669647215,
|
|
"epoch": 3.0331745946813635,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040964039412504734,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.15539941936731339,
|
|
"num_tokens": 61357950.0,
|
|
"step": 28345
|
|
},
|
|
{
|
|
"entropy": 6.521305990219116,
|
|
"epoch": 3.033709668789127,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040960975975930925,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.14250787049531938,
|
|
"num_tokens": 61368394.0,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"entropy": 6.5424047946929935,
|
|
"epoch": 3.0342447428968913,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004095791215067333,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.14610308557748794,
|
|
"num_tokens": 61379763.0,
|
|
"step": 28355
|
|
},
|
|
{
|
|
"entropy": 6.495691585540771,
|
|
"epoch": 3.034779817004655,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040954847936820423,
|
|
"loss": 6.0255,
|
|
"mean_token_accuracy": 0.1478219673037529,
|
|
"num_tokens": 61390404.0,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"entropy": 6.535548353195191,
|
|
"epoch": 3.035314891112419,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040951783334460657,
|
|
"loss": 6.0374,
|
|
"mean_token_accuracy": 0.1496477760374546,
|
|
"num_tokens": 61401979.0,
|
|
"step": 28365
|
|
},
|
|
{
|
|
"entropy": 6.536256504058838,
|
|
"epoch": 3.035849965220183,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004094871834368254,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.1470283031463623,
|
|
"num_tokens": 61413306.0,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"entropy": 6.403626394271851,
|
|
"epoch": 3.036385039327947,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004094565296457457,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.16306300312280655,
|
|
"num_tokens": 61423371.0,
|
|
"step": 28375
|
|
},
|
|
{
|
|
"entropy": 6.482685852050781,
|
|
"epoch": 3.036920113435711,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00040942587197225275,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.14776561334729194,
|
|
"num_tokens": 61435163.0,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"entropy": 6.505590343475342,
|
|
"epoch": 3.037455187543475,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004093952104172315,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.15776750817894936,
|
|
"num_tokens": 61445485.0,
|
|
"step": 28385
|
|
},
|
|
{
|
|
"entropy": 6.546421766281128,
|
|
"epoch": 3.0379902616512386,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004093645449815674,
|
|
"loss": 6.0198,
|
|
"mean_token_accuracy": 0.1499396324157715,
|
|
"num_tokens": 61455765.0,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"entropy": 6.4650660991668705,
|
|
"epoch": 3.0385253357590027,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00040933387566614605,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.15483844876289368,
|
|
"num_tokens": 61467337.0,
|
|
"step": 28395
|
|
},
|
|
{
|
|
"entropy": 6.580773878097534,
|
|
"epoch": 3.0390604098667664,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040930320247185284,
|
|
"loss": 6.1444,
|
|
"mean_token_accuracy": 0.14329703152179718,
|
|
"num_tokens": 61478568.0,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"entropy": 6.602982854843139,
|
|
"epoch": 3.0395954839745305,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004092725253995736,
|
|
"loss": 6.1167,
|
|
"mean_token_accuracy": 0.14540349394083024,
|
|
"num_tokens": 61488456.0,
|
|
"step": 28405
|
|
},
|
|
{
|
|
"entropy": 6.5378257751464846,
|
|
"epoch": 3.0401305580822946,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040924184445019404,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.15205085426568984,
|
|
"num_tokens": 61499996.0,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"entropy": 6.543498611450195,
|
|
"epoch": 3.0406656321900583,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040921115962460003,
|
|
"loss": 6.0397,
|
|
"mean_token_accuracy": 0.14648721143603324,
|
|
"num_tokens": 61511271.0,
|
|
"step": 28415
|
|
},
|
|
{
|
|
"entropy": 6.487405490875244,
|
|
"epoch": 3.0412007062978224,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004091804709236777,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.1449355736374855,
|
|
"num_tokens": 61522284.0,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"entropy": 6.450152254104614,
|
|
"epoch": 3.041735780405586,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004091497783483131,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.15429858565330506,
|
|
"num_tokens": 61532494.0,
|
|
"step": 28425
|
|
},
|
|
{
|
|
"entropy": 6.451062297821045,
|
|
"epoch": 3.04227085451335,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004091190818993925,
|
|
"loss": 6.0514,
|
|
"mean_token_accuracy": 0.14379365593194962,
|
|
"num_tokens": 61543017.0,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"entropy": 6.517848110198974,
|
|
"epoch": 3.042805928621114,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004090883815778023,
|
|
"loss": 6.1035,
|
|
"mean_token_accuracy": 0.1501762665808201,
|
|
"num_tokens": 61552984.0,
|
|
"step": 28435
|
|
},
|
|
{
|
|
"entropy": 6.514907026290894,
|
|
"epoch": 3.043341002728878,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004090576773844288,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.15136003643274307,
|
|
"num_tokens": 61564045.0,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"entropy": 6.49694972038269,
|
|
"epoch": 3.043876076836642,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040902696932015886,
|
|
"loss": 6.0593,
|
|
"mean_token_accuracy": 0.1518414504826069,
|
|
"num_tokens": 61575369.0,
|
|
"step": 28445
|
|
},
|
|
{
|
|
"entropy": 6.53823618888855,
|
|
"epoch": 3.0444111509444056,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040899625738587895,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.14599212780594825,
|
|
"num_tokens": 61586221.0,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"entropy": 6.543770742416382,
|
|
"epoch": 3.0449462250521697,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00040896554158247587,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.14488775581121444,
|
|
"num_tokens": 61597091.0,
|
|
"step": 28455
|
|
},
|
|
{
|
|
"entropy": 6.488984632492065,
|
|
"epoch": 3.045481299159934,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040893482191083677,
|
|
"loss": 6.0975,
|
|
"mean_token_accuracy": 0.14782916903495788,
|
|
"num_tokens": 61608026.0,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"entropy": 6.5420385837554935,
|
|
"epoch": 3.0460163732676975,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040890409837184835,
|
|
"loss": 6.115,
|
|
"mean_token_accuracy": 0.1417987160384655,
|
|
"num_tokens": 61620078.0,
|
|
"step": 28465
|
|
},
|
|
{
|
|
"entropy": 6.436668586730957,
|
|
"epoch": 3.0465514473754616,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004088733709663979,
|
|
"loss": 6.045,
|
|
"mean_token_accuracy": 0.1447290599346161,
|
|
"num_tokens": 61630839.0,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"entropy": 6.463761997222901,
|
|
"epoch": 3.0470865214832252,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004088426396953728,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.15730979293584824,
|
|
"num_tokens": 61640927.0,
|
|
"step": 28475
|
|
},
|
|
{
|
|
"entropy": 6.506276369094849,
|
|
"epoch": 3.0476215955909893,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004088119045596602,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.15401624590158464,
|
|
"num_tokens": 61650631.0,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"entropy": 6.5308445453643795,
|
|
"epoch": 3.0481566696987534,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004087811655601477,
|
|
"loss": 6.1249,
|
|
"mean_token_accuracy": 0.1444139674305916,
|
|
"num_tokens": 61661493.0,
|
|
"step": 28485
|
|
},
|
|
{
|
|
"entropy": 6.558855962753296,
|
|
"epoch": 3.048691743806517,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00040875042269772284,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.14677533954381944,
|
|
"num_tokens": 61673116.0,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"entropy": 6.503303003311157,
|
|
"epoch": 3.049226817914281,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00040871967597327333,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.14918859750032426,
|
|
"num_tokens": 61683471.0,
|
|
"step": 28495
|
|
},
|
|
{
|
|
"entropy": 6.465893077850342,
|
|
"epoch": 3.049761892022045,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00040868892538768693,
|
|
"loss": 6.157,
|
|
"mean_token_accuracy": 0.150797551125288,
|
|
"num_tokens": 61693264.0,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"entropy": 6.45642318725586,
|
|
"epoch": 3.050296966129809,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004086581709418516,
|
|
"loss": 6.0163,
|
|
"mean_token_accuracy": 0.15248336941003798,
|
|
"num_tokens": 61703566.0,
|
|
"step": 28505
|
|
},
|
|
{
|
|
"entropy": 6.5560346126556395,
|
|
"epoch": 3.050832040237573,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040862741263665537,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.15292144268751146,
|
|
"num_tokens": 61714981.0,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"entropy": 6.465506982803345,
|
|
"epoch": 3.0513671143453367,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00040859665047298635,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.15493055433034897,
|
|
"num_tokens": 61726036.0,
|
|
"step": 28515
|
|
},
|
|
{
|
|
"entropy": 6.5165924549102785,
|
|
"epoch": 3.051902188453101,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004085658844517329,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.14532904401421548,
|
|
"num_tokens": 61736614.0,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"entropy": 6.430649995803833,
|
|
"epoch": 3.052437262560865,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004085351145737832,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.15570746958255768,
|
|
"num_tokens": 61746817.0,
|
|
"step": 28525
|
|
},
|
|
{
|
|
"entropy": 6.418033123016357,
|
|
"epoch": 3.0529723366686286,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004085043408400259,
|
|
"loss": 5.9114,
|
|
"mean_token_accuracy": 0.15977892130613328,
|
|
"num_tokens": 61757714.0,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"entropy": 6.47765793800354,
|
|
"epoch": 3.0535074107763926,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004084735632513495,
|
|
"loss": 6.0445,
|
|
"mean_token_accuracy": 0.1542748212814331,
|
|
"num_tokens": 61768719.0,
|
|
"step": 28535
|
|
},
|
|
{
|
|
"entropy": 6.500941324234009,
|
|
"epoch": 3.0540424848841563,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040844278180864274,
|
|
"loss": 6.0613,
|
|
"mean_token_accuracy": 0.14594235196709632,
|
|
"num_tokens": 61778942.0,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"entropy": 6.435892391204834,
|
|
"epoch": 3.0545775589919204,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004084119965127944,
|
|
"loss": 6.002,
|
|
"mean_token_accuracy": 0.15690215229988097,
|
|
"num_tokens": 61789427.0,
|
|
"step": 28545
|
|
},
|
|
{
|
|
"entropy": 6.463628911972046,
|
|
"epoch": 3.0551126330996845,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004083812073646933,
|
|
"loss": 6.0083,
|
|
"mean_token_accuracy": 0.1505459651350975,
|
|
"num_tokens": 61799702.0,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"entropy": 6.47976713180542,
|
|
"epoch": 3.055647707207448,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040835041436522874,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.16514344960451127,
|
|
"num_tokens": 61809346.0,
|
|
"step": 28555
|
|
},
|
|
{
|
|
"entropy": 6.517128419876099,
|
|
"epoch": 3.0561827813152123,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040831961751528964,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.15050550550222397,
|
|
"num_tokens": 61819762.0,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"entropy": 6.509982776641846,
|
|
"epoch": 3.056717855422976,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040828881681576534,
|
|
"loss": 6.0984,
|
|
"mean_token_accuracy": 0.14066144973039627,
|
|
"num_tokens": 61830624.0,
|
|
"step": 28565
|
|
},
|
|
{
|
|
"entropy": 6.564533758163452,
|
|
"epoch": 3.05725292953074,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004082580122675451,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.15381218791007994,
|
|
"num_tokens": 61841684.0,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"entropy": 6.443882179260254,
|
|
"epoch": 3.057788003638504,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040822720387151856,
|
|
"loss": 6.0312,
|
|
"mean_token_accuracy": 0.15979851484298707,
|
|
"num_tokens": 61852239.0,
|
|
"step": 28575
|
|
},
|
|
{
|
|
"entropy": 6.517426347732544,
|
|
"epoch": 3.0583230777462678,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004081963916285752,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.14088232144713403,
|
|
"num_tokens": 61863014.0,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"entropy": 6.525431394577026,
|
|
"epoch": 3.058858151854032,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040816557553960474,
|
|
"loss": 5.9696,
|
|
"mean_token_accuracy": 0.15567672103643418,
|
|
"num_tokens": 61873819.0,
|
|
"step": 28585
|
|
},
|
|
{
|
|
"entropy": 6.484772777557373,
|
|
"epoch": 3.0593932259617955,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040813475560549705,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.15466258823871612,
|
|
"num_tokens": 61885866.0,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"entropy": 6.403206300735474,
|
|
"epoch": 3.0599283000695596,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000408103931827142,
|
|
"loss": 5.9835,
|
|
"mean_token_accuracy": 0.15448476672172545,
|
|
"num_tokens": 61895836.0,
|
|
"step": 28595
|
|
},
|
|
{
|
|
"entropy": 6.377604055404663,
|
|
"epoch": 3.0604633741773237,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004080731042054296,
|
|
"loss": 5.8875,
|
|
"mean_token_accuracy": 0.16803586035966872,
|
|
"num_tokens": 61906284.0,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"entropy": 6.44705719947815,
|
|
"epoch": 3.0609984482850874,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00040804227274125,
|
|
"loss": 6.0486,
|
|
"mean_token_accuracy": 0.15157301649451255,
|
|
"num_tokens": 61917024.0,
|
|
"step": 28605
|
|
},
|
|
{
|
|
"entropy": 6.538745307922364,
|
|
"epoch": 3.0615335223928515,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00040801143743549343,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.1494167998433113,
|
|
"num_tokens": 61927631.0,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"entropy": 6.454978561401367,
|
|
"epoch": 3.062068596500615,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040798059828905036,
|
|
"loss": 6.0479,
|
|
"mean_token_accuracy": 0.1520066276192665,
|
|
"num_tokens": 61938443.0,
|
|
"step": 28615
|
|
},
|
|
{
|
|
"entropy": 6.425399303436279,
|
|
"epoch": 3.0626036706083792,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004079497553028112,
|
|
"loss": 5.9999,
|
|
"mean_token_accuracy": 0.15264809206128122,
|
|
"num_tokens": 61949148.0,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"entropy": 6.5016858100891115,
|
|
"epoch": 3.0631387447161433,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004079189084776665,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.15724919438362123,
|
|
"num_tokens": 61959052.0,
|
|
"step": 28625
|
|
},
|
|
{
|
|
"entropy": 6.491433382034302,
|
|
"epoch": 3.063673818823907,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000407888057814507,
|
|
"loss": 6.0072,
|
|
"mean_token_accuracy": 0.15143886506557463,
|
|
"num_tokens": 61969906.0,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"entropy": 6.519071388244629,
|
|
"epoch": 3.064208892931671,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040785720331422355,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.14516765847802163,
|
|
"num_tokens": 61981511.0,
|
|
"step": 28635
|
|
},
|
|
{
|
|
"entropy": 6.52302508354187,
|
|
"epoch": 3.064743967039435,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000407826344977707,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.1501475214958191,
|
|
"num_tokens": 61993404.0,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"entropy": 6.497239351272583,
|
|
"epoch": 3.065279041147199,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004077954828058484,
|
|
"loss": 6.0977,
|
|
"mean_token_accuracy": 0.14948202520608903,
|
|
"num_tokens": 62004216.0,
|
|
"step": 28645
|
|
},
|
|
{
|
|
"entropy": 6.518730640411377,
|
|
"epoch": 3.065814115254963,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004077646167995389,
|
|
"loss": 6.1073,
|
|
"mean_token_accuracy": 0.14457226246595384,
|
|
"num_tokens": 62014841.0,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"entropy": 6.505550956726074,
|
|
"epoch": 3.0663491893627266,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00040773374695966976,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.1528017796576023,
|
|
"num_tokens": 62025024.0,
|
|
"step": 28655
|
|
},
|
|
{
|
|
"entropy": 6.441663980484009,
|
|
"epoch": 3.0668842634704907,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004077028732871323,
|
|
"loss": 6.0692,
|
|
"mean_token_accuracy": 0.15004220455884934,
|
|
"num_tokens": 62037892.0,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"entropy": 6.539187097549439,
|
|
"epoch": 3.067419337578255,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040767199578281793,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.15077619403600692,
|
|
"num_tokens": 62048226.0,
|
|
"step": 28665
|
|
},
|
|
{
|
|
"entropy": 6.5699005126953125,
|
|
"epoch": 3.0679544116860185,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040764111444761847,
|
|
"loss": 6.1157,
|
|
"mean_token_accuracy": 0.145875883102417,
|
|
"num_tokens": 62059339.0,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"entropy": 6.533188819885254,
|
|
"epoch": 3.0684894857937826,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040761022928242544,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.15184640362858773,
|
|
"num_tokens": 62069008.0,
|
|
"step": 28675
|
|
},
|
|
{
|
|
"entropy": 6.490911674499512,
|
|
"epoch": 3.069024559901546,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040757934028813066,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.15325079411268233,
|
|
"num_tokens": 62079405.0,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"entropy": 6.427926158905029,
|
|
"epoch": 3.0695596340093103,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000407548447465626,
|
|
"loss": 6.0007,
|
|
"mean_token_accuracy": 0.15029284954071045,
|
|
"num_tokens": 62089928.0,
|
|
"step": 28685
|
|
},
|
|
{
|
|
"entropy": 6.452823543548584,
|
|
"epoch": 3.0700947081170744,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004075175508158036,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.1502634659409523,
|
|
"num_tokens": 62100956.0,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"entropy": 6.5439704895019535,
|
|
"epoch": 3.070629782224838,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040748665033955557,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.15566644668579102,
|
|
"num_tokens": 62111673.0,
|
|
"step": 28695
|
|
},
|
|
{
|
|
"entropy": 6.536715650558472,
|
|
"epoch": 3.071164856332602,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004074557460377741,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.14945016354322432,
|
|
"num_tokens": 62122273.0,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"entropy": 6.459893417358399,
|
|
"epoch": 3.071699930440366,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004074248379113516,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.1459229752421379,
|
|
"num_tokens": 62132836.0,
|
|
"step": 28705
|
|
},
|
|
{
|
|
"entropy": 6.573007726669312,
|
|
"epoch": 3.07223500454813,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004073939259611805,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.14548272117972375,
|
|
"num_tokens": 62144228.0,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"entropy": 6.458516788482666,
|
|
"epoch": 3.072770078655894,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004073630101881534,
|
|
"loss": 6.0158,
|
|
"mean_token_accuracy": 0.1547217398881912,
|
|
"num_tokens": 62155126.0,
|
|
"step": 28715
|
|
},
|
|
{
|
|
"entropy": 6.484618902206421,
|
|
"epoch": 3.0733051527636577,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004073320905931629,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.1487065553665161,
|
|
"num_tokens": 62165973.0,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"entropy": 6.507214736938477,
|
|
"epoch": 3.0738402268714218,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004073011671771019,
|
|
"loss": 6.0513,
|
|
"mean_token_accuracy": 0.15229150354862214,
|
|
"num_tokens": 62176258.0,
|
|
"step": 28725
|
|
},
|
|
{
|
|
"entropy": 6.491588497161866,
|
|
"epoch": 3.0743753009791854,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040727023994086345,
|
|
"loss": 6.1058,
|
|
"mean_token_accuracy": 0.14715265333652497,
|
|
"num_tokens": 62186078.0,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"entropy": 6.525811862945557,
|
|
"epoch": 3.0749103750869495,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004072393088853402,
|
|
"loss": 6.0783,
|
|
"mean_token_accuracy": 0.15151109769940377,
|
|
"num_tokens": 62197951.0,
|
|
"step": 28735
|
|
},
|
|
{
|
|
"entropy": 6.557224416732788,
|
|
"epoch": 3.0754454491947136,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040720837401142556,
|
|
"loss": 6.0434,
|
|
"mean_token_accuracy": 0.14970873445272445,
|
|
"num_tokens": 62210187.0,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"entropy": 6.546493053436279,
|
|
"epoch": 3.0759805233024773,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004071774353200128,
|
|
"loss": 6.1295,
|
|
"mean_token_accuracy": 0.14318096041679382,
|
|
"num_tokens": 62220561.0,
|
|
"step": 28745
|
|
},
|
|
{
|
|
"entropy": 6.509161567687988,
|
|
"epoch": 3.0765155974102414,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000407146492811995,
|
|
"loss": 6.1004,
|
|
"mean_token_accuracy": 0.1409086599946022,
|
|
"num_tokens": 62232378.0,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"entropy": 6.532620239257812,
|
|
"epoch": 3.077050671518005,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004071155464882659,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.1451079234480858,
|
|
"num_tokens": 62244823.0,
|
|
"step": 28755
|
|
},
|
|
{
|
|
"entropy": 6.464087295532226,
|
|
"epoch": 3.077585745625769,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004070845963497189,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.15279067382216455,
|
|
"num_tokens": 62255070.0,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"entropy": 6.5138544082641605,
|
|
"epoch": 3.0781208197335332,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004070536423972478,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.14397402703762055,
|
|
"num_tokens": 62267081.0,
|
|
"step": 28765
|
|
},
|
|
{
|
|
"entropy": 6.589392757415771,
|
|
"epoch": 3.078655893841297,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004070226846317463,
|
|
"loss": 6.125,
|
|
"mean_token_accuracy": 0.14922758787870408,
|
|
"num_tokens": 62277512.0,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"entropy": 6.574430179595947,
|
|
"epoch": 3.079190967949061,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00040699172305410833,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.15728534758090973,
|
|
"num_tokens": 62287827.0,
|
|
"step": 28775
|
|
},
|
|
{
|
|
"entropy": 6.492033243179321,
|
|
"epoch": 3.0797260420568247,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040696075766522797,
|
|
"loss": 6.092,
|
|
"mean_token_accuracy": 0.14472799003124237,
|
|
"num_tokens": 62299977.0,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"entropy": 6.551619577407837,
|
|
"epoch": 3.0802611161645888,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004069297884659992,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.15543570816516877,
|
|
"num_tokens": 62310157.0,
|
|
"step": 28785
|
|
},
|
|
{
|
|
"entropy": 6.453998756408692,
|
|
"epoch": 3.080796190272353,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004068988154573163,
|
|
"loss": 6.0042,
|
|
"mean_token_accuracy": 0.15844295769929886,
|
|
"num_tokens": 62320420.0,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"entropy": 6.450648641586303,
|
|
"epoch": 3.0813312643801165,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00040686783864007367,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.1470397189259529,
|
|
"num_tokens": 62330551.0,
|
|
"step": 28795
|
|
},
|
|
{
|
|
"entropy": 6.620399856567383,
|
|
"epoch": 3.0818663384878806,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004068368580151658,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.14810173884034156,
|
|
"num_tokens": 62341131.0,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"entropy": 6.556761884689331,
|
|
"epoch": 3.0824014125956447,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004068058735834871,
|
|
"loss": 6.1453,
|
|
"mean_token_accuracy": 0.15064699500799178,
|
|
"num_tokens": 62352432.0,
|
|
"step": 28805
|
|
},
|
|
{
|
|
"entropy": 6.585370349884033,
|
|
"epoch": 3.0829364867034084,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004067748853459323,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.14073626101016998,
|
|
"num_tokens": 62364029.0,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"entropy": 6.556416606903076,
|
|
"epoch": 3.0834715608111725,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004067438933033963,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.14779388681054115,
|
|
"num_tokens": 62373804.0,
|
|
"step": 28815
|
|
},
|
|
{
|
|
"entropy": 6.383665227890015,
|
|
"epoch": 3.084006634918936,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040671289745677387,
|
|
"loss": 5.938,
|
|
"mean_token_accuracy": 0.16318692341446878,
|
|
"num_tokens": 62384400.0,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"entropy": 6.530467224121094,
|
|
"epoch": 3.0845417090267,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040668189780695995,
|
|
"loss": 6.1338,
|
|
"mean_token_accuracy": 0.1427229031920433,
|
|
"num_tokens": 62395228.0,
|
|
"step": 28825
|
|
},
|
|
{
|
|
"entropy": 6.545812940597534,
|
|
"epoch": 3.0850767831344643,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004066508943548498,
|
|
"loss": 6.0914,
|
|
"mean_token_accuracy": 0.15024547576904296,
|
|
"num_tokens": 62405458.0,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"entropy": 6.589110469818115,
|
|
"epoch": 3.085611857242228,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00040661988710133856,
|
|
"loss": 6.1247,
|
|
"mean_token_accuracy": 0.15524197444319726,
|
|
"num_tokens": 62416838.0,
|
|
"step": 28835
|
|
},
|
|
{
|
|
"entropy": 6.454787826538086,
|
|
"epoch": 3.086146931349992,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00040658887604732154,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.15009115859866143,
|
|
"num_tokens": 62427680.0,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"entropy": 6.441393661499023,
|
|
"epoch": 3.0866820054577557,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004065578611936943,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.15147725939750672,
|
|
"num_tokens": 62438785.0,
|
|
"step": 28845
|
|
},
|
|
{
|
|
"entropy": 6.551818084716797,
|
|
"epoch": 3.08721707956552,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040652684254135227,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.14579840153455734,
|
|
"num_tokens": 62450362.0,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"entropy": 6.616143417358399,
|
|
"epoch": 3.087752153673284,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004064958200911911,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.15035369694232942,
|
|
"num_tokens": 62461962.0,
|
|
"step": 28855
|
|
},
|
|
{
|
|
"entropy": 6.4623950004577635,
|
|
"epoch": 3.0882872277810476,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004064647938441066,
|
|
"loss": 6.0472,
|
|
"mean_token_accuracy": 0.15688687562942505,
|
|
"num_tokens": 62473290.0,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"entropy": 6.563885498046875,
|
|
"epoch": 3.0888223018888117,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00040643376380099466,
|
|
"loss": 6.2639,
|
|
"mean_token_accuracy": 0.13688580095767974,
|
|
"num_tokens": 62484219.0,
|
|
"step": 28865
|
|
},
|
|
{
|
|
"entropy": 6.508276510238647,
|
|
"epoch": 3.0893573759965753,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004064027299627514,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.1466577023267746,
|
|
"num_tokens": 62494542.0,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"entropy": 6.5368468284606935,
|
|
"epoch": 3.0898924501043394,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040637169233027264,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.15175143331289292,
|
|
"num_tokens": 62505351.0,
|
|
"step": 28875
|
|
},
|
|
{
|
|
"entropy": 6.437480640411377,
|
|
"epoch": 3.0904275242121035,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040634065090445473,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.1587792605161667,
|
|
"num_tokens": 62515848.0,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"entropy": 6.493168020248413,
|
|
"epoch": 3.090962598319867,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000406309605686194,
|
|
"loss": 6.1626,
|
|
"mean_token_accuracy": 0.13875755444169044,
|
|
"num_tokens": 62527042.0,
|
|
"step": 28885
|
|
},
|
|
{
|
|
"entropy": 6.564637613296509,
|
|
"epoch": 3.0914976724276313,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004062785566763869,
|
|
"loss": 6.1074,
|
|
"mean_token_accuracy": 0.14599116891622543,
|
|
"num_tokens": 62537830.0,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"entropy": 6.607158613204956,
|
|
"epoch": 3.092032746535395,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004062475038759298,
|
|
"loss": 6.1294,
|
|
"mean_token_accuracy": 0.14160319566726684,
|
|
"num_tokens": 62548391.0,
|
|
"step": 28895
|
|
},
|
|
{
|
|
"entropy": 6.504818534851074,
|
|
"epoch": 3.092567820643159,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004062164472857196,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.15225068479776382,
|
|
"num_tokens": 62557832.0,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"entropy": 6.457401752471924,
|
|
"epoch": 3.093102894750923,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040618538690665286,
|
|
"loss": 6.1032,
|
|
"mean_token_accuracy": 0.14935608357191085,
|
|
"num_tokens": 62568451.0,
|
|
"step": 28905
|
|
},
|
|
{
|
|
"entropy": 6.423559236526489,
|
|
"epoch": 3.093637968858687,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040615432273962657,
|
|
"loss": 5.9426,
|
|
"mean_token_accuracy": 0.1633502498269081,
|
|
"num_tokens": 62579230.0,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"entropy": 6.481175279617309,
|
|
"epoch": 3.094173042966451,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004061232547855376,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.14939259141683578,
|
|
"num_tokens": 62589853.0,
|
|
"step": 28915
|
|
},
|
|
{
|
|
"entropy": 6.572587966918945,
|
|
"epoch": 3.094708117074215,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004060921830452831,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.15477900728583335,
|
|
"num_tokens": 62600929.0,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"entropy": 6.421529817581177,
|
|
"epoch": 3.0952431911819787,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004060611075197601,
|
|
"loss": 5.9801,
|
|
"mean_token_accuracy": 0.1568751499056816,
|
|
"num_tokens": 62611583.0,
|
|
"step": 28925
|
|
},
|
|
{
|
|
"entropy": 6.56083607673645,
|
|
"epoch": 3.0957782652897428,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004060300282098661,
|
|
"loss": 6.0984,
|
|
"mean_token_accuracy": 0.15114142447710038,
|
|
"num_tokens": 62622609.0,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"entropy": 6.552394151687622,
|
|
"epoch": 3.0963133393975064,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040599894511649854,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.13534218892455102,
|
|
"num_tokens": 62633859.0,
|
|
"step": 28935
|
|
},
|
|
{
|
|
"entropy": 6.530284070968628,
|
|
"epoch": 3.0968484135052705,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004059678582405548,
|
|
"loss": 6.0391,
|
|
"mean_token_accuracy": 0.15249624401330947,
|
|
"num_tokens": 62644409.0,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"entropy": 6.5743506908416744,
|
|
"epoch": 3.0973834876130346,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004059367675829325,
|
|
"loss": 6.0802,
|
|
"mean_token_accuracy": 0.15416293144226073,
|
|
"num_tokens": 62653703.0,
|
|
"step": 28945
|
|
},
|
|
{
|
|
"entropy": 6.42941427230835,
|
|
"epoch": 3.0979185617207983,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040590567314452945,
|
|
"loss": 6.0387,
|
|
"mean_token_accuracy": 0.14798267632722856,
|
|
"num_tokens": 62664413.0,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"entropy": 6.431059217453003,
|
|
"epoch": 3.0984536358285624,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040587457492624357,
|
|
"loss": 5.9558,
|
|
"mean_token_accuracy": 0.15953681021928787,
|
|
"num_tokens": 62674520.0,
|
|
"step": 28955
|
|
},
|
|
{
|
|
"entropy": 6.555852460861206,
|
|
"epoch": 3.098988709936326,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040584347292897265,
|
|
"loss": 6.1182,
|
|
"mean_token_accuracy": 0.14552309811115266,
|
|
"num_tokens": 62685584.0,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"entropy": 6.50615086555481,
|
|
"epoch": 3.09952378404409,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004058123671536149,
|
|
"loss": 5.9839,
|
|
"mean_token_accuracy": 0.15618600100278854,
|
|
"num_tokens": 62695999.0,
|
|
"step": 28965
|
|
},
|
|
{
|
|
"entropy": 6.519012451171875,
|
|
"epoch": 3.1000588581518542,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004057812576010684,
|
|
"loss": 6.1014,
|
|
"mean_token_accuracy": 0.14741620644927025,
|
|
"num_tokens": 62706486.0,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"entropy": 6.496386528015137,
|
|
"epoch": 3.100593932259618,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040575014427223145,
|
|
"loss": 6.0108,
|
|
"mean_token_accuracy": 0.1580100253224373,
|
|
"num_tokens": 62716667.0,
|
|
"step": 28975
|
|
},
|
|
{
|
|
"entropy": 6.469983720779419,
|
|
"epoch": 3.101129006367382,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00040571902716800246,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.15117700397968292,
|
|
"num_tokens": 62728101.0,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"entropy": 6.4798651218414305,
|
|
"epoch": 3.1016640804751456,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040568790628927996,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.15146149396896363,
|
|
"num_tokens": 62739796.0,
|
|
"step": 28985
|
|
},
|
|
{
|
|
"entropy": 6.54625129699707,
|
|
"epoch": 3.1021991545829097,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00040565678163696246,
|
|
"loss": 6.0427,
|
|
"mean_token_accuracy": 0.14926021844148635,
|
|
"num_tokens": 62751270.0,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"entropy": 6.592175054550171,
|
|
"epoch": 3.102734228690674,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004056256532119488,
|
|
"loss": 6.1161,
|
|
"mean_token_accuracy": 0.14225017353892327,
|
|
"num_tokens": 62761890.0,
|
|
"step": 28995
|
|
},
|
|
{
|
|
"entropy": 6.550548839569092,
|
|
"epoch": 3.1032693027984375,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004055945210151378,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.15361751466989518,
|
|
"num_tokens": 62773177.0,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"entropy": 6.502053213119507,
|
|
"epoch": 3.1038043769062016,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004055633850474283,
|
|
"loss": 6.0936,
|
|
"mean_token_accuracy": 0.14649026691913605,
|
|
"num_tokens": 62784511.0,
|
|
"step": 29005
|
|
},
|
|
{
|
|
"entropy": 6.528551912307739,
|
|
"epoch": 3.1043394510139652,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004055322453097194,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.14491941332817077,
|
|
"num_tokens": 62795618.0,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"entropy": 6.588932752609253,
|
|
"epoch": 3.1048745251217293,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040550110180291024,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.14209678918123245,
|
|
"num_tokens": 62805936.0,
|
|
"step": 29015
|
|
},
|
|
{
|
|
"entropy": 6.600106239318848,
|
|
"epoch": 3.1054095992294934,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004054699545279001,
|
|
"loss": 6.1029,
|
|
"mean_token_accuracy": 0.14633565545082092,
|
|
"num_tokens": 62815511.0,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"entropy": 6.476437282562256,
|
|
"epoch": 3.105944673337257,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004054388034855884,
|
|
"loss": 6.1213,
|
|
"mean_token_accuracy": 0.14530841261148453,
|
|
"num_tokens": 62826382.0,
|
|
"step": 29025
|
|
},
|
|
{
|
|
"entropy": 6.548928165435791,
|
|
"epoch": 3.106479747445021,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040540764867687463,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.14133374392986298,
|
|
"num_tokens": 62836546.0,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"entropy": 6.605242013931274,
|
|
"epoch": 3.107014821552785,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040537649010265826,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.1463100716471672,
|
|
"num_tokens": 62847407.0,
|
|
"step": 29035
|
|
},
|
|
{
|
|
"entropy": 6.570791387557984,
|
|
"epoch": 3.107549895660549,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000405345327763839,
|
|
"loss": 6.1409,
|
|
"mean_token_accuracy": 0.1454748883843422,
|
|
"num_tokens": 62857139.0,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"entropy": 6.42989068031311,
|
|
"epoch": 3.108084969768313,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00040531416166131686,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.15575001239776612,
|
|
"num_tokens": 62867674.0,
|
|
"step": 29045
|
|
},
|
|
{
|
|
"entropy": 6.494722986221314,
|
|
"epoch": 3.1086200438760767,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040528299179599155,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.15112748146057128,
|
|
"num_tokens": 62878204.0,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"entropy": 6.49635648727417,
|
|
"epoch": 3.109155117983841,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004052518181687631,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.14706916660070418,
|
|
"num_tokens": 62888737.0,
|
|
"step": 29055
|
|
},
|
|
{
|
|
"entropy": 6.475020980834961,
|
|
"epoch": 3.1096901920916045,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040522064078053174,
|
|
"loss": 5.9964,
|
|
"mean_token_accuracy": 0.1613493099808693,
|
|
"num_tokens": 62899481.0,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"entropy": 6.609436750411987,
|
|
"epoch": 3.1102252661993686,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040518945963219767,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.1440240576863289,
|
|
"num_tokens": 62910298.0,
|
|
"step": 29065
|
|
},
|
|
{
|
|
"entropy": 6.494198322296143,
|
|
"epoch": 3.1107603403071327,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040515827472466134,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.1555139347910881,
|
|
"num_tokens": 62921132.0,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"entropy": 6.444632339477539,
|
|
"epoch": 3.1112954144148963,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004051270860588229,
|
|
"loss": 6.096,
|
|
"mean_token_accuracy": 0.15399683862924576,
|
|
"num_tokens": 62932107.0,
|
|
"step": 29075
|
|
},
|
|
{
|
|
"entropy": 6.4593157291412355,
|
|
"epoch": 3.1118304885226604,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004050958936355834,
|
|
"loss": 6.0137,
|
|
"mean_token_accuracy": 0.1491433337330818,
|
|
"num_tokens": 62943177.0,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"entropy": 6.510589933395385,
|
|
"epoch": 3.1123655626304245,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00040506469745584314,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.1547088220715523,
|
|
"num_tokens": 62954017.0,
|
|
"step": 29085
|
|
},
|
|
{
|
|
"entropy": 6.529780721664428,
|
|
"epoch": 3.112900636738188,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040503349752050294,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.15126141607761384,
|
|
"num_tokens": 62964352.0,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"entropy": 6.433767986297608,
|
|
"epoch": 3.1134357108459523,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004050022938304639,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.15574109107255935,
|
|
"num_tokens": 62974414.0,
|
|
"step": 29095
|
|
},
|
|
{
|
|
"entropy": 6.511135911941528,
|
|
"epoch": 3.113970784953716,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004049710863866268,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.1449720822274685,
|
|
"num_tokens": 62985874.0,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"entropy": 6.557854413986206,
|
|
"epoch": 3.11450585906148,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004049398751898929,
|
|
"loss": 6.0757,
|
|
"mean_token_accuracy": 0.14866045564413072,
|
|
"num_tokens": 62996553.0,
|
|
"step": 29105
|
|
},
|
|
{
|
|
"entropy": 6.506796169281006,
|
|
"epoch": 3.115040933169244,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004049086602411633,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.1446715459227562,
|
|
"num_tokens": 63008094.0,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"entropy": 6.501681661605835,
|
|
"epoch": 3.115576007277008,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040487744154133945,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.14343521147966384,
|
|
"num_tokens": 63018517.0,
|
|
"step": 29115
|
|
},
|
|
{
|
|
"entropy": 6.532865524291992,
|
|
"epoch": 3.116111081384772,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040484621909132277,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.1513042613863945,
|
|
"num_tokens": 63029759.0,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"entropy": 6.5227500915527346,
|
|
"epoch": 3.1166461554925355,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004048149928920146,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.1472659446299076,
|
|
"num_tokens": 63039862.0,
|
|
"step": 29125
|
|
},
|
|
{
|
|
"entropy": 6.526119422912598,
|
|
"epoch": 3.1171812296002996,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004047837629443169,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.14831400215625762,
|
|
"num_tokens": 63050298.0,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"entropy": 6.3182861328125,
|
|
"epoch": 3.1177163037080637,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040475252924913126,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.1819575235247612,
|
|
"num_tokens": 63061280.0,
|
|
"step": 29135
|
|
},
|
|
{
|
|
"entropy": 6.5088153839111325,
|
|
"epoch": 3.1182513778158274,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004047212918073595,
|
|
"loss": 6.0856,
|
|
"mean_token_accuracy": 0.15590523779392243,
|
|
"num_tokens": 63071188.0,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"entropy": 6.504253244400024,
|
|
"epoch": 3.1187864519235915,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040469005061990364,
|
|
"loss": 6.0457,
|
|
"mean_token_accuracy": 0.15336413383483888,
|
|
"num_tokens": 63081804.0,
|
|
"step": 29145
|
|
},
|
|
{
|
|
"entropy": 6.481606531143188,
|
|
"epoch": 3.119321526031355,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004046588056876659,
|
|
"loss": 6.1057,
|
|
"mean_token_accuracy": 0.14666095227003098,
|
|
"num_tokens": 63092671.0,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"entropy": 6.583978366851807,
|
|
"epoch": 3.1198566001391193,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040462755701154834,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.14543539956212043,
|
|
"num_tokens": 63104867.0,
|
|
"step": 29155
|
|
},
|
|
{
|
|
"entropy": 6.48559079170227,
|
|
"epoch": 3.1203916742468834,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040459630459245327,
|
|
"loss": 6.006,
|
|
"mean_token_accuracy": 0.15237291008234025,
|
|
"num_tokens": 63115491.0,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"entropy": 6.39586615562439,
|
|
"epoch": 3.120926748354647,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004045650484312831,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.1561280757188797,
|
|
"num_tokens": 63127240.0,
|
|
"step": 29165
|
|
},
|
|
{
|
|
"entropy": 6.483794069290161,
|
|
"epoch": 3.121461822462411,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004045337885289404,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.15079566985368728,
|
|
"num_tokens": 63137180.0,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"entropy": 6.520535039901733,
|
|
"epoch": 3.1219968965701748,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004045025248863277,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.14717809706926346,
|
|
"num_tokens": 63147772.0,
|
|
"step": 29175
|
|
},
|
|
{
|
|
"entropy": 6.529476118087769,
|
|
"epoch": 3.122531970677939,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004044712575043479,
|
|
"loss": 6.0693,
|
|
"mean_token_accuracy": 0.15370687022805213,
|
|
"num_tokens": 63158592.0,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"entropy": 6.469290113449096,
|
|
"epoch": 3.123067044785703,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040443998638390363,
|
|
"loss": 5.9855,
|
|
"mean_token_accuracy": 0.16133179217576982,
|
|
"num_tokens": 63168260.0,
|
|
"step": 29185
|
|
},
|
|
{
|
|
"entropy": 6.473774433135986,
|
|
"epoch": 3.1236021188934666,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00040440871152589797,
|
|
"loss": 6.0407,
|
|
"mean_token_accuracy": 0.1491284802556038,
|
|
"num_tokens": 63178650.0,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"entropy": 6.5629478931427006,
|
|
"epoch": 3.1241371930012307,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040437743293123403,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.15454766750335694,
|
|
"num_tokens": 63188491.0,
|
|
"step": 29195
|
|
},
|
|
{
|
|
"entropy": 6.499769687652588,
|
|
"epoch": 3.124672267108995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040434615060081473,
|
|
"loss": 5.9905,
|
|
"mean_token_accuracy": 0.15635442435741426,
|
|
"num_tokens": 63198915.0,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"entropy": 6.4383337020874025,
|
|
"epoch": 3.1252073412167585,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004043148645355436,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.15689657479524613,
|
|
"num_tokens": 63210010.0,
|
|
"step": 29205
|
|
},
|
|
{
|
|
"entropy": 6.468407154083252,
|
|
"epoch": 3.1257424153245226,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000404283574736324,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.14957141429185866,
|
|
"num_tokens": 63220233.0,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"entropy": 6.517278051376342,
|
|
"epoch": 3.1262774894322862,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004042522812040592,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.15507931262254715,
|
|
"num_tokens": 63231258.0,
|
|
"step": 29215
|
|
},
|
|
{
|
|
"entropy": 6.448086738586426,
|
|
"epoch": 3.1268125635400503,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000404220983939653,
|
|
"loss": 6.0065,
|
|
"mean_token_accuracy": 0.15213130563497543,
|
|
"num_tokens": 63241781.0,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"entropy": 6.535045623779297,
|
|
"epoch": 3.1273476376478144,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004041896829440091,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.1471436493098736,
|
|
"num_tokens": 63253359.0,
|
|
"step": 29225
|
|
},
|
|
{
|
|
"entropy": 6.506486082077027,
|
|
"epoch": 3.127882711755578,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004041583782180312,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.15041868835687638,
|
|
"num_tokens": 63263983.0,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"entropy": 6.42330904006958,
|
|
"epoch": 3.128417785863342,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004041270697626233,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.1595183551311493,
|
|
"num_tokens": 63274503.0,
|
|
"step": 29235
|
|
},
|
|
{
|
|
"entropy": 6.5788647651672365,
|
|
"epoch": 3.128952859971106,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004040957575786894,
|
|
"loss": 6.1206,
|
|
"mean_token_accuracy": 0.1374513290822506,
|
|
"num_tokens": 63285863.0,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"entropy": 6.551848316192627,
|
|
"epoch": 3.12948793407887,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004040644416671337,
|
|
"loss": 6.0984,
|
|
"mean_token_accuracy": 0.15172677785158156,
|
|
"num_tokens": 63297089.0,
|
|
"step": 29245
|
|
},
|
|
{
|
|
"entropy": 6.460995054244995,
|
|
"epoch": 3.130023008186634,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040403312202886026,
|
|
"loss": 6.0035,
|
|
"mean_token_accuracy": 0.1552335575222969,
|
|
"num_tokens": 63307591.0,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"entropy": 6.465104341506958,
|
|
"epoch": 3.1305580822943977,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004040017986647736,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.15929238200187684,
|
|
"num_tokens": 63317895.0,
|
|
"step": 29255
|
|
},
|
|
{
|
|
"entropy": 6.548804426193238,
|
|
"epoch": 3.131093156402162,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040397047157577823,
|
|
"loss": 6.0562,
|
|
"mean_token_accuracy": 0.14854608625173568,
|
|
"num_tokens": 63327829.0,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"entropy": 6.540064191818237,
|
|
"epoch": 3.1316282305099254,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004039391407627785,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.1541123904287815,
|
|
"num_tokens": 63337842.0,
|
|
"step": 29265
|
|
},
|
|
{
|
|
"entropy": 6.510335969924927,
|
|
"epoch": 3.1321633046176895,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040390780622667923,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.15727949142456055,
|
|
"num_tokens": 63349103.0,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"entropy": 6.449616861343384,
|
|
"epoch": 3.1326983787254536,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040387646796838524,
|
|
"loss": 6.0982,
|
|
"mean_token_accuracy": 0.14444032162427903,
|
|
"num_tokens": 63359172.0,
|
|
"step": 29275
|
|
},
|
|
{
|
|
"entropy": 6.511981582641601,
|
|
"epoch": 3.1332334528332173,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040384512598880127,
|
|
"loss": 6.044,
|
|
"mean_token_accuracy": 0.1512990489602089,
|
|
"num_tokens": 63370397.0,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"entropy": 6.4652509689331055,
|
|
"epoch": 3.1337685269409814,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00040381378028883234,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.15019308030605316,
|
|
"num_tokens": 63380592.0,
|
|
"step": 29285
|
|
},
|
|
{
|
|
"entropy": 6.507751417160034,
|
|
"epoch": 3.134303601048745,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040378243086938373,
|
|
"loss": 6.1034,
|
|
"mean_token_accuracy": 0.14464082717895507,
|
|
"num_tokens": 63392115.0,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"entropy": 6.5080053329467775,
|
|
"epoch": 3.134838675156509,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004037510777313604,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.14944097101688386,
|
|
"num_tokens": 63403287.0,
|
|
"step": 29295
|
|
},
|
|
{
|
|
"entropy": 6.501842451095581,
|
|
"epoch": 3.1353737492642733,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004037197208756679,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.15194544047117234,
|
|
"num_tokens": 63415248.0,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"entropy": 6.516400718688965,
|
|
"epoch": 3.135908823372037,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004036883603032115,
|
|
"loss": 6.0782,
|
|
"mean_token_accuracy": 0.14557004123926162,
|
|
"num_tokens": 63425693.0,
|
|
"step": 29305
|
|
},
|
|
{
|
|
"entropy": 6.488477563858032,
|
|
"epoch": 3.136443897479801,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004036569960148968,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.15066845566034318,
|
|
"num_tokens": 63437711.0,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"entropy": 6.4748142719268795,
|
|
"epoch": 3.136978971587565,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00040362562801162937,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.15127295032143592,
|
|
"num_tokens": 63448190.0,
|
|
"step": 29315
|
|
},
|
|
{
|
|
"entropy": 6.531076860427857,
|
|
"epoch": 3.1375140456953288,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040359425629431505,
|
|
"loss": 6.0517,
|
|
"mean_token_accuracy": 0.1518782839179039,
|
|
"num_tokens": 63459285.0,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"entropy": 6.479944133758545,
|
|
"epoch": 3.138049119803093,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040356288086385966,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.148381008207798,
|
|
"num_tokens": 63469093.0,
|
|
"step": 29325
|
|
},
|
|
{
|
|
"entropy": 6.439106178283692,
|
|
"epoch": 3.1385841939108565,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00040353150172116916,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.15276222079992294,
|
|
"num_tokens": 63479108.0,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"entropy": 6.525907754898071,
|
|
"epoch": 3.1391192680186206,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040350011886714957,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.14911627918481826,
|
|
"num_tokens": 63490656.0,
|
|
"step": 29335
|
|
},
|
|
{
|
|
"entropy": 6.51400408744812,
|
|
"epoch": 3.1396543421263843,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040346873230270706,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.15912852734327315,
|
|
"num_tokens": 63501261.0,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"entropy": 6.540085935592652,
|
|
"epoch": 3.1401894162341484,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000403437342028748,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.14391366839408876,
|
|
"num_tokens": 63511926.0,
|
|
"step": 29345
|
|
},
|
|
{
|
|
"entropy": 6.5136676788330075,
|
|
"epoch": 3.1407244903419125,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040340594804617874,
|
|
"loss": 6.089,
|
|
"mean_token_accuracy": 0.1499472126364708,
|
|
"num_tokens": 63523140.0,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"entropy": 6.522920083999634,
|
|
"epoch": 3.141259564449676,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040337455035590583,
|
|
"loss": 6.0405,
|
|
"mean_token_accuracy": 0.1518006518483162,
|
|
"num_tokens": 63532745.0,
|
|
"step": 29355
|
|
},
|
|
{
|
|
"entropy": 6.517468786239624,
|
|
"epoch": 3.1417946385574402,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040334314895883574,
|
|
"loss": 6.074,
|
|
"mean_token_accuracy": 0.15269092470407486,
|
|
"num_tokens": 63544144.0,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"entropy": 6.5570143699646,
|
|
"epoch": 3.1423297126652043,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040331174385587533,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.1392529360949993,
|
|
"num_tokens": 63554615.0,
|
|
"step": 29365
|
|
},
|
|
{
|
|
"entropy": 6.525216484069825,
|
|
"epoch": 3.142864786772968,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004032803350479313,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.15061251819133759,
|
|
"num_tokens": 63565620.0,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"entropy": 6.439367198944092,
|
|
"epoch": 3.143399860880732,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004032489225359106,
|
|
"loss": 5.9985,
|
|
"mean_token_accuracy": 0.15783891826868057,
|
|
"num_tokens": 63575787.0,
|
|
"step": 29375
|
|
},
|
|
{
|
|
"entropy": 6.456002998352051,
|
|
"epoch": 3.1439349349884957,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004032175063207203,
|
|
"loss": 6.0777,
|
|
"mean_token_accuracy": 0.1493025913834572,
|
|
"num_tokens": 63586644.0,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"entropy": 6.526070690155029,
|
|
"epoch": 3.14447000909626,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040318608640326756,
|
|
"loss": 6.0388,
|
|
"mean_token_accuracy": 0.1486140489578247,
|
|
"num_tokens": 63596592.0,
|
|
"step": 29385
|
|
},
|
|
{
|
|
"entropy": 6.560441493988037,
|
|
"epoch": 3.145005083204024,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00040315466278445955,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.1528843268752098,
|
|
"num_tokens": 63607263.0,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"entropy": 6.41722731590271,
|
|
"epoch": 3.1455401573117876,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004031232354652037,
|
|
"loss": 5.9758,
|
|
"mean_token_accuracy": 0.15373275130987168,
|
|
"num_tokens": 63618494.0,
|
|
"step": 29395
|
|
},
|
|
{
|
|
"entropy": 6.390229177474976,
|
|
"epoch": 3.1460752314195517,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040309180444640734,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.15387978106737138,
|
|
"num_tokens": 63629100.0,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"entropy": 6.390478658676147,
|
|
"epoch": 3.1466103055273154,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040306036972897823,
|
|
"loss": 6.0146,
|
|
"mean_token_accuracy": 0.15252063125371934,
|
|
"num_tokens": 63640088.0,
|
|
"step": 29405
|
|
},
|
|
{
|
|
"entropy": 6.445710468292236,
|
|
"epoch": 3.1471453796350795,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004030289313138239,
|
|
"loss": 5.9737,
|
|
"mean_token_accuracy": 0.1506683945655823,
|
|
"num_tokens": 63650262.0,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"entropy": 6.526191568374633,
|
|
"epoch": 3.1476804537428436,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040299748920185214,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.14566997736692427,
|
|
"num_tokens": 63661919.0,
|
|
"step": 29415
|
|
},
|
|
{
|
|
"entropy": 6.502570962905883,
|
|
"epoch": 3.148215527850607,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040296604339397086,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.14677387550473214,
|
|
"num_tokens": 63672185.0,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"entropy": 6.527962589263916,
|
|
"epoch": 3.1487506019583713,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004029345938910881,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.1436070069670677,
|
|
"num_tokens": 63682948.0,
|
|
"step": 29425
|
|
},
|
|
{
|
|
"entropy": 6.574484348297119,
|
|
"epoch": 3.149285676066135,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040290314069411193,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.14141762852668763,
|
|
"num_tokens": 63693227.0,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"entropy": 6.5643353939056395,
|
|
"epoch": 3.149820750173899,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004028716838039505,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.14870040118694305,
|
|
"num_tokens": 63705315.0,
|
|
"step": 29435
|
|
},
|
|
{
|
|
"entropy": 6.496319389343261,
|
|
"epoch": 3.150355824281663,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004028402232215122,
|
|
"loss": 6.0636,
|
|
"mean_token_accuracy": 0.15070207864046098,
|
|
"num_tokens": 63715924.0,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"entropy": 6.427906847000122,
|
|
"epoch": 3.150890898389427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004028087589477054,
|
|
"loss": 6.0318,
|
|
"mean_token_accuracy": 0.1537167251110077,
|
|
"num_tokens": 63726889.0,
|
|
"step": 29445
|
|
},
|
|
{
|
|
"entropy": 6.569262504577637,
|
|
"epoch": 3.151425972497191,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004027772909834387,
|
|
"loss": 6.113,
|
|
"mean_token_accuracy": 0.1476520135998726,
|
|
"num_tokens": 63737102.0,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"entropy": 6.528409957885742,
|
|
"epoch": 3.1519610466049546,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004027458193296206,
|
|
"loss": 6.0548,
|
|
"mean_token_accuracy": 0.15621156096458436,
|
|
"num_tokens": 63747079.0,
|
|
"step": 29455
|
|
},
|
|
{
|
|
"entropy": 6.527632427215576,
|
|
"epoch": 3.1524961207127187,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004027143439871599,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.1492802917957306,
|
|
"num_tokens": 63758852.0,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"entropy": 6.482285356521606,
|
|
"epoch": 3.1530311948204828,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004026828649569656,
|
|
"loss": 6.0274,
|
|
"mean_token_accuracy": 0.15026448518037797,
|
|
"num_tokens": 63770056.0,
|
|
"step": 29465
|
|
},
|
|
{
|
|
"entropy": 6.525629329681396,
|
|
"epoch": 3.1535662689282464,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040265138223994647,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.14662356972694396,
|
|
"num_tokens": 63781241.0,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"entropy": 6.470170640945435,
|
|
"epoch": 3.1541013430360105,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004026198958370115,
|
|
"loss": 6.0657,
|
|
"mean_token_accuracy": 0.14782140254974366,
|
|
"num_tokens": 63792393.0,
|
|
"step": 29475
|
|
},
|
|
{
|
|
"entropy": 6.4739621639251705,
|
|
"epoch": 3.1546364171437746,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004025884057490701,
|
|
"loss": 6.0618,
|
|
"mean_token_accuracy": 0.14977847784757614,
|
|
"num_tokens": 63802474.0,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"entropy": 6.54500789642334,
|
|
"epoch": 3.1551714912515383,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004025569119770313,
|
|
"loss": 6.0005,
|
|
"mean_token_accuracy": 0.1536489650607109,
|
|
"num_tokens": 63812247.0,
|
|
"step": 29485
|
|
},
|
|
{
|
|
"entropy": 6.499966382980347,
|
|
"epoch": 3.1557065653593024,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040252541452180467,
|
|
"loss": 6.0847,
|
|
"mean_token_accuracy": 0.15227219462394714,
|
|
"num_tokens": 63822230.0,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"entropy": 6.457761526107788,
|
|
"epoch": 3.156241639467066,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004024939133842996,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.1466890662908554,
|
|
"num_tokens": 63832594.0,
|
|
"step": 29495
|
|
},
|
|
{
|
|
"entropy": 6.408156633377075,
|
|
"epoch": 3.15677671357483,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004024624085654257,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.14811590015888215,
|
|
"num_tokens": 63844602.0,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"entropy": 6.458574724197388,
|
|
"epoch": 3.1573117876825942,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004024309000660927,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.16220765113830565,
|
|
"num_tokens": 63854683.0,
|
|
"step": 29505
|
|
},
|
|
{
|
|
"entropy": 6.483837747573853,
|
|
"epoch": 3.157846861790358,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040239938788721026,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.15353674367070197,
|
|
"num_tokens": 63865889.0,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"entropy": 6.465010404586792,
|
|
"epoch": 3.158381935898122,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040236787202968847,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.15614334046840667,
|
|
"num_tokens": 63875490.0,
|
|
"step": 29515
|
|
},
|
|
{
|
|
"entropy": 6.475861072540283,
|
|
"epoch": 3.1589170100058857,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004023363524944373,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.1577802777290344,
|
|
"num_tokens": 63886319.0,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"entropy": 6.4152086734771725,
|
|
"epoch": 3.1594520841136498,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004023048292823667,
|
|
"loss": 5.9755,
|
|
"mean_token_accuracy": 0.15367015302181244,
|
|
"num_tokens": 63897588.0,
|
|
"step": 29525
|
|
},
|
|
{
|
|
"entropy": 6.412988948822021,
|
|
"epoch": 3.159987158221414,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004022733023943872,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.15266167372465134,
|
|
"num_tokens": 63908350.0,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"entropy": 6.474171686172485,
|
|
"epoch": 3.1605222323291775,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004022417718314089,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.14895525127649306,
|
|
"num_tokens": 63918744.0,
|
|
"step": 29535
|
|
},
|
|
{
|
|
"entropy": 6.463433074951172,
|
|
"epoch": 3.1610573064369416,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004022102375943424,
|
|
"loss": 5.9878,
|
|
"mean_token_accuracy": 0.15715717524290085,
|
|
"num_tokens": 63928593.0,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"entropy": 6.423540258407593,
|
|
"epoch": 3.1615923805447053,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004021786996840981,
|
|
"loss": 6.0167,
|
|
"mean_token_accuracy": 0.16392265558242797,
|
|
"num_tokens": 63939912.0,
|
|
"step": 29545
|
|
},
|
|
{
|
|
"entropy": 6.498978805541992,
|
|
"epoch": 3.1621274546524694,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00040214715810158667,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.15192784518003463,
|
|
"num_tokens": 63951356.0,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"entropy": 6.508785057067871,
|
|
"epoch": 3.1626625287602335,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000402115612847719,
|
|
"loss": 6.0437,
|
|
"mean_token_accuracy": 0.15685660541057586,
|
|
"num_tokens": 63961252.0,
|
|
"step": 29555
|
|
},
|
|
{
|
|
"entropy": 6.480622720718384,
|
|
"epoch": 3.163197602867997,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004020840639234059,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.14859462678432464,
|
|
"num_tokens": 63972090.0,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"entropy": 6.524064302444458,
|
|
"epoch": 3.163732676975761,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040205251132955825,
|
|
"loss": 6.0646,
|
|
"mean_token_accuracy": 0.15628181174397468,
|
|
"num_tokens": 63983092.0,
|
|
"step": 29565
|
|
},
|
|
{
|
|
"entropy": 6.472568798065185,
|
|
"epoch": 3.164267751083525,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040202095506708727,
|
|
"loss": 6.0318,
|
|
"mean_token_accuracy": 0.15104831010103226,
|
|
"num_tokens": 63992527.0,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"entropy": 6.502049493789673,
|
|
"epoch": 3.164802825191289,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000401989395136904,
|
|
"loss": 6.0491,
|
|
"mean_token_accuracy": 0.15716173499822617,
|
|
"num_tokens": 64003938.0,
|
|
"step": 29575
|
|
},
|
|
{
|
|
"entropy": 6.458790302276611,
|
|
"epoch": 3.165337899299053,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004019578315399197,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.1541299358010292,
|
|
"num_tokens": 64013925.0,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"entropy": 6.5277728080749515,
|
|
"epoch": 3.1658729734068167,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004019262642770459,
|
|
"loss": 6.1672,
|
|
"mean_token_accuracy": 0.14464845582842828,
|
|
"num_tokens": 64024503.0,
|
|
"step": 29585
|
|
},
|
|
{
|
|
"entropy": 6.533604526519776,
|
|
"epoch": 3.166408047514581,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040189469334919416,
|
|
"loss": 6.0458,
|
|
"mean_token_accuracy": 0.1498898059129715,
|
|
"num_tokens": 64035650.0,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"entropy": 6.479456901550293,
|
|
"epoch": 3.166943121622345,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004018631187572759,
|
|
"loss": 6.0858,
|
|
"mean_token_accuracy": 0.14727139472961426,
|
|
"num_tokens": 64047032.0,
|
|
"step": 29595
|
|
},
|
|
{
|
|
"entropy": 6.392290878295898,
|
|
"epoch": 3.1674781957301086,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00040183154050220295,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.16316040605306625,
|
|
"num_tokens": 64057578.0,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"entropy": 6.5737607955932615,
|
|
"epoch": 3.1680132698378727,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000401799958584887,
|
|
"loss": 6.1538,
|
|
"mean_token_accuracy": 0.14138682708144187,
|
|
"num_tokens": 64068679.0,
|
|
"step": 29605
|
|
},
|
|
{
|
|
"entropy": 6.502508735656738,
|
|
"epoch": 3.1685483439456363,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040176837300624015,
|
|
"loss": 6.0619,
|
|
"mean_token_accuracy": 0.1545240879058838,
|
|
"num_tokens": 64078572.0,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"entropy": 6.470043039321899,
|
|
"epoch": 3.1690834180534004,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004017367837671743,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.15096578896045684,
|
|
"num_tokens": 64088507.0,
|
|
"step": 29615
|
|
},
|
|
{
|
|
"entropy": 6.466709804534912,
|
|
"epoch": 3.169618492161164,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00040170519086860166,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.1482529580593109,
|
|
"num_tokens": 64099405.0,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"entropy": 6.514722776412964,
|
|
"epoch": 3.170153566268928,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040167359431143444,
|
|
"loss": 6.0383,
|
|
"mean_token_accuracy": 0.15570422559976577,
|
|
"num_tokens": 64109554.0,
|
|
"step": 29625
|
|
},
|
|
{
|
|
"entropy": 6.485420608520508,
|
|
"epoch": 3.1706886403766923,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000401641994096585,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.1567971870303154,
|
|
"num_tokens": 64119817.0,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"entropy": 6.497474193572998,
|
|
"epoch": 3.171223714484456,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004016103902249658,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.15120346397161483,
|
|
"num_tokens": 64131001.0,
|
|
"step": 29635
|
|
},
|
|
{
|
|
"entropy": 6.500389862060547,
|
|
"epoch": 3.17175878859222,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004015787826974892,
|
|
"loss": 6.0381,
|
|
"mean_token_accuracy": 0.150934661924839,
|
|
"num_tokens": 64142072.0,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"entropy": 6.457733678817749,
|
|
"epoch": 3.172293862699984,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004015471715150682,
|
|
"loss": 6.0587,
|
|
"mean_token_accuracy": 0.15260417759418488,
|
|
"num_tokens": 64153097.0,
|
|
"step": 29645
|
|
},
|
|
{
|
|
"entropy": 6.5134765148162845,
|
|
"epoch": 3.172828936807748,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004015155566786154,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.1445486605167389,
|
|
"num_tokens": 64164952.0,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"entropy": 6.521479082107544,
|
|
"epoch": 3.173364010915512,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00040148393818904366,
|
|
"loss": 6.0606,
|
|
"mean_token_accuracy": 0.1501020148396492,
|
|
"num_tokens": 64175754.0,
|
|
"step": 29655
|
|
},
|
|
{
|
|
"entropy": 6.6159796714782715,
|
|
"epoch": 3.1738990850232756,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004014523160472659,
|
|
"loss": 6.1232,
|
|
"mean_token_accuracy": 0.1464289829134941,
|
|
"num_tokens": 64186888.0,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"entropy": 6.5037421703338625,
|
|
"epoch": 3.1744341591310397,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00040142069025419537,
|
|
"loss": 6.0304,
|
|
"mean_token_accuracy": 0.1506258450448513,
|
|
"num_tokens": 64197362.0,
|
|
"step": 29665
|
|
},
|
|
{
|
|
"entropy": 6.499789667129517,
|
|
"epoch": 3.1749692332388038,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004013890608107451,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.1503922313451767,
|
|
"num_tokens": 64208667.0,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"entropy": 6.545876502990723,
|
|
"epoch": 3.1755043073465674,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004013574277178285,
|
|
"loss": 6.1489,
|
|
"mean_token_accuracy": 0.13736739307641982,
|
|
"num_tokens": 64219525.0,
|
|
"step": 29675
|
|
},
|
|
{
|
|
"entropy": 6.507164335250854,
|
|
"epoch": 3.1760393814543315,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040132579097635897,
|
|
"loss": 5.9869,
|
|
"mean_token_accuracy": 0.15304708182811738,
|
|
"num_tokens": 64228916.0,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"entropy": 6.438566398620606,
|
|
"epoch": 3.176574455562095,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040129415058724993,
|
|
"loss": 6.0551,
|
|
"mean_token_accuracy": 0.1472688600420952,
|
|
"num_tokens": 64241467.0,
|
|
"step": 29685
|
|
},
|
|
{
|
|
"entropy": 6.516100072860718,
|
|
"epoch": 3.1771095296698593,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040126250655141507,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.1536680653691292,
|
|
"num_tokens": 64251330.0,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"entropy": 6.499765539169312,
|
|
"epoch": 3.1776446037776234,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040123085886976804,
|
|
"loss": 5.9954,
|
|
"mean_token_accuracy": 0.15791045576334,
|
|
"num_tokens": 64261991.0,
|
|
"step": 29695
|
|
},
|
|
{
|
|
"entropy": 6.526811695098877,
|
|
"epoch": 3.178179677885387,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040119920754322277,
|
|
"loss": 6.1042,
|
|
"mean_token_accuracy": 0.1451876640319824,
|
|
"num_tokens": 64272402.0,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"entropy": 6.408946228027344,
|
|
"epoch": 3.178714751993151,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040116755257269297,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.15065131336450577,
|
|
"num_tokens": 64283390.0,
|
|
"step": 29705
|
|
},
|
|
{
|
|
"entropy": 6.480000162124634,
|
|
"epoch": 3.1792498261009148,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040113589395909295,
|
|
"loss": 6.0374,
|
|
"mean_token_accuracy": 0.15249679759144782,
|
|
"num_tokens": 64294280.0,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"entropy": 6.561222648620605,
|
|
"epoch": 3.179784900208679,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004011042317033367,
|
|
"loss": 6.1568,
|
|
"mean_token_accuracy": 0.14674644619226457,
|
|
"num_tokens": 64305927.0,
|
|
"step": 29715
|
|
},
|
|
{
|
|
"entropy": 6.426386976242066,
|
|
"epoch": 3.180319974316443,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004010725658063385,
|
|
"loss": 5.9788,
|
|
"mean_token_accuracy": 0.15963343679904937,
|
|
"num_tokens": 64316319.0,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"entropy": 6.513511657714844,
|
|
"epoch": 3.1808550484242066,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004010408962690126,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.14775596261024476,
|
|
"num_tokens": 64326958.0,
|
|
"step": 29725
|
|
},
|
|
{
|
|
"entropy": 6.52355842590332,
|
|
"epoch": 3.1813901225319707,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040100922309227357,
|
|
"loss": 6.0879,
|
|
"mean_token_accuracy": 0.1456541620194912,
|
|
"num_tokens": 64338433.0,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"entropy": 6.436701393127441,
|
|
"epoch": 3.1819251966397344,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040097754627703593,
|
|
"loss": 5.913,
|
|
"mean_token_accuracy": 0.1597264066338539,
|
|
"num_tokens": 64349188.0,
|
|
"step": 29735
|
|
},
|
|
{
|
|
"entropy": 6.477220869064331,
|
|
"epoch": 3.1824602707474985,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004009458658242143,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.146313938498497,
|
|
"num_tokens": 64359837.0,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"entropy": 6.432889413833618,
|
|
"epoch": 3.1829953448552626,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040091418173472356,
|
|
"loss": 6.0434,
|
|
"mean_token_accuracy": 0.15394408255815506,
|
|
"num_tokens": 64370927.0,
|
|
"step": 29745
|
|
},
|
|
{
|
|
"entropy": 6.404416418075561,
|
|
"epoch": 3.1835304189630262,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004008824940094785,
|
|
"loss": 6.008,
|
|
"mean_token_accuracy": 0.1534748673439026,
|
|
"num_tokens": 64381683.0,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"entropy": 6.43355655670166,
|
|
"epoch": 3.1840654930707903,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004008508026493941,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.15665697306394577,
|
|
"num_tokens": 64394063.0,
|
|
"step": 29755
|
|
},
|
|
{
|
|
"entropy": 6.49813175201416,
|
|
"epoch": 3.1846005671785544,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040081910765538543,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.15132833272218704,
|
|
"num_tokens": 64405183.0,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"entropy": 6.511742782592774,
|
|
"epoch": 3.185135641286318,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040078740902836776,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.1631958082318306,
|
|
"num_tokens": 64415325.0,
|
|
"step": 29765
|
|
},
|
|
{
|
|
"entropy": 6.518599033355713,
|
|
"epoch": 3.185670715394082,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040075570676925633,
|
|
"loss": 6.09,
|
|
"mean_token_accuracy": 0.14757880046963692,
|
|
"num_tokens": 64426240.0,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"entropy": 6.404853439331054,
|
|
"epoch": 3.186205789501846,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004007240008789664,
|
|
"loss": 6.0636,
|
|
"mean_token_accuracy": 0.15078577697277068,
|
|
"num_tokens": 64436664.0,
|
|
"step": 29775
|
|
},
|
|
{
|
|
"entropy": 6.517673921585083,
|
|
"epoch": 3.18674086360961,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040069229135841376,
|
|
"loss": 6.1481,
|
|
"mean_token_accuracy": 0.14617200940847397,
|
|
"num_tokens": 64448731.0,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"entropy": 6.632907199859619,
|
|
"epoch": 3.187275937717374,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004006605782085139,
|
|
"loss": 6.1561,
|
|
"mean_token_accuracy": 0.13871113657951356,
|
|
"num_tokens": 64460916.0,
|
|
"step": 29785
|
|
},
|
|
{
|
|
"entropy": 6.563667821884155,
|
|
"epoch": 3.1878110118251377,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004006288614301824,
|
|
"loss": 6.0986,
|
|
"mean_token_accuracy": 0.14399358481168748,
|
|
"num_tokens": 64472114.0,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"entropy": 6.480885553359985,
|
|
"epoch": 3.188346085932902,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040059714102433526,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.15451620519161224,
|
|
"num_tokens": 64482465.0,
|
|
"step": 29795
|
|
},
|
|
{
|
|
"entropy": 6.4045041561126705,
|
|
"epoch": 3.1888811600406655,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004005654169918883,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.15431310683488847,
|
|
"num_tokens": 64493285.0,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"entropy": 6.4837922096252445,
|
|
"epoch": 3.1894162341484296,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040053368933375756,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.147686168551445,
|
|
"num_tokens": 64504037.0,
|
|
"step": 29805
|
|
},
|
|
{
|
|
"entropy": 6.46972918510437,
|
|
"epoch": 3.1899513082561937,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040050195805085907,
|
|
"loss": 5.9854,
|
|
"mean_token_accuracy": 0.15357603281736373,
|
|
"num_tokens": 64513900.0,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"entropy": 6.426800966262817,
|
|
"epoch": 3.1904863823639573,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040047022314410936,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.15024127066135406,
|
|
"num_tokens": 64525273.0,
|
|
"step": 29815
|
|
},
|
|
{
|
|
"entropy": 6.5025269985198975,
|
|
"epoch": 3.1910214564717214,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00040043848461442447,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.15342622995376587,
|
|
"num_tokens": 64535929.0,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"entropy": 6.53921914100647,
|
|
"epoch": 3.191556530579485,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000400406742462721,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.14785778373479844,
|
|
"num_tokens": 64546975.0,
|
|
"step": 29825
|
|
},
|
|
{
|
|
"entropy": 6.5004126071929935,
|
|
"epoch": 3.192091604687249,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040037499668991544,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.1423839658498764,
|
|
"num_tokens": 64558295.0,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"entropy": 6.470630121231079,
|
|
"epoch": 3.1926266787950133,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040034324729692453,
|
|
"loss": 5.9517,
|
|
"mean_token_accuracy": 0.16059553921222686,
|
|
"num_tokens": 64569638.0,
|
|
"step": 29835
|
|
},
|
|
{
|
|
"entropy": 6.517405891418457,
|
|
"epoch": 3.193161752902777,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004003114942846649,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.14844676554203035,
|
|
"num_tokens": 64580693.0,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"entropy": 6.43237075805664,
|
|
"epoch": 3.193696827010541,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040027973765405353,
|
|
"loss": 6.0513,
|
|
"mean_token_accuracy": 0.15717561542987823,
|
|
"num_tokens": 64590947.0,
|
|
"step": 29845
|
|
},
|
|
{
|
|
"entropy": 6.541468095779419,
|
|
"epoch": 3.1942319011183047,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004002479774060073,
|
|
"loss": 6.123,
|
|
"mean_token_accuracy": 0.14765822514891624,
|
|
"num_tokens": 64602340.0,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"entropy": 6.547239875793457,
|
|
"epoch": 3.194766975226069,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004002162135414433,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.14846495166420937,
|
|
"num_tokens": 64614410.0,
|
|
"step": 29855
|
|
},
|
|
{
|
|
"entropy": 6.576959037780762,
|
|
"epoch": 3.195302049333833,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004001844460612788,
|
|
"loss": 6.0842,
|
|
"mean_token_accuracy": 0.1461495764553547,
|
|
"num_tokens": 64624893.0,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"entropy": 6.512037229537964,
|
|
"epoch": 3.1958371234415965,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040015267496643097,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.1548733800649643,
|
|
"num_tokens": 64636172.0,
|
|
"step": 29865
|
|
},
|
|
{
|
|
"entropy": 6.446339464187622,
|
|
"epoch": 3.1963721975493606,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004001209002578172,
|
|
"loss": 6.0486,
|
|
"mean_token_accuracy": 0.14579746648669242,
|
|
"num_tokens": 64647605.0,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"entropy": 6.544587182998657,
|
|
"epoch": 3.1969072716571247,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004000891219363551,
|
|
"loss": 6.1146,
|
|
"mean_token_accuracy": 0.14425014406442643,
|
|
"num_tokens": 64657496.0,
|
|
"step": 29875
|
|
},
|
|
{
|
|
"entropy": 6.502764749526977,
|
|
"epoch": 3.1974423457648884,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00040005734000296225,
|
|
"loss": 6.0051,
|
|
"mean_token_accuracy": 0.15776585415005684,
|
|
"num_tokens": 64668905.0,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"entropy": 6.483946657180786,
|
|
"epoch": 3.1979774198726525,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004000255544585561,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.15464583933353424,
|
|
"num_tokens": 64679207.0,
|
|
"step": 29885
|
|
},
|
|
{
|
|
"entropy": 6.489745616912842,
|
|
"epoch": 3.198512493980416,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003999937653040547,
|
|
"loss": 6.0328,
|
|
"mean_token_accuracy": 0.15790248066186904,
|
|
"num_tokens": 64689536.0,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"entropy": 6.534128713607788,
|
|
"epoch": 3.1990475680881802,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003999619725403759,
|
|
"loss": 6.2321,
|
|
"mean_token_accuracy": 0.13458913341164588,
|
|
"num_tokens": 64700304.0,
|
|
"step": 29895
|
|
},
|
|
{
|
|
"entropy": 6.459638786315918,
|
|
"epoch": 3.199582642195944,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039993017616843775,
|
|
"loss": 6.0179,
|
|
"mean_token_accuracy": 0.14777725487947463,
|
|
"num_tokens": 64711657.0,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"entropy": 6.442101621627808,
|
|
"epoch": 3.200117716303708,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0003998983761891582,
|
|
"loss": 6.005,
|
|
"mean_token_accuracy": 0.15908481180667877,
|
|
"num_tokens": 64722697.0,
|
|
"step": 29905
|
|
},
|
|
{
|
|
"entropy": 6.4185277938842775,
|
|
"epoch": 3.200652790411472,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039986657260345567,
|
|
"loss": 5.9777,
|
|
"mean_token_accuracy": 0.15859111845493318,
|
|
"num_tokens": 64732823.0,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"entropy": 6.476954698562622,
|
|
"epoch": 3.2011878645192358,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003998347654122484,
|
|
"loss": 6.0866,
|
|
"mean_token_accuracy": 0.14406352788209914,
|
|
"num_tokens": 64744471.0,
|
|
"step": 29915
|
|
},
|
|
{
|
|
"entropy": 6.470202350616455,
|
|
"epoch": 3.201722938627,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039980295461645483,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.15302277356386185,
|
|
"num_tokens": 64754079.0,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"entropy": 6.538177824020385,
|
|
"epoch": 3.202258012734764,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039977114021699344,
|
|
"loss": 6.0406,
|
|
"mean_token_accuracy": 0.14705175757408143,
|
|
"num_tokens": 64764489.0,
|
|
"step": 29925
|
|
},
|
|
{
|
|
"entropy": 6.441628170013428,
|
|
"epoch": 3.2027930868425276,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039973932221478293,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.1608467310667038,
|
|
"num_tokens": 64775512.0,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"entropy": 6.411372280120849,
|
|
"epoch": 3.2033281609502917,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039970750061074206,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.1452941656112671,
|
|
"num_tokens": 64787466.0,
|
|
"step": 29935
|
|
},
|
|
{
|
|
"entropy": 6.478132200241089,
|
|
"epoch": 3.2038632350580554,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039967567540578956,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.15518922954797745,
|
|
"num_tokens": 64797380.0,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"entropy": 6.467507219314575,
|
|
"epoch": 3.2043983091658195,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003996438466008446,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.1487541064620018,
|
|
"num_tokens": 64807609.0,
|
|
"step": 29945
|
|
},
|
|
{
|
|
"entropy": 6.393891191482544,
|
|
"epoch": 3.2049333832735836,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003996120141968259,
|
|
"loss": 5.9621,
|
|
"mean_token_accuracy": 0.15769365131855012,
|
|
"num_tokens": 64818601.0,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"entropy": 6.477816438674926,
|
|
"epoch": 3.2054684573813472,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039958017819465285,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.14640337824821473,
|
|
"num_tokens": 64829597.0,
|
|
"step": 29955
|
|
},
|
|
{
|
|
"entropy": 6.477048063278199,
|
|
"epoch": 3.2060035314891113,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039954833859524473,
|
|
"loss": 6.0127,
|
|
"mean_token_accuracy": 0.15280040800571443,
|
|
"num_tokens": 64841293.0,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"entropy": 6.560559415817261,
|
|
"epoch": 3.206538605596875,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039951649539952076,
|
|
"loss": 6.0921,
|
|
"mean_token_accuracy": 0.14674476236104966,
|
|
"num_tokens": 64852724.0,
|
|
"step": 29965
|
|
},
|
|
{
|
|
"entropy": 6.554120922088623,
|
|
"epoch": 3.207073679704639,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00039948464860840047,
|
|
"loss": 6.0729,
|
|
"mean_token_accuracy": 0.15852001309394836,
|
|
"num_tokens": 64864915.0,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"entropy": 6.4934674263000485,
|
|
"epoch": 3.207608753812403,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003994527982228035,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.15349815636873246,
|
|
"num_tokens": 64876431.0,
|
|
"step": 29975
|
|
},
|
|
{
|
|
"entropy": 6.469108963012696,
|
|
"epoch": 3.208143827920167,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003994209442436495,
|
|
"loss": 6.063,
|
|
"mean_token_accuracy": 0.15333183109760284,
|
|
"num_tokens": 64887492.0,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"entropy": 6.48726863861084,
|
|
"epoch": 3.208678902027931,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039938908667185816,
|
|
"loss": 6.085,
|
|
"mean_token_accuracy": 0.15142240151762962,
|
|
"num_tokens": 64897894.0,
|
|
"step": 29985
|
|
},
|
|
{
|
|
"entropy": 6.520753574371338,
|
|
"epoch": 3.2092139761356946,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039935722550834944,
|
|
"loss": 6.0802,
|
|
"mean_token_accuracy": 0.1478661522269249,
|
|
"num_tokens": 64909071.0,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"entropy": 6.490993213653565,
|
|
"epoch": 3.2097490502434587,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003993253607540433,
|
|
"loss": 6.0801,
|
|
"mean_token_accuracy": 0.15133538246154785,
|
|
"num_tokens": 64919434.0,
|
|
"step": 29995
|
|
},
|
|
{
|
|
"entropy": 6.415107917785645,
|
|
"epoch": 3.210284124351223,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0003992934924098598,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.1476921781897545,
|
|
"num_tokens": 64929897.0,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 3.210284124351223,
|
|
"eval_entropy": 6.271181811155334,
|
|
"eval_loss": 6.186514854431152,
|
|
"eval_mean_token_accuracy": 0.15324516140245845,
|
|
"eval_num_tokens": 64929897.0,
|
|
"eval_runtime": 22.8361,
|
|
"eval_samples_per_second": 1299.653,
|
|
"eval_steps_per_second": 162.462,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"entropy": 6.429433727264405,
|
|
"epoch": 3.2108191984589864,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0003992616204767192,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.1643612027168274,
|
|
"num_tokens": 64940219.0,
|
|
"step": 30005
|
|
},
|
|
{
|
|
"entropy": 6.42921085357666,
|
|
"epoch": 3.2113542725667505,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003992297449555419,
|
|
"loss": 5.9343,
|
|
"mean_token_accuracy": 0.15828622728586197,
|
|
"num_tokens": 64950326.0,
|
|
"step": 30010
|
|
},
|
|
{
|
|
"entropy": 6.449179029464721,
|
|
"epoch": 3.211889346674514,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039919786584724796,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.15065066739916802,
|
|
"num_tokens": 64960873.0,
|
|
"step": 30015
|
|
},
|
|
{
|
|
"entropy": 6.47101240158081,
|
|
"epoch": 3.2124244207822783,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039916598315275825,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.15457821637392044,
|
|
"num_tokens": 64972138.0,
|
|
"step": 30020
|
|
},
|
|
{
|
|
"entropy": 6.548863410949707,
|
|
"epoch": 3.2129594948900424,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003991340968729932,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.14464850798249246,
|
|
"num_tokens": 64983002.0,
|
|
"step": 30025
|
|
},
|
|
{
|
|
"entropy": 6.441106176376342,
|
|
"epoch": 3.213494568997806,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039910220700887345,
|
|
"loss": 6.02,
|
|
"mean_token_accuracy": 0.15423458814620972,
|
|
"num_tokens": 64993973.0,
|
|
"step": 30030
|
|
},
|
|
{
|
|
"entropy": 6.522212123870849,
|
|
"epoch": 3.21402964310557,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039907031356131993,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.14242850840091706,
|
|
"num_tokens": 65004711.0,
|
|
"step": 30035
|
|
},
|
|
{
|
|
"entropy": 6.522511911392212,
|
|
"epoch": 3.2145647172133343,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039903841653125366,
|
|
"loss": 6.0549,
|
|
"mean_token_accuracy": 0.14630990475416183,
|
|
"num_tokens": 65016426.0,
|
|
"step": 30040
|
|
},
|
|
{
|
|
"entropy": 6.394894981384278,
|
|
"epoch": 3.215099791321098,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003990065159195955,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.16543169617652892,
|
|
"num_tokens": 65027999.0,
|
|
"step": 30045
|
|
},
|
|
{
|
|
"entropy": 6.486176872253418,
|
|
"epoch": 3.215634865428862,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0003989746117272665,
|
|
"loss": 5.9874,
|
|
"mean_token_accuracy": 0.15445832759141923,
|
|
"num_tokens": 65038216.0,
|
|
"step": 30050
|
|
},
|
|
{
|
|
"entropy": 6.3642786026000975,
|
|
"epoch": 3.2161699395366257,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003989427039551881,
|
|
"loss": 5.9511,
|
|
"mean_token_accuracy": 0.161687234044075,
|
|
"num_tokens": 65049726.0,
|
|
"step": 30055
|
|
},
|
|
{
|
|
"entropy": 6.486101961135864,
|
|
"epoch": 3.2167050136443898,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039891079260428157,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.1446522518992424,
|
|
"num_tokens": 65060675.0,
|
|
"step": 30060
|
|
},
|
|
{
|
|
"entropy": 6.574276113510132,
|
|
"epoch": 3.217240087752154,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039887887767546824,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.14420496672391891,
|
|
"num_tokens": 65072378.0,
|
|
"step": 30065
|
|
},
|
|
{
|
|
"entropy": 6.574113750457764,
|
|
"epoch": 3.2177751618599175,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003988469591696698,
|
|
"loss": 6.063,
|
|
"mean_token_accuracy": 0.1535680115222931,
|
|
"num_tokens": 65082587.0,
|
|
"step": 30070
|
|
},
|
|
{
|
|
"entropy": 6.405022764205933,
|
|
"epoch": 3.2183102359676816,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003988150370878078,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.15627196729183196,
|
|
"num_tokens": 65093210.0,
|
|
"step": 30075
|
|
},
|
|
{
|
|
"entropy": 6.434966278076172,
|
|
"epoch": 3.2188453100754453,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000398783111430804,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.15394776090979576,
|
|
"num_tokens": 65103074.0,
|
|
"step": 30080
|
|
},
|
|
{
|
|
"entropy": 6.4581413745880125,
|
|
"epoch": 3.2193803841832094,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039875118219958016,
|
|
"loss": 6.0593,
|
|
"mean_token_accuracy": 0.14842704981565474,
|
|
"num_tokens": 65113994.0,
|
|
"step": 30085
|
|
},
|
|
{
|
|
"entropy": 6.45810079574585,
|
|
"epoch": 3.2199154582909735,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003987192493950585,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.15351996570825577,
|
|
"num_tokens": 65125381.0,
|
|
"step": 30090
|
|
},
|
|
{
|
|
"entropy": 6.4919932842254635,
|
|
"epoch": 3.220450532398737,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039868731301816076,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.15671349316835403,
|
|
"num_tokens": 65135374.0,
|
|
"step": 30095
|
|
},
|
|
{
|
|
"entropy": 6.441056394577027,
|
|
"epoch": 3.2209856065065012,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00039865537306980924,
|
|
"loss": 5.963,
|
|
"mean_token_accuracy": 0.15753884464502335,
|
|
"num_tokens": 65145514.0,
|
|
"step": 30100
|
|
},
|
|
{
|
|
"entropy": 6.4315869331359865,
|
|
"epoch": 3.221520680614265,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003986234295509262,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.15223814994096757,
|
|
"num_tokens": 65156424.0,
|
|
"step": 30105
|
|
},
|
|
{
|
|
"entropy": 6.532680463790894,
|
|
"epoch": 3.222055754722029,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039859148246243405,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.1426708295941353,
|
|
"num_tokens": 65167774.0,
|
|
"step": 30110
|
|
},
|
|
{
|
|
"entropy": 6.535022783279419,
|
|
"epoch": 3.222590828829793,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039855953180525515,
|
|
"loss": 6.1369,
|
|
"mean_token_accuracy": 0.14083111509680749,
|
|
"num_tokens": 65179552.0,
|
|
"step": 30115
|
|
},
|
|
{
|
|
"entropy": 6.583222150802612,
|
|
"epoch": 3.2231259029375567,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039852757758031217,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.15387350022792817,
|
|
"num_tokens": 65190386.0,
|
|
"step": 30120
|
|
},
|
|
{
|
|
"entropy": 6.504891395568848,
|
|
"epoch": 3.223660977045321,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039849561978852775,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.151320169121027,
|
|
"num_tokens": 65201989.0,
|
|
"step": 30125
|
|
},
|
|
{
|
|
"entropy": 6.431033563613892,
|
|
"epoch": 3.2241960511530845,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0003984636584308248,
|
|
"loss": 5.9813,
|
|
"mean_token_accuracy": 0.1570635750889778,
|
|
"num_tokens": 65212862.0,
|
|
"step": 30130
|
|
},
|
|
{
|
|
"entropy": 6.4596109867095945,
|
|
"epoch": 3.2247311252608486,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039843169350812585,
|
|
"loss": 6.0371,
|
|
"mean_token_accuracy": 0.15501189678907396,
|
|
"num_tokens": 65223381.0,
|
|
"step": 30135
|
|
},
|
|
{
|
|
"entropy": 6.511037969589234,
|
|
"epoch": 3.2252661993686127,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003983997250213542,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.1526182100176811,
|
|
"num_tokens": 65234882.0,
|
|
"step": 30140
|
|
},
|
|
{
|
|
"entropy": 6.523083686828613,
|
|
"epoch": 3.2258012734763764,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039836775297143277,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.14798592478036882,
|
|
"num_tokens": 65244421.0,
|
|
"step": 30145
|
|
},
|
|
{
|
|
"entropy": 6.475531482696534,
|
|
"epoch": 3.2263363475841405,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039833577735928484,
|
|
"loss": 6.0013,
|
|
"mean_token_accuracy": 0.15407465994358063,
|
|
"num_tokens": 65255536.0,
|
|
"step": 30150
|
|
},
|
|
{
|
|
"entropy": 6.481257057189941,
|
|
"epoch": 3.2268714216919046,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003983037981858337,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.15643736273050307,
|
|
"num_tokens": 65265776.0,
|
|
"step": 30155
|
|
},
|
|
{
|
|
"entropy": 6.473739671707153,
|
|
"epoch": 3.227406495799668,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039827181545200264,
|
|
"loss": 6.0326,
|
|
"mean_token_accuracy": 0.149050010740757,
|
|
"num_tokens": 65276003.0,
|
|
"step": 30160
|
|
},
|
|
{
|
|
"entropy": 6.51440281867981,
|
|
"epoch": 3.2279415699074323,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003982398291587153,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.1496956929564476,
|
|
"num_tokens": 65286817.0,
|
|
"step": 30165
|
|
},
|
|
{
|
|
"entropy": 6.446007919311524,
|
|
"epoch": 3.228476644015196,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003982078393068952,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.15184228122234344,
|
|
"num_tokens": 65298142.0,
|
|
"step": 30170
|
|
},
|
|
{
|
|
"entropy": 6.4019382953643795,
|
|
"epoch": 3.22901171812296,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000398175845897466,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.15683982223272325,
|
|
"num_tokens": 65308802.0,
|
|
"step": 30175
|
|
},
|
|
{
|
|
"entropy": 6.469412326812744,
|
|
"epoch": 3.229546792230724,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003981438489313516,
|
|
"loss": 6.0606,
|
|
"mean_token_accuracy": 0.14457352310419083,
|
|
"num_tokens": 65319749.0,
|
|
"step": 30180
|
|
},
|
|
{
|
|
"entropy": 6.5043689727783205,
|
|
"epoch": 3.230081866338488,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039811184840947585,
|
|
"loss": 6.0757,
|
|
"mean_token_accuracy": 0.15361550003290175,
|
|
"num_tokens": 65331519.0,
|
|
"step": 30185
|
|
},
|
|
{
|
|
"entropy": 6.521339750289917,
|
|
"epoch": 3.230616940446252,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003980798443327629,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.14756569415330886,
|
|
"num_tokens": 65342197.0,
|
|
"step": 30190
|
|
},
|
|
{
|
|
"entropy": 6.479731512069702,
|
|
"epoch": 3.2311520145540156,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00039804783670213656,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.14953790828585625,
|
|
"num_tokens": 65353429.0,
|
|
"step": 30195
|
|
},
|
|
{
|
|
"entropy": 6.517356920242309,
|
|
"epoch": 3.2316870886617797,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039801582551852126,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.15467025190591813,
|
|
"num_tokens": 65363836.0,
|
|
"step": 30200
|
|
},
|
|
{
|
|
"entropy": 6.490703153610229,
|
|
"epoch": 3.2322221627695438,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003979838107828414,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.15151716619729996,
|
|
"num_tokens": 65374329.0,
|
|
"step": 30205
|
|
},
|
|
{
|
|
"entropy": 6.472425842285157,
|
|
"epoch": 3.2327572368773074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039795179249602113,
|
|
"loss": 6.0445,
|
|
"mean_token_accuracy": 0.1499427616596222,
|
|
"num_tokens": 65385686.0,
|
|
"step": 30210
|
|
},
|
|
{
|
|
"entropy": 6.439754343032837,
|
|
"epoch": 3.2332923109850715,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00039791977065898525,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.14565275385975837,
|
|
"num_tokens": 65397181.0,
|
|
"step": 30215
|
|
},
|
|
{
|
|
"entropy": 6.471865653991699,
|
|
"epoch": 3.233827385092835,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039788774527265824,
|
|
"loss": 6.0239,
|
|
"mean_token_accuracy": 0.14747481197118759,
|
|
"num_tokens": 65407935.0,
|
|
"step": 30220
|
|
},
|
|
{
|
|
"entropy": 6.49934573173523,
|
|
"epoch": 3.2343624592005993,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003978557163379649,
|
|
"loss": 6.0148,
|
|
"mean_token_accuracy": 0.1479301556944847,
|
|
"num_tokens": 65418699.0,
|
|
"step": 30225
|
|
},
|
|
{
|
|
"entropy": 6.489491271972656,
|
|
"epoch": 3.2348975333083634,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003978236838558298,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.15904944241046906,
|
|
"num_tokens": 65429783.0,
|
|
"step": 30230
|
|
},
|
|
{
|
|
"entropy": 6.38047080039978,
|
|
"epoch": 3.235432607416127,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003977916478271783,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.15889597237110137,
|
|
"num_tokens": 65441001.0,
|
|
"step": 30235
|
|
},
|
|
{
|
|
"entropy": 6.49019422531128,
|
|
"epoch": 3.235967681523891,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0003977596082529352,
|
|
"loss": 6.0579,
|
|
"mean_token_accuracy": 0.15232973247766496,
|
|
"num_tokens": 65451219.0,
|
|
"step": 30240
|
|
},
|
|
{
|
|
"entropy": 6.477341175079346,
|
|
"epoch": 3.236502755631655,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003977275651340256,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.14952543526887893,
|
|
"num_tokens": 65461081.0,
|
|
"step": 30245
|
|
},
|
|
{
|
|
"entropy": 6.491780757904053,
|
|
"epoch": 3.237037829739419,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003976955184713748,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.15321510434150695,
|
|
"num_tokens": 65470391.0,
|
|
"step": 30250
|
|
},
|
|
{
|
|
"entropy": 6.419720649719238,
|
|
"epoch": 3.237572903847183,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039766346826590823,
|
|
"loss": 6.0468,
|
|
"mean_token_accuracy": 0.1461604692041874,
|
|
"num_tokens": 65482199.0,
|
|
"step": 30255
|
|
},
|
|
{
|
|
"entropy": 6.477277231216431,
|
|
"epoch": 3.2381079779549466,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003976314145185511,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.15826510787010192,
|
|
"num_tokens": 65492497.0,
|
|
"step": 30260
|
|
},
|
|
{
|
|
"entropy": 6.4140101909637455,
|
|
"epoch": 3.2386430520627107,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039759935723022923,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.1563556432723999,
|
|
"num_tokens": 65503769.0,
|
|
"step": 30265
|
|
},
|
|
{
|
|
"entropy": 6.481083250045776,
|
|
"epoch": 3.2391781261704744,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039756729640186815,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.15251878499984742,
|
|
"num_tokens": 65513582.0,
|
|
"step": 30270
|
|
},
|
|
{
|
|
"entropy": 6.471528148651123,
|
|
"epoch": 3.2397132002782385,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003975352320343935,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.15004192665219307,
|
|
"num_tokens": 65523829.0,
|
|
"step": 30275
|
|
},
|
|
{
|
|
"entropy": 6.534209156036377,
|
|
"epoch": 3.2402482743860026,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039750316412873134,
|
|
"loss": 6.0151,
|
|
"mean_token_accuracy": 0.15031206607818604,
|
|
"num_tokens": 65534893.0,
|
|
"step": 30280
|
|
},
|
|
{
|
|
"entropy": 6.46133942604065,
|
|
"epoch": 3.2407833484937663,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003974710926858075,
|
|
"loss": 5.8935,
|
|
"mean_token_accuracy": 0.16644540429115295,
|
|
"num_tokens": 65544551.0,
|
|
"step": 30285
|
|
},
|
|
{
|
|
"entropy": 6.461482524871826,
|
|
"epoch": 3.2413184226015304,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003974390177065481,
|
|
"loss": 6.0269,
|
|
"mean_token_accuracy": 0.1528521478176117,
|
|
"num_tokens": 65554991.0,
|
|
"step": 30290
|
|
},
|
|
{
|
|
"entropy": 6.447877025604248,
|
|
"epoch": 3.241853496709294,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003974069391918792,
|
|
"loss": 5.996,
|
|
"mean_token_accuracy": 0.15539947003126145,
|
|
"num_tokens": 65565784.0,
|
|
"step": 30295
|
|
},
|
|
{
|
|
"entropy": 6.462133312225342,
|
|
"epoch": 3.242388570817058,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039737485714272727,
|
|
"loss": 6.0244,
|
|
"mean_token_accuracy": 0.15464544743299485,
|
|
"num_tokens": 65575545.0,
|
|
"step": 30300
|
|
},
|
|
{
|
|
"entropy": 6.529432582855224,
|
|
"epoch": 3.242923644924822,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003973427715600184,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.14405509531497956,
|
|
"num_tokens": 65585987.0,
|
|
"step": 30305
|
|
},
|
|
{
|
|
"entropy": 6.50094518661499,
|
|
"epoch": 3.243458719032586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003973106824446792,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.1476336672902107,
|
|
"num_tokens": 65596991.0,
|
|
"step": 30310
|
|
},
|
|
{
|
|
"entropy": 6.484509134292603,
|
|
"epoch": 3.24399379314035,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039727858979763634,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.15494324862957,
|
|
"num_tokens": 65608161.0,
|
|
"step": 30315
|
|
},
|
|
{
|
|
"entropy": 6.537976217269898,
|
|
"epoch": 3.244528867248114,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039724649361981627,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.1540479063987732,
|
|
"num_tokens": 65619859.0,
|
|
"step": 30320
|
|
},
|
|
{
|
|
"entropy": 6.4742332935333256,
|
|
"epoch": 3.2450639413558777,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003972143939121459,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.1463281236588955,
|
|
"num_tokens": 65631400.0,
|
|
"step": 30325
|
|
},
|
|
{
|
|
"entropy": 6.504411888122559,
|
|
"epoch": 3.245599015463642,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003971822906755521,
|
|
"loss": 6.112,
|
|
"mean_token_accuracy": 0.14348655790090561,
|
|
"num_tokens": 65643519.0,
|
|
"step": 30330
|
|
},
|
|
{
|
|
"entropy": 6.470232391357422,
|
|
"epoch": 3.2461340895714055,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039715018391096185,
|
|
"loss": 5.9407,
|
|
"mean_token_accuracy": 0.15986382067203522,
|
|
"num_tokens": 65654628.0,
|
|
"step": 30335
|
|
},
|
|
{
|
|
"entropy": 6.457698154449463,
|
|
"epoch": 3.2466691636791696,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003971180736193022,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.15106951147317887,
|
|
"num_tokens": 65665910.0,
|
|
"step": 30340
|
|
},
|
|
{
|
|
"entropy": 6.551915979385376,
|
|
"epoch": 3.2472042377869337,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039708595980150025,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.14580769389867781,
|
|
"num_tokens": 65677126.0,
|
|
"step": 30345
|
|
},
|
|
{
|
|
"entropy": 6.520595598220825,
|
|
"epoch": 3.2477393118946973,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003970538424584834,
|
|
"loss": 6.0248,
|
|
"mean_token_accuracy": 0.15161976516246795,
|
|
"num_tokens": 65687609.0,
|
|
"step": 30350
|
|
},
|
|
{
|
|
"entropy": 6.490599870681763,
|
|
"epoch": 3.2482743860024614,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00039702172159117907,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.1500605270266533,
|
|
"num_tokens": 65699585.0,
|
|
"step": 30355
|
|
},
|
|
{
|
|
"entropy": 6.484717464447021,
|
|
"epoch": 3.248809460110225,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003969895972005146,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.14894902110099792,
|
|
"num_tokens": 65710455.0,
|
|
"step": 30360
|
|
},
|
|
{
|
|
"entropy": 6.506793546676636,
|
|
"epoch": 3.249344534217989,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003969574692874177,
|
|
"loss": 5.9845,
|
|
"mean_token_accuracy": 0.15364105850458146,
|
|
"num_tokens": 65721797.0,
|
|
"step": 30365
|
|
},
|
|
{
|
|
"entropy": 6.453266048431397,
|
|
"epoch": 3.2498796083257533,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00039692533785281605,
|
|
"loss": 5.9713,
|
|
"mean_token_accuracy": 0.158487531542778,
|
|
"num_tokens": 65733571.0,
|
|
"step": 30370
|
|
},
|
|
{
|
|
"entropy": 6.493956184387207,
|
|
"epoch": 3.250414682433517,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003968932028976373,
|
|
"loss": 6.07,
|
|
"mean_token_accuracy": 0.14769575595855713,
|
|
"num_tokens": 65744501.0,
|
|
"step": 30375
|
|
},
|
|
{
|
|
"entropy": 6.45971155166626,
|
|
"epoch": 3.250949756541281,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039686106442280946,
|
|
"loss": 6.0198,
|
|
"mean_token_accuracy": 0.15478594303131105,
|
|
"num_tokens": 65755428.0,
|
|
"step": 30380
|
|
},
|
|
{
|
|
"entropy": 6.511416053771972,
|
|
"epoch": 3.2514848306490447,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003968289224292606,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.15281659215688706,
|
|
"num_tokens": 65765535.0,
|
|
"step": 30385
|
|
},
|
|
{
|
|
"entropy": 6.391291713714599,
|
|
"epoch": 3.252019904756809,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039679677691791866,
|
|
"loss": 5.9699,
|
|
"mean_token_accuracy": 0.15159481316804885,
|
|
"num_tokens": 65776084.0,
|
|
"step": 30390
|
|
},
|
|
{
|
|
"entropy": 6.350443410873413,
|
|
"epoch": 3.252554978864573,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003967646278897119,
|
|
"loss": 5.973,
|
|
"mean_token_accuracy": 0.1572132095694542,
|
|
"num_tokens": 65787470.0,
|
|
"step": 30395
|
|
},
|
|
{
|
|
"entropy": 6.4085156440734865,
|
|
"epoch": 3.2530900529723366,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003967324753455687,
|
|
"loss": 5.9818,
|
|
"mean_token_accuracy": 0.16009857803583144,
|
|
"num_tokens": 65796942.0,
|
|
"step": 30400
|
|
},
|
|
{
|
|
"entropy": 6.356693458557129,
|
|
"epoch": 3.2536251270801007,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039670031928641723,
|
|
"loss": 5.942,
|
|
"mean_token_accuracy": 0.15631607323884963,
|
|
"num_tokens": 65806902.0,
|
|
"step": 30405
|
|
},
|
|
{
|
|
"entropy": 6.5245476245880125,
|
|
"epoch": 3.2541602011878643,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039666815971318623,
|
|
"loss": 6.0339,
|
|
"mean_token_accuracy": 0.1514114186167717,
|
|
"num_tokens": 65817689.0,
|
|
"step": 30410
|
|
},
|
|
{
|
|
"entropy": 6.455112028121948,
|
|
"epoch": 3.2546952752956284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039663599662680414,
|
|
"loss": 6.0275,
|
|
"mean_token_accuracy": 0.15641121715307235,
|
|
"num_tokens": 65827995.0,
|
|
"step": 30415
|
|
},
|
|
{
|
|
"entropy": 6.509525918960572,
|
|
"epoch": 3.2552303494033925,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003966038300281999,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.1529524952173233,
|
|
"num_tokens": 65838449.0,
|
|
"step": 30420
|
|
},
|
|
{
|
|
"entropy": 6.473686981201172,
|
|
"epoch": 3.255765423511156,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000396571659918302,
|
|
"loss": 5.9655,
|
|
"mean_token_accuracy": 0.16300844699144362,
|
|
"num_tokens": 65847898.0,
|
|
"step": 30425
|
|
},
|
|
{
|
|
"entropy": 6.380824995040894,
|
|
"epoch": 3.2563004976189203,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003965394862980396,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.15740368217229844,
|
|
"num_tokens": 65859876.0,
|
|
"step": 30430
|
|
},
|
|
{
|
|
"entropy": 6.47112193107605,
|
|
"epoch": 3.2568355717266844,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003965073091683416,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.15496276468038558,
|
|
"num_tokens": 65869875.0,
|
|
"step": 30435
|
|
},
|
|
{
|
|
"entropy": 6.474406576156616,
|
|
"epoch": 3.257370645834448,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039647512853013703,
|
|
"loss": 6.0381,
|
|
"mean_token_accuracy": 0.15824462920427323,
|
|
"num_tokens": 65881351.0,
|
|
"step": 30440
|
|
},
|
|
{
|
|
"entropy": 6.451531887054443,
|
|
"epoch": 3.257905719942212,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003964429443843552,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.1535976782441139,
|
|
"num_tokens": 65892533.0,
|
|
"step": 30445
|
|
},
|
|
{
|
|
"entropy": 6.4120790481567385,
|
|
"epoch": 3.2584407940499758,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039641075673192564,
|
|
"loss": 5.9504,
|
|
"mean_token_accuracy": 0.15168272256851195,
|
|
"num_tokens": 65903754.0,
|
|
"step": 30450
|
|
},
|
|
{
|
|
"entropy": 6.383151960372925,
|
|
"epoch": 3.25897586815774,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039637856557377734,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.16193411499261856,
|
|
"num_tokens": 65915461.0,
|
|
"step": 30455
|
|
},
|
|
{
|
|
"entropy": 6.465198659896851,
|
|
"epoch": 3.2595109422655035,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039634637091083997,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.15467498525977136,
|
|
"num_tokens": 65927108.0,
|
|
"step": 30460
|
|
},
|
|
{
|
|
"entropy": 6.455716514587403,
|
|
"epoch": 3.2600460163732676,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039631417274404334,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.15545969903469087,
|
|
"num_tokens": 65937965.0,
|
|
"step": 30465
|
|
},
|
|
{
|
|
"entropy": 6.419666194915772,
|
|
"epoch": 3.2605810904810317,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00039628197107431694,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.16121579706668854,
|
|
"num_tokens": 65948393.0,
|
|
"step": 30470
|
|
},
|
|
{
|
|
"entropy": 6.427877569198609,
|
|
"epoch": 3.2611161645887954,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039624976590259064,
|
|
"loss": 5.989,
|
|
"mean_token_accuracy": 0.15446554124355316,
|
|
"num_tokens": 65958960.0,
|
|
"step": 30475
|
|
},
|
|
{
|
|
"entropy": 6.496758460998535,
|
|
"epoch": 3.2616512386965595,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00039621755722979446,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.14689398258924485,
|
|
"num_tokens": 65970937.0,
|
|
"step": 30480
|
|
},
|
|
{
|
|
"entropy": 6.549610328674317,
|
|
"epoch": 3.2621863128043236,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003961853450568583,
|
|
"loss": 6.0569,
|
|
"mean_token_accuracy": 0.15138455033302306,
|
|
"num_tokens": 65982444.0,
|
|
"step": 30485
|
|
},
|
|
{
|
|
"entropy": 6.564223289489746,
|
|
"epoch": 3.2627213869120872,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039615312938471236,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.15000004544854165,
|
|
"num_tokens": 65994392.0,
|
|
"step": 30490
|
|
},
|
|
{
|
|
"entropy": 6.5257251262664795,
|
|
"epoch": 3.2632564610198513,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039612091021428683,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.1512551188468933,
|
|
"num_tokens": 66004710.0,
|
|
"step": 30495
|
|
},
|
|
{
|
|
"entropy": 6.480291175842285,
|
|
"epoch": 3.263791535127615,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003960886875465121,
|
|
"loss": 6.0858,
|
|
"mean_token_accuracy": 0.1524755984544754,
|
|
"num_tokens": 66015402.0,
|
|
"step": 30500
|
|
},
|
|
{
|
|
"entropy": 6.408947086334228,
|
|
"epoch": 3.264326609235379,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039605646138231835,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.15544606149196624,
|
|
"num_tokens": 66026795.0,
|
|
"step": 30505
|
|
},
|
|
{
|
|
"entropy": 6.486134243011475,
|
|
"epoch": 3.264861683343143,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039602423172263644,
|
|
"loss": 5.9881,
|
|
"mean_token_accuracy": 0.15890254378318786,
|
|
"num_tokens": 66037339.0,
|
|
"step": 30510
|
|
},
|
|
{
|
|
"entropy": 6.424004030227661,
|
|
"epoch": 3.265396757450907,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003959919985683968,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.15199290290474893,
|
|
"num_tokens": 66047415.0,
|
|
"step": 30515
|
|
},
|
|
{
|
|
"entropy": 6.497801685333252,
|
|
"epoch": 3.265931831558671,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039595976192053023,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.1551337346434593,
|
|
"num_tokens": 66057475.0,
|
|
"step": 30520
|
|
},
|
|
{
|
|
"entropy": 6.489008283615112,
|
|
"epoch": 3.2664669056664346,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003959275217799675,
|
|
"loss": 5.9672,
|
|
"mean_token_accuracy": 0.1574543073773384,
|
|
"num_tokens": 66067018.0,
|
|
"step": 30525
|
|
},
|
|
{
|
|
"entropy": 6.444043731689453,
|
|
"epoch": 3.2670019797741987,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003958952781476396,
|
|
"loss": 6.0489,
|
|
"mean_token_accuracy": 0.1511401727795601,
|
|
"num_tokens": 66077822.0,
|
|
"step": 30530
|
|
},
|
|
{
|
|
"entropy": 6.478795957565308,
|
|
"epoch": 3.267537053881963,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003958630310244775,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.1541394278407097,
|
|
"num_tokens": 66088849.0,
|
|
"step": 30535
|
|
},
|
|
{
|
|
"entropy": 6.555434370040894,
|
|
"epoch": 3.2680721279897265,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039583078041141237,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.1529540926218033,
|
|
"num_tokens": 66098516.0,
|
|
"step": 30540
|
|
},
|
|
{
|
|
"entropy": 6.481693363189697,
|
|
"epoch": 3.2686072020974906,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003957985263093754,
|
|
"loss": 6.0504,
|
|
"mean_token_accuracy": 0.15354204624891282,
|
|
"num_tokens": 66109202.0,
|
|
"step": 30545
|
|
},
|
|
{
|
|
"entropy": 6.482135391235351,
|
|
"epoch": 3.2691422762052547,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000395766268719298,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.15463745594024658,
|
|
"num_tokens": 66119445.0,
|
|
"step": 30550
|
|
},
|
|
{
|
|
"entropy": 6.440516710281372,
|
|
"epoch": 3.2696773503130183,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039573400764211157,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.15710844993591308,
|
|
"num_tokens": 66129922.0,
|
|
"step": 30555
|
|
},
|
|
{
|
|
"entropy": 6.489928197860718,
|
|
"epoch": 3.2702124244207824,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003957017430787476,
|
|
"loss": 6.0871,
|
|
"mean_token_accuracy": 0.14634568691253663,
|
|
"num_tokens": 66141118.0,
|
|
"step": 30560
|
|
},
|
|
{
|
|
"entropy": 6.56249737739563,
|
|
"epoch": 3.270747498528546,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039566947503013786,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.15661334246397018,
|
|
"num_tokens": 66152415.0,
|
|
"step": 30565
|
|
},
|
|
{
|
|
"entropy": 6.440097904205322,
|
|
"epoch": 3.27128257263631,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003956372034972139,
|
|
"loss": 5.9849,
|
|
"mean_token_accuracy": 0.1506528824567795,
|
|
"num_tokens": 66163086.0,
|
|
"step": 30570
|
|
},
|
|
{
|
|
"entropy": 6.421419429779053,
|
|
"epoch": 3.271817646744074,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00039560492848090764,
|
|
"loss": 6.0244,
|
|
"mean_token_accuracy": 0.15224485397338866,
|
|
"num_tokens": 66173020.0,
|
|
"step": 30575
|
|
},
|
|
{
|
|
"entropy": 6.484832429885865,
|
|
"epoch": 3.272352720851838,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000395572649982151,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.15017155855894088,
|
|
"num_tokens": 66183979.0,
|
|
"step": 30580
|
|
},
|
|
{
|
|
"entropy": 6.5438666343688965,
|
|
"epoch": 3.272887794959602,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039554036800187604,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.15439605116844177,
|
|
"num_tokens": 66194703.0,
|
|
"step": 30585
|
|
},
|
|
{
|
|
"entropy": 6.459999322891235,
|
|
"epoch": 3.2734228690673657,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039550808254101497,
|
|
"loss": 6.0359,
|
|
"mean_token_accuracy": 0.14990227445960044,
|
|
"num_tokens": 66206041.0,
|
|
"step": 30590
|
|
},
|
|
{
|
|
"entropy": 6.421757936477661,
|
|
"epoch": 3.27395794317513,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039547579360049977,
|
|
"loss": 6.0525,
|
|
"mean_token_accuracy": 0.1544373944401741,
|
|
"num_tokens": 66218197.0,
|
|
"step": 30595
|
|
},
|
|
{
|
|
"entropy": 6.524124670028686,
|
|
"epoch": 3.274493017282894,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039544350118126315,
|
|
"loss": 6.0242,
|
|
"mean_token_accuracy": 0.1481299877166748,
|
|
"num_tokens": 66229261.0,
|
|
"step": 30600
|
|
},
|
|
{
|
|
"entropy": 6.506369400024414,
|
|
"epoch": 3.2750280913906575,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003954112052842373,
|
|
"loss": 5.9665,
|
|
"mean_token_accuracy": 0.16500921696424484,
|
|
"num_tokens": 66240162.0,
|
|
"step": 30605
|
|
},
|
|
{
|
|
"entropy": 6.324045944213867,
|
|
"epoch": 3.2755631654984216,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003953789059103548,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.15386699736118317,
|
|
"num_tokens": 66250284.0,
|
|
"step": 30610
|
|
},
|
|
{
|
|
"entropy": 6.489652872085571,
|
|
"epoch": 3.2760982396061853,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039534660306054836,
|
|
"loss": 6.0764,
|
|
"mean_token_accuracy": 0.14890287071466446,
|
|
"num_tokens": 66261164.0,
|
|
"step": 30615
|
|
},
|
|
{
|
|
"entropy": 6.488982629776001,
|
|
"epoch": 3.2766333137139494,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039531429673575057,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.15709834694862365,
|
|
"num_tokens": 66272201.0,
|
|
"step": 30620
|
|
},
|
|
{
|
|
"entropy": 6.456832838058472,
|
|
"epoch": 3.2771683878217135,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039528198693689444,
|
|
"loss": 6.0575,
|
|
"mean_token_accuracy": 0.15903141349554062,
|
|
"num_tokens": 66281297.0,
|
|
"step": 30625
|
|
},
|
|
{
|
|
"entropy": 6.431734561920166,
|
|
"epoch": 3.277703461929477,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003952496736649129,
|
|
"loss": 5.9972,
|
|
"mean_token_accuracy": 0.1533118724822998,
|
|
"num_tokens": 66290990.0,
|
|
"step": 30630
|
|
},
|
|
{
|
|
"entropy": 6.46439118385315,
|
|
"epoch": 3.2782385360372412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003952173569207388,
|
|
"loss": 6.0303,
|
|
"mean_token_accuracy": 0.14964908212423325,
|
|
"num_tokens": 66301971.0,
|
|
"step": 30635
|
|
},
|
|
{
|
|
"entropy": 6.506560468673706,
|
|
"epoch": 3.278773610145005,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003951850367053054,
|
|
"loss": 6.1003,
|
|
"mean_token_accuracy": 0.14357309490442277,
|
|
"num_tokens": 66313576.0,
|
|
"step": 30640
|
|
},
|
|
{
|
|
"entropy": 6.5973114490509035,
|
|
"epoch": 3.279308684252769,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003951527130195461,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.14866611510515212,
|
|
"num_tokens": 66325367.0,
|
|
"step": 30645
|
|
},
|
|
{
|
|
"entropy": 6.4512184143066404,
|
|
"epoch": 3.279843758360533,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039512038586439404,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.1619033619761467,
|
|
"num_tokens": 66335686.0,
|
|
"step": 30650
|
|
},
|
|
{
|
|
"entropy": 6.414826583862305,
|
|
"epoch": 3.2803788324682968,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039508805524078263,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.16021918505430222,
|
|
"num_tokens": 66345963.0,
|
|
"step": 30655
|
|
},
|
|
{
|
|
"entropy": 6.439639377593994,
|
|
"epoch": 3.280913906576061,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039505572114964554,
|
|
"loss": 6.0692,
|
|
"mean_token_accuracy": 0.15502590537071229,
|
|
"num_tokens": 66357781.0,
|
|
"step": 30660
|
|
},
|
|
{
|
|
"entropy": 6.533792734146118,
|
|
"epoch": 3.281448980683825,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003950233835919164,
|
|
"loss": 6.0416,
|
|
"mean_token_accuracy": 0.15782453417778014,
|
|
"num_tokens": 66369360.0,
|
|
"step": 30665
|
|
},
|
|
{
|
|
"entropy": 6.431480932235718,
|
|
"epoch": 3.2819840547915886,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003949910425685289,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.1519111581146717,
|
|
"num_tokens": 66381481.0,
|
|
"step": 30670
|
|
},
|
|
{
|
|
"entropy": 6.461650466918945,
|
|
"epoch": 3.2825191288993527,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003949586980804169,
|
|
"loss": 5.9859,
|
|
"mean_token_accuracy": 0.1538042441010475,
|
|
"num_tokens": 66391469.0,
|
|
"step": 30675
|
|
},
|
|
{
|
|
"entropy": 6.4686532497406,
|
|
"epoch": 3.2830542030071164,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039492635012851443,
|
|
"loss": 6.0071,
|
|
"mean_token_accuracy": 0.14981972128152848,
|
|
"num_tokens": 66402094.0,
|
|
"step": 30680
|
|
},
|
|
{
|
|
"entropy": 6.497920083999634,
|
|
"epoch": 3.2835892771148805,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039489399871375536,
|
|
"loss": 5.9905,
|
|
"mean_token_accuracy": 0.15588995367288588,
|
|
"num_tokens": 66412149.0,
|
|
"step": 30685
|
|
},
|
|
{
|
|
"entropy": 6.497140121459961,
|
|
"epoch": 3.284124351222644,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003948616438370739,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.14880287498235703,
|
|
"num_tokens": 66423502.0,
|
|
"step": 30690
|
|
},
|
|
{
|
|
"entropy": 6.537202548980713,
|
|
"epoch": 3.2846594253304082,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003948292854994045,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.15604249984025956,
|
|
"num_tokens": 66433684.0,
|
|
"step": 30695
|
|
},
|
|
{
|
|
"entropy": 6.363313961029053,
|
|
"epoch": 3.2851944994381723,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039479692370168116,
|
|
"loss": 5.9428,
|
|
"mean_token_accuracy": 0.16413553655147553,
|
|
"num_tokens": 66444728.0,
|
|
"step": 30700
|
|
},
|
|
{
|
|
"entropy": 6.418261003494263,
|
|
"epoch": 3.285729573545936,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039476455844483847,
|
|
"loss": 6.0271,
|
|
"mean_token_accuracy": 0.15299393385648727,
|
|
"num_tokens": 66456117.0,
|
|
"step": 30705
|
|
},
|
|
{
|
|
"entropy": 6.477247428894043,
|
|
"epoch": 3.2862646476537,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003947321897298111,
|
|
"loss": 6.0595,
|
|
"mean_token_accuracy": 0.15011582672595977,
|
|
"num_tokens": 66466467.0,
|
|
"step": 30710
|
|
},
|
|
{
|
|
"entropy": 6.5166209697723385,
|
|
"epoch": 3.286799721761464,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003946998175575335,
|
|
"loss": 6.1137,
|
|
"mean_token_accuracy": 0.1408667303621769,
|
|
"num_tokens": 66477702.0,
|
|
"step": 30715
|
|
},
|
|
{
|
|
"entropy": 6.482959508895874,
|
|
"epoch": 3.287334795869228,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039466744192894046,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.15808115899562836,
|
|
"num_tokens": 66489359.0,
|
|
"step": 30720
|
|
},
|
|
{
|
|
"entropy": 6.472474193572998,
|
|
"epoch": 3.287869869976992,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003946350628449669,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.15848996490240097,
|
|
"num_tokens": 66500337.0,
|
|
"step": 30725
|
|
},
|
|
{
|
|
"entropy": 6.474171257019043,
|
|
"epoch": 3.2884049440847556,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039460268030654767,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.15630098879337312,
|
|
"num_tokens": 66510010.0,
|
|
"step": 30730
|
|
},
|
|
{
|
|
"entropy": 6.448852157592773,
|
|
"epoch": 3.2889400181925197,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039457029431461794,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.15370435416698455,
|
|
"num_tokens": 66521570.0,
|
|
"step": 30735
|
|
},
|
|
{
|
|
"entropy": 6.491447591781617,
|
|
"epoch": 3.2894750923002833,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003945379048701127,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.1563722625374794,
|
|
"num_tokens": 66532825.0,
|
|
"step": 30740
|
|
},
|
|
{
|
|
"entropy": 6.5321852684021,
|
|
"epoch": 3.2900101664080474,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039450551197396725,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.1505278617143631,
|
|
"num_tokens": 66543265.0,
|
|
"step": 30745
|
|
},
|
|
{
|
|
"entropy": 6.462469863891601,
|
|
"epoch": 3.2905452405158115,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039447311562711693,
|
|
"loss": 6.153,
|
|
"mean_token_accuracy": 0.14197903424501418,
|
|
"num_tokens": 66553589.0,
|
|
"step": 30750
|
|
},
|
|
{
|
|
"entropy": 6.413259077072143,
|
|
"epoch": 3.291080314623575,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039444071583049717,
|
|
"loss": 6.0072,
|
|
"mean_token_accuracy": 0.1557167187333107,
|
|
"num_tokens": 66564679.0,
|
|
"step": 30755
|
|
},
|
|
{
|
|
"entropy": 6.506803846359253,
|
|
"epoch": 3.2916153887313393,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039440831258504363,
|
|
"loss": 6.0574,
|
|
"mean_token_accuracy": 0.15377009734511377,
|
|
"num_tokens": 66576408.0,
|
|
"step": 30760
|
|
},
|
|
{
|
|
"entropy": 6.55422158241272,
|
|
"epoch": 3.2921504628391034,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039437590589169177,
|
|
"loss": 6.0971,
|
|
"mean_token_accuracy": 0.15141231715679168,
|
|
"num_tokens": 66587535.0,
|
|
"step": 30765
|
|
},
|
|
{
|
|
"entropy": 6.508157730102539,
|
|
"epoch": 3.292685536946867,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039434349575137736,
|
|
"loss": 6.0658,
|
|
"mean_token_accuracy": 0.15163005888462067,
|
|
"num_tokens": 66598493.0,
|
|
"step": 30770
|
|
},
|
|
{
|
|
"entropy": 6.465548372268676,
|
|
"epoch": 3.293220611054631,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003943110821650364,
|
|
"loss": 5.9957,
|
|
"mean_token_accuracy": 0.15177962630987168,
|
|
"num_tokens": 66609366.0,
|
|
"step": 30775
|
|
},
|
|
{
|
|
"entropy": 6.399290084838867,
|
|
"epoch": 3.293755685162395,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003942786651336046,
|
|
"loss": 5.9207,
|
|
"mean_token_accuracy": 0.1607976883649826,
|
|
"num_tokens": 66619902.0,
|
|
"step": 30780
|
|
},
|
|
{
|
|
"entropy": 6.47034215927124,
|
|
"epoch": 3.294290759270159,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003942462446580181,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.14383357614278794,
|
|
"num_tokens": 66630629.0,
|
|
"step": 30785
|
|
},
|
|
{
|
|
"entropy": 6.504256296157837,
|
|
"epoch": 3.294825833377923,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039421382073921306,
|
|
"loss": 6.0419,
|
|
"mean_token_accuracy": 0.15449357479810716,
|
|
"num_tokens": 66640720.0,
|
|
"step": 30790
|
|
},
|
|
{
|
|
"entropy": 6.5148210525512695,
|
|
"epoch": 3.2953609074856867,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003941813933781257,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.14589962661266326,
|
|
"num_tokens": 66653021.0,
|
|
"step": 30795
|
|
},
|
|
{
|
|
"entropy": 6.486313676834106,
|
|
"epoch": 3.2958959815934508,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003941489625756923,
|
|
"loss": 6.0284,
|
|
"mean_token_accuracy": 0.14917487651109695,
|
|
"num_tokens": 66663997.0,
|
|
"step": 30800
|
|
},
|
|
{
|
|
"entropy": 6.480428075790405,
|
|
"epoch": 3.2964310557012144,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039411652833284944,
|
|
"loss": 6.0027,
|
|
"mean_token_accuracy": 0.14644162505865096,
|
|
"num_tokens": 66674632.0,
|
|
"step": 30805
|
|
},
|
|
{
|
|
"entropy": 6.423187398910523,
|
|
"epoch": 3.2969661298089785,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003940840906505336,
|
|
"loss": 6.0028,
|
|
"mean_token_accuracy": 0.16091371476650237,
|
|
"num_tokens": 66685289.0,
|
|
"step": 30810
|
|
},
|
|
{
|
|
"entropy": 6.529962110519409,
|
|
"epoch": 3.2975012039167426,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003940516495296813,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.1510309800505638,
|
|
"num_tokens": 66696448.0,
|
|
"step": 30815
|
|
},
|
|
{
|
|
"entropy": 6.522752523422241,
|
|
"epoch": 3.2980362780245063,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039401920497122934,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.15415026545524596,
|
|
"num_tokens": 66706186.0,
|
|
"step": 30820
|
|
},
|
|
{
|
|
"entropy": 6.46390323638916,
|
|
"epoch": 3.2985713521322704,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039398675697611464,
|
|
"loss": 6.1184,
|
|
"mean_token_accuracy": 0.1455588683485985,
|
|
"num_tokens": 66717586.0,
|
|
"step": 30825
|
|
},
|
|
{
|
|
"entropy": 6.514818954467773,
|
|
"epoch": 3.2991064262400345,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000393954305545274,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.15697546899318696,
|
|
"num_tokens": 66727985.0,
|
|
"step": 30830
|
|
},
|
|
{
|
|
"entropy": 6.46750111579895,
|
|
"epoch": 3.299641500347798,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039392185067964444,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.15512907207012178,
|
|
"num_tokens": 66738966.0,
|
|
"step": 30835
|
|
},
|
|
{
|
|
"entropy": 6.433013153076172,
|
|
"epoch": 3.3001765744555622,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039388939238016327,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.15505146682262422,
|
|
"num_tokens": 66750442.0,
|
|
"step": 30840
|
|
},
|
|
{
|
|
"entropy": 6.502207183837891,
|
|
"epoch": 3.300711648563326,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003938569306477675,
|
|
"loss": 6.0747,
|
|
"mean_token_accuracy": 0.15423641800880433,
|
|
"num_tokens": 66761246.0,
|
|
"step": 30845
|
|
},
|
|
{
|
|
"entropy": 6.525602245330811,
|
|
"epoch": 3.30124672267109,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039382446548339464,
|
|
"loss": 6.0728,
|
|
"mean_token_accuracy": 0.15020278245210647,
|
|
"num_tokens": 66771711.0,
|
|
"step": 30850
|
|
},
|
|
{
|
|
"entropy": 6.345941257476807,
|
|
"epoch": 3.3017817967788536,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003937919968879819,
|
|
"loss": 5.9573,
|
|
"mean_token_accuracy": 0.16535712257027627,
|
|
"num_tokens": 66783185.0,
|
|
"step": 30855
|
|
},
|
|
{
|
|
"entropy": 6.569365835189819,
|
|
"epoch": 3.3023168708866177,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003937595248624671,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.15655670464038848,
|
|
"num_tokens": 66794541.0,
|
|
"step": 30860
|
|
},
|
|
{
|
|
"entropy": 6.481019926071167,
|
|
"epoch": 3.302851944994382,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003937270494077876,
|
|
"loss": 6.0214,
|
|
"mean_token_accuracy": 0.15210807025432588,
|
|
"num_tokens": 66805617.0,
|
|
"step": 30865
|
|
},
|
|
{
|
|
"entropy": 6.474903726577759,
|
|
"epoch": 3.3033870191021455,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039369457052488134,
|
|
"loss": 6.0437,
|
|
"mean_token_accuracy": 0.15722212493419646,
|
|
"num_tokens": 66814784.0,
|
|
"step": 30870
|
|
},
|
|
{
|
|
"entropy": 6.498279666900634,
|
|
"epoch": 3.3039220932099096,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039366208821468596,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.147596388310194,
|
|
"num_tokens": 66825416.0,
|
|
"step": 30875
|
|
},
|
|
{
|
|
"entropy": 6.444157075881958,
|
|
"epoch": 3.3044571673176737,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003936296024781394,
|
|
"loss": 6.0126,
|
|
"mean_token_accuracy": 0.15549614727497102,
|
|
"num_tokens": 66836471.0,
|
|
"step": 30880
|
|
},
|
|
{
|
|
"entropy": 6.41310830116272,
|
|
"epoch": 3.3049922414254373,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00039359711331617993,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.15247081816196442,
|
|
"num_tokens": 66848911.0,
|
|
"step": 30885
|
|
},
|
|
{
|
|
"entropy": 6.481614112854004,
|
|
"epoch": 3.3055273155332014,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039356462072974533,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.15151599496603013,
|
|
"num_tokens": 66860095.0,
|
|
"step": 30890
|
|
},
|
|
{
|
|
"entropy": 6.392287302017212,
|
|
"epoch": 3.306062389640965,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00039353212471977394,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.1604069709777832,
|
|
"num_tokens": 66872676.0,
|
|
"step": 30895
|
|
},
|
|
{
|
|
"entropy": 6.505472183227539,
|
|
"epoch": 3.306597463748729,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003934996252872042,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.14831532910466194,
|
|
"num_tokens": 66883686.0,
|
|
"step": 30900
|
|
},
|
|
{
|
|
"entropy": 6.478116178512574,
|
|
"epoch": 3.3071325378564933,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003934671224329744,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.1480938173830509,
|
|
"num_tokens": 66895971.0,
|
|
"step": 30905
|
|
},
|
|
{
|
|
"entropy": 6.532090139389038,
|
|
"epoch": 3.307667611964257,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003934346161580231,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.14985392689704896,
|
|
"num_tokens": 66907840.0,
|
|
"step": 30910
|
|
},
|
|
{
|
|
"entropy": 6.517180585861206,
|
|
"epoch": 3.308202686072021,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039340210646328887,
|
|
"loss": 6.0804,
|
|
"mean_token_accuracy": 0.14881533533334732,
|
|
"num_tokens": 66918956.0,
|
|
"step": 30915
|
|
},
|
|
{
|
|
"entropy": 6.421125173568726,
|
|
"epoch": 3.3087377601797847,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003933695933497105,
|
|
"loss": 6.0003,
|
|
"mean_token_accuracy": 0.1565177008509636,
|
|
"num_tokens": 66929653.0,
|
|
"step": 30920
|
|
},
|
|
{
|
|
"entropy": 6.421623468399048,
|
|
"epoch": 3.309272834287549,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039333707681822664,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.15990629494190217,
|
|
"num_tokens": 66939268.0,
|
|
"step": 30925
|
|
},
|
|
{
|
|
"entropy": 6.422711420059204,
|
|
"epoch": 3.309807908395313,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039330455686977645,
|
|
"loss": 6.0349,
|
|
"mean_token_accuracy": 0.15489390417933463,
|
|
"num_tokens": 66949669.0,
|
|
"step": 30930
|
|
},
|
|
{
|
|
"entropy": 6.516010761260986,
|
|
"epoch": 3.3103429825030766,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003932720335052987,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.16010974049568177,
|
|
"num_tokens": 66959882.0,
|
|
"step": 30935
|
|
},
|
|
{
|
|
"entropy": 6.528467607498169,
|
|
"epoch": 3.3108780566108407,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003932395067257327,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.14783235937356948,
|
|
"num_tokens": 66972848.0,
|
|
"step": 30940
|
|
},
|
|
{
|
|
"entropy": 6.472320985794068,
|
|
"epoch": 3.3114131307186048,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003932069765320175,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.16075172871351243,
|
|
"num_tokens": 66983289.0,
|
|
"step": 30945
|
|
},
|
|
{
|
|
"entropy": 6.448467540740967,
|
|
"epoch": 3.3119482048263684,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039317444292509253,
|
|
"loss": 5.9935,
|
|
"mean_token_accuracy": 0.15615394935011864,
|
|
"num_tokens": 66994194.0,
|
|
"step": 30950
|
|
},
|
|
{
|
|
"entropy": 6.480628871917725,
|
|
"epoch": 3.3124832789341325,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00039314190590589696,
|
|
"loss": 6.0287,
|
|
"mean_token_accuracy": 0.15758306682109832,
|
|
"num_tokens": 67005889.0,
|
|
"step": 30955
|
|
},
|
|
{
|
|
"entropy": 6.437723588943482,
|
|
"epoch": 3.313018353041896,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003931093654753706,
|
|
"loss": 5.9527,
|
|
"mean_token_accuracy": 0.15652209669351577,
|
|
"num_tokens": 67017237.0,
|
|
"step": 30960
|
|
},
|
|
{
|
|
"entropy": 6.512154865264892,
|
|
"epoch": 3.3135534271496603,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003930768216344529,
|
|
"loss": 6.0238,
|
|
"mean_token_accuracy": 0.15517525970935822,
|
|
"num_tokens": 67027637.0,
|
|
"step": 30965
|
|
},
|
|
{
|
|
"entropy": 6.412390804290771,
|
|
"epoch": 3.314088501257424,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039304427438408354,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.15349312722682953,
|
|
"num_tokens": 67039039.0,
|
|
"step": 30970
|
|
},
|
|
{
|
|
"entropy": 6.44083046913147,
|
|
"epoch": 3.314623575365188,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039301172372520235,
|
|
"loss": 6.0383,
|
|
"mean_token_accuracy": 0.1501325398683548,
|
|
"num_tokens": 67048944.0,
|
|
"step": 30975
|
|
},
|
|
{
|
|
"entropy": 6.490383052825928,
|
|
"epoch": 3.315158649472952,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003929791696587492,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.15526601672172546,
|
|
"num_tokens": 67059724.0,
|
|
"step": 30980
|
|
},
|
|
{
|
|
"entropy": 6.477940416336059,
|
|
"epoch": 3.315693723580716,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003929466121856641,
|
|
"loss": 5.9751,
|
|
"mean_token_accuracy": 0.15467856973409652,
|
|
"num_tokens": 67070128.0,
|
|
"step": 30985
|
|
},
|
|
{
|
|
"entropy": 6.518723058700561,
|
|
"epoch": 3.31622879768848,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00039291405130688725,
|
|
"loss": 6.0517,
|
|
"mean_token_accuracy": 0.15169492363929749,
|
|
"num_tokens": 67080739.0,
|
|
"step": 30990
|
|
},
|
|
{
|
|
"entropy": 6.465508937835693,
|
|
"epoch": 3.316763871796244,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039288148702335863,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.15118373259902002,
|
|
"num_tokens": 67091020.0,
|
|
"step": 30995
|
|
},
|
|
{
|
|
"entropy": 6.408154153823853,
|
|
"epoch": 3.3172989459040076,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003928489193360186,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.14903202950954436,
|
|
"num_tokens": 67101201.0,
|
|
"step": 31000
|
|
},
|
|
{
|
|
"entropy": 6.454351997375488,
|
|
"epoch": 3.3178340200117717,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003928163482458078,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.16207730323076247,
|
|
"num_tokens": 67112829.0,
|
|
"step": 31005
|
|
},
|
|
{
|
|
"entropy": 6.555992221832275,
|
|
"epoch": 3.3183690941195354,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039278377375366624,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.15120434612035752,
|
|
"num_tokens": 67123626.0,
|
|
"step": 31010
|
|
},
|
|
{
|
|
"entropy": 6.4986790180206295,
|
|
"epoch": 3.3189041682272995,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00039275119586053487,
|
|
"loss": 6.0524,
|
|
"mean_token_accuracy": 0.15462590605020524,
|
|
"num_tokens": 67134858.0,
|
|
"step": 31015
|
|
},
|
|
{
|
|
"entropy": 6.424458408355713,
|
|
"epoch": 3.3194392423350636,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003927186145673543,
|
|
"loss": 5.9364,
|
|
"mean_token_accuracy": 0.15291513055562972,
|
|
"num_tokens": 67144496.0,
|
|
"step": 31020
|
|
},
|
|
{
|
|
"entropy": 6.442574453353882,
|
|
"epoch": 3.3199743164428273,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039268602987506526,
|
|
"loss": 6.0068,
|
|
"mean_token_accuracy": 0.16010928004980088,
|
|
"num_tokens": 67155443.0,
|
|
"step": 31025
|
|
},
|
|
{
|
|
"entropy": 6.554600572586059,
|
|
"epoch": 3.3205093905505914,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003926534417846086,
|
|
"loss": 6.0601,
|
|
"mean_token_accuracy": 0.14864143282175063,
|
|
"num_tokens": 67167604.0,
|
|
"step": 31030
|
|
},
|
|
{
|
|
"entropy": 6.450956583023071,
|
|
"epoch": 3.321044464658355,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039262085029692536,
|
|
"loss": 5.9847,
|
|
"mean_token_accuracy": 0.15527070611715316,
|
|
"num_tokens": 67177915.0,
|
|
"step": 31035
|
|
},
|
|
{
|
|
"entropy": 6.469762372970581,
|
|
"epoch": 3.321579538766119,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039258825541295666,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.1618947446346283,
|
|
"num_tokens": 67188515.0,
|
|
"step": 31040
|
|
},
|
|
{
|
|
"entropy": 6.460102319717407,
|
|
"epoch": 3.322114612873883,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039255565713364356,
|
|
"loss": 6.0287,
|
|
"mean_token_accuracy": 0.15610078871250152,
|
|
"num_tokens": 67199139.0,
|
|
"step": 31045
|
|
},
|
|
{
|
|
"entropy": 6.462683248519897,
|
|
"epoch": 3.322649686981647,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003925230554599273,
|
|
"loss": 6.0482,
|
|
"mean_token_accuracy": 0.1515887275338173,
|
|
"num_tokens": 67210335.0,
|
|
"step": 31050
|
|
},
|
|
{
|
|
"entropy": 6.49856481552124,
|
|
"epoch": 3.323184761089411,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039249045039274947,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.15731117725372315,
|
|
"num_tokens": 67220128.0,
|
|
"step": 31055
|
|
},
|
|
{
|
|
"entropy": 6.424364995956421,
|
|
"epoch": 3.3237198351971746,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003924578419330513,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.16587020307779313,
|
|
"num_tokens": 67231251.0,
|
|
"step": 31060
|
|
},
|
|
{
|
|
"entropy": 6.498381280899048,
|
|
"epoch": 3.3242549093049387,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003924252300817745,
|
|
"loss": 6.0457,
|
|
"mean_token_accuracy": 0.15195570141077042,
|
|
"num_tokens": 67243336.0,
|
|
"step": 31065
|
|
},
|
|
{
|
|
"entropy": 6.527823495864868,
|
|
"epoch": 3.324789983412703,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003923926148398606,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.1477130502462387,
|
|
"num_tokens": 67256210.0,
|
|
"step": 31070
|
|
},
|
|
{
|
|
"entropy": 6.498104667663574,
|
|
"epoch": 3.3253250575204665,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003923599962082516,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.1612095519900322,
|
|
"num_tokens": 67266271.0,
|
|
"step": 31075
|
|
},
|
|
{
|
|
"entropy": 6.458006954193115,
|
|
"epoch": 3.3258601316282306,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00039232737418788905,
|
|
"loss": 6.0465,
|
|
"mean_token_accuracy": 0.1527703434228897,
|
|
"num_tokens": 67278206.0,
|
|
"step": 31080
|
|
},
|
|
{
|
|
"entropy": 6.48355016708374,
|
|
"epoch": 3.3263952057359942,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003922947487797151,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.15149478912353515,
|
|
"num_tokens": 67289002.0,
|
|
"step": 31085
|
|
},
|
|
{
|
|
"entropy": 6.5096639633178714,
|
|
"epoch": 3.3269302798437583,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039226211998467177,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.15390699058771135,
|
|
"num_tokens": 67300219.0,
|
|
"step": 31090
|
|
},
|
|
{
|
|
"entropy": 6.52296552658081,
|
|
"epoch": 3.3274653539515224,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039222948780370126,
|
|
"loss": 6.114,
|
|
"mean_token_accuracy": 0.15166312605142593,
|
|
"num_tokens": 67311611.0,
|
|
"step": 31095
|
|
},
|
|
{
|
|
"entropy": 6.46249623298645,
|
|
"epoch": 3.328000428059286,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003921968522377456,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.1569169469177723,
|
|
"num_tokens": 67322674.0,
|
|
"step": 31100
|
|
},
|
|
{
|
|
"entropy": 6.540855264663696,
|
|
"epoch": 3.32853550216705,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003921642132877474,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.15172367542982101,
|
|
"num_tokens": 67333574.0,
|
|
"step": 31105
|
|
},
|
|
{
|
|
"entropy": 6.5435404777526855,
|
|
"epoch": 3.3290705762748143,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000392131570954649,
|
|
"loss": 5.9755,
|
|
"mean_token_accuracy": 0.15386370867490767,
|
|
"num_tokens": 67343500.0,
|
|
"step": 31110
|
|
},
|
|
{
|
|
"entropy": 6.497877836227417,
|
|
"epoch": 3.329605650382578,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000392098925239393,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.1525736480951309,
|
|
"num_tokens": 67354108.0,
|
|
"step": 31115
|
|
},
|
|
{
|
|
"entropy": 6.4898176193237305,
|
|
"epoch": 3.330140724490342,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039206627614292195,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.15061581432819365,
|
|
"num_tokens": 67366177.0,
|
|
"step": 31120
|
|
},
|
|
{
|
|
"entropy": 6.5261921882629395,
|
|
"epoch": 3.3306757985981057,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003920336236661786,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.1570025533437729,
|
|
"num_tokens": 67377000.0,
|
|
"step": 31125
|
|
},
|
|
{
|
|
"entropy": 6.440125608444214,
|
|
"epoch": 3.33121087270587,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039200096781010586,
|
|
"loss": 5.9787,
|
|
"mean_token_accuracy": 0.15636404752731323,
|
|
"num_tokens": 67388052.0,
|
|
"step": 31130
|
|
},
|
|
{
|
|
"entropy": 6.39323239326477,
|
|
"epoch": 3.3317459468136335,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003919683085756466,
|
|
"loss": 6.0068,
|
|
"mean_token_accuracy": 0.16015061289072036,
|
|
"num_tokens": 67398701.0,
|
|
"step": 31135
|
|
},
|
|
{
|
|
"entropy": 6.454569244384766,
|
|
"epoch": 3.3322810209213976,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039193564596374386,
|
|
"loss": 6.0098,
|
|
"mean_token_accuracy": 0.15444852113723756,
|
|
"num_tokens": 67410207.0,
|
|
"step": 31140
|
|
},
|
|
{
|
|
"entropy": 6.529144716262818,
|
|
"epoch": 3.3328160950291617,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003919029799753408,
|
|
"loss": 6.0202,
|
|
"mean_token_accuracy": 0.1500282518565655,
|
|
"num_tokens": 67420883.0,
|
|
"step": 31145
|
|
},
|
|
{
|
|
"entropy": 6.442582273483277,
|
|
"epoch": 3.3333511691369253,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003918703106113806,
|
|
"loss": 5.9748,
|
|
"mean_token_accuracy": 0.1609154924750328,
|
|
"num_tokens": 67430558.0,
|
|
"step": 31150
|
|
},
|
|
{
|
|
"entropy": 6.419910001754761,
|
|
"epoch": 3.3338862432446894,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003918376378728066,
|
|
"loss": 6.0261,
|
|
"mean_token_accuracy": 0.15712810456752777,
|
|
"num_tokens": 67441774.0,
|
|
"step": 31155
|
|
},
|
|
{
|
|
"entropy": 6.506383609771729,
|
|
"epoch": 3.3344213173524535,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00039180496176056224,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.15120686441659928,
|
|
"num_tokens": 67452176.0,
|
|
"step": 31160
|
|
},
|
|
{
|
|
"entropy": 6.510138368606567,
|
|
"epoch": 3.334956391460217,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039177228227559095,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.16433421671390533,
|
|
"num_tokens": 67462427.0,
|
|
"step": 31165
|
|
},
|
|
{
|
|
"entropy": 6.432904577255249,
|
|
"epoch": 3.3354914655679813,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039173959941883645,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.1622195228934288,
|
|
"num_tokens": 67472611.0,
|
|
"step": 31170
|
|
},
|
|
{
|
|
"entropy": 6.424222230911255,
|
|
"epoch": 3.336026539675745,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039170691319124253,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.14518814906477928,
|
|
"num_tokens": 67483138.0,
|
|
"step": 31175
|
|
},
|
|
{
|
|
"entropy": 6.472430753707886,
|
|
"epoch": 3.336561613783509,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003916742235937528,
|
|
"loss": 6.0227,
|
|
"mean_token_accuracy": 0.1553667888045311,
|
|
"num_tokens": 67493962.0,
|
|
"step": 31180
|
|
},
|
|
{
|
|
"entropy": 6.44260802268982,
|
|
"epoch": 3.337096687891273,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003916415306273112,
|
|
"loss": 6.0188,
|
|
"mean_token_accuracy": 0.15434340238571168,
|
|
"num_tokens": 67506882.0,
|
|
"step": 31185
|
|
},
|
|
{
|
|
"entropy": 6.5067503452301025,
|
|
"epoch": 3.3376317619990368,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039160883429286195,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.156253120303154,
|
|
"num_tokens": 67517357.0,
|
|
"step": 31190
|
|
},
|
|
{
|
|
"entropy": 6.515198850631714,
|
|
"epoch": 3.338166836106801,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039157613459134884,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.15136998891830444,
|
|
"num_tokens": 67528480.0,
|
|
"step": 31195
|
|
},
|
|
{
|
|
"entropy": 6.505551385879516,
|
|
"epoch": 3.3387019102145645,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003915434315237163,
|
|
"loss": 6.1036,
|
|
"mean_token_accuracy": 0.15570399910211563,
|
|
"num_tokens": 67539288.0,
|
|
"step": 31200
|
|
},
|
|
{
|
|
"entropy": 6.389894676208496,
|
|
"epoch": 3.3392369843223286,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003915107250909085,
|
|
"loss": 5.9544,
|
|
"mean_token_accuracy": 0.15719910115003585,
|
|
"num_tokens": 67551105.0,
|
|
"step": 31205
|
|
},
|
|
{
|
|
"entropy": 6.485951471328735,
|
|
"epoch": 3.3397720584300927,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039147801529386997,
|
|
"loss": 6.0381,
|
|
"mean_token_accuracy": 0.14690223038196565,
|
|
"num_tokens": 67562421.0,
|
|
"step": 31210
|
|
},
|
|
{
|
|
"entropy": 6.512796020507812,
|
|
"epoch": 3.3403071325378564,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039144530213354505,
|
|
"loss": 6.0589,
|
|
"mean_token_accuracy": 0.15139680951833726,
|
|
"num_tokens": 67574134.0,
|
|
"step": 31215
|
|
},
|
|
{
|
|
"entropy": 6.459736013412476,
|
|
"epoch": 3.3408422066456205,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003914125856108785,
|
|
"loss": 6.0068,
|
|
"mean_token_accuracy": 0.1537305846810341,
|
|
"num_tokens": 67585557.0,
|
|
"step": 31220
|
|
},
|
|
{
|
|
"entropy": 6.447339630126953,
|
|
"epoch": 3.3413772807533846,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003913798657268148,
|
|
"loss": 5.9545,
|
|
"mean_token_accuracy": 0.15473181903362274,
|
|
"num_tokens": 67596854.0,
|
|
"step": 31225
|
|
},
|
|
{
|
|
"entropy": 6.559619045257568,
|
|
"epoch": 3.3419123548611482,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003913471424822988,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.15435885339975358,
|
|
"num_tokens": 67607282.0,
|
|
"step": 31230
|
|
},
|
|
{
|
|
"entropy": 6.495668172836304,
|
|
"epoch": 3.3424474289689123,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003913144158782754,
|
|
"loss": 6.0232,
|
|
"mean_token_accuracy": 0.1507868006825447,
|
|
"num_tokens": 67618228.0,
|
|
"step": 31235
|
|
},
|
|
{
|
|
"entropy": 6.4208066940307615,
|
|
"epoch": 3.342982503076676,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039128168591568975,
|
|
"loss": 5.9957,
|
|
"mean_token_accuracy": 0.16518424451351166,
|
|
"num_tokens": 67630618.0,
|
|
"step": 31240
|
|
},
|
|
{
|
|
"entropy": 6.464799213409424,
|
|
"epoch": 3.34351757718444,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003912489525954866,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.1529540166258812,
|
|
"num_tokens": 67641052.0,
|
|
"step": 31245
|
|
},
|
|
{
|
|
"entropy": 6.450567197799683,
|
|
"epoch": 3.3440526512922037,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039121621591861134,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.15473459362983705,
|
|
"num_tokens": 67651315.0,
|
|
"step": 31250
|
|
},
|
|
{
|
|
"entropy": 6.460121440887451,
|
|
"epoch": 3.344587725399968,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039118347588600917,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.15650847405195237,
|
|
"num_tokens": 67661637.0,
|
|
"step": 31255
|
|
},
|
|
{
|
|
"entropy": 6.390079164505005,
|
|
"epoch": 3.345122799507732,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003911507324986254,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.16533294469118118,
|
|
"num_tokens": 67672863.0,
|
|
"step": 31260
|
|
},
|
|
{
|
|
"entropy": 6.455962467193603,
|
|
"epoch": 3.3456578736154956,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003911179857574056,
|
|
"loss": 6.0252,
|
|
"mean_token_accuracy": 0.15891761481761932,
|
|
"num_tokens": 67683711.0,
|
|
"step": 31265
|
|
},
|
|
{
|
|
"entropy": 6.484324598312378,
|
|
"epoch": 3.3461929477232597,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003910852356632953,
|
|
"loss": 5.9762,
|
|
"mean_token_accuracy": 0.16233128309249878,
|
|
"num_tokens": 67694345.0,
|
|
"step": 31270
|
|
},
|
|
{
|
|
"entropy": 6.509876871109009,
|
|
"epoch": 3.346728021831024,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003910524822172402,
|
|
"loss": 6.06,
|
|
"mean_token_accuracy": 0.15566004514694215,
|
|
"num_tokens": 67705339.0,
|
|
"step": 31275
|
|
},
|
|
{
|
|
"entropy": 6.420624160766602,
|
|
"epoch": 3.3472630959387875,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003910197254201858,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.1529044382274151,
|
|
"num_tokens": 67715800.0,
|
|
"step": 31280
|
|
},
|
|
{
|
|
"entropy": 6.501112222671509,
|
|
"epoch": 3.3477981700465516,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003909869652730783,
|
|
"loss": 6.129,
|
|
"mean_token_accuracy": 0.15643897354602815,
|
|
"num_tokens": 67725733.0,
|
|
"step": 31285
|
|
},
|
|
{
|
|
"entropy": 6.514887762069702,
|
|
"epoch": 3.348333244154315,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039095420177686334,
|
|
"loss": 5.9922,
|
|
"mean_token_accuracy": 0.15721810311079026,
|
|
"num_tokens": 67737637.0,
|
|
"step": 31290
|
|
},
|
|
{
|
|
"entropy": 6.485174179077148,
|
|
"epoch": 3.3488683182620793,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003909214349324872,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.15653251260519027,
|
|
"num_tokens": 67748016.0,
|
|
"step": 31295
|
|
},
|
|
{
|
|
"entropy": 6.443537712097168,
|
|
"epoch": 3.3494033923698434,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039088866474089583,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.1513347275555134,
|
|
"num_tokens": 67758439.0,
|
|
"step": 31300
|
|
},
|
|
{
|
|
"entropy": 6.527566814422608,
|
|
"epoch": 3.349938466477607,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039085589120303564,
|
|
"loss": 6.0047,
|
|
"mean_token_accuracy": 0.15049190074205399,
|
|
"num_tokens": 67768978.0,
|
|
"step": 31305
|
|
},
|
|
{
|
|
"entropy": 6.393413639068603,
|
|
"epoch": 3.350473540585371,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003908231143198529,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.1659313216805458,
|
|
"num_tokens": 67779557.0,
|
|
"step": 31310
|
|
},
|
|
{
|
|
"entropy": 6.496394062042237,
|
|
"epoch": 3.351008614693135,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039079033409229394,
|
|
"loss": 6.0548,
|
|
"mean_token_accuracy": 0.15027439296245576,
|
|
"num_tokens": 67791561.0,
|
|
"step": 31315
|
|
},
|
|
{
|
|
"entropy": 6.530108213424683,
|
|
"epoch": 3.351543688800899,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003907575505213053,
|
|
"loss": 5.9869,
|
|
"mean_token_accuracy": 0.15252052247524261,
|
|
"num_tokens": 67801703.0,
|
|
"step": 31320
|
|
},
|
|
{
|
|
"entropy": 6.506937026977539,
|
|
"epoch": 3.352078762908663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003907247636078337,
|
|
"loss": 6.0465,
|
|
"mean_token_accuracy": 0.15492548868060113,
|
|
"num_tokens": 67812413.0,
|
|
"step": 31325
|
|
},
|
|
{
|
|
"entropy": 6.513444471359253,
|
|
"epoch": 3.3526138370164267,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039069197335282583,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.1546009287238121,
|
|
"num_tokens": 67823184.0,
|
|
"step": 31330
|
|
},
|
|
{
|
|
"entropy": 6.529324388504028,
|
|
"epoch": 3.353148911124191,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039065917975722854,
|
|
"loss": 6.0635,
|
|
"mean_token_accuracy": 0.14834645092487336,
|
|
"num_tokens": 67834372.0,
|
|
"step": 31335
|
|
},
|
|
{
|
|
"entropy": 6.396627521514892,
|
|
"epoch": 3.3536839852319544,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003906263828219886,
|
|
"loss": 5.9014,
|
|
"mean_token_accuracy": 0.15849861204624177,
|
|
"num_tokens": 67845324.0,
|
|
"step": 31340
|
|
},
|
|
{
|
|
"entropy": 6.500179958343506,
|
|
"epoch": 3.3542190593397185,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003905935825480531,
|
|
"loss": 5.9617,
|
|
"mean_token_accuracy": 0.15285177379846573,
|
|
"num_tokens": 67856140.0,
|
|
"step": 31345
|
|
},
|
|
{
|
|
"entropy": 6.542001819610595,
|
|
"epoch": 3.3547541334474826,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039056077893636916,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.14958110004663466,
|
|
"num_tokens": 67867117.0,
|
|
"step": 31350
|
|
},
|
|
{
|
|
"entropy": 6.484523916244507,
|
|
"epoch": 3.3552892075552463,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039052797198788406,
|
|
"loss": 6.1054,
|
|
"mean_token_accuracy": 0.147844360768795,
|
|
"num_tokens": 67877006.0,
|
|
"step": 31355
|
|
},
|
|
{
|
|
"entropy": 6.428301811218262,
|
|
"epoch": 3.3558242816630104,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003904951617035448,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.17186660915613175,
|
|
"num_tokens": 67886873.0,
|
|
"step": 31360
|
|
},
|
|
{
|
|
"entropy": 6.502016925811768,
|
|
"epoch": 3.356359355770774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003904623480842992,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.1522527664899826,
|
|
"num_tokens": 67897033.0,
|
|
"step": 31365
|
|
},
|
|
{
|
|
"entropy": 6.484689474105835,
|
|
"epoch": 3.356894429878538,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003904295311310944,
|
|
"loss": 5.9891,
|
|
"mean_token_accuracy": 0.15675554871559144,
|
|
"num_tokens": 67909030.0,
|
|
"step": 31370
|
|
},
|
|
{
|
|
"entropy": 6.505921030044556,
|
|
"epoch": 3.3574295039863022,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003903967108448782,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.1544977217912674,
|
|
"num_tokens": 67918736.0,
|
|
"step": 31375
|
|
},
|
|
{
|
|
"entropy": 6.399167537689209,
|
|
"epoch": 3.357964578094066,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039036388722659803,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.1608656406402588,
|
|
"num_tokens": 67929392.0,
|
|
"step": 31380
|
|
},
|
|
{
|
|
"entropy": 6.540145635604858,
|
|
"epoch": 3.35849965220183,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000390331060277202,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.14573802724480628,
|
|
"num_tokens": 67940634.0,
|
|
"step": 31385
|
|
},
|
|
{
|
|
"entropy": 6.473884344100952,
|
|
"epoch": 3.359034726309594,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003902982299976377,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.15839997678995132,
|
|
"num_tokens": 67951132.0,
|
|
"step": 31390
|
|
},
|
|
{
|
|
"entropy": 6.459851932525635,
|
|
"epoch": 3.3595698004173578,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00039026539638885326,
|
|
"loss": 6.0662,
|
|
"mean_token_accuracy": 0.14532821252942085,
|
|
"num_tokens": 67961651.0,
|
|
"step": 31395
|
|
},
|
|
{
|
|
"entropy": 6.394487476348877,
|
|
"epoch": 3.360104874525122,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0003902325594517967,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.16227962523698808,
|
|
"num_tokens": 67971906.0,
|
|
"step": 31400
|
|
},
|
|
{
|
|
"entropy": 6.462641811370849,
|
|
"epoch": 3.3606399486328855,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039019971918741615,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.15389315336942672,
|
|
"num_tokens": 67983059.0,
|
|
"step": 31405
|
|
},
|
|
{
|
|
"entropy": 6.471459865570068,
|
|
"epoch": 3.3611750227406496,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00039016687559665985,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.1519065245985985,
|
|
"num_tokens": 67993635.0,
|
|
"step": 31410
|
|
},
|
|
{
|
|
"entropy": 6.547579002380371,
|
|
"epoch": 3.3617100968484133,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003901340286804763,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.15944345891475678,
|
|
"num_tokens": 68003857.0,
|
|
"step": 31415
|
|
},
|
|
{
|
|
"entropy": 6.439539289474487,
|
|
"epoch": 3.3622451709561774,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00039010117843981377,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.15127893537282944,
|
|
"num_tokens": 68014993.0,
|
|
"step": 31420
|
|
},
|
|
{
|
|
"entropy": 6.493534946441651,
|
|
"epoch": 3.3627802450639415,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039006832487562096,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.1504395842552185,
|
|
"num_tokens": 68026245.0,
|
|
"step": 31425
|
|
},
|
|
{
|
|
"entropy": 6.510143613815307,
|
|
"epoch": 3.363315319171705,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003900354679888464,
|
|
"loss": 6.0807,
|
|
"mean_token_accuracy": 0.15890005826950074,
|
|
"num_tokens": 68038023.0,
|
|
"step": 31430
|
|
},
|
|
{
|
|
"entropy": 6.504014110565185,
|
|
"epoch": 3.363850393279469,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003900026077804389,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.15138578563928604,
|
|
"num_tokens": 68048527.0,
|
|
"step": 31435
|
|
},
|
|
{
|
|
"entropy": 6.4610930442810055,
|
|
"epoch": 3.3643854673872333,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003899697442513472,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.1508680284023285,
|
|
"num_tokens": 68059345.0,
|
|
"step": 31440
|
|
},
|
|
{
|
|
"entropy": 6.4357555389404295,
|
|
"epoch": 3.364920541494997,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038993687740252034,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.15003749281167983,
|
|
"num_tokens": 68070295.0,
|
|
"step": 31445
|
|
},
|
|
{
|
|
"entropy": 6.467582368850708,
|
|
"epoch": 3.365455615602761,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003899040072349073,
|
|
"loss": 5.9703,
|
|
"mean_token_accuracy": 0.15312543883919716,
|
|
"num_tokens": 68081665.0,
|
|
"step": 31450
|
|
},
|
|
{
|
|
"entropy": 6.465695571899414,
|
|
"epoch": 3.3659906897105247,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003898711337494571,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.1643015369772911,
|
|
"num_tokens": 68092474.0,
|
|
"step": 31455
|
|
},
|
|
{
|
|
"entropy": 6.494434022903443,
|
|
"epoch": 3.366525763818289,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003898382569471191,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.1474827527999878,
|
|
"num_tokens": 68102981.0,
|
|
"step": 31460
|
|
},
|
|
{
|
|
"entropy": 6.460698032379151,
|
|
"epoch": 3.367060837926053,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038980537682884266,
|
|
"loss": 5.9606,
|
|
"mean_token_accuracy": 0.15551196783781052,
|
|
"num_tokens": 68113785.0,
|
|
"step": 31465
|
|
},
|
|
{
|
|
"entropy": 6.4379644870758055,
|
|
"epoch": 3.3675959120338166,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038977249339557703,
|
|
"loss": 6.0611,
|
|
"mean_token_accuracy": 0.15548268854618072,
|
|
"num_tokens": 68123419.0,
|
|
"step": 31470
|
|
},
|
|
{
|
|
"entropy": 6.421049404144287,
|
|
"epoch": 3.3681309861415807,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038973960664827177,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.15533210188150406,
|
|
"num_tokens": 68134816.0,
|
|
"step": 31475
|
|
},
|
|
{
|
|
"entropy": 6.522781276702881,
|
|
"epoch": 3.3686660602493443,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038970671658787647,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.15362566709518433,
|
|
"num_tokens": 68146063.0,
|
|
"step": 31480
|
|
},
|
|
{
|
|
"entropy": 6.483579874038696,
|
|
"epoch": 3.3692011343571084,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038967382321534094,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.15662998408079148,
|
|
"num_tokens": 68156735.0,
|
|
"step": 31485
|
|
},
|
|
{
|
|
"entropy": 6.4631610870361325,
|
|
"epoch": 3.3697362084648725,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038964092653161474,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.14960170835256575,
|
|
"num_tokens": 68167768.0,
|
|
"step": 31490
|
|
},
|
|
{
|
|
"entropy": 6.452051305770874,
|
|
"epoch": 3.370271282572636,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000389608026537648,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.171490640938282,
|
|
"num_tokens": 68179325.0,
|
|
"step": 31495
|
|
},
|
|
{
|
|
"entropy": 6.446336460113526,
|
|
"epoch": 3.3708063566804003,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003895751232343906,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.1500459372997284,
|
|
"num_tokens": 68190615.0,
|
|
"step": 31500
|
|
},
|
|
{
|
|
"entropy": 6.450361204147339,
|
|
"epoch": 3.3713414307881644,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003895422166227926,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.1565784364938736,
|
|
"num_tokens": 68201323.0,
|
|
"step": 31505
|
|
},
|
|
{
|
|
"entropy": 6.5007706642150875,
|
|
"epoch": 3.371876504895928,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003895093067038042,
|
|
"loss": 6.0316,
|
|
"mean_token_accuracy": 0.1539457067847252,
|
|
"num_tokens": 68213296.0,
|
|
"step": 31510
|
|
},
|
|
{
|
|
"entropy": 6.444532299041748,
|
|
"epoch": 3.372411579003692,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003894763934783757,
|
|
"loss": 6.0727,
|
|
"mean_token_accuracy": 0.14802486151456834,
|
|
"num_tokens": 68224707.0,
|
|
"step": 31515
|
|
},
|
|
{
|
|
"entropy": 6.529166889190674,
|
|
"epoch": 3.372946653111456,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003894434769474573,
|
|
"loss": 6.0764,
|
|
"mean_token_accuracy": 0.14929986819624902,
|
|
"num_tokens": 68236651.0,
|
|
"step": 31520
|
|
},
|
|
{
|
|
"entropy": 6.5361944198608395,
|
|
"epoch": 3.37348172721922,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003894105571119996,
|
|
"loss": 6.0592,
|
|
"mean_token_accuracy": 0.14857451468706132,
|
|
"num_tokens": 68246933.0,
|
|
"step": 31525
|
|
},
|
|
{
|
|
"entropy": 6.420639896392823,
|
|
"epoch": 3.3740168013269836,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038937763397295323,
|
|
"loss": 6.02,
|
|
"mean_token_accuracy": 0.15359316393733025,
|
|
"num_tokens": 68257934.0,
|
|
"step": 31530
|
|
},
|
|
{
|
|
"entropy": 6.463315343856811,
|
|
"epoch": 3.3745518754347477,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038934470753126867,
|
|
"loss": 5.9811,
|
|
"mean_token_accuracy": 0.15888938307762146,
|
|
"num_tokens": 68268841.0,
|
|
"step": 31535
|
|
},
|
|
{
|
|
"entropy": 6.494793558120728,
|
|
"epoch": 3.3750869495425118,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038931177778789685,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.15312849581241608,
|
|
"num_tokens": 68280391.0,
|
|
"step": 31540
|
|
},
|
|
{
|
|
"entropy": 6.399728393554687,
|
|
"epoch": 3.3756220236502754,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003892788447437885,
|
|
"loss": 5.997,
|
|
"mean_token_accuracy": 0.15559949427843095,
|
|
"num_tokens": 68291886.0,
|
|
"step": 31545
|
|
},
|
|
{
|
|
"entropy": 6.403946447372436,
|
|
"epoch": 3.3761570977580395,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038924590839989445,
|
|
"loss": 5.9932,
|
|
"mean_token_accuracy": 0.1489808179438114,
|
|
"num_tokens": 68302909.0,
|
|
"step": 31550
|
|
},
|
|
{
|
|
"entropy": 6.49025411605835,
|
|
"epoch": 3.3766921718658036,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038921296875716596,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.14892928749322892,
|
|
"num_tokens": 68314204.0,
|
|
"step": 31555
|
|
},
|
|
{
|
|
"entropy": 6.481174564361572,
|
|
"epoch": 3.3772272459735673,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038918002581655406,
|
|
"loss": 6.0239,
|
|
"mean_token_accuracy": 0.15424363017082215,
|
|
"num_tokens": 68325861.0,
|
|
"step": 31560
|
|
},
|
|
{
|
|
"entropy": 6.510799789428711,
|
|
"epoch": 3.3777623200813314,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003891470795790098,
|
|
"loss": 6.0473,
|
|
"mean_token_accuracy": 0.14951711744070054,
|
|
"num_tokens": 68336390.0,
|
|
"step": 31565
|
|
},
|
|
{
|
|
"entropy": 6.449477624893189,
|
|
"epoch": 3.378297394189095,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038911413004548477,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.14930295646190644,
|
|
"num_tokens": 68347429.0,
|
|
"step": 31570
|
|
},
|
|
{
|
|
"entropy": 6.48308424949646,
|
|
"epoch": 3.378832468296859,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003890811772169302,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.15160712450742722,
|
|
"num_tokens": 68358417.0,
|
|
"step": 31575
|
|
},
|
|
{
|
|
"entropy": 6.532841491699219,
|
|
"epoch": 3.3793675424046232,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038904822109429773,
|
|
"loss": 5.9809,
|
|
"mean_token_accuracy": 0.15799239426851272,
|
|
"num_tokens": 68369495.0,
|
|
"step": 31580
|
|
},
|
|
{
|
|
"entropy": 6.4528796672821045,
|
|
"epoch": 3.379902616512387,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003890152616785389,
|
|
"loss": 6.0474,
|
|
"mean_token_accuracy": 0.14927760660648345,
|
|
"num_tokens": 68380122.0,
|
|
"step": 31585
|
|
},
|
|
{
|
|
"entropy": 6.410782384872436,
|
|
"epoch": 3.380437690620151,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038898229897060544,
|
|
"loss": 5.9938,
|
|
"mean_token_accuracy": 0.16365791559219361,
|
|
"num_tokens": 68389997.0,
|
|
"step": 31590
|
|
},
|
|
{
|
|
"entropy": 6.49708890914917,
|
|
"epoch": 3.3809727647279146,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038894933297144906,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.14776387214660644,
|
|
"num_tokens": 68399726.0,
|
|
"step": 31595
|
|
},
|
|
{
|
|
"entropy": 6.454077291488647,
|
|
"epoch": 3.3815078388356787,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038891636368202173,
|
|
"loss": 5.9412,
|
|
"mean_token_accuracy": 0.15663443505764008,
|
|
"num_tokens": 68410022.0,
|
|
"step": 31600
|
|
},
|
|
{
|
|
"entropy": 6.270445728302002,
|
|
"epoch": 3.382042912943443,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038888339110327544,
|
|
"loss": 5.8147,
|
|
"mean_token_accuracy": 0.18612581640481948,
|
|
"num_tokens": 68421269.0,
|
|
"step": 31605
|
|
},
|
|
{
|
|
"entropy": 6.286657810211182,
|
|
"epoch": 3.3825779870512065,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00038885041523616223,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.16787441074848175,
|
|
"num_tokens": 68432979.0,
|
|
"step": 31610
|
|
},
|
|
{
|
|
"entropy": 6.4442342758178714,
|
|
"epoch": 3.3831130611589706,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038881743608163414,
|
|
"loss": 5.9626,
|
|
"mean_token_accuracy": 0.15474584996700286,
|
|
"num_tokens": 68443379.0,
|
|
"step": 31615
|
|
},
|
|
{
|
|
"entropy": 6.480328178405761,
|
|
"epoch": 3.3836481352667347,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038878445364064375,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.1510286509990692,
|
|
"num_tokens": 68454277.0,
|
|
"step": 31620
|
|
},
|
|
{
|
|
"entropy": 6.477165555953979,
|
|
"epoch": 3.3841832093744983,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038875146791414315,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.14915145337581634,
|
|
"num_tokens": 68465774.0,
|
|
"step": 31625
|
|
},
|
|
{
|
|
"entropy": 6.489587593078613,
|
|
"epoch": 3.3847182834822624,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038871847890308497,
|
|
"loss": 6.0275,
|
|
"mean_token_accuracy": 0.1531556189060211,
|
|
"num_tokens": 68476083.0,
|
|
"step": 31630
|
|
},
|
|
{
|
|
"entropy": 6.449621057510376,
|
|
"epoch": 3.385253357590026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003886854866084216,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.15558649003505706,
|
|
"num_tokens": 68486696.0,
|
|
"step": 31635
|
|
},
|
|
{
|
|
"entropy": 6.474633693695068,
|
|
"epoch": 3.38578843169779,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003886524910311058,
|
|
"loss": 6.0473,
|
|
"mean_token_accuracy": 0.15105312317609787,
|
|
"num_tokens": 68497458.0,
|
|
"step": 31640
|
|
},
|
|
{
|
|
"entropy": 6.477666664123535,
|
|
"epoch": 3.386323505805554,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003886194921720904,
|
|
"loss": 6.0284,
|
|
"mean_token_accuracy": 0.1518389254808426,
|
|
"num_tokens": 68508603.0,
|
|
"step": 31645
|
|
},
|
|
{
|
|
"entropy": 6.486009883880615,
|
|
"epoch": 3.386858579913318,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000388586490032328,
|
|
"loss": 5.9941,
|
|
"mean_token_accuracy": 0.1519061177968979,
|
|
"num_tokens": 68519389.0,
|
|
"step": 31650
|
|
},
|
|
{
|
|
"entropy": 6.442571210861206,
|
|
"epoch": 3.387393654021082,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003885534846127717,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.16071781665086746,
|
|
"num_tokens": 68529272.0,
|
|
"step": 31655
|
|
},
|
|
{
|
|
"entropy": 6.470805835723877,
|
|
"epoch": 3.3879287281288457,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003885204759143746,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.15169288069009781,
|
|
"num_tokens": 68539644.0,
|
|
"step": 31660
|
|
},
|
|
{
|
|
"entropy": 6.434387302398681,
|
|
"epoch": 3.38846380223661,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003884874639380895,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.15868661552667618,
|
|
"num_tokens": 68549601.0,
|
|
"step": 31665
|
|
},
|
|
{
|
|
"entropy": 6.4291284561157225,
|
|
"epoch": 3.388998876344374,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038845444868486996,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.16576840579509736,
|
|
"num_tokens": 68561105.0,
|
|
"step": 31670
|
|
},
|
|
{
|
|
"entropy": 6.525542163848877,
|
|
"epoch": 3.3895339504521376,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003884214301556692,
|
|
"loss": 6.1184,
|
|
"mean_token_accuracy": 0.1471312575042248,
|
|
"num_tokens": 68572117.0,
|
|
"step": 31675
|
|
},
|
|
{
|
|
"entropy": 6.465865993499756,
|
|
"epoch": 3.3900690245599017,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038838840835144053,
|
|
"loss": 6.0554,
|
|
"mean_token_accuracy": 0.15180726498365402,
|
|
"num_tokens": 68582241.0,
|
|
"step": 31680
|
|
},
|
|
{
|
|
"entropy": 6.4053184509277346,
|
|
"epoch": 3.3906040986676653,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038835538327313746,
|
|
"loss": 5.9744,
|
|
"mean_token_accuracy": 0.15084423273801803,
|
|
"num_tokens": 68594977.0,
|
|
"step": 31685
|
|
},
|
|
{
|
|
"entropy": 6.43016791343689,
|
|
"epoch": 3.3911391727754294,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038832235492171363,
|
|
"loss": 5.954,
|
|
"mean_token_accuracy": 0.15999606549739837,
|
|
"num_tokens": 68605483.0,
|
|
"step": 31690
|
|
},
|
|
{
|
|
"entropy": 6.4066003322601315,
|
|
"epoch": 3.391674246883193,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038828932329812275,
|
|
"loss": 5.9049,
|
|
"mean_token_accuracy": 0.16300432980060578,
|
|
"num_tokens": 68615274.0,
|
|
"step": 31695
|
|
},
|
|
{
|
|
"entropy": 6.463304138183593,
|
|
"epoch": 3.392209320990957,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003882562884033186,
|
|
"loss": 6.0318,
|
|
"mean_token_accuracy": 0.15229685306549073,
|
|
"num_tokens": 68626512.0,
|
|
"step": 31700
|
|
},
|
|
{
|
|
"entropy": 6.404597425460816,
|
|
"epoch": 3.3927443950987213,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038822325023825507,
|
|
"loss": 6.0092,
|
|
"mean_token_accuracy": 0.15445471853017806,
|
|
"num_tokens": 68637846.0,
|
|
"step": 31705
|
|
},
|
|
{
|
|
"entropy": 6.473957204818726,
|
|
"epoch": 3.393279469206485,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038819020880388603,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.14285230487585068,
|
|
"num_tokens": 68650377.0,
|
|
"step": 31710
|
|
},
|
|
{
|
|
"entropy": 6.453735256195069,
|
|
"epoch": 3.393814543314249,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0003881571641011656,
|
|
"loss": 6.0264,
|
|
"mean_token_accuracy": 0.1533817544579506,
|
|
"num_tokens": 68661358.0,
|
|
"step": 31715
|
|
},
|
|
{
|
|
"entropy": 6.439703321456909,
|
|
"epoch": 3.394349617422013,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000388124116131048,
|
|
"loss": 6.0074,
|
|
"mean_token_accuracy": 0.15100138038396835,
|
|
"num_tokens": 68673592.0,
|
|
"step": 31720
|
|
},
|
|
{
|
|
"entropy": 6.451644468307495,
|
|
"epoch": 3.394884691529777,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038809106489448743,
|
|
"loss": 5.9153,
|
|
"mean_token_accuracy": 0.16878464221954345,
|
|
"num_tokens": 68684225.0,
|
|
"step": 31725
|
|
},
|
|
{
|
|
"entropy": 6.430613231658936,
|
|
"epoch": 3.395419765637541,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038805801039243826,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.1558352679014206,
|
|
"num_tokens": 68694243.0,
|
|
"step": 31730
|
|
},
|
|
{
|
|
"entropy": 6.44554500579834,
|
|
"epoch": 3.3959548397453045,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000388024952625855,
|
|
"loss": 6.0155,
|
|
"mean_token_accuracy": 0.15177218317985536,
|
|
"num_tokens": 68704359.0,
|
|
"step": 31735
|
|
},
|
|
{
|
|
"entropy": 6.445982265472412,
|
|
"epoch": 3.3964899138530686,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038799189159569194,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.15457366555929183,
|
|
"num_tokens": 68714317.0,
|
|
"step": 31740
|
|
},
|
|
{
|
|
"entropy": 6.468947505950927,
|
|
"epoch": 3.3970249879608327,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000387958827302904,
|
|
"loss": 6.09,
|
|
"mean_token_accuracy": 0.1489025816321373,
|
|
"num_tokens": 68725601.0,
|
|
"step": 31745
|
|
},
|
|
{
|
|
"entropy": 6.527911043167114,
|
|
"epoch": 3.3975600620685964,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038792575974844575,
|
|
"loss": 6.0225,
|
|
"mean_token_accuracy": 0.15689507573843003,
|
|
"num_tokens": 68735692.0,
|
|
"step": 31750
|
|
},
|
|
{
|
|
"entropy": 6.4312550067901615,
|
|
"epoch": 3.3980951361763605,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003878926889332721,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.16875397264957429,
|
|
"num_tokens": 68746693.0,
|
|
"step": 31755
|
|
},
|
|
{
|
|
"entropy": 6.386112356185913,
|
|
"epoch": 3.398630210284124,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003878596148583379,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.15305046811699868,
|
|
"num_tokens": 68757769.0,
|
|
"step": 31760
|
|
},
|
|
{
|
|
"entropy": 6.404603290557861,
|
|
"epoch": 3.3991652843918883,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003878265375245982,
|
|
"loss": 5.9697,
|
|
"mean_token_accuracy": 0.1555817574262619,
|
|
"num_tokens": 68768066.0,
|
|
"step": 31765
|
|
},
|
|
{
|
|
"entropy": 6.4245459079742435,
|
|
"epoch": 3.3997003584996524,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000387793456933008,
|
|
"loss": 5.9616,
|
|
"mean_token_accuracy": 0.14956895187497138,
|
|
"num_tokens": 68780093.0,
|
|
"step": 31770
|
|
},
|
|
{
|
|
"entropy": 6.391851711273193,
|
|
"epoch": 3.400235432607416,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003877603730845227,
|
|
"loss": 6.0158,
|
|
"mean_token_accuracy": 0.1549658417701721,
|
|
"num_tokens": 68791113.0,
|
|
"step": 31775
|
|
},
|
|
{
|
|
"entropy": 6.441417789459228,
|
|
"epoch": 3.40077050671518,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003877272859800975,
|
|
"loss": 6.0439,
|
|
"mean_token_accuracy": 0.15697846710681915,
|
|
"num_tokens": 68801723.0,
|
|
"step": 31780
|
|
},
|
|
{
|
|
"entropy": 6.504461765289307,
|
|
"epoch": 3.401305580822944,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003876941956206876,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.1534028932452202,
|
|
"num_tokens": 68813130.0,
|
|
"step": 31785
|
|
},
|
|
{
|
|
"entropy": 6.523074960708618,
|
|
"epoch": 3.401840654930708,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038766110200724876,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.1564378872513771,
|
|
"num_tokens": 68823699.0,
|
|
"step": 31790
|
|
},
|
|
{
|
|
"entropy": 6.4348362445831295,
|
|
"epoch": 3.402375729038472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038762800514073636,
|
|
"loss": 6.0087,
|
|
"mean_token_accuracy": 0.1453996941447258,
|
|
"num_tokens": 68835295.0,
|
|
"step": 31795
|
|
},
|
|
{
|
|
"entropy": 6.47829155921936,
|
|
"epoch": 3.4029108031462356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003875949050221062,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.15807265043258667,
|
|
"num_tokens": 68845618.0,
|
|
"step": 31800
|
|
},
|
|
{
|
|
"entropy": 6.45537109375,
|
|
"epoch": 3.4034458772539997,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003875618016523139,
|
|
"loss": 6.0719,
|
|
"mean_token_accuracy": 0.1579635486006737,
|
|
"num_tokens": 68855829.0,
|
|
"step": 31805
|
|
},
|
|
{
|
|
"entropy": 6.371795225143432,
|
|
"epoch": 3.4039809513617634,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003875286950323155,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.1521754264831543,
|
|
"num_tokens": 68866731.0,
|
|
"step": 31810
|
|
},
|
|
{
|
|
"entropy": 6.5802239894866945,
|
|
"epoch": 3.4045160254695275,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003874955851630668,
|
|
"loss": 6.1203,
|
|
"mean_token_accuracy": 0.14571314603090285,
|
|
"num_tokens": 68877795.0,
|
|
"step": 31815
|
|
},
|
|
{
|
|
"entropy": 6.530199813842773,
|
|
"epoch": 3.4050510995772916,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038746247204552386,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.15803396850824356,
|
|
"num_tokens": 68886993.0,
|
|
"step": 31820
|
|
},
|
|
{
|
|
"entropy": 6.396942234039306,
|
|
"epoch": 3.4055861736850552,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003874293556806428,
|
|
"loss": 6.0506,
|
|
"mean_token_accuracy": 0.15199720114469528,
|
|
"num_tokens": 68899022.0,
|
|
"step": 31825
|
|
},
|
|
{
|
|
"entropy": 6.5242737293243405,
|
|
"epoch": 3.4061212477928193,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038739623606937995,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.15113475322723388,
|
|
"num_tokens": 68911052.0,
|
|
"step": 31830
|
|
},
|
|
{
|
|
"entropy": 6.462888479232788,
|
|
"epoch": 3.4066563219005834,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038736311321269155,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.16126797050237657,
|
|
"num_tokens": 68921093.0,
|
|
"step": 31835
|
|
},
|
|
{
|
|
"entropy": 6.479865550994873,
|
|
"epoch": 3.407191396008347,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003873299871115341,
|
|
"loss": 6.0623,
|
|
"mean_token_accuracy": 0.1533772125840187,
|
|
"num_tokens": 68931664.0,
|
|
"step": 31840
|
|
},
|
|
{
|
|
"entropy": 6.463776540756226,
|
|
"epoch": 3.407726470116111,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003872968577668641,
|
|
"loss": 6.0331,
|
|
"mean_token_accuracy": 0.15653365850448608,
|
|
"num_tokens": 68942758.0,
|
|
"step": 31845
|
|
},
|
|
{
|
|
"entropy": 6.336092615127564,
|
|
"epoch": 3.408261544223875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038726372517963796,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.1600252389907837,
|
|
"num_tokens": 68953408.0,
|
|
"step": 31850
|
|
},
|
|
{
|
|
"entropy": 6.455204010009766,
|
|
"epoch": 3.408796618331639,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038723058935081264,
|
|
"loss": 6.0048,
|
|
"mean_token_accuracy": 0.15885516554117202,
|
|
"num_tokens": 68964077.0,
|
|
"step": 31855
|
|
},
|
|
{
|
|
"entropy": 6.4457801342010494,
|
|
"epoch": 3.409331692439403,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003871974502813448,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.164150407910347,
|
|
"num_tokens": 68975761.0,
|
|
"step": 31860
|
|
},
|
|
{
|
|
"entropy": 6.471848821640014,
|
|
"epoch": 3.4098667665471667,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003871643079721914,
|
|
"loss": 6.0426,
|
|
"mean_token_accuracy": 0.15319600254297255,
|
|
"num_tokens": 68986965.0,
|
|
"step": 31865
|
|
},
|
|
{
|
|
"entropy": 6.445593070983887,
|
|
"epoch": 3.410401840654931,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003871311624243092,
|
|
"loss": 6.0195,
|
|
"mean_token_accuracy": 0.14691827446222305,
|
|
"num_tokens": 68998102.0,
|
|
"step": 31870
|
|
},
|
|
{
|
|
"entropy": 6.468770837783813,
|
|
"epoch": 3.4109369147626944,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003870980136386556,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.15123599171638488,
|
|
"num_tokens": 69008530.0,
|
|
"step": 31875
|
|
},
|
|
{
|
|
"entropy": 6.5051017761230465,
|
|
"epoch": 3.4114719888704585,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038706486161618753,
|
|
"loss": 6.0162,
|
|
"mean_token_accuracy": 0.15051537305116652,
|
|
"num_tokens": 69018866.0,
|
|
"step": 31880
|
|
},
|
|
{
|
|
"entropy": 6.495798349380493,
|
|
"epoch": 3.4120070629782226,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038703170635786237,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.15336152017116547,
|
|
"num_tokens": 69029050.0,
|
|
"step": 31885
|
|
},
|
|
{
|
|
"entropy": 6.475523614883423,
|
|
"epoch": 3.4125421370859863,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038699854786463744,
|
|
"loss": 5.9746,
|
|
"mean_token_accuracy": 0.1506906345486641,
|
|
"num_tokens": 69040117.0,
|
|
"step": 31890
|
|
},
|
|
{
|
|
"entropy": 6.428022956848144,
|
|
"epoch": 3.4130772111937504,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038696538613747016,
|
|
"loss": 6.0181,
|
|
"mean_token_accuracy": 0.15593162328004836,
|
|
"num_tokens": 69051704.0,
|
|
"step": 31895
|
|
},
|
|
{
|
|
"entropy": 6.478220653533936,
|
|
"epoch": 3.4136122853015145,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038693222117731804,
|
|
"loss": 5.9588,
|
|
"mean_token_accuracy": 0.1506402686238289,
|
|
"num_tokens": 69062359.0,
|
|
"step": 31900
|
|
},
|
|
{
|
|
"entropy": 6.415967845916748,
|
|
"epoch": 3.414147359409278,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038689905298513886,
|
|
"loss": 5.959,
|
|
"mean_token_accuracy": 0.15414198786020278,
|
|
"num_tokens": 69072936.0,
|
|
"step": 31905
|
|
},
|
|
{
|
|
"entropy": 6.433611059188843,
|
|
"epoch": 3.4146824335170423,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038686588156189024,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.14832476824522017,
|
|
"num_tokens": 69083468.0,
|
|
"step": 31910
|
|
},
|
|
{
|
|
"entropy": 6.4854501247406,
|
|
"epoch": 3.415217507624806,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003868327069085299,
|
|
"loss": 6.044,
|
|
"mean_token_accuracy": 0.15553727895021438,
|
|
"num_tokens": 69093565.0,
|
|
"step": 31915
|
|
},
|
|
{
|
|
"entropy": 6.4131604671478275,
|
|
"epoch": 3.41575258173257,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000386799529026016,
|
|
"loss": 6.0658,
|
|
"mean_token_accuracy": 0.14083562642335892,
|
|
"num_tokens": 69103660.0,
|
|
"step": 31920
|
|
},
|
|
{
|
|
"entropy": 6.437024545669556,
|
|
"epoch": 3.4162876558403337,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003867663479153063,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.15854933708906174,
|
|
"num_tokens": 69114810.0,
|
|
"step": 31925
|
|
},
|
|
{
|
|
"entropy": 6.531202745437622,
|
|
"epoch": 3.4168227299480978,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038673316357735907,
|
|
"loss": 6.0334,
|
|
"mean_token_accuracy": 0.15378662049770356,
|
|
"num_tokens": 69127634.0,
|
|
"step": 31930
|
|
},
|
|
{
|
|
"entropy": 6.505884313583374,
|
|
"epoch": 3.417357804055862,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003866999760131324,
|
|
"loss": 5.9954,
|
|
"mean_token_accuracy": 0.15769582837820054,
|
|
"num_tokens": 69136957.0,
|
|
"step": 31935
|
|
},
|
|
{
|
|
"entropy": 6.37451319694519,
|
|
"epoch": 3.4178928781636255,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038666678522358464,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.1540164291858673,
|
|
"num_tokens": 69148353.0,
|
|
"step": 31940
|
|
},
|
|
{
|
|
"entropy": 6.4860681056976315,
|
|
"epoch": 3.4184279522713896,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003866335912096741,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.15889904648065567,
|
|
"num_tokens": 69158329.0,
|
|
"step": 31945
|
|
},
|
|
{
|
|
"entropy": 6.397528839111328,
|
|
"epoch": 3.4189630263791537,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003866003939723595,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.1663876071572304,
|
|
"num_tokens": 69168689.0,
|
|
"step": 31950
|
|
},
|
|
{
|
|
"entropy": 6.473160648345948,
|
|
"epoch": 3.4194981004869174,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00038656719351259894,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.14770401567220687,
|
|
"num_tokens": 69181166.0,
|
|
"step": 31955
|
|
},
|
|
{
|
|
"entropy": 6.5317230224609375,
|
|
"epoch": 3.4200331745946815,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003865339898313515,
|
|
"loss": 5.9997,
|
|
"mean_token_accuracy": 0.15340589731931686,
|
|
"num_tokens": 69192221.0,
|
|
"step": 31960
|
|
},
|
|
{
|
|
"entropy": 6.4784928321838375,
|
|
"epoch": 3.420568248702445,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038650078292957573,
|
|
"loss": 6.0641,
|
|
"mean_token_accuracy": 0.1556587263941765,
|
|
"num_tokens": 69203225.0,
|
|
"step": 31965
|
|
},
|
|
{
|
|
"entropy": 6.4752418994903564,
|
|
"epoch": 3.4211033228102092,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00038646757280823047,
|
|
"loss": 6.0623,
|
|
"mean_token_accuracy": 0.15200510919094085,
|
|
"num_tokens": 69214349.0,
|
|
"step": 31970
|
|
},
|
|
{
|
|
"entropy": 6.500887012481689,
|
|
"epoch": 3.421638396917973,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003864343594682748,
|
|
"loss": 6.0958,
|
|
"mean_token_accuracy": 0.15116338878870011,
|
|
"num_tokens": 69225863.0,
|
|
"step": 31975
|
|
},
|
|
{
|
|
"entropy": 6.452427339553833,
|
|
"epoch": 3.422173471025737,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038640114291066765,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.1595476284623146,
|
|
"num_tokens": 69236572.0,
|
|
"step": 31980
|
|
},
|
|
{
|
|
"entropy": 6.420526599884033,
|
|
"epoch": 3.422708545133501,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038636792313636816,
|
|
"loss": 6.046,
|
|
"mean_token_accuracy": 0.1539657786488533,
|
|
"num_tokens": 69246034.0,
|
|
"step": 31985
|
|
},
|
|
{
|
|
"entropy": 6.4731663227081295,
|
|
"epoch": 3.4232436192412647,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003863347001463355,
|
|
"loss": 5.9715,
|
|
"mean_token_accuracy": 0.15376254618167878,
|
|
"num_tokens": 69256471.0,
|
|
"step": 31990
|
|
},
|
|
{
|
|
"entropy": 6.451621723175049,
|
|
"epoch": 3.423778693349029,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000386301473941529,
|
|
"loss": 5.9232,
|
|
"mean_token_accuracy": 0.1593514621257782,
|
|
"num_tokens": 69266601.0,
|
|
"step": 31995
|
|
},
|
|
{
|
|
"entropy": 6.468747663497925,
|
|
"epoch": 3.424313767456793,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003862682445229081,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.14997867494821548,
|
|
"num_tokens": 69276929.0,
|
|
"step": 32000
|
|
},
|
|
{
|
|
"entropy": 6.435034656524659,
|
|
"epoch": 3.4248488415645566,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038623501189143225,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.1513144016265869,
|
|
"num_tokens": 69287654.0,
|
|
"step": 32005
|
|
},
|
|
{
|
|
"entropy": 6.48564133644104,
|
|
"epoch": 3.4253839156723207,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003862017760480611,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.15391103625297547,
|
|
"num_tokens": 69297346.0,
|
|
"step": 32010
|
|
},
|
|
{
|
|
"entropy": 6.4824529647827145,
|
|
"epoch": 3.4259189897800844,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038616853699375425,
|
|
"loss": 6.0295,
|
|
"mean_token_accuracy": 0.15331365168094635,
|
|
"num_tokens": 69307806.0,
|
|
"step": 32015
|
|
},
|
|
{
|
|
"entropy": 6.482572460174561,
|
|
"epoch": 3.4264540638878485,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003861352947294716,
|
|
"loss": 6.0427,
|
|
"mean_token_accuracy": 0.14983974471688272,
|
|
"num_tokens": 69317964.0,
|
|
"step": 32020
|
|
},
|
|
{
|
|
"entropy": 6.431033563613892,
|
|
"epoch": 3.4269891379956126,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038610204925617285,
|
|
"loss": 5.9381,
|
|
"mean_token_accuracy": 0.16431807428598405,
|
|
"num_tokens": 69328051.0,
|
|
"step": 32025
|
|
},
|
|
{
|
|
"entropy": 6.4480509757995605,
|
|
"epoch": 3.427524212103376,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00038606880057481807,
|
|
"loss": 5.9854,
|
|
"mean_token_accuracy": 0.15440534353256224,
|
|
"num_tokens": 69339949.0,
|
|
"step": 32030
|
|
},
|
|
{
|
|
"entropy": 6.493301725387573,
|
|
"epoch": 3.4280592862111403,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038603554868636735,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.15667613595724106,
|
|
"num_tokens": 69350188.0,
|
|
"step": 32035
|
|
},
|
|
{
|
|
"entropy": 6.4639139652252195,
|
|
"epoch": 3.428594360318904,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003860022935917807,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.15239210724830626,
|
|
"num_tokens": 69360244.0,
|
|
"step": 32040
|
|
},
|
|
{
|
|
"entropy": 6.461587285995483,
|
|
"epoch": 3.429129434426668,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003859690352920184,
|
|
"loss": 5.996,
|
|
"mean_token_accuracy": 0.15892176181077958,
|
|
"num_tokens": 69371060.0,
|
|
"step": 32045
|
|
},
|
|
{
|
|
"entropy": 6.4993565559387205,
|
|
"epoch": 3.429664508534432,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038593577378804087,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.15409663021564485,
|
|
"num_tokens": 69382371.0,
|
|
"step": 32050
|
|
},
|
|
{
|
|
"entropy": 6.475294160842895,
|
|
"epoch": 3.430199582642196,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0003859025090808083,
|
|
"loss": 6.0092,
|
|
"mean_token_accuracy": 0.15791660249233247,
|
|
"num_tokens": 69392747.0,
|
|
"step": 32055
|
|
},
|
|
{
|
|
"entropy": 6.451462125778198,
|
|
"epoch": 3.43073465674996,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003858692411712815,
|
|
"loss": 5.9524,
|
|
"mean_token_accuracy": 0.1571361981332302,
|
|
"num_tokens": 69403403.0,
|
|
"step": 32060
|
|
},
|
|
{
|
|
"entropy": 6.40102972984314,
|
|
"epoch": 3.431269730857724,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000385835970060421,
|
|
"loss": 5.9698,
|
|
"mean_token_accuracy": 0.15572308897972106,
|
|
"num_tokens": 69414276.0,
|
|
"step": 32065
|
|
},
|
|
{
|
|
"entropy": 6.421910190582276,
|
|
"epoch": 3.4318048049654877,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038580269574918735,
|
|
"loss": 6.0242,
|
|
"mean_token_accuracy": 0.15735460966825485,
|
|
"num_tokens": 69424707.0,
|
|
"step": 32070
|
|
},
|
|
{
|
|
"entropy": 6.398789358139038,
|
|
"epoch": 3.4323398790732518,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038576941823854135,
|
|
"loss": 5.9327,
|
|
"mean_token_accuracy": 0.16665709018707275,
|
|
"num_tokens": 69436638.0,
|
|
"step": 32075
|
|
},
|
|
{
|
|
"entropy": 6.407001543045044,
|
|
"epoch": 3.4328749531810154,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038573613752944407,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.1631282538175583,
|
|
"num_tokens": 69448431.0,
|
|
"step": 32080
|
|
},
|
|
{
|
|
"entropy": 6.4116345882415775,
|
|
"epoch": 3.4334100272887795,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00038570285362285635,
|
|
"loss": 5.962,
|
|
"mean_token_accuracy": 0.17106360495090484,
|
|
"num_tokens": 69458897.0,
|
|
"step": 32085
|
|
},
|
|
{
|
|
"entropy": 6.510710430145264,
|
|
"epoch": 3.433945101396543,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038566956651973927,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.1557389974594116,
|
|
"num_tokens": 69468517.0,
|
|
"step": 32090
|
|
},
|
|
{
|
|
"entropy": 6.402906465530395,
|
|
"epoch": 3.4344801755043073,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000385636276221054,
|
|
"loss": 6.0181,
|
|
"mean_token_accuracy": 0.15323443412780763,
|
|
"num_tokens": 69478634.0,
|
|
"step": 32095
|
|
},
|
|
{
|
|
"entropy": 6.454672718048096,
|
|
"epoch": 3.4350152496120714,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003856029827277619,
|
|
"loss": 5.9755,
|
|
"mean_token_accuracy": 0.15503484457731248,
|
|
"num_tokens": 69490235.0,
|
|
"step": 32100
|
|
},
|
|
{
|
|
"entropy": 6.497976922988892,
|
|
"epoch": 3.435550323719835,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038556968604082413,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.1468839317560196,
|
|
"num_tokens": 69501678.0,
|
|
"step": 32105
|
|
},
|
|
{
|
|
"entropy": 6.471465969085694,
|
|
"epoch": 3.436085397827599,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038553638616120226,
|
|
"loss": 5.9769,
|
|
"mean_token_accuracy": 0.15240469723939895,
|
|
"num_tokens": 69512214.0,
|
|
"step": 32110
|
|
},
|
|
{
|
|
"entropy": 6.47495322227478,
|
|
"epoch": 3.4366204719353632,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038550308308985773,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.1529521718621254,
|
|
"num_tokens": 69522959.0,
|
|
"step": 32115
|
|
},
|
|
{
|
|
"entropy": 6.507119655609131,
|
|
"epoch": 3.437155546043127,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003854697768277522,
|
|
"loss": 6.0691,
|
|
"mean_token_accuracy": 0.15201021134853362,
|
|
"num_tokens": 69534187.0,
|
|
"step": 32120
|
|
},
|
|
{
|
|
"entropy": 6.462261104583741,
|
|
"epoch": 3.437690620150891,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003854364673758474,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.1607736751437187,
|
|
"num_tokens": 69545240.0,
|
|
"step": 32125
|
|
},
|
|
{
|
|
"entropy": 6.395844316482544,
|
|
"epoch": 3.4382256942586547,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038540315473510514,
|
|
"loss": 5.9469,
|
|
"mean_token_accuracy": 0.159482292085886,
|
|
"num_tokens": 69555457.0,
|
|
"step": 32130
|
|
},
|
|
{
|
|
"entropy": 6.470520067214966,
|
|
"epoch": 3.4387607683664188,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003853698389064873,
|
|
"loss": 6.037,
|
|
"mean_token_accuracy": 0.1576562702655792,
|
|
"num_tokens": 69565604.0,
|
|
"step": 32135
|
|
},
|
|
{
|
|
"entropy": 6.489256811141968,
|
|
"epoch": 3.439295842474183,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038533651989095587,
|
|
"loss": 6.0598,
|
|
"mean_token_accuracy": 0.15276462212204933,
|
|
"num_tokens": 69576265.0,
|
|
"step": 32140
|
|
},
|
|
{
|
|
"entropy": 6.530917119979859,
|
|
"epoch": 3.4398309165819465,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003853031976894729,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.15642134249210357,
|
|
"num_tokens": 69586983.0,
|
|
"step": 32145
|
|
},
|
|
{
|
|
"entropy": 6.394391870498657,
|
|
"epoch": 3.4403659906897106,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003852698723030006,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.17386248409748079,
|
|
"num_tokens": 69598455.0,
|
|
"step": 32150
|
|
},
|
|
{
|
|
"entropy": 6.3872405052185055,
|
|
"epoch": 3.4409010647974743,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038523654373250125,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.16040198057889937,
|
|
"num_tokens": 69609922.0,
|
|
"step": 32155
|
|
},
|
|
{
|
|
"entropy": 6.356645154953003,
|
|
"epoch": 3.4414361389052384,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00038520321197893715,
|
|
"loss": 5.9426,
|
|
"mean_token_accuracy": 0.16337401419878006,
|
|
"num_tokens": 69620641.0,
|
|
"step": 32160
|
|
},
|
|
{
|
|
"entropy": 6.403621053695678,
|
|
"epoch": 3.4419712130130025,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003851698770432709,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.16731720864772798,
|
|
"num_tokens": 69631906.0,
|
|
"step": 32165
|
|
},
|
|
{
|
|
"entropy": 6.407867193222046,
|
|
"epoch": 3.442506287120766,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003851365389264649,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.15513896346092224,
|
|
"num_tokens": 69642379.0,
|
|
"step": 32170
|
|
},
|
|
{
|
|
"entropy": 6.340929317474365,
|
|
"epoch": 3.44304136122853,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038510319762948166,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.17273476123809814,
|
|
"num_tokens": 69653363.0,
|
|
"step": 32175
|
|
},
|
|
{
|
|
"entropy": 6.464059686660766,
|
|
"epoch": 3.4435764353362943,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003850698531532843,
|
|
"loss": 5.9467,
|
|
"mean_token_accuracy": 0.16382309645414353,
|
|
"num_tokens": 69663693.0,
|
|
"step": 32180
|
|
},
|
|
{
|
|
"entropy": 6.4415679454803465,
|
|
"epoch": 3.444111509444058,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038503650549883523,
|
|
"loss": 6.017,
|
|
"mean_token_accuracy": 0.15437292903661728,
|
|
"num_tokens": 69673935.0,
|
|
"step": 32185
|
|
},
|
|
{
|
|
"entropy": 6.4024275779724125,
|
|
"epoch": 3.444646583551822,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003850031546670975,
|
|
"loss": 5.9451,
|
|
"mean_token_accuracy": 0.16414360105991363,
|
|
"num_tokens": 69684364.0,
|
|
"step": 32190
|
|
},
|
|
{
|
|
"entropy": 6.4891791343688965,
|
|
"epoch": 3.4451816576595857,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038496980065903433,
|
|
"loss": 6.0795,
|
|
"mean_token_accuracy": 0.15160396471619605,
|
|
"num_tokens": 69695034.0,
|
|
"step": 32195
|
|
},
|
|
{
|
|
"entropy": 6.453883361816406,
|
|
"epoch": 3.44571673176735,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003849364434756084,
|
|
"loss": 6.0381,
|
|
"mean_token_accuracy": 0.1552782878279686,
|
|
"num_tokens": 69705450.0,
|
|
"step": 32200
|
|
},
|
|
{
|
|
"entropy": 6.480652093887329,
|
|
"epoch": 3.4462518058751135,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003849030831177832,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.15626300424337386,
|
|
"num_tokens": 69716365.0,
|
|
"step": 32205
|
|
},
|
|
{
|
|
"entropy": 6.505519151687622,
|
|
"epoch": 3.4467868799828776,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038486971958652196,
|
|
"loss": 6.0565,
|
|
"mean_token_accuracy": 0.15279971659183503,
|
|
"num_tokens": 69726484.0,
|
|
"step": 32210
|
|
},
|
|
{
|
|
"entropy": 6.457992506027222,
|
|
"epoch": 3.4473219540906417,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000384836352882788,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.15070653557777405,
|
|
"num_tokens": 69737498.0,
|
|
"step": 32215
|
|
},
|
|
{
|
|
"entropy": 6.435974788665772,
|
|
"epoch": 3.4478570281984053,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038480298300754473,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.1666262060403824,
|
|
"num_tokens": 69748284.0,
|
|
"step": 32220
|
|
},
|
|
{
|
|
"entropy": 6.499364376068115,
|
|
"epoch": 3.4483921023061694,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038476960996175583,
|
|
"loss": 6.0471,
|
|
"mean_token_accuracy": 0.15263347774744035,
|
|
"num_tokens": 69759745.0,
|
|
"step": 32225
|
|
},
|
|
{
|
|
"entropy": 6.489264488220215,
|
|
"epoch": 3.4489271764139335,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003847362337463848,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.15206801593303682,
|
|
"num_tokens": 69770546.0,
|
|
"step": 32230
|
|
},
|
|
{
|
|
"entropy": 6.394433450698853,
|
|
"epoch": 3.449462250521697,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038470285436239545,
|
|
"loss": 5.9519,
|
|
"mean_token_accuracy": 0.162910296022892,
|
|
"num_tokens": 69781154.0,
|
|
"step": 32235
|
|
},
|
|
{
|
|
"entropy": 6.394288110733032,
|
|
"epoch": 3.4499973246294613,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003846694718107516,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.15400747507810592,
|
|
"num_tokens": 69792311.0,
|
|
"step": 32240
|
|
},
|
|
{
|
|
"entropy": 6.526070594787598,
|
|
"epoch": 3.450532398737225,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003846360860924172,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.153266441822052,
|
|
"num_tokens": 69803181.0,
|
|
"step": 32245
|
|
},
|
|
{
|
|
"entropy": 6.5479419231414795,
|
|
"epoch": 3.451067472844989,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00038460269720835615,
|
|
"loss": 6.0377,
|
|
"mean_token_accuracy": 0.15486300438642503,
|
|
"num_tokens": 69815177.0,
|
|
"step": 32250
|
|
},
|
|
{
|
|
"entropy": 6.5192542552948,
|
|
"epoch": 3.451602546952753,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038456930515953265,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.1486043632030487,
|
|
"num_tokens": 69826730.0,
|
|
"step": 32255
|
|
},
|
|
{
|
|
"entropy": 6.488128900527954,
|
|
"epoch": 3.452137621060517,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003845359099469109,
|
|
"loss": 6.0926,
|
|
"mean_token_accuracy": 0.1526093676686287,
|
|
"num_tokens": 69837321.0,
|
|
"step": 32260
|
|
},
|
|
{
|
|
"entropy": 6.386314725875854,
|
|
"epoch": 3.452672695168281,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003845025115714551,
|
|
"loss": 5.9409,
|
|
"mean_token_accuracy": 0.1579664334654808,
|
|
"num_tokens": 69849093.0,
|
|
"step": 32265
|
|
},
|
|
{
|
|
"entropy": 6.431071853637695,
|
|
"epoch": 3.4532077692760446,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003844691100341297,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.16255209147930144,
|
|
"num_tokens": 69859131.0,
|
|
"step": 32270
|
|
},
|
|
{
|
|
"entropy": 6.453418493270874,
|
|
"epoch": 3.4537428433838087,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003844357053358991,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.1531774789094925,
|
|
"num_tokens": 69870089.0,
|
|
"step": 32275
|
|
},
|
|
{
|
|
"entropy": 6.415515422821045,
|
|
"epoch": 3.4542779174915728,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003844022974777279,
|
|
"loss": 6.0025,
|
|
"mean_token_accuracy": 0.15771927908062935,
|
|
"num_tokens": 69880761.0,
|
|
"step": 32280
|
|
},
|
|
{
|
|
"entropy": 6.501542234420777,
|
|
"epoch": 3.4548129915993364,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003843688864605807,
|
|
"loss": 5.9457,
|
|
"mean_token_accuracy": 0.15849718004465102,
|
|
"num_tokens": 69891205.0,
|
|
"step": 32285
|
|
},
|
|
{
|
|
"entropy": 6.4620973587036135,
|
|
"epoch": 3.4553480657071005,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038433547228542233,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.15515270680189133,
|
|
"num_tokens": 69902038.0,
|
|
"step": 32290
|
|
},
|
|
{
|
|
"entropy": 6.550300884246826,
|
|
"epoch": 3.455883139814864,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038430205495321753,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.14657480120658875,
|
|
"num_tokens": 69914449.0,
|
|
"step": 32295
|
|
},
|
|
{
|
|
"entropy": 6.5377472877502445,
|
|
"epoch": 3.4564182139226283,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003842686344649312,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.1492585778236389,
|
|
"num_tokens": 69926096.0,
|
|
"step": 32300
|
|
},
|
|
{
|
|
"entropy": 6.446306467056274,
|
|
"epoch": 3.4569532880303924,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038423521082152844,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.1593390956521034,
|
|
"num_tokens": 69935947.0,
|
|
"step": 32305
|
|
},
|
|
{
|
|
"entropy": 6.399693870544434,
|
|
"epoch": 3.457488362138156,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003842017840239744,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.15324069708585739,
|
|
"num_tokens": 69946701.0,
|
|
"step": 32310
|
|
},
|
|
{
|
|
"entropy": 6.5204565048217775,
|
|
"epoch": 3.45802343624592,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003841683540732341,
|
|
"loss": 6.0926,
|
|
"mean_token_accuracy": 0.1493264392018318,
|
|
"num_tokens": 69957011.0,
|
|
"step": 32315
|
|
},
|
|
{
|
|
"entropy": 6.485901927947998,
|
|
"epoch": 3.458558510353684,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003841349209702729,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.1567941352725029,
|
|
"num_tokens": 69968224.0,
|
|
"step": 32320
|
|
},
|
|
{
|
|
"entropy": 6.48239803314209,
|
|
"epoch": 3.459093584461448,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003841014847160563,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.1513494461774826,
|
|
"num_tokens": 69979171.0,
|
|
"step": 32325
|
|
},
|
|
{
|
|
"entropy": 6.496701574325561,
|
|
"epoch": 3.459628658569212,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003840680453115496,
|
|
"loss": 6.0047,
|
|
"mean_token_accuracy": 0.15916132628917695,
|
|
"num_tokens": 69990001.0,
|
|
"step": 32330
|
|
},
|
|
{
|
|
"entropy": 6.448809337615967,
|
|
"epoch": 3.4601637326769756,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038403460275771836,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.1587820306420326,
|
|
"num_tokens": 70001263.0,
|
|
"step": 32335
|
|
},
|
|
{
|
|
"entropy": 6.409688901901245,
|
|
"epoch": 3.4606988067847397,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038400115705552833,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.15736901313066481,
|
|
"num_tokens": 70011586.0,
|
|
"step": 32340
|
|
},
|
|
{
|
|
"entropy": 6.2942039489746096,
|
|
"epoch": 3.461233880892504,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003839677082059453,
|
|
"loss": 5.914,
|
|
"mean_token_accuracy": 0.16126955002546312,
|
|
"num_tokens": 70023607.0,
|
|
"step": 32345
|
|
},
|
|
{
|
|
"entropy": 6.4862018585205075,
|
|
"epoch": 3.4617689550002675,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038393425620993483,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.15311522483825685,
|
|
"num_tokens": 70033099.0,
|
|
"step": 32350
|
|
},
|
|
{
|
|
"entropy": 6.498335170745849,
|
|
"epoch": 3.4623040291080316,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038390080106846314,
|
|
"loss": 5.9744,
|
|
"mean_token_accuracy": 0.16738997399806976,
|
|
"num_tokens": 70043609.0,
|
|
"step": 32355
|
|
},
|
|
{
|
|
"entropy": 6.443398904800415,
|
|
"epoch": 3.4628391032157952,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003838673427824962,
|
|
"loss": 5.9881,
|
|
"mean_token_accuracy": 0.1581096202135086,
|
|
"num_tokens": 70054901.0,
|
|
"step": 32360
|
|
},
|
|
{
|
|
"entropy": 6.4767418384552,
|
|
"epoch": 3.4633741773235593,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038383388135299984,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.1500343680381775,
|
|
"num_tokens": 70065729.0,
|
|
"step": 32365
|
|
},
|
|
{
|
|
"entropy": 6.470161199569702,
|
|
"epoch": 3.463909251431323,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003838004167809406,
|
|
"loss": 5.9842,
|
|
"mean_token_accuracy": 0.1510693535208702,
|
|
"num_tokens": 70077841.0,
|
|
"step": 32370
|
|
},
|
|
{
|
|
"entropy": 6.491604900360107,
|
|
"epoch": 3.464444325539087,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003837669490672845,
|
|
"loss": 6.0496,
|
|
"mean_token_accuracy": 0.1519874095916748,
|
|
"num_tokens": 70089205.0,
|
|
"step": 32375
|
|
},
|
|
{
|
|
"entropy": 6.416820764541626,
|
|
"epoch": 3.464979399646851,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003837334782129981,
|
|
"loss": 6.0494,
|
|
"mean_token_accuracy": 0.1606932058930397,
|
|
"num_tokens": 70100118.0,
|
|
"step": 32380
|
|
},
|
|
{
|
|
"entropy": 6.413497877120972,
|
|
"epoch": 3.465514473754615,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038370000421904775,
|
|
"loss": 5.9197,
|
|
"mean_token_accuracy": 0.15871790796518326,
|
|
"num_tokens": 70110502.0,
|
|
"step": 32385
|
|
},
|
|
{
|
|
"entropy": 6.531287288665771,
|
|
"epoch": 3.466049547862379,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003836665270864001,
|
|
"loss": 6.0146,
|
|
"mean_token_accuracy": 0.15480633825063705,
|
|
"num_tokens": 70121040.0,
|
|
"step": 32390
|
|
},
|
|
{
|
|
"entropy": 6.5234331607818605,
|
|
"epoch": 3.466584621970143,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038363304681602174,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.1556089624762535,
|
|
"num_tokens": 70132537.0,
|
|
"step": 32395
|
|
},
|
|
{
|
|
"entropy": 6.4742859363555905,
|
|
"epoch": 3.4671196960779067,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003835995634088794,
|
|
"loss": 6.0129,
|
|
"mean_token_accuracy": 0.16051765084266661,
|
|
"num_tokens": 70143449.0,
|
|
"step": 32400
|
|
},
|
|
{
|
|
"entropy": 6.3762012958526615,
|
|
"epoch": 3.467654770185671,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038356607686593994,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.1617530271410942,
|
|
"num_tokens": 70154674.0,
|
|
"step": 32405
|
|
},
|
|
{
|
|
"entropy": 6.46034460067749,
|
|
"epoch": 3.4681898442934345,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003835325871881703,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.15474030524492263,
|
|
"num_tokens": 70165342.0,
|
|
"step": 32410
|
|
},
|
|
{
|
|
"entropy": 6.495969009399414,
|
|
"epoch": 3.4687249184011986,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003834990943765374,
|
|
"loss": 5.9725,
|
|
"mean_token_accuracy": 0.1597425624728203,
|
|
"num_tokens": 70177028.0,
|
|
"step": 32415
|
|
},
|
|
{
|
|
"entropy": 6.443191957473755,
|
|
"epoch": 3.4692599925089627,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003834655984320084,
|
|
"loss": 6.058,
|
|
"mean_token_accuracy": 0.15102147981524466,
|
|
"num_tokens": 70188655.0,
|
|
"step": 32420
|
|
},
|
|
{
|
|
"entropy": 6.509590196609497,
|
|
"epoch": 3.4697950666167263,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003834320993555505,
|
|
"loss": 6.0944,
|
|
"mean_token_accuracy": 0.14951472282409667,
|
|
"num_tokens": 70199288.0,
|
|
"step": 32425
|
|
},
|
|
{
|
|
"entropy": 6.504211807250977,
|
|
"epoch": 3.4703301407244904,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00038339859714813104,
|
|
"loss": 6.0229,
|
|
"mean_token_accuracy": 0.15812589675188066,
|
|
"num_tokens": 70210417.0,
|
|
"step": 32430
|
|
},
|
|
{
|
|
"entropy": 6.459775352478028,
|
|
"epoch": 3.470865214832254,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003833650918107172,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.15469842851161958,
|
|
"num_tokens": 70220339.0,
|
|
"step": 32435
|
|
},
|
|
{
|
|
"entropy": 6.415725374221802,
|
|
"epoch": 3.471400288940018,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003833315833442766,
|
|
"loss": 6.0244,
|
|
"mean_token_accuracy": 0.1562066376209259,
|
|
"num_tokens": 70230699.0,
|
|
"step": 32440
|
|
},
|
|
{
|
|
"entropy": 6.489306306838989,
|
|
"epoch": 3.4719353630477823,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038329807174977676,
|
|
"loss": 6.0057,
|
|
"mean_token_accuracy": 0.15389417558908464,
|
|
"num_tokens": 70242464.0,
|
|
"step": 32445
|
|
},
|
|
{
|
|
"entropy": 6.543923664093017,
|
|
"epoch": 3.472470437155546,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038326455702818537,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.14856957644224167,
|
|
"num_tokens": 70253631.0,
|
|
"step": 32450
|
|
},
|
|
{
|
|
"entropy": 6.45035309791565,
|
|
"epoch": 3.47300551126331,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038323103918047,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.14910193383693696,
|
|
"num_tokens": 70266055.0,
|
|
"step": 32455
|
|
},
|
|
{
|
|
"entropy": 6.460875177383423,
|
|
"epoch": 3.473540585371074,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003831975182075987,
|
|
"loss": 6.0574,
|
|
"mean_token_accuracy": 0.15265400856733322,
|
|
"num_tokens": 70276680.0,
|
|
"step": 32460
|
|
},
|
|
{
|
|
"entropy": 6.534516286849976,
|
|
"epoch": 3.474075659478838,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038316399411053917,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.15694202929735185,
|
|
"num_tokens": 70287424.0,
|
|
"step": 32465
|
|
},
|
|
{
|
|
"entropy": 6.456464099884033,
|
|
"epoch": 3.474610733586602,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003831304668902595,
|
|
"loss": 5.961,
|
|
"mean_token_accuracy": 0.15774993896484374,
|
|
"num_tokens": 70298005.0,
|
|
"step": 32470
|
|
},
|
|
{
|
|
"entropy": 6.405784654617309,
|
|
"epoch": 3.4751458076943655,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003830969365477279,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.15035266876220704,
|
|
"num_tokens": 70309200.0,
|
|
"step": 32475
|
|
},
|
|
{
|
|
"entropy": 6.406075811386108,
|
|
"epoch": 3.4756808818021296,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038306340308391233,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.16079496145248412,
|
|
"num_tokens": 70320957.0,
|
|
"step": 32480
|
|
},
|
|
{
|
|
"entropy": 6.497291421890258,
|
|
"epoch": 3.4762159559098933,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003830298664997813,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.15070699602365495,
|
|
"num_tokens": 70331960.0,
|
|
"step": 32485
|
|
},
|
|
{
|
|
"entropy": 6.476868963241577,
|
|
"epoch": 3.4767510300176574,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000382996326796303,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.15679605454206466,
|
|
"num_tokens": 70342449.0,
|
|
"step": 32490
|
|
},
|
|
{
|
|
"entropy": 6.428432273864746,
|
|
"epoch": 3.4772861041254215,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003829627839744459,
|
|
"loss": 5.9878,
|
|
"mean_token_accuracy": 0.15438885986804962,
|
|
"num_tokens": 70353322.0,
|
|
"step": 32495
|
|
},
|
|
{
|
|
"entropy": 6.425268363952637,
|
|
"epoch": 3.477821178233185,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003829292380351786,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.16452835500240326,
|
|
"num_tokens": 70364824.0,
|
|
"step": 32500
|
|
},
|
|
{
|
|
"entropy": 6.483251142501831,
|
|
"epoch": 3.4783562523409493,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003828956889794698,
|
|
"loss": 5.9722,
|
|
"mean_token_accuracy": 0.15855835974216462,
|
|
"num_tokens": 70376811.0,
|
|
"step": 32505
|
|
},
|
|
{
|
|
"entropy": 6.470626544952393,
|
|
"epoch": 3.4788913264487134,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038286213680828804,
|
|
"loss": 6.0299,
|
|
"mean_token_accuracy": 0.15371640175580978,
|
|
"num_tokens": 70387735.0,
|
|
"step": 32510
|
|
},
|
|
{
|
|
"entropy": 6.4015003681182865,
|
|
"epoch": 3.479426400556477,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003828285815226023,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.1603648245334625,
|
|
"num_tokens": 70398860.0,
|
|
"step": 32515
|
|
},
|
|
{
|
|
"entropy": 6.399206066131592,
|
|
"epoch": 3.479961474664241,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038279502312338137,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.15422433540225028,
|
|
"num_tokens": 70409340.0,
|
|
"step": 32520
|
|
},
|
|
{
|
|
"entropy": 6.520442390441895,
|
|
"epoch": 3.4804965487720048,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003827614616115943,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.1522905021905899,
|
|
"num_tokens": 70419880.0,
|
|
"step": 32525
|
|
},
|
|
{
|
|
"entropy": 6.438402700424194,
|
|
"epoch": 3.481031622879769,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003827278969882102,
|
|
"loss": 5.9686,
|
|
"mean_token_accuracy": 0.16474663615226745,
|
|
"num_tokens": 70431033.0,
|
|
"step": 32530
|
|
},
|
|
{
|
|
"entropy": 6.424052572250366,
|
|
"epoch": 3.481566696987533,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003826943292541982,
|
|
"loss": 6.0143,
|
|
"mean_token_accuracy": 0.15661125928163527,
|
|
"num_tokens": 70442315.0,
|
|
"step": 32535
|
|
},
|
|
{
|
|
"entropy": 6.47323522567749,
|
|
"epoch": 3.4821017710952966,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038266075841052763,
|
|
"loss": 6.0282,
|
|
"mean_token_accuracy": 0.1551033452153206,
|
|
"num_tokens": 70453195.0,
|
|
"step": 32540
|
|
},
|
|
{
|
|
"entropy": 6.3998770236969,
|
|
"epoch": 3.4826368452030607,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003826271844581677,
|
|
"loss": 5.9723,
|
|
"mean_token_accuracy": 0.15436771661043167,
|
|
"num_tokens": 70463855.0,
|
|
"step": 32545
|
|
},
|
|
{
|
|
"entropy": 6.441708946228028,
|
|
"epoch": 3.4831719193108244,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000382593607398088,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.15093257427215576,
|
|
"num_tokens": 70474517.0,
|
|
"step": 32550
|
|
},
|
|
{
|
|
"entropy": 6.477252721786499,
|
|
"epoch": 3.4837069934185885,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000382560027231258,
|
|
"loss": 6.0692,
|
|
"mean_token_accuracy": 0.14820388853549957,
|
|
"num_tokens": 70486256.0,
|
|
"step": 32555
|
|
},
|
|
{
|
|
"entropy": 6.518399238586426,
|
|
"epoch": 3.4842420675263526,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003825264439586473,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.15542059987783433,
|
|
"num_tokens": 70496771.0,
|
|
"step": 32560
|
|
},
|
|
{
|
|
"entropy": 6.542031288146973,
|
|
"epoch": 3.4847771416341162,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00038249285758122566,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.15250821709632872,
|
|
"num_tokens": 70507994.0,
|
|
"step": 32565
|
|
},
|
|
{
|
|
"entropy": 6.45143141746521,
|
|
"epoch": 3.4853122157418803,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038245926809996284,
|
|
"loss": 6.0155,
|
|
"mean_token_accuracy": 0.15486550331115723,
|
|
"num_tokens": 70518544.0,
|
|
"step": 32570
|
|
},
|
|
{
|
|
"entropy": 6.441517925262451,
|
|
"epoch": 3.485847289849644,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003824256755158288,
|
|
"loss": 6.0258,
|
|
"mean_token_accuracy": 0.1579287827014923,
|
|
"num_tokens": 70530075.0,
|
|
"step": 32575
|
|
},
|
|
{
|
|
"entropy": 6.422108745574951,
|
|
"epoch": 3.486382363957408,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003823920798297934,
|
|
"loss": 6.0289,
|
|
"mean_token_accuracy": 0.1622357189655304,
|
|
"num_tokens": 70542125.0,
|
|
"step": 32580
|
|
},
|
|
{
|
|
"entropy": 6.547072076797486,
|
|
"epoch": 3.486917438065172,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038235848104282684,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.15195575207471848,
|
|
"num_tokens": 70552710.0,
|
|
"step": 32585
|
|
},
|
|
{
|
|
"entropy": 6.497435092926025,
|
|
"epoch": 3.487452512172936,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038232487915589925,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.15305493474006654,
|
|
"num_tokens": 70564467.0,
|
|
"step": 32590
|
|
},
|
|
{
|
|
"entropy": 6.407402515411377,
|
|
"epoch": 3.4879875862807,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038229127416998076,
|
|
"loss": 5.9221,
|
|
"mean_token_accuracy": 0.16476698219776154,
|
|
"num_tokens": 70575164.0,
|
|
"step": 32595
|
|
},
|
|
{
|
|
"entropy": 6.451571655273438,
|
|
"epoch": 3.4885226603884636,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038225766608604184,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.16152308583259584,
|
|
"num_tokens": 70584841.0,
|
|
"step": 32600
|
|
},
|
|
{
|
|
"entropy": 6.421479797363281,
|
|
"epoch": 3.4890577344962277,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038222405490505296,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.15591635629534722,
|
|
"num_tokens": 70595189.0,
|
|
"step": 32605
|
|
},
|
|
{
|
|
"entropy": 6.450427055358887,
|
|
"epoch": 3.489592808603992,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038219044062798454,
|
|
"loss": 6.008,
|
|
"mean_token_accuracy": 0.1581943541765213,
|
|
"num_tokens": 70607858.0,
|
|
"step": 32610
|
|
},
|
|
{
|
|
"entropy": 6.474091243743897,
|
|
"epoch": 3.4901278827117554,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038215682325580714,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.15936322510242462,
|
|
"num_tokens": 70618281.0,
|
|
"step": 32615
|
|
},
|
|
{
|
|
"entropy": 6.421411752700806,
|
|
"epoch": 3.4906629568195195,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003821232027894916,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.15639851242303848,
|
|
"num_tokens": 70629822.0,
|
|
"step": 32620
|
|
},
|
|
{
|
|
"entropy": 6.384566974639893,
|
|
"epoch": 3.4911980309272836,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003820895792300086,
|
|
"loss": 6.006,
|
|
"mean_token_accuracy": 0.1559011831879616,
|
|
"num_tokens": 70639981.0,
|
|
"step": 32625
|
|
},
|
|
{
|
|
"entropy": 6.538076734542846,
|
|
"epoch": 3.4917331050350473,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038205595257832906,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.1464655339717865,
|
|
"num_tokens": 70651196.0,
|
|
"step": 32630
|
|
},
|
|
{
|
|
"entropy": 6.4686055183410645,
|
|
"epoch": 3.4922681791428114,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038202232283542385,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.15865162312984465,
|
|
"num_tokens": 70662930.0,
|
|
"step": 32635
|
|
},
|
|
{
|
|
"entropy": 6.410705614089966,
|
|
"epoch": 3.492803253250575,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003819886900022642,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.15615216940641402,
|
|
"num_tokens": 70674276.0,
|
|
"step": 32640
|
|
},
|
|
{
|
|
"entropy": 6.4635059356689455,
|
|
"epoch": 3.493338327358339,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003819550540798212,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.1563323199748993,
|
|
"num_tokens": 70684706.0,
|
|
"step": 32645
|
|
},
|
|
{
|
|
"entropy": 6.4172626495361325,
|
|
"epoch": 3.493873401466103,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000381921415069066,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.15530487447977065,
|
|
"num_tokens": 70695468.0,
|
|
"step": 32650
|
|
},
|
|
{
|
|
"entropy": 6.3938051700592045,
|
|
"epoch": 3.494408475573867,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038188777297096986,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.16544314175844194,
|
|
"num_tokens": 70706141.0,
|
|
"step": 32655
|
|
},
|
|
{
|
|
"entropy": 6.519157218933105,
|
|
"epoch": 3.494943549681631,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038185412778650435,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.14648372679948807,
|
|
"num_tokens": 70716615.0,
|
|
"step": 32660
|
|
},
|
|
{
|
|
"entropy": 6.496552801132202,
|
|
"epoch": 3.4954786237893947,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038182047951664097,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.15660737305879593,
|
|
"num_tokens": 70727734.0,
|
|
"step": 32665
|
|
},
|
|
{
|
|
"entropy": 6.41196928024292,
|
|
"epoch": 3.4960136978971588,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003817868281623512,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.16553709656000137,
|
|
"num_tokens": 70738539.0,
|
|
"step": 32670
|
|
},
|
|
{
|
|
"entropy": 6.408115720748901,
|
|
"epoch": 3.496548772004923,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038175317372460683,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.16444526463747025,
|
|
"num_tokens": 70749043.0,
|
|
"step": 32675
|
|
},
|
|
{
|
|
"entropy": 6.422844743728637,
|
|
"epoch": 3.4970838461126865,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038171951620437957,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.15550876557826995,
|
|
"num_tokens": 70759154.0,
|
|
"step": 32680
|
|
},
|
|
{
|
|
"entropy": 6.421111679077148,
|
|
"epoch": 3.4976189202204506,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038168585560264124,
|
|
"loss": 6.0007,
|
|
"mean_token_accuracy": 0.15765813887119293,
|
|
"num_tokens": 70770650.0,
|
|
"step": 32685
|
|
},
|
|
{
|
|
"entropy": 6.454835510253906,
|
|
"epoch": 3.4981539943282143,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003816521919203639,
|
|
"loss": 5.9941,
|
|
"mean_token_accuracy": 0.1596194848418236,
|
|
"num_tokens": 70781254.0,
|
|
"step": 32690
|
|
},
|
|
{
|
|
"entropy": 6.414627933502198,
|
|
"epoch": 3.4986890684359784,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038161852515851934,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.16208407580852507,
|
|
"num_tokens": 70791090.0,
|
|
"step": 32695
|
|
},
|
|
{
|
|
"entropy": 6.387426137924194,
|
|
"epoch": 3.4992241425437425,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0003815848553180799,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.1553620621562004,
|
|
"num_tokens": 70801020.0,
|
|
"step": 32700
|
|
},
|
|
{
|
|
"entropy": 6.384316444396973,
|
|
"epoch": 3.499759216651506,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003815511824000179,
|
|
"loss": 5.915,
|
|
"mean_token_accuracy": 0.16743748486042023,
|
|
"num_tokens": 70811308.0,
|
|
"step": 32705
|
|
},
|
|
{
|
|
"entropy": 6.4936450004577635,
|
|
"epoch": 3.5002942907592702,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038151750640530533,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.15193752944469452,
|
|
"num_tokens": 70822155.0,
|
|
"step": 32710
|
|
},
|
|
{
|
|
"entropy": 6.5279113292694095,
|
|
"epoch": 3.500829364867034,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003814838273349147,
|
|
"loss": 6.059,
|
|
"mean_token_accuracy": 0.15734566748142242,
|
|
"num_tokens": 70834132.0,
|
|
"step": 32715
|
|
},
|
|
{
|
|
"entropy": 6.462293815612793,
|
|
"epoch": 3.501364438974798,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038145014518981864,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.15426165759563445,
|
|
"num_tokens": 70845756.0,
|
|
"step": 32720
|
|
},
|
|
{
|
|
"entropy": 6.412227916717529,
|
|
"epoch": 3.501899513082562,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003814164599709895,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.15408299416303634,
|
|
"num_tokens": 70856672.0,
|
|
"step": 32725
|
|
},
|
|
{
|
|
"entropy": 6.470078611373902,
|
|
"epoch": 3.5024345871903257,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038138277167940006,
|
|
"loss": 5.989,
|
|
"mean_token_accuracy": 0.15067895054817199,
|
|
"num_tokens": 70867993.0,
|
|
"step": 32730
|
|
},
|
|
{
|
|
"entropy": 6.466637039184571,
|
|
"epoch": 3.50296966129809,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003813490803160231,
|
|
"loss": 5.9765,
|
|
"mean_token_accuracy": 0.15929671972990037,
|
|
"num_tokens": 70878061.0,
|
|
"step": 32735
|
|
},
|
|
{
|
|
"entropy": 6.328454542160034,
|
|
"epoch": 3.503504735405854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038131538588183133,
|
|
"loss": 5.9474,
|
|
"mean_token_accuracy": 0.16418026387691498,
|
|
"num_tokens": 70889244.0,
|
|
"step": 32740
|
|
},
|
|
{
|
|
"entropy": 6.451546049118042,
|
|
"epoch": 3.5040398095136176,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003812816883777977,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.1527376651763916,
|
|
"num_tokens": 70900391.0,
|
|
"step": 32745
|
|
},
|
|
{
|
|
"entropy": 6.456113624572754,
|
|
"epoch": 3.5045748836213817,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003812479878048953,
|
|
"loss": 5.8855,
|
|
"mean_token_accuracy": 0.16041273921728133,
|
|
"num_tokens": 70910743.0,
|
|
"step": 32750
|
|
},
|
|
{
|
|
"entropy": 6.442938327789307,
|
|
"epoch": 3.5051099577291454,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038121428416409725,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.16228840202093125,
|
|
"num_tokens": 70922126.0,
|
|
"step": 32755
|
|
},
|
|
{
|
|
"entropy": 6.465249824523926,
|
|
"epoch": 3.5056450318369095,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003811805774563765,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.15352711379528045,
|
|
"num_tokens": 70932657.0,
|
|
"step": 32760
|
|
},
|
|
{
|
|
"entropy": 6.433500957489014,
|
|
"epoch": 3.506180105944673,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003811468676827066,
|
|
"loss": 5.9989,
|
|
"mean_token_accuracy": 0.15631604045629502,
|
|
"num_tokens": 70943609.0,
|
|
"step": 32765
|
|
},
|
|
{
|
|
"entropy": 6.485906934738159,
|
|
"epoch": 3.506715180052437,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003811131548440608,
|
|
"loss": 6.0101,
|
|
"mean_token_accuracy": 0.1610604465007782,
|
|
"num_tokens": 70954055.0,
|
|
"step": 32770
|
|
},
|
|
{
|
|
"entropy": 6.3821007251739506,
|
|
"epoch": 3.5072502541602013,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00038107943894141256,
|
|
"loss": 5.9489,
|
|
"mean_token_accuracy": 0.16231930553913115,
|
|
"num_tokens": 70965411.0,
|
|
"step": 32775
|
|
},
|
|
{
|
|
"entropy": 6.432525968551635,
|
|
"epoch": 3.507785328267965,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038104571997573544,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.15526009052991868,
|
|
"num_tokens": 70976310.0,
|
|
"step": 32780
|
|
},
|
|
{
|
|
"entropy": 6.519391059875488,
|
|
"epoch": 3.508320402375729,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003810119979480031,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.1469672605395317,
|
|
"num_tokens": 70986578.0,
|
|
"step": 32785
|
|
},
|
|
{
|
|
"entropy": 6.477600955963135,
|
|
"epoch": 3.508855476483493,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003809782728591891,
|
|
"loss": 5.9845,
|
|
"mean_token_accuracy": 0.16497037410736085,
|
|
"num_tokens": 70997360.0,
|
|
"step": 32790
|
|
},
|
|
{
|
|
"entropy": 6.456406116485596,
|
|
"epoch": 3.509390550591257,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003809445447102675,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.15778759866952896,
|
|
"num_tokens": 71006754.0,
|
|
"step": 32795
|
|
},
|
|
{
|
|
"entropy": 6.39552493095398,
|
|
"epoch": 3.509925624699021,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038091081350221203,
|
|
"loss": 5.9599,
|
|
"mean_token_accuracy": 0.15698970556259156,
|
|
"num_tokens": 71017842.0,
|
|
"step": 32800
|
|
},
|
|
{
|
|
"entropy": 6.389916610717774,
|
|
"epoch": 3.5104606988067846,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038087707923599657,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.1597716748714447,
|
|
"num_tokens": 71028622.0,
|
|
"step": 32805
|
|
},
|
|
{
|
|
"entropy": 6.416409206390381,
|
|
"epoch": 3.5109957729145487,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038084334191259547,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.17437755316495895,
|
|
"num_tokens": 71041212.0,
|
|
"step": 32810
|
|
},
|
|
{
|
|
"entropy": 6.470283031463623,
|
|
"epoch": 3.5115308470223123,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003808096015329827,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.15438440591096877,
|
|
"num_tokens": 71051394.0,
|
|
"step": 32815
|
|
},
|
|
{
|
|
"entropy": 6.403356885910034,
|
|
"epoch": 3.5120659211300764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003807758580981325,
|
|
"loss": 5.9746,
|
|
"mean_token_accuracy": 0.15477490276098252,
|
|
"num_tokens": 71062099.0,
|
|
"step": 32820
|
|
},
|
|
{
|
|
"entropy": 6.543943071365357,
|
|
"epoch": 3.5126009952378405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038074211160901933,
|
|
"loss": 6.0657,
|
|
"mean_token_accuracy": 0.15459081828594207,
|
|
"num_tokens": 71072647.0,
|
|
"step": 32825
|
|
},
|
|
{
|
|
"entropy": 6.396431732177734,
|
|
"epoch": 3.513136069345604,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003807083620666175,
|
|
"loss": 5.9474,
|
|
"mean_token_accuracy": 0.165768039226532,
|
|
"num_tokens": 71083261.0,
|
|
"step": 32830
|
|
},
|
|
{
|
|
"entropy": 6.434049320220947,
|
|
"epoch": 3.5136711434533683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038067460947190156,
|
|
"loss": 6.0408,
|
|
"mean_token_accuracy": 0.15459303706884384,
|
|
"num_tokens": 71094427.0,
|
|
"step": 32835
|
|
},
|
|
{
|
|
"entropy": 6.5002806186676025,
|
|
"epoch": 3.5142062175611324,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003806408538258462,
|
|
"loss": 5.9938,
|
|
"mean_token_accuracy": 0.15522413998842238,
|
|
"num_tokens": 71103985.0,
|
|
"step": 32840
|
|
},
|
|
{
|
|
"entropy": 6.4912923812866214,
|
|
"epoch": 3.514741291668896,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003806070951294259,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.15380573868751526,
|
|
"num_tokens": 71114748.0,
|
|
"step": 32845
|
|
},
|
|
{
|
|
"entropy": 6.461653375625611,
|
|
"epoch": 3.51527636577666,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003805733333836158,
|
|
"loss": 5.9673,
|
|
"mean_token_accuracy": 0.156727197766304,
|
|
"num_tokens": 71126074.0,
|
|
"step": 32850
|
|
},
|
|
{
|
|
"entropy": 6.456625843048096,
|
|
"epoch": 3.5158114398844242,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003805395685893903,
|
|
"loss": 6.0386,
|
|
"mean_token_accuracy": 0.1546942934393883,
|
|
"num_tokens": 71136471.0,
|
|
"step": 32855
|
|
},
|
|
{
|
|
"entropy": 6.487563514709473,
|
|
"epoch": 3.516346513992188,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003805058007477247,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.15239442884922028,
|
|
"num_tokens": 71147348.0,
|
|
"step": 32860
|
|
},
|
|
{
|
|
"entropy": 6.4964159488677975,
|
|
"epoch": 3.516881588099952,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038047202985959394,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.15408742129802705,
|
|
"num_tokens": 71158015.0,
|
|
"step": 32865
|
|
},
|
|
{
|
|
"entropy": 6.453237724304199,
|
|
"epoch": 3.5174166622077156,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003804382559259731,
|
|
"loss": 6.0017,
|
|
"mean_token_accuracy": 0.15890237390995027,
|
|
"num_tokens": 71169271.0,
|
|
"step": 32870
|
|
},
|
|
{
|
|
"entropy": 6.403283214569091,
|
|
"epoch": 3.5179517363154797,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003804044789478374,
|
|
"loss": 5.9568,
|
|
"mean_token_accuracy": 0.15997139513492584,
|
|
"num_tokens": 71179493.0,
|
|
"step": 32875
|
|
},
|
|
{
|
|
"entropy": 6.454048442840576,
|
|
"epoch": 3.5184868104232434,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003803706989261622,
|
|
"loss": 5.9826,
|
|
"mean_token_accuracy": 0.16297055780887604,
|
|
"num_tokens": 71190117.0,
|
|
"step": 32880
|
|
},
|
|
{
|
|
"entropy": 6.506569862365723,
|
|
"epoch": 3.5190218845310075,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003803369158619229,
|
|
"loss": 5.9845,
|
|
"mean_token_accuracy": 0.1547867774963379,
|
|
"num_tokens": 71200177.0,
|
|
"step": 32885
|
|
},
|
|
{
|
|
"entropy": 6.451822137832641,
|
|
"epoch": 3.5195569586387716,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038030312975609494,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.1573134958744049,
|
|
"num_tokens": 71211505.0,
|
|
"step": 32890
|
|
},
|
|
{
|
|
"entropy": 6.400374031066894,
|
|
"epoch": 3.5200920327465353,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003802693406096539,
|
|
"loss": 5.9913,
|
|
"mean_token_accuracy": 0.15990067422389984,
|
|
"num_tokens": 71221055.0,
|
|
"step": 32895
|
|
},
|
|
{
|
|
"entropy": 6.447267150878906,
|
|
"epoch": 3.5206271068542994,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003802355484235756,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.1477471485733986,
|
|
"num_tokens": 71230702.0,
|
|
"step": 32900
|
|
},
|
|
{
|
|
"entropy": 6.430709791183472,
|
|
"epoch": 3.5211621809620635,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003802017531988354,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.15857502967119216,
|
|
"num_tokens": 71241665.0,
|
|
"step": 32905
|
|
},
|
|
{
|
|
"entropy": 6.477494764328003,
|
|
"epoch": 3.521697255069827,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038016795493640946,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.15493522137403487,
|
|
"num_tokens": 71252662.0,
|
|
"step": 32910
|
|
},
|
|
{
|
|
"entropy": 6.424300813674927,
|
|
"epoch": 3.522232329177591,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003801341536372736,
|
|
"loss": 5.976,
|
|
"mean_token_accuracy": 0.15801501274108887,
|
|
"num_tokens": 71263198.0,
|
|
"step": 32915
|
|
},
|
|
{
|
|
"entropy": 6.412079238891602,
|
|
"epoch": 3.522767403285355,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038010034930240376,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.16029412150382996,
|
|
"num_tokens": 71274464.0,
|
|
"step": 32920
|
|
},
|
|
{
|
|
"entropy": 6.392494153976441,
|
|
"epoch": 3.523302477393119,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003800665419327762,
|
|
"loss": 6.0077,
|
|
"mean_token_accuracy": 0.15940517336130142,
|
|
"num_tokens": 71285897.0,
|
|
"step": 32925
|
|
},
|
|
{
|
|
"entropy": 6.4309686660766605,
|
|
"epoch": 3.5238375515008826,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003800327315293669,
|
|
"loss": 5.9217,
|
|
"mean_token_accuracy": 0.15925260484218598,
|
|
"num_tokens": 71296374.0,
|
|
"step": 32930
|
|
},
|
|
{
|
|
"entropy": 6.442317533493042,
|
|
"epoch": 3.5243726256086467,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037999891809315233,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.1600348472595215,
|
|
"num_tokens": 71307401.0,
|
|
"step": 32935
|
|
},
|
|
{
|
|
"entropy": 6.442062044143677,
|
|
"epoch": 3.524907699716411,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037996510162510873,
|
|
"loss": 5.9433,
|
|
"mean_token_accuracy": 0.16476712375879288,
|
|
"num_tokens": 71318261.0,
|
|
"step": 32940
|
|
},
|
|
{
|
|
"entropy": 6.397099733352661,
|
|
"epoch": 3.5254427738241745,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003799312821262126,
|
|
"loss": 5.9175,
|
|
"mean_token_accuracy": 0.16159497052431107,
|
|
"num_tokens": 71328911.0,
|
|
"step": 32945
|
|
},
|
|
{
|
|
"entropy": 6.458343839645385,
|
|
"epoch": 3.5259778479319386,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037989745959744037,
|
|
"loss": 5.9826,
|
|
"mean_token_accuracy": 0.1549224264919758,
|
|
"num_tokens": 71339783.0,
|
|
"step": 32950
|
|
},
|
|
{
|
|
"entropy": 6.484084701538086,
|
|
"epoch": 3.5265129220397027,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037986363403976875,
|
|
"loss": 6.0032,
|
|
"mean_token_accuracy": 0.15459722131490708,
|
|
"num_tokens": 71349561.0,
|
|
"step": 32955
|
|
},
|
|
{
|
|
"entropy": 6.435168504714966,
|
|
"epoch": 3.5270479961474663,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003798298054541744,
|
|
"loss": 5.9376,
|
|
"mean_token_accuracy": 0.15985777974128723,
|
|
"num_tokens": 71360037.0,
|
|
"step": 32960
|
|
},
|
|
{
|
|
"entropy": 6.349410772323608,
|
|
"epoch": 3.5275830702552304,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003797959738416343,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.16688323020935059,
|
|
"num_tokens": 71371484.0,
|
|
"step": 32965
|
|
},
|
|
{
|
|
"entropy": 6.410812520980835,
|
|
"epoch": 3.5281181443629945,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000379762139203125,
|
|
"loss": 6.0404,
|
|
"mean_token_accuracy": 0.1568843275308609,
|
|
"num_tokens": 71382818.0,
|
|
"step": 32970
|
|
},
|
|
{
|
|
"entropy": 6.483251571655273,
|
|
"epoch": 3.528653218470758,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003797283015396238,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.1597086548805237,
|
|
"num_tokens": 71393938.0,
|
|
"step": 32975
|
|
},
|
|
{
|
|
"entropy": 6.484730339050293,
|
|
"epoch": 3.5291882925785223,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037969446085210753,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.1632386863231659,
|
|
"num_tokens": 71403678.0,
|
|
"step": 32980
|
|
},
|
|
{
|
|
"entropy": 6.409056568145752,
|
|
"epoch": 3.529723366686286,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037966061714155344,
|
|
"loss": 5.9911,
|
|
"mean_token_accuracy": 0.1555747479200363,
|
|
"num_tokens": 71414877.0,
|
|
"step": 32985
|
|
},
|
|
{
|
|
"entropy": 6.388189697265625,
|
|
"epoch": 3.53025844079405,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00037962677040893867,
|
|
"loss": 5.9408,
|
|
"mean_token_accuracy": 0.15760304033756256,
|
|
"num_tokens": 71424823.0,
|
|
"step": 32990
|
|
},
|
|
{
|
|
"entropy": 6.428362703323364,
|
|
"epoch": 3.5307935149018137,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003795929206552407,
|
|
"loss": 5.9835,
|
|
"mean_token_accuracy": 0.1544021636247635,
|
|
"num_tokens": 71434664.0,
|
|
"step": 32995
|
|
},
|
|
{
|
|
"entropy": 6.3940380096435545,
|
|
"epoch": 3.531328589009578,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003795590678814368,
|
|
"loss": 5.9418,
|
|
"mean_token_accuracy": 0.16156888902187347,
|
|
"num_tokens": 71444556.0,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"epoch": 3.531328589009578,
|
|
"eval_entropy": 6.2142082968812105,
|
|
"eval_loss": 6.120935440063477,
|
|
"eval_mean_token_accuracy": 0.1582693143815525,
|
|
"eval_num_tokens": 71444556.0,
|
|
"eval_runtime": 22.8476,
|
|
"eval_samples_per_second": 1298.996,
|
|
"eval_steps_per_second": 162.38,
|
|
"step": 33000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 93440,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.05028476694272e+17,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|