41f37d9d54
Model: fpadovani/ind-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2334176230305388,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.428324794769287,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.0654,
|
|
"mean_token_accuracy": 0.09049141183495521,
|
|
"num_tokens": 8755.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.406369161605835,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.9787,
|
|
"mean_token_accuracy": 0.09639345631003379,
|
|
"num_tokens": 17641.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.410000467300415,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.9408,
|
|
"mean_token_accuracy": 0.09870931878685951,
|
|
"num_tokens": 26293.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.406883716583252,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.0309,
|
|
"mean_token_accuracy": 0.08720004037022591,
|
|
"num_tokens": 35627.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.423058557510376,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.8901,
|
|
"mean_token_accuracy": 0.09724865928292274,
|
|
"num_tokens": 43861.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.4552548885345455,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.0147,
|
|
"mean_token_accuracy": 0.0973876304924488,
|
|
"num_tokens": 52816.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.438412618637085,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.9921,
|
|
"mean_token_accuracy": 0.09515059664845467,
|
|
"num_tokens": 61370.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.441454601287842,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.9487,
|
|
"mean_token_accuracy": 0.10167206972837448,
|
|
"num_tokens": 69444.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.507920455932617,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.9887,
|
|
"mean_token_accuracy": 0.09499939382076264,
|
|
"num_tokens": 77892.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.525271081924439,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.9882,
|
|
"mean_token_accuracy": 0.10243152678012848,
|
|
"num_tokens": 86154.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.477654314041137,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.0953,
|
|
"mean_token_accuracy": 0.09470769762992859,
|
|
"num_tokens": 95589.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.454274988174438,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.0717,
|
|
"mean_token_accuracy": 0.09005340784788132,
|
|
"num_tokens": 105268.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.460178375244141,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.9674,
|
|
"mean_token_accuracy": 0.10172970369458198,
|
|
"num_tokens": 113347.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.5014667987823485,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.9797,
|
|
"mean_token_accuracy": 0.0966665655374527,
|
|
"num_tokens": 121235.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.449297571182251,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.9313,
|
|
"mean_token_accuracy": 0.1067626990377903,
|
|
"num_tokens": 129529.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.443627548217774,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.9599,
|
|
"mean_token_accuracy": 0.09893447831273079,
|
|
"num_tokens": 137918.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.364729690551758,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.8697,
|
|
"mean_token_accuracy": 0.10501775741577149,
|
|
"num_tokens": 146445.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.389777565002442,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.054,
|
|
"mean_token_accuracy": 0.09568696841597557,
|
|
"num_tokens": 155904.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.473219966888427,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.0199,
|
|
"mean_token_accuracy": 0.1002066396176815,
|
|
"num_tokens": 164436.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.500016736984253,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.9907,
|
|
"mean_token_accuracy": 0.0998419389128685,
|
|
"num_tokens": 172985.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.358818578720093,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.8944,
|
|
"mean_token_accuracy": 0.09846496134996414,
|
|
"num_tokens": 182084.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.398036003112793,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.9349,
|
|
"mean_token_accuracy": 0.10587768033146858,
|
|
"num_tokens": 190742.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.430330848693847,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.009,
|
|
"mean_token_accuracy": 0.10080742314457894,
|
|
"num_tokens": 199600.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.456536912918091,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.9662,
|
|
"mean_token_accuracy": 0.10005040019750595,
|
|
"num_tokens": 207883.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.459503984451294,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.0087,
|
|
"mean_token_accuracy": 0.09876146614551544,
|
|
"num_tokens": 216216.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.439739942550659,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.998,
|
|
"mean_token_accuracy": 0.10104034319519997,
|
|
"num_tokens": 225250.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.446091413497925,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.9821,
|
|
"mean_token_accuracy": 0.0969055637717247,
|
|
"num_tokens": 233748.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.454025363922119,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.0076,
|
|
"mean_token_accuracy": 0.09575914740562438,
|
|
"num_tokens": 242629.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.417604207992554,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.9827,
|
|
"mean_token_accuracy": 0.0998191438615322,
|
|
"num_tokens": 251458.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.431661653518677,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.946,
|
|
"mean_token_accuracy": 0.10091756880283356,
|
|
"num_tokens": 260557.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.441375064849853,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.0783,
|
|
"mean_token_accuracy": 0.09568855166435242,
|
|
"num_tokens": 269262.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.405449151992798,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.9389,
|
|
"mean_token_accuracy": 0.10365158095955848,
|
|
"num_tokens": 277804.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.441110897064209,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.9126,
|
|
"mean_token_accuracy": 0.10729183256626129,
|
|
"num_tokens": 287450.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.436047601699829,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.9786,
|
|
"mean_token_accuracy": 0.09779882282018662,
|
|
"num_tokens": 296497.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.377359676361084,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.8905,
|
|
"mean_token_accuracy": 0.10251178741455078,
|
|
"num_tokens": 305414.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.3786688327789305,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.9482,
|
|
"mean_token_accuracy": 0.10084712728857995,
|
|
"num_tokens": 313639.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.403275775909424,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.9637,
|
|
"mean_token_accuracy": 0.10111333504319191,
|
|
"num_tokens": 322855.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.512465000152588,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.1052,
|
|
"mean_token_accuracy": 0.09858241751790046,
|
|
"num_tokens": 332071.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.459011697769165,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.8957,
|
|
"mean_token_accuracy": 0.1045821987092495,
|
|
"num_tokens": 339990.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.3208598613739015,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.9542,
|
|
"mean_token_accuracy": 0.1042078159749508,
|
|
"num_tokens": 348581.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.4775693893432615,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.9543,
|
|
"mean_token_accuracy": 0.10210119113326073,
|
|
"num_tokens": 357032.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.342398071289063,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.9412,
|
|
"mean_token_accuracy": 0.09677820205688477,
|
|
"num_tokens": 366562.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.483612537384033,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.9321,
|
|
"mean_token_accuracy": 0.10381355360150338,
|
|
"num_tokens": 374555.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.41501030921936,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.9808,
|
|
"mean_token_accuracy": 0.09787384644150735,
|
|
"num_tokens": 383583.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.477314519882202,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.0253,
|
|
"mean_token_accuracy": 0.09879604578018189,
|
|
"num_tokens": 392932.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.3631621360778805,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.8465,
|
|
"mean_token_accuracy": 0.10572261735796928,
|
|
"num_tokens": 401653.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.390638160705566,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.9697,
|
|
"mean_token_accuracy": 0.1092008151113987,
|
|
"num_tokens": 410432.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.437095785140992,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.9627,
|
|
"mean_token_accuracy": 0.09653985649347305,
|
|
"num_tokens": 419380.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.364046430587768,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.8292,
|
|
"mean_token_accuracy": 0.10461175367236138,
|
|
"num_tokens": 427682.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.408738136291504,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.9587,
|
|
"mean_token_accuracy": 0.09456864520907401,
|
|
"num_tokens": 437708.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.433396196365356,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.9371,
|
|
"mean_token_accuracy": 0.09942449256777763,
|
|
"num_tokens": 446480.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.379309272766113,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.9721,
|
|
"mean_token_accuracy": 0.09638917818665504,
|
|
"num_tokens": 455273.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.356784772872925,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.883,
|
|
"mean_token_accuracy": 0.10503410249948501,
|
|
"num_tokens": 464306.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.388022518157959,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.8831,
|
|
"mean_token_accuracy": 0.10173421129584312,
|
|
"num_tokens": 472812.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.331966209411621,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.8727,
|
|
"mean_token_accuracy": 0.10593024790287017,
|
|
"num_tokens": 481326.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.374731874465942,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.8428,
|
|
"mean_token_accuracy": 0.10759447142481804,
|
|
"num_tokens": 489147.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.36668381690979,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.8504,
|
|
"mean_token_accuracy": 0.10656936541199684,
|
|
"num_tokens": 497455.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.356879997253418,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.758,
|
|
"mean_token_accuracy": 0.10305927395820617,
|
|
"num_tokens": 506735.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.270456027984619,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.8849,
|
|
"mean_token_accuracy": 0.09658203423023223,
|
|
"num_tokens": 515976.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.3423985004425045,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.866,
|
|
"mean_token_accuracy": 0.10728994905948638,
|
|
"num_tokens": 524986.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.408446359634399,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.8928,
|
|
"mean_token_accuracy": 0.110896135866642,
|
|
"num_tokens": 533146.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.319546413421631,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.785,
|
|
"mean_token_accuracy": 0.1116275131702423,
|
|
"num_tokens": 541704.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.265841770172119,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.7781,
|
|
"mean_token_accuracy": 0.10793708562850952,
|
|
"num_tokens": 550088.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.317618799209595,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.7721,
|
|
"mean_token_accuracy": 0.11174670755863189,
|
|
"num_tokens": 558763.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.293882560729981,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8912,
|
|
"mean_token_accuracy": 0.10175719037652016,
|
|
"num_tokens": 567538.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.340778779983521,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.8854,
|
|
"mean_token_accuracy": 0.09728848040103913,
|
|
"num_tokens": 577626.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.330549144744873,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8596,
|
|
"mean_token_accuracy": 0.096848464012146,
|
|
"num_tokens": 587163.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.255002021789551,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8158,
|
|
"mean_token_accuracy": 0.10388773456215858,
|
|
"num_tokens": 595896.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.4087928295135494,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8486,
|
|
"mean_token_accuracy": 0.10652071833610535,
|
|
"num_tokens": 603815.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.324870347976685,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.8768,
|
|
"mean_token_accuracy": 0.10469710528850555,
|
|
"num_tokens": 612208.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.263567209243774,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.836,
|
|
"mean_token_accuracy": 0.10391956865787506,
|
|
"num_tokens": 621840.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.413131141662598,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8576,
|
|
"mean_token_accuracy": 0.10285800844430923,
|
|
"num_tokens": 630770.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.226842975616455,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8735,
|
|
"mean_token_accuracy": 0.10087347999215127,
|
|
"num_tokens": 640313.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.4696742534637455,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.8818,
|
|
"mean_token_accuracy": 0.10657392218708991,
|
|
"num_tokens": 648594.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.3582908630371096,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.8691,
|
|
"mean_token_accuracy": 0.11030346155166626,
|
|
"num_tokens": 656478.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.226627206802368,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8622,
|
|
"mean_token_accuracy": 0.10462825298309326,
|
|
"num_tokens": 665405.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.430356884002686,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8824,
|
|
"mean_token_accuracy": 0.10508352369070054,
|
|
"num_tokens": 674301.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.297737455368042,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9,
|
|
"mean_token_accuracy": 0.10454680025577545,
|
|
"num_tokens": 683159.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.246564197540283,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7087,
|
|
"mean_token_accuracy": 0.11614901497960091,
|
|
"num_tokens": 690992.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.255606651306152,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8127,
|
|
"mean_token_accuracy": 0.10583920776844025,
|
|
"num_tokens": 699934.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.349058151245117,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8701,
|
|
"mean_token_accuracy": 0.10579104423522949,
|
|
"num_tokens": 708844.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.31098198890686,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9175,
|
|
"mean_token_accuracy": 0.10112065151333809,
|
|
"num_tokens": 718148.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.361715412139892,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.8723,
|
|
"mean_token_accuracy": 0.09706154093146324,
|
|
"num_tokens": 726859.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.335133504867554,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8699,
|
|
"mean_token_accuracy": 0.10610849931836128,
|
|
"num_tokens": 735045.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.167201137542724,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7586,
|
|
"mean_token_accuracy": 0.10604033321142196,
|
|
"num_tokens": 743538.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.356954431533813,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8011,
|
|
"mean_token_accuracy": 0.10508049800992011,
|
|
"num_tokens": 752518.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.231763410568237,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8318,
|
|
"mean_token_accuracy": 0.1046580545604229,
|
|
"num_tokens": 760354.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.280563879013061,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.8757,
|
|
"mean_token_accuracy": 0.10113996267318726,
|
|
"num_tokens": 769522.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.253572177886963,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7992,
|
|
"mean_token_accuracy": 0.11093137413263321,
|
|
"num_tokens": 778548.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.248162889480591,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8203,
|
|
"mean_token_accuracy": 0.10633306801319123,
|
|
"num_tokens": 787666.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.291629838943481,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.761,
|
|
"mean_token_accuracy": 0.11031401231884956,
|
|
"num_tokens": 796550.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.261716270446778,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8326,
|
|
"mean_token_accuracy": 0.10464341267943382,
|
|
"num_tokens": 804549.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.214675569534302,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.796,
|
|
"mean_token_accuracy": 0.10827421844005584,
|
|
"num_tokens": 813328.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.345154762268066,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8591,
|
|
"mean_token_accuracy": 0.10106633976101875,
|
|
"num_tokens": 821733.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.146458864212036,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.788,
|
|
"mean_token_accuracy": 0.10371901914477348,
|
|
"num_tokens": 830243.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.294699192047119,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.7664,
|
|
"mean_token_accuracy": 0.10468717440962791,
|
|
"num_tokens": 839059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.164042663574219,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6576,
|
|
"mean_token_accuracy": 0.11653261855244637,
|
|
"num_tokens": 846932.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.279664421081543,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.8641,
|
|
"mean_token_accuracy": 0.09954719170928002,
|
|
"num_tokens": 855333.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.079974603652954,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6271,
|
|
"mean_token_accuracy": 0.11037061735987663,
|
|
"num_tokens": 863571.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.1013068675994875,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7244,
|
|
"mean_token_accuracy": 0.11674270778894424,
|
|
"num_tokens": 872145.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.247890615463257,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7569,
|
|
"mean_token_accuracy": 0.1087301380932331,
|
|
"num_tokens": 880634.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.207820320129395,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.7062,
|
|
"mean_token_accuracy": 0.10853548645973206,
|
|
"num_tokens": 889178.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.169516324996948,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7134,
|
|
"mean_token_accuracy": 0.10897102132439614,
|
|
"num_tokens": 898255.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.152969646453857,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.774,
|
|
"mean_token_accuracy": 0.10289896130561829,
|
|
"num_tokens": 907369.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.14563512802124,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6889,
|
|
"mean_token_accuracy": 0.10718784034252167,
|
|
"num_tokens": 915946.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.151228046417236,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7328,
|
|
"mean_token_accuracy": 0.10271384865045548,
|
|
"num_tokens": 925579.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.176724624633789,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.7277,
|
|
"mean_token_accuracy": 0.10272877439856529,
|
|
"num_tokens": 934732.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.142701244354248,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.8021,
|
|
"mean_token_accuracy": 0.10387543737888336,
|
|
"num_tokens": 943371.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.137252473831177,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6423,
|
|
"mean_token_accuracy": 0.11301440745592117,
|
|
"num_tokens": 951977.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.172152137756347,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.6448,
|
|
"mean_token_accuracy": 0.11049823835492134,
|
|
"num_tokens": 960474.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.159184741973877,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.754,
|
|
"mean_token_accuracy": 0.10716015249490737,
|
|
"num_tokens": 969823.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.191059017181397,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.682,
|
|
"mean_token_accuracy": 0.12077577039599419,
|
|
"num_tokens": 977417.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.131459283828735,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6929,
|
|
"mean_token_accuracy": 0.11818830072879791,
|
|
"num_tokens": 985519.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.157332468032837,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.6985,
|
|
"mean_token_accuracy": 0.11225624307990074,
|
|
"num_tokens": 994136.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.024613523483277,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6678,
|
|
"mean_token_accuracy": 0.11105563789606095,
|
|
"num_tokens": 1002896.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.242383337020874,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.7489,
|
|
"mean_token_accuracy": 0.11493279933929443,
|
|
"num_tokens": 1011032.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.015460014343262,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7204,
|
|
"mean_token_accuracy": 0.10362800061702729,
|
|
"num_tokens": 1019901.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.18277530670166,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.7207,
|
|
"mean_token_accuracy": 0.10517120659351349,
|
|
"num_tokens": 1029049.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.049787425994873,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6798,
|
|
"mean_token_accuracy": 0.1185940608382225,
|
|
"num_tokens": 1037580.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.167644882202149,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.7261,
|
|
"mean_token_accuracy": 0.1120360367000103,
|
|
"num_tokens": 1045804.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.098359155654907,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.694,
|
|
"mean_token_accuracy": 0.10400344282388688,
|
|
"num_tokens": 1054719.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.160435199737549,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6834,
|
|
"mean_token_accuracy": 0.11288492232561112,
|
|
"num_tokens": 1063373.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.067417621612549,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6745,
|
|
"mean_token_accuracy": 0.1108371913433075,
|
|
"num_tokens": 1073021.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.10958251953125,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.7372,
|
|
"mean_token_accuracy": 0.10155223831534385,
|
|
"num_tokens": 1081547.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.040739250183106,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.7017,
|
|
"mean_token_accuracy": 0.10570611953735351,
|
|
"num_tokens": 1090695.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.087480449676514,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5995,
|
|
"mean_token_accuracy": 0.11334518268704415,
|
|
"num_tokens": 1099563.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.126954460144043,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.6643,
|
|
"mean_token_accuracy": 0.10861440300941468,
|
|
"num_tokens": 1109021.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.063493824005127,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6672,
|
|
"mean_token_accuracy": 0.11145636141300201,
|
|
"num_tokens": 1118281.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.050823497772217,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.7071,
|
|
"mean_token_accuracy": 0.10184085294604302,
|
|
"num_tokens": 1127513.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.994142723083496,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.5873,
|
|
"mean_token_accuracy": 0.113088721036911,
|
|
"num_tokens": 1136140.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.076479101181031,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.6142,
|
|
"mean_token_accuracy": 0.10685904398560524,
|
|
"num_tokens": 1144297.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.086294746398925,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.6877,
|
|
"mean_token_accuracy": 0.1043604202568531,
|
|
"num_tokens": 1153639.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.073908519744873,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.6662,
|
|
"mean_token_accuracy": 0.10644880160689354,
|
|
"num_tokens": 1162825.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.004607772827148,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6953,
|
|
"mean_token_accuracy": 0.11124756038188935,
|
|
"num_tokens": 1171887.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.069401454925537,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6135,
|
|
"mean_token_accuracy": 0.11303046569228173,
|
|
"num_tokens": 1179963.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.96059250831604,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5779,
|
|
"mean_token_accuracy": 0.11756718456745148,
|
|
"num_tokens": 1188408.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.045384645462036,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.6249,
|
|
"mean_token_accuracy": 0.11092553362250328,
|
|
"num_tokens": 1197751.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.961059188842773,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6564,
|
|
"mean_token_accuracy": 0.11087723523378372,
|
|
"num_tokens": 1207101.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.06245789527893,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.6611,
|
|
"mean_token_accuracy": 0.10940892472863198,
|
|
"num_tokens": 1216395.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.076578807830811,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.6477,
|
|
"mean_token_accuracy": 0.1117068886756897,
|
|
"num_tokens": 1225496.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.017858028411865,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.7116,
|
|
"mean_token_accuracy": 0.11090820804238319,
|
|
"num_tokens": 1233934.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.977232789993286,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5591,
|
|
"mean_token_accuracy": 0.1176533691585064,
|
|
"num_tokens": 1242165.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.053106498718262,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.6346,
|
|
"mean_token_accuracy": 0.11234478205442429,
|
|
"num_tokens": 1250021.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.054070568084716,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.6627,
|
|
"mean_token_accuracy": 0.10676235780119896,
|
|
"num_tokens": 1258397.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.966783428192139,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.6435,
|
|
"mean_token_accuracy": 0.1090509571135044,
|
|
"num_tokens": 1266764.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.071456336975098,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.6525,
|
|
"mean_token_accuracy": 0.10880729258060455,
|
|
"num_tokens": 1275643.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.989516830444336,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.6201,
|
|
"mean_token_accuracy": 0.11093898415565491,
|
|
"num_tokens": 1284379.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.985952568054199,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4795,
|
|
"mean_token_accuracy": 0.11814915612339974,
|
|
"num_tokens": 1293115.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.051576614379883,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.682,
|
|
"mean_token_accuracy": 0.10519764646887779,
|
|
"num_tokens": 1301583.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.9952661991119385,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5803,
|
|
"mean_token_accuracy": 0.11081231012940407,
|
|
"num_tokens": 1310721.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.042070531845093,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.7291,
|
|
"mean_token_accuracy": 0.10293859988451004,
|
|
"num_tokens": 1319056.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.974556493759155,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.6182,
|
|
"mean_token_accuracy": 0.1109778843820095,
|
|
"num_tokens": 1327259.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.920253753662109,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.11307926774024964,
|
|
"num_tokens": 1335906.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.978034830093383,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5646,
|
|
"mean_token_accuracy": 0.10813911706209182,
|
|
"num_tokens": 1344743.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.963363122940064,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5806,
|
|
"mean_token_accuracy": 0.1119392916560173,
|
|
"num_tokens": 1353211.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.029351425170899,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6888,
|
|
"mean_token_accuracy": 0.10860950574278831,
|
|
"num_tokens": 1361849.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.0644081115722654,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.6819,
|
|
"mean_token_accuracy": 0.11109407320618629,
|
|
"num_tokens": 1369804.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.8550738334655765,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.4614,
|
|
"mean_token_accuracy": 0.11694267019629478,
|
|
"num_tokens": 1378478.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.972127914428711,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5706,
|
|
"mean_token_accuracy": 0.1196007214486599,
|
|
"num_tokens": 1387225.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.917468309402466,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.11665247678756714,
|
|
"num_tokens": 1395338.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.90943489074707,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.11467550322413445,
|
|
"num_tokens": 1403794.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.851684522628784,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.594,
|
|
"mean_token_accuracy": 0.10971078649163246,
|
|
"num_tokens": 1412522.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.944258499145508,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.586,
|
|
"mean_token_accuracy": 0.11532295569777488,
|
|
"num_tokens": 1421347.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.928653335571289,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5611,
|
|
"mean_token_accuracy": 0.11696547418832778,
|
|
"num_tokens": 1429788.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.896436071395874,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5596,
|
|
"mean_token_accuracy": 0.11556609123945236,
|
|
"num_tokens": 1437442.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.894798803329468,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.5008,
|
|
"mean_token_accuracy": 0.11221573501825333,
|
|
"num_tokens": 1445604.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.868392038345337,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.5733,
|
|
"mean_token_accuracy": 0.11458783373236656,
|
|
"num_tokens": 1454342.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.891533136367798,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.5434,
|
|
"mean_token_accuracy": 0.11737344339489937,
|
|
"num_tokens": 1463189.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.914099884033203,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.6141,
|
|
"mean_token_accuracy": 0.10967839807271958,
|
|
"num_tokens": 1471608.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.9978296756744385,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.6144,
|
|
"mean_token_accuracy": 0.1100444920361042,
|
|
"num_tokens": 1480452.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.94025354385376,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.5336,
|
|
"mean_token_accuracy": 0.11354602947831154,
|
|
"num_tokens": 1489118.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.8302192211151125,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.535,
|
|
"mean_token_accuracy": 0.10949739366769791,
|
|
"num_tokens": 1498961.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.9123735427856445,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.5356,
|
|
"mean_token_accuracy": 0.11317324861884118,
|
|
"num_tokens": 1506772.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.865458965301514,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.4228,
|
|
"mean_token_accuracy": 0.12698905244469644,
|
|
"num_tokens": 1515095.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.808365058898926,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4697,
|
|
"mean_token_accuracy": 0.12296628281474113,
|
|
"num_tokens": 1523477.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.824631023406982,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.5022,
|
|
"mean_token_accuracy": 0.11501481533050537,
|
|
"num_tokens": 1531786.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.805560159683227,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.5989,
|
|
"mean_token_accuracy": 0.10919139832258225,
|
|
"num_tokens": 1540737.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.883869266510009,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4469,
|
|
"mean_token_accuracy": 0.11882291138172149,
|
|
"num_tokens": 1548923.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.784322309494018,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4067,
|
|
"mean_token_accuracy": 0.12390651702880859,
|
|
"num_tokens": 1557043.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.771895265579223,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.4486,
|
|
"mean_token_accuracy": 0.1224091038107872,
|
|
"num_tokens": 1564994.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.809636068344116,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4563,
|
|
"mean_token_accuracy": 0.1136368915438652,
|
|
"num_tokens": 1573859.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.830642652511597,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.429,
|
|
"mean_token_accuracy": 0.11435260772705078,
|
|
"num_tokens": 1581947.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.772935581207276,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4005,
|
|
"mean_token_accuracy": 0.11757316365838051,
|
|
"num_tokens": 1589971.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.689200162887573,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3619,
|
|
"mean_token_accuracy": 0.11918411031365395,
|
|
"num_tokens": 1598612.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.844861602783203,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.5099,
|
|
"mean_token_accuracy": 0.11082213446497917,
|
|
"num_tokens": 1607378.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.754356575012207,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.5073,
|
|
"mean_token_accuracy": 0.11739620044827462,
|
|
"num_tokens": 1615987.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.726682090759278,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3035,
|
|
"mean_token_accuracy": 0.12486169338226319,
|
|
"num_tokens": 1625366.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.736809110641479,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4848,
|
|
"mean_token_accuracy": 0.11880016550421715,
|
|
"num_tokens": 1633020.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.754602718353271,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3883,
|
|
"mean_token_accuracy": 0.11748389154672623,
|
|
"num_tokens": 1641518.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.705056047439575,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.4726,
|
|
"mean_token_accuracy": 0.11781010702252388,
|
|
"num_tokens": 1650472.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.785799169540406,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.507,
|
|
"mean_token_accuracy": 0.11363615766167641,
|
|
"num_tokens": 1659037.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.829026794433593,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.5735,
|
|
"mean_token_accuracy": 0.11651240065693855,
|
|
"num_tokens": 1667897.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.732403898239136,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.4198,
|
|
"mean_token_accuracy": 0.11139412000775337,
|
|
"num_tokens": 1676535.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.8594677448272705,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4466,
|
|
"mean_token_accuracy": 0.11887699663639069,
|
|
"num_tokens": 1684415.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.723340702056885,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.12453912273049354,
|
|
"num_tokens": 1692443.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.670280694961548,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4114,
|
|
"mean_token_accuracy": 0.12035818472504616,
|
|
"num_tokens": 1700814.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.637305498123169,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2552,
|
|
"mean_token_accuracy": 0.12497311756014824,
|
|
"num_tokens": 1709591.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.758705091476441,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.491,
|
|
"mean_token_accuracy": 0.11199909374117852,
|
|
"num_tokens": 1718951.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.755342149734497,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.4487,
|
|
"mean_token_accuracy": 0.11627254337072372,
|
|
"num_tokens": 1727481.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.776053047180175,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.4373,
|
|
"mean_token_accuracy": 0.1180419959127903,
|
|
"num_tokens": 1736985.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.759429550170898,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.5256,
|
|
"mean_token_accuracy": 0.1146937295794487,
|
|
"num_tokens": 1745470.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.769218778610229,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.4193,
|
|
"mean_token_accuracy": 0.11607462614774704,
|
|
"num_tokens": 1754185.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.672504806518555,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.4365,
|
|
"mean_token_accuracy": 0.11394271180033684,
|
|
"num_tokens": 1762100.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.805412864685058,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.4533,
|
|
"mean_token_accuracy": 0.11515071243047714,
|
|
"num_tokens": 1771070.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.658144235610962,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.4549,
|
|
"mean_token_accuracy": 0.11719758063554764,
|
|
"num_tokens": 1780085.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.757973384857178,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.4477,
|
|
"mean_token_accuracy": 0.12243591025471687,
|
|
"num_tokens": 1789316.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.678041696548462,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.3704,
|
|
"mean_token_accuracy": 0.1213125005364418,
|
|
"num_tokens": 1797975.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.65592589378357,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.4589,
|
|
"mean_token_accuracy": 0.12353531643748283,
|
|
"num_tokens": 1806129.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.8409473419189455,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.4574,
|
|
"mean_token_accuracy": 0.11680945232510567,
|
|
"num_tokens": 1813956.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.737816333770752,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.481,
|
|
"mean_token_accuracy": 0.11468739807605743,
|
|
"num_tokens": 1822572.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.6663189888000485,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.11563698872923851,
|
|
"num_tokens": 1831870.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.598942708969116,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.4276,
|
|
"mean_token_accuracy": 0.11558841541409492,
|
|
"num_tokens": 1840414.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.852775192260742,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.4426,
|
|
"mean_token_accuracy": 0.11738709583878518,
|
|
"num_tokens": 1850385.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.492261695861816,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.12343356981873513,
|
|
"num_tokens": 1858479.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.708926773071289,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.4097,
|
|
"mean_token_accuracy": 0.11067359670996665,
|
|
"num_tokens": 1867357.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.690218782424926,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.3768,
|
|
"mean_token_accuracy": 0.1146676443517208,
|
|
"num_tokens": 1876211.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.6100105285644535,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.11257534921169281,
|
|
"num_tokens": 1884301.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.706263875961303,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.461,
|
|
"mean_token_accuracy": 0.1196840226650238,
|
|
"num_tokens": 1893191.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.564361143112182,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.3293,
|
|
"mean_token_accuracy": 0.11676682159304619,
|
|
"num_tokens": 1901434.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.664592123031616,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.1269494652748108,
|
|
"num_tokens": 1910054.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.6648547649383545,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.4633,
|
|
"mean_token_accuracy": 0.11476121544837951,
|
|
"num_tokens": 1918607.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.6421819686889645,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.3989,
|
|
"mean_token_accuracy": 0.11885848641395569,
|
|
"num_tokens": 1927610.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.606335258483886,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.3591,
|
|
"mean_token_accuracy": 0.11808456256985664,
|
|
"num_tokens": 1936174.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.620585012435913,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.285,
|
|
"mean_token_accuracy": 0.12242377102375031,
|
|
"num_tokens": 1944228.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.607644987106323,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.3877,
|
|
"mean_token_accuracy": 0.12339339479804039,
|
|
"num_tokens": 1953144.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.704639625549317,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.4318,
|
|
"mean_token_accuracy": 0.11419345438480377,
|
|
"num_tokens": 1961947.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.676687431335449,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.11595526710152626,
|
|
"num_tokens": 1970674.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.671134376525879,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.3788,
|
|
"mean_token_accuracy": 0.12137411832809449,
|
|
"num_tokens": 1979173.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.589903163909912,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.3583,
|
|
"mean_token_accuracy": 0.12250440344214439,
|
|
"num_tokens": 1988134.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.666301631927491,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.12049696892499924,
|
|
"num_tokens": 1996977.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.652774333953857,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.3871,
|
|
"mean_token_accuracy": 0.11820772588253022,
|
|
"num_tokens": 2005946.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.566985940933227,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.2172,
|
|
"mean_token_accuracy": 0.12243169024586678,
|
|
"num_tokens": 2014882.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.548052835464477,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.407,
|
|
"mean_token_accuracy": 0.11777823343873024,
|
|
"num_tokens": 2024858.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.58183331489563,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.3198,
|
|
"mean_token_accuracy": 0.12247655168175697,
|
|
"num_tokens": 2034072.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.619194364547729,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.1233485259115696,
|
|
"num_tokens": 2042649.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.5773601055145265,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.12649165764451026,
|
|
"num_tokens": 2050866.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.624700975418091,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.356,
|
|
"mean_token_accuracy": 0.12287835404276848,
|
|
"num_tokens": 2058914.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.566097354888916,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.287,
|
|
"mean_token_accuracy": 0.12197296395897865,
|
|
"num_tokens": 2068098.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.562694406509399,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.11417963430285454,
|
|
"num_tokens": 2077299.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.573287296295166,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.3798,
|
|
"mean_token_accuracy": 0.11859698817133904,
|
|
"num_tokens": 2087868.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.565402412414551,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.3108,
|
|
"mean_token_accuracy": 0.1254733011126518,
|
|
"num_tokens": 2096553.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.652924728393555,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.2801,
|
|
"mean_token_accuracy": 0.1194481149315834,
|
|
"num_tokens": 2104809.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.454768133163452,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.2644,
|
|
"mean_token_accuracy": 0.12134657055139542,
|
|
"num_tokens": 2113869.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.491008758544922,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.11863267570734023,
|
|
"num_tokens": 2121749.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.488491821289062,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.3197,
|
|
"mean_token_accuracy": 0.11957874894142151,
|
|
"num_tokens": 2130828.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.629486036300659,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.2794,
|
|
"mean_token_accuracy": 0.12205140367150306,
|
|
"num_tokens": 2138928.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.551081609725952,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.12222919836640359,
|
|
"num_tokens": 2147643.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.581508445739746,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.2547,
|
|
"mean_token_accuracy": 0.12721101716160774,
|
|
"num_tokens": 2156766.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.509366512298584,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.3083,
|
|
"mean_token_accuracy": 0.12237787693738937,
|
|
"num_tokens": 2165517.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.485399150848389,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.1935,
|
|
"mean_token_accuracy": 0.1266528323292732,
|
|
"num_tokens": 2174812.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.535298681259155,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.3305,
|
|
"mean_token_accuracy": 0.11914158836007119,
|
|
"num_tokens": 2183968.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.618254613876343,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.3459,
|
|
"mean_token_accuracy": 0.12755375280976294,
|
|
"num_tokens": 2191947.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.528839731216431,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.1907,
|
|
"mean_token_accuracy": 0.1307717591524124,
|
|
"num_tokens": 2199951.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.479862356185913,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.3421,
|
|
"mean_token_accuracy": 0.12372912466526031,
|
|
"num_tokens": 2208714.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.498292541503906,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.2,
|
|
"mean_token_accuracy": 0.1264264166355133,
|
|
"num_tokens": 2217250.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.5420334815979,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.12835126966238022,
|
|
"num_tokens": 2225468.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.4549304962158205,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.1315177209675312,
|
|
"num_tokens": 2233893.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.566325521469116,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.2795,
|
|
"mean_token_accuracy": 0.12629038318991662,
|
|
"num_tokens": 2242487.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.4853943347930905,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.1073,
|
|
"mean_token_accuracy": 0.1271251358091831,
|
|
"num_tokens": 2250518.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.446168088912964,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.2792,
|
|
"mean_token_accuracy": 0.11826291009783745,
|
|
"num_tokens": 2259024.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.553367996215821,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.3272,
|
|
"mean_token_accuracy": 0.1139446422457695,
|
|
"num_tokens": 2267832.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.4859734058380125,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.3817,
|
|
"mean_token_accuracy": 0.1167535126209259,
|
|
"num_tokens": 2276834.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.623997735977173,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.3096,
|
|
"mean_token_accuracy": 0.12032428234815598,
|
|
"num_tokens": 2285736.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.567375421524048,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.256,
|
|
"mean_token_accuracy": 0.13201069533824922,
|
|
"num_tokens": 2294177.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.438686847686768,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.13524992465972902,
|
|
"num_tokens": 2302784.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.362113523483276,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.171,
|
|
"mean_token_accuracy": 0.12782380506396293,
|
|
"num_tokens": 2311650.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.510524940490723,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.2756,
|
|
"mean_token_accuracy": 0.12364537864923478,
|
|
"num_tokens": 2319828.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.539057922363281,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.2842,
|
|
"mean_token_accuracy": 0.12230362668633461,
|
|
"num_tokens": 2328636.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.401849460601807,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.17,
|
|
"mean_token_accuracy": 0.12805957421660424,
|
|
"num_tokens": 2336771.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.524014139175415,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.3125,
|
|
"mean_token_accuracy": 0.12446440905332565,
|
|
"num_tokens": 2346106.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.554375123977661,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.116956078261137,
|
|
"num_tokens": 2354943.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.330786418914795,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.2156,
|
|
"mean_token_accuracy": 0.12508122622966766,
|
|
"num_tokens": 2363699.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.5141215324401855,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.3486,
|
|
"mean_token_accuracy": 0.11765544191002845,
|
|
"num_tokens": 2373316.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.683814477920532,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.4201,
|
|
"mean_token_accuracy": 0.11839015111327171,
|
|
"num_tokens": 2381550.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.481244421005249,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.221,
|
|
"mean_token_accuracy": 0.12212294861674308,
|
|
"num_tokens": 2389546.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.468661642074585,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.1852,
|
|
"mean_token_accuracy": 0.1323728546500206,
|
|
"num_tokens": 2398852.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.469674444198608,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.2775,
|
|
"mean_token_accuracy": 0.11976648792624474,
|
|
"num_tokens": 2407815.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.445081806182861,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.12592858001589774,
|
|
"num_tokens": 2417300.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.435740280151367,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.2916,
|
|
"mean_token_accuracy": 0.1248296931385994,
|
|
"num_tokens": 2426257.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.594287014007568,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.12577738165855407,
|
|
"num_tokens": 2434595.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.599342203140258,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.3221,
|
|
"mean_token_accuracy": 0.12230012863874436,
|
|
"num_tokens": 2443945.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.375091934204102,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.1907,
|
|
"mean_token_accuracy": 0.12613629177212715,
|
|
"num_tokens": 2453141.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.551033687591553,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.2644,
|
|
"mean_token_accuracy": 0.12420548647642135,
|
|
"num_tokens": 2461873.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.461436748504639,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.2966,
|
|
"mean_token_accuracy": 0.12048030272126198,
|
|
"num_tokens": 2471238.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.48109073638916,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.1976,
|
|
"mean_token_accuracy": 0.12889449149370194,
|
|
"num_tokens": 2479412.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.289962291717529,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.0753,
|
|
"mean_token_accuracy": 0.12814749032258987,
|
|
"num_tokens": 2488150.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.453941392898559,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.2458,
|
|
"mean_token_accuracy": 0.1274418205022812,
|
|
"num_tokens": 2498103.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.403725814819336,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.12846592366695403,
|
|
"num_tokens": 2506211.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.322660779953003,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.1592,
|
|
"mean_token_accuracy": 0.12967515960335732,
|
|
"num_tokens": 2514743.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.377335548400879,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.12324637621641159,
|
|
"num_tokens": 2523824.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.491170978546142,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.2174,
|
|
"mean_token_accuracy": 0.12356971949338913,
|
|
"num_tokens": 2532360.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.422462749481201,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.13105847761034967,
|
|
"num_tokens": 2540547.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.408833074569702,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.12942414954304696,
|
|
"num_tokens": 2549193.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.430090045928955,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.12359017059206963,
|
|
"num_tokens": 2557553.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.530663251876831,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.12577586844563485,
|
|
"num_tokens": 2565945.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.482461261749267,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.1625,
|
|
"mean_token_accuracy": 0.12412880286574364,
|
|
"num_tokens": 2574364.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.351671361923218,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.1036,
|
|
"mean_token_accuracy": 0.1279638461768627,
|
|
"num_tokens": 2582825.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.4820616245269775,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.2311,
|
|
"mean_token_accuracy": 0.12474912479519844,
|
|
"num_tokens": 2591628.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.486547756195068,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.2322,
|
|
"mean_token_accuracy": 0.11734669506549836,
|
|
"num_tokens": 2600436.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.3622339248657225,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.1925,
|
|
"mean_token_accuracy": 0.12901659011840821,
|
|
"num_tokens": 2609709.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.497528409957885,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.12794017940759658,
|
|
"num_tokens": 2617992.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.297898578643799,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.12741497829556464,
|
|
"num_tokens": 2626706.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.547286319732666,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.13434533700346946,
|
|
"num_tokens": 2634642.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.450995445251465,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.12014995068311692,
|
|
"num_tokens": 2644160.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.299431896209716,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.1913,
|
|
"mean_token_accuracy": 0.12312416806817054,
|
|
"num_tokens": 2653390.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.493148279190064,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.1258779875934124,
|
|
"num_tokens": 2662561.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.428391170501709,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.1935,
|
|
"mean_token_accuracy": 0.12642016857862473,
|
|
"num_tokens": 2670694.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.3111365795135494,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.13140376582741736,
|
|
"num_tokens": 2679583.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.370851612091064,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.130515868216753,
|
|
"num_tokens": 2688429.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.420472621917725,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.1548,
|
|
"mean_token_accuracy": 0.12875235974788665,
|
|
"num_tokens": 2697134.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.406427812576294,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.2798,
|
|
"mean_token_accuracy": 0.1203388474881649,
|
|
"num_tokens": 2705641.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.430809783935547,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.2262,
|
|
"mean_token_accuracy": 0.13087129667401315,
|
|
"num_tokens": 2714977.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.429128837585449,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.0765,
|
|
"mean_token_accuracy": 0.1384890541434288,
|
|
"num_tokens": 2723120.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.230881023406982,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.13497595563530923,
|
|
"num_tokens": 2731964.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.525674676895141,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.1425,
|
|
"mean_token_accuracy": 0.12706299051642417,
|
|
"num_tokens": 2741537.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.336614084243775,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.2488,
|
|
"mean_token_accuracy": 0.1276876747608185,
|
|
"num_tokens": 2751522.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.4886940002441404,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.2514,
|
|
"mean_token_accuracy": 0.11896501258015632,
|
|
"num_tokens": 2761100.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.379914951324463,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.12824108004570006,
|
|
"num_tokens": 2769171.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.368760776519776,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.12826206013560296,
|
|
"num_tokens": 2778021.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.2863696098327635,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.0772,
|
|
"mean_token_accuracy": 0.1298437587916851,
|
|
"num_tokens": 2787206.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.341671276092529,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.1293750949203968,
|
|
"num_tokens": 2796051.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.3663938522338865,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.13239880800247192,
|
|
"num_tokens": 2804961.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.326526165008545,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.13350202292203903,
|
|
"num_tokens": 2813691.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.385087394714356,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.1812,
|
|
"mean_token_accuracy": 0.12938434183597564,
|
|
"num_tokens": 2822248.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.396917104721069,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.142,
|
|
"mean_token_accuracy": 0.130577003210783,
|
|
"num_tokens": 2830826.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.3590367317199705,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.1216,
|
|
"mean_token_accuracy": 0.12951069474220275,
|
|
"num_tokens": 2839766.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.207428693771362,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.0657,
|
|
"mean_token_accuracy": 0.13443321511149406,
|
|
"num_tokens": 2848728.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.306617021560669,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.13172278329730033,
|
|
"num_tokens": 2857221.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.388878870010376,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.1457,
|
|
"mean_token_accuracy": 0.13395920395851135,
|
|
"num_tokens": 2865314.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.261692237854004,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.0185,
|
|
"mean_token_accuracy": 0.13654017597436904,
|
|
"num_tokens": 2873654.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.265604686737061,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 5.9357,
|
|
"mean_token_accuracy": 0.14313312098383904,
|
|
"num_tokens": 2881604.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.309537696838379,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.1277,
|
|
"mean_token_accuracy": 0.12997377887368203,
|
|
"num_tokens": 2890427.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.385668992996216,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.0921,
|
|
"mean_token_accuracy": 0.13262823969125748,
|
|
"num_tokens": 2899206.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.25797815322876,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.13411636501550675,
|
|
"num_tokens": 2907738.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.371025228500367,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.2274,
|
|
"mean_token_accuracy": 0.12602662891149521,
|
|
"num_tokens": 2916881.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.40340576171875,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.1783,
|
|
"mean_token_accuracy": 0.12609613835811614,
|
|
"num_tokens": 2926467.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.337603616714477,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.1299,
|
|
"mean_token_accuracy": 0.13105945885181428,
|
|
"num_tokens": 2934671.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.33728141784668,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.12666159719228745,
|
|
"num_tokens": 2943925.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.37947564125061,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.1889,
|
|
"mean_token_accuracy": 0.1274726241827011,
|
|
"num_tokens": 2952118.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.279305553436279,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.1581,
|
|
"mean_token_accuracy": 0.12846080139279364,
|
|
"num_tokens": 2961110.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.348481130599976,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.13976106271147729,
|
|
"num_tokens": 2968877.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.393802261352539,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 6.1459,
|
|
"mean_token_accuracy": 0.12958939224481583,
|
|
"num_tokens": 2977346.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.370845556259155,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.12310019731521607,
|
|
"num_tokens": 2987494.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.3494658946990965,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.13097773119807243,
|
|
"num_tokens": 2996728.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.2700177192687985,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.1329,
|
|
"mean_token_accuracy": 0.12893041744828224,
|
|
"num_tokens": 3005810.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.3634881496429445,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.12823313996195793,
|
|
"num_tokens": 3014603.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.431996059417725,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.13290574923157691,
|
|
"num_tokens": 3023170.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.219868755340576,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 5.9015,
|
|
"mean_token_accuracy": 0.14494576007127763,
|
|
"num_tokens": 3030565.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.2956647872924805,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.1691,
|
|
"mean_token_accuracy": 0.13108205273747445,
|
|
"num_tokens": 3040124.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.294409704208374,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.0324,
|
|
"mean_token_accuracy": 0.13331486508250237,
|
|
"num_tokens": 3048458.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.263208246231079,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 6.006,
|
|
"mean_token_accuracy": 0.12804921418428422,
|
|
"num_tokens": 3057926.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.294978046417237,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.033,
|
|
"mean_token_accuracy": 0.13218592926859857,
|
|
"num_tokens": 3066683.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.193322563171387,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.12744091004133223,
|
|
"num_tokens": 3075117.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.409311723709107,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.1632,
|
|
"mean_token_accuracy": 0.12578216195106506,
|
|
"num_tokens": 3084399.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.222201776504517,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.13312947526574134,
|
|
"num_tokens": 3093030.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.30834550857544,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.13578457087278367,
|
|
"num_tokens": 3101670.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.144382953643799,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.13799581676721573,
|
|
"num_tokens": 3109703.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.229348421096802,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 5.9804,
|
|
"mean_token_accuracy": 0.1379885770380497,
|
|
"num_tokens": 3118388.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.2648790836334225,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 5.9672,
|
|
"mean_token_accuracy": 0.1371411792933941,
|
|
"num_tokens": 3126466.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.259693765640259,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.0299,
|
|
"mean_token_accuracy": 0.13593954741954803,
|
|
"num_tokens": 3135322.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.272290372848511,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.14133850261569023,
|
|
"num_tokens": 3144498.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.185325717926025,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.12976517975330354,
|
|
"num_tokens": 3153573.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.203995656967163,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 5.9301,
|
|
"mean_token_accuracy": 0.13893781676888467,
|
|
"num_tokens": 3161705.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.24528398513794,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 6.0915,
|
|
"mean_token_accuracy": 0.13699387311935424,
|
|
"num_tokens": 3170068.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.246503305435181,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.13167436718940734,
|
|
"num_tokens": 3178140.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.2965551853179935,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 6.0795,
|
|
"mean_token_accuracy": 0.13575641214847564,
|
|
"num_tokens": 3186518.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.261485242843628,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.0548,
|
|
"mean_token_accuracy": 0.13169616609811782,
|
|
"num_tokens": 3195246.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.323240137100219,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.13250553533434867,
|
|
"num_tokens": 3203946.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.248462677001953,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 6.0928,
|
|
"mean_token_accuracy": 0.13283114582300187,
|
|
"num_tokens": 3212208.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.229254961013794,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.0241,
|
|
"mean_token_accuracy": 0.13466759771108627,
|
|
"num_tokens": 3221572.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.36988377571106,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.12890521064400673,
|
|
"num_tokens": 3230898.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.229429626464844,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.1284354142844677,
|
|
"num_tokens": 3240524.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.201262140274048,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 5.8856,
|
|
"mean_token_accuracy": 0.13885571360588073,
|
|
"num_tokens": 3248864.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.266730690002442,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.068,
|
|
"mean_token_accuracy": 0.1342063754796982,
|
|
"num_tokens": 3256823.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.170843505859375,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.14102984592318535,
|
|
"num_tokens": 3265621.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.1978428840637205,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 5.9998,
|
|
"mean_token_accuracy": 0.1362139955163002,
|
|
"num_tokens": 3273515.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.338559913635254,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.13152379617094995,
|
|
"num_tokens": 3282283.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.185009860992432,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.13816771656274796,
|
|
"num_tokens": 3290792.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.146698713302612,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.1381203569471836,
|
|
"num_tokens": 3299430.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.161927223205566,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 5.9877,
|
|
"mean_token_accuracy": 0.14127052575349808,
|
|
"num_tokens": 3307949.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.291336107254028,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.13172024860978127,
|
|
"num_tokens": 3316900.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.205208778381348,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.1432355299592018,
|
|
"num_tokens": 3325656.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.190450620651245,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.198,
|
|
"mean_token_accuracy": 0.1225706160068512,
|
|
"num_tokens": 3334219.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.228388118743896,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 5.9451,
|
|
"mean_token_accuracy": 0.13421944826841353,
|
|
"num_tokens": 3343637.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.189314556121826,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 6.0871,
|
|
"mean_token_accuracy": 0.13039903715252876,
|
|
"num_tokens": 3352624.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.1881711959838865,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.14228348284959794,
|
|
"num_tokens": 3361394.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.3036641597747805,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.13427391052246093,
|
|
"num_tokens": 3369406.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.243283081054687,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.13894839733839034,
|
|
"num_tokens": 3377737.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.194996166229248,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.1303106352686882,
|
|
"num_tokens": 3385514.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.298865890502929,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 5.9586,
|
|
"mean_token_accuracy": 0.13934986293315887,
|
|
"num_tokens": 3394500.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.167548418045044,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.1368454597890377,
|
|
"num_tokens": 3403289.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.102401065826416,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.14984163641929626,
|
|
"num_tokens": 3410892.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.029754686355591,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 5.9761,
|
|
"mean_token_accuracy": 0.13527074232697486,
|
|
"num_tokens": 3420329.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.220583820343018,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.13858482763171195,
|
|
"num_tokens": 3429429.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.295728540420532,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 6.0824,
|
|
"mean_token_accuracy": 0.13455277010798455,
|
|
"num_tokens": 3438198.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.339246654510498,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.13310084342956544,
|
|
"num_tokens": 3447732.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.231119155883789,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 5.9915,
|
|
"mean_token_accuracy": 0.1366339311003685,
|
|
"num_tokens": 3456392.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.148554086685181,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.043,
|
|
"mean_token_accuracy": 0.13072005808353424,
|
|
"num_tokens": 3464473.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.224080324172974,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.13627456203103067,
|
|
"num_tokens": 3473740.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.042808628082275,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.1403045043349266,
|
|
"num_tokens": 3482249.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.339179420471192,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 6.1273,
|
|
"mean_token_accuracy": 0.1341732420027256,
|
|
"num_tokens": 3490753.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.26419415473938,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.13692996352910997,
|
|
"num_tokens": 3499373.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.20645318031311,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 6.0476,
|
|
"mean_token_accuracy": 0.13018234223127365,
|
|
"num_tokens": 3508344.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.330630493164063,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 6.0069,
|
|
"mean_token_accuracy": 0.13502927049994468,
|
|
"num_tokens": 3517009.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.123447847366333,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.13788192793726922,
|
|
"num_tokens": 3525989.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.272771978378296,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 5.9269,
|
|
"mean_token_accuracy": 0.1317255400121212,
|
|
"num_tokens": 3533947.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.155836677551269,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 5.9925,
|
|
"mean_token_accuracy": 0.1387178160250187,
|
|
"num_tokens": 3541974.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.133522939682007,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.14313246235251426,
|
|
"num_tokens": 3550436.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.209865283966065,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.14274076968431473,
|
|
"num_tokens": 3558283.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.033965444564819,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.14578440189361572,
|
|
"num_tokens": 3566968.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.2075746059417725,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.13596091344952582,
|
|
"num_tokens": 3575580.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.221923780441284,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.13546983748674393,
|
|
"num_tokens": 3584389.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.1582318305969235,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.13753796219825745,
|
|
"num_tokens": 3593009.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.11220064163208,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 5.9179,
|
|
"mean_token_accuracy": 0.13649867624044418,
|
|
"num_tokens": 3601914.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.034575176239014,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 5.8876,
|
|
"mean_token_accuracy": 0.14072516635060311,
|
|
"num_tokens": 3609883.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.121336221694946,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 5.8222,
|
|
"mean_token_accuracy": 0.14431814327836037,
|
|
"num_tokens": 3618103.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.2555018901824955,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.13108571246266365,
|
|
"num_tokens": 3625861.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.118966913223266,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.13489673435688018,
|
|
"num_tokens": 3634498.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.024101257324219,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.13758305013179778,
|
|
"num_tokens": 3644186.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.0807852268219,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.13705984950065614,
|
|
"num_tokens": 3652831.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.256798458099365,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.14277086704969405,
|
|
"num_tokens": 3661230.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.076580953598023,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 5.9843,
|
|
"mean_token_accuracy": 0.13940260484814643,
|
|
"num_tokens": 3669250.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.178564977645874,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 5.9566,
|
|
"mean_token_accuracy": 0.13556850478053092,
|
|
"num_tokens": 3677568.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.145662260055542,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 5.9574,
|
|
"mean_token_accuracy": 0.1433981440961361,
|
|
"num_tokens": 3685488.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.112370824813842,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 5.9228,
|
|
"mean_token_accuracy": 0.1389925181865692,
|
|
"num_tokens": 3694357.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.203349447250366,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.1359809495508671,
|
|
"num_tokens": 3703173.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.132759428024292,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.1417309373617172,
|
|
"num_tokens": 3712070.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.10051646232605,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.14509744718670844,
|
|
"num_tokens": 3720245.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.081886148452758,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.13998848721385002,
|
|
"num_tokens": 3730064.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.055927038192749,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.1380058228969574,
|
|
"num_tokens": 3738741.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.19128189086914,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 5.973,
|
|
"mean_token_accuracy": 0.1361282914876938,
|
|
"num_tokens": 3747472.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.153685426712036,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.1330367848277092,
|
|
"num_tokens": 3756643.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.19166932106018,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.12960731536149978,
|
|
"num_tokens": 3765490.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.169116973876953,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 5.8612,
|
|
"mean_token_accuracy": 0.13973119109869003,
|
|
"num_tokens": 3773063.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.154691886901856,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 6.0261,
|
|
"mean_token_accuracy": 0.1344061642885208,
|
|
"num_tokens": 3781763.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.188900423049927,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.1358758971095085,
|
|
"num_tokens": 3790582.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.089183139801025,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.14113157913088797,
|
|
"num_tokens": 3798745.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.06810245513916,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 5.9187,
|
|
"mean_token_accuracy": 0.1380026899278164,
|
|
"num_tokens": 3806901.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.149272918701172,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.8776,
|
|
"mean_token_accuracy": 0.14875079840421676,
|
|
"num_tokens": 3815742.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.092239236831665,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 5.9658,
|
|
"mean_token_accuracy": 0.13768358528614044,
|
|
"num_tokens": 3824468.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.058383893966675,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 5.9261,
|
|
"mean_token_accuracy": 0.14319675862789155,
|
|
"num_tokens": 3832834.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.115259170532227,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.1424368679523468,
|
|
"num_tokens": 3841780.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.149002027511597,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.13416145145893096,
|
|
"num_tokens": 3849840.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.18777437210083,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 5.9945,
|
|
"mean_token_accuracy": 0.13655759170651435,
|
|
"num_tokens": 3858204.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.167106294631958,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 5.9472,
|
|
"mean_token_accuracy": 0.13820890188217164,
|
|
"num_tokens": 3866615.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.092865514755249,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.1438558429479599,
|
|
"num_tokens": 3876003.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.155641174316406,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.14134934842586516,
|
|
"num_tokens": 3884362.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.0395012378692625,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 5.8524,
|
|
"mean_token_accuracy": 0.14561742097139357,
|
|
"num_tokens": 3893177.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.08151388168335,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.9069,
|
|
"mean_token_accuracy": 0.14305766448378562,
|
|
"num_tokens": 3903006.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.071657657623291,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.7658,
|
|
"mean_token_accuracy": 0.14124478846788407,
|
|
"num_tokens": 3912256.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.0484153747558596,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.1354946233332157,
|
|
"num_tokens": 3921121.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.089042663574219,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.1439758561551571,
|
|
"num_tokens": 3929348.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.124771785736084,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.13560474514961243,
|
|
"num_tokens": 3938073.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.176717805862427,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 6.0357,
|
|
"mean_token_accuracy": 0.13639540523290633,
|
|
"num_tokens": 3946641.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.192051935195923,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.13934031128883362,
|
|
"num_tokens": 3954586.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.054885196685791,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 5.9597,
|
|
"mean_token_accuracy": 0.14134562537074088,
|
|
"num_tokens": 3963745.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.0358985424041744,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 5.7746,
|
|
"mean_token_accuracy": 0.14625951200723647,
|
|
"num_tokens": 3972452.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.034676504135132,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 5.8922,
|
|
"mean_token_accuracy": 0.14618094712495805,
|
|
"num_tokens": 3980770.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.117841482162476,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.1389491453766823,
|
|
"num_tokens": 3989545.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.102830028533935,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.8846,
|
|
"mean_token_accuracy": 0.1403166502714157,
|
|
"num_tokens": 3998034.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.014950513839722,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.1459874078631401,
|
|
"num_tokens": 4007110.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.135031366348267,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 5.9831,
|
|
"mean_token_accuracy": 0.1331685684621334,
|
|
"num_tokens": 4015930.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.003888893127441,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.14710479527711867,
|
|
"num_tokens": 4024510.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.005897569656372,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 5.8876,
|
|
"mean_token_accuracy": 0.14109528660774232,
|
|
"num_tokens": 4033714.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.209692478179932,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.1327739931643009,
|
|
"num_tokens": 4042376.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.037041902542114,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.14402748942375182,
|
|
"num_tokens": 4050521.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.196396255493164,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 6.01,
|
|
"mean_token_accuracy": 0.13692177534103395,
|
|
"num_tokens": 4059384.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.081640815734863,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.1395252026617527,
|
|
"num_tokens": 4067655.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.1328636646270756,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 5.8762,
|
|
"mean_token_accuracy": 0.14391948282718658,
|
|
"num_tokens": 4075828.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.070217180252075,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.14209648966789246,
|
|
"num_tokens": 4083796.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.027770709991455,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 5.9639,
|
|
"mean_token_accuracy": 0.14366325587034226,
|
|
"num_tokens": 4092981.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.0527486324310305,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 5.7937,
|
|
"mean_token_accuracy": 0.14437015652656554,
|
|
"num_tokens": 4101363.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.061078214645386,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.13865672498941423,
|
|
"num_tokens": 4110164.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.193390893936157,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.1382698208093643,
|
|
"num_tokens": 4119098.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.045206737518311,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.14405231848359107,
|
|
"num_tokens": 4127522.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.047341442108154,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.9272,
|
|
"mean_token_accuracy": 0.1469861164689064,
|
|
"num_tokens": 4136311.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.066590690612793,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 5.8304,
|
|
"mean_token_accuracy": 0.1474180541932583,
|
|
"num_tokens": 4145160.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.014827108383178,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.8197,
|
|
"mean_token_accuracy": 0.14966430738568307,
|
|
"num_tokens": 4153921.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.020003175735473,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.9001,
|
|
"mean_token_accuracy": 0.13874251693487166,
|
|
"num_tokens": 4162580.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.064752817153931,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.1460046499967575,
|
|
"num_tokens": 4170623.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.044636297225952,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.14949819520115853,
|
|
"num_tokens": 4178724.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.043307685852051,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 5.8736,
|
|
"mean_token_accuracy": 0.1448787271976471,
|
|
"num_tokens": 4187773.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.046842908859253,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.1425296075642109,
|
|
"num_tokens": 4196628.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.044779539108276,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.13880138099193573,
|
|
"num_tokens": 4205090.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.079436826705932,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.8185,
|
|
"mean_token_accuracy": 0.14609641581773758,
|
|
"num_tokens": 4212757.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.997606372833252,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.9013,
|
|
"mean_token_accuracy": 0.13931182399392128,
|
|
"num_tokens": 4221556.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.99919490814209,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.1436249643564224,
|
|
"num_tokens": 4231524.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.080678129196167,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.9193,
|
|
"mean_token_accuracy": 0.14638482481241227,
|
|
"num_tokens": 4240229.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.062763833999634,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.7908,
|
|
"mean_token_accuracy": 0.14704818427562713,
|
|
"num_tokens": 4248053.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.035331726074219,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.8422,
|
|
"mean_token_accuracy": 0.14500436931848526,
|
|
"num_tokens": 4256019.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.968196296691895,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.1476341411471367,
|
|
"num_tokens": 4263805.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.042609071731567,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.8832,
|
|
"mean_token_accuracy": 0.14107748866081238,
|
|
"num_tokens": 4272712.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.127231884002685,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.14344534873962403,
|
|
"num_tokens": 4281222.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.9839294910430905,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 5.9239,
|
|
"mean_token_accuracy": 0.13669644743204118,
|
|
"num_tokens": 4290558.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.183317375183106,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.13987561762332917,
|
|
"num_tokens": 4299684.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.019082832336426,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.14164622724056244,
|
|
"num_tokens": 4308938.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.95548644065857,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.1458887979388237,
|
|
"num_tokens": 4317646.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.9978094577789305,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.13895228877663612,
|
|
"num_tokens": 4326876.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.007184743881226,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.14383746013045312,
|
|
"num_tokens": 4335391.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.137946605682373,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.8362,
|
|
"mean_token_accuracy": 0.14361774623394014,
|
|
"num_tokens": 4343253.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.859136152267456,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.14489779770374298,
|
|
"num_tokens": 4352161.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.0031920909881595,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.1499246060848236,
|
|
"num_tokens": 4360414.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.0329090595245365,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.7595,
|
|
"mean_token_accuracy": 0.15170303583145142,
|
|
"num_tokens": 4369375.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.8901123046875,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.789,
|
|
"mean_token_accuracy": 0.1448018729686737,
|
|
"num_tokens": 4378638.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.047815895080566,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.1467505469918251,
|
|
"num_tokens": 4388262.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.0011697769165036,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.7862,
|
|
"mean_token_accuracy": 0.14499384984374047,
|
|
"num_tokens": 4396894.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.04869327545166,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.9252,
|
|
"mean_token_accuracy": 0.14205848649144173,
|
|
"num_tokens": 4405455.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.017027759552002,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.1469386860728264,
|
|
"num_tokens": 4414355.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.904364156723022,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.7141,
|
|
"mean_token_accuracy": 0.1543835937976837,
|
|
"num_tokens": 4422305.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.0292998313903805,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.8479,
|
|
"mean_token_accuracy": 0.1407075747847557,
|
|
"num_tokens": 4430813.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.011082410812378,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.8193,
|
|
"mean_token_accuracy": 0.1463027387857437,
|
|
"num_tokens": 4440229.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.949166488647461,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.14452947080135345,
|
|
"num_tokens": 4449417.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.0368249893188475,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.8755,
|
|
"mean_token_accuracy": 0.14237613081932068,
|
|
"num_tokens": 4457377.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.04552845954895,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.1423659287393093,
|
|
"num_tokens": 4466839.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.96616497039795,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.8135,
|
|
"mean_token_accuracy": 0.14745612293481827,
|
|
"num_tokens": 4476369.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.971952486038208,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.14230666756629945,
|
|
"num_tokens": 4485609.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.022813320159912,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.8464,
|
|
"mean_token_accuracy": 0.14304948300123216,
|
|
"num_tokens": 4494535.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.004377222061157,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.14025293588638305,
|
|
"num_tokens": 4503133.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.923559379577637,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.7086,
|
|
"mean_token_accuracy": 0.1545959234237671,
|
|
"num_tokens": 4511465.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.973448705673218,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.1495731770992279,
|
|
"num_tokens": 4520177.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.008311653137207,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 5.934,
|
|
"mean_token_accuracy": 0.14287928119301796,
|
|
"num_tokens": 4528370.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.135716485977173,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 5.9736,
|
|
"mean_token_accuracy": 0.13521070554852485,
|
|
"num_tokens": 4538258.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.009545373916626,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.14092498347163201,
|
|
"num_tokens": 4547300.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.087115001678467,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.13737687543034555,
|
|
"num_tokens": 4556877.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.95903000831604,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.15062909051775933,
|
|
"num_tokens": 4565999.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.973028469085693,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.8182,
|
|
"mean_token_accuracy": 0.14192517548799516,
|
|
"num_tokens": 4574027.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.941861963272094,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.8217,
|
|
"mean_token_accuracy": 0.1367108166217804,
|
|
"num_tokens": 4582402.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.983818292617798,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.1477700263261795,
|
|
"num_tokens": 4590381.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.012215900421142,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.8301,
|
|
"mean_token_accuracy": 0.14014950394630432,
|
|
"num_tokens": 4598910.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.1034973621368405,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.13985663801431655,
|
|
"num_tokens": 4607400.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.96677680015564,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.14142798110842705,
|
|
"num_tokens": 4616510.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.054764366149902,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.8317,
|
|
"mean_token_accuracy": 0.14837341755628586,
|
|
"num_tokens": 4624529.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.982214736938476,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.7662,
|
|
"mean_token_accuracy": 0.14475079774856567,
|
|
"num_tokens": 4632141.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.031361770629883,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.14176981151103973,
|
|
"num_tokens": 4640378.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.981580209732056,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.1444416418671608,
|
|
"num_tokens": 4649313.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.000965023040772,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 5.8336,
|
|
"mean_token_accuracy": 0.14503469914197922,
|
|
"num_tokens": 4658272.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.966818475723267,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.1511964574456215,
|
|
"num_tokens": 4665970.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.062405920028686,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.1380128502845764,
|
|
"num_tokens": 4675308.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.959730434417724,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.14492155313491822,
|
|
"num_tokens": 4684316.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.986378192901611,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.7096,
|
|
"mean_token_accuracy": 0.1470434159040451,
|
|
"num_tokens": 4693029.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.935003757476807,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 5.9259,
|
|
"mean_token_accuracy": 0.1361936129629612,
|
|
"num_tokens": 4702404.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.070126581192016,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.8719,
|
|
"mean_token_accuracy": 0.1365981914103031,
|
|
"num_tokens": 4711126.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.990424919128418,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.8809,
|
|
"mean_token_accuracy": 0.14911534413695335,
|
|
"num_tokens": 4719816.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.009741735458374,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.8253,
|
|
"mean_token_accuracy": 0.14253749400377275,
|
|
"num_tokens": 4728294.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.006847667694092,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.1469218373298645,
|
|
"num_tokens": 4736708.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.951018142700195,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.13391065895557402,
|
|
"num_tokens": 4744893.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.096749687194825,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.8831,
|
|
"mean_token_accuracy": 0.146332485973835,
|
|
"num_tokens": 4753246.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.942298698425293,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.14182316064834594,
|
|
"num_tokens": 4762229.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.863367128372192,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.14836178421974183,
|
|
"num_tokens": 4771315.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.856457233428955,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.15656755715608597,
|
|
"num_tokens": 4779848.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.063330602645874,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.9217,
|
|
"mean_token_accuracy": 0.13790412321686746,
|
|
"num_tokens": 4788939.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.016645288467407,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.146475438028574,
|
|
"num_tokens": 4797719.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.004975509643555,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.14507240653038025,
|
|
"num_tokens": 4805601.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.079917144775391,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.8329,
|
|
"mean_token_accuracy": 0.13957922384142876,
|
|
"num_tokens": 4814993.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.004630899429321,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.7945,
|
|
"mean_token_accuracy": 0.14447189047932624,
|
|
"num_tokens": 4824156.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.940205669403076,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.14048577919602395,
|
|
"num_tokens": 4833827.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.976140832901001,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.8214,
|
|
"mean_token_accuracy": 0.14300673305988312,
|
|
"num_tokens": 4842801.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.935723829269409,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.14900791123509408,
|
|
"num_tokens": 4850928.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.938062143325806,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.14658517614006997,
|
|
"num_tokens": 4859510.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.017436552047729,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.8329,
|
|
"mean_token_accuracy": 0.14880072325468063,
|
|
"num_tokens": 4868201.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.924137544631958,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.1540842115879059,
|
|
"num_tokens": 4876896.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.861286544799805,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.15085181072354317,
|
|
"num_tokens": 4885136.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.949110889434815,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.15433648526668547,
|
|
"num_tokens": 4893277.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.893832397460938,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.14084682166576384,
|
|
"num_tokens": 4901977.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.035731315612793,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.13519714698195456,
|
|
"num_tokens": 4910888.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.9839459419250485,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.873,
|
|
"mean_token_accuracy": 0.1393221788108349,
|
|
"num_tokens": 4920369.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.038845252990723,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.852,
|
|
"mean_token_accuracy": 0.1393017925322056,
|
|
"num_tokens": 4928799.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.034655618667602,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.7549,
|
|
"mean_token_accuracy": 0.1501436188817024,
|
|
"num_tokens": 4937194.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.931065654754638,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.14632293730974197,
|
|
"num_tokens": 4946174.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.936599540710449,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.7925,
|
|
"mean_token_accuracy": 0.13978436663746835,
|
|
"num_tokens": 4955376.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.937894487380982,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.7927,
|
|
"mean_token_accuracy": 0.15235631987452508,
|
|
"num_tokens": 4964138.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.9808601379394535,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.14401781558990479,
|
|
"num_tokens": 4973868.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.941016101837159,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.1464352160692215,
|
|
"num_tokens": 4982687.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.9928521633148195,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.1418926164507866,
|
|
"num_tokens": 4992072.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.967259168624878,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 5.7397,
|
|
"mean_token_accuracy": 0.15427607148885727,
|
|
"num_tokens": 5000551.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.983960723876953,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.9152,
|
|
"mean_token_accuracy": 0.14138678908348085,
|
|
"num_tokens": 5009292.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.977126598358154,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.7549,
|
|
"mean_token_accuracy": 0.1445073001086712,
|
|
"num_tokens": 5018407.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.952081108093262,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.1417175605893135,
|
|
"num_tokens": 5027353.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.0577531337738035,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.8279,
|
|
"mean_token_accuracy": 0.14191178530454635,
|
|
"num_tokens": 5036476.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.93521409034729,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.1461431086063385,
|
|
"num_tokens": 5045132.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.991693019866943,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.7998,
|
|
"mean_token_accuracy": 0.14501917809247972,
|
|
"num_tokens": 5053665.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.985103130340576,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.1550862744450569,
|
|
"num_tokens": 5062516.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.932449817657471,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.1438561961054802,
|
|
"num_tokens": 5071260.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.883814859390259,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.15051764249801636,
|
|
"num_tokens": 5079215.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.976101589202881,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.14436266273260118,
|
|
"num_tokens": 5088404.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.9055495262146,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.7343,
|
|
"mean_token_accuracy": 0.1516444243490696,
|
|
"num_tokens": 5096756.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.991645336151123,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.14260229244828224,
|
|
"num_tokens": 5106160.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.823283624649048,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.8332,
|
|
"mean_token_accuracy": 0.14509238600730895,
|
|
"num_tokens": 5114915.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.0273322582244875,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.7454,
|
|
"mean_token_accuracy": 0.1477459713816643,
|
|
"num_tokens": 5123249.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.918133068084717,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.1458730474114418,
|
|
"num_tokens": 5131906.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.9432145118713375,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.1492404267191887,
|
|
"num_tokens": 5140740.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.023179388046264,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.9131,
|
|
"mean_token_accuracy": 0.1447205662727356,
|
|
"num_tokens": 5149748.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.831229782104492,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.6358,
|
|
"mean_token_accuracy": 0.1557387501001358,
|
|
"num_tokens": 5158475.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.921968793869018,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.8501,
|
|
"mean_token_accuracy": 0.13665784075856208,
|
|
"num_tokens": 5166593.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.01880030632019,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.1443267844617367,
|
|
"num_tokens": 5175557.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.942876625061035,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.7114,
|
|
"mean_token_accuracy": 0.1499389424920082,
|
|
"num_tokens": 5184140.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.920814514160156,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.14361362606287004,
|
|
"num_tokens": 5192347.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.987712621688843,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.1525233119726181,
|
|
"num_tokens": 5201327.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.954172992706299,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.8512,
|
|
"mean_token_accuracy": 0.14315994083881378,
|
|
"num_tokens": 5209873.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.992607831954956,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.148164002597332,
|
|
"num_tokens": 5219176.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.708837842803603,
|
|
"eval_loss": 5.805070877075195,
|
|
"eval_mean_token_accuracy": 0.15528924172677824,
|
|
"eval_num_tokens": 5219176.0,
|
|
"eval_runtime": 21.7192,
|
|
"eval_samples_per_second": 1913.423,
|
|
"eval_steps_per_second": 239.189,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"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": 1052336906403840.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|