99ae1ba0c6
Model: fpadovani/heb-hebr-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3210444646583552,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 9543356688384000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|